Smart home control method, system and device, storage medium and computer program

Abstract

The invention relates to a smart home control method, system and device, a storage medium and a computer program. The method comprises the steps of determining a to-be-recognized user demand, a to-be-recognized device operation state and to-be-recognized environment parameters; inputting the to-be-identified user demand, the equipment operation state and the environment parameters into an intelligent home control model configured in the central control screen to obtain intelligent control results of a plurality of home equipment connected with the central control screen, wherein the intelligent control results are output by the intelligent home control model; wherein the smart home control model is obtained by training a neural network based on a neural network constructed based on multiple task types, sample data of use habits, equipment operation states and environmental parameters of a user and classification label labels corresponding to the sample data; meanwhile, the invention discloses a system corresponding to the method. According to the invention, the problems of complex operation and low intelligent degree in the prior art are solved, so that better experience of intelligent control and efficient management of household equipment is brought to a user.

Description

Technical Field

[0001] The present disclosure relates to the field of smart home control technology, and in particular to a smart home control method, system, device, storage medium and computer program. Background Art

[0002] With the rapid development of Internet of Things technology, smart home has become an important part of modern family life. However, the smart home control systems currently on the market often have problems such as complex operation and insufficient intelligence. In order to solve these problems, it is urgent to propose a smart home control method and system based on a neural network set in the central control screen, aiming to bring users a more convenient and efficient smart home experience through intelligent control and management. Summary of the invention

[0003] The present invention provides a smart home control method, system, device, storage medium and computer program to solve the problems of complex operation and insufficient intelligence in the prior art.

[0004] In a first aspect, the present disclosure provides a smart home control method for controlling a plurality of home appliances connected to a central control screen, including:

[0005] Determine the user needs, equipment operating status and environmental parameters to be identified;

[0006] Inputting the user needs to be identified, the device operating status and the environmental parameters into the smart home control model configured in the central control screen, and obtaining the smart control results of the several home devices connected to the central control screen output by the smart home control model;

[0007] Among them, the smart home control model is obtained by training the neural network based on a multi-task type and based on sample data of user usage habits, device operating status and environmental parameters and classification labels corresponding to the sample data.

[0008] In some embodiments, the smart home control model includes a data preprocessing model, a feature extraction model, and a multi-task control model;

[0009] The user needs to be identified, the device operating status and the environmental parameters are input into the smart home control model configured in the central control screen, and the smart control results of the home devices connected to the central control screen output by the smart home control model are obtained, including:

[0010] Inputting the user needs to be identified, the equipment operating status and the environmental parameters into the data preprocessing model, and outputting the preprocessed normalized data;

[0011] Inputting the preprocessed normalized data into the feature extraction model, and outputting multiple types of features of the normalized data;

[0012] The various types of features of the normalized data are input into the multi-task control model, and the intelligent control results of the multi-task control instructions of the home appliance are output.

[0013] In some embodiments, the multiple types of features of the normalized data include statistical features, time series features, and predetermined domain knowledge features; wherein the statistical features include one of a mean, a median, and a standard deviation; and the time series features include one of a trend and a cycle.

[0014] In some embodiments, the smart home control model is obtained by training a neural network constructed based on a multi-task type and based on sample data of user usage habits, device operating status and environmental parameters and classification labels corresponding to the sample data, including:

[0015] Constructing a neural network structure including a convolutional neural network, a recurrent neural network and / or a multi-layer perceptron based on multiple task types; wherein the neural network structure includes an input layer, a hidden layer and an output layer, and the hidden layer includes a loss function;

[0016] Based on the user's usage habits, device operating status and environmental parameters, sample data and classification labels corresponding to the sample data are divided into a training set, a validation set and a test set as a data set;

[0017] The loss function is minimized through a training set to train the smart home control model, and the performance of the smart home control model is monitored through a validation set to adjust the parameters of the smart home control model.

[0018] In some embodiments, the multiple task types include user habit classification, device state classification, fault detection and classification, device control parameter regression, and sequence prediction.

