Personalized temperature control method, system and equipment based on user feedback and storage medium

Abstract

The invention provides a personalized temperature control method, system and device based on user feedback and a storage medium, and the method comprises the steps that a personalized compensation data array of a user is loaded, and the personalized compensation data array comprises an air blower gear and a target air outlet temperature compensation value; the working mode of the air conditioner and user operation are monitored in real time, and when the air conditioner is in a refrigerating or heating mode, adjustment of a user on gears and set temperature is continuously tracked; when effective adjustment is detected, a current air conditioner load demand characterization value is obtained, the change amount caused by user operation is calculated, a corresponding compensation value is calculated according to a preset learning rate, and the compensation value is updated to a compensation array of a corresponding user; the compensation value is subjected to confidence attenuation along with time, and correction is carried out in combination with user comfort evaluation; and in combination with the basic control curve and the personalized compensation value, the target air blower gear and the target air outlet temperature are calculated and output. According to the method, personalized calibration of the comfort of the vehicle air conditioner can be realized only according to daily operation behaviors of the user without massive data training.

Description

Technical Field

[0001] This invention relates to the field of temperature control, and more specifically, to personalized temperature control methods, systems, devices, and storage media based on user feedback. Background Technology

[0002] As vehicles become increasingly intelligent and connected, users' personalized demands for in-car comfort are becoming more prominent. As a key component affecting driving comfort, the vehicle's air conditioning system is evolving from a traditional "one-size-fits-all" approach towards intelligent and personalized control strategies. Due to individual differences in age, gender, physical condition, and clothing habits, different users have varying perceptions and preferences regarding air conditioning comfort parameters such as airflow and temperature in the same environment. Therefore, personalized air conditioning systems that can automatically learn and adapt to different user habits have become an important development direction for the next generation of intelligent cockpits.

[0003] Currently, most mainstream vehicle air conditioning automatic control strategies are based on the Thermodynamic Aspiration Objective (TAO) value. The TAO value is an intermediate-dimensional value calculated by integrating various heat load-related parameters such as the vehicle's internal and external ambient temperature, solar radiation, humidity, set temperature, blower status, and airflow mode. The TAO value range can be customized according to the project (e.g., 0~100 or 0~255), and its magnitude directly reflects the system's cooling or heating demand: the smaller the value, the stronger the cooling demand; the larger the value, the stronger the heating demand. The control system uses the real-time TAO value to look up the target blower speed and target airflow temperature through a pre-calibrated mapping table (curve), and then drives the actuators. This method provides basic automated comfort control, but it does not consider the personalized preferences of different users.

[0004] To achieve personalization, existing technologies have proposed several solutions. For example, some solutions utilize in-vehicle cameras (such as infrared thermal imaging cameras) to capture the facial or body surface temperature distribution of occupants, combining this with thermal comfort models or machine learning algorithms (such as backpropagation neural networks) to dynamically adjust air conditioning parameters. While these solutions can accurately sense the user's thermal state, they have significant limitations: First, they require additional, costly dedicated sensing hardware (such as infrared cameras), increasing the overall vehicle cost and hindering widespread adoption in mainstream models; second, neural network-based solutions typically require large amounts of training data to ensure model accuracy, placing high demands on the computing power, storage, and data collection costs of the onboard computing unit, making them difficult to deploy on resource-constrained low- to mid-range vehicle platforms.

[0005] Other solutions focus on recording users' historical operating habits. For example, by recording frequently set air conditioning parameters (such as set temperature and airflow) under different environmental conditions (such as ambient temperature range), the system prioritizes recommending those historical settings when similar environments recur. This method is relatively simple to implement, but to cover various possible combinations of environmental conditions, it requires recording and storing a large amount of "environment-operation" pairing data, and still requires a certain model (such as a probabilistic model or a simple classifier) ​​for processing and recommendation. Whether stored locally or potentially synchronized to the cloud, it will consume certain storage and computing resources. Moreover, this type of method passively relies on historical data and lacks the ability to learn and respond to individual user adjustments, making its adaptability relatively rigid.

[0006] Furthermore, whether based on biometric recognition or historical behavior records, user habits may shift with seasonal changes, changes in physical condition, or changes in subjective preferences. Most existing solutions lack effective "forgetting" mechanisms, and outdated or inaccurate preference data may continue to affect the system, causing the "personalized" services they provide to actually reduce the user experience.

[0007] In view of this, the present invention provides a personalized temperature control method, system, device and storage medium based on user feedback. Summary of the Invention

[0008] To address the problems in the prior art, the present invention aims to provide a personalized temperature control method, system, device, and storage medium based on user feedback. This overcomes the difficulties of the prior art and enables low-cost, adaptive, and forgettable personalized calibration of vehicle air conditioning comfort based solely on the user's daily operating behavior, without the need for complex sensors and model training.

[0009] Embodiments of the present invention provide a personalized temperature control method based on user feedback, comprising the following steps: S100. Identify the user identity of the currently driving vehicle, and load the corresponding personalized compensation data array from the local storage module according to the user identity. The personalized compensation data array includes at least a blower gear compensation value array and a target air outlet temperature compensation value array based on the vehicle air conditioning load demand characterization value. The blower gear compensation value is achieved by adjusting the blower gear, and the target air outlet temperature compensation value is achieved by adjusting the air conditioning set temperature. S200: Real-time monitoring of the vehicle's air conditioning system's operating mode and user operation behavior; when the air conditioning system is determined to be in cooling or heating mode, continuous monitoring of the user's adjustment of the blower speed and the user's adjustment of the air conditioning set temperature. S300. When a valid adjustment operation is detected by the user, the vehicle air conditioning load demand characterization value at the time of the adjustment operation is obtained; the blower speed change or air conditioning set temperature change caused by the adjustment operation is calculated; based on a predefined learning rate corresponding to the current air conditioning operating mode and the user's adjustment object, the blower speed compensation value or target air outlet temperature compensation value to be applied under the current vehicle air conditioning load demand characterization value is calculated; the learning rate defines the compensation offset of the vehicle air conditioning load demand characterization value corresponding to the user's unit operation change. S400. Update the calculated blower speed compensation value or target outlet air temperature compensation value to the personalized compensation data array corresponding to the current user identity, current air conditioning working mode and adjustment object, and store the updated array. S500: Apply confidence processing based on a time decay factor to the historical compensation values ​​stored in the personalized compensation data array, wherein the confidence decays over time; obtain the user's subjective evaluation coefficient of the air conditioning comfort in the current driving cycle, and correct the compensation value calculated in the current driving cycle based on the evaluation coefficient, and use the corrected compensation value to update the array; S600: Based on the current vehicle air conditioning load demand characteristic value, query the preset basic blower speed control curve and basic target air outlet temperature control curve to obtain the basic control value; based on the current vehicle air conditioning load demand characteristic value, query the corrected personalized compensation data array to obtain the personalized compensation value; combine the basic control value and the personalized compensation value to calculate the final target blower speed and target air outlet temperature, and send them to the actuator of the vehicle air conditioning system for control.

[0010] Preferably, step S300 includes: S301. In cooling mode, when the user lowers or raises the blower speed, the vehicle air conditioning load demand characterization value is TAO. Cool Let the blower speed difference be BlowerLevel. Cool (d) - BlowerLevel Cool (d-1), where (d-1) represents the blower speed before adjustment, and d is the blower speed after adjustment. The learning rate (LearnRate) is the rate at which the blower speed is adjusted in cooling mode. Cool The value range is [-1, 0], LearnRate Cool = (-1 / 100) × (TAO MAX - TAO MIN ) / (D MAX -D MIN ), among which, TAO MAXThis is the upper limit of the TAO value, TAO MIN D is the lower limit of the TAO value. MAX D is the upper limit of the blower speed. MIN This is the lower limit of the blower speed; S302, Calculate the blower speed compensation value TAOOffset in cooling mode. Cool = [BlowerLevel Cool (d)-BlowerLevel Cool [(d-1)]×LearnRate Cool and TAOOffset Cool Updated to TAO as blower gear compensation value. Cool The corresponding array position; S303. In heating mode, when the user lowers or raises the blower speed, the vehicle air conditioning load demand characterization value is TAO. Heat The learning rate (LearnRate) for adjusting the blower speed during heating. Heat The value range is [0, 1], and LearnRate Heat = (1 / 100) × (TAO MAX - TAO MIN ) / (D MAX -D MIN ); S304, Calculate the blower speed compensation value TAOOffset in heating mode. Heat = [BlowerLevel Heat (d)-BlowerLevel Heat [(d-1)]×LearnRate Heat and TAOOffset Heat Updated to TAO as blower gear compensation value. Heat The corresponding array position.

