Temperature linkage control method and device, smart home system and storage medium

Abstract

The invention discloses a temperature linkage control method and device, a smart home system and a storage medium, the method and device are applied to the smart home system, the smart home system comprises an air conditioner and a smart lamp, and the method comprises the steps that current environment actual parameters are collected; wherein the actual environment parameter comprises an actual environment temperature; acquiring a temperature difference value between the actual environment temperature and a set temperature preset by a user; based on the temperature difference value, a linkage control strategy is generated through a spectrum-temperature sensing mapping model; wherein the spectrum-temperature sensing mapping model is constructed according to the mapping relation between the environment temperature and the spectrum of the intelligent lamp; and controlling the air conditioner and / or the intelligent lamp according to the linkage control strategy. Vision and thermal inductance are cooperatively regulated and controlled, the influence of the spectrum of the intelligent lamp on the thermal comfort perception of the human body is fully utilized, and the energy consumption of the air conditioner is effectively reduced while the comfort of a user is guaranteed.

Description

Technical Field

[0001] This invention relates to the field of smart home technology, and in particular to a temperature-linked control method, device, smart home system, and storage medium. Background Technology

[0002] In the field of building environmental control, heating, ventilation, and air conditioning (HVAC) systems are the core component of building energy consumption. Their energy consumption share is becoming increasingly significant with the development of intelligent and large-scale buildings, making them a key area requiring breakthroughs in building energy conservation. Currently, traditional temperature control systems generally adopt a control mode where a single air conditioning unit regulates the physical temperature of the environment. This mode has revealed many core pain points in practical applications, severely restricting the synergistic improvement of building environmental comfort and energy-saving benefits.

[0003] First, traditional temperature control systems suffer from high energy consumption. Because users often set air conditioner temperatures outside the economical operating range in pursuit of instant thermal comfort—for example, setting them too low in summer and too high in winter—this results in significant energy waste. According to relevant data, for every 1°C deviation in the air conditioner's set temperature, energy consumption can fluctuate by 6%-8%, further exacerbating energy consumption pressures.

[0004] Secondly, traditional temperature control systems suffer from a significant limitation in their control dimensions. Existing systems rely solely on ambient physical temperature as the only feedback control parameter, failing to fully recognize that human thermal comfort is not simply dependent on physical temperature, but rather a complex psychophysiological process influenced by multiple senses. This results in a significant discrepancy between the system's regulatory effect and the actual comfort needs of the human body.

[0005] Furthermore, traditional temperature control systems neglect the importance of individual differences and cross-modal perception. On the one hand, the system cannot adapt to the differences in hot and cold sensations among different users in the same environment, making it difficult to achieve personalized comfort control. On the other hand, lighting and temperature control systems in the building environment have long operated in a disconnected manner, failing to leverage the scientific principle of the "temperature effect of color" to optimize control performance. This means that warm and cool tones of light can influence human temperature perception and thus regulate the human body's thermal comfort experience, resulting in the system's control potential not being fully explored.

[0006] To address these issues, existing technologies have proposed some intelligent improvement schemes, such as introducing indicators like humidity and human body sensing into the control parameters to enhance the accuracy of regulation by enriching the perception dimensions. However, these schemes still do not break through the traditional paradigm of "achieving regulation solely by changing physical environment parameters," failing to fundamentally solve the complexity and individual differences in human thermal comfort perception, nor do they achieve synergistic optimization of visual perception and thermal regulation.

[0007] In summary, in the current field of building environmental control, traditional temperature control systems and existing improved solutions cannot meet the core requirement of "achieving deep energy saving while ensuring human comfort." Therefore, developing an innovative technical solution that can integrate visual and thermal sensing for coordinated regulation to improve user experience and reduce air conditioning energy consumption is a problem that needs to be solved by those skilled in the art. Summary of the Invention

[0008] This invention provides a temperature linkage control method, device, smart home system, and storage medium, aiming to achieve air conditioning energy saving while ensuring user comfort, thereby solving the problem of excessive energy consumption in air conditioning systems.

[0009] In a first aspect, embodiments of the present invention provide a temperature linkage control method applied to a smart home system, the smart home system including an air conditioner and smart lighting fixtures, the method comprising: Collect current environmental parameters; wherein, the environmental parameters include the actual environmental temperature; Obtain the temperature difference between the actual ambient temperature and the user-preset temperature; Based on the temperature difference, a linkage control strategy is generated through a spectral-temperature sensing mapping model; wherein, the spectral-temperature sensing mapping model is constructed based on the mapping relationship between ambient temperature and the spectrum of the smart lamp. The air conditioner and / or smart lighting fixtures are controlled according to the aforementioned linkage control strategy.

[0010] Secondly, embodiments of the present invention provide a temperature-linked control device applied to a smart home system, the smart home system including an air conditioner and smart lighting fixtures, the device comprising: A parameter acquisition unit is used to acquire the current actual environmental parameters; wherein, the actual environmental parameters include the actual environmental temperature; The difference acquisition unit is used to acquire the temperature difference between the actual ambient temperature and the preset temperature set by the user. The strategy generation unit is used to generate a linkage control strategy based on the temperature difference using a spectral-temperature sensing mapping model; wherein the spectral-temperature sensing mapping model is constructed based on the mapping relationship between ambient temperature and the spectrum of the smart lamp. The linkage control unit is used to control the air conditioner and / or smart lighting fixtures according to the linkage control strategy.

[0011] Thirdly, embodiments of the present invention provide a smart home system, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the temperature linkage control method as described in the first aspect.

[0012] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the temperature linkage control method as described in the first aspect.