[0019] In some embodiments, the smart home control model is used to identify the user needs to be identified, the device operating status and the environmental parameters to intelligently control the home appliances based on the user's usage habits, the sample data of the device operating status and the environmental parameters and the classification labels corresponding to the sample data after training, including:

[0020] Based on the trained smart home control model, real-time monitoring of user usage habits, device operating status and environmental parameters;

[0021] Based on the real-time monitoring of the user's usage habits, equipment operating status and environmental parameters, the convolutional neural network is used to classify user habits, classify equipment status, detect and classify faults, and the recurrent neural network is used to perform sequence prediction and time series analysis, and the multi-layer perceptron is used to predict the continuous value of equipment control parameters;

[0022] The neural network constructed based on the multi-task type dynamically identifies the user's usage habits, device operating status and environmental parameters monitored in real time to achieve intelligent control of the plurality of home appliances.

[0023] In a second aspect, the present disclosure provides a smart home control system, which is arranged in a central control screen connected to a number of home appliances, and includes:

[0024] A data determination unit, used to determine the user needs, equipment operating status and environmental parameters to be identified;

[0025] An intelligent control unit, used to input the user needs to be identified, the device operating status and the environmental parameters into the intelligent home control model configured in the central control screen, and obtain the intelligent control results of the plurality of home appliances connected to the central control screen output by the intelligent home control model;

[0026] The smart home control model is obtained by training a neural network based on a multi-task type and based on sample data of user usage habits, device operating status and environmental parameters and classification labels corresponding to the sample data;

[0027] The smart home control model is used to identify the user needs, device operating status and environmental parameters to be identified after training based on the sample data of the user's usage habits, device operating status and environmental parameters and the classification labels corresponding to the sample data to intelligently control the several home appliances.

[0028] In a third aspect, the present disclosure provides a computer device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the smart home control method described in the above aspects.

[0029] In a fourth aspect, the present disclosure provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the smart home control method described in the above aspects.

[0030] In a fifth aspect, the present disclosure provides a computer program product, including a computer program / instructions, which, when executed by a processor, implements the steps of the smart home control method described in the above aspects.

[0031] The present disclosure adopts the above technical solution, which has the following technical effects compared with the prior art:

[0032] The present invention provides a smart home control method, system, device, storage medium and computer program, which integrates multiple operation modes and functions through the central control screen as a bridge between the user and the smart home system, so as to facilitate the user to control and manage the home appliances anytime and anywhere, and optimizes the intelligent control of the home appliances. By building the learning and recognition functions of a multi-task type neural network, the system can automatically adjust the operating status and energy-saving mode of the equipment, thereby improving the energy efficiency and service life of the equipment. The system can also dynamically monitor the operating status and abnormal data of the equipment to timely discover equipment failures. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The present disclosure will be described in more detail below based on embodiments and with reference to the accompanying drawings:

[0034] Figure 1 A schematic diagram of a neural network-based smart home central control screen system provided in an embodiment of the present disclosure.

[0035] Figure 2 A flowchart of a smart home control method provided in an embodiment of the present disclosure.

[0036] Figure 3 This is a block diagram of a smart home control model provided in an embodiment of the present disclosure.

[0037] Figure 4 A flowchart of the smart home control model training provided in an embodiment of the present disclosure.

[0038] Figure 5 A control flow chart of a smart home control model provided in an embodiment of the present disclosure.

[0039] Figure 6 A schematic diagram of the structure of a smart home control system provided in an embodiment of the present disclosure.

[0040] In the drawings, the same reference numerals are used for the same components, and the drawings are not drawn to scale. DETAILED DESCRIPTION

[0041] In order to enable those skilled in the art to better understand the technical solution of the present disclosure, and to fully understand and implement how the present disclosure applies technical means to solve technical problems and achieve the corresponding technical effects, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only embodiments of a part of the present disclosure, not all of the embodiments. The embodiments of the present disclosure and the various features in the embodiments can be combined with each other without conflict, and the technical solutions formed are all within the scope of protection of the present disclosure. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative work should fall within the scope of protection of the present disclosure.

