A home scene self-adaptive intelligent linkage control method and system

Abstract

The application provides a kind of home scene adaptive intelligent linkage control method and system, it is related to process control technical field.The method comprises: based on the first environment parameter, second environment parameter, clock information and environment layout parameter of each area in home environment, construct the fusion dataset containing fluctuation range and deviation value;If target event occurs, determine update vector according to the historical operation data of each household appliance;Based on update vector and deviation value, determine the adjustment strategy for controlling each household appliance.The application can realize the dynamic perception of the space-time change of home environment, generate adaptive adjustment strategy combined with the historical operation characteristics of the equipment, effectively solve the problem of rigid linkage control and low energy efficiency of the equipment, improve the comfort and energy efficiency of residence.

Description

Technical Field

[0001] This disclosure generally relates to the field of process control technology, and in particular to a method and system for adaptive intelligent linkage control in home scenarios. Background Technology

[0002] In modern life, smart home technology has become an important direction for improving quality of life and energy conservation. In practice, smart home systems are typically used to control and link devices to achieve intelligent home operation, automatically adjusting the indoor environment to meet users' urgent needs for comfort and convenience. However, research and application in this field still face many challenges and urgently need to overcome the bottlenecks of existing technologies to adapt to complex and ever-changing living scenarios.

[0003] Currently, most methods for intelligent home control rely on preset rules or fixed trigger conditions. This approach often struggles to account for both periodic changes over time and spatial variations in complex and ever-changing home environments, resulting in an inability to achieve precise and efficient intelligent linkage across different time periods and spatial areas. Summary of the Invention

[0004] In view of the above-mentioned defects or deficiencies in related technologies, this application provides a home scene adaptive intelligent linkage control method and system, which can solve the technical problems of rigid device linkage control, slow response and low energy efficiency caused by the lack of dynamic adaptation capability when facing dual changes in time and space in existing smart home systems.

[0005] Firstly, a home scene adaptive intelligent linkage control method is provided, including:

[0006] A fusion dataset is constructed based on the first environmental parameter, the second environmental parameter, clock information, and environmental layout parameters of each area in the home environment. The fusion dataset includes: the fluctuation range of the first environmental parameter within a preset time period, the first deviation value of the first environmental parameter at the current time, the second deviation value of the second environmental parameter at the current time, and the environmental layout parameters. The end time of the preset time period is the current time, which is determined by the clock information.

[0007] If a target event occurs, an update vector is determined based on the historical operating data of each household appliance. The target event includes at least one of the following: the fluctuation range exceeds the range threshold, the first deviation value exceeds the first deviation threshold, and the second deviation value exceeds the second deviation threshold.

[0008] Based on the update vector, the first deviation value, and the second deviation value, an adjustment strategy for controlling each of the home appliances is determined.

[0009] This application provides an adaptive intelligent linkage control method for home scenarios. This method constructs a fusion dataset based on first environmental parameters, second environmental parameters, clock information, and environmental layout parameters for each area within the home environment. This allows the system to comprehensively quantify the fluctuation range of the environment over time and the degree of deviation from the target value at the current moment. By introducing the fluctuation range within a preset time period and combining it with a time weight factor determined by clock information, the system can effectively identify the dynamic trend of environmental changes, thereby avoiding misjudgments caused by short-term noise or fixed thresholds. Furthermore, the first and second deviation values ​​are used to characterize the deviation states of different environmental parameters, providing precise data support for differentiated control. When a target event occurs, the system determines an update vector containing response priority weights and energy consumption weights based on the historical operating data of each home appliance. This ensures that the generation of the adjustment strategy not only depends on the current environmental requirements but also fully integrates the device's own response capabilities and energy consumption constraints, thereby achieving optimized allocation of device resources. Based on the collaborative determination of the adjustment strategy using the update vector and dual deviation values, the system can extract matching instructions from the device linkage library and perform parameter corrections for different spatial coverage areas and operating time intervals, effectively solving the problems of rigid strategies, lag in response, and low energy efficiency in traditional control methods. Furthermore, by evaluating the matching degree between the operation plan and the spatial distribution characteristics and conducting iterative optimization, the consistency and stability of the control results throughout the house are further ensured, significantly improving the comfort of the home environment and the energy efficiency of the system.

[0010] Secondly, a home scene adaptive intelligent linkage control system is provided, including:

[0011] A construction module is used to construct a fusion dataset based on the first environmental parameter, the second environmental parameter, clock information, and environmental layout parameters of each area in the home environment. The fusion dataset includes: the fluctuation range of the first environmental parameter within a preset time period, the first deviation value of the first environmental parameter at the current time, the second deviation value of the second environmental parameter at the current time, and the environmental layout parameters. The end time of the preset time period is the current time, which is determined by the clock information.

[0012] The first determining module is used to determine an update vector based on the historical operating data of each household appliance if a target event occurs. The target event includes at least one of the following: the fluctuation range exceeds a range threshold, the first deviation value exceeds a first deviation threshold, and the second deviation value exceeds a second deviation threshold.

[0013] The second determining module is used to determine the adjustment strategy for controlling each of the home appliances based on the update vector, the first deviation value, and the second deviation value. Attached Figure Description

[0014] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0015] Figure 1 A flowchart illustrating the steps of a home scene adaptive intelligent linkage control method provided in this application embodiment;

[0016] Figure 2 A flowchart illustrating yet another home scene adaptive intelligent linkage control method provided in this application embodiment;

[0017] Figure 3 A flowchart illustrating another home scene adaptive intelligent linkage control method provided in this application embodiment;

[0018] Figure 4 A flowchart illustrating another home scene adaptive intelligent linkage control method provided in this application embodiment;

[0019] Figure 5 A flowchart illustrating another home scene adaptive intelligent linkage control method provided in this application embodiment;

[0020] Figure 6 A flowchart illustrating another home scene adaptive intelligent linkage control method provided in this application embodiment;

[0021] Figure 7 A flowchart illustrating another home scene adaptive intelligent linkage control method provided in this application embodiment;

[0022] Figure 8 This is a structural block diagram of a home scene adaptive intelligent linkage control system provided in an embodiment of this application. Detailed Implementation

[0023] The present application will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings.

[0024] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other.

[0025] In modern smart home applications, existing control methods often rely on preset fixed rules or single trigger conditions, making it difficult to effectively cope with the complexity of dynamic changes in the indoor environment over time and space. Especially in scenarios where different time periods (such as day-night temperature variations) and different spatial areas (such as the layout differences between the living room and bedroom) intertwine, traditional systems cannot flexibly adjust device linkage strategies, leading to inaccurate operation of appliances such as air conditioners and humidifiers, easily resulting in resource waste or decreased user comfort. Overcoming the technical bottlenecks caused by dual changes in time and space to achieve dynamic adaptive device linkage has become a critical issue that urgently needs to be addressed.

[0026] The following is combined with Figure 1 For an explanation of the adaptive intelligent linkage control method for home scenarios provided in this application, please refer to [link / reference]. Figure 1 , Figure 1 A flowchart illustrating the steps of a home scene adaptive intelligent linkage control method provided in an exemplary embodiment of this application includes the following steps:

[0027] Step S20: Based on the first environmental parameter, second environmental parameter, clock information and environmental layout parameter of each area in the home environment, construct a fusion dataset; the fusion dataset includes: the fluctuation range of the first environmental parameter within a preset time period, the first deviation value of the first environmental parameter at the current time, the second deviation value of the second environmental parameter at the current time, and the environmental layout parameter. The end time of the preset time period is the current time, which is determined by the clock information.

[0028] This step aims to integrate multi-source heterogeneous data in the home environment (including spatially distributed environmental parameters, temporal information, and room layout) into a unified structured dataset, providing a data foundation for subsequent adaptive control decisions.