[0013] This invention provides a temperature-linked control method, device, smart home system, and storage medium. The temperature-linked control method is applied to a smart home system, which includes an air conditioner and smart lighting. The method includes: collecting current environmental parameters, including the actual ambient temperature; obtaining the temperature difference between the actual ambient temperature and a user-preset temperature; generating a linkage control strategy based on the temperature difference using a spectral-temperature sensing mapping model; wherein the spectral-temperature sensing mapping model is constructed based on the mapping relationship between the ambient temperature and the spectrum of the smart lighting; and controlling the air conditioner and / or the smart lighting according to the linkage control strategy. This invention, by coordinating visual and thermal sensing, fully utilizes the influence of the smart lighting spectrum on human thermal comfort perception, effectively reducing air conditioner energy consumption while ensuring user comfort. Specifically, when there is a difference between the actual ambient temperature and the set temperature, this invention no longer relies solely on adjusting the air conditioner to change the physical ambient temperature, but instead combines the spectral-temperature sensing mapping model to flexibly generate a linkage control strategy for the air conditioner and smart lighting based on different temperature difference conditions. Attached Figure Description

[0014] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0015] Figure 1 A schematic flowchart of a temperature linkage control method provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of the first sub-process of a temperature linkage control method provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the second sub-process of a temperature linkage control method provided in an embodiment of the present invention; Figure 4 A schematic diagram of the third sub-process of a temperature linkage control method provided in an embodiment of the present invention; Figure 5 A schematic diagram of the fourth sub-process of a temperature linkage control method provided in an embodiment of the present invention; Figure 6This is a schematic diagram of the principle architecture of a temperature linkage control method provided in an embodiment of the present invention; Figure 7 This is another principle architecture diagram of a temperature linkage control method provided in an embodiment of the present invention; Figure 8 A schematic block diagram of a temperature linkage control device provided in an embodiment of the present invention; Figure 9 This is a first sub-schematic block diagram of a temperature linkage control device provided in an embodiment of the present invention; Figure 10 This is a second schematic block diagram of a temperature linkage control device provided in an embodiment of the present invention; Figure 11 This is a third schematic block diagram of a temperature linkage control device provided in an embodiment of the present invention; Figure 12 This is a fourth schematic block diagram of a temperature linkage control device provided in an embodiment of the present invention; Figure 13 This is a schematic block diagram of a smart home system provided in an embodiment of the present invention. Detailed Implementation

[0016] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0017] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0018] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0019] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0020] Please see below. Figure 1This invention provides a temperature linkage control method for use in a smart home system, which includes an air conditioner and smart lighting. The method includes steps S101 to S104.

[0021] Step S101: Collect the current actual environmental parameters; wherein, the actual environmental parameters include the actual environmental temperature; Step S102: Obtain the temperature difference between the actual ambient temperature and the user-preset temperature. Step S103: Based on the temperature difference, generate a linkage control strategy through a spectrum-temperature sensing mapping model; wherein, the spectrum-temperature sensing mapping model is constructed according to the mapping relationship between ambient temperature and the spectrum of the smart lamp. Step S104: Control the air conditioner and / or smart lighting fixtures according to the linkage control strategy.

[0022] In this embodiment, firstly, actual environmental parameters, including the actual ambient temperature, are collected; then, the difference between the actual ambient temperature and the user-set temperature is calculated; then, based on this temperature difference, a linkage control strategy is generated using a spectral-temperature sensing mapping model constructed according to the spectral mapping relationship between ambient temperature and smart lighting fixtures; finally, the air conditioner and / or smart lighting fixtures are controlled according to this strategy.

[0023] This embodiment utilizes the synergistic regulation of vision and thermal sensing to fully leverage the influence of the spectrum of smart lighting fixtures on human thermal comfort perception, effectively reducing air conditioner energy consumption while ensuring user comfort. Specifically, when there is a difference between the actual ambient temperature and the set temperature, this embodiment no longer relies solely on adjusting the air conditioner to change the physical ambient temperature. Instead, it combines a spectrum-temperature sensing mapping model to flexibly generate a coordinated control strategy for both the air conditioner and smart lighting fixtures based on different temperature difference scenarios. Thus, by leveraging spectral adjustment, the user's tolerance range for actual temperature differences is expanded, allowing the air conditioner to operate at a more economical setpoint (higher set temperature in summer, lower set temperature in winter), thereby directly reducing its operating time and power consumption, achieving energy-saving goals. Simultaneously, by introducing temperature sensing as a second control dimension in addition to adjusting the actual temperature, this provides a novel, low-power technical approach to environmental control. The user experience is no longer just a simple feeling of cold or heat, but an overall atmosphere created by the coordination of light and temperature (such as the experience of "cool clear sky" or "warm fire"), making the comfort more natural and three-dimensional; and it makes users clearly realize that while enjoying a comfortable environment, they are also contributing to energy conservation and emission reduction, thereby gaining a positive psychological experience and social value recognition.

[0024] In practical applications, combined with Figure 6 and Figure 7Based on the temperature linkage control method provided in this embodiment, a system with a smart home hub as its core is constructed using a star topology. The system hardware components and interconnections include: a central controller (such as an embedded host or smart hub); an adjustable spectrum LED lighting system whose color temperature and spectral power distribution can be precisely programmed and controlled; an air conditioning unit that can communicate with the control host via network or infrared; environmental sensors, including at least a high-precision temperature sensor; and a user interface, such as a mobile APP or voice assistant, for receiving feedback. Details are shown in Table 1. Table 1 Based on Table 1 above, environmental data is periodically transmitted to the smart home hub via Zigbee or Bluetooth Mesh Low Energy protocols using temperature and humidity sensors and human body sensors. The mobile app and voice assistant interact with the hub via Wi-Fi or the cloud. The core algorithm within the hub continuously runs, comparing T... set With T actual The system invokes the spectral-temperature mapping model and makes decisions based on the linkage control strategy. The central control unit sends the set_color_temperature(CCT, RGB) command to the smart lighting fixture via Wi-Fi or Zigbee, and the set_ac(temperature, mode, fan_speed) command to the air conditioner via infrared or Zigbee.

