An intelligent household appliance interaction control method and system

Abstract

The application discloses an intelligent household appliance interaction control method and system, comprising the following steps: collecting the running state parameters, environment sensing data and user behavior characteristics of each household appliance in the living space in real time, generating the environment sensing data package through a multi-modal data fusion model; constructing a user habit preference model library, generating a household appliance control strategy decision tree in combination with historical interaction records, and matching an optimal control strategy set according to a real-time scene type; when a user active intervention signal or an environment mutation event is detected, triggering a dynamic strategy reconstruction mechanism, broadcasting an instruction update request carrying a priority identifier to an associated household appliance group, and generating a reallocation control instruction set. The application has the following advantages and effects: multi-source environment data can be deeply fused, a user habit model can be constructed in real time, and a dynamic strategy reconstruction capability is possessed, so as to solve the response lag, strategy rigidity and energy efficiency imbalance problems of the prior art in a complex home environment.

Description

Technical Field

[0001] This invention relates to the field of home appliance interaction technology, and in particular to a smart home appliance interactive control method and system. Background Technology

[0002] With the rapid development of IoT technology, smart home systems are becoming increasingly common, enabling various home appliances to be interconnected and remotely controlled and automated. Existing smart home appliance control systems often employ timed control, scene mode switching, or simple response mechanisms based on single sensor feedback, such as automatically starting and stopping air conditioners based on ambient temperature or adjusting light brightness based on light intensity. While these methods improve convenience and energy efficiency to some extent, they still have significant limitations. The core issue is that existing systems lack comprehensive perception and dynamic decision-making capabilities regarding the multi-dimensional states of the living environment. Especially when faced with user intervention, sudden environmental changes, or the need for multi-device collaboration, the system cannot quickly generate optimized control strategies that balance comfort, energy efficiency, and safety. Specifically, the system often relies on predefined static rules, making it difficult to adapt to the randomness of user behavior, the volatility of environmental parameters, and the time-varying nature of device states within the home environment. When multiple events occur concurrently, the system lacks effective priority arbitration and resource allocation mechanisms, easily leading to command conflicts, response delays, or energy consumption spikes, failing to achieve truly intelligent adaptive control. Therefore, there is an urgent need for a smart home appliance interactive control method that can deeply integrate multi-source environmental data, build user habit models in real time, and have the ability to dynamically reconstruct strategies, in order to solve the problems of response lag, strategy rigidity and energy efficiency imbalance faced by existing technologies in complex home environments. Summary of the Invention

[0003] The purpose of this invention is to provide an interactive control method and system for intelligent home appliances to solve the problems mentioned in the background art.

[0004] The above-mentioned technical objective of the present invention is achieved through the following technical solution:

[0005] This invention provides a method for interactive control of intelligent home appliances, comprising the following steps:

[0006] S100: Real-time collection of operating status parameters, environmental perception data and user behavior characteristics of various home appliances in the living space; generates environmental perception data packages through a multimodal data fusion model; used to comprehensively quantify the comfort index of the home environment and the energy consumption characteristics of the equipment.

[0007] S200. Based on the environmental perception data packet, construct a user habit preference model library, generate a decision tree for home appliance control strategies in combination with historical interaction records, and match the optimal control strategy set according to the real-time scene type; wherein, the decision tree for home appliance control strategies includes time-dependent strategy branches, event-triggered strategy branches, and energy-saving optimization strategy branches, and the optimal control strategy set is used to initialize the collaborative control instruction sequence of home appliances.

[0008] S300. When a user active intervention signal or an environmental mutation event is detected, trigger the dynamic strategy reconstruction mechanism, broadcast an instruction update request carrying a priority identifier to the associated home appliance group, and generate a reallocation control instruction set based on the device response delay threshold and the energy consumption constraint condition; wherein, the active intervention signal includes voice control instructions, gesture recognition instructions, and emergency button trigger signals, and the environmental mutation event includes sudden changes in temperature and humidity, abnormal power consumption fluctuations, and safety risk warnings.

[0009] By adopting the above technical solution, the environmental perception data packet integrates device status, environmental parameters, and user behavior into a unified index system, which not only accurately reflects the comprehensive comfort of the home space but also synchronously quantifies the energy consumption characteristics of each device, enabling the system to have the dual capabilities of optimizing the user experience and energy efficiency simultaneously; the constructed user habit preference model library analyzes the internal relationship between historical interaction records and real-time data through machine learning technology, dynamically generating a multi-branch strategy decision tree, making the control strategy have scene adaptability. The time-dependent strategy can automatically adjust the device working mode based on living habits, the event-triggered strategy can quickly respond to emergencies, and the energy-saving optimization strategy continuously explores the energy efficiency potential of the collaborative operation of devices. The three-dimensional architecture of the three strategy branches ensures full coverage from regular scenes to emergency scenes; the matching mechanism of the optimal control strategy set relies on the scene type recognition model to improve the strategy switching efficiency, and the generated collaborative control instruction sequence significantly improves the accuracy and response speed of multi-device linkage; more importantly, the dynamic strategy reconstruction mechanism solves the rigidity problem of the smart home system during user intervention or environmental mutation. Through the broadcast mechanism of the priority identifier and the instruction reallocation under constraint conditions, dynamic adjustment of the strategy is achieved while ensuring the stability of the system, making the system have the flexibility of both automation and manual intervention. Especially when dealing with environmental mutations such as sudden changes in temperature and humidity or emergencies such as safety warnings, instruction reconfiguration can be performed based on the device response delay threshold and the energy consumption constraint condition, effectively avoiding safety risks or energy waste caused by strategy lag.

[0010] A further setting is that the S100 specifically includes the steps of:

[0011] Real-time collect the operation state parameters of each home appliance in the living space through an embedded power metering module, and the operation state parameters include the instantaneous power consumption value, the current working mode code, and the remaining life prediction value calculated based on the device operation duration.

[0012] Deploy a distributed environmental sensor network to synchronously collect multi-dimensional environmental sensing data; among them, generate a three-dimensional spatial temperature distribution matrix through a temperature sensor array, construct indoor humidity gradient data through a humidity sensor group, and generate dynamic spatiotemporal distribution data of light intensity using a light sensor matrix.

[0013] The system uses millimeter-wave radar monitoring system and non-contact infrared sensing system to capture user behavior characteristics. Specifically, it analyzes human heart rate data through bio-reflection signals from millimeter-wave radar, obtains body surface temperature distribution data through non-contact infrared sensing system, and generates user activity trajectory heat map based on multi-target trajectory tracking algorithm.

[0014] The fusion operation is performed based on a multimodal data fusion model. Specifically, the operating status parameters, environmental perception data, and user behavior characteristics are time-stamped and mapped to spatial coordinates. A feature-weighted fusion algorithm is used to generate a set of comfort indices for the home environment, which includes thermal comfort sub-indices, visual comfort sub-indices, and behavioral adaptability sub-indices. Furthermore, an energy consumption feature vector is generated based on the analysis of operating status parameters, and this feature vector includes peak energy consumption indicators, steady-state energy consumption curves, and energy efficiency deviation coefficients.

[0015] An environmental perception data packet is generated based on the fusion results. The environmental perception data packet includes a set of comfort indices with timestamps, a device energy consumption feature vector, and a raw data check code.

[0016] By adopting the above technical solutions, the deployment of a distributed environmental sensor network generates a three-dimensional spatial temperature distribution through a temperature sensor array, constructs a humidity gradient model through humidity sensors, and captures dynamic spatiotemporal distribution of light through a light sensor, enabling environmental monitoring to break through the limitations of traditional single-point measurement and achieve dynamic monitoring. Millimeter-wave radar and non-contact infrared sensing incorporate user physiological indicators and behavioral trajectories into the monitoring system. Heart rate data and body surface temperature distribution provide biometric evidence for environmental comfort assessment, while activity trajectory heatmaps based on multi-target tracking algorithms accurately capture behavioral patterns. The multimodal data fusion model aligns data through timestamps. By mapping spatial coordinates to solve the problem of inconsistent spatiotemporal benchmarks for multi-source data, the feature-weighted fusion algorithm generates three sub-indices: thermal comfort, visual comfort, and behavioral adaptability. These sub-indices scientifically quantify the living experience from three levels: human physiological adaptability, environmental optical suitability, and behavioral interaction convenience. The construction of equipment energy consumption feature vectors combines instantaneous power and steady-state curve features. In particular, the introduction of the energy efficiency deviation coefficient provides a quantitative basis for diagnosing energy efficiency anomalies. Finally, the generated environmental perception data package ensures data integrity and traceability through timestamps and check codes, establishing a data foundation with both breadth and depth for upper-level decision-making.