[0029] A home environment can include various types of home appliances, such as humidifiers, air conditioners, and air purifiers. Therefore, different types of environmental parameters can be collected from the home environment, such as temperature and humidity parameters. To distinguish between different types of environmental parameters, they can be named as the first environmental parameter and the second environmental parameter. The first environmental parameter can represent the temperature parameter, and the second environmental parameter can represent the humidity parameter. Of course, the first environmental parameter can also represent the humidity parameter, and the second environmental parameter can represent the temperature parameter. There is no specific limitation, as long as they represent different types of parameters.

[0030] It is understandable that a home environment typically includes multiple areas, such as a kitchen, living room, balcony, bedroom one, bedroom two, and bedroom three. Each area requires different environmental parameters, such as humidity and temperature. For example, bedroom one is used by elderly people and can be set to a higher temperature; bedroom two is used by young men and can be set to a lower temperature. This application can collect first and second environmental parameters for different areas of the home environment using various types of data acquisition devices, such as temperature sensors and humidity sensors, placed in different areas. Further, these parameters can be obtained and processed by a processing device (such as a server, host computer, or mobile terminal) to perform subsequent control based on the processing results. The processing device can establish a communication connection (wireless or wired) with the data acquisition devices and then send acquisition commands to the data acquisition devices to obtain the first and second environmental parameters for each area from each data acquisition device. It should be noted that when the data acquisition devices send the first and second environmental parameters to the processing device, they can bind the unique identifier of the data acquisition device to these parameters and send them to the processing device simultaneously, so that when the processing device receives these parameters, it can quickly locate the area to which the parameter belongs based on the unique identifier of the data acquisition device.

[0031] Clock information serves as the basis for time alignment of different parameters. It can categorize first and second environmental parameters collected at different times according to the time dimension, facilitating the determination of fluctuation ranges and differences. For example, the processing device may be equipped with a high-precision timing module, which can categorize the received first and second environmental parameters from various regions based on the timing of the high-precision timing module. It should be noted that when constructing the fused dataset subsequently, the current time can be determined first based on the clock information, and then used as the cutoff time to determine a preset time period within a predetermined time window. For example, if the current time is 13:00 and the predetermined time window is 1 hour, then the preset time period is 12:00-13:00.

[0032] Environmental layout parameters can come from user-inputted floor plans or automatically generated spatial models, including the area, coordinates, and connectivity of each zone. These parameters allow for the division of different zones, enabling a more accurate understanding of each zone's needs and facilitating adjustments tailored to those needs.

[0033] The fluctuation range can refer to the degree of drastic change of a first environmental parameter over a preset time period, used to identify the dynamic stability of the environment. For example, the fluctuation range can be obtained by dividing the preset time period into multiple moments, and then subtracting the first environmental parameter corresponding to adjacent moments to obtain a trend of the first environmental parameter continuously increasing, continuously decreasing, or sometimes increasing and sometimes decreasing within the preset time period. This trend can then be used as the fluctuation range.

[0034] The first deviation value can be obtained by calculating the difference between the first environmental parameter at the current moment and the first target value (such as a set temperature of 24°C), and is used to characterize the degree to which the current first environmental parameter deviates from the comfort zone; the second deviation value can be obtained by calculating the difference between the second environmental parameter at the current moment and the second target value (such as a set humidity of 50%), and is used to characterize the degree to which the current second environmental parameter deviates from the comfort zone.

[0035] The fused dataset can be a structured data record that includes at least the fluctuation range, a first deviation value, a second deviation value, environmental layout parameters, and clock information. These data can form a one-to-one correspondence and are then stored in the memory of the processing device. For example, if the temperature in the living room area is 26.5℃ at the current moment, and the fluctuation range over the past hour ending at the current moment is 2.0℃, the first deviation value is +2.5℃, and the second deviation value is -10%, then the constructed fused dataset could be (living room area; 13:00; 26.5℃; 2.0℃; +2.5℃; -10%).

[0036] This application stores the fluctuation range, the first deviation value, the second deviation value, the environmental layout parameters, and the clock information in a one-to-one correspondence, forming the basis for subsequent decision-making. This provides a digital foundation that comprehensively reflects the spatiotemporal environmental characteristics for the process control of smart homes, thereby significantly improving the granularity and accuracy of the processing equipment's perception of the environmental state.

[0037] Step S30: If the target event occurs, determine the update vector based on the historical operating data of each household appliance. The target event includes at least one of the following: fluctuation range exceeding the range threshold, first deviation value exceeding the first deviation threshold, and second deviation value exceeding the second deviation threshold.

[0038] The target event is the logical condition that triggers the entry into the adjustment strategy generation mode, and its function is to realize the automatic perception and response to environmental anomalies. The determination of the target event is based on the comparison results of key indicators in the fusion dataset constructed above with the corresponding preset thresholds. The key indicators here include at least one of the following: fluctuation range, first deviation value, and second deviation value.

[0039] The range threshold, the first deviation threshold, and the second deviation threshold can all be determined based on human experience, historical operating data of household appliances, etc. The range threshold can be a range of values ​​used to assess the drastic change in the first environmental parameter; the first deviation threshold can be a range of values ​​used to assess the deviation of the first environmental parameter from the comfort zone; and the second deviation threshold can be a range of values ​​used to assess the deviation of the second environmental parameter from the comfort zone. For example, the range threshold could be ±1.5℃, the first deviation threshold could be ±2℃, and the second deviation threshold could be ±10%.

[0040] It is understood that the processing equipment of this application can determine that the target event has occurred when the fluctuation range exceeds ±1.5℃, or when the first deviation value exceeds ±2℃, or when the second deviation value exceeds ±10%. As long as at least one of the above conditions is met, it is determined that the target event has occurred.

[0041] Historical operating data refers to the record of the operating performance of each household appliance over a past period, used to measure the responsiveness and energy consumption characteristics of the equipment. This includes, for example, historical response time, historical energy consumption data, and preset energy consumption limits. Historical response time refers to the average delay from receiving a control command to the actual execution of the appliance (e.g., compressor starting, fan starting). This can be obtained by averaging the delays of the appliance's past 10 starts. Historical energy consumption data refers to the average power consumption of the appliance during operation or the power consumption within a single adjustment cycle. This can be collected through smart sockets or electricity meters, and the energy consumption over the past hour or the past three runs can be calculated. Preset energy consumption limits refer to the set maximum allowable energy consumption value, which can be the limit for a single device or the global total energy consumption limit. The unit is consistent with the historical energy consumption data. This limit can be set by the user based on historical data or automatically generated based on energy-saving modes; this application does not impose any restrictions on this.

[0042] The update vector can be a set of multi-dimensional parameters generated based on the historical operating data of each home appliance. Its source is the statistical analysis of the past performance data of the home appliances. For example, after normalizing the historical response time and historical energy consumption data, a comprehensive score for each home appliance is obtained by weighted summation. Then, different adjustment priorities and magnitude coefficients are assigned according to the scores. Finally, the adjustment priorities and magnitude coefficients are used as the update vector.

[0043] This step is executed upon detecting abnormal environmental parameters. By incorporating the historical characteristics of individual home appliances, the updated vector not only reflects environmental demands but also integrates the actual load-bearing capacity and response characteristics of the appliances. This significantly improves the targeting and feasibility of the control strategy, avoiding response lag or overload operation caused by ignoring differences in home appliances.

[0044] Step S40: Based on the update vector, the first deviation value, and the second deviation value, determine the adjustment strategy for controlling each household appliance.

[0045] The adjustment strategy can refer to a set of control instructions that guide various home appliances to perform specific actions, including equipment power adjustment values, operating speed adjustment values, and execution timing arrangements. The process of determining the adjustment strategy can involve using the update vector, the first deviation value, and the second deviation value as joint input parameters, and solving them through a preset control algorithm. Specifically, the first deviation value is used, for example, for power correction of temperature-regulating devices (such as air conditioners and underfloor heating), and the second deviation value is used, for example, for speed correction of humidity-regulating devices (such as humidifiers and dehumidifiers). The update vector is then used to perform weighted optimization on the above correction amounts to balance response speed and energy consumption constraints.