[0011] Preferably, step S300 further includes: When the user adjusts the set temperature, the vehicle air conditioning load demand characterization value is TAO. TempSet The temperature difference is set as TempSet(t) - TempSet(t-1), where (t-1) represents the set temperature before adjustment and t is the set temperature after adjustment. The learn rate (LearnRate) of the air conditioner when adjusting the temperature is set. TempSet The defined range is [0,1], LearnRate TempSet = (1 / 100) × (TAO MAX - TAOMIN (Set upper temperature limit - Set lower temperature limit) Calculate the target temperature compensation TempSet Offset = LearnRate TempSet × [TempSet(t) - TempSet(t-1)], and the target outlet air temperature compensation value TempSet Offset Updated to TAO as the target outlet air temperature compensation value. TempSet The corresponding array position.

[0012] Preferably, in step S300, the process of determining whether the user has performed a valid adjustment operation includes: anti-shake filtering processing, starting from the user's first adjustment action, ignoring all subsequent adjustment operations within a predetermined filtering time window, and only recording and using the blower speed value or air conditioner set temperature value that finally stabilizes at the end of the filtering time window as the state after the adjustment operation for compensation calculation.

[0013] Preferably, in step S500, applying confidence processing based on a time decay factor to the historical compensation values ​​stored in the personalized compensation data array, wherein the confidence decays over time, includes: associating a confidence coefficient Conf with each compensation value element in the personalized compensation data array, the confidence coefficient being updated according to an exponential decay law: Conf = exp(-λ × t), where λ is a configurable forgetting coefficient, and t is the time elapsed since the compensation value was recorded or last reinforced; when synthesizing personalized parameters, the historical compensation value retrieved from the array must first be multiplied by its current corresponding confidence coefficient Conf before use; In step S500, obtaining the user's subjective evaluation coefficient of the air conditioning comfort in the current driving cycle, and correcting the compensation value calculated in the current driving cycle based on the evaluation coefficient, and using the corrected compensation value to update the array, includes: obtaining the user's evaluation coefficient α of the current air conditioning comfort through the human-computer interaction interface at the end of the driving cycle or when the user actively triggers it, wherein the evaluation coefficient α has a value range of [0, 1]; multiplying all compensation values ​​calculated based on the user's operation in the current driving cycle by the evaluation coefficient α to obtain the corrected compensation value B. corrected = α×B raw B raw As the initial compensation value, the corrected compensation value B is then used. corrected Used to update the personalized compensation data array.

[0014] Preferably, step S500 further includes maintaining the trend consistency of the compensation value array. After updating the personalized compensation data array, the trend of the elements in the array changing with the TAO value is checked. The overall trend of the final control parameter after superimposing the compensation value changing with the TAO value is checked and ensured to meet expectations: the blower speed is not increasing in the cooling TAO range and not decreasing in the heating TAO range; the target air outlet temperature is not decreasing in the entire TAO range. If the array update causes the above trend to be destroyed, the compensation value array is smoothed or adjusted to restore a logical trend.

[0015] Preferably, in step S600, calculating the personalized compensation value includes: Ultimate goal: Blower gear B final = Basic blower speed TAOBase Level + Confidence coefficient Conf × Historical blower gear compensation value B Level + This blower speed compensation value (BlowerLevel) Offset ; Final target air outlet temperature T final = Base target outlet air temperature TAOBase TempSet + Confidence coefficient Conf × Historical target temperature compensation value B TempSet + Target temperature compensation value TempSet Offset ; Among them, the basic blower speed TAOBase Level and the baseline target outlet air temperature TAOBase TempSet The historical blower gear compensation value B is obtained by querying the preset basic control curve corresponding to the current TAO value. Level and historical target temperature compensation value B TempSet The personalized compensation data array processed by step S500 is obtained by querying the current blower gear compensation value and the current target temperature compensation value, which are the compensation values ​​to be stored in the array after evaluation and correction by step S500 in the current driving cycle.

[0016] Embodiments of the present invention also provide a personalized temperature control system based on user feedback, used to implement the above-described personalized temperature control method based on user feedback, wherein the personalized temperature control system based on user feedback includes: An array loading module identifies the user identity of the currently driving vehicle and loads the corresponding personalized compensation data array from the local storage module based on the user identity. The personalized compensation data array includes at least a blower gear compensation value array and a target air outlet temperature compensation value array based on the vehicle's air conditioning load demand characterization value. The blower gear compensation value is achieved by adjusting the blower gear, and the target air outlet temperature compensation value is achieved by adjusting the air conditioning set temperature. The operation monitoring module monitors the vehicle's air conditioning system's operating mode and user operation behavior in real time. When it is determined that the air conditioning system is in cooling or heating mode, it continuously monitors the user's adjustment of the blower speed and the user's adjustment of the air conditioning set temperature. A compensation module is established to acquire the vehicle air conditioning load demand characterization value at the moment the user performs a valid adjustment operation when the adjustment operation is detected; calculate the blower speed change or air conditioning set temperature change caused by the adjustment operation; and calculate the blower speed compensation value or target air outlet temperature compensation value to be applied under the current vehicle air conditioning load demand characterization value based on a predefined learning rate corresponding to the current air conditioning operating mode and the user's adjustment object. The learning rate defines the compensation offset of the vehicle air conditioning load demand characterization value corresponding to a unit change in user operation. The array update module updates the calculated blower gear compensation value or target outlet air temperature compensation value into the personalized compensation data array corresponding to the current user identity, current air conditioning working mode and adjustment object, and stores the updated array. The evaluation and correction module applies a confidence level based on a time decay factor to the historical compensation values ​​stored in the personalized compensation data array, where the confidence level decays over time; it obtains the user's subjective evaluation coefficient of the air conditioning comfort in the current driving cycle, and corrects the compensation values ​​calculated in the current driving cycle based on the evaluation coefficient, and uses the corrected compensation values ​​to update the array; The personalized synthesis module queries the preset basic blower speed control curve and basic target air outlet temperature control curve based on the current vehicle air conditioning load demand characterization value to obtain the basic control value; it queries the corrected personalized compensation data array based on the current vehicle air conditioning load demand characterization value to obtain the personalized compensation value; it combines the basic control value and the personalized compensation value to calculate the final target blower speed and target air outlet temperature, and sends them to the actuator of the vehicle air conditioning system for control.

[0017] Embodiments of the present invention also provide a personalized temperature control device based on user feedback, comprising: processor; A memory in which executable instructions of the processor are stored; The processor is configured to execute the steps of the aforementioned personalized temperature control method based on user feedback by executing the executable instructions.

[0018] Embodiments of the present invention also provide a computer-readable storage medium for storing a program that, when executed, implements the steps of the above-described personalized temperature control method based on user feedback.

[0019] The purpose of this invention is to provide a personalized temperature control method, system, device, and storage medium based on user feedback, which can achieve low-cost, adaptive, and forgettable personalized calibration of vehicle air conditioning comfort based solely on the user's daily operating behavior, without the need for complex sensors and model training. Attached Figure Description

[0020] Other features, objects, and advantages of the invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings.

[0021] Figure 1 This is a flowchart of the personalized temperature control method based on user feedback of the present invention.

[0022] Figure 2 This is a schematic diagram illustrating the process of implementing the user-feedback-based personalized temperature control method of the present invention.

[0023] Figure 3 This is the control flow of an air conditioning component that runs the personalized temperature control method based on user feedback of the present invention.

[0024] Figure 4 It is a graph showing the blower speed curves for different users after running the personalized temperature control method based on user feedback of this invention.

[0025] Figure 5 It is a graph showing the target air outlet temperature curves for different users after running the personalized temperature control method based on user feedback of the present invention.

[0026] Figure 6 This is a system architecture diagram of the personalized temperature control system based on user feedback of the present invention.

[0027] Figure 7 This is a schematic diagram of the structure of the personalized temperature control device based on user feedback according to the present invention.

[0028] Figure 8 This is a schematic diagram of the structure of a computer-readable storage medium according to an embodiment of the present invention. Detailed Implementation

[0029] The following specific examples illustrate the implementation methods of this application. Those skilled in the art can easily understand the other advantages and effects of this application from the content disclosed herein. This application can also be implemented or applied through other different specific embodiments, and various details in this application can be modified or changed according to different viewpoints and application systems without departing from the spirit of this application. It should be noted that, unless otherwise specified, the embodiments and features in the embodiments of this application can be combined with each other.

[0030] The embodiments of this application will now be described in detail with reference to the accompanying drawings, so that those skilled in the art can easily implement the application. This application may be embodied in many different forms and is not limited to the embodiments described herein.

[0031] In this application, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics represented in connection with that embodiment or example, which are included in at least one embodiment or example of this application. Furthermore, the specific features, structures, materials, or characteristics represented may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate different embodiments or examples represented in this application, as well as features of different embodiments or examples.