[0017] A further setting involves the generation of the thermal comfort sub-index, visual comfort sub-index, and behavioral adaptability sub-index, specifically including the following steps:

[0018] Based on a three-dimensional spatial temperature distribution matrix, body surface temperature distribution data, and human heart rate data, a thermal comfort sub-index is generated through a thermal balance model, and humidity gradient data is used to correct for humidity effects. Based on dynamic spatiotemporal distribution data of light intensity, a visual comfort sub-index is generated through a light adaptation model, and a user activity trajectory heatmap is integrated for spatial location correlation analysis. Based on the user activity trajectory heatmap, a behavior adaptation sub-index is generated through a behavior pattern matching algorithm, and the device interaction adaptation is evaluated by combining the current working mode code in the operating status parameters. The thermal comfort sub-index, visual comfort sub-index, and behavior adaptation sub-index are then normalized.

[0019] By adopting the above technical solutions, the visual comfort sub-index relies on the illumination adaptation model to analyze the spatiotemporal distribution of illumination data and combines it with the user's actual activity trajectory for positional correlation correction, thus solving the defect that the uniform illumination index cannot reflect the real visual experience. For example, it automatically improves the uniformity of illumination in the reading area. The behavior adaptation sub-index uses a behavior pattern matching algorithm to couple and analyze the activity trajectory with the device's working mode, quantitatively evaluating the fit between the device status and the user's behavior. For example, it predicts the need to adjust the air conditioning direction based on the user's movement trajectory. The normalization processing of the three sub-indices constructs a unified comfort evaluation scale, making the comfort experience of different dimensions comparable and weighted, providing a foundation for multi-objective optimization control.

[0020] A further setting involves generating the device's energy consumption feature vector, specifically including the following steps:

[0021] Extract the power consumption value sequence of each household appliance within a continuous preset period, generate a steady-state energy consumption curve through a steady-state feature extraction algorithm, and mark the peak energy consumption exceeding a preset threshold; based on the current working mode code in the operating status parameters, group the devices, and calculate the deviation between the instantaneous power consumption value of the device and the rated power or historical average power under the same working mode to generate an energy efficiency deviation coefficient; based on the remaining life prediction value, dynamically adjust the energy efficiency alarm threshold used to determine whether the energy efficiency deviation coefficient is abnormal; integrate the peak energy consumption marker, steady-state energy consumption curve, and energy efficiency deviation coefficient to form a device energy consumption feature vector.

[0022] By adopting the above technical solutions, the peak energy consumption labeling mechanism provides an early warning basis for overload protection, and its preset threshold dynamic adjustment capability can adapt to the operating characteristics of different equipment; the grouped energy consumption analysis technology based on working mode, combined with the calculation model of energy efficiency deviation coefficient, realizes real-time comparison between actual equipment energy consumption and theoretical benchmark value, breaking through the limitation of traditional monitoring only absolute power consumption, and can directly locate abnormally high energy-consuming equipment; innovatively, the remaining life prediction value is associated with the energy efficiency alarm threshold, for example, relaxing the deviation tolerance for aging equipment, avoiding false alarms while accurately identifying the real energy efficiency degradation phenomenon; finally, the constructed equipment energy consumption feature vector forms a three-dimensional energy efficiency profile of "basic energy consumption - peak feature - health correlation", providing refined data support for energy-saving strategy formulation.

[0023] A further setting is that S200 specifically includes the following steps:

[0024] Based on the comfort index set, device energy consumption feature vector, and historical interaction records in the environmental perception data packet, a user habit preference model library is constructed using a clustering algorithm. The historical interaction records include the frequency of user active intervention signals, device usage time distribution data, and energy-saving preference scores. The clustering algorithm uses a K-means optimization model to generate user habit preference clusters, with each cluster corresponding to a habit preference type and a corresponding habit preference weight value.

[0025] By combining the habit preference clusters and habit preference weights in the user habit preference model library, a home appliance control strategy decision tree is generated; wherein, the home appliance control strategy decision tree includes time-dependent strategy branches, event-triggered strategy branches, and energy-saving optimization strategy branches, and each branch is divided based on the decision tree splitting algorithm;

[0026] The optimal control strategy set in the home appliance control strategy decision tree is matched based on the real-time scene type. The real-time scene type includes daily mode, energy-saving mode and emergency mode. The matching operation adopts a scene similarity calculation model to calculate the Euclidean distance between the current environmental perception data packet and each scene type, and selects the scene type with the smallest distance to activate the optimal control strategy set of the corresponding strategy branch.

[0027] By adopting the above technical solutions, in the process of constructing the decision tree for home appliance control strategies, the time-dependent strategy branch recommends the optimal combination of operating modes based on the clustering of equipment usage periods and the combination of comfort requirements and energy consumption characteristics, such as automatically activating the energy-saving mode during peak electricity consumption periods; the event-triggered strategy branch predicts the occurrence pattern of intervention signals through a probability model and achieves second-level response by combining an event action rule base. The multi-objective optimization algorithm of the energy-saving optimization strategy branch explores energy efficiency potential while ensuring the comfort threshold, such as adjusting the linkage parameters between the air conditioner set temperature and the fresh air system; the scene similarity calculation model matches real-time scene types based on Euclidean distance, enabling the strategy switching to have scene adaptability. The daily mode focuses on comfort, the energy-saving mode strengthens energy management, and the emergency mode prioritizes safety, solving the pain point that fixed strategies cannot adapt to changing scenarios.

[0028] A further step is to include, after the step of matching the optimal set of control strategies in the home appliance control strategy decision tree based on the real-time scene type, the following step is also included:

[0029] Initialize the collaborative control instruction sequence of home appliances; wherein, the collaborative control instruction sequence is generated based on the optimal control strategy set, and the instruction sequence includes device identifiers, control action parameters and timing scheduling information, and the initialization operation includes instruction priority sorting and resource conflict detection to ensure that the instruction sequence is compatible with the peak energy consumption identifier and steady-state energy consumption curve in the device energy consumption feature vector.

[0030] By adopting the above technical solutions, the collaborative execution mechanism of multi-device instructions is optimized. The collaborative control instruction sequence is transformed from the optimal control strategy set. The executability of the strategy is ensured by the precise binding of device identifiers and control action parameters. The embedding of timing scheduling information solves the time coupling problem of multi-device actions, such as avoiding tripping caused by the simultaneous start-up of multiple high-power devices. The instruction priority sorting mechanism ensures that critical operations are executed first. The resource conflict detection function actively avoids the risk of conflict during the execution process by predicting the compatibility between instructions and real-time energy consumption curves. For example, when the current circuit load is detected to be close to the safety threshold, the start-up request of unnecessary devices is automatically delayed.

[0031] A further step involves generating a home appliance control strategy decision tree by combining the habit preference clusters and habit preference weights from the user habit preference model library. This includes the following steps:

[0032] Based on the device usage time distribution data in the user habit preference model library, and combined with the comfort index set and device energy consumption feature vector in the environmental perception data package, multiple time intervals are divided through a time interval clustering algorithm, and a set of recommended operating modes for home appliances in each time interval is generated to construct a time-dependent strategy branch; wherein, the time-dependent strategy branch includes multiple time interval strategy nodes, and each time interval strategy node corresponds to a time interval and the set of recommended operating modes for that time interval;

[0033] Based on the frequency of user-initiated intervention signals in the user habit preference model library, an event triggering probability model is established. Combined with the real-time collected active intervention signal types and environmental change event types, an event-triggered strategy branch is constructed through an event-action association rule library. The event-triggered strategy branch includes multiple event strategy nodes, each corresponding to an intervention event or environmental event type and the response action sequence of the home appliance when the event is triggered.

[0034] The energy-saving preference score in the user habit preference model library and the energy efficiency deviation coefficient in the device energy consumption feature vector are integrated, and an energy-saving optimization strategy branch is generated by a multi-objective optimization algorithm with optimal energy efficiency as the goal. The energy-saving optimization strategy branch includes multiple energy efficiency strategy nodes, each corresponding to an energy efficiency optimization goal and a set of energy efficiency adjustment instructions that the home appliance needs to execute to achieve the goal.

[0035] By adopting the above technical solutions, the branch construction logic of the strategy decision tree is deepened. The time-dependent strategy branch divides time intervals with similar behavioral characteristics through time-interval clustering algorithms, and customizes a set of recommended operating modes for each interval, such as automatically executing the energy-saving mode of air conditioner preheating and lighting gradual brightening strategy in the morning of weekdays; the event-triggered strategy branch predicts the trigger probability of different events based on probability models and matches response action sequences in the association rule base; in the energy-saving optimization strategy branch, each energy efficiency strategy node corresponds to a specific optimization target and its adjustment instruction set, such as setting a temperature difference dead zone to reduce the frequent start and stop of air conditioner compressors, so that energy-saving control is upgraded from coarse switching to precise parameter adjustment; the three-branch structure covers three types of scenarios: periodic patterns, random events, and continuous optimization, forming a complete control strategy map.

