Vehicle control method, vehicle and storage medium

Abstract

The invention provides a vehicle control method, a vehicle and a storage medium, the method is applied to the technical field of intelligent cabins, and the method comprises the steps that environmental data in a vehicle cabin, allergic sign information of at least one passenger and sensitive object data are acquired; based on the environment data, calculating an allergy risk index of each passenger according to the allergy sign information and the sensitive object data of the at least one passenger; and target air quality parameters of the position where each passenger is located are determined according to the allergy risk index of each passenger, a target control instruction of the air conditioning system is generated according to the target air quality parameters of the position where each passenger is located, and the air conditioning system is controlled according to the target control instruction. Therefore, through environment-physiology collaborative perception and personalized risk assessment, the problem that dynamic and closed-loop active protection based on individual risks cannot be realized due to the lack of real-time collaborative perception capability for sensitization substances in a cabin and physiological states of passengers in the prior art is solved, and the effectiveness of allergy protection and the comfort level of the passengers are remarkably improved.

Description

Technical Field

[0001] This application relates to the field of smart cockpit technology, and more specifically, to vehicle control methods, vehicles, and storage media in the field of smart cockpit technology. Background Technology

[0002] With the rapid development of vehicle intelligence and consumer upgrading, drivers and passengers' requirements for the cabin environment have risen from basic temperature and humidity comfort to proactive concern for air quality and health and safety. According to medical reports, allergic diseases are highly prevalent among motor vehicle drivers and passengers, especially in certain seasons and regions. Allergic symptoms triggered by in-vehicle air pollutants (such as pollen, dust mites, and dry air) have become a significant factor affecting driving experience and road safety. Therefore, developing intelligent cabin systems capable of proactively identifying and controlling allergy risks has become an important research direction in the field of vehicle health technology.

[0003] Related technologies have evolved from basic passive filtering to early warning systems that combine user identity with external environmental data, and further to simple automatic interventions based on external risk identification (such as closing windows). However, this method still remains at the level of "external perception triggering preset actions," lacking the ability to coordinate real-time perception of allergens in the cabin and the physiological state of occupants. It cannot achieve dynamic, closed-loop active protection based on individual risks, which urgently needs to be addressed. Summary of the Invention

[0004] This application provides a vehicle control method, a vehicle, and a storage medium. This method solves the problem that related technologies lack the ability to perceive allergens in the cabin and the physiological state of occupants in real time through environmental-physiological collaborative perception and personalized risk assessment, and cannot achieve dynamic, closed-loop active protection based on individual risk. This significantly improves the effectiveness of allergy protection and occupant comfort.

[0005] In a first aspect, a vehicle control method is provided, comprising: acquiring environmental data within the vehicle cabin, allergy symptoms information and sensitization data of at least one occupant; calculating an allergy risk index for each occupant based on the environmental data and the allergy symptoms information and sensitization data of the at least one occupant; determining a target air quality parameter for the location of each occupant based on the allergy risk index of each occupant, generating a target control command for an air conditioning system based on the target air quality parameter for the location of each occupant, and controlling the air conditioning system according to the target control command.

[0006] The above technical solution firstly integrates data on allergens in the cabin, occupants' physiological characteristics, and the environment to achieve multi-dimensional collaborative perception of allergy risks, overcoming the limitations of relying solely on a single environmental indicator. Secondly, based on this fused data, a personalized dynamic allergy risk index is calculated for each occupant, upgrading risk assessment from a static threshold to a precise quantification tailored to each individual. Furthermore, the system sets customized target air quality parameters for each location based on the individual's risk index, achieving individualized protection standards. Finally, this personalized target drives the air conditioning system to generate and execute collaboratively optimized control commands, thereby transforming fixed-mode air conditioning into intelligent microenvironmental precision control centered on the real-time health needs of the occupants.

[0007] In conjunction with the first aspect, in some possible implementations, the step of calculating the allergy risk index for each passenger based on the environmental data, according to the allergy symptoms and sensitization data of the at least one passenger, includes: calculating the cumulative exposure of each passenger based on the sensitization data of the at least one passenger; calculating the physiological reaction intensity of each passenger based on the allergy symptoms and sensitization data of the at least one passenger; and correcting the cumulative exposure and physiological reaction intensity of each passenger based on the environmental data to obtain the allergy risk index for each passenger.

[0008] The above technical solution quantifies the individualized dose of allergens actually encountered by each occupant by analyzing sensitive substance data to calculate cumulative exposure, rather than relying on the average concentration across the entire cabin, thus making the risk assessment basis more accurate. By analyzing allergy signs and calculating the intensity of physiological reactions, subjective and vague bodily responses are transformed into objective and quantifiable indicators, enabling the direct capture of allergy physiological signals. Environmental data is introduced to dynamically correct the cumulative exposure and physiological reaction intensity, quantifying the amplifying or inhibiting effect of environmental factors (such as dry air exacerbating irritation) on allergy risk. Finally, by integrating individualized exposure doses, objective physiological reactions, and environmental coupling effects, the system generates a scientific, dynamic, and highly personalized allergy risk index. This represents a qualitative leap in risk assessment, moving from simple threshold judgments to multi-source data fusion modeling, fundamentally improving the targeting and scientific rigor of the protection system.

[0009] In conjunction with the first aspect and the above implementation methods, in some possible implementation methods, the step of calculating the cumulative exposure of each occupant based on the sensitive substance data of the at least one occupant includes: obtaining the identity information of each occupant and the exposure duration of each occupant in the vehicle cabin; determining the allergen information of each occupant based on the identity information of each occupant; and calculating the cumulative exposure of each occupant based on the exposure duration of each occupant in the vehicle cabin, the allergen information, and the sensitive substance data.

[0010] Through the aforementioned technical solution, by acquiring occupant identity information, pre-stored personal allergen profiles can be accurately accessed to identify the specific allergens posing a risk, enabling precise targeting from a "general allergy population" to a "specific allergy individual." Secondly, by combining the occupant's actual exposure time within the cabin, the system dynamically tracks the duration of their exposure to specific allergen concentrations, closely linking exposure calculations to the individual's actual activity trajectory. Finally, by integrating personal allergen information, real-time monitored allergen data, and precise exposure duration, the system can calculate a highly personalized cumulative exposure. This ensures that the exposure amount used in allergy risk assessment truly corresponds to the individual occupant, rather than a general environmental average, thus ensuring that all subsequent risk assessments and protective decisions are based on solid individualized facts, enhancing the accuracy, specificity, and credibility of the entire protection chain.

[0011] In combination with the first aspect and the above implementation methods, in some possible implementation methods, the step of calculating the physiological response intensity of each passenger based on the allergic sign information of the at least one passenger includes: determining the actual sign feature vector of the at least one passenger based on the allergic sign information of the at least one passenger; and obtaining the physiological response intensity of each passenger based on the actual sign feature vector of each passenger and a preset physiological sign baseline vector.

[0012] Through the aforementioned technical solution, the system can process real-time allergy symptoms (such as infrared thermal imaging data) of occupants into actual characteristic vectors, transforming complex physiological signals into a set of measurable digital features. Secondly, by calculating the statistical deviation between this vector and the occupant's individual physiological baseline vector (representing their healthy, calm state), the system can objectively and quantitatively assess the degree of abnormality in their physiological state. This process transforms subjective or vague symptoms such as sneezing and facial flushing into clear, comparable intensity values, enabling the system to focus on identifying specific physiological changes triggered by allergies. This provides a direct, reliable, and highly personalized physiological response basis for allergy risk assessment, significantly improving the system's sensitivity and accuracy in detecting early allergy symptoms.

[0013] In combination with the first aspect and the above-described implementation methods, in some possible implementation methods, the step of obtaining the allergy risk index of each passenger by correcting the cumulative exposure dose and physiological response intensity of each passenger based on the environmental data includes: determining an environmental modulation coefficient based on the environmental data; fusing the exposure dose and physiological response intensity of each passenger to obtain an initial allergy risk index of each passenger; and obtaining the allergy risk index of each passenger based on the initial allergy risk index and the environmental modulation coefficient.