[0032] Furthermore, the terms "first" and "second" are used for illustrative purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the representation of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0033] For the purpose of clearly describing this application, devices that are not relevant to the description are omitted, and the same or similar components throughout the specification are given the same reference numerals.

[0034] Throughout this specification, when it is said that a device is "connected" to another device, this includes not only "direct connection" but also "indirect connection" by placing other components in between. Furthermore, when it is said that a device "comprises" a certain constituent element, unless otherwise stated otherwise, this does not exclude other constituent elements, but rather implies that other constituent elements may be included.

[0035] When we say that a device is "above" another device, this can mean that it is directly above the other device, or it can mean that other devices are present in between. Conversely, when we say that a device is "directly" "above" another device, there are no other devices present in between.

[0036] Although the terms first, second, etc., are used in some instances herein to refer to various elements, these elements should not be limited by these terms. These terms are used only to distinguish one element from another. For example, first interface and second interface, etc., are used. Furthermore, as used herein, the singular forms “a,” “an,” and “the” are intended to also include the plural forms unless the context indicates otherwise. It should be further understood that the terms “comprising,” “including,” indicate the presence of features, steps, operations, elements, components, items, kinds, and / or groups, but do not exclude the presence, occurrence, or addition of one or more other features, steps, operations, elements, components, items, kinds, and / or groups. The terms “or” and “and / or” as used herein are interpreted as inclusive, or mean any one or any combination thereof. Thus, “A, B, or C” or “A, B, and / or C” means “any one of: A; B; C; A and B; A and C; B and C; A, B, and C.” Exceptions to this definition will only occur if the combination of elements, functions, steps, or operations is inherently mutually exclusive in some way.

[0037] The technical terms used herein are for reference only to specific embodiments and are not intended to limit the scope of this application. The singular form used herein includes the plural form unless the statement explicitly indicates otherwise. The word "comprising" as used in the specification means to specify a particular characteristic, region, integer, step, operation, element, and / or component, and does not exclude the presence or addition of other characteristics, regions, integers, steps, operations, elements, and / or components.

[0038] Although not explicitly defined, all terms, including technical and scientific terms used herein, shall have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. Terms defined in commonly used dictionaries shall be further interpreted as having a meaning consistent with the relevant technical literature and the content of this present application, and shall not be over-interpreted as having an ideal or overly formulaic meaning unless otherwise defined.

[0039] Figure 1 This is a flowchart of the personalized temperature control method based on user feedback according to the present invention. Figure 1 As shown, the personalized temperature control method based on user feedback of the present invention includes the following steps: S100. Identify the user identity of the currently driving vehicle, and load the corresponding personalized compensation data array from the local storage module according to the user identity. The personalized compensation data array includes at least a blower gear compensation value array and a target air outlet temperature compensation value array based on the vehicle air conditioning load demand characterization value. The blower gear compensation value is achieved by adjusting the blower gear, and the target air outlet temperature compensation value is achieved by adjusting the air conditioning set temperature.

[0040] S200: Real-time monitoring of the vehicle's air conditioning system's operating mode and user behavior. When the air conditioning system is determined to be in cooling or heating mode, it continuously monitors the user's adjustments to the blower speed and the user's settings for the air conditioning temperature.

[0041] S300: Upon detecting a valid adjustment operation performed by the user, obtain the vehicle's air conditioning load demand characterization value at the moment the adjustment operation occurs. Calculate the change in blower speed or air conditioning set temperature caused by the adjustment operation. Based on a predefined learning rate corresponding to the current air conditioning operating mode and the user's adjustment object, calculate the blower speed compensation value or target outlet temperature compensation value to be applied under the current vehicle air conditioning load demand characterization value. The learning rate defines the compensation offset of the vehicle air conditioning load demand characterization value corresponding to a unit change in user operation.

[0042] S400: Update the calculated blower speed compensation value or target outlet air temperature compensation value to the personalized compensation data array corresponding to the current user identity, current air conditioning working mode and adjustment object, and store the updated array.

[0043] S500: Apply confidence processing based on a time decay factor to the historical compensation values ​​stored in the personalized compensation data array. The confidence level decays over time. Obtain the user's subjective evaluation coefficient of the air conditioning comfort in the current driving cycle, and correct the compensation values ​​calculated in the current driving cycle based on the evaluation coefficient. Use the corrected compensation values ​​to update the array.

[0044] S600: Based on the current vehicle air conditioning load demand, query the preset basic blower speed control curve and basic target outlet air temperature control curve to obtain the basic control value. Based on the current vehicle air conditioning load demand, query the corrected personalized compensation data array to obtain the personalized compensation value. Combine the basic control value and the personalized compensation value to calculate the final target blower speed and target outlet air temperature, and send them to the actuator of the vehicle air conditioning system for control.

[0045] This embodiment provides a complete, closed-loop framework for personalized temperature control. Its core effect lies in transforming the traditional "one-way, fixed" control mode of air conditioning into a "two-way, learnable, and adaptive" intelligent interaction mode. This method achieves a "personalized service" foundation through user identification. Through real-time monitoring and learning, every user's proactive adjustment is transformed into system knowledge. Confidence and evaluation mechanisms endow the system with the intelligence of "memory" and "forgetting." Finally, parameter synthesis achieves seamless implementation of personalized strategies. Compared to existing technologies, this method systematically solves three core challenges: achieving personalization at low cost, adapting to changing habits, and ensuring reasonable control logic. It provides a cost-effective and user-sticky path for upgrading comfort functions in vehicle intelligence, and is particularly suitable for widespread adoption on mid-to-low-end vehicle platforms, significantly enhancing product market competitiveness and user experience value.

[0046] In a preferred embodiment, step S300 includes: S301. In cooling mode, when the user lowers or raises the blower speed, the vehicle's air conditioning load demand is represented by the value TAO. Cool Let the blower speed difference be BlowerLevel. Cool (d) - BlowerLevel Cool (d-1), where (d-1) represents the blower speed before adjustment, and d is the blower speed after adjustment. The learning rate (LearnRate) is the rate at which the blower speed is adjusted in cooling mode. Cool The value range is [-1, 0], LearnRate Cool = (-1 / 100) × (TAO MAX -TAO MIN ) / (D MAX -D MIN ), among which, TAO MAX This is the upper limit of the TAO value, TAO MIN D is the lower limit of the TAO value. MAX D is the upper limit of the blower speed. MIN This is the lower limit of the blower speed.

[0047] S302, Calculate the blower speed compensation value TAOOffset in cooling mode. Cool = [BlowerLevel Cool (d)-BlowerLevel Cool [(d-1)]×LearnRate Cool and TAOOffset Cool Updated to TAO as blower gear compensation value. Cool The corresponding array position.

[0048] S303. In heating mode, when the user lowers or raises the blower speed, the vehicle's air conditioning load demand is represented by the value of TAO. Heat The learning rate (LearnRate) for adjusting the blower speed during heating. Heat The value range is [0, 1], and LearnRate Heat = (1 / 100) × (TAO MAX - TAO MIN ) / (D MAX -D MIN ).

[0049] S304, Calculate the blower speed compensation value TAOOffset in heating mode. Heat = [BlowerLevel Heat (d)-BlowerLevel Heat [(d-1)]×LearnRate Heat and TAOOffset Heat Updated to TAO as blower gear compensation value. Heat The corresponding array position, but not limited to this. This embodiment features a refined design for airflow compensation learning, distinguishing between cooling and heating modes with opposite thermodynamic directions, and assigning different signs (negative and positive) to the learning rate. The key effect of this design is that it accurately maps the relationship between the user's physical perception and the system's control logic. In cooling mode, the user feels hot and increases the airflow, resulting in a negative learning rate and a negative compensation value. This conveys a precise semantic to the system: "At the current TAO value (representing a certain heat load), the airflow you provide (corresponding to the current cooling intensity) is insufficient and needs to be increased." By negatively compensating the TAO value, the system will drive the base curve to output a larger airflow under the same environmental conditions in the future, thereby responding to the user's demand for "cooler" airflow. In heating mode, the logic is exactly the opposite. This symbolic and directional learning design gives the system's learning process clear physical meaning and high interpretability, avoiding confusion in the learning logic. It ensures that the learned compensation can accurately "translate" the user's feelings of hot and cold, and translate them into the correct correction of the cooling / heating demand intensity of the air conditioning system. This greatly improves the accuracy and convergence speed of personalized learning, enabling the system to adapt to user preferences more quickly.