[0046] For example, when the first deviation is +3℃ (requiring cooling) and the second deviation is -15% (requiring humidification), and the air conditioner's update vector has a high response priority weight, the adjustment strategy generated by the processing device will instruct the air conditioner to operate at higher power to quickly eliminate the temperature deviation. Simultaneously, it will adjust the humidifier's atomization rate according to its energy consumption weight, ensuring that the total energy consumption limit is not exceeded while meeting humidity requirements. Through the coordinated operation of the update vector and the two deviation values, the processing device can achieve precise cross-device, multi-dimensional linkage: the deviation value indicates what to adjust and how much, while the update vector determines the strategy of how to adjust and which to adjust first. This mechanism effectively avoids the one-sidedness of single-parameter control, enabling the home environment to achieve the dual goals of improved comfort and energy-saving optimization under complex and ever-changing conditions.

[0047] This application achieves refined quantification of environmental spatiotemporal characteristics by constructing a fusion dataset containing fluctuation range and dual deviation values. By defining a target event mechanism based on threshold comparison, it ensures that the system initiates adjustment only when necessary, reducing ineffective computation. Furthermore, by introducing update vectors based on historical operating data, the adjustment strategy acquires device-level adaptive capabilities. Based on this, by using the weighted correction of deviation values ​​with update vectors, the processing device can dynamically balance the response speed and energy consumption of different devices, ultimately generating an optimal adjustment strategy that meets both environmental requirements and device characteristics. This solves the technical problems of rigid device linkage, low energy efficiency, and poor user experience in existing technologies.

[0048] In an optional embodiment, such as Figure 2 As shown, this application provides an optional method embodiment for constructing a fused dataset based on first environmental parameters, second environmental parameters, clock information, and environmental layout parameters of each area in a home environment. This method embodiment includes the following steps:

[0049] Step S201: Obtain the first initial environmental parameters and the second initial environmental parameters of the first area, where sensors are deployed.

[0050] The first region can refer to the spatial area in a home environment where physical sensors are pre-installed, such as the living room or master bedroom—core activity areas. The first initial environmental parameter is, for example, real-time temperature data, and the second initial environmental parameter is, for example, real-time humidity data. These parameters can be directly collected by temperature and humidity sensor nodes deployed within the first region. The temperature and humidity sensors can convert the collected analog signals into digital signals at a preset sampling frequency (e.g., once every 5 minutes) and transmit them to the processing unit via a wireless communication protocol. The existence of the first region provides a reliable baseline data source for the entire processing device, used for subsequent extrapolation of sensorless areas and assessment of the overall environmental state. For example, a sensor numbered S01 is deployed in the living room area, and at the current moment, it collects a first initial environmental parameter of 23.5℃ and a second initial environmental parameter of 55%. By directly acquiring these measured data, the accuracy of the foundational part of the fused dataset can be ensured, providing a solid anchor for subsequent interpolation calculations.

[0051] Step S202: Based on the environmental layout parameters, an interpolation algorithm is used to determine the first initial environmental parameters and the second initial environmental parameters of the second region. No sensors are deployed in the second region.

[0052] The second region can refer to the spatial area in a home environment where sensors are not directly deployed due to cost constraints or installation difficulties, such as a corridor, storage room, or part of a secondary bedroom. Environmental layout parameters include, for example, floor plan data, geometric dimensions of each room, wall location coordinates, and the distribution of doors and windows; these data constitute spatial constraints. Interpolation algorithms are mathematical processing methods used to estimate the values ​​of unknown points (second region) based on data from known points (first region). Examples of interpolation algorithms include inverse distance weighted interpolation or Kriging interpolation. During the calculation process, the processing device can first read the environmental layout parameters, identify the spatial adjacency and obstruction between the first and second regions (e.g., load-bearing walls reduce parameter correlation due to reduced airflow), and then use the first and second initial environmental parameters already obtained for the first region, combined with the Euclidean distance or path distance between the regions, to calculate the estimated value of the corresponding location in the second region. For example, assuming the temperature in the bedroom (zone 1) is 22.8℃ and the temperature in the living room (zone 1) is 23.5℃, and a corridor (zone 2) without sensors is located between them, 3 meters from the bedroom and 2 meters from the living room, if the inverse distance-weighted method is used for calculation, the estimated temperature of the corridor is approximately 23.22℃. By introducing environmental layout parameters to constrain the interpolation process, errors caused by simple distance calculations (such as ignoring the wall insulation effect) can be effectively avoided, making the parameter inference for the second zone more consistent with physical reality, thereby filling the monitoring blind spot.

[0053] Step S203: The first initial environmental parameters and the second initial environmental parameters of the first region and the second initial environmental parameters of the second region are determined as the first environmental parameters and the second environmental parameters of each region.

[0054] This step integrates the measured data and estimated data obtained in the first two steps. After this step, each logical partition in the home environment (whether it's the first area with sensors deployed or the second area without sensors) possesses complete first and second environmental parameters. This integration eliminates spatial data gaps, forming a comprehensive set of environmental parameters. This set of environmental parameters includes not only high-precision measured data but also estimated data corrected through spatial modeling, ensuring the continuity and completeness of the subsequently constructed dataset in the spatial dimension. For example, the processing device uniformly labels the measured values ​​in the living room (23.5℃, 55%), the bedroom (22.8℃, 58%), and the estimated value in the hallway (23.22℃, 56%) as the standard environmental parameters for their respective areas, serving as a unified input source for subsequent calculations of fluctuation ranges and deviation values.

[0055] Step S204: For each region, calculate the difference between the maximum and minimum values ​​of the first environmental parameter within a preset time period, and use this difference as the original fluctuation range.

[0056] The preset time period is a continuous duration ending at the current time, such as the past hour or the past 30 minutes. The original fluctuation range reflects the magnitude of change in the primary environmental parameter (such as temperature) within this time period and is a fundamental indicator for measuring environmental stability. The calculation method involves iterating through all sampling points within the time period, finding the maximum value Tmax and the minimum value Tmin, and then performing the subtraction operation Rangeraw = Tmax - Tmin. For example, in the living room area, if the highest temperature recorded in the past hour was 23.8℃ and the lowest was 23.0℃, then its original fluctuation range is 0.8℃. This indicator can intuitively reflect the degree of drastic change in environmental parameters within a short period. If the original fluctuation range is large, it indicates that the area is significantly affected by heat source interference or air conditioning start-up and shutdown, requiring more attention from processing equipment.

[0057] Step S205: Determine the time weight factor corresponding to the preset time period based on the clock information, and multiply the original fluctuation range by the time weight factor to obtain the fluctuation range.

[0058] The clock information refers to the current specific time (e.g., hour and minute) and date information (e.g., season, weekday / weekend). The time weighting factor is a coefficient set according to time characteristics, used to assign different levels of importance or semantic meaning to environmental fluctuations at different times. This is because the same temperature fluctuation has different impacts on user comfort at different times. For example, a slight fluctuation in the early morning may be due to natural warming, which is a normal phenomenon and has a lower weight; while the same fluctuation in the hot afternoon may indicate insufficient cooling and has a higher weight. The processing device may have a pre-set time-weight mapping table, which is used to look up the table based on the clock information or to calculate the current time weighting factor Wt using a function. Then, the original fluctuation range obtained above is multiplied by this factor, i.e., Range = Rangeraw × Wt, to obtain the final fluctuation range. For example, if the current time is 14:30 (afternoon), and the time weighting factor is set to 1.2, while the weighting factor for 02:00 AM is 0.8; for the original fluctuation of 0.8℃ in the living room mentioned above, if calculated in the afternoon, the weighted fluctuation range would be 0.8 × 1.2 = 0.96; if calculated in the early morning, it would be 0.8 × 0.8 = 0.64. By introducing the time weighting factor, the processing device can encode the contextual information of the time dimension into the fluctuation range index, making the subsequent event judgment logic more intelligent and able to distinguish between normal diurnal temperature differences and abnormal environmental changes.