[0025] Therefore, this embodiment provides a detailed plan for a complete intelligent system that includes hardware deployment, algorithmic decision-making, and continuous evolution. This system achieves quantified perception through a spectral-temperature sensing mapping model, realizes precise energy saving based on dynamic linkage control strategies, provides personalized care according to user calibration processes, and finally integrates all modules into a highly efficient, considerate, and environmentally friendly comprehensive solution through a multi-sensory fusion architecture.

[0026] In one embodiment, such as Figure 2 As shown, the construction steps of the spectrum-temperature sensing mapping model include: steps S201 to S204.

[0027] Step S201: Use multiple actual temperatures as corresponding reference temperatures; Step S202: At each of the reference temperatures, control the smart lamp to output multiple different test spectra; Step S203: Obtain the subject's subjective thermal sensation vote for the test spectrum feedback and record the corresponding spectral parameter vector; wherein, the spectral parameter vector includes the correlated color temperature and RGB power ratio; Step S204: Using the subjective thermal sensation vote as the dependent variable and the spectral parameter vector as the independent variable, train a nonlinear model to construct the spectral-temperature sensing mapping model.

[0028] In this embodiment, when constructing the spectral-temperature mapping model, multiple actual temperatures (T) are first selected. actual These serve as reference temperatures (e.g., 24℃, 26℃, 28℃, etc.) to set different temperature scenarios for subsequent experiments. At each reference temperature, the smart lamps are controlled to output multiple different test spectra S. i The test spectrum S i Using correlated color temperature as the main gradient (e.g., 2700K, 3500K, 4500K, 5500K, and 6500K), and including special spectra with intensity variations in specific wavelengths (e.g., 450nm blue light, 660nm red light), we can comprehensively explore the effects of different spectra on human thermal sensation under different temperature environments.

[0029] Then, the subjective thermal sensation votes of the test subjects regarding the test spectrum feedback are obtained and the corresponding spectral parameter vectors are recorded. This data is the key basis for building the model. For example, for each (T) actual ,S i After the subjects had adapted to the combination of the two methods for a period of time, they submitted their subjective thermal perception vote (TSV) using the ASHRAE 7-point thermal perception scale, and the spectral parameter vector S at this time was recorded. i (CCT,R,G,B, ...), where CCT is the correlated color temperature, R represents the power / proportion of the red light band, G represents the power / proportion of the green light band, and B represents the power / proportion of the blue light band.

[0030] Then, using subjective thermal sensation voting as the dependent variable and the spectral parameter vector as the independent variable, a nonlinear model is trained. This method can more accurately capture the complex nonlinear relationship between the spectrum and human thermal sensation. Here, since sensory perception often follows a logarithmic or power-law relationship, a nonlinear model is used to construct the spectrum-temperature mapping model. The specific formula of the spectrum-temperature mapping model is as follows: ΔTSV predicted =α* log(CCT / CCT neutral )+β* (B ratio γ ); Wherein, ΔTSV predicted CCT represents the change in subjective thermal perception votes in the output of the spectral-thermal mapping model prediction. neutral Indicates neutral correlated color temperature, B ratioα represents the power proportion of the blue light band, β represents the nonlinear coefficient related to color temperature, γ represents the nonlinear coefficient related to the blue light proportion, and γ represents the power exponent of the blue light proportion.

[0031] The above formula is a nonlinear optimization expression of the spectral-thermal sensing mapping model, suitable for accurately capturing the nonlinear correlation between spectral parameters and changes in subjective thermal sensation. This correlation conforms to the logarithmic / power-law characteristics of human sensory perception. Essentially, this formula uses a nonlinear mathematical model to precisely quantify "correlated color temperature (CCT) + blue light percentage (B)". ratio The combined impact of changes in the combination of ")" on the user's subjective thermal perception (TSV) can be broken down into three core layers: First, it aligns with the non-linear characteristics of human senses. The human body's perception of heat from light is not a linear change in spectral parameters leading to a linear change in thermal sensation, but rather follows a non-linear law of logarithmic / power law. For example, when the color temperature increases from 3000K (warm light) to 4000K (neutral light), the user can clearly feel a "cooling" sensation; however, when increasing from 6000K (cool light) to 7000K (extremely cool light), even with the same change of 1000K, the perceived intensity of the "cooling" sensation will be significantly reduced. The logarithmic term in the formula is log(CCT / CCT). neutral This is precisely to fit the characteristic of being "sensitive in the low color temperature range and desensitized in the high color temperature range." For example, when the blue light percentage increases from 5% to 10%, the perception of "cooling down" significantly increases; however, when it increases from 20% to 25%, the increase in perception decreases, while the power term B... ratio γ (e.g., γ>1) can accurately describe this nonlinear relationship of "sensitive when the proportion is low and saturated when the proportion is high".