[0050] In a preferred embodiment, step S300 further includes: When the user adjusts the set temperature, the vehicle's air conditioning load demand is represented by the value of TAO. TempSetThe temperature difference is set as TempSet(t) - TempSet(t-1), where (t-1) represents the set temperature before adjustment and t is the set temperature after adjustment. The learn rate (LearnRate) of the air conditioner when adjusting the temperature is set. TempSet The defined range is [0,1], LearnRate TempSet = (1 / 100) × (TAO MAX - TAO MIN (Set upper temperature limit - Set lower temperature limit) Calculate the target temperature compensation TempSet Offset = LearnRate TempSet × [TempSet(t) - TempSet(t-1)], and set the target outlet air temperature compensation value TempSet Offset Updated to TAO as the target outlet air temperature compensation value. TempSet The corresponding array position, but not limited to this.

[0051] This embodiment expands the learning dimension by incorporating user adjustments to the air conditioner's set temperature into the personalized learning system. Its significant effect lies in capturing and learning the user's "global comfort baseline." User temperature adjustments are typically "macro" adjustments to the overall perceived temperature, affecting the baseline of the core control objective: the target airflow temperature. By learning this operation, the system can understand the user's overall preference shift towards "warmth" or "coolness." Combining this with learning about airflow adjustment (which affects the speed and intensity of reaching the target temperature), the system can construct a two-dimensional, more comprehensive personalized comfort model. For example, user A might prefer a "gentle breeze and warmth" (higher set temperature compensation + lower airflow compensation), while user B might prefer a "strong breeze and refreshing coolness" (lower set temperature compensation + higher airflow compensation). This ability to learn from complex operations upgrades the system's personalized service from a single "airflow preference" to a comprehensive "perceived climate" customization, more closely aligning with the user's real and complex comfort needs, achieving a deeper level of personalized adaptation.

[0052] In a preferred embodiment, step S300, the process of determining whether a user performs a valid adjustment operation, includes: anti-shake filtering. Starting from the user's first adjustment action, within a predetermined filtering time window, all subsequent adjustment operations are ignored. Only the blower speed setting or air conditioner set temperature value that stabilizes at the end of the filtering time window is recorded and used as the post-adjustment state for compensation calculation, but this is not a limitation. This embodiment introduces an anti-shake filtering mechanism to define a "valid adjustment operation." Its direct and crucial effect is to greatly improve the quality and reliability of the learning data, thereby ensuring the robustness of the entire personalized learning system. Filtering out operation noise: In actual operation, users may engage in accidental touches, rapid and continuous clicks to test the optimal speed, etc. Anti-shake filtering, through a time window (e.g., 5 seconds) delay, can filter out these brief, unstable, and unintentional adjustments, capturing only the final stable set value after the user's consideration. This effectively prevents accidental and exploratory operations from contaminating the learning data. Ensuring clear learning intent: Only operations that stabilize after a period of time are considered as the user's "deterministic correction opinion" to the current automatic control output. This allows subsequent calculations of changes and learned compensation values ​​to more accurately reflect the user's stable preferences under that operating condition. It also reduces computational overhead and the risk of mislearning: by avoiding calculations and array updates for every operation signal, unnecessary processing overhead is reduced. More importantly, it fundamentally lowers the probability of the system learning incorrectly due to "misreading" user intent, ensuring the stability and accuracy of long-term learning results.

[0053] In a preferred embodiment, step S500 involves applying a confidence factor based on time decay to the historical compensation values ​​stored in the personalized compensation data array. The confidence factor decays over time. This includes associating a confidence coefficient Conf with each compensation value element in the personalized compensation data array. This confidence coefficient is updated according to an exponential decay law: Conf = exp(-λ × t), where λ is a configurable forgetting coefficient, and t is the time elapsed since the compensation value was recorded or last reinforced. When synthesizing personalized parameters, the historical compensation value retrieved from the array must be multiplied by its current corresponding confidence coefficient Conf before use.

[0054] In step S500, the user's subjective evaluation coefficient of the air conditioning comfort in the current driving cycle is obtained, and the compensation value calculated in the current driving cycle is corrected based on this evaluation coefficient. The corrected compensation value is used to update the array. This includes: at the end of the driving cycle or when the user actively triggers the process, obtaining the user's evaluation coefficient α of the current air conditioning comfort through the human-machine interface. The evaluation coefficient α has a value range of [0, 1]. All compensation values ​​calculated based on the user's operation in the current driving cycle are multiplied by the evaluation coefficient α to obtain the corrected compensation value B.corrected = α × B raw B raw The initial compensation value is then adjusted to the corrected compensation value B. corrected This system is used to update the personalized compensation data array, but is not limited to this. This embodiment constructs a dynamic, intelligent, and lifecycle-based memory management system through two main mechanisms: confidence decay and user evaluation. Its effect is to endow the system with human-like "memory reinforcement" and "natural forgetting" capabilities. Confidence decay (active forgetting): Through an exponential decay model, the influence of historical compensation values ​​naturally weakens over time. Its effect is to adaptively solve the "habit drift" problem. For example, a user's preference for strong cold winds formed in summer will naturally be "forgotten" by the system in winter, thus avoiding interference from outdated preferences on current seasonal control. This allows the personalized model to smoothly evolve with the seasonal and phased changes in user habits, always maintaining synchronization with the user's current needs. User evaluation (active feedback and reinforcement): The user evaluation coefficient α provides the system with high-quality direct supervision signals. Its effect is to achieve reinforcement learning based on rewards (satisfaction) and punishments (dissatisfaction). Satisfactory experiences (α=1) solidify correct learning. Dissatisfactory experiences (α=0) immediately clear incorrect learning, preventing further deviation in the wrong direction. Average experiences are adjusted proportionally. This not only significantly improves the efficiency and accuracy of learning, but also gives users a sense of participation and control in leading the system's learning process, enhancing the usability of the functions and user trust. The combination of these two aspects transforms the system's "memory" from a static accumulation of data into a dynamic, malleable, and self-updating intelligent entity.

[0055] In a preferred embodiment, step S500 further includes maintaining the trend consistency of the compensation value array. After updating the personalized compensation data array, the trend of the elements in the array changing with the TAO value is checked. It is checked and ensured that the overall trend of the final control parameters after superimposed compensation values ​​changing with the TAO value conforms to expectations: the blower speed is not increasing overall in the cooling TAO range, and not decreasing overall in the heating TAO range. The target outlet air temperature is not decreasing overall across the entire TAO range. If the array update causes the above trends to be disrupted, the compensation value array is smoothed or adjusted to restore a logical trend, but this is not a limitation. This embodiment introduces a trend consistency maintenance mechanism, the core effect of which is to ensure the high-level logical rationality and physical feasibility of personalized control, preventing the learning process from damaging the basic control principles of the air conditioning system. Maintaining thermodynamic logic: A basic common sense of air conditioning control is that the stronger the cooling demand (the lower the TAO value), the greater the required air volume. The stronger the heating demand (the higher the TAO value), the greater the required air volume. The outlet air temperature should monotonically increase with the increase of the TAO value (heat demand). This embodiment mandates that the compensation value array conforms to these trends, ensuring that the final control curve after superimposed compensation will not exhibit logical errors such as "the airflow is smaller when it's hotter" or "the outlet temperature is lower when it's colder." Ensuring control stability and comfort: A smooth, monotonous control curve is fundamental to stable system operation and providing a seamless, comfortable experience. Trend maintenance, through smoothing or adjusting the array, eliminates abrupt changes, oscillations, or plateaus in the curve that may arise from discrete-point learning. This guarantees a smooth, continuous, and predictable control output, avoiding new control jitter or discomfort introduced by personalized learning, thus ensuring the ultimate goal of the function—improved comfort—from an engineering perspective. Enhancing the robustness of the learning system: As a post-correction mechanism, this can correct occasional abnormal learning data (potentially originating from sensor noise, extreme operations, etc.), enhancing the fault tolerance and robustness of the entire learning system.

[0056] In a preferred embodiment, step S600, calculating the personalized compensation value, includes: Ultimate goal: Blower gear B final = Basic blower speed TAOBase Level + Confidence coefficient Conf × Historical blower gear compensation value B Level + This blower speed compensation value (BlowerLevel) Offset .

[0057] Final target air outlet temperature T final = Base target outlet air temperature TAOBase TempSet + Confidence coefficient Conf × Historical target temperature compensation value B TempSet + Target temperature compensation value TempSetOffset .