[0059] Step S206: Calculate the difference between the first environmental parameter and the first target value as the first deviation value, and calculate the difference between the second environmental parameter and the second target value as the second deviation value.

[0060] The first target value and the second target value are the user-preset or default ideal temperature and humidity values ​​of the processing device, respectively. The first target value can be set using historical data from a first home appliance (e.g., an air conditioner); the second target value can be set using historical data from a second home appliance (e.g., a humidifier). The first deviation value indicates the degree to which the current temperature deviates from the ideal state, calculated using the formula Deviation1 = Tcurrent - Ttarget; the second deviation value indicates the degree to which the current humidity deviates from the ideal state, calculated using the formula Deviation2 = Hcurrent - Htarget. These two deviation values ​​have positive and negative signs; positive values ​​indicate values ​​higher than the target value, and negative values ​​indicate values ​​lower than the target value. They directly indicate the direction of adjustment (heating / cooling, humidifying / dehumidifying). For example, if the current temperature in the living room is 23.5℃ and the first target value is 24.0℃, then the first deviation value is -0.5℃; if the current humidity is 55% and the second target value is 50%, then the second deviation value is +5%. By quantifying these deviations, the processing device can accurately grasp the gap between the current environmental conditions and the desired conditions in each area, providing a direct basis for generating specific adjustment strategies.

[0061] Step S207: Match the current time, the spatial coordinates of each region with the corresponding fluctuation range, first deviation value and second deviation value of each region to obtain the fused dataset.

[0062] Spatial coordinates are the geometric location identifiers of each area within the home's floor plan, which can be the (x, y) coordinates of the room's center point or the index number of a grid cell. This step involves structurally binding all the previously calculated feature data (fluctuation range, first deviation value, second deviation value) with the timestamp (current moment) and spatial location (spatial coordinates). The resulting fused dataset is a multi-dimensional data structure, where each row or data object fully describes the environmental state characteristics of a specific area at a specific moment. For example, the generated data record might look like this: {Time: 14:30, Coordinates: (0, 0), Area: Living Room, Fluctuation Range: 0.96, Temperature Deviation: -0.5, Humidity Deviation: +5}. This one-to-one structured storage method ensures that the dataset not only contains numerical information but also retains rich spatiotemporal context, facilitating subsequent steps to quickly retrieve historical trends of specific areas or perform spatial correlation analysis, thereby achieving precise zoning control.

[0063] Through the above steps, the present application effectively compensates for the problem of missing data in some areas caused by uneven sensor deployment by using the interpolation algorithm in combination with the environmental layout parameters, achieving the global coverage of the whole-house environmental parameters; at the same time, by introducing a time weight factor based on clock information to weight the original fluctuation range, the environmental fluctuation data is given time semantics, enabling the processing device to more sensitively identify abnormal environmental changes at different times; finally, by tightly binding the time and space coordinates with various deviation and fluctuation indicators, a high-dimensional fusion data set is constructed, laying a solid data foundation for the subsequent fine-grained linkage control based on the spatial distribution characteristics.

[0064] In an optional embodiment, as Figure 3 shown, the present application provides an optional method embodiment for determining an update vector according to the historical operation data of each household electrical appliance. This method embodiment includes:

[0065] Step S301, compare the historical response duration of each household electrical appliance with a preset standard response duration threshold, and allocate a response priority weight according to the comparison result.

[0066] Among them, the historical response duration may refer to the time interval experienced by the household electrical appliance from receiving a control instruction to actually completing the adjustment of environmental parameters (such as the temperature change reaching the set amplitude). This data comes from the statistical records of the device operation log or the cloud historical database. The standard response duration threshold is a benchmark value preset according to the average performance indicators of similar devices in the home environment, and is used to measure the speed of the device response. The response priority weight is a numerical coefficient, and its function is to quantify the execution priority order of the device in the subsequent linkage control; when the historical response duration is less than the standard response duration threshold, it indicates that the device responds quickly, and a larger response priority weight is allocated; conversely, if the historical response duration is greater than or equal to the standard response duration threshold, a smaller weight is allocated. Specifically, the weight can be determined by constructing a linearly decreasing function or a piecewise assignment rule. For example, if the standard response duration threshold is set to 120 seconds, and the historical average response duration of a variable-frequency air conditioner is 60 seconds, then the response priority weight is allocated as 0.9; if the historical average response duration of an old fixed-frequency air conditioner is 180 seconds, then the response priority weight is allocated as 0.4. Through this comparison and allocation mechanism, it can be ensured that when a target event occurs, the processing device preferentially schedules the device with a fast response speed, thereby shortening the recovery time of environmental parameters.

[0067] Step S302, compare the historical energy consumption data of each household electrical appliance with a preset energy consumption upper limit, and allocate an energy consumption weight according to the comparison result.

[0068] Historical energy consumption data refers to the average or cumulative energy consumption of household appliances within a preset statistical period (such as the past month or quarter). This data comes from the metering records of smart meters or the energy consumption monitoring module built into the devices. The preset energy consumption limit is the maximum allowable energy consumption value set based on the total household electricity load limit or energy-saving target, used to constrain the operation of high-energy-consuming devices. Energy consumption weight is a coefficient reflecting the economic efficiency of device operation, its function being to curb the excessive use of high-energy-consuming devices. When historical energy consumption data is close to or exceeds the preset energy consumption limit, it indicates that the device has low energy efficiency or high operating costs, and is assigned a smaller energy consumption weight; conversely, if historical energy consumption data is far below the preset energy consumption limit, the assigned energy consumption weight is larger. For example, assuming the preset energy consumption limit is 2.5 kWh / hour, if a humidifier's historical energy consumption data is 1.0 kWh / hour, then the assigned energy consumption weight is 0.95; if an older electric heater's historical energy consumption data is 2.4 kWh / hour, then the assigned energy consumption weight is 0.3. By introducing energy consumption weights, the processing equipment can automatically guide resources toward low-energy-consuming equipment while meeting environmental regulation requirements, thus avoiding exceeding the overall power load limit.

[0069] Step S303: Determine the update vector based on the allocated response priority weight and the allocated energy consumption weight.

[0070] The update vector can be a multi-dimensional data set composed of response priority weights and energy consumption weights. It originates from a combination of weight values ​​calculated in the previous two steps. This application can obtain the update vector by vectorizing the allocated response priority weights and energy consumption weights. Formally, it can be represented as update vector V = [wresponse, wenergy], where wresponse represents the response priority weight and wenergy represents the energy consumption weight. This update vector serves as the core input parameter for determining the subsequent adjustment strategy, used to correct the device power or rate parameters in the control command sequence. Specifically, the response priority weight and energy consumption weight work together in the update vector to depict the capability profile of each household appliance: the response priority weight ensures rapid response capability under large environmental deviations, while the energy consumption weight ensures long-term operational economy. For example, for a new air conditioner with fast response and low energy consumption, both components in its update vector are relatively high, and the processing device will assign it a larger power adjustment range when generating the adjustment strategy; while for an older device with slow response and high energy consumption, both components in its update vector are relatively low, and the processing device will limit its output or use it only as an auxiliary adjustment means. By integrating these two weights into an update vector, dynamic matching between individual equipment characteristics and environmental adjustment requirements is achieved, enabling differentiated response strategies for the same environmental deviation on different equipment, thereby achieving optimal allocation of equipment resources.