[0042] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0043] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0044] The technical concept basis of the present disclosure is as follows: Figure 1The schematic diagram of the central control screen system of a smart home based on a neural network is shown. The central control screen 110 is a bridge between the user and the smart home device. It integrates a variety of operation modes and functions, which facilitates the user to control and manage the home device 120 anytime and anywhere. In this embodiment, a high-definition touch screen is used as the display interface of the central control screen, which supports multi-touch and gesture operations, so that the user can easily complete the switch, adjustment, timing and other operations of the device. In this embodiment, advanced voice recognition and natural language processing technology are also used to enable the user to control the home device 120 through simple voice commands. The user can also remotely operate the home device 120 through the mobile phone APP to achieve intelligent control. At the same time, the central control screen 110 can also display the operating status, energy consumption information and personalized services of the home device 120, providing users with a comprehensive smart home experience. In this embodiment, the home device 120 includes various smart home devices, such as smart lighting, smart air conditioning, smart security, etc. These home devices 120 communicate with the central control screen 110 wirelessly to achieve data transmission and execution of control instructions. In this embodiment, standardized communication protocols and device interfaces are used to ensure that smart home devices of different brands and models can be smoothly connected to the system and interconnected. In addition, the intelligent control of the home device 120 is optimized, and the smart home control model is obtained through the learning and recognition function training of the neural network 130. The system can automatically adjust the operating state and energy-saving mode of the home device 120 to improve the energy efficiency and service life of the device.

[0045] The neural network 130 is the core part of the system. It is responsible for processing and analyzing the data collected from the home appliances 120, and learning and optimizing the control strategy accordingly. In this embodiment, a deep learning algorithm is used to construct a neural network model. By training the user's usage habits, device status, environmental parameters and other data, the model can accurately identify the user's needs and the status of the device, and automatically adjust the control parameters of the device to achieve intelligent control. In addition, the neural network model also has fault detection and diagnosis functions. By monitoring the operating status and abnormal data of the device, the module can detect the fault of the device in time and provide corresponding solutions. This can not only improve the efficiency and long-term stability of the equipment, but also save maintenance costs and time for users.

[0046] Embodiment 1

[0047] Figure 2 The present disclosure provides a flow chart of a smart home control method for controlling a number of home appliances connected to a central control screen, such as Figure 2 As shown, including:

[0048] 210, determining the user needs, equipment operating status and environmental parameters to be identified;

[0049] 220, inputting the user needs to be identified, the device operating status and the environmental parameters into the smart home control model configured in the central control screen, and obtaining the smart control results of the plurality of home appliances connected to the central control screen output by the smart home control model;

[0050] Among them, the smart home control model is obtained by training the neural network based on a multi-task type and based on sample data of user usage habits, device operating status and environmental parameters and classification labels corresponding to the sample data.

[0051] Specifically, in the model training phase, we collect a large amount of user usage habit data (such as switching frequency, usage time, temperature preference, etc.), device status data (such as power consumption, operating status, temperature, fault log, etc.) and environmental parameter data (such as indoor and outdoor temperature, humidity, light, etc.), and then label and classify the data, normalize it, and then use the convolutional neural network (CNN) to extract features from these data to train the model. It should be noted that data labeling: for user needs and device status, label the corresponding labels or categories; for fault data, clearly label the fault type and location.

[0052] The smart home control model is used to identify the user needs, device operating status and environmental parameters to be identified after training based on the sample data of the user's usage habits, device operating status and environmental parameters and the classification labels corresponding to the sample data to intelligently control the several home appliances.

[0053] Specifically, in the model application phase: real-time monitoring of user control instructions, environmental parameter data, equipment operating status data, etc.; then the convolutional neural network (CNN) performs fault detection and classification, while the recurrent neural network (RNN) performs sequence prediction and time series analysis to more accurately predict user needs and achieve intelligent control.

