Electric blanket system capable of adjusting calorific value by self-adaption to environment temperature

Abstract

The invention relates to the technical field of smart home, and discloses an electric blanket system capable of adjusting calorific value by self-adaption to environment temperature, comprising a sleep sensing module used for collecting physiological signal data of a user; the state recognition module is used for recognizing the current sleep state of the user; the temperature target generation module is used for determining a corresponding target temperature value according to the current sleep state; the control calculation module is used for calculating a control instruction of each heating area; the multi-area heating execution module is used for performing heating control on the plurality of independent heating areas; and the temperature acquisition and feedback module is used for acquiring the real-time temperature of each heating area and feeding back the temperature to the control calculation module. Through linkage of the AI housekeeper and the external electronic bracelet, adaptive adjustment of the intelligent temperature control system is realized, a temperature control strategy is dynamically optimized according to real-time temperature data, user behaviors and environmental changes, limitation of a traditional static scheme is avoided, personalized temperature adjustment is provided, and flexibility and comfort are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of smart home, and specifically to an adaptive ambient temperature-regulated heat-generating electric blanket system. Background Art

[0002] Currently, the temperature control technology of electric blankets mainly adopts a preset temperature regulation scheme based on a schedule or a simple temperature control switch. Many traditional electric blanket systems use a single temperature sensor to monitor the temperature of the entire device, and temperature changes can often only be achieved through manual adjustment. Common systems usually heat according to a fixed power output or time period, without considering the actual needs of users in different sleep stages or environmental conditions. In addition, some traditional temperature control systems also have a relatively single heating strategy, usually only setting a global temperature control mode, and failing to provide users with a flexible and personalized temperature control experience.

[0003] However, the existing technologies have obvious deficiencies in terms of temperature control accuracy, energy efficiency management, and user experience. First, the use of a single-point temperature sensor makes the entire temperature control system unable to comprehensively reflect the temperature changes in different regions, resulting in uneven temperature control. Especially in traditional systems, the system often cannot make flexible adjustments according to the different needs of the user's sleep stage and body parts, thus affecting the user's comfort. Second, due to the lack of an adaptive learning mechanism, traditional systems usually cannot be optimized in real time according to the user's historical data or behavior changes. This makes the system may lose efficiency after long-term use and cannot continuously meet the personalized needs of users. Finally, traditional systems often use simple power switch control, while ignoring the real-time monitoring and dynamic adjustment of current changes, resulting in excessive energy consumption and certain safety hazards. Summary of the Invention

[0004] Aiming at the deficiencies of the existing technologies, the present invention provides an adaptive ambient temperature-regulated heat-generating electric blanket system, which solves the problems of inaccurate temperature control, lack of personalized adjustment, and adaptive optimization in traditional electric blanket systems.

[0005] To achieve the above objectives, the present invention is realized through the following technical solutions: An adaptive ambient temperature-regulated heat-generating electric blanket system, comprising: A sleep perception module, configured to collect physiological signal data of a user; A state recognition module, connected to the sleep perception module, configured to identify the current sleep state of the user according to the physiological signals; A temperature target generation module, connected to the state recognition module, configured to determine a corresponding target temperature value according to the current sleep state; A control calculation module, connected to the temperature target generation module and the temperature acquisition and feedback module, configured to calculate control instructions for each heating region according to the target temperature and the current temperature state; A multi - zone heating execution module, which is connected to the control calculation module and is used to perform heating control on multiple independent heating zones respectively according to the control instructions; A temperature acquisition and feedback module, which is connected to the control calculation module and is used to obtain the real - time temperature of each heating zone and feedback the temperature to the control calculation module to achieve closed - loop regulation.

[0006] Preferably, the sleep perception module includes: A physiological signal acquisition unit, which is used to acquire the user's heart rate signal, body movement signal and breathing signal; A data pre - processing unit, which is used to filter, denoise and standardize the physiological signals for use by the state recognition module.

[0007] Preferably, the state recognition module includes: A state inference unit, which analyzes the physiological signal sequences at multiple moments based on a probability model and calculates the occurrence probabilities of various sleep states; A state decision unit, which is used to select the sleep state with the highest probability from all candidate states as the current state output.

[0008] Preferably, the temperature target generation module includes: A state - temperature mapping unit, which is used to store the target temperature values corresponding to different sleep states; The sleep states and target temperature values are specifically: Light sleep state, the target temperature value is 22℃ - 24℃; Deep sleep state, the target temperature value is 20℃ - 22℃; Rapid eye movement sleep state, the target temperature value is 21℃ - 23℃; Wakeful state, the target temperature value is 23℃ - 25℃; A temperature calling unit, which is used to call and output the corresponding target temperature value according to the current sleep state identified by the smart bracelet through the AI butler with a built - in general AI model.