[0058] Among them, the basic blower speed TAOBase Level and the baseline target outlet air temperature TAOBase TempSet The historical blower gear compensation value B is obtained by querying the preset base control curve corresponding to the current TAO value. Level and historical target temperature compensation value B TempSet The personalized compensation data array processed in step S500 is obtained by querying the data. The blower gear compensation value and the target temperature compensation value are the compensation values ​​to be stored in the array after evaluation and correction in step S500 during the current driving cycle, but are not limited to these. This embodiment clarifies the synthesis formula of the final control parameters. Its technical effect lies in achieving multi-level, smooth transition of personalized control fusion, and ensuring the real-time performance and continuity of control. Three-layer fusion architecture: Formula B final = Basic blower speed TAOBase Level + Confidence coefficient Conf × Historical blower gear compensation value B Level + This blower speed compensation value (BlowerLevel) Offset A clear three-tier control architecture has been constructed: the base layer (TAOBase) Level ): Provides baseline controls that comply with engineering standards and safety specifications to ensure basic functional reliability. (B) Level This layer (Blower Level) carries users' long-term, stable personalized preferences and is the main outcome of learning. However, due to confidence decay, its influence dynamically adjusts with time or season. Offset This reflects the user's temporary, scenario-based adjustment intentions during this driving cycle, has the highest priority, and can achieve the fastest response. Smoothness and coherence: This additive synthesis method makes the transition from "general control" to "deep personalization" smooth, continuous, and interpretable. When the user uses it for the first time or after a long period of inactivity, B... Level It's very small; the system is close to basic control. As learning progresses, B... Level Gradually taking shape, personalization becomes more prominent. And when users make temporary adjustments, BlowerLevel... Offset It allows for instantaneous fine-tuning. This design avoids abrupt changes in control modes, ensuring a consistent and natural user experience. It is computationally efficient: the synthesis formula is a simple addition operation with minimal computational load, easily completed in real-time within each control cycle (e.g., milliseconds) of the vehicle controller. This meets the stringent requirements of onboard systems for real-time performance and low latency, ensuring timely and accurate control.

[0059] Figure 2This is a schematic diagram illustrating the process of implementing the user-feedback-based personalized temperature control method of the present invention. Figure 3 This describes the control flow of an air conditioning component implementing the user-feedback-based personalized temperature control method of the present invention. This embodiment elaborates on the implementation process of the user-feedback-based personalized temperature control method provided by the present invention. (Reference) Figure 1 , 2 As shown in Figure 3, the process of running the personalized temperature control method based on user feedback of the present invention includes: Step S100: User Identification and Personalized Array Loading. When the vehicle is powered on or wakes up from sleep mode, the system first needs to identify the current driver or primary occupant. The user identification identifier, i.e., the user ID, can be obtained in various ways, such as: facial recognition via the in-vehicle camera, association via Bluetooth or NFC key on a mobile device, login to the vehicle system using the driver's account, or manual selection of the user profile directly on the central control screen. This invention does not limit the specific method of obtaining the user ID, as long as it can uniquely distinguish different users. After identifying the user ID, the system reads the personalized compensation data array bound to the user ID from the vehicle's local non-volatile storage module. These arrays are the results that the system has previously learned and saved for this user. They mainly contain two core arrays: the blower gear compensation value array: this array is indexed by the TAO value (or corresponds to the TAO value range) and stores the blower gear compensation values ​​learned according to the user's habits under various historical TAO value conditions. Target air outlet temperature compensation value array: This array, also indexed by TAO value, stores the target air outlet temperature compensation value learned based on the user's habits under various historical TAO value conditions. Blower motor speed compensation value is achieved by adjusting the blower motor speed, and target air outlet temperature compensation value is achieved by adjusting the air conditioning set temperature. If the system is recognizing the user for the first time, or if the user has not yet formed any personalized data, the initial values ​​of the loaded arrays are all zero. These arrays constitute the "knowledge base" for personalized control of the user. Step S200: Air conditioning status and user operation monitoring. The system enters real-time operation monitoring state. First, it continuously determines the current operating mode of the vehicle's air conditioning system. The key is to distinguish whether the air conditioning is in an "active" state capable of performing cooling or heating functions. For example, when the air conditioning compressor or PTC heater is not started, and only the blower is turned on for ventilation, this state is defined as "ventilation state," in which the system does not perform personalized learning. When the system determines that the air conditioning is in "cooling mode" or "heating mode," it initiates continuous monitoring of specific user operation behaviors. These operations mainly refer to the adjustments made by users to the "blower fan speed setting" and "air conditioner set temperature" via physical buttons, knobs, or a touchscreen interface. The system captures these adjustment commands and their changes in real time.

[0060] Step S300: Effective Adjustment Detection and Compensation Value Calculation. This is the core calculation step of personalized learning. When the monitoring module detects that the user has started adjusting the airflow or temperature, it does not immediately calculate, but instead initiates an "effective operation judgment" process. Taking adjusting the blower speed as an example, from the first action of the user pressing the airflow "+" or "-" button, the system starts a timer and sets a filtering time window, such as 5 seconds. Within these 5 seconds, the user may click multiple times in succession for rapid adjustment. The system ignores these intermediate processes and only continuously records the real-time value of the airflow. When the 5-second timer ends, the user stops operating, and the stable blower speed value at this time is recognized as the final value after this "effective adjustment". This method effectively avoids noise data introduced by the user's rapid, tentative operations. The same anti-shake filtering logic is used for temperature adjustment. Then, the change in blower speed or air conditioning set temperature caused by the adjustment operation is calculated. Based on the predefined learning rate corresponding to the current air conditioning operating mode and the user's adjustment object, the blower speed compensation value or target outlet temperature compensation value to be applied under the current vehicle air conditioning load demand characterization value is calculated. The learning rate defines the compensation offset of the vehicle air conditioning load demand characterization value corresponding to a unit change in user operation. The learning rate is a key proportional coefficient that maps the user's operation "physical quantity change" to the system control "logical quantity offset".

[0061] In cooling mode, when the user adjusts the blower speed down or up, the vehicle's air conditioning load demand is represented by the value TAO. Cool Let the blower speed difference be BlowerLevel. Cool (d) - BlowerLevel Cool (d-1), where (d-1) represents the blower speed before adjustment, and d is the blower speed after adjustment. The learning rate (LearnRate) is the rate at which the blower speed is adjusted in cooling mode. Cool The value range is [-1, 0], LearnRate Cool = (-1 / 100) × (TAO MAX -TAO MIN ) / (D MAX -D MIN ), among which, TAO MAX This is the upper limit of the TAO value, TAO MIN D is the lower limit of the TAO value. MAX D is the upper limit of the blower speed. MIN This is the lower limit of the blower speed; Calculate the blower speed compensation value TAOOffset in cooling mode Cool = [BlowerLevel Cool (d)-BlowerLevelCool [(d-1)]×LearnRate Cool and TAOOffset Cool Updated to TAO as blower gear compensation value. Cool The corresponding array position. The numerator of this formula is the full range of the TAO value, and the denominator is the full range of the blower speed setting. In cooling mode, when a user feels hot (and wants it cooler) and increases the airflow, the system should understand that the TAO value (representing cooling demand) under this condition is overestimated and requires negative compensation. This allows the system to behave as if it has a "stronger cooling demand" under the same environmental conditions, thus automatically outputting a larger airflow for the same TAO value in the future.

[0062] Furthermore, in heating mode, when the user adjusts the blower speed down or up, the vehicle's air conditioning load demand is represented by the value TAO. Heat The learning rate (LearnRate) for adjusting the blower speed during heating. Heat The value range is [0, 1], and LearnRate Heat = (1 / 100) × (TAO MAX - TAO MIN ) / (D MAX -D MIN ); Calculate the blower speed compensation value TAOOffset in heating mode. Heat = [BlowerLevel Heat (d)- BlowerLevel Heat [(d-1)]×LearnRate Heat and TAOOffset Heat Updated to TAO as blower gear compensation value. Heat The corresponding array position. In heating mode, when a user feels cold (and wants to be warmer) and increases the airflow, the system should understand that the TAO value (representing heating demand) under this condition is underestimated and requires positive compensation so that the system can automatically output a larger airflow under the same TAO value in the future.

[0063] Furthermore, when the user adjusts the set temperature, the vehicle's air conditioning load demand is represented by the value of TAO. TempSet The temperature difference is set as TempSet(t) - TempSet(t-1), where (t-1) represents the set temperature before adjustment and t is the set temperature after adjustment. The learning rate (LearnRate) of the air conditioner when adjusting the temperature is set is used. TempSet The defined range is [0,1], LearnRate TempSet = (1 / 100) × (TAO MAX - TAOMIN (Set upper temperature limit - Set lower temperature limit). Calculate the target temperature compensation TempSet. Offset = LearnRate TempSet × [TempSet(t) - TempSet(t-1)], and set the target outlet air temperature compensation value TempSet. Offset Updated to TAO as the target outlet air temperature compensation value. TempSet The corresponding array position. The denominator is the adjustable range of the set temperature. When a user increases the set temperature (TempSet is positive), it usually means they feel cold and want a higher overall airflow temperature. The system interprets this as: at the current TAO value, the basic target airflow temperature curve is too low, requiring positive compensation to increase the target airflow temperature under this condition in the future.

