Linkage control method of intelligent household electrical appliance and access control equipment

Abstract

The invention discloses a linkage control method for an intelligent household electrical appliance and access control equipment, and particularly relates to the field of equipment linkage control, and the method comprises the following steps: determining whether there is no person in a room through an access control record and a biological signal, and controlling the intelligent household electrical appliance to enter or exit an automatic maintenance mode; the method comprises the steps of collecting household appliance operation characteristics and environment parameters, and generating multi-dimensional data used for sensing performance changes in combination with a preset rule; constructing a performance attenuation prediction model, dividing equipment risk levels, and dynamically generating a maintenance task plan; constructing an energy consumption hierarchical model according to the energy consumption characteristics of the maintenance tasks, and optimizing energy consumption distribution; predicting an unmanned living period based on a door lock historical record, and performing maintenance task scheduling in combination with a task priority and an energy consumption budget; according to the scheme, through linkage of the access control equipment and the household appliances, the purpose of automatically maintaining the household appliances which are idle for a long time so as to protect the household appliances is achieved, and the technical effect of improving the loss condition caused by long-term idle of the intelligent household appliances is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of device linkage control, and more specifically, to a linkage control method for smart home appliances and access control equipment. Background Art

[0002] With the popularity of smart home appliances, the automated management of home appliances has received more and more attention. In an environment where no one lives for a long time, home appliances such as smart air conditioners and refrigerators often face performance degradation due to idleness. When such devices are not used for a long time, circuit aging, component failure, oil accumulation and other phenomena may occur, resulting in poor performance or even failure of the equipment when it is reactivated. Traditional home appliance management methods fail to perform intelligent regulation and control for the special needs of long-term idle equipment, and cannot actively perform self-maintenance on long-term idle equipment. For example, smart water heaters accumulate internal scale due to long-term inactivity. Traditional home appliance management methods will not actively enter the self-cleaning mode to remove sediment or scale in the water tank, which leads to performance degradation of the equipment.

[0003] Therefore, how to propose a method to determine whether a home is unoccupied based on the access control status, and on this basis link the access control device with the home appliances to achieve automated maintenance of long-term idle home appliances to achieve the purpose of protecting home appliances has become an urgent problem to be solved in the current intelligent home appliance control system. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a linkage control method of a smart home appliance and a door access control device to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions: S1: Determine whether the room is unoccupied based on the access control operation record and the biological signal activity pattern. If so, generate a control signal to start the automatic maintenance mode of the smart home appliance. If not, generate a control signal to turn off the automatic maintenance mode of the smart home appliance. S2: Compare and analyze the integrated data of home appliance operation characteristics and external environment parameters with the preset association rules to generate a multi-dimensional association data set for perceiving changes in home appliance performance; S3: Build a performance degradation prediction model for household appliances, classify the performance degradation risk levels of household appliances according to the prediction results of the model, and dynamically generate a maintenance task schedule for household appliances; S4: Build a task energy consumption hierarchical model based on the energy consumption characteristics of household appliance maintenance tasks and dynamically adjust energy consumption allocation; S5: predicting the unoccupied state period based on the door lock operation history in the local storage unit, and scheduling the maintenance tasks based on the priority of the home appliance maintenance tasks and the energy budget allocation; S6: Monitor the abnormal operation characteristics of household appliances in real time, and send the abnormal data to the remote user end after identifying the abnormal signal.