[0014] The above technical solution quantifies the potential aggravating or alleviating effect of the current environment on allergic reactions by calculating an environmental modulation coefficient based on environmental data. The previously calculated individualized cumulative exposure is initially integrated with the intensity of the physiological response to obtain an initial allergy risk index reflecting the exposure-response relationship. Finally, the environmental modulation coefficient is introduced to dynamically correct this initial index, thereby generating a more realistic current allergy risk index. Therefore, allergy risk assessment not only considers the direct effects of sensitizers on the body but also incorporates the environment as a key regulatory variable, ensuring that the risk index can dynamically adjust with environmental changes (such as dry winters and humid summers). This greatly improves the environmental adaptability and medical rationality of the allergy risk model, making the protective decisions made by the system more accurate and robust.

[0015] In combination with the first aspect and the above implementation methods, in some possible implementation methods, the step of generating the target control command of the air conditioning system based on the target air quality parameters of the location of each occupant includes: determining the air outlet adjustment range of the location of each occupant; obtaining the current air quality parameters of the location of each occupant; and generating the target control command of the air conditioning system based on the current air quality parameters, the target air quality parameters, and the air outlet adjustment range of the location of each occupant.

[0016] The above technical solution translates control intentions into executable actions by clearly defining the air vents and hardware adjustment ranges (such as maximum / minimum airflow and airflow angle) corresponding to each occupant's location. Secondly, it acquires the current air quality parameters at that location to understand the environmental status. Finally, by comprehensively considering three key dimensions—"what is the current situation," "what is the goal," and "what can the hardware do"—the final control command is generated. Thus, the system no longer issues commands based on idealized models, but rather seeks the optimal solution to meet personalized health needs while fully respecting the physical constraints of the air conditioning system. This fundamentally avoids control failures or reduced effectiveness caused by commands exceeding hardware capabilities, reliably combining personalized health goals with actual engineering conditions, and ensuring the effectiveness, stability, and engineering feasibility of the entire intelligent protection system chain, from algorithmic decision-making to physical execution.

[0017] In conjunction with the first aspect and the above implementation methods, in some possible implementation methods, the step of generating the target control command of the air conditioning system based on the current air quality parameters, target air quality parameters, and air outlet adjustment range of each occupant's location includes: calculating the air quality deviation value of each occupant's location based on the current air quality parameters and target air quality parameters; taking minimizing the air quality deviation value of all occupant locations as the global optimization objective, determining the air volume-velocity distribution strategy of the air outlet at each occupant's location based on the air outlet adjustment range of each occupant's location; and generating the target control command of the air conditioning system based on the air volume-velocity distribution strategy of the air outlet at each occupant's location.

[0018] By calculating the air quality deviation value for each occupant's location using the aforementioned technical solution, the gap between personalized health needs (target parameters) and the current environment (current parameters) can be precisely quantified. This problem is structured as a multi-objective optimization task, with the global optimization objective being to minimize the sum of air quality deviation values ​​for all occupants. Guided by this objective, the system simultaneously considers the physical constraint of the hardware adjustment range of all air outlets. An optimization algorithm is used to solve for the globally optimal airflow-velocity distribution strategy, and based on this strategy, coordinated system-level control commands are generated. Thus, the system no longer adjusts airflow independently and potentially conflictingly for each area. Instead, it seeks a collaborative control scheme that maximizes the overall satisfaction of all occupants (minimizes overall deviation) while satisfying all hardware constraints. This solves the control challenge in multi-occupant scenarios where different occupants may have different or even conflicting health needs, achieving intelligent, fair, and efficient allocation of protective resources (such as clean air). This maximizes the overall protective effectiveness and occupant experience in complex real-world scenarios.

[0019] In conjunction with the first aspect and the above-described implementation methods, in some possible implementation methods, after controlling the air conditioning system according to the target control command, the method further includes: monitoring the dynamic response of the sensitive object data of the at least one occupant within a preset time period, the dynamic response of the environmental data within the preset time period, and the dynamic response of the allergy symptoms information of the at least one occupant within the preset time period; determining a control index for the allergy risk index of each occupant based on the dynamic response; and updating the target air quality parameters of the location of each occupant according to the control index.

[0020] Through the aforementioned technical solution, by continuously monitoring the dynamic responses of allergen data, environmental data, and occupant allergy symptoms within a preset time period, the system can quantitatively analyze and calculate control indicators for each occupant's allergy risk index based on this multi-dimensional dynamic feedback data, thereby objectively assessing the effectiveness of the protection strategy. Finally, based on these assessment results, the system dynamically updates the personalized target air quality parameters for each occupant's location. Thus, the protection strategy can continuously adapt to changes in the individual reaction characteristics of occupants and the vehicle's operating environment, thereby continuously improving the accuracy and personalization of the protection.

[0021] Secondly, a vehicle control device is provided, the device comprising:

[0022] The acquisition module is used to acquire environmental data inside the vehicle cabin, allergy symptoms information of at least one occupant, and data on sensitized substances. The calculation module is used to calculate the allergy risk index of each passenger based on the environmental data, according to the allergy signs information and sensitization data of at least one passenger; The generation module is used to determine the target air quality parameters of each occupant's location based on the allergy risk index of each occupant, generate target control instructions for the air conditioning system based on the target air quality parameters of each occupant's location, and control the air conditioning system according to the target control instructions.

[0023] In conjunction with the second aspect, in some possible implementations, the computing module includes: The first calculation unit is used to calculate the cumulative exposure of each occupant based on the sensitive material data of the at least one occupant; The second calculation unit is used to calculate the intensity of the physiological reaction of each passenger based on the allergic signs information of the at least one passenger. The unit is used to obtain an allergy risk index for each occupant by correcting the cumulative exposure and physiological response intensity of each occupant based on the environmental data.

[0024] In combination with the second aspect and the above implementation methods, in some possible implementations, the first computing unit is specifically used for: Obtain the identity information of each occupant and the exposure time of each occupant in the vehicle cabin; The allergen information of each passenger is determined based on the identity information of each passenger; The cumulative exposure of each occupant is calculated based on the duration of exposure, allergen information, and sensitizer data within the vehicle cabin.

[0025] In combination with the second aspect and the above implementation methods, in some possible implementations, the second computing unit is specifically used for: Based on the allergy symptoms information of the at least one occupant, determine the actual vital sign feature vector of the at least one occupant; The physiological response intensity of each passenger is obtained based on the actual vital sign feature vector of each passenger and the preset physiological vital sign baseline vector.

[0026] In combination with the second aspect and the above implementation methods, in some possible implementations, the obtaining calculation unit is specifically used for: The process of adjusting the cumulative exposure and physiological response intensity of each occupant based on the environmental data to obtain an allergy risk index for each occupant includes: Based on the environmental data, determine the environmental modulation coefficient; The exposure dose and physiological response intensity of each passenger are combined to obtain the initial allergy risk index for each passenger. The allergy risk index of each passenger is obtained based on the initial allergy risk index of each passenger and the environmental modulation coefficient.

[0027] In combination with the second aspect and the above implementation methods, in some possible implementations, the generation module includes: A determining unit is used to determine the air outlet adjustment range at the location of each occupant; The acquisition unit is used to acquire the current air quality parameters of the location of each occupant; The generation unit is used to generate target control commands for the air conditioning system based on the current air quality parameters, target air quality parameters, and air outlet adjustment range of each occupant's location.

[0028] In combination with the second aspect and the above implementation methods, in some possible implementations, the generating unit is specifically used for: The air quality deviation value for each occupant's location is calculated based on the current air quality parameters and the target air quality parameters at each occupant's location; The global optimization objective is to minimize the air quality deviation at all occupant locations. Based on the air outlet adjustment range at each occupant location, the air volume-velocity distribution strategy for each occupant location is determined. The target control command for the air conditioning system is generated based on the air volume-speed distribution strategy of the air outlet at the location of each occupant.