[0036] A further setting is that S300 specifically includes the following steps:

[0037] Real-time monitoring of proactive intervention signals and sudden environmental events; wherein, the proactive intervention signals include voice control commands, gesture recognition commands, and emergency button trigger signals, and the sudden environmental events include sudden changes in temperature and humidity, abnormal power consumption fluctuations, and safety risk alarms; when any signal or event is detected, a dynamic policy reconstruction mechanism is activated; the dynamic policy reconstruction mechanism performs the following operations:

[0038] Broadcast a request for an update of instructions with a priority identifier to the associated appliance group; and

[0039] A set of redistribution control instructions is generated based on the equipment response delay threshold and energy consumption constraints;

[0040] Otherwise, maintain the current sequence of coordinated control instructions.

[0041] By adopting the above technical solutions, the emergency response mechanism covers natural interaction methods such as voice and gestures. The monitoring scope of environmental mutation events includes environmental anomalies such as sudden changes in temperature and humidity, as well as risk signals such as safety alarms, enabling the system to have all-weather anomaly perception capabilities. The trigger condition design of the dynamic strategy reconfiguration mechanism ensures stable system operation while maintaining a sensitive response to critical events. The broadcast mechanism sends priority update requests to related device groups, avoiding the waste of resources caused by system-wide refreshes and ensuring that critical devices receive instructions first. When generating the redistribution control instruction set, the device response delay threshold and energy consumption constraints are comprehensively considered. For example, the response speed of low-priority devices is slowed down under critical circuit load conditions, effectively preventing the risk of system crash.

[0042] A further setting is that the dynamic strategy reconstruction mechanism specifically includes the following steps:

[0043] Broadcast an instruction update request carrying a priority identifier to the associated home appliance group; wherein, the priority identifier is generated based on the event type: the highest priority identifier is assigned to the security risk alarm and emergency button trigger signal, the medium priority identifier is assigned to the sudden change in temperature and humidity and abnormal power consumption fluctuation, and the basic priority identifier is assigned to the regular voice control instructions and gesture recognition instructions.

[0044] A set of redistribution control instructions is generated based on the equipment response delay threshold and energy consumption constraints, including:

[0045] Obtain the real-time response delay parameters and device energy consumption feature vectors of each home appliance in the associated home appliance group; wherein, the device response delay threshold is preset according to the device type, and the device energy consumption feature vector includes peak energy consumption identifier, steady-state energy consumption curve and energy efficiency deviation coefficient;

[0046] A redistribution optimization model is established, with priority identifier as the primary constraint, device response delay threshold as the secondary constraint, and energy consumption constraint as the boundary condition for multi-objective optimization calculation; wherein, the energy consumption constraint integrates steady-state energy consumption curve and peak energy consumption identifier, limiting the total power consumption after redistribution to not exceed a preset safety threshold.

[0047] Based on the optimization calculation results, a set of reallocation control instructions is generated, which includes device identifiers, reallocation control action parameters and timing scheduling information.

[0048] Execute a dynamic strategy reconstruction mechanism: freeze the instructions in the current cooperative control instruction sequence that conflict with the reallocation control instruction set, and insert the reallocation control instruction set in descending order of priority identifier to generate a reconstructed cooperative control instruction sequence;

[0049] If the compatibility between the reconstructed instruction sequence and energy consumption constraints is verified by a resource conflict detection algorithm, the reconstructed collaborative control instruction sequence will be sent to the associated home appliance group for execution. If the verification fails, a degradation strategy will be initiated: based on the priority identifier, the sub-instruction set with the highest priority identifier will be selected from the redistribution control instruction set; the compatibility between this sub-instruction set and the energy consumption constraints will be verified again. If the verification passes, the sub-instruction set will be sent for execution, and a system exception log will be generated. If the verification of this sub-instruction set still fails, the current collaborative control instruction sequence will remain unchanged, and the highest level system alarm signal will be triggered.

[0050] By adopting the above technical solutions, the redistribution optimization model performs multi-objective optimization with priority as the primary constraint, response delay as the secondary constraint, and energy consumption conditions as the boundary. The generation of the reconstructed instruction set includes three information: device identification, execution parameters, and time-series scheduling, ensuring the integrity and executability of the instructions. The instruction freezing and priority interpolation mechanism in the dynamic reconstruction operation solves the conflict problem during the transition between old and new strategies. The two-level verification process of the resource conflict detection algorithm automatically downgrades the execution of a subset of instructions when energy consumption exceeds the limit, and the triggering of the highest-level alarm signal provides the final guarantee for manual intervention. A three-level fault protection system of "conflict prevention - local degradation - emergency alarm" is constructed, enabling the system to maintain its core functions even under extreme anomalies.

[0051] The present invention also provides an intelligent home appliance interactive control system, comprising the following modules:

[0052] The data acquisition module is configured to collect real-time operating status parameters of various household appliances in the living space, environmental perception data, and user behavior characteristics.

[0053] The data processing module is configured to generate environmental perception data packets through a multimodal data fusion model, which are used to comprehensively quantify the comfort index of the home environment and the energy consumption characteristics of the equipment.

[0054] The user habit modeling module is configured to build a user habit preference model library based on the environmental perception data package, and generate a home appliance control strategy decision tree by combining historical interaction records;

[0055] The strategy matching module is configured to match the optimal set of control strategies based on the real-time scenario type and initialize the collaborative control instruction sequence of home appliances;

[0056] The dynamic reconfiguration module is configured to trigger a dynamic policy reconfiguration mechanism and generate a set of reallocation control instructions when a user-initiated intervention signal or a sudden environmental event is detected.

[0057] The communication control module is configured to broadcast control commands to associated home appliance groups and receive device status feedback.

[0058] The data storage module is used to store environment-aware data packets, user habit and preference model library, control strategy decision tree, and historical interaction records.

[0059] In summary, the present invention has the following beneficial effects: it can deeply integrate multi-source environmental data, build user habit models in real time, and has the ability to dynamically reconstruct strategies, so as to solve the problems of response lag, strategy rigidity and energy efficiency imbalance faced by existing technologies in complex home environments. Attached Figure Description

[0060] Figure 1 This is a schematic diagram of the main flow of an embodiment;

[0061] Figure 2 This is a flowchart illustrating S100 in the embodiment;

[0062] Figure 3 This is a flowchart illustrating S200 in the embodiment;

[0063] Figure 4 This is a flowchart illustrating S300 in the embodiment;

[0064] Figure 5 This is a system block diagram for an embodiment. Detailed Implementation

[0065] The present invention will be further described in detail below with reference to the accompanying drawings.

[0066] As attached Figures 1 to 5 As shown;

[0067] This embodiment discloses an interactive control method for smart home appliances, including the following steps:

[0068] S100: Real-time collection of operating status parameters, environmental perception data, and user behavior characteristics of various home appliances within the living space. An environmental perception data package is generated through a multimodal data fusion model to comprehensively quantify the comfort index of the home environment and the energy consumption characteristics of the equipment. Specific steps include:

[0069] The system collects real-time operating status parameters of various household appliances within the living space through an embedded power metering module. These parameters include instantaneous power consumption, current operating mode codes, and predicted remaining lifespan based on device runtime. These parameters reflect the current energy consumption status, operating mode, and estimated remaining lifespan of the devices, providing foundational data for subsequent energy efficiency assessments and strategy development. Simultaneously, a distributed environmental sensor network is deployed to collect multi-dimensional environmental perception data, including a three-dimensional spatial temperature distribution matrix generated by a temperature sensor array, indoor humidity gradient data constructed by a humidity sensor group, and dynamic spatiotemporal distribution data of light intensity generated by a light sensor matrix. This environmental data is used to assess the thermal environment, humidity distribution, and lighting conditions of the living space, providing input for calculating the comfort index. Furthermore, a millimeter-wave radar monitoring system and a non-contact infrared sensing system capture user behavioral characteristics. Human heart rate data is analyzed using bioreflection signals from the millimeter-wave radar, and body surface temperature distribution data is obtained through the non-contact infrared sensing system. A user activity trajectory heatmap is generated based on a multi-target trajectory tracking algorithm. This behavioral characteristic data is used to analyze user activity patterns, physiological states, and location distribution within the space, providing a basis for behavioral suitability assessment. Based on a multimodal data fusion model, the system aligns operational status parameters, environmental perception data, and user behavior characteristics with timestamps and maps them to spatial coordinates. It then uses a feature-weighted fusion algorithm to generate a set of comfort indices for the home environment, including thermal comfort sub-indices, visual comfort sub-indices, and behavioral adaptability sub-indices. Simultaneously, based on operational status parameter analysis, it generates device energy consumption feature vectors, including peak energy consumption identifiers, steady-state energy consumption curves, and energy efficiency deviation coefficients. Finally, the system generates an environmental perception data package containing a timestamped set of comfort indices, device energy consumption feature vectors, and original data checksums for subsequent control strategy formulation and optimization.