[0009] Preferably, the control calculation module includes: A heat modeling unit, which establishes a temperature change model of the electric blanket in the spatial position and time dimensions based on the heat conduction principle; A control strategy generation unit, which is used to construct an optimization objective function of energy consumption and temperature deviation according to the relationship between the current temperature, target temperature and heating power; A heating power calculation unit, which is used to solve the optimization objective function to obtain the power control instructions for each heating zone.

[0010] Preferably, the multi - zone heating execution module includes: A PWM modulation unit, configured to convert the heating power control instruction into a corresponding PWM signal; A regional heating drive unit, configured to apply the PWM signal to the heating elements in multiple heating regions to achieve independent heating control for each region.

[0011] Preferably, the temperature acquisition and feedback module includes: A multi-point temperature sensing unit, configured to acquire temperature data at multiple spatial positions of the electric blanket; A temperature feedback interface unit, configured to transmit the acquired temperature information to the control calculation module to participate in the closed-loop regulation of the heating power.

[0012] Preferably, the state inference unit includes: A feature extraction mechanism, configured to extract time-series features and frequency-domain features from physiological signals such as heart rate, body movement, and respiration; a pattern recognition mechanism, which uses deep learning algorithms to train the extracted features to accurately identify different sleep states; a probability calculation mechanism, which calculates the occurrence probability of the current sleep state based on the model and calculates the occurrence probability of each sub-stage through a multi-layer neural network, and finally outputs the probability distribution of the current sleep state.

[0013] Preferably, the thermal modeling unit includes: A heat conduction calculation mechanism, which establishes a temperature change model of the electric blanket in different spatial positions and time dimensions based on the heat conduction principle, considering the heat conduction coefficients, heat transfer rates, and ambient temperatures of different regions; A temperature deviation feedback mechanism, which monitors the real-time temperature deviation of each heating region and feeds it back to the control calculation module; an optimization target generation mechanism, which dynamically adjusts the heating power control strategy by constructing an optimization target function between energy efficiency and temperature deviation.

[0014] Preferably, the PWM modulation unit includes the following mechanisms: A PWM signal generation mechanism, configured to generate a PWM signal according to the power regulation instruction generated by the control calculation module and adjust the power of the heating element; A PWM signal adjustment mechanism, configured to dynamically adjust the duty cycle of the PWM signal according to the temperature feedback signal to ensure that the temperature of each heating region is stable within a comfortable range; The comfortable range temperature interval is 20°C to 25°C; A dynamic response mechanism, which adjusts according to the real-time temperature changes in each region to ensure that the temperature fluctuation is controlled within the set target temperature range.

[0015] The present invention provides an electric blanket system with self-adaptive ambient temperature regulation of heat generation. It has the following beneficial effects: 1. The present invention realizes the adaptive adjustment function of the intelligent temperature control system by introducing an AI butler to connect with an external electronic bracelet. The AI butler dynamically optimizes the temperature control strategies for each area based on real-time temperature data, user behavior patterns, and environmental changes. Compared with the traditional static temperature control solutions in the prior art, the introduction of the connection between the AI butler and the external electronic bracelet enables the system to make personalized adjustments according to user needs, improving the flexibility and comfort of temperature control and avoiding the cumbersome steps of manual intervention and setting.

[0016] 2. The present invention achieves the technical effect of accurate temperature monitoring and control through a multi-point temperature sensor combined with the intelligent correction mechanism of the AI butler. Compared with the solutions in the prior art that only rely on single-point data collection and simple control strategies, the multi-point temperature monitoring system of the present invention can real-time feedback the temperature of each heating area, and the AI butler makes dynamic corrections based on this data, avoiding problems such as uneven local temperature control, too high or too low temperature, and making the temperature adjustment for each area more accurate and timely.

[0017] 3. The present invention achieves the technical effect of more efficient energy consumption management and safety protection through a control scheme combining PWM modulation and current feedback monitoring technology. Compared with the single power control method in the prior art, the present invention, through the real-time adjustment of the AI butler, combines the current sampling and feedback mechanism to intelligently adjust the power output of each area, ensuring more accurate power control and lower energy consumption. At the same time, the system can also real-time detect current changes, prevent overload, and improve safety and system stability.

[0018] 4. The present invention achieves the technical effect of adaptive optimization of intelligent temperature control through the feedback mechanism of behavior data and temperature feedback. Most of the prior art lacks a learning mechanism and cannot adapt to changes in user needs for a long time, while the AI butler of the present invention can continuously optimize the adjustment strategy according to historical temperature control data and user behavior, gradually adapting to the needs of different users, so that the temperature control performance of the system remains efficient and accurate during long-term use. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 is the system module framework diagram of the present invention; Figure 2 is the schematic diagram of the sleep perception module of the present invention; Figure 3 is the schematic diagram of the state recognition module of the present invention; Figure 4 is the schematic diagram of the temperature target generation module of the present invention; Figure 5 is the schematic diagram of the control calculation module of the present invention; Figure 6 is the schematic diagram of the multi-area heating execution module of the present invention; Figure 7 Schematic diagram of the temperature acquisition and feedback module of the present invention. Specific embodiments