[0006] In a preferred embodiment, in S1, judging whether the room is unoccupied based on the access control operation record and the biological signal activity pattern, if so, generating a control signal to start the automatic maintenance mode of the smart home appliance, if not, generating a control signal to turn off the automatic maintenance mode of the smart home appliance specifically includes: Integrate access control equipment and home appliances into a linkage control system, and connect all device control units to a unified central controller; Through the built-in data acquisition device of the access control device, a unique timestamp and operation identity information are recorded each time the door lock is operated, and the data is stored in a local storage unit; Using the indoor sensor unit to collect indoor biological signal data at a set frequency, including infrared sensing signal data and acoustic signal data, to obtain an independent dynamic parameter set of the indoor biological signal data; Define the monitoring cycle of the bio-signal activity pattern and the unmanned pattern feature matching rules, and establish an evaluation model for real-time calculation of the possibility of the indoor unmanned state based on the access control operation records and indoor bio-signal data in the local storage unit; Compare the real-time calculated value generated by the unmanned state assessment model with the preset judgment threshold, trigger the logical judgment of whether the room is unmanned, and update the state variable in the system state unit based on the judgment result; When the status in the system status unit is unoccupied, the central controller generates a control signal and sends it to the designated smart home appliance control unit to control the home appliance to enter the automatic maintenance mode. Conversely, when the status is not unoccupied, the home appliance is controlled to exit the automatic maintenance mode.

[0007] In a preferred embodiment, in S2, comparing and analyzing the integrated data of the operation characteristics of the household appliance and the external environment parameters with the preset association rules to generate a multidimensional association data set for sensing the performance changes of the household appliance specifically includes: Collect multi-dimensional indoor environmental parameters in real time through indoor sensor units; The household appliances are powered on intermittently at set intervals. The linkage control system integrates embedded sensing devices to capture the operating characteristics of the household appliances. The operating characteristic data includes the motor operating temperature, vibration frequency and current waveform changes. The operation characteristic data and the multi-dimensional environmental parameters are integrated according to the time series correspondence, and the integrated data is synchronously updated to the equipment operation status data table in the form of a multi-dimensional array; Predefine the association rules between environmental parameters and equipment operation characteristics, match and compare with the time series multi-dimensional environmental parameters and household appliance operation characteristic data in the operation status data table, and generate a multi-dimensional association data set for sensing the performance changes of household appliances; The multidimensional associated data set of the performance changes of household appliances is synchronously verified through a dynamic comparison algorithm to eliminate abnormal data, and the remaining multidimensional associated data set is stored in a local storage unit.

[0008] In a preferred embodiment, in S3, a performance degradation prediction model for household appliances is constructed, and household appliances are classified into performance degradation risk levels according to the prediction results of the model. The dynamic generation of a maintenance task schedule for household appliances specifically includes: Extract the operation characteristic data and multi-dimensional environmental parameters of the equipment from the multi-dimensional associated data set of historical household appliance performance changes in the local storage unit, and generate a multi-dimensional historical feature matrix through a feature extraction algorithm; Based on the multi-dimensional historical feature matrix, a deep learning algorithm is selected to build a household appliance performance degradation prediction model, and an evaluation mechanism for the impact of household appliance performance degradation rate and environmental parameters is established; Input the real-time operation characteristic data and real-time environmental parameters of the equipment into the performance degradation prediction model, generate the performance degradation estimation index of the equipment according to the prediction result, and divide the degradation risk level according to the performance degradation estimation index; According to the attenuation risk level, a maintenance task list for household appliances is generated according to the principle of giving priority to high risk levels, forming a dynamic priority queue for equipment maintenance; Based on the dynamic priority queue of home appliance maintenance, the execution order of maintenance tasks is determined by the scheduling algorithm, and a maintenance task schedule for home appliance equipment is generated.

[0009] In a preferred embodiment, in S4, a task energy consumption hierarchical model is constructed according to the energy consumption characteristics of the household appliance maintenance task, and the dynamic adjustment of energy consumption allocation specifically includes: Generate an energy consumption characteristic data set for each task based on the average power consumption and continuous running time of the historical execution of tasks in the household appliance maintenance task schedule; By comparing the changes in equipment operation characteristic data after the execution of historical tasks, the impact of maintenance tasks on performance degradation recovery is evaluated. The impact of performance degradation recovery and task execution energy consumption are combined through weight analysis to construct a task energy consumption impact matrix. According to the task energy consumption impact matrix, the corresponding gradient intervals of different levels of energy consumption classification standards are set, a dynamic hierarchical energy consumption model is established, and energy consumption is hierarchical for tasks in the equipment maintenance task schedule; The remaining energy storage in the detection linkage system is used as the energy budget. The energy consumption constraints of task execution are dynamically generated based on the energy consumption stratification results of the task. The energy allocation logic for maintenance of each home appliance is adjusted to allocate the energy budget to the maintenance tasks of the home appliances.