[0070] In this implementation scheme, the embedded power metering module is a hardware unit integrated into each household appliance. It is responsible for periodically collecting the electrical parameters of the equipment, including instantaneous power consumption, current operating mode code, and remaining life prediction calculated based on the cumulative operating time of the equipment and the life model provided by the manufacturer. The instantaneous power consumption reflects the actual energy consumption level of the equipment at a certain moment and is a key indicator for evaluating the energy efficiency status of the equipment. The current operating mode code is used to identify the operating state of the equipment (such as cooling, heating, standby, etc.) and provides contextual information for subsequent strategy matching. The remaining life prediction is estimated based on the historical operating data of the equipment and a preset attenuation model, and is used to warn of potential equipment failures and optimize maintenance strategies. The distributed environmental sensor network consists of a temperature sensor array, a humidity sensor group, and a light sensor matrix deployed at key locations in the living space. The temperature sensor array is arranged in a three-dimensional grid and generates three-dimensional matrix data reflecting the spatial temperature distribution through synchronous sampling. The humidity sensor group is deployed by region to construct a scalar field characterizing the gradient of indoor humidity changes. The light sensor matrix dynamically captures the intensity and spatiotemporal distribution of natural light and artificial light sources, generating a spatiotemporal distribution dataset of light intensity. These environmental perception data provide an objective physical representation of the comfort environment for comfort assessment. The capture of user behavior characteristics relies on non-invasive sensing technologies: millimeter-wave radar monitoring systems transmit and receive millimeter-wave signals, analyzing human body reflection signals to extract heart rate data; non-contact infrared sensing systems generate body surface temperature distribution maps by detecting infrared radiation from the human body surface; combined with multi-target trajectory tracking algorithms (such as target tracking models based on Kalman filtering or deep learning), the system further generates user activity trajectory heatmaps reflecting user movement patterns and activity hotspots. This behavioral characteristic data not only reveals the user's real-time status but also provides a basis for personalized comfort adjustment. In the multimodal data fusion stage, the system first performs timestamp alignment and spatial coordinate mapping on data from different sources to ensure data consistency in the spatiotemporal dimensions. Subsequently, a feature-weighted fusion algorithm was used to integrate the processed data: for the generation of the comfort index set, the system calculated the thermal comfort sub-index (based on a three-dimensional spatial temperature distribution matrix, body surface temperature distribution data, and heart rate data, combined with a thermal balance model and humidity correction), the visual comfort sub-index (based on spatial correlation analysis of dynamic light intensity spatiotemporal distribution data and user activity trajectory heatmaps), and the behavioral fit sub-index (based on behavioral pattern matching between user activity trajectory heatmaps and device operating modes). After normalization, each sub-index was combined into a unified comfort index set.The construction of equipment energy consumption feature vectors is achieved through in-depth analysis of operating state parameters: extracting power consumption sequences within continuous time windows, applying steady-state feature extraction algorithms (such as moving average or change point detection) to identify steady-state energy consumption curves and labeling peak energy consumption events; combining the current operating mode encoding, calculating the deviation between the actual power and rated power of the equipment under the same mode, and generating an energy efficiency deviation coefficient; the remaining lifespan prediction value is used to dynamically adjust the energy efficiency alarm threshold used to determine whether the energy efficiency deviation coefficient is abnormal, realizing lifespan-aware energy efficiency monitoring. Finally, the system encapsulates the timestamped comfort index set, equipment energy consumption feature vectors, and original data verification codes used for data integrity verification into an environmental perception data package, providing standardized, multi-dimensional environmental representation inputs for upper-level decision-making.

[0071] In this implementation scheme, the generation of the thermal comfort sub-index is based on the PMV-PPD thermal balance model framework. A three-dimensional spatial temperature distribution matrix is ​​introduced as the ambient temperature input, body surface temperature distribution data is used as a characterization of individual thermal state, and human heart rate data is used as an auxiliary indicator for estimating metabolic rate. The model first calculates the operating temperature of the user's microenvironment, then corrects for evaporative cooling efficiency by incorporating humidity gradient data, quantifying the impact of environmental thermal stress on comfort. The output results are as follows: Scalar values ​​within the range, the closer to A higher thermal comfort level indicates greater thermal comfort. The visual comfort sub-index is calculated using a lighting adaptation model. This model comprehensively considers illuminance levels, color temperature distribution, and glare index provided by dynamic spatiotemporal distribution data of light intensity, and combines this with a user activity trajectory heatmap to identify the visual needs of the user's usual area. By calculating the deviation between the current lighting conditions and the ideal visual environment (such as illuminance recommendations based on CIE standards), and weighting the user's location, an index value reflecting the degree of visual comfort is generated. Specifically, this is the visual comfort sub-index. ;in This indicates the number of light sensors or virtual grid points in areas of frequent user activity. Indicates an index; Represents the location in the spatiotemporal distribution data of dynamic illumination intensity The measured illuminance value at the location; This indicates that the location is based on standards such as CIE. The ideal illuminance value recommended for each activity type (such as reading or rest) is determined by the user's main behavioral patterns inferred from the user activity trajectory heatmap. Indicates position The weight of the region is proportional to its "heat" value in the user activity trajectory heatmap. The longer a user stays in a region, the greater its visual comfort's impact on the overall index; the denominator of the formula is used for normalization to keep the output value within a certain range. The final result can be strictly constrained to a certain range using the Sigmoid function. Within the specified interval. The behavior fit sub-index relies on a behavior pattern matching algorithm, which performs similarity matching between a real-time generated user activity trajectory heatmap and a preset behavior pattern library (such as "rest," "activity," "work," etc.) to identify the current user behavior pattern. Specifically, the input is a real-time user activity trajectory heatmap. ;calculate With the preset behavior pattern library , , The similarity score of each template heatmap (e.g., cosine similarity, Jaccard index, or direct calculation based on dwell time percentage in specific functional areas such as sofas and desks) is used to output the most likely behavioral pattern. Simultaneously, combining the current operating mode code of the devices, the fit between device operation and user behavior is evaluated (e.g., whether the air conditioner is in silent mode when the user is resting), and a behavioral fit score is output. Specifically, the current operating mode codes of all home appliances are then input. , , ,…, Then, it queries the preset "Behavioral Pattern - Ideal Device State" rule base and outputs: the ratio of the number of devices that meet the rules to the total number of devices, or the matching score weighted according to the importance of the devices. (scope The behavioral fit sub-index is... The closer the value is This indicates that the operating status of home appliances is more in line with the user's current behavioral habits. Finally, the three sub-indices are processed by Min-Max normalization to eliminate differences in dimensions, and interfaces are reserved to allow for weight adjustments based on user's personalized preferences, forming a comprehensive comfort index set.

[0072] In this implementation scheme, the construction of the equipment energy consumption feature vector is a multi-step analysis process: the system first extracts the most recent complete cycle (e.g., The instantaneous power consumption sequence of each device within a given hour (the power consumption sequence is obtained by combining continuously collected instantaneous power consumption values ​​in chronological order) is used to identify the periods when the devices are in a stable operating state using a steady-state feature extraction algorithm based on sliding window and change point detection. The average power consumption during these periods is then fitted to form a steady-state energy consumption curve. Simultaneously, short-term power spikes are detected in the sequence; if their values ​​exceed a certain proportion of the device's rated power (e.g., ...), ... If the energy consumption is more than 10 times the historical peak power consumption threshold, it is marked as peak energy consumption. The calculation of the energy efficiency deviation coefficient depends on equipment grouping: the system divides equipment into different groups (such as air conditioning cooling group, washing machine washing group, etc.) according to the current working mode code. For equipment in the same group, the relative deviation of its instantaneous power consumption value from the rated power or historical average power of the group is calculated. This coefficient reflects the degree of energy efficiency abnormality of the equipment operating in the current mode. A positive value indicates high energy consumption, and a negative value indicates low energy consumption. Specifically, the energy efficiency deviation coefficient... ;in, This represents the steady-state power measured in the current mode; This indicates the expected power in this mode, which can be the rated power or the group-average power based on historical data. The remaining lifespan prediction is incorporated as an adaptive adjustment factor: the system presets a baseline energy efficiency alarm threshold, but this threshold is gradually relaxed as the predicted remaining lifespan of the equipment decreases (indicating equipment aging), avoiding excessive alarms for older equipment. Specifically, ;in This indicates the adjusted energy efficiency alarm threshold. Indicates the baseline energy efficiency alarm threshold; This is the preset maximum relaxation range; This represents the normalized remaining lifetime prediction value. The lower the predicted remaining lifetime value of the equipment, the more relaxed the corresponding energy efficiency alarm threshold. Finally, the system encapsulates the peak energy consumption identifier (Boolean type or level identifier), steady-state energy consumption curve (time series data or fitting parameters), and energy efficiency deviation coefficient (scalar value) into a structured equipment energy consumption feature vector. This vector not only describes the real-time energy consumption status of the equipment but also incorporates the lifetime-aware energy efficiency assessment logic, providing a quantitative basis for subsequent energy-saving strategy formulation.