[0054] Compared with the prior art, the central control screen system of the present invention can automatically learn and identify the user's usage habits and device status by integrating neural network technology, and realize intelligent control and management. That is, a neural network model is constructed by using a deep learning algorithm, and by training data such as user usage habits, device status, and environmental parameters, the model can accurately identify user needs and device status, and automatically adjust the control parameters of the device to realize intelligent control.

[0055] Embodiment 2

[0056] Based on the above embodiments, Figure 3As shown, the smart home control model includes a data preprocessing model 310, a feature extraction model 320 and a multi-task control model 330;

[0057] The user needs to be identified, the device operating status and the environmental parameters are input into the smart home control model configured in the central control screen, and the smart control results of the home devices connected to the central control screen output by the smart home control model are obtained, including:

[0058] Inputting the user needs to be identified, the equipment operating status and the environmental parameters into the data preprocessing model, and outputting the preprocessed normalized data;

[0059] Specifically, data preprocessing first requires data cleaning to remove noise, outliers, and duplicate data, and then standardizing, normalizing, or encoding the cleaned data.

[0060] Inputting the preprocessed normalized data into the feature extraction model, and outputting multiple types of features of the normalized data;

[0061] The various types of features of the normalized data are input into the multi-task control model, and the intelligent control results of the multi-task control instructions of the home appliance are output.

[0062] It should be noted that the multi-task control model adopts multi-task learning and constructs a multi-task learning framework to simultaneously process control instructions of multiple tasks (such as user demand identification, equipment status monitoring, and fault detection).

[0063] Embodiment 3

[0064] Based on the above embodiment, the multiple types of features of the normalized data include statistical features, time series features and predetermined domain knowledge features; wherein the statistical features include one of the mean, median and standard deviation; and the time series features include one of the trend and cycle.

[0065] That is to say, meaningful features are extracted from normalized data, which may include statistical features (such as mean, median, standard deviation, etc.), time series features (such as trend, periodicity, etc.), and features based on domain knowledge.

[0066] Embodiment 4

[0067] On the basis of the above embodiment, the smart home control model is obtained by training the neural network based on a multi-task type and based on the user's usage habits, device operation status and environmental parameter sample data and the classification label annotation corresponding to the sample data. Figure 4 As shown, including:

[0068] 410. Constructing a neural network structure including a convolutional neural network, a recurrent neural network and / or a multi-layer perceptron based on the multi-task type; wherein the neural network structure includes an input layer, a hidden layer and an output layer, and the hidden layer includes a loss function;

[0069] Specifically, neural network architecture selection: select the appropriate neural network architecture according to the task type (such as classification, regression, sequence prediction, etc.). For classification problems of user habits and device status, multi-layer perceptron (MLP), convolutional neural network (CNN), or recurrent neural network (RNN / LSTM) can be used. For problems that require prediction of continuous values ​​(such as device control parameters), regression models such as MLP or deep reinforcement learning models can be used. Build a structural model: Design the network structure, including the input layer, hidden layer, and output layer. The hidden layer can choose different types of neurons (such as ReLU, Sigmoid, etc.) as needed. For sequence data, architectures such as RNN or LSTM can be used. Select appropriate activation functions, optimizers, and loss functions. Use regularization techniques (such as Dropout, L1 / L2 regularization) to prevent overfitting.

[0070] 420, dividing the sample data based on the user's usage habits, device operating status and environmental parameters and the classification label annotations corresponding to the sample data into a training set, a validation set and a test set;

[0071] 430 , minimizing the loss function through a training set to train the smart home control model, and monitoring the performance of the smart home control model through a validation set to adjust the parameters of the smart home control model.