[0029] In conjunction with the second aspect and the above implementation methods, in some possible implementation methods, after controlling the air conditioning system according to the target control command, the generation module is further configured to: The system monitors the dynamic response of the sensitized data of at least one occupant within a preset time period, the dynamic response of the environmental data within the preset time period, and the dynamic response of the allergic signs information of at least one occupant within the preset time period. Based on the dynamic response, control indicators for the allergy risk index of each passenger are determined. Based on the control indicators, update the target air quality parameters for the location of each occupant.

[0030] Thirdly, a vehicle is provided, including a controller, the controller including a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the vehicle control method described in the above embodiments.

[0031] Fourthly, a computer program product is provided, comprising: computer program code, which, when run on a computer, causes the computer to execute the vehicle control method in the first aspect or any possible implementation thereof.

[0032] Fifthly, a computer-readable storage medium is provided that stores computer program code, which, when executed on a computer, causes the computer to perform the vehicle control method of the first aspect or any possible implementation thereof. Attached Figure Description

[0033] Figure 1 A schematic flowchart illustrating the vehicle control method provided in an embodiment of this application; Figure 2 A block diagram of a vehicle control device provided in an embodiment of this application; Figure 3 This is a schematic diagram of the vehicle structure according to an embodiment of this application. Detailed Implementation

[0034] The technical solutions in this application will be clearly and thoroughly described below with reference to the accompanying drawings. In the description of the embodiments of this application, unless otherwise stated, " / " means "or," for example, A / B can mean A or B. "And / or" in the text is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Furthermore, in the description of the embodiments of this application, "multiple" refers to two or more than two.

[0035] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature.

[0036] Among related technologies, there are already solutions for personalized comfort adjustments based on occupant physical and mental states and cabin environment data. For example, by monitoring occupant physiological parameters (such as heart rate and body surface temperature), mood parameters (such as facial expressions), and in-vehicle environmental parameters (such as temperature, humidity, and noise), human thermal comfort and cabin comfort can be calculated, and the target environmental parameters preferred by the occupant can be derived in reverse. Then, the air conditioning, fragrance, music, and other cabin modules can be automatically adjusted to improve the overall driving and riding comfort experience.

[0037] However, the core objective of this method is to optimize subjective comfort. Its perception dimensions, computational models, and control logic all revolve around "comfort," without addressing the identification and protection against specific health risks (such as allergies). In other words, it lacks real-time monitoring of allergen concentrations (such as pollen and dust mites) within the cabin and fails to correlate with real-time allergy-specific physiological signs of occupants (such as abnormal facial heat zones and changes in breathing patterns). Therefore, it cannot quantify individualized allergy risks, let alone achieve precise, targeted proactive protection based on dynamic risks. Thus, the limitations of this technology mean that vehicle cabin systems remain in a passive response or are completely unresponsive to the increasingly prominent issue of allergies among drivers and passengers.

[0038] Based on the aforementioned problems, this application proposes a vehicle control method. By real-time collaborative sensing and fusion analysis of allergen concentration monitoring in the cabin, identification of occupant allergy-specific physiological signs, and macro-environmental data (such as temperature and humidity), the system can calculate the current allergy risk index for each occupant and set customized target air quality parameters (such as extremely low pollen concentration) for their location based on this index. This, in turn, drives the air conditioning system to execute globally optimized collaborative control commands (such as zoned air supply strategies, filter mode switching, and circulation path adjustment). Therefore, this application solves the problem of related technologies lacking real-time collaborative sensing capabilities of allergens in the cabin and the physiological state of occupants, thus failing to achieve dynamic, closed-loop active protection based on individual risk, significantly improving the effectiveness of allergy protection and occupant comfort.

[0039] The vehicle control method proposed in the embodiments of this application will be described in detail below.

[0040] Figure 1 This is a schematic flowchart of a vehicle control method provided in an embodiment of this application.

[0041] For example, such as Figure 1 As shown, the vehicle control method includes the following steps: In step S101, environmental data inside the vehicle cabin, allergy symptoms information of at least one occupant, and data on sensitized substances are acquired.

[0042] Understandably, environmental data refers to the macroscopic physicochemical conditions within the vehicle cabin that affect the occurrence and intensity of allergic reactions. These primarily include temperature, relative humidity, total volatile organic compound (TVOC) concentration, and carbon dioxide concentration. For example, low humidity can exacerbate dryness and irritation of the respiratory mucosa. Allergic signs refer to objective signals, captured by technologies such as infrared thermal imaging and millimeter-wave radar, characterizing the physiological allergic reactions occurring in occupants. These can include temperature changes in specific facial areas (such as the nose and around the eyes), abnormal respiratory rate / rhythm, and coughing / sneezing events. Sensitive substance data refers to information on specific biological particulate matter in the vehicle cabin air that can directly trigger allergies. This can be achieved through the identification and concentration monitoring of specific categories such as pollen, dust mite allergens, and mold spores using multimodal sensor arrays with optical feature recognition capabilities.

[0043] Specifically, the system can collect data synchronously through multiple sensors, which can not only know "what allergens are in the cabin (sensitive substance data)", but also "whether the current environment is likely to trigger allergies (environmental data)", and can even detect in real time "whether the occupants' bodies have already reacted (allergy signs information)".

[0044] For example, in one possible embodiment, the hardware architecture of a collaborative sensing system for intelligent allergy protection may include an environmental allergen multimodal sensor array module and a non-contact physiological state monitoring module. The environmental allergen multimodal sensor array module may integrate at least two sensing units, including a pollen / particulate matter sensing unit that uses optical scattering principles to output particle size distribution and identify pollen characteristics to form a "pollen probability" index, and a humidity / temperature / CO2 / VOC sensing unit for monitoring key environmental parameters such as relative humidity, temperature, CO2, and TVOC (Total Volatile Organic Compounds). Additionally, it may include a filter / duct status sensing unit for estimating filter capacity. All units of the environmental allergen multimodal sensor array module can synchronously output data via a unified timestamp to collaboratively determine external inputs, internal accumulation, and environmental risk amplification factors. The non-contact physiological state monitoring module is primarily based on an infrared thermal imaging unit. This unit can continuously image the occupant's face and upper respiratory tract area, extracting features such as nasal temperature changes, periorbital temperature changes, and respiratory heat flux fluctuations. It then utilizes face detection and keypoint tracking technology to achieve adaptive localization of the area of ​​interest, thereby capturing physiological signs related to allergic reactions (i.e., allergy symptoms) imperceptibly. Through the collaborative work of these two modules, a real-time, synchronous data foundation can be provided to the upper-level system, integrating environmental allergen status and occupant physiological responses.

[0045] In step S102, based on environmental data, the allergy risk index of each passenger is calculated according to the allergy signs information and sensitization data of at least one passenger.

[0046] Understandably, the allergy risk index is a comprehensive quantitative indicator used to characterize the probability and potential severity of an allergic reaction in a specific occupant under the current cabin environment. This allergy risk index is not a simple yes or no judgment, but rather a continuous numerical value or classification (such as low / medium / high), serving as a core basis for subsequent intelligent decision-making.

[0047] In other words, the system can use environmental data as a background correction factor, and at the same time, it can perform correlation analysis between allergy signs information reflecting the individual physiological state of the occupant and sensitive substance data indicating the presence of allergens. This generates a dynamic and personalized allergy risk index for each occupant, thus providing a direct decision-making basis for subsequent differentiated and precise protective control.

[0048] In step S103, the target air quality parameters for each passenger's location are determined based on the allergy risk index of each passenger, and a target control command for the air conditioning system is generated based on the target air quality parameters for each passenger's location. The air conditioning system is then controlled according to the target control command.