[0073] S200. Based on the environmental awareness data packet, a user habit preference model library is constructed. A home appliance control strategy decision tree is generated by combining historical interaction records, and the optimal control strategy set is matched according to the real-time scenario type. The home appliance control strategy decision tree includes time-dependent strategies, event-triggered strategies, and energy-saving optimization strategy branches. The optimal control strategy set is used to initialize the collaborative control instruction sequence of home appliances. Specific steps include:

[0074] The system first constructs a user habit preference model library based on the time-stamped comfort index set (including thermal comfort sub-index, visual comfort sub-index, and behavioral fit sub-index), equipment energy consumption feature vector (including peak energy consumption identifier, steady-state energy consumption curve, and energy efficiency deviation coefficient) and historical interaction records (including user active intervention signal execution frequency, equipment usage time distribution data, and energy-saving preference scores) contained in the environmental perception data packet. This is achieved through an improved K-means clustering algorithm. In this process, historical interaction records provide a quantitative representation of long-term user behavior patterns, such as the frequency of user operations on specific equipment during different time periods, records of adjustments to environmental parameters such as temperature, humidity, and light, and the displayed energy-saving tendency scores. The clustering algorithm uses this multidimensional data as input, calculates Euclidean distance or cosine similarity to measure sample similarity, and determines the optimal number of clusters based on the elbow rule or silhouette coefficient. Finally generated Each user habit preference is clustered. Each cluster represents a typical user behavior pattern, such as "morning active and energy-saving", "nighttime comfort-first", or "balanced home-work" and is assigned a habit preference weight value. This weight value is dynamically updated based on the number of historical data samples contained in the cluster and their matching degree with the current user's real-time behavior, so as to reflect the degree of influence of different habit patterns on the current strategy formulation.

[0075] Based on the successful construction of a user habit preference model library, the system further combines the obtained habit preference clusters and their corresponding habit preference weights to generate a structured home appliance control strategy decision tree. This decision tree is constructed using a decision tree splitting algorithm based on information gain or Gini impurity, and includes three main strategy branches: a time-dependent strategy branch, an event-triggered strategy branch, and an energy-saving optimization strategy branch. The generation of the time-dependent strategy branch specifically involves: based on the device usage time distribution data extracted from the user habit preference model library, and integrating the comfort index set in the environmental perception data package with the time-related performance consumption and comfort patterns reflected by the device energy consumption feature vector, a time-series clustering algorithm (such as K-means for time-series data or clustering based on dynamic time warping) is used to divide the day into multiple time intervals with significant differences in characteristics (e.g., "early morning low temperature and low activity period," "midday high light period," "evening high comfort demand period," "late night ultra-low power consumption period," etc.). For each defined time period, the system comprehensively analyzes the historical optimal comfort index range, typical steady-state energy consumption levels of devices, and user habits and preferences within that period to generate a set of recommended operating modes for each household appliance during that time period (for example, during the "high comfort demand period in the evening," it recommends setting the air conditioner to a comfortable temperature, the lights to a warm color temperature with medium brightness, and keeping the curtains open; during the "ultra-low power consumption period at night," it recommends putting the air conditioner into sleep mode, turning off the lights, and putting all non-essential devices into standby or off mode). Each time period and its corresponding set of recommended operating modes constitute a time-dependent strategy node in the time-dependent strategy branch. The construction of the event-triggered strategy branch relies on the frequency of user-initiated intervention signals statistically analyzed in the user habit and preference model library. Based on this, the system establishes an event trigger probability model to predict the likelihood of various intervention events (such as voice commands and gesture control) occurring. Simultaneously, combining a predefined event-action association rule base (which includes rules such as "triggering a sequence of shutting down all non-essential devices upon detecting a 'leaving home' voice command" and "triggering the air purifier's high-speed mode and activating the fresh air system upon an environmental sensor reporting an excessive air quality index"), a sequence of home appliance response actions to be executed when triggered is defined for each known intervention event type (voice control command, gesture recognition command) and environmental abrupt event type (sudden changes in temperature and humidity, abnormal power consumption fluctuations, security risk alarms). Each event type and its corresponding response action sequence constitute an event policy node in the event-triggered strategy branch. The execution frequency of user-initiated intervention signals can be specifically expressed by the formula: ;in This indicates the frequency of user-initiated intervention signals, comprehensively reflecting the overall frequency of user-initiated control per unit time. A higher value indicates that the user intervenes manually more frequently. This indicates the total number of active intervention signal types, including voice control commands, gesture recognition commands, emergency button trigger signals, etc. Indicates the signal type index; Indicates the first The weighting coefficients of information categories are used to distinguish the importance of different types of signals. For example, the weight of the emergency button trigger signal should be much higher than that of the regular voice control command, indicating that although emergency events occur infrequently, they are extremely important once they occur. The specific settings can be preset or learned from historical data. Indicates the statistical time window within, no. The number of times this type of signal occurs; This indicates the length of the statistical time window, such as the past 24 hours or the past week, used to normalize the counts to frequency. The generation of the energy-saving optimization strategy branch involves integrating energy-saving preference scores (quantifying users' acceptance of energy saving) from the user habit preference model library with the energy efficiency deviation coefficient (indicating the current energy efficiency status of the device) from the device energy consumption feature vector. This constructs a multi-objective optimization model with optimal overall energy efficiency as the primary goal, while also considering comfort constraints (e.g., linear weighting, ...). (Multi-objective optimization methods such as constraint methods or evolutionary algorithms). After solving the model, it outputs a series of energy efficiency optimization objectives (such as "minimizing total power consumption", "reducing peak demand", "prioritizing load reduction for high-efficiency deviation equipment") and a detailed set of energy efficiency adjustment instructions that home appliances need to execute to achieve each objective (for example, to achieve the objective of "minimizing total power consumption", the instruction set may include appropriately increasing the air conditioner's set temperature). Reduce light brightness by degrees Celsius while maintaining visual comfort. (e.g., delaying the start of high-power washing tasks). In this embodiment, the energy-saving preference score can be specifically expressed by the formula: ;in This represents an energy-saving preference score, which will ultimately be transformed into a multi-objective optimization function. Energy saving preference weight ; This represents the user's historical average energy consumption, which is the actual average total power consumption in the user's home during the statistical period. This represents baseline energy consumption, which can be the average energy consumption of similar households, an estimated energy consumption based on house size and number of appliances, or a user-defined energy consumption budget. (Ratio) This reflects the user's relative energy consumption level; This indicates the user's response rate to energy-saving suggestions. When the system recommends an energy-saving strategy (such as raising the air conditioner temperature), the percentage of times the user accepts the suggestion out of the total number of recommendations. This indicates the number of times the user has actively intervened to switch to energy-saving mode. For example, the user manually switched the air conditioner from low temperature mode to high temperature mode, or actively turned off unnecessary lights; This represents all the user's active interventions. It represents a very small positive number, used to prevent the denominator from being zero. , and These are preset weighting coefficients used to adjust the importance of energy consumption level, system interaction response, and proactive behavior in the final score. These coefficients can be preset or optimized through machine learning. The multi-objective optimization model in this embodiment can be expressed by the formula: Overall Objective Function Energy consumption target and comfort goals We get the weighted sum. The optimization objective is to minimize the overall objective function. ;in Indicates the weight of energy-saving preference. This indicates that energy conservation is the top priority. This indicates that comfort is given top priority, and the value is directly derived from the energy-saving preference score in the user habit preference model library. The system maps user ratings to this weighted range. Each energy efficiency optimization target and its corresponding energy efficiency adjustment instruction set constitutes an energy efficiency strategy node in the energy-saving optimization strategy branch.

[0076] After generating the home appliance control strategy decision tree, the system matches the optimal control strategy set based on real-time scene types. Real-time scene types are divided into three categories: daily mode, energy-saving mode, and emergency mode. The matching operation is implemented through a scene similarity calculation model: this model extracts key features from the environmental perception data packets collected and generated in the current period (such as the current comfort index set values ​​and the instantaneous state of the device energy consumption feature vector), and compares them with predefined feature templates for each scene type. The Euclidean distance between the feature vector of the current environmental perception data packet and the feature vectors of each scene template is calculated, and the scene type with the smallest Euclidean distance is selected as the current active scene. For example, if the currently calculated comfort index is generally high and the device energy consumption is within the normal range, the daily mode is matched; if the device energy consumption feature vector shows frequent peak energy consumption indicators or a high total energy efficiency deviation coefficient, and the user's energy-saving preference score is also high, the energy-saving mode is matched; if the environmental perception data packet contains safety risk alarms or emergency signals from sudden environmental events, the emergency mode is immediately matched. After matching a scenario type, the system activates the optimal set of control strategies from the corresponding strategy branches in the appliance control strategy decision tree (daily mode focuses on time-dependent branches, energy-saving mode focuses on energy-saving optimization branches, and emergency mode prioritizes the high-priority strategy nodes in the event-triggered branches). This optimal set of control strategies is selected from the activated strategy branches based on the currently matched scenario type, choosing the combination of strategy nodes that best suits the current environmental state and user preferences.