[0010] In a preferred embodiment, in S5, predicting the unoccupied state period according to the door lock operation history record in the local storage unit, and scheduling the maintenance task based on the priority of the household appliance maintenance task and the energy budget allocation specifically include: Extract the historical door lock operation timestamps and operator identity information from the local storage unit to generate time series data. Based on the time interval characteristics of the door lock operation, the uninhabited period is predicted through the time series analysis method. According to the energy budget allocation of maintenance tasks in each level in the task energy consumption hierarchical model, the expected maintenance time is calculated in combination with the preset maintenance input power of each household appliance, and the energy consumption constraint of the equipment maintenance task execution is converted into a time constraint; According to the maintenance priority order of the equipment maintenance task schedule and the execution time constraints of the equipment maintenance tasks, the maintenance tasks are dispersed and matched to the time windows of the predicted unoccupied periods, and the maintenance tasks are scheduled regularly through the central controller.

[0011] In a preferred embodiment, in S6, real-time monitoring of abnormal operation characteristics of household appliances and sending abnormal data to a remote user terminal after identifying abnormal signals specifically include: During the equipment maintenance process, the sensing device monitors the operating characteristics of the household appliance in real time, sets the normal data range of each operating characteristic data used to judge abnormal characteristics, and sends an abnormal signal to the central controller when the normal data range of the operating characteristic data is exceeded; After the central controller identifies the abnormal signal, it retrieves the equipment under maintenance during the period and the corresponding operating characteristic data and environmental parameters of the equipment, and sends them to the remote user end.

[0012] The technical effects and advantages of the linkage control method of a smart home appliance and a door access control device of the present invention are as follows: The system can accurately identify whether a home is unoccupied by real-time recording of access control operations and judging indoor activity patterns. When it is detected that no one is living in the house, the system collects the internal operation data and external environmental parameters of the home appliances in real time, and compares and analyzes these data with the preset association rules to generate a multi-dimensional home appliance performance perception data set. This enables the system to accurately judge the performance changes of the equipment and conduct dynamic maintenance needs assessment in a timely manner. Combined with the performance decay prediction model, the system predicts the equipment's decay risk level based on the equipment's operating status and environmental conditions, and intelligently generates a maintenance task schedule to avoid equipment failures or performance degradation due to neglected maintenance. The system also optimizes the allocation of task energy consumption through an energy consumption hierarchical model to ensure efficient and reasonable energy use of home appliance maintenance tasks. Based on the access control record to predict the unoccupied period, the system can accurately schedule the execution time of maintenance tasks, avoid energy waste, and complete automated self-maintenance tasks within the energy budget.

[0013] This solution realizes automated maintenance of long-term idle home appliances through the linkage between access control equipment and home appliances to achieve the purpose of protecting home appliances, and achieves the technical effect of improving the wear and tear of smart home appliances caused by long-term idleness. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 The present invention is a schematic diagram of a linkage control method between a smart home appliance and an access control device. DETAILED DESCRIPTION

[0015] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0016] Embodiment 1, Figure 1 The present invention provides a linkage control method for a smart home appliance and a door access control device, which comprises the following steps: S1: Determine whether the room is unoccupied based on the access control operation record and the biological signal activity pattern. If so, generate a control signal to start the automatic maintenance mode of the smart home appliance. If not, generate a control signal to turn off the automatic maintenance mode of the smart home appliance. S2: Compare and analyze the integrated data of home appliance operation characteristics and external environment parameters with the preset association rules to generate a multi-dimensional association data set for perceiving changes in home appliance performance; S3: Build a performance degradation prediction model for household appliances, classify the performance degradation risk levels of household appliances according to the prediction results of the model, and dynamically generate a maintenance task schedule for household appliances; S4: Build a task energy consumption hierarchical model based on the energy consumption characteristics of household appliance maintenance tasks and dynamically adjust energy consumption allocation; S5: predicting the unoccupied state period based on the door lock operation history in the local storage unit, and scheduling the maintenance tasks based on the priority of the home appliance maintenance tasks and the energy budget allocation; S6: Monitor the abnormal operation characteristics of household appliances in real time, and send the abnormal data to the remote user end after identifying the abnormal signal.