[0032] Second, the synergistic quantification of multispectral parameters. The formula uses a weighted summation of "logarithmic term of color temperature + exponential term of blue light proportion" (α and β are weights), simultaneously considering the influence of two core spectral parameters: color temperature (CCT) is a "macroscopic warm / cool adjustment" parameter that determines the overall warm / cool tone of the light; blue light proportion (B) is a weighted summation of "logarithmic term of color temperature + exponential term of blue light proportion". ratio The "micro-precise adjustment" parameter refines the intensity of the coldness of light. The two work together to enable the model to more comprehensively and accurately predict the impact of spectral changes on thermal sensation (compared to a simple linear model that only considers color temperature, the prediction error of the nonlinear model can be reduced by more than 30%).

[0033] Third, it provides precise algorithmic support for spectral adjustment. The core objective of the formula is to achieve "input spectral parameters → output predicted thermal sensation changes," and then deduce "the spectral parameters required to meet the target thermal sensation," providing an algorithmic basis for system linkage control. For example, when the physical temperature difference ΔT = +1℃ (the actual temperature is 1℃ higher than the set value), the system needs to adjust the spectrum to make the user feel "0.8 TSV levels cooler" (i.e., ΔTSV). predicted=-0.8); After substituting into the formula, the corresponding CCT (e.g., from 4000K to 5500K) and B can be solved in reverse. ratio (For example, when the light intensity increases from 8% to 15%), the controller sends the spectral command to the smart lighting fixture, which can compensate for the physical temperature difference through low-energy optical adjustment, thereby reducing the energy consumption of the air conditioner.

[0034] The completed spectral-temperature sensing mapping model provides a scientific and accurate reference for subsequent temperature-linked control strategies. Specifically, when a difference exists between the actual ambient temperature and the set temperature, this model, combined with the current temperature difference, can accurately generate a linked control strategy for air conditioners and smart lighting fixtures. Furthermore, this model can be continuously optimized and improved as the system operates. The system can continuously collect data such as actual environmental parameters, temperature differences, and the execution effect of the linked control strategy to update and adjust the spectral-temperature sensing mapping model, making it more closely aligned with actual usage scenarios and further improving the accuracy and energy-saving effect of temperature-linked control.

[0035] In addition, other methods can be used to construct the spectral-temperature mapping model in practical applications. For example, a simple linear model can be used to construct the spectral-temperature mapping model: assuming that color temperature is the main influencing factor, a univariate linear model can be established: ΔTSV predicted =k*(CCT-CCT neutral ); Where k is the regression coefficient. For example, when k is negative, it indicates that the color temperature increases and the surface feels cooler.

[0036] For example, a spectral-temperature mapping model can be constructed using a multivariate linear model: Considering more spectral parameters, the model can be extended to: ΔTSV predicted =a*(CCT-CCT neutral )+b*(B ratio -B ratio neutral )+c*(R ratio -R ratio neutral ); Among them, B ratio and R ratio , respectively, are the ratios of blue light and red light band power to total power, and a, b, and c are regression coefficients.

[0037] It should be noted here that the above nonlinear model is the "optimal form" of the spectral-temperature mapping model in this embodiment. Compared with the simple linear model (considering only color temperature) and the multivariate linear model (considering color temperature + red and blue light ratio), its advantages are: it is closer to the real perception law of human senses and has higher prediction accuracy; it can cover the full spectrum adjustment range (2700K-6500K color temperature, 0-20% blue light ratio), and has wider applicability; it provides flexible parameter adjustment space for subsequent user personalized correction (adaptation to different users' sensory sensitivities can be achieved by fine-tuning α, β, and γ).

[0038] This embodiment establishes a functional relationship or lookup table from spectral parameters to the sensed temperature change through statistical analysis (such as regression analysis), i.e., ΔT. perceived = f(spectral parameters), ΔT perceived This is the core parameter of "Perceived Temperature Change," used to quantify the difference in temperature perceived by the user relative to a baseline state after a change in spectral parameters. It is a key quantitative indicator connecting "optical adjustment" and "thermal comfort perception," and also the core output of the spectral-temperature sensing mapping model. This model will serve as the initial control kernel of the system. For example, as shown in Table 2, the spectral-temperature sensing mapping relationship can be: Table 2 In one embodiment, the step of constructing the spectral-temperature mapping model further includes: Obtain the user's calibration instructions and generate a personal calibration factor based on the calibration instructions; The spectral-temperature mapping model is modified using the personal calibration factor to obtain a user-personalized spectral-temperature mapping model.

[0039] In this embodiment, when constructing the spectral-temperature mapping model, the user's actual calibration needs are also considered to further improve the model's accuracy and personalization. When the user issues a calibration command, based on that command, such as the user's actual preferences for ambient temperature and light spectrum, a personalized calibration factor is accurately generated.

[0040] In practical applications, personal calibration factors can be generated by considering multiple factors. For example, users may have different requirements for temperature and light spectrum at certain times or in specific scenarios. Upon waking in the morning, users may prefer warm, soft light and a relatively high temperature; while working in the afternoon, they may need brighter, cooler-toned light and a slightly lower temperature to stay alert and focused. By combining user feedback from these different scenarios and using appropriate data processing and analysis algorithms, the personal calibration factor that best matches the user's actual needs can be calculated.

[0041] After obtaining the individual calibration factor, it is applied to the spectral-temperature mapping model for comprehensive and in-depth optimization. This allows the model to more accurately reflect the user's perception of the relationship between spectrum and temperature. The revised, personalized spectral-temperature mapping model will provide users with more precise and considerate services.

[0042] In one embodiment, such as Figure 3 As shown, step S103 includes steps S301 to S304.