[0077] After successfully matching and obtaining the optimal control strategy set, the system immediately initializes the sequence of collaborative control instructions for home appliances. This sequence is an ordered list of instructions generated based on the various strategies included in the optimal control strategy set. Each instruction contains a clear device identifier (specifying the controlled device), control action parameters (such as setting temperature, brightness level, on / off state, operating mode, etc.), and precise timing information (specifying the start time, duration, or relative trigger time of instruction execution). The initialization process is not simply a list of instructions, but includes crucial instruction priority sorting logic and a resource conflict detection mechanism. Instruction priority sorting is based on the importance of the strategy source (e.g., event-triggered strategy instructions in emergency mode usually have the highest priority, followed by energy-saving optimization instructions, and finally time-dependent instructions) and the constraints within the strategy. Resource conflict detection focuses on whether the execution of the instruction sequence will conflict with the device energy consumption characteristics depicted in the device energy consumption feature vector. For example, it checks whether any instructions would cause multiple high-power devices to operate simultaneously during peak energy consumption periods, potentially leading to circuit overload, or whether any instructions require a device operating mode that deviates significantly from the optimal energy efficiency range represented by its steady-state energy consumption curve. The system iteratively adjusts the timing or parameters of the instructions to ensure that the final generated sequence of collaborative control instructions satisfies the intent of the optimal control strategy set while being compatible with the current energy consumption capacity and state of the equipment, thus guaranteeing the feasibility of control and the stability of the system. The initialized sequence of collaborative control instructions will be loaded into the execution queue, thereby realizing intelligent, collaborative, and precise control of home appliances in the home environment.

[0078] S300: When a user-initiated intervention signal or a sudden environmental event is detected, a dynamic strategy reconfiguration mechanism is triggered. An instruction update request carrying a priority identifier is broadcast to the associated home appliance group. A redistribution control instruction set is generated based on the device response delay threshold and energy consumption constraints. The active intervention signal includes voice control instructions, gesture recognition instructions, and emergency button trigger signals. The sudden environmental event includes sudden changes in temperature and humidity, abnormal power consumption fluctuations, and safety risk alarms. Specific steps include:

[0079] The system continuously and highly sensitively monitors and analyzes various input signal streams through multi-signal acquisition and event monitoring modules deployed on the central controller and edge devices. These signal streams mainly include three categories: First, user-initiated intervention signals, specifically including voice control commands acquired by microphone arrays deployed in key areas such as the living room and bedroom and parsed by a voice recognition engine; gesture recognition commands captured by millimeter-wave radar or depth cameras and recognized by computer vision algorithms; and emergency button trigger signals generated when emergency buttons physically installed on walls or mobile terminals are triggered; Second, sudden environmental events, specifically including changes in humidity sensor values ​​exceeding preset safety thresholds within a unit of time (e.g., temperature changes exceeding a certain threshold per minute). Temperature or humidity changes by more than [amount] per minute The sudden change in temperature and humidity triggered by the embedded power metering module, which monitors and determines in real time that the instantaneous power consumption value deviates significantly from the reference range of the device's steady-state energy consumption curve based on historical data learning by a certain proportion (e.g., exceeding...). This monitoring process detects abnormal power consumption fluctuations triggered by certain events, as well as security risk alarms triggered and uploaded by security subsystems (such as smoke sensors, door magnetic sensors, and carbon monoxide alarms). It employs multi-level filtering technology and event correlation analysis algorithms to effectively distinguish between occasional interference such as environmental noise and equipment fluctuations, and truly critical events requiring system response. Once a confidence check confirms the detection of any valid active intervention signal or sudden environmental event, the system immediately triggers its built-in dynamic strategy reconstruction mechanism, interrupting the normal flow of the currently executing collaborative control command sequence.

[0080] Once the dynamic strategy reconfiguration mechanism is activated, its internal logic unit first performs precise event classification and priority determination: based on a predefined and continuously learned and updated event classification and priority rule base, the system automatically identifies the specific type of triggering event and assigns it a corresponding priority label. Signals directly related to life and property safety, such as safety risk alarms indicating fire, gas leaks, or illegal intrusion, as well as emergency button trigger signals explicitly issued by the user, are assigned the highest priority label; signals indicating potential risks such as rapidly deteriorating environmental conditions or equipment malfunctions, such as the aforementioned sudden changes in temperature and humidity and abnormal power consumption fluctuations, are assigned a medium priority label; and routine voice control commands and gesture recognition commands reflecting the user's normal comfort or convenience adjustment needs are assigned a basic priority label. Next, based on the event type and its location (determined by sensor ID or event source location), the system dynamically determines the related home appliance groups directly affected by the event (for example, a sudden drop in living room temperature mainly relates to the living room air conditioner, radiator, fresh air system, and smart curtains; abnormally high power consumption detected in the kitchen mainly relates to high-power devices such as ovens, induction cookers, and refrigerators in the kitchen). Then, using a reliable broadcast protocol with redundant retransmission mechanism, the system broadcasts an instruction update request message carrying the event type code and priority identifier to all device control nodes in the group, ensuring that all related devices can reliably and promptly receive and parse the request in a complex home wireless network environment.

[0081] While broadcasting the update request, the system simultaneously initiates the calculation process for generating the reallocation control instruction set. The core of this calculation process is a reallocation optimization model based on a multi-objective constraint satisfaction problem. The model first obtains the latest status data of each appliance in the associated appliance group in real time through the device status query interface. This mainly includes real-time response latency parameters read from the device's built-in controller or agent program (this parameter represents the theoretical or measured maximum time required for the device to start executing hardware actions from receiving an instruction; this threshold is pre-set according to the device type and model and stored in the device capability database; for example, the response latency of a smart curtain motor is typically hundreds of milliseconds to several seconds, while the switching latency of a smart light bulb can be as low as tens of milliseconds) and the device energy consumption feature vector extracted from the latest periodically generated environmental perception data packet (this vector includes a peak energy consumption identifier, a steady-state energy consumption curve representing the typical power consumption level of the device under stable operating conditions, and an energy efficiency deviation coefficient reflecting the degree of deviation between the current actual energy consumption and the expected energy efficiency level). The redistribution optimization model uses the priority marker assigned to the event as the primary optimization objective (ensuring that the highest priority instruction request is met most quickly and efficiently), and uses the response latency threshold of each device as a hard time constraint (requiring that the redistributed task must be completed within the response time allowed by the device's own capabilities). Simultaneously, global and local energy consumption constraints are used as strict boundary conditions (this condition integrates the steady-state energy consumption curves of each device within the group and whether it is currently in a peak energy consumption state, ensuring that the total instantaneous power consumption or expected peak power consumption of the entire associated appliance group after redistribution does not exceed the preset circuit safety threshold or the rated capacity of the smart meter, thereby absolutely preventing the risk of overload). In this embodiment, heuristic algorithms (such as genetic algorithms or particle swarm optimization algorithms) or dedicated online constraint solvers are used for fast approximate solutions. The final output is a series of specific, executable control commands, i.e., the redistribution control instruction set. This instruction set specifies in detail the unique identifier (device identifier) ​​of each device that needs to be adjusted, the specific control actions to be performed and their parameters (redistributing control action parameters, such as setting a target temperature value, switching to a specific operating mode, adjusting the brightness percentage, setting the on / off state, etc.), and the precise execution timing requirements (timing scheduling information, which fully considers the differences in response delay between devices and the logical order and coordination relationship between device actions).

[0082] Next, the system performs a substantive dynamic strategy reconfiguration operation: First, it freezes all existing instructions in the current collaborative control instruction sequence that conflict with the newly generated redistribution control instruction set in any way regarding the target device, execution time window, or desired final state (for example, if the redistribution instruction requires the living room air conditioner to immediately switch to high-power heating mode). minutes, then the original sequence may contain The instruction to lower the living room air conditioner temperature or switch to ventilation mode in minutes will be identified and frozen. Then, all instruction units in the redistribution control instruction set are strictly sorted in descending order according to their internal priority identifiers. Based on this order and the timing information of each instruction, they are inserted into the appropriate time position in the current cooperative control instruction sequence after conflict avoidance calculation (usually, very high-priority instructions will attempt to preempt the earliest executable time slot, or even interrupt the currently executing low-priority instructions). Thus, a reconstructed, new cooperative control instruction sequence is generated.