[0020] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0021] Please refer to the attached Figure 1 - attached Figure 7 , the embodiment of the present invention provides an adaptive ambient temperature-regulated heating electric blanket system, including: A sleep perception module for collecting physiological signal data of a user; Specifically, the core function of the sleep perception module is to accurately identify the current sleep state of the user by collecting physiological signal data in real time. The role of this module is to provide basic data for subsequent temperature regulation, ensuring that the electric blanket system can make effective temperature adjustments according to the actual needs of the user. Through effective connection with the state recognition module, the physiological data provided by the sleep perception module is used for further state inference and decision-making, ultimately achieving the optimal temperature control effect.

[0022] In this embodiment, the sleep perception module includes multiple sub-modules, and the most important ones are the physiological signal acquisition unit and the data preprocessing unit. Specifically, the physiological signal acquisition unit is used to collect physiological data including the user's heart rate signal, body movement signal, and breathing signal. These signals have different characteristics in different sleep stages. By analyzing these characteristics, the current sleep state of the user can be inferred. The acquisition of physiological signals is completed through various sensors, which are generally placed inside the electric blanket and closely attached to the user's body to ensure the accuracy and real-time nature of the signals.

[0023] In some embodiments, the physiological signal acquisition unit includes a heart rate sensor, an acceleration sensor, and an airflow sensor. The heart rate sensor is used to monitor the user's heart rate changes in real time, the body movement signal is obtained through the acceleration sensor, and the breathing signal is detected by the airflow sensor. The data collected by these sensors can provide multi-dimensional user sleep information.

[0024] As an option, the data preprocessing unit filters, denoises, and normalizes the collected physiological signals. Specifically, physiological signals are often disturbed by noise, so they need to be filtered to remove high-frequency noise and other interference signals. The denoised signals are convenient for subsequent processing and analysis, ensuring the accuracy of sleep state recognition. Filtering techniques can use low-pass filters or band-pass filters to filter out high-frequency or low-frequency noise. Normalization processing is to uniformly quantify the signals collected by different sensors, so as to facilitate comparison and analysis by subsequent modules.

[0025] In a specific implementation, the original signals collected by the physiological signal acquisition unit are preprocessed and then transmitted to the state recognition module for further analysis. The state recognition module will combine the model of the sleep stage to deeply mine these data and identify the sleep state of the user. The specific filtering algorithms and normalization methods used in the preprocessing process vary according to the specific scenario of the application, but their core goal is always to ensure the accuracy and effectiveness of the data.

[0026] For the processing of physiological signals, filtering methods based on certain statistical models can be used, such as Kalman filtering or other time series analysis methods. For heart rate signals body movement signals and respiratory signals their filtering process can be expressed by the following formula: where, α1 is the filtering coefficient; usually the value range is between 0 and 1; it is used to balance the weights of the current data and the data at the previous moment; the signal obtained after filtering is used for subsequent sleep state recognition; t is a certain moment.

[0027] In a possible implementation, after the physiological signals are filtered, through a normalization algorithm (such as Z-score normalization), each signal can be compared and processed under a unified dimension: where, X1 is the original signal value; μ is the mean value of the signal; σ is the standard deviation of the signal; the obtained Z value after normalization can eliminate the scale difference of the signal, making the data more suitable for subsequent pattern recognition and state inference.

[0028] The state recognition module, which is connected to the sleep perception module, is used to identify the current sleep state of the user according to the physiological signals; Specifically, the function of the state recognition module is to identify the user's current sleep state based on the physiological signals of the user collected by the sleep perception module. Specifically, the state recognition module analyzes the physiological signal sequences at multiple moments, calculates the occurrence probabilities of different sleep states, and determines the user's current sleep state according to the principle of probability maximization. This process plays a crucial role in the subsequent generation and adjustment of the temperature target. Through close cooperation with the sleep perception module, the state recognition module can provide accurate input data for the control calculation module, thereby realizing the adaptive adjustment of the electric blanket system.

[0029] In this embodiment, the state recognition module includes a state inference unit and a state decision unit. The state inference unit analyzes the physiological signals at multiple moments through a probability model and calculates the occurrence probability of each sleep state. The state decision unit then selects the sleep state with the maximum probability as the current state output according to the above probability values.

[0030] In some embodiments, the state inference unit uses an algorithm based on deep learning for signal pattern recognition. Specifically, a deep neural network (DNN) or a convolutional neural network (CNN) is applied to the pattern recognition of physiological signals. For example, the heart rate signal, body movement signal, and respiratory signal are used as inputs. After extracting features through the deep neural network, the model is trained to determine the sleep stage of the user.