[0064] Step S400: Personalized array update. The blower gear compensation value (TAOOffset) calculated in step S300 is updated. Cool or TAOOffset Heat Update the corresponding blower gear compensation value array for that user, with the index being the recorded TAO value (TAO). Cool Or TAO Heat Similarly, the calculated target outlet air temperature compensation value TempSet will be used. Offset Update the target outlet air temperature compensation value array corresponding to this user, with the index TAO. TempSet The update operation can directly replace the old value, or perform smoothing processing such as weighted averaging on the old value, and then save the updated array back to the local storage module. In this way, each effective adjustment by the user gradually fills and improves their exclusive personalized compensation "map".

[0065] Step S500: Confidence Processing and User Evaluation Correction. This step introduces the "timeliness of memory" and "direct user feedback," making the system more intelligent. Confidence decay (forgetting mechanism): The system maintains a dynamic confidence coefficient Conf for each historical compensation value element in the array. This coefficient decays exponentially over time: Conf = exp(-λ ×t). Where λ is the forgetting coefficient, which can be configured by the user or developer to determine the rate of forgetting. t is the time elapsed since the compensation value was last recorded or reinforced (usually in days or hours). For example, λ is set so that the confidence of the data decays to 90% after one week. Whenever a historical compensation value needs to be used (as in step S600), the system first queries its current confidence Conf, then multiplies the compensation value by Conf before using it. This means that an old habit that has not been "verified" or "reinforced" by the user for a long time will have less and less influence on the current control and will gradually be "forgotten." This perfectly solves the problems caused by seasonal changes (habits learned in summer are not applicable in winter) or long-term changes in user preferences.

[0066] User evaluation correction (reinforcement learning): At the end of each driving cycle (when the vehicle is powered off), or when the user actively triggers the evaluation via voice (e.g., "The air conditioning was very comfortable today") or a screen button, the system invites the user to rate the comfort of the air conditioning during the trip. The evaluation result is quantified as a coefficient α, ranging from 0 to 1.

[0067] If α = 0 (very unsatisfactory), the system determines that all compensation values ​​learned during this trip are invalid, and clears these compensation values ​​from the cache to be stored in the array before the vehicle is powered off, and does not save them.

[0068] If α = 1 (very satisfactory), then the original compensation value obtained in this calculation will be completely retained.

[0069] If 0 < α < 1 (generally satisfactory), then multiply all the original compensation values ​​obtained in this calculation by α to obtain an attenuated value and save it.

[0070] This mechanism allows users to become "mentors" in the system's learning process. Satisfactory experiences reinforce correct learning directions, while unsatisfactory experiences correct or discard incorrect learning. Simultaneously, the user's evaluation behavior itself resets the confidence decay timer t of the relevant compensation value, effectively "reinforcing" the memory and restoring or maintaining its confidence at a high level.

[0071] Trend Consistency Maintenance: Since the compensation values ​​are learned at discrete TAO points, directly updating the array may lead to unreasonable fluctuations in the final synthesized control curve. For example, in regions with low TAO values ​​(forced cooling demand), the blower speed compensation value should increase or remain unchanged as the TAO value decreases (because hotter temperatures require stronger airflow), and there should not be a situation where the compensation value decreases as the TAO value decreases. Therefore, after updating the array, the system checks the overall trend of the compensation value array as the TAO value changes. For the blower speed compensation array, it is required to be non-increasing overall in the cooling TAO range (low TAO value segment) and non-decreasing overall in the heating TAO range (high TAO value segment). For the target outlet temperature compensation array, it is required to be non-decreasing overall across the entire TAO range. If a new update is found to disrupt this trend, adjacent array elements will be smoothed by interpolation or slightly adjusted to ensure that the final control curve is logically sound, smooth, and monotonic.

[0072] Step S600: Personalized Control Parameter Synthesis and Execution. This step applies the results of personalized learning to real-time control. At every moment of air conditioning operation, the system executes the following: Obtaining Base Values: Based on the currently calculated TAO value, the system queries the factory-preset, standardized "Basic Blower Gear Control Curve" and "Basic Target Airflow Temperature Control Curve" to obtain the baseline control parameters TAOBase for all users. Level and TAOBase TempSet Obtain personalized compensation value: Historical compensation value: Based on the current TAO value, query the personalized compensation data array processed in step S500 (i.e., the array multiplied by the confidence level Conf) to obtain the historical blower gear compensation value B. Level and historical target temperature compensation value B TempSet Current compensation value: Retrieves the current compensation value (BlowerLevel) after user feedback and adjustments, to be stored in the array during the current driving cycle. Offset and TempSet Offset (If new data is learned during this trip). Final parameters: Calculate the final control commands sent to the actuators using the following formula: Ultimate goal: Blower gear B final = Basic blower speed TAOBase Level + Confidence coefficient Conf × Historical blower gear compensation value B Level + This blower speed compensation value (BlowerLevel) Offset ; Final target air outlet temperature T final = Base target outlet air temperature TAOBase TempSet + Confidence coefficient Conf × Historical target temperature compensation value BTempSet + Target temperature compensation value TempSet Offset ; Among them, the basic blower speed TAOBase Level and the baseline target outlet air temperature TAOBase TempSet The historical blower gear compensation value B is obtained by querying the preset basic control curve corresponding to the current TAO value. Level and historical target temperature compensation value B TempSet The personalized compensation data array processed by step S500 is obtained by querying the current blower gear compensation value and the current target temperature compensation value. These are the compensation values ​​to be stored in the array after evaluation and correction by step S500 in the current driving cycle, so that the control can reflect the user's stable preferences and respond quickly to temporary adjustment needs.

[0073] Execution control: Calculate the final target blower speed B. final and the final target outlet air temperature T final The signal is sent to the vehicle's air conditioning controller, which in turn drives the blower motor, temperature damper, compressor, and other actuators to achieve precise temperature control that meets the user's current personalized comfort needs.

[0074] Figure 4 It is a graph showing the blower speed curves for different users after running the personalized temperature control method based on user feedback of this invention. Figure 5 This is a graph showing the target outlet air temperature curves for different users after implementing the user feedback-based personalized temperature control method of this invention. By repeatedly executing the above steps, the system continuously learns, corrects, and forgets from user operations, ultimately generating graphs for different users as shown above. Figure 4 and Figure 5 The diagram shows distinctly different personalized control curves. User A might prefer a gentle, low-heat cooling, resulting in a downward shift in their blower curve. User B might prefer rapid, powerful cooling, leading to an upward shift in their curve. The target temperature curve will also shift individually based on the user's preference for perceived temperature. The entire process is fully automated, requiring no complex settings from the user.

[0075] Compared with the prior art, the present invention has the following significant advantages: Low cost and low resource consumption: This invention completely eliminates the reliance on expensive dedicated sensors such as infrared cameras, and also eliminates the need for large-scale data collection and complex neural network model training. Its core logic is based on monitoring the user's existing operating interface (airflow, temperature adjustment buttons) and simple arithmetic operations, which greatly reduces the requirements for onboard hardware computing power, storage space, and system deployment costs, making personalized air conditioning functions easily achievable in various models from high-end to economy cars.

[0076] Real-time proactive learning and high adaptability: The solution does not passively rely on historical statistics, but rather interprets and learns from every proactive adjustment by the user in real time. The system treats user adjustments as "correction instructions" for the current automatic control output and quantifies them as personalized offsets in the TAO-parameter mapping relationship through the learning rate. This learning is continuous and online, enabling rapid response to changes in user habits and truly "understanding you better the more you use it."

[0077] Intelligent Forgetting and Overfitting Prevention Mechanisms: By introducing a confidence coefficient based on exponential decay and an explicit user evaluation mechanism, the system possesses the intelligence to "remember" and "forget." Old habits that haven't been reinforced over time will naturally decay, unsatisfactory adjustments will be weakened or cleared, while satisfactory adjustments will be reinforced. This effectively solves the problem of learning data becoming "outdated" or "contaminated" due to seasonal changes, shifts in user preferences, or accidental misoperations, ensuring that the personalized model always maintains a high degree of consistency with the user's current real needs.

[0078] Ensuring the rationality and stability of the control logic: By maintaining trend consistency, it is ensured that the learned personalized compensation will not disrupt the most basic physical logic and comfort gradient of the air conditioning control. Anti-shake filtering avoids data noise caused by operational jitter. The final control parameters are jointly determined by the base value, the attenuated historical habit value, and the current correction value, resulting in a smooth and stable output that avoids abrupt changes in control parameters, thereby improving the consistency and comfort of the user experience.

[0079] High user engagement and transparency: The introduction of a user evaluation mechanism empowers users with direct intervention and feedback channels in the system's learning process. Users are no longer passive recipients of the system's adaptation but have become "coaches" for personalized model training. This increases the functionality's appeal and users' sense of control, while also providing the system with high-quality positive and negative feedback signals, significantly improving learning efficiency and accuracy.