[0083] Before issuing the reconstructed sequence of collaborative control instructions to the actuators, the system must initiate a resource conflict detection algorithm to conduct a final, comprehensive feasibility verification. This algorithm is a crucial step in ensuring the stable and secure operation of the system, and its details are as follows:

[0084] Resource conflict detection algorithms are multi-dimensional, hierarchical verification processes that primarily detect the following three types of conflicts:

[0085] Energy consumption conflict detection: This is the most critical safety detection method. First, extract all planned events within the same time period (usually one main power cycle or a short time window, such as...) from the reconstructed instruction sequence. The algorithm queries a device energy consumption feature vector library to obtain the power consumption requirements of each device when executing specific instructions (such as "air conditioner turns on high-power heating" or "oven preheats to [temperature value]"). The system calculates the typical power consumption value or range (from the steady-state power consumption curve) at a certain temperature ("degree") and whether it is in a peak power consumption state. Next, it calculates the estimated total power consumption of all concurrently operating devices within this time window. This estimated value is then compared with multiple preset safety thresholds (e.g., line rated capacity). , , The comparison is performed. If the total power consumption estimate exceeds the highest safety threshold (e.g., ...), the comparison is performed. If an energy consumption conflict is detected, the sequence is marked as "dangerous." If it is at a high warning threshold (e.g., ...), then an energy consumption conflict is detected, and the sequence is marked as "dangerous." If the value is above a certain threshold, it will be marked as a "warning" and may require optimization. This process also considers the energy efficiency deviation coefficient. If a device's coefficient is abnormally high, it indicates that its current energy efficiency is low, and the actual power consumption for executing the same instructions may far exceed the typical value. The algorithm will use a penalty coefficient to amplify its power consumption estimate, thereby making a more conservative risk assessment.

[0086] Timing Conflict Detection: This detection ensures the rationality of instruction timing. The algorithm checks for the following situations in the sequence: First, two instructions assigned to the same device have overlapping execution times; second, instructions with logical dependencies (such as "close the curtains first, then turn on the projector") are scheduled in the wrong time order; third, the start time required by an instruction has expired or is much later than the trigger time of its associated event, rendering it meaningless; fourth, the duration of the instruction does not conform to the device's response latency threshold or minimum stable operating time requirement. The algorithm maintains a virtual timeline for all devices, simulating the instruction execution process to detect these timing inconsistencies.

[0087] Device State Conflict Detection: This detection ensures that the state required by an instruction is reachable and does not conflict with the device's current state or the target state required by other instructions. The algorithm accesses the device's current state (e.g., "Off", "Idle", "Running - Cooling Mode") and checks whether the state transition required by the instruction is allowed by the device's capabilities (e.g., whether the device supports the mode, and whether the time required to switch from the current state to the target state exceeds a response latency threshold). It also checks whether multiple instructions in the sequence attempt to set the same device to different, mutually exclusive states within a short period (e.g., one instruction requests the air conditioner to heat, while a later instruction requests it to cool).

[0088] The resource conflict detection algorithm iterates through the entire reconstructed instruction sequence, performing the aforementioned checks on all potential time windows and device combinations. If all checks pass and no "dangerous" level conflicts are found, the reconstructed collaborative control instruction sequence is securely sent to each device in the associated appliance group for execution. If any conflict is detected, the algorithm initiates different processing strategies based on the conflict level and type: for "warning" level conflicts (such as power consumption approaching a threshold), the algorithm may attempt automatic fine-tuning (such as slightly delaying the start time of a non-critical instruction); for "dangerous" level conflicts or conflicts that cannot be automatically resolved, the verification fails. When verification fails, the system initiates the degradation strategy described above: based on priority identifiers, it selects the sub-instruction set with the highest priority identifier from the redistribution control instruction set. The system then runs the resource conflict detection algorithm again to attempt to verify the compatibility of this streamlined highest-priority sub-instruction set with constraints such as energy consumption. If this verification passes, only this sub-instruction set is sent and executed, and a system exception log is generated, recording the situation and reason why not all redistribution instructions were fully executed. If even the highest priority sub-instruction set fails verification (indicating extreme resource bottlenecks or irreconcilable conflicts), the system will maintain the current collaborative control instruction sequence without executing any refactoring operations triggered by this event. However, it will simultaneously trigger the highest-level system alarm signal (such as pushing an emergency notification to the mobile app or activating an audible and visual alarm) to notify the user or system administrator of a major conflict or system resource bottleneck that cannot be automatically handled, requiring manual intervention. If no proactive intervention signal or environmental abrupt event requiring handling is detected throughout the process, the dynamic policy refactoring mechanism remains in standby dormant state, and the system continues to stably execute the current collaborative control instruction sequence, maintaining the established operating state of the home environment.

[0089] This embodiment also discloses an intelligent home appliance interactive control system, including the following modules:

[0090] The data acquisition module is configured to collect real-time operating status parameters of various household appliances in the living space, environmental perception data, and user behavior characteristics.

[0091] The data processing module is configured to generate environmental perception data packets through a multimodal data fusion model, which are used to comprehensively quantify the comfort index of the home environment and the energy consumption characteristics of the equipment.

[0092] The user habit modeling module is configured to build a user habit preference model library based on the environmental perception data package, and generate a home appliance control strategy decision tree by combining historical interaction records;

[0093] The strategy matching module is configured to match the optimal set of control strategies based on the real-time scenario type and initialize the collaborative control instruction sequence of home appliances;

[0094] The dynamic reconfiguration module is configured to trigger a dynamic policy reconfiguration mechanism and generate a set of reallocation control instructions when a user-initiated intervention signal or a sudden environmental event is detected.

[0095] The communication control module is configured to broadcast control commands to associated home appliance groups and receive device status feedback.

[0096] The data storage module is used to store environment-aware data packets, user habit and preference model library, control strategy decision tree, and historical interaction records.

[0097] This specific embodiment is merely an explanation of the present invention and is not intended to limit the invention. After reading this specification, those skilled in the art can make modifications to this embodiment without contributing any inventive step, but such modifications are protected by patent law as long as they are within the scope of the claims of the present invention.

Claims

1. A method for interactive control of intelligent home appliances, characterized in that, Includes the following steps: S100: Real-time collection of operating status parameters, environmental perception data and user behavior characteristics of various home appliances in the living space; generates environmental perception data packages through a multimodal data fusion model; used to comprehensively quantify the comfort index of the home environment and the energy consumption characteristics of the equipment. S200. Based on the environmental perception data packet, a user habit preference model library is constructed, and a home appliance control strategy decision tree is generated by combining historical interaction records. The optimal control strategy set is matched according to the real-time scenario type. The home appliance control strategy decision tree includes time-dependent strategy, event-triggered strategy and energy-saving optimization strategy branches. The optimal control strategy set is used to initialize the collaborative control instruction sequence of home appliances. S300: When a user-initiated intervention signal or an environmental abrupt event is detected, a dynamic strategy reconstruction mechanism is triggered to broadcast an instruction update request carrying a priority identifier to the associated home appliance group, and a redistribution control instruction set is generated based on the device response delay threshold and energy consumption constraints; wherein, the active intervention signal includes voice control instructions, gesture recognition instructions and emergency button trigger signals, and the environmental abrupt event includes sudden changes in temperature and humidity, abnormal power consumption fluctuations and safety risk alarms. The specific steps include: Real-time monitoring of proactive intervention signals and sudden environmental events; wherein, the proactive intervention signals include voice control commands, gesture recognition commands, and emergency button trigger signals, and the sudden environmental events include sudden changes in temperature and humidity, abnormal power consumption fluctuations, and safety risk alarms; when any signal or event is detected, a dynamic policy reconstruction mechanism is activated; the dynamic policy reconstruction mechanism performs the following operations: Broadcast a request for an update of instructions with a priority identifier to the associated appliance group; and A set of redistribution control instructions is generated based on the equipment response delay threshold and energy consumption constraints; Otherwise, maintain the current sequence of coordinated control instructions; The dynamic strategy refactoring mechanism specifically includes the following steps: Broadcast an instruction update request carrying a priority identifier to the associated home appliance group; wherein, the priority identifier is generated based on the event type: the highest priority identifier is assigned to the security risk alarm and emergency button trigger signal, the medium priority identifier is assigned to the sudden change in temperature and humidity and abnormal power consumption fluctuation, and the basic priority identifier is assigned to the regular voice control instructions and gesture recognition instructions. A set of redistribution control instructions is generated based on the equipment response delay threshold and energy consumption constraints, including: Obtain the real-time response delay parameters and device energy consumption feature vectors of each home appliance in the associated home appliance group; wherein, the device response delay threshold is preset according to the device type, and the device energy consumption feature vector includes peak energy consumption identifier, steady-state energy consumption curve and energy efficiency deviation coefficient; A redistribution optimization model is established, with priority identifier as the primary constraint, device response delay threshold as the secondary constraint, and energy consumption constraint as the boundary condition for multi-objective optimization calculation; wherein, the energy consumption constraint integrates steady-state energy consumption curve and peak energy consumption identifier, limiting the total power consumption after redistribution to not exceed a preset safety threshold. Based on the optimization calculation results, a set of reallocation control instructions is generated, which includes device identifiers, reallocation control action parameters and timing scheduling information. Execute a dynamic strategy reconstruction mechanism: freeze the instructions in the current cooperative control instruction sequence that conflict with the reallocation control instruction set, and insert the reallocation control instruction set in descending order of priority identifier to generate a reconstructed cooperative control instruction sequence; If the compatibility between the reconstructed instruction sequence and energy consumption constraints is verified by a resource conflict detection algorithm, the reconstructed collaborative control instruction sequence will be sent to the associated home appliance group for execution. If the verification fails, a degradation strategy will be initiated: based on the priority identifier, the sub-instruction set with the highest priority identifier will be selected from the redistribution control instruction set; the compatibility between this sub-instruction set and the energy consumption constraints will be verified again. If the verification passes, the sub-instruction set will be sent for execution, and a system exception log will be generated. If the verification of this sub-instruction set still fails, the current collaborative control instruction sequence will remain unchanged, and the highest level system alarm signal will be triggered.