[0043] Step S301: Compare the temperature difference with a preset difference threshold; Step S302: When the temperature difference is less than or equal to the first difference threshold, generate a linkage control strategy that only adjusts the smart lamp. Step S303: When the temperature difference is greater than a first difference threshold and less than or equal to a second difference threshold, a coordinated control strategy for regulating the air conditioner and the smart lighting is generated; wherein, the second difference threshold is greater than the first difference threshold. Step S304: When the temperature difference is greater than the third difference threshold, a linkage control strategy that prioritizes adjusting the air conditioner is generated; wherein the third difference threshold is greater than the second difference threshold.

[0044] In this embodiment, when generating a linkage control strategy based on the temperature difference using a spectral-temperature sensing mapping model, the temperature difference is first compared with a preset difference threshold. This difference threshold can be derived from a large amount of experimental data and practical application experience, and can more accurately reflect the reasonable control method that the system should adopt under different temperature difference conditions.

[0045] Combination Figure 7 When the temperature difference is less than or equal to the first difference threshold (i.e., the micro-difference zone, for example |ΔT) actual When the temperature difference is less than or equal to 1℃, it means the deviation between the actual temperature and the set temperature is small. In this case, adjusting the spectral output of the smart light fixture can meet the user's temperature perception needs to a certain extent. Because smart light fixtures have the advantages of fast response and low energy consumption when adjusting the spectrum, users can perceive temperature changes without significantly altering the actual temperature. For example, in summer, when the temperature difference is small, the spectrum of the smart light fixture can be adjusted to cool white light, giving users a cooling sensation, thereby reducing reliance on air conditioning and achieving energy savings.

[0046] When the temperature difference is greater than the first difference threshold and less than or equal to the second difference threshold (i.e., the intermediate difference zone, 1℃ < |ΔT) actualWhen the temperature difference is ≤2℃, it indicates a significant increase in the deviation between the actual and set temperatures. In this case, adjusting only the smart lights may not meet the user's temperature requirements; a coordinated adjustment of both the air conditioner and the smart lights is necessary. Using a spectral-temperature sensing mapping model, the required air conditioning temperature and the spectral parameters of the smart lights can be accurately calculated based on the current temperature difference and spectral parameters. During the adjustment process, the air conditioner can make small temperature adjustments, while the smart lights simultaneously adjust their spectra accordingly. This synergy ensures both user comfort and energy savings.

[0047] When the temperature difference exceeds the third difference threshold (i.e., the strong difference zone, for example |ΔT) actual When the temperature difference exceeds 2°C, it indicates a significant deviation between the actual and set temperatures. In this case, adjusting the air conditioner is the most effective approach. Air conditioners have powerful cooling or heating capabilities, quickly changing the actual indoor temperature. However, while adjusting the air conditioner, smart lighting can also adjust its spectrum based on a spectral-temperature mapping model to assist the air conditioner in regulating the user's perceived temperature. For example, in winter, when the temperature difference is large, the air conditioner quickly heats up, while the smart lighting adjusts its spectrum to a warm yellow light, allowing the user to feel both the actual temperature increase and visual warmth, further enhancing comfort.

[0048] Through this hierarchical linkage control strategy based on temperature differences, this embodiment can flexibly and precisely adjust smart lighting and air conditioning according to different actual conditions, achieving a perfect balance between energy saving and comfort. Meanwhile, with continuous feedback on user habits and the system's ongoing learning, the spectral-temperature sensing mapping model and linkage control strategy will be continuously optimized and improved, providing users with a more intelligent, efficient, and comfortable home environment.

[0049] In one embodiment, such as Figure 4 As shown, step S103 further includes steps S401 to S403.

[0050] Step S401: Convert the temperature difference into a target subjective thermal sensation vote according to a preset conversion strategy; Step S402: Input the target subjective thermal sensation vote into the spectrum-temperature sensing mapping model, and have the spectrum-temperature sensing mapping model output the corresponding target spectral parameters; Step S403: Generate the linkage control strategy based on the target spectral parameters.

[0051] When generating the linkage control strategy through the spectrum-temperature perception mapping model in this embodiment, first, the temperature difference is converted into the target subjective thermal sensation vote. Then, the obtained target subjective thermal sensation vote is input into the already constructed spectrum-temperature perception mapping model. This model has been trained and optimized with a large amount of data in the early stage and can accurately output the corresponding target spectrum parameters according to the input subjective thermal sensation vote. These target spectrum parameters can include key information such as the correlated color temperature and the RGB power ratio, which determine the spectrum finally output by the intelligent lamp. Then, a linkage control strategy is generated based on the output target spectrum parameters to control the intelligent lamp according to the target spectrum parameters.

[0052] For example, in the micro-difference area, when the difference between the actual temperature and the set temperature is small, after converting the temperature difference into the target subjective thermal sensation vote and inputting it into the spectrum-temperature perception mapping model, the target spectrum parameters are obtained. For example, if the temperature difference shows that the actual temperature is 0.8 °C lower than the set temperature, the converted target subjective thermal sensation vote may be "feeling slightly warmer". Inputting it into the model, the output target spectrum parameters may be warm white light with a correlated color temperature of 3500K, and the RGB power ratio will also be determined accordingly. Based on this target spectrum parameter, the generated linkage control strategy is to only adjust the intelligent lamp and adjust its spectrum to warm white light of 3500K. In this way, without starting or changing the operating state of the air conditioner, by using the change of the spectrum of the intelligent lamp, users can visually and perceptually feel that the temperature has risen, meeting the user's temperature requirements, and at the same time avoiding the increase in energy consumption caused by the frequent start of the air conditioner.