[0031] The occurrence probability of each sleep state can be calculated through a probability model based on time series. Generally, a Markov process or a hidden Markov model (HMM) is used to model different sleep states. The transition probability matrix and emission probability matrix of the hidden Markov model are used to describe the transition law of the system from one sleep state to another.

[0032] In this model, the state transition equation is: P(S t |S t-1 )=α2·P(S t |S t-1 )+(1-α2)·P(S t ); where P(S t |S t-1 ) represents the probability that the sleep state at time t - 1 is S t-1 and the system transitions to the sleep state S t at the current time t; α2 is the smoothing coefficient.

[0033] In a possible implementation, the state decision unit selects the most likely sleep state based on the maximum a posteriori probability (MAP) principle. Suppose there are multiple candidate states S1, S2, …, Sn at time t, then the current sleep state S cur can be calculated by the following formula: where P(S i |X) is the posterior probability of the sleep state S i occurring given the input signal X2. By calculating the posterior probability, the state decision unit selects the state corresponding to the maximum probability as the current state output.

[0034] Generally, the state recognition module needs to process not only a single physiological signal, but a combination of multiple signals. For this reason, the state inference unit can perform more accurate state prediction by fusing multiple sensor signals (such as heart rate, body movement, breathing, etc.). For example, when there is more body movement, it may correspond to the light sleep state, and when the heart rate fluctuates greatly, it may correspond to the rapid eye movement (REM) sleep stage.

[0035] As an option, the state recognition module can also combine environmental factors (such as temperature, humidity, etc.) for comprehensive analysis to further improve the recognition accuracy. Under different temperature conditions, the physiological responses of the human body will also be different, which may affect the recognition effect of the sleep state.

[0036] Specifically, the state inference unit is trained through a deep learning model so that the model can automatically learn the mapping relationship from the input signal to the sleep state. Through large-scale data training, the system can adapt to the physiological characteristics of different individuals, thus ensuring stability and accuracy in various scenarios.

[0037] In a possible implementation, the training of the model can adopt the method of transfer learning. By obtaining the physiological signal data of users from multiple data sources, the model is pre-trained on a large-scale dataset and fine-tuned with a small amount of individualized data. In this way, the personalized characteristics of different users can be quickly adapted, thereby improving the universality of the system.

[0038] A temperature target generation module, which is connected to the state recognition module and is used to determine the corresponding target temperature value according to the current sleep state; Specifically, the role of the temperature target generation module is to generate the corresponding target temperature value according to the current sleep state of the user, so as to provide a basis for temperature adjustment for the control calculation module. Through close cooperation with the aforementioned sleep perception module and state recognition module, the temperature target generation module can automatically adjust the temperature of the electric blanket according to the physiological state of the user and environmental requirements to ensure the comfort and health needs of the user in different sleep stages.

[0039] The temperature acquisition and feedback module monitors the temperature of each area of the electric blanket in real time through multiple sensors. Each sensor sends the captured temperature data to the AI butler, which predicts and analyzes the temperature change trend of each area and the user's comfort requirements based on the collected temperature information and the historical data model. The AI butler not only simply reads the data during acquisition, but also uses deep learning or fuzzy control algorithms to dynamically correct the data and generate corresponding control instructions.

[0040] For example, when the AI butler detects that the temperature of a certain area is too high or too low through external devices such as an electronic bracelet and other detections, it not only makes adjustments based on the current real-time data, but also makes personalized adjustments by referring to the user's past behavior patterns (such as reducing the foot temperature during deep sleep). Behind each temperature data feedback is actually the accurate calculation of the user's needs by the AI butler.

[0041] The temperature feedback interface unit of the temperature acquisition and feedback module transmits the temperature data collected by the sensor to the AI butler in real time. The AI butler not only responds based on the current temperature data, but also predicts the trend of temperature change through cooperation with the control calculation module. For example, when the temperature of a certain area is rising rapidly, the AI butler can predict in advance that the temperature may reach the set critical value and adjust the heating power in advance according to the data feedback to avoid discomfort caused by too high temperature.

[0042] In some embodiments, the temperature feedback interface unit can use a high-speed data bus (such as SPI, I2C, etc.) to ensure the stable and real-time transmission of temperature data. After receiving these data, the AI butler further makes refined temperature control adjustments to ensure that the temperature of each area always meets the user's expectations.

[0043] Through the deep learning of the AI butler and real-time data input, the temperature acquisition and feedback module not only provides the basic temperature acquisition function for the system, but also greatly improves the adaptability and predictability of the system. When the AI butler infers the user's current sleep stage or special needs through temperature data, the temperature control strategy will be adjusted immediately. For example, the AI butler analyzes the temperature feedback and the user's behavior data to calculate that the temperature of the back area needs to be reduced during deep sleep, and the temperature of the foot area needs to be increased appropriately when waking up.

[0044] Such adjustments are not simply immediate reactions, but are driven by the personalized learning model established by the AI butler. Each change in temperature feedback adds new data to the learning library of the AI butler, enabling the system to self-optimize and reduce manual intervention and adjustment.