[0049] Understandably, the target air quality parameter refers to a specific air quality indicator that is dynamically set for each occupant's location based on their allergy risk index. This parameter can be characterized using pollen concentration (unit: grains / cubic meter). For example, for occupants at high risk of allergies, the target pollen concentration for their corresponding location may be set to an extremely low value (e.g., ≤5 grains / cubic meter), while for occupants at low risk of allergies, this value can be appropriately relaxed.

[0050] Specifically, after determining the allergy risk index of each occupant in the vehicle cabin, the system can customize target air quality parameters for each occupant's location based on their allergy risk index, thereby transforming abstract health risks into concrete and measurable environmental quality goals. Subsequently, the system can take a global optimization perspective, comprehensively considering the personalized goals (i.e., target air quality parameters) of all occupants, and generate a set of coordinated, efficient, and executable target control commands. Finally, the system can send the target control commands to the vehicle's air conditioning system, driving its actuators (such as fans, dampers, filter switching mechanisms, humidifiers, etc.) to make precise adjustments, thereby proactively changing the air distribution and quality in different areas of the cabin, aiming to create and maintain a cabin microenvironment that meets the current health needs of each occupant.

[0051] Thus, by integrating data on allergens in the cabin, occupants' physiological characteristics, and the environment, a multi-dimensional collaborative perception of allergy risks is achieved, overcoming the limitations of relying solely on a single environmental indicator. By calculating a personalized dynamic allergy risk index for each occupant based on this fused data, risk assessment is upgraded from a static threshold to a precise quantification tailored to each individual. Furthermore, the system sets customized target air quality parameters for each location based on the individual's risk index, achieving individualized protection standards. Finally, this personalized target drives the air conditioning system to generate and execute collaboratively optimized control commands, thereby transforming fixed-mode air conditioning into intelligent microenvironmental precision control centered on the real-time health needs of the occupants.

[0052] As one possible approach, in some embodiments, an allergy risk index for each passenger is calculated based on environmental data, using information on allergic signs and sensitized substances from at least one passenger. This includes: calculating the cumulative exposure of each passenger based on sensitized substance data from at least one passenger; calculating the intensity of the physiological reaction of each passenger based on information on allergic signs from at least one passenger; and adjusting the cumulative exposure and intensity of the physiological reaction for each passenger based on environmental data to obtain the allergy risk index for each passenger.

[0053] As is understandable, cumulative exposure is a quantitative indicator for a specific passenger, representing the total "dose" of a particular allergen (such as pollen) that the passenger is exposed to over a period of time, used to more scientifically assess chronic or cumulative risk. Physiological response intensity is also a quantitative indicator, used to objectively measure the degree of an passenger's immediate response to an allergen. It is derived by feature extraction and calculation of allergy signs (such as changes in facial thermal imaging), converting subjective feelings into comparable numerical values.

[0054] Specifically, the system first separates and calculates the cumulative exposure of each occupant from sensitizer data, shifting the focus of allergy risk assessment from environmental concentration to individual dose. Simultaneously, the system can analyze the intensity of the physiological response of the corresponding occupant from allergy symptoms, thus achieving an objective measurement of the body's actual response signals. Subsequently, the system can incorporate environmental data as a "modulator" to dynamically adjust the calculated cumulative exposure and physiological response intensity (for example, in low humidity environments, the same exposure may lead to a stronger physiological response, thereby increasing the risk value). Finally, by comprehensively adjusting the exposure and response intensity, a more scientific and realistic allergy risk index is generated that better reflects each occupant's individual situation. In other words, the system comprehensively assesses three dimensions: whether the current cabin environment is conducive to allergic reactions, whether the occupant's body has already reacted, and the level of sensitizer exposure, ultimately generating a dynamic and personalized allergy risk index for each occupant.

[0055] Therefore, by analyzing sensitive substance data to calculate cumulative exposure, the individualized dose of the sensitizer actually encountered by each occupant was quantified, rather than relying on the average concentration across the entire cabin, making the risk assessment basis more accurate. By analyzing allergy signs and calculating the intensity of physiological reactions, subjective and vague bodily reactions were transformed into objective and quantifiable indicators, enabling the direct capture of allergic physiological signals. By introducing environmental data to dynamically correct the aforementioned cumulative exposure and physiological reaction intensity, the amplification or inhibition effect of environmental factors (such as dry air exacerbating irritation) on allergy risk was quantified. Finally, by integrating individualized exposure doses, objective physiological reactions, and environmental coupling effects, the system generated a scientific, dynamic, and highly personalized allergy risk index. This represents a qualitative leap in risk assessment, moving from simple threshold judgments to multi-source data fusion modeling, fundamentally improving the targeting and scientific rigor of the protection system.

[0056] As one possible approach, in some embodiments, the cumulative exposure of each occupant is calculated based on the sensitive substance data of at least one occupant, including: obtaining the identity information of each occupant and the exposure duration of each occupant in the vehicle cabin; determining the allergen information of each occupant based on the identity information of each occupant; and calculating the cumulative exposure of each occupant based on the exposure duration of each occupant in the vehicle cabin, the allergen information, and the sensitive substance data.

[0057] Understandably, allergen information is pre-stored health data linked to a specific passenger's identity, which clearly lists which specific substances (such as birch pollen, dust mites, and mold) the passenger is known to be allergic to.

[0058] Specifically, in calculating the cumulative exposure of occupants, the system first uses in-vehicle cameras for facial recognition, or detects signals from smart devices (such as mobile phones or car keys) linked to the occupant, or identifies preset seat positions to automatically and seamlessly obtain the occupant's identity information. Based on this, it retrieves the occupant's personal allergen information, thereby identifying the types of allergens that need to be focused on in this allergy risk assessment (for example, for an occupant allergic only to pollen A, the system will ignore pollen B data). Simultaneously, the system can track the occupant's exposure time in the vehicle cabin (i.e., the cumulative time spent in the cabin from when the system identifies the occupant entering the vehicle until the current moment), clarifying the cumulative time spent in the monitored environment. Finally, by combining the individual's list of sensitive substances (i.e., allergen information), the concentration of sensitive substances they are exposed to in real time (i.e., sensitive substance data), and the duration of exposure (i.e., exposure time), the system calculates the cumulative exposure amount that is only meaningful to that occupant.

[0059] For example, suppose passenger Mr. Li (ID: User_A) has a personal allergen profile showing that he is allergic to birch pollen. At 9:00 a.m., Mr. Li drives to work. The system confirms his identity through facial recognition, and the vehicle's pollen sensor monitors the concentration of birch pollen in the cabin (unit: grains / cubic meter).

[0060] During this period, the system can record the concentration of birch pollen inside the cabin at fixed time intervals (e.g., 1 minute). Assuming a trip from 9:00 to 9:30, taking three time points as examples, as shown in Table 1: Table 1

[0061] It should be noted that the cumulative exposure is not the instantaneous concentration, but rather the integral of concentration over time. Based on Table 1, the approximate dose of the sensitizing substance inhaled by Mr. Li during each time period was calculated, i.e., time period 1 (9:00-9:10): average concentration ≈ (100+300) / 2 = 200 (particles / m³). 3Exposure duration = 10 min, dose increment during this period = average concentration × exposure duration = 200 × 10 = 2000 (particles·min / m²) 3 Time period 2 (9:10-9:20): Average concentration ≈ (300+50) / 2 = 175 (particles / m³) 3 Exposure duration = 10 min, dose increment during this period = average concentration × exposure duration = 175 × 10 = 1750 (particles·min / m²) 3 Time period 3 (9:20-9:30): Average concentration ≈ (50+150) / 2=100 (particles / m³) 3 Exposure duration = 10 min, dose increment during this period = average concentration × exposure duration = 100 × 10 = 1000 (particles·min / m²) 3 ).

[0062] The cumulative dose increments at each time point throughout the entire trip represent Mr. Li's total exposure to birch pollen during this trip. Therefore, the cumulative exposure is calculated as: 2000 + 1750 + 1000 = 4750 (particles per minute). 3 This value can scientifically reflect the total allergen load that Mr. Li's respiratory tract actually faced during these 30 minutes.