2. The intelligent home appliance interactive control method according to claim 1, characterized in that: S100 specifically includes the following steps: The operating status parameters of each household appliance in the living space are collected in real time through an embedded power metering module. The operating status parameters include instantaneous power consumption value, current working mode code and remaining life prediction value calculated based on the device's running time. Deploy a distributed environmental sensor network to synchronously collect multi-dimensional environmental sensing data; among them, generate a three-dimensional spatial temperature distribution matrix through a temperature sensor array, construct indoor humidity gradient data through a humidity sensor group, and generate dynamic spatiotemporal distribution data of light intensity using a light sensor matrix. The system uses millimeter-wave radar monitoring system and non-contact infrared sensing system to capture user behavior characteristics. Specifically, it analyzes human heart rate data through bio-reflection signals from millimeter-wave radar, obtains body surface temperature distribution data through non-contact infrared sensing system, and generates user activity trajectory heat map based on multi-target trajectory tracking algorithm. The fusion operation is performed based on a multimodal data fusion model. Specifically, the operating status parameters, environmental perception data, and user behavior characteristics are time-stamped and mapped to spatial coordinates. A feature-weighted fusion algorithm is used to generate a set of comfort indices for the home environment, which includes thermal comfort sub-indices, visual comfort sub-indices, and behavioral adaptability sub-indices. Furthermore, an energy consumption feature vector is generated based on the analysis of operating status parameters, and this feature vector includes peak energy consumption indicators, steady-state energy consumption curves, and energy efficiency deviation coefficients. An environmental perception data packet is generated based on the fusion results. The environmental perception data packet includes a set of comfort indices with timestamps, a device energy consumption feature vector, and a raw data check code.

3. The intelligent home appliance interactive control method according to claim 2, characterized in that: The generation of the thermal comfort sub-index, visual comfort sub-index, and behavioral fit sub-index specifically includes the following steps: Based on a three-dimensional spatial temperature distribution matrix, body surface temperature distribution data, and human heart rate data, a thermal comfort sub-index is generated through a thermal balance model, and humidity gradient data is used to correct for humidity effects. Based on dynamic spatiotemporal distribution data of light intensity, a visual comfort sub-index is generated through a light adaptation model, and a user activity trajectory heatmap is integrated for spatial location correlation analysis. Based on the user activity trajectory heatmap, a behavior adaptation sub-index is generated through a behavior pattern matching algorithm, and the device interaction adaptation is evaluated by combining the current working mode code in the operating status parameters. The thermal comfort sub-index, visual comfort sub-index, and behavior adaptation sub-index are then normalized.

4. The intelligent home appliance interactive control method according to claim 2, characterized in that: The generation of the device energy consumption feature vector specifically includes the following steps: Extract the power consumption value sequence of each household appliance within a continuous preset period, generate a steady-state energy consumption curve through a steady-state feature extraction algorithm, and mark the peak energy consumption exceeding the preset threshold. Based on the current operating mode code in the operating status parameters, the devices are grouped, and the deviation between the instantaneous power consumption value of the device under the same operating mode and the rated power or historical average power is calculated to generate an energy efficiency deviation coefficient; based on the remaining life prediction value, the energy efficiency alarm threshold used to determine whether the energy efficiency deviation coefficient is abnormal is dynamically adjusted; the peak energy consumption identifier, steady-state energy consumption curve and energy efficiency deviation coefficient are integrated to form a device energy consumption feature vector.

5. The intelligent home appliance interactive control method according to claim 1, characterized in that: S200 specifically includes the following steps: Based on the comfort index set, device energy consumption feature vector, and historical interaction records in the environmental perception data packet, a user habit preference model library is constructed using a clustering algorithm. The historical interaction records include the frequency of user active intervention signals, device usage time distribution data, and energy-saving preference scores. The clustering algorithm uses a K-means optimization model to generate user habit preference clusters, with each cluster corresponding to a habit preference type and a corresponding habit preference weight value. By combining the habit preference clusters and habit preference weights in the user habit preference model library, a home appliance control strategy decision tree is generated; wherein, the home appliance control strategy decision tree includes time-dependent strategy branches, event-triggered strategy branches, and energy-saving optimization strategy branches, and each branch is divided based on the decision tree splitting algorithm; The optimal control strategy set in the home appliance control strategy decision tree is matched based on the real-time scene type. The real-time scene type includes daily mode, energy-saving mode and emergency mode. The matching operation adopts a scene similarity calculation model to calculate the Euclidean distance between the current environmental perception data packet and each scene type, and selects the scene type with the smallest distance to activate the optimal control strategy set of the corresponding strategy branch.

6. The intelligent home appliance interactive control method according to claim 5, characterized in that: Following the step of matching the optimal set of control strategies in the home appliance control strategy decision tree based on the real-time scenario type, the following step is also included: Initialize the collaborative control instruction sequence of home appliances; wherein, the collaborative control instruction sequence is generated based on the optimal control strategy set, and the instruction sequence includes device identifiers, control action parameters and timing scheduling information, and the initialization operation includes instruction priority sorting and resource conflict detection to ensure that the instruction sequence is compatible with the peak energy consumption identifier and steady-state energy consumption curve in the device energy consumption feature vector.

7. The intelligent home appliance interactive control method according to claim 5, characterized in that: By combining the habit preference clusters and habit preference weights in the user habit preference model library, a home appliance control strategy decision tree is generated, specifically including the following steps: Based on the device usage time distribution data in the user habit preference model library, and combined with the comfort index set and device energy consumption feature vector in the environmental perception data package, multiple time intervals are divided through a time interval clustering algorithm, and a set of recommended operating modes for home appliances in each time interval is generated to construct a time-dependent strategy branch; wherein, the time-dependent strategy branch includes multiple time interval strategy nodes, and each time interval strategy node corresponds to a time interval and the set of recommended operating modes for that time interval; Based on the frequency of user-initiated intervention signals in the user habit preference model library, an event triggering probability model is established. Combined with the real-time collected active intervention signal types and environmental change event types, an event-triggered strategy branch is constructed through an event-action association rule library. The event-triggered strategy branch includes multiple event strategy nodes, each corresponding to an intervention event or environmental event type and the response action sequence of the home appliance when the event is triggered. The energy-saving preference score in the user habit preference model library and the energy efficiency deviation coefficient in the device energy consumption feature vector are integrated, and an energy-saving optimization strategy branch is generated by a multi-objective optimization algorithm with optimal energy efficiency as the goal. The energy-saving optimization strategy branch includes multiple energy efficiency strategy nodes, each corresponding to an energy efficiency optimization goal and a set of energy efficiency adjustment instructions that the home appliance needs to execute to achieve the goal.

8. An intelligent home appliance interactive control system, applied to the intelligent home appliance interactive control method according to any one of claims 1-7, characterized in that, It includes the following modules: The data acquisition module is configured to collect real-time operating status parameters of various household appliances in the living space, environmental perception data, and user behavior characteristics. The data processing module is configured to generate environmental perception data packets through a multimodal data fusion model, which are used to comprehensively quantify the comfort index of the home environment and the energy consumption characteristics of the equipment. The user habit modeling module is configured to build a user habit preference model library based on the environmental perception data package, and generate a home appliance control strategy decision tree by combining historical interaction records; The strategy matching module is configured to match the optimal set of control strategies based on the real-time scenario type and initialize the collaborative control instruction sequence of home appliances; The dynamic reconfiguration module is configured to trigger a dynamic policy reconfiguration mechanism and generate a set of reallocation control instructions when a user-initiated intervention signal or a sudden environmental event is detected. The communication control module is configured to broadcast control commands to associated home appliance groups and receive device status feedback. The data storage module is used to store environment-aware data packets, user habit and preference model library, control strategy decision tree, and historical interaction records.

Images