[0045] Moreover, the temperature target generation module is mainly composed of a state temperature mapping unit and a temperature calling unit. The state temperature mapping unit is responsible for storing the target temperature values corresponding to different sleep states, while the temperature calling unit calls and outputs the corresponding target temperature value according to the current sleep state information transmitted by the state recognition module.

[0046] Generally, the state temperature mapping unit is a database or a mapping table used to record and manage the correspondence between various sleep states and the corresponding target temperatures. Specifically, each sleep state, such as light sleep state, deep sleep state, rapid eye movement (REM) sleep state, and wakefulness state, has a specific target temperature range, which is set according to the physiological characteristics of the human body and comfort requirements.

[0047] For example, during the light sleep stage, the human body needs a certain temperature to maintain a mild state of relaxation, and the target temperature is usually set between 22°C and 24°C; during the deep sleep stage, the body's metabolism is lower and it is less sensitive to external temperatures, so the target temperature is generally set between 20°C and 22°C; for the rapid eye movement sleep stage, since the brain is active at this time and the human body is more sensitive to environmental temperatures, the target temperature is set at 21°C to 23°C; the wakefulness state requires a higher level of comfort, and the target temperature is usually in the range of 23°C to 25°C.

[0048] As an option, the state temperature mapping unit can be dynamically adjusted based on historical data and user feedback. For example, by collecting long-term sleep data and user feedback, the system can gradually optimize the target temperature settings for different sleep states to improve comfort and energy-saving effects.

[0049] In a possible implementation, the temperature calling unit queries and outputs the corresponding target temperature value according to the current sleep state information transmitted from the state recognition module. The function of the temperature calling unit is similar to a table lookup operation. Specifically, given the current sleep state S current , the temperature target generation module outputs the target temperature T target , which is represented by the following formula: T target = f(S current ); where f(S current ) is the target temperature value found and output from the state temperature mapping unit according to the current sleep state S current . This process ensures that each sleep state can be adjusted to the corresponding temperature according to the preset temperature range.

[0050] Specifically, the target temperature range in the state temperature mapping unit can be dynamically adjusted according to individual differences. For example, different users may have different temperature requirements, and the system can optimize the target temperature range through personalized settings. Based on the user's historical data, the system can automatically learn and predict the optimal temperature requirements of each user at different sleep stages.

[0051] In some embodiments, the temperature target generation module not only generates the target temperature based on the current sleep state, but also can be adjusted in combination with external environmental conditions (such as room temperature, humidity, etc.). Specifically, when the environmental temperature is too low, the system can automatically increase the target temperature to ensure that the user stays within a comfortable range; while in the case of a higher environmental temperature, the system may reduce the target temperature to improve comfort and reduce energy consumption.

[0052] For example, assuming the environmental temperature is T env , in some cases, the target temperature T target can be adjusted by the following formula: T target = T state + β(T env - T base ); Wherein, T target is the reference target temperature set according to the current sleep state; T base is the preset reference environmental temperature; β is the adjustment coefficient used to control the influence of the environmental temperature on the target temperature. Through this adjustment formula, the system can automatically adapt under changing environmental conditions to ensure that the user is always in the optimal comfort range.

[0053] The control calculation module, which is connected to the temperature target generation module and the temperature acquisition and feedback module, is used to calculate the control instructions for each heating area according to the target temperature and the current temperature state; Specifically, the function of the control calculation module is to calculate the heating power control instructions for each heating area based on the target temperature value output by the temperature target generation module and the real-time temperature data provided by the current temperature acquisition and feedback module. Through these control instructions, the system can accurately adjust the heating power of different areas of the electric blanket, thereby achieving precise temperature control and closed-loop regulation. The control calculation module is the core of the entire temperature regulation system, and it ensures the comfort of the user in different sleep stages by optimizing the control strategy.

[0054] In this embodiment, the control calculation module includes a thermal modeling unit, a control strategy generation unit, and a heating power calculation unit. The thermal modeling unit establishes a temperature change model of the electric blanket based on the principle of heat conduction. The control strategy generation unit constructs an optimization objective function according to the difference between the current temperature and the target temperature. Finally, the heating power calculation unit solves the power control instruction according to the optimization objective function to ensure that the temperature of each heating area reaches the expected value.

[0055] Generally, the task of the thermal modeling unit is to establish an accurate temperature change model, which should consider the heat conduction characteristics of each heating area inside and on the surface of the electric blanket. Specifically, the thermal modeling unit simulates the temperature change in different spatial positions and time dimensions based on the heat conduction equation. For each heating area, the thermal modeling unit should calculate the temperature distribution according to the thermal conductivity of the material, the heat transfer rate, and the geometric shape of the area.