[0071] This application integrates response priority weights generated by comparing historical response times with standard thresholds and energy consumption weights generated by comparing historical energy consumption data with upper limits to construct an update vector that reflects the real-time efficiency and economy of equipment execution. Based on this, the response priority weights ensure that critical equipment (such as rapid-cooling air conditioners) receives higher control authority under emergency deviations, effectively shortening environmental recovery time. Simultaneously, the energy consumption weights inhibit the abuse of high-energy-consuming equipment, guiding processing equipment to prioritize the use of high-efficiency devices, thus reducing overall energy consumption. The resulting update vector, as the device-side coefficient of the adjustment strategy, is multiplied by the environmental deviation value, enabling the final generated power or rate adjustment to automatically adapt to the actual capabilities of each device. This achieves differentiated and precise control of different devices under the same environmental deviation, significantly improving the flexibility and energy-saving effect of adaptive intelligent linkage in home scenarios.

[0072] In an optional embodiment, such as Figure 4 As shown, this application provides an optional method embodiment for determining the adjustment strategy for controlling each of the home appliances based on the update vector, the first deviation value, and the second deviation value. This method embodiment includes:

[0073] Step S401: Based on the current spatial coverage and operating time interval of each household appliance, extract the control instruction sequence that matches the spatial coverage and operating time interval from the preset device linkage library.

[0074] Among them, the spatial coverage range can refer to the set of areas in the physical space where home appliances can effectively adjust environmental parameters. It is derived from the mapping relationship between home environment layout parameters and equipment rated power, and is used to define the functional boundaries of the equipment. The operating time interval can refer to the time period during which the equipment is allowed or expected to operate. It can be determined based on user habit data or preset work and rest schedules, and is used to avoid starting and stopping the equipment during unnecessary periods. The equipment linkage library is a database that pre-stores standard control logic for various scenarios, including basic instruction templates for different space types (such as living room, bedroom, kitchen) at different times (such as daytime, nighttime, sleep mode).

[0075] For example, when the processing device detects that the air conditioner's current spatial coverage area is the master bedroom, and the current clock information is within the nighttime operating time range of 22:00-06:00, it extracts a matching control command sequence from the device linkage library. This sequence may include basic commands such as disabling strong wind mode, setting the target temperature to 26℃, and automatic fan speed adjustment, rather than the rapid cooling commands commonly used during the day. Similarly, for an exhaust fan covering an open kitchen, if the operating time range is during peak cooking hours (11:00-13:00, 17:00-19:00), the extracted command sequence includes high-speed standby and odor-linked activation commands.

[0076] This two-dimensional retrieval mechanism, based on spatial coverage and operating time interval, ensures that the extracted control command sequence is naturally scene-adaptable, avoiding the execution of incorrect control logic in unsuitable spaces or time periods. This safeguards the safety and compliance of the home environment and provides an accurate benchmark template for subsequent parameter correction.

[0077] Step S402: Using the update vector, the first deviation value, and the second deviation value as input parameters, the device power or rate parameters in the control command sequence are corrected to generate an adjustment strategy.

[0078] The update vector is a composite parameter composed of response priority weight and energy consumption weight determined based on the above embodiments, used to characterize the device's capability scaling factor in the current state; the first deviation value is the difference between the current first environmental parameter (e.g., temperature) and the target value, serving as the incremental base value for temperature-related parameters; the second deviation value is the difference between the current second environmental parameter (e.g., humidity) and the target value, serving as the incremental base value for humidity-related parameters. The correction process can refer to dynamically calculating and adjusting the numerical parameters (e.g., power percentage, fan speed, atomization rate, etc.) in the extracted basic instruction sequence using the above three input parameters.

[0079] Specifically, the correction logic can be expressed as: Corrected power = Base power × (1 + First deviation value coefficient) × Energy consumption weight in the update vector. For example, if the air conditioning cooling power in the extracted base instruction sequence is 60%, the current first deviation value is +3℃ (indicating that the room temperature is too high), the corresponding deviation coefficient is 0.1 / ℃, and the energy consumption weight in the update vector is set to 1.2 due to the device's historical fast response, then the corrected power parameter is calculated as 60% × (1 + 3 × 0.1) × 1.2 = 93.6%. Similarly, for the atomization rate of a humidifier, if the base rate is 10ml / min, the second deviation value is -15% (indicating that the air is dry), and the response priority weight in the update vector is 0.9 (indicating that it needs to be slightly suppressed to prevent overshoot), then the corrected rate is 10 × (1 + 15 × 0.05) × 0.9 ≈ 15.75ml / min.

[0080] By applying the update vector, the first deviation value, and the second deviation value together to the control command sequence, dynamic coupling between the general command template and the real-time environmental state and the actual capabilities of the equipment is achieved. This mechanism enables the same basic command for cooling a living room to output drastically different execution power when faced with small and large temperature differences. This not only improves the control accuracy but also prevents the equipment from overloading under extreme deviations through the constraint of the update vector, thus enhancing the robustness of the processing equipment.

[0081] Optionally, this application provides a generation regulation strategy, including:

[0082] Based on the historical response time of each home appliance, the execution time of different types of devices in the control command sequence is scheduled in a time-sharing manner so that home appliances with fast response times are executed first and home appliances with slow response times are executed later.

[0083] The historical response time can be the sum of the appliance startup delay, parameter ramp-up time, and stable convergence time. For example, for a certain brand of air conditioner, the processing device records that the average time it takes for it to operate from standby mode in cooling mode until the set temperature deviation is less than 0.5℃ is 180 seconds; while for a certain model of humidifier, the average time for its atomization rate to increase to the target value and remain stable is 45 seconds. Time-sharing scheduling can refer to allocating different instruction issuance times or execution start times for different types of appliances on the time axis based on the above historical response times, rather than all devices acting synchronously at the same time. Specifically, the processing device can first read the control instruction sequence containing device power or rate parameters generated in the above embodiment, and then traverse each device object in the sequence to extract its corresponding historical response time value. Then, according to a preset time offset algorithm, the execution time corresponding to the device with a longer historical response time is postponed, or the execution time corresponding to the device with a shorter historical response time is advanced. Through this scheduling method, the actions of multiple high-energy-consuming or high-inertia devices that might have been triggered at the same time are staggered in the time dimension.

[0084] Fast response speed refers to the device characteristic where the historical response time is less than a preset fast response threshold (e.g., 60 seconds), while slow response speed refers to the device characteristic where the historical response time is greater than or equal to this threshold. Priority execution means that the start time of the control command sequence for this type of device is set to the initial moment (t0) of the current scheduling cycle, or has the smallest time offset relative to other slower devices; delayed execution means that the start time of this type of device is set to t0 + Δt, where Δt is a positive time delay, which is usually proportional to the difference in response time between devices. For example, in the living room scenario above, if the humidifier is determined to be a fast-response device (45 seconds) and the air conditioner a slow-response device (180 seconds), the processing device will set the execution time of the humidifier to 14:30:00, while delaying the execution time of the air conditioner to 14:32:15 (i.e., a delay of approximately 135 seconds, to match the synchronization of both reaching a stable state, or simply for off-peak startup). The core of this execution strategy is to use the time difference to decouple physical interference and electrical shocks between devices. Specifically, when fast-response devices (such as humidifiers or fans) are activated first, a basic environmental flow field can be quickly established or the local microenvironment can be initially adjusted. Then, slower-response devices (such as air conditioner compressors or electric heaters) intervene to conduct a significant energy exchange. This not only avoids the problems of condensation or uneven humidity distribution caused by direct clashes between hot and cold air currents in the space, but also effectively smooths out the instantaneous load peaks of household electrical distribution equipment. By delaying the activation of high-power, slow-speed devices before low-power, fast-speed devices, the grid current exhibits a stepped increase rather than a pulsed spike, significantly reducing the instantaneous stress on household circuit breakers and lines. Furthermore, this stepped optimization process, starting with faster devices and then slowing down, allows the overall environmental control to reach a convergence state more quickly. Fast-speed devices complete the coarse adjustment first, followed by the fine adjustment of slower devices, thereby improving the stability and comfort of the final environmental parameters.

[0085] In an optional embodiment, such as Figure 5 As shown, this application provides an optional embodiment of a home scene adaptive intelligent linkage control method, including the following steps:

[0086] Step S501: After controlling the operation of each household appliance according to the adjustment strategy, evaluate the matching degree between the current operation plan and the spatial distribution characteristics of each area in the home environment.