[0072] Specifically, divide the dataset into training set, validation set and test set. Choose an appropriate loss function (such as cross entropy loss for classification problems and mean squared error loss for regression problems). Use an optimization algorithm (such as stochastic gradient descent SGD, Adam, etc.) to minimize the loss function. Adjust hyperparameters (such as learning rate, batch size, number of network layers, etc.) by monitoring the performance of the model on the validation set. Use Early Stopping or Model Checkpointing to avoid overfitting. Use the training data to train the model and evaluate the performance of the model on the validation set. Adjust hyperparameters (such as learning rate, batch size, number of network layers, etc.) based on the performance of the validation set.

[0073] Embodiment 5

[0074] Based on the above embodiment, the multi-task types include user habit classification, device status classification, fault detection and classification, device control parameter regression and sequence prediction.

[0075] Specifically, for classification problems of user habits and device status, multi-layer perceptrons (MLP), convolutional neural networks (CNN), or recurrent neural networks (RNN / LSTM) can be used. For problems that require prediction of continuous values ​​(such as device control parameters), regression models such as MLP or deep reinforcement learning models can be used. Convolutional neural networks (CNN) perform fault detection and classification, while recurrent neural networks (RNN) perform sequence prediction and time series analysis to more accurately predict user needs and achieve intelligent control.

[0076] Anomaly detection: Use unsupervised learning methods (such as Isolation Forest, DBSCAN, etc.) or density-based clustering methods (such as LOF) to detect abnormal data. Abnormal data may indicate equipment failure or abnormal status.

[0077] Fault classification: Once abnormal data is detected, supervised learning models (such as classifiers) can be used to further identify the fault type. This requires a labeled fault dataset for training. Diagnosis: Based on the fault type, output diagnostic information or recommended repair measures.

[0078] Embodiment 6

[0079] On the basis of the above embodiment, the smart home control model is used to identify the user needs to be identified, the device operating status and the environmental parameters to intelligently control the home appliances, such as Figure 5 As shown, including:

[0080] 510, based on the trained smart home control model, real-time monitoring of user usage habits, device operating status and environmental parameters;

[0081] 520, based on the real-time monitored user usage habits, device operating status and environmental parameters, perform user habit classification, device status classification, fault detection and classification through the convolutional neural network, perform sequence prediction and time series analysis through the recurrent neural network, and perform continuous value prediction of device control parameters through the multi-layer perceptron;

[0082] 530, dynamically identifying the user's usage habits, device operating status and environmental parameters monitored in real time based on the neural network constructed based on the multi-task type, so as to realize intelligent control of the plurality of home appliances.

[0083] It should be emphasized that model deployment: deploy the trained model to the central control screen system to receive user and device data in real time. Real-time monitoring: continuously monitor the operating status of the equipment and use the model for fault detection. Control parameter adjustment: automatically adjust the control parameters of the device according to user needs and device status. Specifically, according to user needs and device status, the model can automatically adjust the control parameters of the device, such as temperature, humidity, brightness, etc., which can be achieved by using the control parameters as the output layer of the model. Feedback loop: by continuously collecting new user feedback and device data, the model can gradually learn and improve its control strategy.

[0084] Embodiment 7

[0085] Based on the above embodiments, the present disclosure provides a smart home control system. Figure 6 The schematic diagram of the structure of the smart home control system shown is set in the central control screen connected to several home appliances, including:

[0086] A data determination unit 610 is used to determine the user needs, device operating status and environmental parameters to be identified;

[0087] The intelligent control unit 620 is used to input the user needs to be identified, the device operating status and the environmental parameters into the smart home control model configured in the central control screen, and obtain the intelligent control results of the several home appliances connected to the central control screen output by the smart home control model;

[0088] The smart home control model is obtained by training a neural network based on a multi-task type and based on sample data of user usage habits, device operating status and environmental parameters and classification labels corresponding to the sample data;

[0089] The smart home control model is used to identify the user needs, device operating status and environmental parameters to be identified after training based on the sample data of the user's usage habits, device operating status and environmental parameters and the classification labels corresponding to the sample data to intelligently control the several home appliances.