[0056] For example, assume that the temperature change of a certain heating area of the electric blanket can be described by the following heat conduction equation: where T(x,t) is the temperature at position x at time t; is the thermal diffusivity; Q(x,t) is the heat source power at this position. This equation is solved to obtain the temperature change of each area at different time points.

[0057] In a possible implementation, the thermal modeling unit combines the actual structure and material parameters of the electric blanket, discretizes each heating area, and solves the temperature distribution by numerical methods (such as the finite difference method or the finite element method). In this way, the control calculation module can obtain the temperature prediction values of different areas in real time.

[0058] The function of the control strategy generation unit is to generate an optimization objective function for temperature regulation according to the difference between the current temperature and the target temperature. Specifically, the control strategy generation unit constructs an optimization objective function between energy efficiency and temperature deviation by analyzing the deviation between the current temperature state and the target temperature. This function takes into account both the temperature error and the use efficiency of the heating power to achieve the balance between temperature and energy efficiency.

[0059] The optimization objective function can be expressed as: where J is the optimization objective function; T i,cur and T i,target are the current temperature and the target temperature of the i-th area respectively; P iis the power of the i-th region; w1 and w2 are weight coefficients; n is a constant. The first term of this objective function represents the square of the temperature deviation, and the second term penalizes excessive power usage. By solving this objective function, the control strategy generation unit can obtain the optimal heating power command for each heating region.

[0060] In some embodiments, the task of the heating power calculation unit is to solve the heating power required for each heating region according to the optimized objective function output by the control strategy generation unit. By solving the optimized objective function, the heating power control command for each region can be obtained, and then the power output of each heating region of the electric blanket can be adjusted. Specifically, the heating power calculation unit uses numerical solution methods, such as the gradient descent method or the optimization algorithm, to solve the power control commands for each region.

[0061] Generally, the heating power calculation unit adjusts the power control of each region according to the objective function generated by the control strategy through the backpropagation algorithm. The optimization process usually uses the following iterative formula to calculate the optimal power command: where, P i (t) is the power of the i-th region at time t; η is the learning rate; is the gradient of the optimized objective function with respect to power.

[0062] The multi-region heating execution module, which is connected to the control calculation module, is used to perform heating control on multiple independent heating regions respectively according to the control instructions; Specifically, the main function of the multi-region heating execution module is to perform independent heating control on multiple independent heating regions of the electric blanket according to the heating power control instructions generated by the control calculation module. The temperature adjustment of each heating region is precisely controlled according to the user's current sleep state and specific needs, so as to achieve comfortable and efficient temperature adjustment. The multi-region heating execution module works closely with the temperature target generation module and the control calculation module to ensure that the temperature distribution of the entire electric blanket system is uniform and meets the preset standards.

[0063] In this embodiment, the multi-region heating execution module includes a PWM modulation unit, a region heating drive unit, and a current detection unit. These units work together to ensure that the heating power of each heating region is accurate, real-time, and safe through precise signal regulation and feedback mechanisms.

[0064] Under normal circumstances, the task of the PWM modulation unit is to convert the power control instructions output by the control calculation module into corresponding pulse-width modulation (PWM) signals. The PWM signals can precisely adjust the power of the electrothermal elements, thereby controlling the temperature of the heating area. Specifically, the PWM signals generated by the PWM modulation unit adjust the duty cycle of the electrothermal elements according to the power requirements provided by the control calculation module, so as to achieve temperature regulation.

[0065] In some embodiments, the PWM signal generation mechanism of the PWM modulation unit is based on the power adjustment instructions transmitted by the control calculation module. Specifically, assume that the heating power calculated by the control calculation module for a certain heating area is P i , the duty cycle D of the PWM signal generated by the PWM modulation unit according to this power value can be calculated by the following formula: where P max is the maximum power of the electrothermal element; P i is the calculated current heating power; D is the duty cycle, which controls the proportion of the working time of the electrothermal element. By adjusting the duty cycle, the system can adjust the heating power of each area in real time.

[0066] As an option, the function of the area heating drive unit is to apply the PWM signal to the electrothermal elements of multiple heating areas. The heating power of each electrothermal element is adjusted by the PWM signal, and this signal realizes the real-time control of the electrothermal element through the area heating drive unit. The area heating drive unit can control the temperature of each heating area by controlling the time when the current flows through the heating element.

[0067] In a possible implementation, the area heating drive unit uses an efficient electronic drive circuit to realize the control of the electrothermal element. Through this drive circuit, the system can independently distribute power among different heating areas, thereby realizing multi-area independent heating. In this process, the magnitude of the current is closely related to the duty cycle of the PWM signal, ensuring the accuracy and stability of temperature regulation.

[0068] The current detection unit is used to monitor the current situation of the electrothermal elements in each heating area in real time. This unit can detect the change of the current and ensure that the electrothermal elements work within a safe range. The current detection unit collects current data through precise sensors and feeds it back to the control calculation module for real-time power adjustment and temperature regulation.