[0087] This step aims to quantify the degree of fit between the implemented control strategy and the actual spatial environment requirements to determine whether further optimization is needed. Specifically, the evaluation process compares the actual environmental parameters of each area, collected in real time by a sensor network, with the preset target parameters in the adjustment strategy. Spatial distribution characteristics refer to the specific environmental distribution patterns formed by differences in area, orientation, obstructions, and human activity density in different areas of a home environment. For example, the living room area typically has a larger heat capacity and faster airflow, while the bedroom area is relatively enclosed and more sensitive to temperature fluctuations. The degree of fit can be calculated using the root mean square error or weighted average deviation method, mapping the deviation between the actual temperature and humidity values ​​of each area and the target values ​​to a value between 0 and 1. The closer the value is to 1, the higher the degree of fit. For example, if the adjustment strategy sets the target temperature for the entire house to 24℃, and after execution, the actual measured temperatures in the living room are 23.8℃, the bedroom 24.1℃, and the study 23.9℃, the calculated overall temperature deviation is minimal, with a matching degree of approximately 0.95. Conversely, if a corner area experiences a temperature as high as 26℃ due to a dead airflow, the overall matching degree will drop to 0.7. Through this quantitative assessment, the processing equipment can accurately identify blind spots or over-adjusted areas, providing data support for subsequent iterative decisions.

[0088] In step S502, if the matching degree is lower than the matching degree threshold, the judgment process of the target event is re-triggered, and the fusion dataset is updated based on the updated environmental parameters. The steps of determining the update vector and determining the adjustment strategy are iteratively executed until the matching degree is greater than or equal to the matching degree threshold.

[0089] This step establishes a closed-loop feedback mechanism to ensure the processing equipment has self-healing and continuous optimization capabilities when the initial adjustment fails to meet expectations. The matching degree threshold is a pre-set minimum acceptable standard, for example, 0.85. When the evaluation result is below this value, the processing equipment determines that the current operating scheme has failed to effectively solve the problem of uneven spatial distribution. In this case, re-triggering the target event is not a simple repetition, but rather treats the insufficient matching degree as a new trigger condition, activating the judgment logic defined in the above embodiment. The processing equipment immediately calls the sensors to obtain the latest environmental parameters (i.e., the updated environmental parameters). These parameters reflect the real-time state after the previous round of adjustment and possible external disturbances (such as sudden changes caused by opening windows for ventilation). Based on this new data, the processing equipment reconstructs the fused dataset, updates the fluctuation range, the first deviation value, and the second deviation value, and then recalculates the update vector reflecting the historical response characteristics of the equipment. Based on this, the processing equipment executes the adjustment strategy generation step again, generating revised control commands. For example, if the bedroom humidity is still too low after the first iteration, the strategy generated in the second iteration may increase the priority of the humidifier's atomization rate or adjust the air conditioner's airflow direction to avoid localized overcooling caused by direct airflow. This iterative process runs cyclically, with each round making fine adjustments based on the latest feedback data, until the calculated matching degree reaches or exceeds the matching degree threshold, at which point the iteration stops and the current operating scheme is maintained. This mechanism effectively avoids the limitations of single-time adjustments, ensuring the long-term stability and comfort of the home environment under complex and dynamic conditions.

[0090] This application achieves closed-loop optimization of home environment control by introducing a matching degree evaluation and iterative execution mechanism. By feeding back the effect of the current operating scheme to the input, the processing device can dynamically sense subtle changes in spatial distribution characteristics and automatically initiate a re-triggering process when the matching degree is insufficient. In this process, the updated environmental parameters are combined with the real-time updates of the fused dataset, ensuring that each iteration is a precise correction based on the latest state, rather than blind repetition. The repeated deduction of update vectors and adjustment strategies allows parameters such as device power and rate to gradually approach the optimal solution, effectively eliminating local over-adjustment or under-adjustment caused by complex spatial structure or sudden environmental changes. Ultimately, this multi-level iteration not only improves the control accuracy but also enhances the processing device's adaptability to sudden environmental changes, ensuring a high degree of consistency of the whole-house environment in both time and space dimensions.

[0091] Optionally, the process of re-triggering the judgment of the target event includes:

[0092] When the matching degree is lower than the matching degree threshold, at least one of the upper limit of the range threshold, the upper limit of the first deviation threshold, and the upper limit of the second deviation threshold is reduced by a preset step size.

[0093] When the assessed matching degree value is less than the matching degree threshold, it indicates that the current control strategy has failed to effectively improve environmental quality. The processing equipment determines that the target event judgment process needs to be retried to start a new round of iteration. At this time, the processing equipment performs a threshold adjustment operation, that is, reduces the severity of the triggering conditions by a preset step size. The preset step size is a small fixed value or proportional factor, such as reducing the upper limit of the temperature-related range threshold by 0.1℃ each time, that is, adjusting the range threshold to (1.4℃, -1.5℃); or reducing the upper limit of the temperature-related first deviation threshold by 0.2℃ each time, that is, adjusting the first deviation threshold to (1.8℃, -2℃); or reducing the upper limit of the humidity-related second deviation threshold by 1% each time, that is, adjusting the second deviation threshold to (9℃, -10℃). This mechanism ensures that when conventional control fails, the processing equipment can detect more subtle environmental anomalies by increasing sensitivity, thereby avoiding falling into an ineffective cycle.

[0094] In an optional embodiment, such as Figure 6 As shown, this application provides an optional method embodiment for evaluating the matching degree between the current operating scheme and the spatial distribution characteristics of various areas in a home environment, including the following steps:

[0095] Step S601: Divide the home environment into multiple spatial grid units and obtain the first and second actual environmental parameters within each spatial grid unit;

[0096] In this context, a spatial grid cell refers to the smallest computational area formed by discretizing a continuous physical space (i.e., the home environment) to quantify the effectiveness of environmental control. The first actual environmental parameter may refer to temperature data, and the second actual environmental parameter may refer to humidity data. These parameters can be obtained in real-time through a sensor network deployed in each area, or calculated using interpolation algorithms based on surrounding sensor data in areas without sensor deployment. By dividing the home environment into grids, the processing device can overcome the limitations of traditional whole-house average assessments and accurately capture spatial heterogeneity. For example, areas such as the living room and bedroom can be divided into several square grid cells with a resolution of 1 meter × 1 meter. For a specific grid cell with coordinates (x, y), the processing device directly reads the sensor reading at that location, or calculates the real-time temperature (26.5℃) and humidity (42%) using an inverse distance weighting method. This division method enables the assessment process to perceive local microenvironments, ensuring that subsequent control strategy adjustments target specific weak areas rather than a vague overall area.

[0097] Step S602: Compare the first actual environmental parameter and the second actual environmental parameter with the target value of the corresponding spatial grid cell in the adjustment strategy, and calculate the parameter deviation in each spatial grid cell;

[0098] The parameter deviation refers to the difference between the currently monitored environmental value and the preset ideal target value, representing the execution error of the current operating scheme in that local area. The target value may be derived from the adjustment strategy generated in the preceding steps, which may set differentiated control standards for different spatial grid cells (e.g., slightly lower target temperature near windows and slightly higher in the central area). The calculation process involves subtracting the target value of the corresponding cell defined in the strategy from the actual value obtained above. For example, if the target temperature of a grid cell is set to 24.0℃, and the measured first actual environmental parameter is 26.5℃, then the temperature parameter deviation of that cell is +2.5℃; if the target humidity is 50%, and the measured second actual environmental parameter is 42%, then the humidity parameter deviation is -8%. Through unit-by-unit comparison and calculation, the processing device can generate a deviation distribution matrix covering the entire home environment. This matrix intuitively reflects which areas have problems of being too cold, too hot, too dry, or too humid, providing basic data input for subsequent root mean square calculations.