[0090] Compared with the prior art, the central control screen system of the present invention can automatically learn and identify the user's usage habits and device status by integrating neural network technology, and realize intelligent control and management. That is, a neural network model is constructed by using a deep learning algorithm, and by training data such as user usage habits, device status, and environmental parameters, the model can accurately identify user needs and device status, and automatically adjust the control parameters of the device to realize intelligent control.

[0091] Embodiment 8

[0092] On the basis of the above embodiment, the intelligent control unit includes a data preprocessing module, a feature extraction module and a multi-task control module;

[0093] The data preprocessing module is used to input the user needs to be identified, the equipment operating status and the environmental parameters, and output the preprocessed normalized data;

[0094] The feature extraction module is used to input the preprocessed normalized data and output multiple types of features of the normalized data;

[0095] The multi-task control module is used to input multiple types of features of the normalized data and output the intelligent control results of the multi-task control instructions of the home appliance.

[0096] Embodiment 9

[0097] On the basis of the above embodiments, this embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method described in the above embodiments.

[0098] In some implementations of this embodiment, a computer-readable storage medium is provided, on which a computer program is stored, characterized in that when the computer program is executed by a processor, the steps of the method described in the above embodiment are implemented.

[0099] In some implementations of this embodiment, a computer program product is provided, including a computer program / instructions, characterized in that when the computer program is executed by a processor, the steps of the method described in the above embodiment are implemented.

[0100] The processor may include, but is not limited to, one or more processors or microprocessors. Each processor may be an application specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a controller, a microcontroller, a microprocessor or other electronic components to execute the method in the above embodiments.

[0101] The computer-readable storage medium may be implemented by any type of volatile or non-volatile storage device or a combination thereof. The computer-readable storage medium may include, but is not limited to, for example, random access memory (RAM), read-only memory (ROM), flash memory, EPROM memory, EEPROM memory, registers, computer storage media (e.g., hard disk, floppy disk, solid-state drive, removable disk, CDROM, DVDROM, Blu-ray disc, etc.).

[0102] The computer-readable storage medium may also store at least one computer executable program / instruction, which may be, for example, a computer-readable instruction. The computer-readable storage medium includes, but is not limited to, for example, a volatile memory and / or a non-volatile memory. The volatile memory may include, for example, a random access memory (RAM) and / or a cache memory (cache), etc. The computer-readable storage medium may include, for example, a read-only memory (ROM), a hard disk, a flash memory, etc. For example, a non-transitory computer-readable storage medium may be connected to a computing device such as a computer, and then, when the computing device runs the computer-readable instructions stored on the computer-readable storage medium, the various methods described above may be performed.

[0103] In addition, the computer device may also include (but not limited to) a data bus, an input / output (I / O) bus, a display, and input / output devices (eg, keyboard, mouse, speaker, etc.), etc.

[0104] The processor may communicate with external devices via an I / O bus via a wired or wireless network.

[0105] In one embodiment, the at least one computer executable instruction may also be compiled into or constitute a software product / computer program product, wherein one or more computer executable instructions are executed by a processor to perform the various functions and / or method steps in the embodiments described in the present technology.

[0106] In the embodiments provided in the present disclosure, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the above-mentioned module, program segment or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0107] It should be noted that in the present disclosure, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element limited by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0108] Although the embodiments disclosed in the present disclosure are as above, the above contents are only embodiments adopted for facilitating the understanding of the present disclosure and are not intended to limit the present disclosure. Any technician in the technical field to which the present disclosure belongs can make any modifications and changes in the form and details of the implementation without departing from the spirit and scope disclosed in the present disclosure, but the scope of patent protection of the present disclosure shall still be subject to the scope defined in the attached claims.

Claims

1. A smart home control method for controlling several home appliances connected to a central control screen, characterized in that: include: Determine the user needs, equipment operating status and environmental parameters to be identified; Inputting the user needs to be identified, the device operating status and the environmental parameters into the smart home control model configured in the central control screen, and obtaining the smart control results of the several home devices connected to the central control screen output by the smart home control model; Among them, the smart home control model is obtained by training the neural network based on a multi-task type and based on sample data of user usage habits, device operating status and environmental parameters and classification labels corresponding to the sample data.