[0069] For example, when the current in a certain area exceeds the preset safety value, the current detection unit can trigger a safety mechanism to stop the current supply or reduce the power output. Specifically, the current detection unit can measure the magnitude of the current through a current sensor and calculate the power P of the current area i, and is compared with the power demand through the following formula: P i = V·I; where P i is the power of the i-th heating area; V is the voltage; I is the current, and the current is proportional to the power. In this way, the current detection unit can monitor the power conditions of each heating area in real time and ensure that it operates within a safe range.

[0070] In some embodiments, to ensure the safety of the electric blanket system, the current detection unit further includes a fault detection mechanism. Specifically, when the current detection unit detects abnormal current or too high temperature, the system will automatically trigger the safety protection mechanism. This mechanism may include power-off protection, temperature limitation or power adjustment strategies to ensure that the system will not overheat or have electrical faults.

[0071] For example, when the current exceeds a certain threshold I max , the system can immediately cut off the power or limit the power output. The power-off protection mechanism can timely detect abnormal situations through the current detection unit to prevent system damage or potential safety hazards.

[0072] Specifically, the design of the multi-region heating execution module can fully meet the needs of different users. For example, some users may be more sensitive to a certain part of their body during sleep and require a higher heating power. By adjusting the duty cycle of the PWM signal and current drive control, the system can achieve personalized temperature control within the region, enabling each user to obtain the most comfortable sleep experience according to their own needs.

[0073] In some embodiments, the region heating drive unit not only controls the temperature of each region, but also takes into account the heat accumulation effect of the electric blanket. When a certain region is in a high-power working state for a long time, the region heating drive unit can avoid local overheating and ensure the overall comfort of the electric blanket by reducing the power or decreasing the duty cycle.

[0074] The temperature acquisition and feedback module, which is connected to the control calculation module, is used to obtain the real-time temperature of each heating area and feedback the temperature to the control calculation module to achieve closed-loop regulation; Specifically, the core task of the temperature acquisition and feedback module is to monitor the temperature changes of each heating area of the electric blanket in real time and feedback the acquired temperature information to the control calculation module. The accuracy of temperature feedback is crucial for the closed-loop control of the system. Through the temperature acquisition and feedback module, the control calculation module can adjust the power control instruction in real time, so as to ensure that the temperature of each region is maintained within the set target temperature range. This module closely cooperates with the aforementioned multi-region heating execution module and control calculation module to complete the dynamic regulation of the system.

[0075] In this embodiment, the temperature acquisition and feedback module includes a multi-point temperature sensing unit and a temperature feedback interface unit. The multi-point temperature sensing unit is used to collect temperature data in different areas of the electric blanket, and the temperature feedback interface unit transmits this data to the control calculation module to participate in the closed-loop regulation of the heating power.

[0076] Generally, the temperature acquisition and feedback module monitors the temperature of different areas of the electric blanket through multiple temperature sensors. Each sensor is located at a different position on the electric blanket to ensure the comprehensiveness and accuracy of the temperature data. By collecting the temperatures at multiple positions, the system can comprehensively monitor the overall temperature distribution of the electric blanket.

[0077] In some embodiments, the temperature sensors are thermocouples, thermistors, or digital temperature sensors. Each temperature sensor has a different working principle, but they can all accurately measure the temperature changes at their respective positions. For example, a thermocouple uses the thermoelectric effect of metals to generate a voltage, which is then converted into a temperature signal; while a thermistor measures temperature based on the characteristic that its resistance changes with temperature.

[0078] Specifically, the temperature sensing unit feeds back the collected temperature data T i to the temperature feedback interface unit and converts it into the power adjustment signal required for the heating element through the following formula: P i = f(T i , T target ); where P i is the power control instruction for the i-th area; T i is the actual temperature of the current area; T target is the target temperature value. This formula adjusts the power to ensure that the temperature of each heating area approaches the target temperature.

[0079] The function of the temperature feedback interface unit is to transmit the temperature information collected by the multi-point temperature sensing unit to the control calculation module. Generally, the temperature data is transmitted to the control calculation module wirelessly or wired. To ensure the stability and real-time nature of the transmission, the temperature feedback interface unit adopts an efficient communication protocol to ensure that each temperature data reaches the control calculation module in a timely manner.

[0080] In a possible implementation, the temperature feedback interface unit uses digital signal processing technologies (such as SPI, I2C, or CAN bus) to transmit the temperature data. Through these high-speed data buses, the system can update the temperature information of each heating area in real time and quickly adjust the power control instructions, thereby achieving precise temperature regulation.