[0099] Step S603: Determine the matching degree based on the root mean square value of the parameter deviation of all spatial grid cells.

[0100] The root mean square (RMS) value is a statistical indicator used to measure the dispersion or deviation of a set of data. In this embodiment, the matching degree is determined based on the square root of the average of the sum of squares of the parameter deviations (including temperature and humidity deviations, which can be calculated separately or after weighted merging) of all spatial grid cells. The specific calculation logic is as follows: First, the parameter deviation of each grid cell obtained above is squared. This step amplifies the influence weight of larger deviations, making severe local mismatches (such as severely excessive temperature in a corner) dominate the final result; then, the square deviations of all grid cells are summed and averaged; finally, the square root of the average is taken to obtain the RMS value. The smaller the RMS value, the higher the degree of fit between the actual environment and the target strategy, i.e., the higher the matching degree; conversely, the larger the RMS value, the lower the matching degree. For example, if the calculated RMS value of the temperature deviation of 100 grid cells in the whole house is 0.5℃, the matching degree is considered high, meeting the conditions for continued operation; if the RMS value reaches 2.0℃, it indicates that there is a significant local discomfort zone, and the matching degree is below the threshold. By introducing the root mean square value as a quantitative indicator of matching degree, the average comfort illusion caused by the mutual cancellation of positive and negative deviations is effectively avoided, forcing the processing equipment to prioritize the area with the largest deviation, thereby improving the environmental consistency of the overall space.

[0101] This application achieves closed-loop optimization from macro-control to micro-verification through the synergistic effect of the aforementioned technical features. Dividing the home environment into multiple spatial grid units provides a high-resolution spatial benchmark for evaluation, solving the problem of traditional methods failing to identify local hot or cold spots. Based on this, the actual parameters of each unit are compared one by one with the target values ​​in the adjustment strategy, and parameter deviations are calculated, ensuring a strict correspondence between the evaluation object and the control intention. Furthermore, the root mean square (RMSE) value of the parameter deviations of all units is used to determine the degree of matching, which not only quantifies the overall error but also highlights the impact of extreme deviations through a square operation mechanism, making the processing equipment highly sensitive to severe local mismatches. This processing logic of grid-based discretization + point-by-point comparison + RMSE aggregation can accurately reveal the true degree of matching between the operating scheme and spatial distribution characteristics. When the degree of matching is insufficient, it can accurately trigger subsequent iterative optimization processes, guiding the processing equipment to adjust the output of specific areas, thereby completely avoiding the technical drawback of global averages masking local comfort defects and significantly improving the overall control accuracy and user comfort of the home environment.

[0102] In an optional embodiment, such as Figure 7 As shown, this application provides an optional method embodiment for determining the adjustment strategy for controlling various household appliances, including the following steps:

[0103] Step S701: Obtain the preset temperature regulation accuracy threshold and humidity balance threshold;

[0104] The temperature regulation accuracy threshold refers to the maximum allowable temperature deviation set by the processing equipment to maintain a stable indoor temperature. It is used to define the critical point for fine-tuning the starting power of the first household appliance (such as an air conditioner). The humidity balance threshold refers to the maximum allowable humidity deviation set by the processing equipment to maintain comfortable indoor humidity. It is used to define the critical point for adjusting the starting rate of the second household appliance (such as a humidifier or dehumidifier). These two thresholds can be preset based on human physiological comfort models and the physical characteristics of the equipment. For example, considering that the human body is relatively sensitive to temperature changes, the temperature regulation accuracy threshold can be set to ±0.2℃ to ensure the absolute stability of the core comfort zone; while considering the relative lag in humidity perception and to avoid frequent start-stop of the equipment, the humidity balance threshold can be set to ±3%. The temperature regulation accuracy threshold and humidity balance threshold can be manually set by the user or automatically and dynamically generated by the processing equipment based on historical operating data, seasonal changes, or the current time period. There are no restrictions on this. When environmental parameters change, the above thresholds can be updated to values ​​that adapt to the new scenario. For example, the temperature regulation accuracy threshold can be automatically relaxed in sleep mode to reduce noise interference. By introducing differentiated threshold settings, the processing equipment can implement a high-precision, fast-response control strategy for temperature and a wide-range, stable control strategy for humidity, thereby improving comfort while extending the equipment's lifespan.

[0105] Step S702: Adjust the output power of the first household appliance according to the relationship between the first deviation value and the temperature regulation accuracy threshold.

[0106] The first deviation value is the difference between the current environmental parameter (real-time temperature) and the first target value (set temperature). The first household appliance is typically a device with temperature regulation functions, such as an air conditioner or electric heater. The specific execution logic of this step is as follows: the absolute value of the calculated first deviation value is compared with a preset temperature regulation accuracy threshold. If the absolute value of the first deviation value is greater than the temperature regulation accuracy threshold, it indicates that the current temperature deviates significantly from the comfort zone, and the processing device determines that aggressive adjustment is needed. In this case, the output power of the first household appliance is increased proportionally according to the extent to which the deviation exceeds the threshold, in order to quickly close the distance between the actual temperature and the target temperature. If the absolute value of the first deviation value is less than or equal to the temperature regulation accuracy threshold, it indicates that the current temperature is within a small fluctuation range, and the processing device determines that only fine-tuning is needed. In this case, the output power of the first household appliance is reduced or low-power operation is maintained to avoid temperature overshoot and frequent start-stop of the device. For example, assuming the temperature regulation accuracy threshold is 0.2℃, when the first deviation is detected to be +0.5℃, since 0.5℃ > 0.2℃, the processing device will increase the air conditioning cooling power from the current 50% to 80%. However, when the first deviation is only +0.1℃, since 0.1℃ ≤ 0.2℃, the processing device will only fine-tune the power to 52% or maintain the status quo. This differentiated power adjustment based on threshold relationships effectively solves the problem of coarse temperature fine-tuning in traditional control, ensuring that the indoor temperature is always maintained within the most sensitive comfort range for the human body.

[0107] Step S703: Adjust the output rate of the second household appliance according to the relationship between the second deviation value and the humidity balance threshold.

[0108] The second deviation value is the difference between the current environmental parameter (real-time humidity) and the second target value (set humidity). The second household appliance is typically a device with humidity control functions, such as a humidifier, dehumidifier, or fresh air handling unit. The specific execution logic of this step is as follows: the absolute value of the calculated second deviation value is compared with a preset humidity balance threshold. If the absolute value of the second deviation value is greater than the humidity balance threshold, it indicates that the current humidity environment is relatively dry or humid, exceeding the allowable balance range. The processing equipment determines that accelerated adjustment is needed, and at this time, the atomization rate or fan speed of the second household appliance is increased according to the degree of deviation. If the absolute value of the second deviation value is less than or equal to the humidity balance threshold, it indicates that the humidity is within an acceptable fluctuation range. The processing equipment determines that no drastic action is needed, and at this time, the output rate of the second household appliance is reduced or it enters standby mode to reduce energy consumption, water waste, and operating noise. For example, assuming a humidity balance threshold of 3%, when a second deviation value of -5% (i.e., excessively dry) is detected, since 5% > 3%, the processing equipment increases the humidifier's atomization rate from the base of 10 ml / min to 25 ml / min. However, when the second deviation value is -2%, since 2% ≤ 3%, the processing equipment only maintains the rate at 12 ml / min or operates intermittently. This step, along with the parallel or sequential execution mentioned above, constitutes a refined closed-loop control of environmental parameters. By flexibly adjusting the output rate based on the humidity balance threshold, repeated start-stop cycles of the humidifier under small humidity fluctuations are avoided, achieving smooth transitions in humidity control and energy-saving operation.