[0017] In S1, it is determined whether the room is unoccupied according to the access control operation record and the biological signal activity pattern. If so, a control signal is generated to start the automatic maintenance mode of the smart home appliance. If not, a control signal is generated to turn off the automatic maintenance mode of the smart home appliance. Specifically, it includes: The control units of access control devices and smart home appliances are integrated into a unified linkage control system, and all device control units are connected to the central controller. The central controller has real-time data processing and logic judgment capabilities, and supports data interaction with access control devices, indoor sensor units, and home appliance control units.

[0018] Through the built-in data acquisition device of the access control device, each time the door lock is operated (such as opening or closing the door), a unique timestamp and operation identity information are recorded, the homeowner's operation data set is filtered out, and the data is stored in the local storage unit as the time basis for determining the indoor status.

[0019] The indoor sensor unit is used to collect indoor biological signal data at a set frequency, including infrared sensing signal data and acoustic signal data, to obtain an independent dynamic parameter set of the indoor biological signal data. The time series dynamic parameter sets of the infrared sensing signal data and the acoustic signal data are respectively used and express.

[0020] Define the monitoring cycle of the biosignal activity pattern (e.g. once every 5 minutes) and the unmanned mode feature matching rules (e.g. no sensing signal or low noise activity for a long time). Combine the access control operation records and indoor biosignal data in the local storage unit to build an unmanned state assessment model. The model uses a dynamic calculation formula, which is: ; In the formula, is the probability score of the unmanned state within the time span of the i-th monitoring cycle, is the duration of the ith monitoring cycle, , They are respectively The infrared sensing signal data and acoustic signal data corresponding to the timing of each monitoring cycle, and Set weight coefficients respectively.

[0021] The time series and changes in biological signal characteristics are used as input parameters, and the probability score of the room being unmanned is output.

[0022] The real-time calculated value generated by the unoccupied state assessment model is compared with the preset judgment threshold to trigger the logical judgment of whether the room is unoccupied, and the state variable in the system state unit is updated based on the judgment result. When the state in the system state unit is unoccupied, the central controller generates a control signal and sends it to the designated smart home appliance control unit to control the home appliance to enter the automatic maintenance mode. Conversely, when the state is not unoccupied, the home appliance is controlled to exit the automatic maintenance mode.

[0023] In S2, the integrated data of the operation characteristics of the household appliances and the external environment parameters are compared and analyzed with the preset association rules to generate a multidimensional association data set for sensing the performance changes of the household appliances.

[0024] Arrange a variety of environmental sensor units indoors, including temperature sensors, humidity sensors, light intensity sensors, and air particle sensors. The sensors collect multi-dimensional environmental parameters in real time at a set sampling frequency (e.g., every 5 seconds) and generate time series parameters of environmental data including temperature, humidity, light intensity, and particle concentration.

[0025] The household appliances are powered on intermittently at a set period (for example, powered on for 5 minutes every 12 hours). The linkage control system integrates an embedded sensing device to capture the operating characteristics of the household appliances. The operating characteristic data includes the motor operating temperature, vibration frequency and current waveform changes. The operating characteristic data and multi-dimensional environmental parameters are aligned according to the time series correspondence and the timestamp alignment algorithm is used to integrate the data into a multi-dimensional array and update it to the equipment operation status data table.

[0026] A reference relationship table of association rules between environmental parameters and equipment operation characteristics is predefined. The reference relationship table stores standard comparison data of equipment operation characteristics under all combinations of environmental parameters (the comparison data is obtained according to the equipment operation specification manual or actual experimental measurements). The comparison data is matched and compared with the time-series multidimensional environmental parameters and household appliance operation characteristic data in the operation status data table to generate a multidimensional association data set for sensing changes in household appliance performance. The multidimensional association data set is mainly used to represent the differences in the operation characteristic data of equipment under the same or similar environmental parameters (by calculating the weighted Euclidean distance of the equipment operation characteristics).