[0053] In the medium-difference area, assuming that the actual temperature is 1.5 °C lower than the set temperature, the converted target subjective thermal sensation vote is "feeling warmer". The target spectrum parameters output by the spectrum-temperature perception mapping model may be warm yellow light with a correlated color temperature of 2700K, and the RGB power ratio is also adjusted correspondingly. At this time, the generated linkage control strategy is to coordinately adjust the air conditioner and the intelligent lamp. The air conditioner slightly raises the temperature, and at the same time, the intelligent lamp adjusts its spectrum to warm yellow light of 2700K. The two cooperate with each other, which not only ensures that users can quickly feel the temperature rise but also reduces the energy consumption of the air conditioner to a certain extent.

[0054] In the strong-difference area, if the actual temperature is 3 °C lower than the set temperature, the target subjective thermal sensation vote is "feeling significantly warmer". The target spectrum parameters output by the spectrum-temperature perception mapping model will also be a spectrum with a warm tone and a lower color temperature, such as warm yellow light of 2700K. The linkage control strategy preferentially adjusts the air conditioner to make it heat quickly, and at the same time, the intelligent lamp adjusts its spectrum to warm yellow light to assist the air conditioner in adjusting the user's perceived temperature from the visual and physical sensations, improving the user's comfort.

[0055] As usage time increases, the spectral-temperature mapping model and linkage control strategy can be continuously optimized based on user feedback. For example, if a user repeatedly reports that the temperature regulation is ineffective at a certain temperature difference, the system will reanalyze the data, adjust the model parameters and control strategy, so that subsequent temperature regulation better meets the user's personalized needs, further achieving a perfect combination of energy saving and comfort.

[0056] In practical applications, when converting the temperature difference into a target subjective thermal perception vote according to a preset conversion strategy, the temperature difference ΔT can be converted into the target subjective thermal perception vote ΔTSV that needs to be compensated, using a proportional control conversion strategy. desired That is, ΔTSV desired =K p *ΔT. The conversion can also be achieved directly according to predefined rules. For example, if ΔT = +1°C, then ΔTSV... desired =+0.7.

[0057] In one embodiment, after the step of controlling the air conditioner and / or smart lighting fixtures according to the linkage control strategy, the process includes: Obtain user feedback data on the linkage control strategy; Based on the feedback data, the parameters of the spectral-temperature sensing mapping model are updated using machine learning algorithms.

[0058] In this embodiment, after controlling the air conditioner and / or smart lighting according to the linkage control strategy, feedback data on the control effect from the user continues to be acquired. This feedback data can be evaluations manually entered by the user through a smartphone app, such as feeling too cold, too hot, or just right; it can also be user voice feedback received by the smart speaker, such as "I feel a little hot" or "The lights are too bright." Simultaneously, changes in environmental parameters, such as actual temperature, humidity, and light intensity, can also be automatically recorded as part of the feedback data.

[0059] Based on this feedback data, machine learning algorithms (such as Bayesian updates or online learning) are used to update the parameters of the spectral-temperature mapping model. Machine learning algorithms can analyze patterns and characteristics in the feedback data to identify discrepancies between the model's predictions and the user's actual experience, thereby generating a personalized profile for that user. For example, if a user reports feeling hotter under a specific spectrum than the model predicts, the algorithm will adjust the parameter representing the perceived temperature change corresponding to that spectrum.

[0060] During parameter updates, an appropriate update method can be selected based on the quantity and quality of the feedback data. If there is little feedback data, incremental learning can be used to fine-tune the model's parameters; if there is a lot of feedback data and it shows a clear trend, the model can be retrained to more accurately reflect the user's personalized needs.

[0061] By continuously acquiring feedback data and updating model parameters, the system can gradually adapt to different user preferences and environmental changes, improving the accuracy of control strategies and user comfort. For example, for users who are sensitive to changes in light, the spectral-temperature mapping model can be adjusted to more accurately meet the user's thermal sensation needs when adjusting lighting; the control strategy can also be adjusted in a timely manner for environmental changes in different seasons and time periods to ensure that users are always in a comfortable environment.

[0062] Furthermore, the updated model can be evaluated and validated. Evaluation metrics can include user satisfaction, energy consumption, and the stability of temperature and light intensity. By monitoring and analyzing these metrics, the effectiveness of the model update can be determined, and it can be decided whether further adjustments to the update strategy are needed. If the updated model performs poorly in certain aspects, it can be rolled back to the previous model version, and the feedback data can be re-analyzed to find a more suitable update method. Over long-term operation, a closed-loop optimization mechanism can be formed. Continuously acquiring user feedback, updating model parameters, and evaluating model performance allows the spectral-temperature sensing mapping model and the linkage control strategy to continuously evolve, providing users with a more efficient, user-friendly, and environmentally friendly comprehensive solution.

[0063] In one embodiment, the actual environmental parameters also include human body detection data, such as... Figure 5 As shown, before step S102, steps S501 to S503 are included.

[0064] Step S501: Determine whether there are people in the current environment based on the human body detection data; Step S502: If it is determined that there are no people in the current environment, continue to collect actual environmental parameters according to the predetermined collection strategy; Step S503: If it is determined that there are people in the current environment, then obtain the temperature difference between the actual temperature of the environment and the preset temperature set by the user.

[0065] In addition to real-time collection of ambient temperature data, this embodiment also acquires human body detection data, enabling the smart home system to perform more accurate and efficient environmental monitoring and intelligent control. When the human body detection data determines that the indoor environment is unoccupied, it continuously collects environmental parameters according to a preset collection strategy, such as recording the actual ambient temperature at regular intervals. This ensures that when the user returns, adjustments can be quickly made based on the latest environmental conditions to restore a comfortable experience. During this process, unnecessary temperature control and device adjustments can be paused, avoiding energy waste, extending device lifespan, and significantly improving overall energy efficiency.