[0109] This application constructs a differentiated control mechanism for different types of environmental parameters by introducing temperature regulation accuracy thresholds and humidity balance thresholds. Specifically, by utilizing the temperature regulation accuracy threshold to sensitively capture the first deviation value, the first household appliance is driven to make high-precision power output adjustments, ensuring the sensitivity and stability of temperature control. At the same time, by using the humidity balance threshold to judge the tolerance of the second deviation value, the second household appliance is guided to make smooth rate adjustments, taking into account both the comfort of humidity control and the lifespan of the equipment. The synergistic effect of the temperature regulation accuracy threshold and the humidity balance threshold enables the processing equipment to adopt precise control strategies and balanced control strategies according to the different weights of temperature and humidity on human perception. This parameter-level refined control not only solves the technical problems of coarse temperature fine-tuning and sluggish humidity balance under general regulation strategies, but also forms a three-dimensional adaptive control architecture integrating parameters, equipment, and location through cooperation with the aforementioned update vector and spatial coverage, ultimately realizing efficient, comfortable, and energy-saving intelligent linkage control of the home environment under complex dynamic changes.

[0110] It should be noted that although the operations of the method of the present invention are described in a specific order in the accompanying drawings, this does not require or imply that these operations must be performed in that specific order, or that all of the operations shown must be performed to achieve the desired result. On the contrary, the steps depicted in the flowchart may be performed in a different order.

[0111] In one alternative embodiment, such as Figure 8 As shown, this application also provides a home scene adaptive intelligent linkage control system 800, including: a construction module 801, a first determining module 802 and a second determining module 803.

[0112] Module 801 is used to construct a fusion dataset based on the first environmental parameter, second environmental parameter, clock information and environmental layout parameters of each area in the home environment. The fusion dataset includes: the fluctuation range of the first environmental parameter within a preset time period, the first deviation value of the first environmental parameter at the current moment, and the second deviation value of the second environmental parameter. The preset time period ends at the current moment.

[0113] The first determining module 802 is used to determine an update vector based on the historical operating data of each household appliance if a target event occurs. The target event includes at least one of the following: fluctuation range exceeding a range threshold, first deviation value exceeding a first deviation threshold, and second deviation value exceeding a second deviation threshold.

[0114] The second determining module 803 is used to determine the adjustment strategy for controlling each household appliance based on the update vector, the first deviation value, and the second deviation value.

[0115] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the inventive concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this application.

Claims

1. A home scene adaptive intelligent linkage control method, characterized in that, include: A fusion dataset is constructed based on the first environmental parameter, second environmental parameter, clock information, and environmental layout parameter of each area in the home environment. The fused dataset includes: the fluctuation range of the first environmental parameter within a preset time period, the first deviation value of the first environmental parameter at the current time, the second deviation value of the second environmental parameter at the current time, and the environmental layout parameter. The end time of the preset time period is the current time, which is determined by the clock information. If a target event occurs, an update vector is determined based on the historical operating data of each household appliance. The target event includes at least one of the following: the fluctuation range exceeds the range threshold, the first deviation value exceeds the first deviation threshold, and the second deviation value exceeds the second deviation threshold. Based on the update vector, the first deviation value, and the second deviation value, an adjustment strategy for controlling each of the home appliances is determined.

2. The method according to claim 1, characterized in that, The fused dataset is constructed based on the first environmental parameters, second environmental parameters, clock information, and environmental layout parameters of each area in the home environment, including: Acquire first and second initial environmental parameters for a first region, where sensors are deployed. Based on the environmental layout parameters, an interpolation algorithm is used to determine the first and second initial environmental parameters of the second region, where no sensor is deployed. The first and second initial environmental parameters of the first region and the first and second initial environmental parameters of the second region are determined as the first environmental parameter and the second environmental parameter of each region. For each of the aforementioned regions, the difference between the maximum and minimum values ​​of the first environmental parameter within the preset time period is calculated as the original fluctuation range; The time weighting factor corresponding to the preset time period is determined based on the clock information, and the original fluctuation range is multiplied by the time weighting factor to obtain the fluctuation range; The difference between the first environmental parameter and the first target value is calculated as the first deviation value, and the difference between the second environmental parameter and the second target value is calculated as the second deviation value; The current time, the spatial coordinates of each region, the fluctuation range corresponding to each region, the first deviation value, and the second deviation value are mapped one-to-one to obtain the fused dataset.

3. The method according to claim 1, characterized in that, The historical operating data includes historical response time, historical energy consumption data, and preset energy consumption limits. The step of determining the update vector based on the historical operating data of each household appliance includes: The historical response time of each of the aforementioned home appliances is compared with a preset standard response time threshold, and response priority weights are assigned based on the comparison results. The historical energy consumption data of each of the aforementioned home appliances is compared with the preset energy consumption limit, and energy consumption weights are assigned based on the comparison results. The update vector is determined based on the allocated response priority weight and the allocated energy consumption weight.

4. The method according to claim 3, characterized in that, The step of determining the adjustment strategy for controlling each of the home appliances based on the update vector, the first deviation value, and the second deviation value includes: Based on the current spatial coverage and operating time interval of each of the aforementioned home appliances, extract a sequence of control instructions that matches the spatial coverage and operating time interval from a preset device linkage library; Using the update vector, the first deviation value, and the second deviation value as input parameters, the device power or rate parameters in the control command sequence are corrected to generate the adjustment strategy.

5. The method according to claim 4, characterized in that, The generation of the adjustment strategy further includes: Based on the historical response time of each of the aforementioned home appliances, the execution times of different types of devices in the control command sequence are scheduled in a time-sharing manner, so that home appliances with fast response times are executed first and home appliances with slow response times are executed later.

6. The method according to claim 1, characterized in that, The method further includes: After controlling the operation of each of the home appliances according to the adjustment strategy, the matching degree between the current operation plan and the spatial distribution characteristics of each of the areas in the home environment is evaluated. If the matching degree is lower than the matching degree threshold, the judgment process of the target event is retried, and the fused dataset is updated based on the updated environmental parameters. The steps of determining the update vector and determining the adjustment strategy are iteratively executed until the matching degree is greater than or equal to the matching degree threshold.

7. The method according to claim 6, characterized in that, The process of determining whether to re-trigger the target event includes: When the matching degree is lower than the matching degree threshold, at least one of the upper limit of the fluctuation threshold, the upper limit of the first deviation threshold, and the upper limit of the second deviation threshold is reduced by a preset step size.

8. The method according to claim 6, characterized in that, The assessment of the matching degree between the current operating plan and the spatial distribution characteristics of each area in the home environment includes: The home environment is divided into multiple spatial grid units, and the first and second actual environmental parameters within each spatial grid unit are obtained. The first and second actual environmental parameters are compared with the target values ​​of the corresponding spatial grid cells in the adjustment strategy, and the parameter deviations within each spatial grid cell are calculated. The matching degree is determined based on the root mean square value of the parameter deviations of all spatial grid cells.

9. The method according to claim 1, characterized in that, The determination of the adjustment strategy for controlling each of the home appliances further includes: Obtain the preset temperature regulation accuracy threshold and humidity balance threshold; Based on the relationship between the first deviation value and the temperature regulation accuracy threshold, the output power of the first household appliance is adjusted; The output rate of the second household appliance is adjusted based on the relationship between the second deviation value and the humidity balance threshold.

10. A home scene adaptive intelligent linkage control system, characterized in that, include: The module is used to build a fusion dataset based on the first environmental parameters, second environmental parameters, clock information, and environmental layout parameters of each area in the home environment. The fused dataset includes: the fluctuation range of the first environmental parameter within a preset time period, the first deviation value of the first environmental parameter at the current time, the second deviation value of the second environmental parameter at the current time, and the environmental layout parameter. The end time of the preset time period is the current time, which is determined by the clock information. The first determining module is used to determine an update vector based on the historical operating data of each household appliance if a target event occurs. The target event includes at least one of the following: the fluctuation range exceeds a range threshold, the first deviation value exceeds a first deviation threshold, and the second deviation value exceeds a second deviation threshold. The second determining module is used to determine the adjustment strategy for controlling each of the home appliances based on the update vector, the first deviation value, and the second deviation value.

Images