[0063] Therefore, by acquiring occupant identification information, the system can accurately access pre-stored personal allergen profiles to identify the specific allergens posing a risk, enabling precise targeting from the "general allergy population" to the "specific allergy-prone individual." Secondly, by combining the occupant's actual exposure time within the cabin, the system dynamically tracks the duration of their exposure to specific allergen concentrations, closely linking exposure calculations to the individual's actual activity trajectory. Finally, by integrating personal allergen information, real-time monitored allergen data, and precise exposure duration, the system can calculate a highly personalized cumulative exposure. This ensures that the exposure amount used in allergy risk assessment truly corresponds to the individual occupant, rather than a general environmental average, thus ensuring that all subsequent risk assessments and protective decisions are based on solid individualized facts, enhancing the accuracy, specificity, and credibility of the entire protection chain.

[0064] As one possible implementation method, in some embodiments, the physiological response intensity of each passenger is calculated based on the allergic sign information of at least one passenger, including: determining the actual sign feature vector of at least one passenger based on the allergic sign information of at least one passenger; and obtaining the physiological response intensity of each passenger based on the actual sign feature vector of each passenger and a preset physiological sign baseline vector.

[0065] Understandably, the actual physiological characteristic vector refers to a set of values ​​constructed by arranging multiple key physiological characteristics (such as nasal tip temperature, temperature difference between the left and right eyelids, respiratory rate, etc.) extracted from the occupant's current allergy symptoms in a specific order. The preset physiological characteristic baseline vector refers to a typical physiological characteristic vector representing each occupant in a healthy, calm, and allergy-free state, which serves as a "personal normal value" reference benchmark for assessing physiological changes.

[0066] Specifically, in calculating the intensity of an occupant's physiological response, the system first processes real-time allergy symptoms (such as facial thermograms) into digitized vectors representing actual physiological characteristics. Simultaneously, it calls upon a pre-learned baseline vector representing the occupant's normal health (e.g., Mr. Li's nasal temperature is 36.5℃ and his breathing is stable when calm). Then, by calculating the deviation between these two vectors (e.g., calculating the difference between the current nasal temperature and the baseline nasal temperature, and combining this with other features for comprehensive evaluation), the system obtains a specific numerical value characterizing the degree to which the occupant's current physiological state deviates from the normal range. This deviation value serves as the intensity of the physiological response.

[0067] For example, when passenger Mr. Li (ID: User_A) uses the system for the first time or is repeatedly in a low-allergy-risk environment within the cabin, the system can collect facial thermal image data using a facial infrared thermal imaging camera in a calm state, extract key features, and form Mr. Li's personal baseline vector (i.e., the preset physiological characteristic baseline vector). In this process, it is assumed that three key features are extracted and calculated from the facial thermal image data: the average temperature of the nasal tip region (T_nose), the average temperature difference between the left and right eye regions (ΔT_eyes), and the frequency of thermal fluctuations in the nostril region caused by respiration (F_breath). After a period of statistical learning, the system establishes a baseline vector A and its fluctuation range (standard deviation) for Mr. Li, namely: the preset physiological characteristic baseline vector A = [T_nose_base = 36.2℃, ΔT_eyes_base = 0.3℃, F_breath_base = 0.25Hz], and the standard deviation vector = [0.2℃, 0.1℃, 0.02Hz].

[0068] During a drive, the system detected that Mr. Li was sneezing. The system processed the current facial thermal image in real time and extracted the same three features, which yielded the following: Actual feature vector X = [T_nose_now = 36.8℃, ΔT_eyes_now = 1.1℃, F_breath_now = 0.31Hz].

[0069] When calculating the deviation, in order to eliminate the influence of different characteristic units and inherent fluctuations, we can calculate how many standard deviations each characteristic value deviates from its baseline, i.e., Nasal temperature deviation: Z_T=(36.8-36.2) / 0.2=3.0 (nasal temperature is 3 standard deviations higher than normal, which is considered significantly abnormal); Ocular temperature difference deviation: Z_ΔT=(1.1-0.3) / 0.1=8.0 (the periocular temperature difference increases sharply and is abnormally significant); Respiratory rate deviation: Z_F=(0.31-0.25) / 0.02=3.0 (respiratory rate also increased significantly).

[0070] The three standardized deviations mentioned above are combined into a single intensity value using the sum of squares method, namely: Physiological response intensity S = Z - T 2 +Z_ΔT 2 +Z_F 2 =3.0 2 +8.0 2 +3.0 2 =82.

[0071] Therefore, by processing real-time allergy symptoms of occupants into actual characteristic vectors, complex physiological signals can be transformed into a set of measurable digital features. By calculating the statistical deviation between this vector and the occupant's individual physiological baseline vector, the system can objectively and quantitatively assess the degree of abnormality in their physiological state deviating from the normal range. This process transforms subjective or vague symptoms such as sneezing and facial flushing into clear and comparable intensity values, enabling the system to focus on identifying specific physiological changes triggered by allergies. This provides a direct, reliable, and highly personalized physiological response basis for allergy risk assessment, significantly improving the system's sensitivity and accuracy in detecting early allergy symptoms.

[0072] As one possible approach, in some embodiments, an allergy risk index for each occupant is obtained by adjusting the cumulative exposure dose and physiological response intensity of each occupant based on environmental data, including: determining an environmental modulation coefficient based on environmental data; fusing the exposure dose of each occupant and the physiological response intensity of at least one occupant to obtain an initial allergy risk index for each occupant; and obtaining an allergy risk index for each occupant based on the initial allergy risk index and the environmental modulation coefficient.

[0073] Understandably, the environmental modulation factor is a numerical factor (ranging from 0.5 to 2.0) determined by environmental data (primarily relative humidity and TVOC). This factor quantifies the amplifying or suppressing effect of the current environment on allergy risk. For example, dry air (low humidity) may correspond to an environmental modulation factor >1 (amplifying risk), while comfortable humidity may correspond to an environmental modulation factor ≈1 (no significant effect).

[0074] Specifically, in obtaining the allergy risk index of occupants based on their cumulative exposure and physiological response intensity, the system can first obtain a corresponding environmental modulation coefficient by looking up a table based on environmental data. Subsequently, the system can employ a linear weighted summation strategy (e.g., R = w1 × f(E) + w2 × g(S), where R is the initial allergy risk index, w1 and w2 are weighting coefficients (w1 + w2 = 1), f(E) is a standardized function of the cumulative exposure E, and g(S) is a standardized function of the physiological intensity S, because the units and numerical ranges of the cumulative exposure E and physiological intensity S may be completely different (e.g., E is thousands of particles per minute / m³). 3 S is a sum of squared deviations (sqrt(s)) of tens, which needs to be normalized to the same scale (e.g., 0-100 points). The individualized cumulative exposure and physiological response intensity are then combined into an initial allergy risk index. For example, if Mr. Li's standardized exposure f(E) = 70, standardized physiological response intensity g(S) = 30, w1 = 0.5, w2 = 0.5, then the initial allergy risk index = 0.5 × 70 + 0.5 × 30 = 50. Finally, the system can combine the initial index with the environmental modulation coefficients (e.g., multiplying the two) to obtain the occupant's allergy risk index.

[0075] In constructing the mapping table between environmental data and environmental modulation coefficients, key environmental modulation factors can be identified first from the environmental data. Based on medical knowledge, relative humidity and TVOC can be selected as the two most critical environmental modulation factors. Then, the system can preset an influence coefficient lookup table or piecewise function for each environmental modulation factor. For example, for the humidity influence coefficient (H_factor): relative humidity < 30%: H_factor = 1.5 (dry air, significantly amplifying allergy risk); 30% ≤ relative humidity ≤ 60%: H_factor = 1.0 (comfortable range, no significant impact); relative humidity > 60%: H_factor = 1.2 (humid air, slightly amplifying mold / dust mite risk). For the TVOC influence coefficient (V_factor), TVOC concentration < 0.5 mg / m³... 3 V_factor=1.0 (high-quality air, no effect); 0.5mg / m³ 3 ≤TVOC concentration<1.0mg / m³ 3 V_factor=1.1 (slight pollution, slightly amplified); TVOC concentration ≥1.0mg / m³ 3 V_factor = 1.3 (Heavy pollution, significantly amplified). The final environmental modulation coefficient can be obtained by combining the influence coefficients of two (or more) environmental modulation factors through multiplication or weighting. For example, the environmental modulation coefficient E_factor = H_factor × V_factor.