[0081] Although embodiments of the present invention have been shown and described, those of ordinary skill in the art will appreciate that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An electric blanket system that can adjust the heating value based on the self-adaptive ambient temperature, characterized in that: include: Sleep sensing module, used to collect the user's physiological signal data; A state recognition module, which is connected to the sleep sensing module and is used to recognize the current sleep state of the user according to the physiological signal; A temperature target generation module, which is connected to the state recognition module and is used to determine a corresponding target temperature value according to the current sleep state; A control calculation module, which is connected to the temperature target generation module and the temperature acquisition feedback module, and is used to calculate the control instructions of each heating area according to the target temperature and the current temperature state; A multi-zone heating execution module, which is connected to the control calculation module and is used to perform heating control on multiple independent heating zones according to the control instructions; The temperature acquisition feedback module is connected to the control calculation module to obtain the real-time temperature of each heating area and feed the temperature back to the control calculation module to achieve closed-loop regulation.

2. The self-adaptive environment temperature regulating heating electric blanket system according to claim 1, characterized in that: The sleep sensing module comprises: A physiological signal acquisition unit, used to collect the user's heart rate signal, body movement signal and breathing signal; The data preprocessing unit is used to filter, denoise and standardize the physiological signal for use by the state recognition module.

3. The self-adaptive environment temperature regulating heating electric blanket system according to claim 1, characterized in that: The state recognition module comprises: The state inference unit analyzes the physiological signal sequences at multiple moments based on the probability model and calculates the probability of occurrence of each sleep state; The state decision unit is used to select the sleep state with the highest probability from all candidate states as the current state output.

4. The self-adaptive environment temperature regulating heating electric blanket system according to claim 1, characterized in that: The temperature target generation module includes: A state temperature mapping unit, used to store target temperature values ​​corresponding to different sleep states; The sleeping state and target temperature value are specifically: In light sleep state, the target temperature is 22℃~24℃; In deep sleep state, the target temperature is 20℃~22℃; Rapid eye movement sleep state, the target temperature is 21℃~23℃; In the awake state, the target temperature is 23℃~25℃; The temperature calling unit is used to call and output the corresponding target temperature value through the AI ​​butler with a built-in general AI model according to the current sleep state identified by the electronic bracelet.

5. The self-adaptive environment temperature regulating heating electric blanket system according to claim 1, characterized in that: The control calculation module comprises: Thermal modeling unit, which establishes the temperature change model of the electric blanket in spatial position and time dimension based on the principle of heat conduction; A control strategy generation unit, used to construct an optimization objective function of energy consumption and temperature deviation according to the relationship between the current temperature, the target temperature and the heating power; The heating power calculation unit is used to solve the optimization objective function to obtain the power control instructions of each heating area.

6. The self-adaptive environment temperature regulating heating electric blanket system according to claim 1, characterized in that: The multi-zone heating execution module includes: A PWM modulation unit, used to convert the heating power control instruction into a corresponding PWM signal; The regional heating driving unit is used to apply the PWM signal to the electric heating elements of multiple heating areas to achieve independent heating control of each area.

7. The self-adaptive heating blanket system for adjusting heating value according to claim 1, characterized in that: The temperature collection and feedback module includes: A multi-point temperature sensing unit is used to collect temperature data at multiple spatial locations of the electric blanket; The temperature feedback interface unit is used to transmit the collected temperature information to the control calculation module and participate in the heating power regulation closed loop.

8. The self-adaptive environment temperature regulating heating electric blanket system according to claim 3, characterized in that: The state reasoning unit comprises: Feature extraction mechanism, used to extract time series features and frequency domain features from physiological signals such as heart rate, body movement and breathing; Pattern recognition mechanism, which uses deep learning algorithms to train the extracted features to accurately identify different sleep states; The probability calculation mechanism predicts the probability of the current sleep state based on the model, and calculates the probability of each sub-stage through a multi-layer neural network, and finally outputs the probability distribution of the current sleep state.

9. The self-adaptive environment temperature regulating heating electric blanket system according to claim 5, characterized in that: The thermal modeling unit comprises: The heat conduction calculation mechanism establishes a temperature change model of the electric blanket in different spatial positions and time dimensions based on the heat conduction principle, taking into account the heat conduction coefficient, heat transfer rate and ambient temperature in different areas; Temperature deviation feedback mechanism monitors the real-time temperature deviation of each heating area and feeds it back to the control calculation module; The target generation mechanism is optimized to dynamically adjust the heating power control strategy by constructing an optimization objective function between energy efficiency and temperature deviation.

10. The self-adaptive heating blanket system for adjusting heating value according to claim 6, characterized in that: The PWM modulation unit, The following mechanisms are included: A PWM signal generation mechanism is used to generate a PWM signal according to the power adjustment instruction generated by the control calculation module and adjust the power of the heating element; PWM signal regulation mechanism, used to dynamically adjust the duty cycle of the PWM signal according to the temperature feedback signal to ensure that the temperature of each heating area is stable within a comfortable range; The comfortable temperature range is 20℃~25℃; The dynamic response mechanism adjusts according to the real-time temperature changes in each area to ensure that temperature fluctuations are controlled within the set target temperature range.

Images