[0027] The multidimensional associated data set of household appliance performance changes is synchronously verified through a dynamic comparison algorithm to eliminate abnormal data (missing or redundant data at the same time node), and the remaining multidimensional associated data set is stored in a local storage unit.

[0028] In S3, a performance degradation prediction model for household appliances is constructed, the performance degradation risk levels of household appliances are divided according to the model prediction results, and a maintenance task schedule for household appliances is dynamically generated.

[0029] The operation feature data of the equipment and the multi-dimensional environmental parameters in the multi-dimensional correlation data set of the historical home appliance performance changes in the local storage unit are extracted, and a multi-dimensional historical feature matrix is ​​generated through a feature extraction algorithm. The matrix includes the mapping relationship between the time dimension and the equipment feature dimension. Each row represents the state and environmental changes of the equipment within a time window, and each column represents the specific characteristics of the equipment and the environment.

[0030] Select appropriate deep learning algorithms (such as long short-term memory network (LSTM), convolutional neural network (CNN), etc.) to build a household appliance performance degradation prediction model. The model learns the complex relationship between equipment performance and environmental changes by training historical data. The established model includes an evaluation mechanism between environmental factors (such as temperature, humidity, etc.) and the equipment performance degradation rate. The multidimensional correlation data set of household appliance performance changes in historical data is used to optimize the model weights, so that the model can accurately predict the performance degradation of the equipment under specific environmental conditions. The performance degradation is evaluated by the differential change rate of the operating feature data in the multidimensional correlation data set.

[0031] The real-time operation characteristic data and real-time environmental parameters of the equipment are input into the performance degradation prediction model, and the performance degradation estimation index of the equipment is generated according to the prediction results (the speed of change of the differential change rate of the operation characteristic data in the multi-dimensional correlation data set is used as the performance degradation estimation index), and the degradation risk level is divided according to the performance degradation estimation index. According to the degradation risk level, a maintenance task list of household appliances is generated according to the principle of giving priority to high risk levels, forming a dynamic priority queue for equipment maintenance.

[0032] Based on the dynamic priority queue of home appliance maintenance, the execution order of maintenance tasks is determined through the scheduling algorithm, and a maintenance task schedule for home appliance equipment is generated. The tasks of each device include necessary maintenance operations (such as cleaning, component replacement, performance calibration, etc.), and the task content and execution timing are dynamically adjusted in combination with the attenuation rate of the device and environmental factors. If the attenuation risk level of a certain device is "high risk (assuming the risk level is divided into low risk, medium risk, and high risk)", the priority of its maintenance task will be automatically increased to ensure that the device is repaired or maintained in time before the problem occurs.

[0033] In S4, a task energy consumption hierarchical model is constructed according to the energy consumption characteristics of household appliance maintenance tasks, and energy consumption allocation is adjusted dynamically.

[0034] According to the historical execution records of tasks in the household appliance maintenance task schedule, the average power consumption and continuous running time of each task are extracted. These data can be obtained from the log of each maintenance task, including the start time, end time and average power consumption of each task. The data of all historical tasks are summarized and sorted to generate the energy consumption characteristic data set of each task. The energy consumption characteristic data set must include the total energy consumption of each task, which is calculated as follows: ; In the formula, is the total energy consumption of the kth task, is the average power consumption of the kth task, , The end time and start time of the task respectively.

[0035] By comparing the changes in the operating characteristic data of household appliances before and after the maintenance task (such as motor temperature, vibration frequency, etc.), the impact of the maintenance task on the recovery of equipment performance degradation is evaluated. For example, the maintenance task may restore the operating efficiency of the equipment, reduce vibration or lower the temperature, thereby improving the operating stability of the equipment. The specific method for evaluating the impact of the maintenance task on the recovery of performance degradation is as follows: ; in, is the evaluation value of the impact of maintenance tasks on performance degradation recovery, and They are the weighted Euclidean distances between the equipment operation characteristics before and after the maintenance task is executed and the preset equipment operation characteristics standard comparison data. The impact degree of performance degradation recovery is combined with the task execution energy consumption through weight analysis method to construct the task energy consumption impact matrix , the construction method is: .