[0076] Assuming the current relative humidity is 25% and the TVOC concentration is 0.3 mg / m³ 3 By looking up the table, we can obtain the current humidity influence coefficient H_factor=1.5 and the TVOC influence coefficient V_factor=1.0. From this, we can calculate the environmental modulation coefficient E_factor=1.5, which means that the current dry environment makes the overall allergy risk assessed as 1.5 times that of the baseline.

[0077] Therefore, by calculating the environmental modulation coefficient based on environmental data, the potential aggravating or alleviating effect of the current environment on allergic reactions was quantified. The previously calculated individualized cumulative exposure was initially integrated with the intensity of the physiological response to obtain an initial allergy risk index reflecting the exposure-response relationship. Finally, the environmental modulation coefficient was introduced to dynamically correct this initial index, thereby generating a more realistic current allergy risk index. Thus, allergy risk assessment not only considers the direct effects of sensitizers on the body but also incorporates the environment as a key regulatory variable, ensuring that the risk index can dynamically adjust with environmental changes (such as dry winters and humid summers). This greatly improves the environmental adaptability and medical rationality of the allergy risk model, making the protective decisions made by the system more accurate and robust.

[0078] As one possible implementation, in some embodiments, a target control command for the air conditioning system is generated based on the target air quality parameters of each occupant's location, including: determining the air outlet adjustment range of each occupant's location; obtaining the current air quality parameters of each occupant's location; and generating the target control command for the air conditioning system based on the current air quality parameters, the target air quality parameters, and the air outlet adjustment range of each occupant's location.

[0079] Understandably, the air vent adjustment range refers to the inherent adjustable parameter limits of the air conditioning vents serving a specific occupant's area. These mainly include: the maximum and minimum output airflow, the range of vertical and horizontal airflow oscillation angles, and whether independent temperature control is supported. These are physical constraints that must be followed when generating any control commands. The current air quality parameter refers to the specific air quality value measured in real time by sensors at the occupant's location (or its nearest monitoring point), corresponding to the target air quality parameter index (e.g., pollen concentration, measured in grains per cubic meter). It reflects the current environmental status at that location.

[0080] Specifically, the system identifies the air vents serving each occupant's location and obtains the adjustment range of each vent to determine "what it can do." Simultaneously, the system acquires the current air quality parameters for each occupant's location and performs real-time calculations based on the question of "how to most effectively adjust the current air quality parameters (current state) to the target air quality parameters (ideal state) using existing hardware capabilities (i.e., the air vent adjustment range)," thereby obtaining the target control command for the air conditioning system.

[0081] Therefore, by clearly defining the air vents corresponding to each occupant's location and their hardware adjustment range (such as maximum / minimum airflow and airflow angle), the control intent is translated into executable actions. Secondly, by acquiring the current air quality parameters at that location, the current environmental status is understood. Finally, by comprehensively considering the three key dimensions of "what is the current situation," "what is the goal," and "what can the hardware do," the final control command is generated. Thus, the system no longer issues commands based on an idealized model, but seeks the optimal solution to meet personalized health needs while fully respecting the physical constraints of the air conditioning system. This fundamentally avoids control failures or reduced effectiveness caused by commands exceeding hardware capabilities, reliably combining personalized health goals with actual engineering conditions, and ensuring the effectiveness, stability, and engineering feasibility of the entire intelligent protection system chain, from algorithmic decision-making to physical execution.

[0082] In one possible implementation, in some embodiments, a target control command for the air conditioning system is generated based on the current air quality parameters, target air quality parameters, and air outlet adjustment range of each occupant's location. This includes: calculating the air quality deviation value for each occupant's location based on the current and target air quality parameters; minimizing the air quality deviation value for all occupant locations as a global optimization objective; determining the airflow-velocity distribution strategy for the air outlets at each occupant's location based on the air outlet adjustment range of each occupant's location; and generating the target control command for the air conditioning system based on the airflow-velocity distribution strategy for the air outlets at each occupant's location.

[0083] Understandably, the air quality deviation value refers to the absolute value (or squared difference) of the difference between the current air quality parameter at a certain occupant's location and its target air quality parameter. This value quantifies the degree to which the environmental quality at that location is substandard; the larger the deviation value, the greater the gap between the current situation and health requirements, and the higher the urgency for optimization and adjustment. The global optimization goal refers to the control system's pursuit of maximizing the overall satisfaction of all occupants in the entire cabin in a multi-person scenario, rather than just satisfying the needs of a single occupant. The airflow-velocity distribution strategy can specify the airflow volume, velocity, and direction that each air outlet should output, aiming to systematically achieve the aforementioned global optimization goal.

[0084] Specifically, in generating target control commands, the system first calculates the air quality deviation for each occupant's location based on the current and target air quality parameters. Then, the system constructs this problem as a multi-objective optimization problem: the objective function is to minimize the weighted sum or squared sum of all deviations, with constraints on the hardware adjustment range of each air outlet (i.e., the air outlet adjustment range). Optimization algorithms (such as linear programming or quadratic programming) are solved within this framework to find an optimal airflow-velocity setpoint for each air outlet, a solution that minimizes the deviation of all occupant positions simultaneously to the greatest extent possible. Finally, the system converts this optimal solution into specific target control commands and issues them to each actuator.

[0085] It should be noted that the process of generating the optimal airflow-velocity distribution strategy (i.e., target control command) can be integrated into an adaptive closed-loop control module. This module can take the real-time calculated allergy risk index (allergy risk level) and the current cabin environment status (environmental data) as inputs to coordinate and regulate at least three key execution objects, and is not limited to air supply control: (1) Air conditioning filter mode control, the system can automatically activate high-efficiency filtration or enhanced purification mode (such as switching to a high-level filter channel or activating the ion purification unit) when the allergy risk index increases, and dynamically adjust the airflow according to the filter pressure difference and lifespan prediction to balance purification efficiency and operating noise; (2) Humidification intensity control, the system can intelligently determine the coupling relationship between cabin relative humidity and allergy risk. When the relative humidity is low and there is an allergy risk, the system automatically humidifies to a comfortable range to relieve respiratory irritation. When the humidity is too high and microorganisms may grow, the system inhibits humidification and starts ventilation or dehumidification to achieve a dynamic balance between humidity and microbial risk. (3) Air circulation path control: The system can intelligently adjust the internal / external circulation ratio and air duct distribution according to the concentration of internal and external allergens. That is, when the external allergens are high, the internal circulation is prioritized and the filtration is strengthened. When the accumulated pollution in the cabin is high, the external circulation is increased. The system can also combine the seat distribution and individual risk level to implement a zoned air supply and return strategy to prioritize the cleanliness and renewal of air in high-risk passenger areas.

[0086] The entire control strategy can be generated using a closed-loop and hierarchical architecture: the upper layer selects a preset strategy level based on the allergy risk index (which includes the optimal airflow-speed distribution strategy obtained through optimization above), and the lower layer can accurately track specific indicators such as humidity targets and particulate matter concentration reduction rates through algorithms such as PID or model predictive control, while strictly balancing comfort constraints (such as noise and temperature fluctuations), safety priorities (such as defrosting and defogging), energy consumption limits, and the priority of user manual operation throughout the process.