[0080] Figure 6 This is a system architecture diagram of the personalized temperature control system based on user feedback according to the present invention. Figure 6 As shown, the personalized temperature control system 5 based on user feedback of the present invention includes: The array loading module 51 identifies the user identity of the currently driving vehicle and loads the corresponding personalized compensation data array from the local storage module according to the user identity. The personalized compensation data array includes at least a blower gear compensation value array and a target air outlet temperature compensation value array based on the vehicle air conditioning load demand representation value. The blower gear compensation value is achieved by adjusting the blower gear, and the target air outlet temperature compensation value is achieved by adjusting the air conditioning set temperature.

[0081] The operation monitoring module 52 monitors the operating mode of the vehicle's air conditioning system and user operation behavior in real time. When it is determined that the air conditioning system is in cooling or heating mode, it continuously monitors the user's adjustment of the blower speed and the user's adjustment of the air conditioning set temperature.

[0082] A compensation module 53 is established to acquire the vehicle air conditioning load demand characterization value at the moment the user performs a valid adjustment operation. It calculates the change in blower speed or air conditioning set temperature caused by the adjustment operation. Based on a predefined learning rate corresponding to the current air conditioning operating mode and the user's adjustment object, it calculates the blower speed compensation value or target outlet temperature compensation value to be applied under the current vehicle air conditioning load demand characterization value. The learning rate defines the compensation offset of the vehicle air conditioning load demand characterization value corresponding to a unit change in user operation.

[0083] The array update module 54 updates the calculated blower speed compensation value or target air outlet temperature compensation value to the personalized compensation data array corresponding to the current user identity, current air conditioning working mode and adjustment object, and stores the updated array.

[0084] The evaluation correction module 55 applies a confidence level based on a time decay factor to the historical compensation values ​​stored in the personalized compensation data array. The confidence level decays over time. It obtains the user's subjective evaluation coefficient for the air conditioning comfort in the current driving cycle and corrects the compensation values ​​calculated in the current driving cycle based on this evaluation coefficient. The corrected compensation values ​​are then used to update the array.

[0085] The personalized synthesis module 56, based on the current vehicle air conditioning load demand characteristic value, queries the preset basic blower speed control curve and basic target outlet air temperature control curve to obtain the basic control value. Based on the current vehicle air conditioning load demand characteristic value, it queries the corrected personalized compensation data array to obtain the personalized compensation value. Combining the basic control value and the personalized compensation value, it calculates the final target blower speed and target outlet air temperature, and sends them to the actuator of the vehicle air conditioning system for control.

[0086] In summary, the user-feedback-based personalized temperature control system of the present invention can achieve low-cost, adaptive, and forgettable personalized calibration of vehicle air conditioning comfort based solely on the user's daily operating behavior, without the need for complex sensors and model training.

[0087] This invention also provides a personalized temperature control device based on user feedback, including a processor and a memory storing executable instructions for the processor. The processor is configured to execute steps of a personalized temperature control method based on user feedback via executing the executable instructions.

[0088] As shown above, the user-feedback-based personalized temperature control device of this invention can achieve low-cost, adaptive, and forgettable personalized calibration of vehicle air conditioning comfort based solely on the user's daily operating behavior, without the need for complex sensors and model training.

[0089] Those skilled in the art will understand that various aspects of the present invention can be implemented as systems, methods, or program products. Therefore, various aspects of the present invention can be specifically implemented in the following forms: a completely hardware implementation, a completely software implementation (including firmware, microcode, etc.), or a combination of hardware and software aspects, collectively referred to herein as a "circuit," "module," or "platform."

[0090] Figure 7 This is a schematic diagram of the personalized temperature control device based on user feedback according to the present invention. See below for reference. Figure 7 To describe an electronic device 600 according to this embodiment of the present invention. Figure 7 The electronic device 600 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0091] like Figure 7 As shown, the electronic device 600 is presented in the form of a general-purpose computing device. The components of the electronic device 600 may include, but are not limited to: at least one processing unit 610, at least one storage unit 620, a bus 630 connecting different platform components (including storage unit 620 and processing unit 610), a display unit 640, etc.

[0092] The storage unit stores program code, which can be executed by the processing unit 610 to perform the steps described in the method section of this specification according to various exemplary embodiments of the present invention. For example, the processing unit 610 can perform actions such as... Figure 1 The steps are shown in the figure.

[0093] Storage unit 620 may include readable media in the form of volatile storage units, such as random access memory (RAM) 6201 and / or cache memory 6202, and may further include read-only memory (ROM) 6203.

[0094] Storage unit 620 may also include a program / utility 6204 having a set (at least one) program module 6205, such program module 6205 including but not limited to: operating system, one or more application programs, other program modules and program data, each or some combination of these examples may include an implementation of a network environment.

[0095] Bus 630 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the multiple bus structures.

[0096] Electronic device 600 can also communicate with one or more external devices 700 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with electronic device 600, and / or with any device that enables electronic device 600 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 650. Furthermore, electronic device 600 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 660. Network adapter 660 can communicate with other modules of electronic device 600 via bus 630. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms.

[0097] This invention also provides a computer-readable storage medium for storing a program that, when executed, implements the steps of a personalized temperature control method based on user feedback. In some possible implementations, various aspects of the invention can also be implemented as a program product comprising program code that, when run on a terminal device, causes the terminal device to perform the steps described in the above-described method section of this specification according to various exemplary embodiments of the invention.

[0098] As shown above, the user-feedback-based personalized temperature control system of this invention can achieve low-cost, adaptive, and forgettable personalized calibration of vehicle air conditioning comfort based solely on the user's daily operating behavior, without the need for complex sensors and model training.

[0099] Figure 8 This is a schematic diagram of the structure of the computer-readable storage medium of the present invention. (Reference) Figure 8 As shown, a program product 800 for implementing the above-described method according to an embodiment of the present invention is described. It may employ a portable compact disc read-only memory (CD-ROM) and include program code, and may run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, the readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0100] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0101] Computer-readable storage media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable storage medium may also be any readable medium other than a readable storage medium that can transmit, propagate, or transfer a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0102] Program code for performing the operations of this invention can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0103] In summary, the purpose of this invention is to provide a personalized temperature control method, system, device, and storage medium based on user feedback, which can achieve low-cost, adaptive, and forgettable personalized calibration of vehicle air conditioning comfort based solely on the user's daily operating behavior, without the need for complex sensors and model training.

[0104] The above description, in conjunction with specific preferred embodiments, provides a further detailed explanation of the present invention. It should not be construed that the specific implementation of the present invention is limited to these descriptions. For those skilled in the art, various simple deductions or substitutions can be made without departing from the concept of the present invention, and all such modifications and substitutions should be considered within the scope of protection of the present invention.

Claims

1. A personalized temperature control method based on user feedback, characterized in that, Includes the following steps: S100. Identify the user identity of the currently driving vehicle, and load the corresponding personalized compensation data array from the local storage module according to the user identity. The personalized compensation data array includes at least a blower gear compensation value array and a target air outlet temperature compensation value array based on the vehicle air conditioning load demand characterization value. The blower gear compensation value is achieved by adjusting the blower gear, and the target air outlet temperature compensation value is achieved by adjusting the air conditioning set temperature. S200: Real-time monitoring of the vehicle's air conditioning system's operating mode and user behavior; When the air conditioning system is determined to be in cooling or heating mode, the system continuously monitors the user's adjustment of the blower speed and the user's adjustment of the air conditioning set temperature. S300: When a valid adjustment operation is detected by the user, the vehicle air conditioning load demand characterization value at the time of the adjustment operation is obtained; the amount of change in blower gear or air conditioning set temperature caused by the adjustment operation is calculated; and the blower gear compensation value or target air outlet temperature compensation value to be applied under the current vehicle air conditioning load demand characterization value is calculated according to the predefined learning rate corresponding to the current air conditioning working mode and the user adjustment object. The learning rate defines the compensation offset of the vehicle air conditioning load demand representation value corresponding to a unit change in user operation. S400. Update the calculated blower speed compensation value or target outlet air temperature compensation value to the personalized compensation data array corresponding to the current user identity, current air conditioning working mode and adjustment object, and store the updated array. S500, Apply confidence processing based on a time decay factor to the historical compensation values ​​stored in the personalized compensation data array, wherein the confidence decays over time; Obtain the user's subjective evaluation coefficient of the air conditioning comfort in the current driving cycle, and correct the compensation value calculated in the current driving cycle based on the evaluation coefficient. Use the corrected compensation value to update the array. S600. Based on the current vehicle air conditioning load demand characteristic value, query the preset control curve of the basic blower gear and the control curve of the basic target air outlet temperature to obtain the basic control value; based on the current vehicle air conditioning load demand characteristic value, query the corrected personalized compensation data array to obtain the personalized compensation value. The basic control value is combined with the personalized compensation value to calculate the final target blower speed and target air outlet temperature, and then sent to the actuator of the vehicle air conditioning system for control.