[0036] Low energy consumption tasks can be classified into the first level (energy consumption ≤ 5Wh), medium energy consumption tasks can be classified into the second level (5Wh < energy consumption ≤ 20Wh), and high energy consumption tasks can be classified into the third level (energy consumption > 20Wh). Through this classification standard, tasks are layered according to energy consumption characteristics, and a dynamic layered energy consumption model is established. The energy consumption of equipment maintenance tasks is layered, and the model will include the energy consumption gradient and impact of each task, and finally output the energy consumption layer identification of each task.

[0037] The remaining energy storage in the detection linkage system is used as the energy budget. The energy consumption constraints of task execution are dynamically generated based on the energy consumption stratification results of the task. The energy allocation logic for maintenance of each household appliance is adjusted. For example, strategies such as priority scheduling or uniform resource allocation are adopted. Energy is reasonably allocated according to the priority, urgency and energy efficiency requirements of the maintenance task, and finally an energy allocation plan for each task is obtained.

[0038] In S5, the unoccupied state period is predicted according to the door lock operation history records in the local storage unit, and the maintenance tasks are scheduled based on the priority of the household appliance maintenance tasks and the energy budget allocation.

[0039] Extract the historical door lock operation timestamps and operator identity information from the local storage unit to generate time series data. Use time series analysis methods (such as autoregressive model AR, ARIMA model, etc.) to model the time interval characteristics of door lock operations and predict future unoccupied periods. By analyzing the seasonality, trend, and periodicity of time series data, identify whether a household is unoccupied during a specific time period (such as weekdays, holidays, etc.). For example, if the commuting time on weekdays is the time node with the highest frequency of door lock operations, it is inferred that the period between these time nodes on weekdays is unoccupied. In this way, unoccupied periods are predicted, and the prediction results are combined with equipment maintenance task scheduling to ensure that maintenance tasks are performed during unoccupied periods.

[0040] According to the energy budget allocation of maintenance tasks in each level in the task energy consumption hierarchical model (must be within the set range corresponding to the energy consumption level), combined with the preset maintenance input power of each household appliance, the expected maintenance time is calculated (by dividing the energy budget interval allocation by the maintenance input power), and the energy consumption constraints of the equipment maintenance task execution are converted into time constraints.

[0041] According to the priority order of equipment maintenance tasks, the scheduling algorithm is used to disperse and match maintenance tasks to time windows during unoccupied periods. During the task allocation process, if the execution time of a task exceeds the remaining time of the unoccupied period, the task will be adjusted to the next available period. After completing the matching of tasks and time windows, the central controller generates a scheduling plan and allocates equipment maintenance tasks to corresponding time windows according to priority. The central controller will control the corresponding equipment to start the maintenance task within the matched time window and automatically exit the automatic maintenance mode after completion.

[0042] In S6, the abnormal operation characteristics of the household electrical appliances are monitored in real time, and after the abnormal signal is identified, the abnormal data is sent to the remote user end.

[0043] During equipment maintenance, the sensing device monitors the operating characteristics of household appliances in real time and sets the normal data range of each operating characteristic data. For example, the normal range of motor temperature is 20°C to 60°C, the normal range of vibration frequency is 0Hz to 50Hz, and the fluctuation range of current waveform change is ±10%. The normal data range is set according to historical data and equipment specifications. When the normal data range of the operating characteristic data is exceeded, an abnormal signal is sent to the central controller.

[0044] After the central controller recognizes the abnormal signal, it will obtain the operating characteristic data and environmental parameters of the device during this period, such as the current motor temperature, current waveform, humidity, vibration frequency, etc. The real-time operating characteristic data of all devices will be stored in the device status table and sent to the receiving device terminal at the user end as the basic data for fault diagnosis and fault cause analysis.