[0087] For example, suppose there are two occupants in the vehicle, occupant A is the driver, and the target air quality parameter (pollen concentration) is 10 grains / m³. 3 The current air quality parameter (pollen concentration) is 50 grains / m³. 3 The air quality deviation value is 40; passenger B is the passenger on the right rear, and their target air quality parameter (pollen concentration) is 30 grains / m³. 3 The current air quality parameter (pollen concentration) is 60 grains / m³. 3 The air quality deviation value is 30. Taking the air quality deviation values ​​for occupants A and B, and the airflow adjustment range (e.g., 0-100%) of air outlets 1 and 2 serving their locations as input, the algorithm can try various airflow combinations (e.g., air outlet 1 = 70%, air outlet 2 = 50%). Using a preset airflow field model, it predicts the pollen concentration changes at the locations of occupants A and B under each combination and calculates the new total deviation value. Suppose the algorithm finds that when the airflow of air outlet 1 (driver's side) is set to 80%, and the airflow of air outlet 2 (right rear side) is set to 60%, and the airflow direction of air outlet 2 is slightly adjusted towards occupant B, the predicted concentration at occupant A can drop to 15 (at which point the air quality deviation value is 25), and the concentration at occupant B can drop to 25 (at which point the air quality deviation value is 5), with the total deviation value decreasing from 70 to 30. This adjustment is the airflow-velocity distribution strategy. The system can then generate target control commands based on this strategy to coordinate the operation of the two air outlets according to this strategy.

[0088] It should be noted that the preset airflow field model is a computational or data model used to simulate, analyze, and predict the airflow state within the cabin and its interaction with pollutant transport processes. That is, before issuing actual control commands, simulations can be performed in this model to predict how the airflow within the cabin will change, how pollen will be carried away, and when the concentration in different areas will decrease after commands such as "adjusting the left-side airflow to 80%." During the vehicle design phase, extensive simulations of the vehicle cabin are conducted using professional CFD (Computational Fluid Dynamics) software to calculate typical flow fields under different air delivery modes, and these "flow field maps" are then embedded into the vehicle's infotainment system. For real-time computational efficiency, the onboard system can use a significantly simplified reduced-order model or a parametric model, which can quickly estimate the approximate flow field effect based on several key control commands (such as damper opening).

[0089] Therefore, by calculating the air quality deviation value for each occupant's location, the gap between personalized health needs (target parameters) and the current environment (current parameters) can be precisely quantified. This problem is structured as a multi-objective optimization task, with the global optimization objective being to minimize the sum of air quality deviation values ​​for all occupants. Guided by this objective, the system simultaneously considers the physical constraint of the hardware adjustment range of all air outlets. An optimization algorithm is used to solve for the globally optimal airflow-velocity distribution strategy, and based on this strategy, coordinated system-level control commands are generated. Thus, the system no longer adjusts airflow independently and potentially conflictingly for each area. Instead, it seeks a collaborative control scheme that maximizes the overall satisfaction of all occupants (minimizes overall deviation) while satisfying all hardware constraints. This solves the control challenge in multi-occupant scenarios where different occupants may have different or even conflicting health needs, achieving intelligent, fair, and efficient allocation of protective resources (such as clean air). This maximizes the overall protective effectiveness and occupant experience in complex real-world scenarios.

[0090] Optionally, in some embodiments, after controlling the air conditioning system according to the target control command, the method further includes: monitoring the dynamic response of sensitive object data of at least one occupant within a preset time period, the dynamic response of environmental data within a preset time period, and the dynamic response of allergy symptoms information of at least one occupant within a preset time period; determining a control index for the allergy risk index of each occupant based on the dynamic response; and updating the target air quality parameters of the location of each occupant according to the control index.

[0091] As can be understood, dynamic response refers to the trend or curve of relevant monitoring data changing over time within an observation window (such as the next 3-5 minutes) after the air conditioning system executes the target control command. For example, "dynamic response of sensitive data" can refer to the entire process of pollen concentration decreasing from its initial value to a stable value (the rate of decrease, the final concentration, etc.), rather than an isolated instantaneous value.

[0092] Specifically, after executing protective controls, the system does not end its work but enters an evaluation phase, continuously observing the dynamic response of the cabin environment and occupants over a subsequent period: Has the sensitizer been quickly eliminated? Have environmental conditions improved? Have the occupants' physiological signs tended to subside? Based on the analysis of these dynamic responses, the system can calculate an objective control index, thereby scientifically determining whether the protective strategy is "very effective," "moderately effective," or "basically ineffective."

[0093] It should be noted that the determination of monitoring and control indicators for dynamic responses can be systematically integrated into an intervention-learning closed loop, namely, a learning and individualized update module. Within this module's framework, the system's evaluation and optimization mechanisms are more in-depth. Specifically, at the effect evaluation level, the system can not only monitor the dynamic changes in sensitizer data, environmental data, and allergy symptoms, but also conduct multi-dimensional and comprehensive quantitative evaluations from the environmental side (quantifying the decrease in indices such as particulate matter and pollen and the convergence time to reach steady state), the physiological side (analyzing the frequency of sneezing / coughing events, whether the respiratory irregularity index has decreased, and the speed at which facial thermal features return to the individual baseline), and the system's overall performance (tracking the trajectory and stability of the allergy risk index). Based on this comprehensive evaluation data, the system can initiate an online, multi-level update mechanism. Finally, under the premise of meeting comfort and safety constraints, the system can autonomously learn and optimize control strategies by analyzing the actual marginal benefits of different control actions on allergy risk reduction.

[0094] Therefore, as one of the most direct outputs of this learning loop, the system can dynamically update the personalized target air quality parameters for each occupant based on the comprehensive evaluation and learning results (i.e., control indicators). For example, if the system discovers through long-term learning that an occupant is abnormally sensitive to a certain type of pollen, and even if the current control strategy has reduced the concentration at their location to the general target value, the occupant's physiological response is still slow to subside, then the system will automatically lower their future target air quality parameters based on their personal sensitivity model, setting stricter and more personalized protection standards for them.

[0095] Therefore, by continuously monitoring the dynamic responses of allergen data, environmental data, and occupant allergy symptoms within a preset time period, the system can quantitatively analyze and calculate the control indicators for each occupant's allergy risk index based on this multi-dimensional dynamic feedback data, thereby objectively assessing the effectiveness of the protection strategy. Finally, based on these assessment results, the system dynamically updates the personalized target air quality parameters for each occupant's location. Thus, the protection strategy can continuously adapt to changes in the individual reaction characteristics of occupants and the vehicle's operating environment, thereby continuously improving the accuracy and personalization of the protection.

[0096] Figure 2 This is a schematic diagram of the structure of a vehicle control device provided in an embodiment of this application.

[0097] For example, such as Figure 2 As shown, the vehicle control device 10 may include: an acquisition module 100, a calculation module 200, and a generation module 300.

[0098] Among them, the acquisition module 100 is used to acquire environmental data inside the vehicle cabin, allergy symptoms information of at least one occupant, and sensitive substance data; The calculation module 200 is used to calculate the allergy risk index of each passenger based on environmental data, the allergy signs information of at least one passenger, and the sensitive substance data. The generation module 300 is used to determine the target air quality parameters of each occupant's location based on the allergy risk index of each occupant, generate target control instructions for the air conditioning system based on the target air quality parameters of each occupant's location, and control the air conditioning system according to the target control instructions.

[0099] Optionally, in one embodiment of this application, the computing module 200 includes: The first calculation unit is used to calculate the cumulative exposure of each occupant based on the sensitive substance data of at least one occupant; The second calculation unit is used to calculate the intensity of each passenger's physiological response based on the allergic signs information of at least one passenger. The unit is used to obtain an allergy risk index for each occupant by adjusting the cumulative exposure and physiological response intensity based on environmental data.

[0100] Optionally, in one embodiment of this application, the first computing unit is specifically used for: Obtain the identity information of each occupant and the exposure time of each occupant in the vehicle cabin; Allergen information for each passenger was determined based on their identification information; The cumulative exposure of each occupant is calculated based on the duration of exposure in the vehicle cabin, allergen information, and sensitive substance data.