2. The method according to claim 1, characterized in that, Step S300 includes: S301. In cooling mode, when the user lowers or raises the blower speed, the vehicle air conditioning load demand characterization value is TAO. Cool Let the blower speed difference be BlowerLevel. Cool (d) - BlowerLevel Cool (d-1), where (d-1) represents the blower speed before adjustment, and d is the blower speed after adjustment. The learning rate (LearnRate) is the rate at which the blower speed is adjusted in cooling mode. Cool The value range is [-1, 0], LearnRate Cool = (-1 / 100) × (TAO MAX -TAO MIN ) / (D MAX -D MIN ), among which, TAO MAX This is the upper limit of the TAO value, TAO MIN D is the lower limit of the TAO value. MAX D is the upper limit of the blower speed. MIN This is the lower limit of the blower speed; S302, Calculate the blower speed compensation value TAOOffset in cooling mode. Cool = [BlowerLevel Cool (d)-BlowerLevel Cool [(d-1)]×LearnRate Cool and TAOOffset Cool Updated to TAO as blower gear compensation value. Cool The corresponding array position; S303. In heating mode, when the user lowers or raises the blower speed, the vehicle air conditioning load demand characterization value is TAO. Heat The learning rate (LearnRate) for adjusting the blower speed during heating. Heat The value range is [0, 1], and LearnRate Heat = (1 / 100) × (TAO MAX - TAO MIN ) / (D MAX -D MIN ); S304, Calculate the blower speed compensation value TAOOffset in heating mode. Heat = [BlowerLevel Heat (d)-BlowerLevel Heat [(d-1)]×LearnRate Heat and TAOOffset Heat Updated to TAO as blower gear compensation value. Heat The corresponding array position.

3. The method according to claim 1, characterized in that, Step S300 further includes: When the user adjusts the set temperature, the vehicle air conditioning load demand characterization value is TAO. TempSet The temperature difference is set as TempSet(t) - TempSet(t-1), where (t-1) represents the set temperature before adjustment and t is the set temperature after adjustment. The learn rate (LearnRate) of the air conditioner when adjusting the temperature is set. TempSet The defined range is [0,1], LearnRate TempSet = (1 / 100) × (TAO MAX - TAO MIN (Set upper temperature limit - Set lower temperature limit) Calculate the target temperature compensation TempSet Offset = LearnRate TempSet × [TempSet(t) - TempSet(t-1)], and the target outlet air temperature compensation value TempSet Offset Updated to TAO as the target outlet air temperature compensation value. TempSet The corresponding array position.

4. The method according to claim 1, characterized in that, In step S300, the process of determining whether a user performs a valid adjustment operation includes: anti-shake filtering processing. Starting from the user's first adjustment action, within a predetermined filtering time window, all subsequent adjustment operations are ignored. Only the blower speed value or air conditioner set temperature value that finally stabilizes at the end of the filtering time window is recorded and used as the state after the adjustment operation for compensation calculation.

5. The method according to claim 1, characterized in that, In step S500, applying confidence processing based on a time decay factor to the historical compensation values ​​stored in the personalized compensation data array, wherein the confidence decays over time, includes: associating a confidence coefficient Conf with each compensation value element in the personalized compensation data array, the confidence coefficient being updated according to an exponential decay law: Conf = exp(-λ × t), where λ is a configurable forgetting coefficient, and t is the time elapsed since the compensation value was recorded or last reinforced; when synthesizing personalized parameters, the historical compensation value retrieved from the array must first be multiplied by its current corresponding confidence coefficient Conf before use; In step S500, obtaining the user's subjective evaluation coefficient of the air conditioning comfort in the current driving cycle, and correcting the compensation value calculated in the current driving cycle based on the evaluation coefficient, and using the corrected compensation value to update the array, includes: obtaining the user's evaluation coefficient α of the current air conditioning comfort through the human-computer interaction interface at the end of the driving cycle or when the user actively triggers it, wherein the evaluation coefficient α has a value range of [0, 1]; multiplying all compensation values ​​calculated based on the user's operation in the current driving cycle by the evaluation coefficient α to obtain the corrected compensation value B. corrected = α × B raw B raw As the initial compensation value, the corrected compensation value B is then used. corrected Used to update the personalized compensation data array.

6. The method according to claim 5, characterized in that, Step S500 further includes maintaining the trend consistency of the compensation value array. After updating the personalized compensation data array, the trend of the elements in the array changing with the TAO value is checked. The overall trend of the final control parameters after superimposing the compensation value with the TAO value is checked and ensured to meet expectations: the blower speed is not increasing in the cooling TAO range and not decreasing in the heating TAO range; the target air outlet temperature is not decreasing in the entire TAO range. If the array update causes the above trend to be destroyed, the compensation value array is smoothed or adjusted to restore a logical trend.

7. The method according to claim 1, characterized in that, In step S600, calculating the personalized compensation value includes: Ultimate goal: Blower gear B final = Basic blower speed TAOBase Level + Confidence coefficient Conf × Historical blower gear compensation value B Level + This blower speed compensation value (BlowerLevel) Offset ; Final target air outlet temperature T final = Base target outlet air temperature TAOBase TempSet + Confidence coefficient Conf × Historical target temperature compensation value B TempSet + Target temperature compensation value TempSet Offset ; Among them, the basic blower speed TAOBase Level and the baseline target outlet air temperature TAOBase TempSet The historical blower gear compensation value B is obtained by querying the preset basic control curve corresponding to the current TAO value. Level and historical target temperature compensation value B TempSet The personalized compensation data array processed by step S500 is obtained by querying the current blower gear compensation value and the current target temperature compensation value, which are the compensation values ​​to be stored in the array after evaluation and correction by step S500 in the current driving cycle.

8. A personalized temperature control system based on user feedback, used to implement the personalized temperature control method based on user feedback as described in claim 1, characterized in that, include: An array loading module identifies the user identity of the currently driving vehicle and loads the corresponding personalized compensation data array from the local storage module based on the user identity. The personalized compensation data array includes at least a blower gear compensation value array and a target air outlet temperature compensation value array based on the vehicle's air conditioning load demand characterization value. The blower gear compensation value is achieved by adjusting the blower gear, and the target air outlet temperature compensation value is achieved by adjusting the air conditioning set temperature. The operation monitoring module monitors the vehicle's air conditioning system's operating mode and user operation behavior in real time. When the air conditioning system is determined to be in cooling or heating mode, the system continuously monitors the user's adjustment of the blower speed and the user's adjustment of the air conditioning set temperature. Establish a compensation module to obtain the vehicle air conditioning load demand characterization value at the time of the adjustment operation when a user performs a valid adjustment operation. Calculate the change in blower speed or change in air conditioning set temperature caused by the adjustment operation; based on the predefined learning rate corresponding to the current air conditioning working mode and the user adjustment object, calculate the blower speed compensation value or target air outlet temperature compensation value to be applied under the current vehicle air conditioning load demand characterization value. The learning rate defines the compensation offset of the vehicle air conditioning load demand representation value corresponding to a unit change in user operation. The array update module updates the calculated blower gear compensation value or target outlet air temperature compensation value into the personalized compensation data array corresponding to the current user identity, current air conditioning working mode and adjustment object, and stores the updated array. The evaluation and correction module applies a confidence level based on a time decay factor to the historical compensation values ​​stored in the personalized compensation data array, wherein the confidence level decays over time. Obtain the user's subjective evaluation coefficient of the air conditioning comfort in the current driving cycle, and correct the compensation value calculated in the current driving cycle based on the evaluation coefficient. Use the corrected compensation value to update the array. The personalized synthesis module queries the preset basic blower gear control curve and basic target outlet air temperature control curve based on the current vehicle air conditioning load demand characterization value to obtain the basic control value; and queries the corrected personalized compensation data array based on the current vehicle air conditioning load demand characterization value to obtain the personalized compensation value. The basic control value is combined with the personalized compensation value to calculate the final target blower speed and target air outlet temperature, and then sent to the actuator of the vehicle air conditioning system for control.

9. A personalized temperature control device based on user feedback, characterized in that, include: processor; A memory in which executable instructions of the processor are stored; The processor is configured to perform the steps of the personalized temperature control method based on user feedback as described in any one of claims 1 to 7 by executing the executable instructions.

10. A computer-readable storage medium for storing a program, characterized in that, When the program is executed by the processor, it implements the steps of the personalized temperature control method based on user feedback as described in any one of claims 1 to 7.

Images