[0045] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0046] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0047] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A linkage control method for smart home appliances and access control equipment, characterized in that: The steps include: S1: Determine whether the room is unoccupied based on the access control operation record and the biological signal activity pattern. If so, generate a control signal to start the automatic maintenance mode of the smart home appliance. If not, generate a control signal to turn off the automatic maintenance mode of the smart home appliance. S2: Compare and analyze the integrated data of home appliance operation characteristics and external environment parameters with the preset association rules to generate a multi-dimensional association data set for perceiving changes in home appliance performance; S3: Build a performance degradation prediction model for household appliances, classify the performance degradation risk levels of household appliances according to the prediction results of the model, and dynamically generate a maintenance task schedule for household appliances; S4: Build a task energy consumption hierarchical model based on the energy consumption characteristics of household appliance maintenance tasks and dynamically adjust energy consumption allocation; S5: predicting the unoccupied state period based on the door lock operation history in the local storage unit, and scheduling the maintenance tasks based on the priority of the home appliance maintenance tasks and the energy budget allocation; S6: Monitor the abnormal operation characteristics of household appliances in real time, and send the abnormal data to the remote user end after identifying the abnormal signal.

2. The linkage control method of a smart home appliance and a door access control device according to claim 1, characterized in that: In S1, it is determined whether the room is unoccupied according to the access control operation record and the biological signal activity pattern. If so, a control signal is generated to start the automatic maintenance mode of the smart home appliance. If not, a control signal is generated to turn off the automatic maintenance mode of the smart home appliance. Specifically, it includes: Integrate access control equipment and home appliances into a linkage control system, and connect all device control units to a unified central controller; Through the built-in data acquisition device of the access control device, a unique timestamp and operation identity information are recorded each time the door lock is operated, and the data is stored in a local storage unit; Using the indoor sensor unit to collect indoor biological signal data at a set frequency, including infrared sensing signal data and acoustic signal data, to obtain an independent dynamic parameter set of the indoor biological signal data; Define the monitoring cycle of the bio-signal activity pattern and the unmanned pattern feature matching rules, and establish an evaluation model for real-time calculation of the possibility of the indoor unmanned state based on the access control operation records and indoor bio-signal data in the local storage unit; Compare the real-time calculated value generated by the unmanned state assessment model with the preset judgment threshold, trigger the logical judgment of whether the room is unmanned, and update the state variable in the system state unit based on the judgment result; When the status in the system status unit is unoccupied, the central controller generates a control signal and sends it to the designated smart home appliance control unit to control the home appliance to enter the automatic maintenance mode. Conversely, when the status is not unoccupied, the home appliance is controlled to exit the automatic maintenance mode.

3. The linkage control method of a smart home appliance and a door access control device according to claim 2, characterized in that: In S2, the integrated data of the operation characteristics of the household appliances and the external environment parameters are compared and analyzed with the preset association rules to generate a multi-dimensional association data set for sensing the performance changes of the household appliances, including: Collect multi-dimensional indoor environmental parameters in real time through indoor sensor units; The household appliances are powered on intermittently at set intervals. The linkage control system integrates embedded sensing devices to capture the operating characteristics of the household appliances. The operating characteristic data includes the motor operating temperature, vibration frequency and current waveform changes. The operation characteristic data and the multi-dimensional environmental parameters are integrated according to the time series correspondence, and the integrated data is synchronously updated to the equipment operation status data table in the form of a multi-dimensional array; Predefine the association rules between environmental parameters and equipment operation characteristics, match and compare with the time series multi-dimensional environmental parameters and household appliance operation characteristic data in the operation status data table, and generate a multi-dimensional association data set for sensing the performance changes of household appliances; The multidimensional associated data set of the performance changes of household appliances is synchronously verified through a dynamic comparison algorithm to eliminate abnormal data, and the remaining multidimensional associated data set is stored in a local storage unit.