[0066] When indoor activity is detected, the system will obtain the difference between the current ambient temperature and the user's preset target temperature in real time, and activate the corresponding linkage control mechanism based on the temperature difference data to dynamically maintain a balance between comfort and energy saving.

[0067] In practical applications, human body detection data can be collected using various sensors, such as infrared sensors and millimeter-wave radar sensors. These sensors can accurately detect the presence of people in the environment in real time, providing reliable data support for the intelligent control of the system. Furthermore, human body detection data can be combined with other environmental parameters to further optimize the linkage control strategy. For example, when a person is detected entering the environment, the spectrum and air conditioning intensity can be dynamically adjusted based on factors such as the person's activity level and dwell time to provide a more comfortable and personalized environmental experience.

[0068] Figure 8 This is a schematic block diagram of a temperature linkage control device 800 provided in an embodiment of the present invention. The device 800 is applied to a smart home system, which includes an air conditioner and smart lighting fixtures. The device 800 includes: The parameter acquisition unit 801 is used to acquire the current actual environmental parameters; wherein, the actual environmental parameters include the actual environmental temperature; The difference acquisition unit 802 is used to acquire the temperature difference between the actual ambient temperature and the preset temperature set by the user. The strategy generation unit 803 is used to generate a linkage control strategy based on the temperature difference through a spectrum-temperature sensing mapping model; wherein the spectrum-temperature sensing mapping model is constructed according to the mapping relationship between the ambient temperature and the spectrum of the smart lamp. The linkage control unit 804 is used to control the air conditioner and / or smart lighting fixtures according to the linkage control strategy.

[0069] In one embodiment, such as Figure 9 As shown, the temperature linkage control device 800 further includes: The reference setting unit 901 is used to adopt multiple actual temperatures as the corresponding reference temperatures. The test control unit 902 is used to control the smart lamp to output multiple different test spectra at each of the reference temperatures; The test recording unit 903 is used to acquire the subject's subjective thermal sensation vote for the test spectrum feedback and record the corresponding spectral parameter vector; wherein, the spectral parameter vector includes correlated color temperature and RGB power ratio; The model building unit 904 is used to train a nonlinear model with the subjective thermal sensation vote as the dependent variable and the spectral parameter vector as the independent variable, thereby constructing the spectral-temperature sensing mapping model.

[0070] In one embodiment, the temperature linkage control device 800 further includes: The calibration generation unit is used to acquire the user's calibration instructions and generate personal calibration factors based on the calibration instructions; The model correction unit is used to correct the spectral-temperature mapping model using the personal calibration factor to obtain a user-personalized spectral-temperature mapping model.

[0071] In one embodiment, such as Figure 10 As shown, the strategy generation unit 803 includes: The difference comparison unit 1001 is used to compare the temperature difference with a preset difference threshold. The first generation unit 1002 is used to generate a linkage control strategy that only adjusts the smart lamp when the temperature difference is less than or equal to a first difference threshold. The second generation unit 1003 is used to generate a coordinated control strategy for the air conditioner and the smart lighting when the temperature difference is greater than a first difference threshold and less than or equal to a second difference threshold; wherein the second difference threshold is greater than the first difference threshold. The third generation unit 1004 is used to generate a linkage control strategy that prioritizes adjusting the air conditioner when the temperature difference is greater than a third difference threshold; wherein the third difference threshold is greater than a second difference threshold.

[0072] In one embodiment, such as Figure 11 As shown, the strategy generation unit 803 further includes: Temperature conversion unit 1101 is used to convert the temperature difference into a target subjective thermal sensation vote according to a preset conversion strategy; The model output unit 1102 is used to input the target subjective thermal sensation vote into the spectrum-temperature sensing mapping model, and the spectrum-temperature sensing mapping model outputs the corresponding target spectral parameters. The parameter generation unit 1103 is used to generate the linkage control strategy based on the target spectral parameters.

[0073] In one embodiment, the temperature linkage control device 800 includes: Feedback acquisition unit, used to acquire user feedback data on the linkage control strategy; The parameter update unit is used to update the parameters of the spectral-temperature sensing mapping model based on the feedback data and using a machine learning algorithm.

[0074] In one embodiment, such as Figure 12 As shown, the temperature linkage control device 800 further includes: Personnel determination unit 1201 is used to determine whether there are personnel in the current environment based on the human body detection data; The first determination unit 1202 is used to continue collecting actual environmental parameters according to a predetermined collection strategy if it is determined that there are no personnel in the current environment. The second determination unit 1203 is used to obtain the temperature difference between the actual ambient temperature and the preset temperature set by the user if it is determined that there are people in the current environment.

[0075] Please see Figure 13 This invention also provides a smart home system 1300, which is a device with both wireless and wired communication capabilities.

[0076] The smart home system 1300 includes a processor 1302, a memory, and a network interface 1305 connected via a system bus 1301. The memory may include a non-volatile storage medium 1303 and internal memory 1304.

[0077] The non-volatile storage medium 1303 can store an operating system 13031 and a computer program 13032. When the computer program 13032 is executed, it causes the processor 1302 to execute a temperature-linked control method.

[0078] The processor 1302 provides computing and control capabilities to support the operation of the entire smart home system 1300.

[0079] The internal memory 1304 provides an environment for the operation of the computer program 13032 in the non-volatile storage medium 1303. When the computer program 13032 is executed by the processor 1302, the processor 1302 can execute a temperature linkage control method.