2. The smart home control method according to claim 1, characterized in that: The smart home control model includes a data preprocessing model, a feature extraction model and a multi-task control model; The user needs to be identified, the device operating status and the environmental parameters are input into the smart home control model configured in the central control screen, and the smart control results of the home devices connected to the central control screen output by the smart home control model are obtained, including: Inputting the user needs to be identified, the equipment operating status and the environmental parameters into the data preprocessing model, and outputting the preprocessed normalized data; Inputting the preprocessed normalized data into the feature extraction model, and outputting multiple types of features of the normalized data; The various types of features of the normalized data are input into the multi-task control model, and the intelligent control results of the multi-task control instructions of the home appliance are output.

3. The smart home control method according to claim 2, characterized in that: The multiple types of features of the normalized data include statistical features, time series features and predetermined domain knowledge features; wherein the statistical features include one of a mean, a median and a standard deviation; and the time series features include one of a trend and a cycle.

4. The smart home control method according to claim 1, characterized in that: The smart home control model is obtained by training a neural network based on a multi-task type and based on sample data of user usage habits, device operating status and environmental parameters and classification labels corresponding to the sample data, including: Constructing a neural network structure including a convolutional neural network, a recurrent neural network and / or a multi-layer perceptron based on multiple task types; wherein the neural network structure includes an input layer, a hidden layer and an output layer, and the hidden layer includes a loss function; The sample data based on the user's usage habits, device operating status and environmental parameters and the classification label annotations corresponding to the sample data are divided into a training set, a validation set and a test set as a data set; The smart home control model is trained by minimizing the loss function through a training set, and the performance of the smart home control model is monitored through a validation set to adjust the parameters of the smart home control model.

5. The smart home control method according to claim 4, characterized in that: The multi-task types include user habit classification, device status classification, fault detection and classification, device control parameter regression and sequence prediction.

6. The smart home control method according to any one of claims 1 to 5, characterized in that: The smart home control model is used to identify the user needs to be identified, the device operating status and the environmental parameters to intelligently control the home appliances based on the user's usage habits, the sample data of the device operating status and the environmental parameters and the classification labels corresponding to the sample data after training, including: Based on the trained smart home control model, real-time monitoring of user usage habits, device operating status and environmental parameters; Based on the real-time monitoring of the user's usage habits, equipment operating status and environmental parameters, the convolutional neural network is used to classify user habits, classify equipment status, detect and classify faults, and the recurrent neural network is used to perform sequence prediction and time series analysis, and the multi-layer perceptron is used to predict the continuous value of equipment control parameters; The neural network constructed based on the multi-task type dynamically identifies the user's usage habits, device operating status and environmental parameters monitored in real time to achieve intelligent control of the plurality of home appliances.

7. A smart home control system, arranged in a central control screen connected to a number of home appliances, characterized in that: include: A data determination unit, used to determine the user needs, equipment operating status and environmental parameters to be identified; An intelligent control unit, used to input the user needs to be identified, the device operating status and the environmental parameters into the intelligent home control model configured in the central control screen, and obtain the intelligent control results of the plurality of home appliances connected to the central control screen output by the intelligent home control model; The smart home control model is obtained by training a neural network based on a multi-task type and based on sample data of user usage habits, device operating status and environmental parameters and classification labels corresponding to the sample data; The smart home control model is used to identify the user needs, device operating status and environmental parameters to be identified after training based on the sample data of the user's usage habits, device operating status and environmental parameters and the classification labels corresponding to the sample data to intelligently control the several home appliances.

8. A computer device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the smart home control method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the smart home control method described in any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program is executed by a processor, the steps of the smart home control method described in any one of claims 1 to 6 are implemented.

Images