[0101] Optionally, in one embodiment of this application, the second computing unit is specifically used for: Based on the allergy symptoms information of at least one occupant, determine the actual symptom feature vector of at least one occupant; The physiological response intensity of each passenger is obtained based on the actual vital sign feature vector of each passenger and the preset physiological vital sign baseline vector.

[0102] Optionally, in one embodiment of this application, the computing unit is specifically used for: Based on environmental data, the cumulative exposure and physiological response intensity for each occupant were adjusted to obtain an allergy risk index for each occupant, including: Determine the environmental modulation coefficients based on environmental data; The initial allergy risk index for each passenger was obtained by combining the exposure dose and the intensity of the physiological response of each passenger. Based on each passenger's initial allergy risk index and environmental modulation coefficient, the current allergy risk index of each passenger is obtained.

[0103] Optionally, in one embodiment of this application, the generation module 300 includes: The determining unit is used to determine the air outlet adjustment range for each occupant's location; The acquisition unit is used to acquire the current air quality parameters of each occupant's location; The generation unit is used to generate target control commands for the air conditioning system based on the current air quality parameters, target air quality parameters, and air outlet adjustment range of each occupant's location.

[0104] Optionally, in one embodiment of this application, the generating unit is specifically used for: The air quality deviation value for each occupant's location is calculated based on the current air quality parameters and the target air quality parameters at each occupant's location; The global optimization objective is to minimize the air quality deviation at all occupant locations. The air volume-velocity distribution strategy for each occupant's location is determined based on the air outlet adjustment range at each occupant's location. The target control command for the air conditioning system is generated based on the air volume-speed distribution strategy of the air outlet at each occupant's location.

[0105] Optionally, in one embodiment of this application, after controlling the air conditioning system according to the target control command, the generation module 300 is further configured to: Monitor the dynamic response of at least one occupant's sensitized substance data, the dynamic response of environmental data, and the dynamic response of at least one occupant's allergic signs information within a preset time period; Based on dynamic response, control indicators for the allergy risk index of each passenger were determined. Based on the control indicators, update the target air quality parameters for each passenger's location.

[0106] In summary, the vehicle control device according to the embodiments of this application solves the problem that related technologies lack the ability to perceive allergens in the cabin and the physiological state of the occupants in real time through environmental-physiological collaborative perception and personalized risk assessment, and cannot achieve dynamic, closed-loop active protection based on individual risk, thus significantly improving the effectiveness of allergy protection and the comfort of the occupants.

[0107] Figure 3 This is a schematic diagram of the structure of a vehicle provided in an embodiment of this application.

[0108] It should be understood that the methods described above can be applied to... Figure 3 In the vehicle with the structure shown.

[0109] like Figure 3As shown, the vehicle includes a controller, which may include a memory 301 and a processor 302. The memory 301 stores executable program code, and the processor 302 is used to call and execute the executable program code to perform the vehicle control method provided in the embodiments of this application.

[0110] Furthermore, the controller also includes a communication interface 303 for communication between the memory 301 and the processor 302.

[0111] This embodiment can divide the vehicle into functional modules based on the above method example. For example, each module can correspond to a separate function module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0112] It should be noted that all relevant content of each step involved in the above method embodiments can be referenced from the functional description of the corresponding functional module, and will not be repeated here.

[0113] It should be understood that the vehicle provided in this embodiment is used to execute the vehicle control method described above, and therefore can achieve the same effect as the above implementation method.

[0114] This embodiment also provides a computer-readable storage medium storing computer program code. When the computer program code is run on a computer, the computer executes the above-described related method steps to implement a vehicle control method provided in the above embodiment.

[0115] This embodiment also provides a computer program product that, when run on a computer, causes the computer to perform the aforementioned related steps to implement a vehicle control method provided in the above embodiment.

[0116] In this embodiment, the vehicle, computer-readable storage medium, computer program product, or chip are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can be referred to the beneficial effects of the corresponding methods provided above, and will not be repeated here.

[0117] Through the above description of the embodiments, those skilled in the art will understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0118] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, 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 devices or units may be electrical, mechanical, or other forms.

[0119] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A vehicle control method, characterized in that, Includes the following steps: Acquire environmental data from inside the vehicle cabin, allergy symptoms and sensitization data of at least one occupant; Based on the environmental data, an allergy risk index is calculated for each passenger according to the allergy symptoms and allergen data of at least one passenger. The target air quality parameters for each passenger's location are determined based on the allergy risk index of each passenger, and a target control command for the air conditioning system is generated based on the target air quality parameters for each passenger's location. The air conditioning system is then controlled according to the target control command.

2. The method according to claim 1, characterized in that, The calculation of the allergy risk index for each passenger based on the environmental data, according to the allergy symptoms and allergen data of at least one passenger, includes: The cumulative exposure of each occupant is calculated based on the sensitive material data of at least one occupant; The intensity of each passenger's physiological response is calculated based on the allergic symptoms information of at least one passenger; Based on the environmental data, the cumulative exposure and physiological response intensity of each occupant are adjusted to obtain the allergy risk index for each occupant.

3. The method according to claim 2, characterized in that, The calculation of the cumulative exposure of each occupant based on the sensitive substance data of at least one occupant includes: Obtain the identity information of each occupant and the exposure time of each occupant in the vehicle cabin; The allergen information of each passenger is determined based on the identity information of each passenger; The cumulative exposure of each occupant is calculated based on the duration of exposure, allergen information, and sensitizer data within the vehicle cabin.

4. The method according to claim 2, characterized in that, The calculation of the physiological response intensity of each passenger based on the allergic reaction information of at least one passenger includes: Based on the allergy symptoms information of the at least one occupant, determine the actual vital sign feature vector of the at least one occupant; The physiological response intensity of each passenger is obtained based on the actual vital sign feature vector of each passenger and the preset physiological vital sign baseline vector.

5. The method according to claim 2, characterized in that, The process of adjusting the cumulative exposure and physiological response intensity of each occupant based on the environmental data to obtain an allergy risk index for each occupant includes: Based on the environmental data, determine the environmental modulation coefficient; The exposure dose and physiological response intensity of each passenger are combined to obtain the initial allergy risk index for each passenger. The allergy risk index of each passenger is obtained based on the initial allergy risk index of each passenger and the environmental modulation coefficient.

6. The method according to claim 1, characterized in that, The step of generating target control commands for the air conditioning system based on the target air quality parameters of each occupant's location includes: Determine the air vent adjustment range for each occupant's location; Obtain the current air quality parameters for the location of each occupant; The target control command for the air conditioning system is generated based on the current air quality parameters, target air quality parameters, and air outlet adjustment range of each occupant's location.

7. The method according to claim 6, characterized in that, The step of generating the target control command for the air conditioning system based on the current air quality parameters, target air quality parameters, and air outlet adjustment range of each occupant's location includes: The air quality deviation value for each occupant's location is calculated based on the current air quality parameters and the target air quality parameters at each occupant's location; The global optimization objective is to minimize the air quality deviation at all occupant locations. Based on the air outlet adjustment range at each occupant location, the air volume-velocity distribution strategy for each occupant location is determined. The target control command for the air conditioning system is generated based on the air volume-speed distribution strategy of the air outlet at the location of each occupant.

8. The method according to claim 7, characterized in that, After controlling the air conditioning system according to the target control command, the method further includes: The system monitors the dynamic response of the sensitized data of at least one occupant within a preset time period, the dynamic response of the environmental data within the preset time period, and the dynamic response of the allergic signs information of at least one occupant within the preset time period. Based on the dynamic response, control indicators for the allergy risk index of each passenger are determined. Based on the control indicators, update the target air quality parameters for the location of each occupant.

9. A vehicle comprising a controller, the controller including a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the program to implement the vehicle control 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 a computer program that, when executed, implements the vehicle control method as described in any one of claims 1-8.

Images