[0080] This network interface 1305 is used for network communication with other devices. Those skilled in the art will understand that... Figure 13The structure shown is merely a block diagram of a portion of the structure related to the present invention and does not constitute a limitation on the smart home system 1300 to which the present invention is applied. The specific smart home system 1300 may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0081] The processor 1302 is used to run a computer program 13032 stored in a memory to implement any embodiment of the temperature linkage control method described above.

[0082] It should be understood that, in this embodiment of the invention, the processor 1302 may be a Central Processing Unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0083] It will be understood by those skilled in the art that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program may be stored in a storage medium, which is a computer-readable storage medium. The computer program is executed by at least one processor in the computer system to implement the process steps of the embodiments of the above methods.

[0084] This invention also provides a computer-readable storage medium storing a computer program thereon, which, when executed, can perform the steps provided in the above embodiments. The storage medium may include various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0085] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the systems disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple; relevant parts can be referred to in the method section. It should be noted that those skilled in the art can make various improvements and modifications to this application without departing from the principles of this application, and these improvements and modifications also fall within the protection scope of the claims of this application.

[0086] It should also be noted that, in this specification, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

Claims

1. A temperature-linked control method applied to a smart home system, the smart home system including an air conditioner and smart lighting fixtures, characterized in that, The method includes: Collect current environmental parameters; wherein, the environmental parameters include the actual environmental temperature; Obtain the temperature difference between the actual ambient temperature and the user-preset temperature; Based on the temperature difference, a linkage control strategy is generated through a spectral-temperature sensing mapping model; wherein, the spectral-temperature sensing mapping model is constructed based on the mapping relationship between ambient temperature and the spectrum of the smart lamp. The air conditioner and / or smart lighting fixtures are controlled according to the aforementioned linkage control strategy.

2. The temperature linkage control method according to claim 1, characterized in that, The steps for constructing the spectral-temperature mapping model include: Multiple actual temperatures are used as the corresponding reference temperatures; At each of the aforementioned reference temperatures, the smart luminaire is controlled to output multiple different test spectra; Obtain the subject's subjective thermal sensation vote for the test spectrum feedback and record the corresponding spectral parameter vector; wherein, the spectral parameter vector includes correlated color temperature and RGB power ratio; Using the subjective thermal sensation vote as the dependent variable and the spectral parameter vector as the independent variable, a nonlinear model is trained to construct the spectral-temperature sensing mapping model.

3. The temperature linkage control method according to claim 2, characterized in that, The construction steps of the spectral-temperature mapping model also include: Obtain the user's calibration instructions and generate a personal calibration factor based on the calibration instructions; The spectral-temperature mapping model is modified using the personal calibration factor to obtain a user-personalized spectral-temperature mapping model.

4. The temperature linkage control method according to claim 1, characterized in that, Based on the temperature difference, a linkage control strategy is generated through a spectral-temperature sensing mapping model, including: The temperature difference is compared with a preset difference threshold. When the temperature difference is less than or equal to the first difference threshold, a linkage control strategy is generated that only adjusts the smart lamp. When the temperature difference is greater than a first difference threshold and less than or equal to a second difference threshold, a coordinated control strategy for regulating the air conditioner and the smart lighting is generated; wherein, the second difference threshold is greater than the first difference threshold. When the temperature difference is greater than the third difference threshold, a linkage control strategy that prioritizes adjusting the air conditioner is generated; wherein the third difference threshold is greater than the second difference threshold.

5. The temperature linkage control method according to claim 2, characterized in that, The step of generating a linkage control strategy based on the temperature difference using a spectral-temperature sensing mapping model further includes: The temperature difference is converted into a target subjective thermal sensation vote according to a preset conversion strategy; The target subjective thermal sensation vote is input into the spectrum-temperature sensing mapping model, and the spectrum-temperature sensing mapping model outputs the corresponding target spectral parameters; The linkage control strategy is generated based on the target spectral parameters.

6. The temperature linkage control method according to claim 1, characterized in that, After the step of controlling the air conditioner and / or smart lighting fixtures according to the linkage control strategy, the following steps are included: Obtain user feedback data on the linkage control strategy; Based on the feedback data, the parameters of the spectral-temperature sensing mapping model are updated using machine learning algorithms.

7. The temperature linkage control method according to claim 1, characterized in that, The actual environmental parameters also include human body detection data. Before the step of obtaining the temperature difference between the actual environmental temperature and the user-preset temperature, the following steps are included: Based on the human body detection data, determine whether there are people in the current environment; If it is determined that there are no people in the current environment, the actual environmental parameters will continue to be collected according to the predetermined collection strategy. If it is determined that there are people in the current environment, the temperature difference between the actual temperature of the environment and the preset temperature set by the user is obtained.

8. A temperature-linked control device, applied to a smart home system, the smart home system including an air conditioner and smart lighting fixtures, characterized in that, The device includes: A parameter acquisition unit is used to acquire the current actual environmental parameters; wherein, the actual environmental parameters include the actual environmental temperature; The difference acquisition unit is used to acquire the temperature difference between the actual ambient temperature and the preset temperature set by the user. The strategy generation unit is used to generate a linkage control strategy based on the temperature difference using a spectral-temperature sensing mapping model; wherein the spectral-temperature sensing mapping model is constructed based on the mapping relationship between ambient temperature and the spectrum of the smart lamp. The linkage control unit is used to control the air conditioner and / or smart lighting fixtures according to the linkage control strategy.

9. A smart home system, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the temperature linkage control method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the temperature linkage control method as described in any one of claims 1 to 7.

Images