4. The linkage control method of a smart home appliance and a door access control device according to claim 3, characterized in that: In S3, a performance degradation prediction model for household appliances is constructed, and the performance degradation risk level of household appliances is divided according to the prediction results of the model. The maintenance task schedule for household appliances is dynamically generated, including: Extract the operation feature data and multi-dimensional environmental parameters of the equipment from the multi-dimensional associated data set of historical household appliance performance changes in the local storage unit, and generate a multi-dimensional historical feature matrix through a feature extraction algorithm; Based on the multi-dimensional historical feature matrix, a deep learning algorithm is selected to build a household appliance performance degradation prediction model, and an evaluation mechanism for the impact of household appliance performance degradation rate and environmental parameters is established; Input the real-time operation characteristic data and real-time environmental parameters of the equipment into the performance degradation prediction model, generate the performance degradation estimation index of the equipment according to the prediction result, and divide the degradation risk level according to the performance degradation estimation index; According to the attenuation risk level, a maintenance task list for household appliances is generated according to the principle of giving priority to high risk levels, forming a dynamic priority queue for equipment maintenance; Based on the dynamic priority queue of home appliance maintenance, the execution order of maintenance tasks is determined by the scheduling algorithm, and a maintenance task schedule for home appliance is generated.

5. The linkage control method of a smart home appliance and a door access control device according to claim 4, characterized in that: In S4, a task energy consumption hierarchical model is constructed according to the energy consumption characteristics of household appliance maintenance tasks, and the energy consumption allocation is dynamically adjusted, including: Generate an energy consumption characteristic data set for each task based on the average power consumption and continuous running time of the historical execution of tasks in the household appliance maintenance task schedule; By comparing the changes in equipment operation characteristic data after the execution of historical tasks, the impact of maintenance tasks on performance degradation recovery is evaluated. The impact of performance degradation recovery and task execution energy consumption are combined through weight analysis to construct a task energy consumption impact matrix. According to the task energy consumption impact matrix, the corresponding gradient intervals of different levels of energy consumption classification standards are set, a dynamic hierarchical energy consumption model is established, and energy consumption is hierarchical for tasks in the equipment maintenance task schedule; The remaining energy storage in the detection linkage system is used as the energy budget. The energy consumption constraints of task execution are dynamically generated based on the energy consumption stratification results of the task. The energy allocation logic for maintenance of each home appliance is adjusted to allocate the energy budget to the maintenance tasks of the home appliances.

6. The linkage control method of a smart home appliance and a door access control device according to claim 5, characterized in that: In S5, the unoccupied state period is predicted based on the door lock operation history in the local storage unit, and the maintenance task is scheduled based on the priority of the home appliance maintenance task and the energy budget allocation, which specifically includes: Extract the historical door lock operation timestamps and operator identity information from the local storage unit to generate time series data. Based on the time interval characteristics of the door lock operation, the uninhabited period is predicted through the time series analysis method. According to the energy budget allocation of maintenance tasks in each level in the task energy consumption hierarchical model, the expected maintenance time is calculated in combination with the preset maintenance input power of each household appliance, and the energy consumption constraint of the equipment maintenance task execution is converted into a time constraint; According to the maintenance priority order of the equipment maintenance task schedule and the execution time constraints of the equipment maintenance tasks, the maintenance tasks are dispersed and matched to the time windows of the predicted unoccupied periods, and the maintenance tasks are scheduled regularly through the central controller.

7. The linkage control method of a smart home appliance and a door access control device according to claim 6, characterized in that: In S6, real-time monitoring of abnormal operation characteristics of household appliances and sending abnormal data to a remote user after identifying abnormal signals specifically include: During the equipment maintenance process, the sensing device monitors the operating characteristics of the household appliance in real time, sets the normal data range of each operating characteristic data used to judge abnormal characteristics, and sends an abnormal signal to the central controller when the normal data range of the operating characteristic data is exceeded; After the central controller identifies the abnormal signal, it retrieves the equipment under maintenance during the period and the corresponding operating characteristic data and environmental parameters of the equipment, and sends them to the remote user end.

Images