Cooperative control method and device for household equipment, and storage medium

Abstract

The invention relates to the technical field of smart home and smart home, and discloses a cooperative control method and device for home equipment and a storage medium, and the method comprises the steps: obtaining target data features of control reference data, the control reference data comprising user behavior data, environment data and operation state data of a plurality of pieces of home equipment; predicting intention information of the user based on the target data features, and generating an initial cooperative control strategy based on the intention information and the control reference data; obtaining an evaluation index of the initial cooperative control strategy, and determining a target cooperative control strategy based on the initial cooperative control strategy and the evaluation index thereof; and controlling the cooperative operation of the plurality of home devices based on the target cooperative control strategy. According to the cooperative operation of the plurality of household devices according to the target cooperative control strategy, the environment created by the household devices can be better matched with the actual willingness of the user and the current environment condition.

Description

Technical Field

[0001] The present disclosure relates to the technical field of smart homes, for example, to a collaborative control method, device and storage medium for home appliances. Background Art

[0002] With the rapid development of science and technology, intelligent home appliances have gradually entered people's lives, and people's demand for the intelligence of home appliances has gradually increased. For example, users usually hope that multiple home appliances can jointly create the desired living environment through automated collaborative control.

[0003] In the related art, the potential needs and behavior patterns of users can be predicted, and then multiple home appliances can be linked and controlled according to the corresponding scene modes. However, the scene modes in the related art are relatively fixed, lacking flexibility and adaptability, and cannot relatively ideally meet the actual wishes of users.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0005] In order to provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. The summary is not an extensive review, nor is it intended to identify key / critical components or delineate the scope of protection of these embodiments, but rather serves as a prelude to the detailed description that follows.

[0006] The embodiments of the present disclosure provide a collaborative control method, device, and storage medium for home appliances, which can make the environment created by the home appliances more compatible with the actual wishes of the user and the current environmental conditions.

[0007] According to a first aspect of the present disclosure, a collaborative control method for home appliances is provided, the collaborative control method comprising:

[0008] Acquire target data features of control reference data, where the control reference data includes at least one or more of the following data types: user behavior data, environmental data, and operating status data of a plurality of home appliances;

[0009] Predict the user's intention information based on the target data features, and generate an initial collaborative control strategy based on the intention information and control reference data;

[0010] Obtaining evaluation indicators of the initial collaborative control strategy, and determining a target collaborative control strategy based on the initial collaborative control strategy and its evaluation indicators;

[0011] Control the collaborative operation of multiple home devices based on target collaborative control strategy.

[0012] In some embodiments, obtaining target data features of control reference data includes:

[0013] Obtain control reference data;

[0014] Extracting initial data features from control reference data;

[0015] The preset regression algorithm and variational random features are used to enhance the initial data features to obtain the target data features.

[0016] In some embodiments, the preset regression algorithm is kernel ridge regression, and the kernel function used in kernel ridge regression is composed of an exponential decay kernel and a cosine kernel. The exponential decay kernel is used to capture local characteristics in the data, and the cosine kernel is used to capture periodicity or rotation invariance in the data.

[0017] In some embodiments, the expression of the evidence lower bound of the variational random feature consists of an expectation term, a KL divergence, and a variational free energy term. The expectation term is used to measure the predictive ability of the observed data, the KL divergence is used to measure the degree of difference between the variational distribution and the prior distribution, and the variational free energy term is used to improve the quality of the variational posterior distribution.

[0018] In some embodiments, the initial data features are enhanced using a preset regression algorithm and a variational random feature to obtain a target data feature, including:

[0019] The initial data features are enhanced using the preset regression algorithm and variational random features to obtain intermediate data features;

[0020] The conditional normalization flow is used to diversify the intermediate data features to obtain the target data features.

[0021] In some embodiments, predicting user intention information based on target data features includes:

[0022] The target data features are input into the long short-term memory model, and the long short-term memory model is used to predict the user's intention information. The degree of attention of the long short-term memory model to different time steps is dynamically adjusted by the attention mechanism.

[0023] In some embodiments, obtaining an evaluation index of an initial collaborative control strategy and determining a target collaborative control strategy based on the initial collaborative control strategy and its evaluation index include:

[0024] The control strategy optimization process is iterated until the evaluation index that reaches the maximum value is determined. The control strategy optimization process includes:

[0025] Obtaining the evaluation index of the initial collaborative control strategy, and determining whether the evaluation index reaching the maximum value is searched;

[0026] When it is determined that the evaluation index that reaches the maximum value has not been searched, the strategy parameters of the initial collaborative control strategy are adjusted;

[0027] When it is determined that the evaluation index that has reached the maximum value is searched, the initial collaborative control strategy corresponding to the evaluation index that has reached the maximum value is determined as the target collaborative control strategy.

[0028] In some embodiments, the evaluation indicators include: user comfort indicators, energy consumption indicators, and device response speed indicators.

[0029] According to a second aspect of the present disclosure, a collaborative control device for household appliances is provided, the collaborative control device comprising:

[0030] a feature acquisition module configured to acquire target data features of control reference data, wherein the control reference data includes at least one or more of the following data types: user behavior data, environmental data, and operating status data of a plurality of home appliances;

[0031] A strategy generation module is configured to predict the user's intention information based on the target data characteristics, and generate an initial collaborative control strategy based on the intention information and the control reference data;

[0032] A strategy optimization module is configured to obtain an evaluation index of an initial collaborative control strategy and determine a target collaborative control strategy based on the initial collaborative control strategy and its evaluation index;

[0033] The device control module is configured to control the coordinated operation of multiple home appliances based on a target collaborative control strategy.

[0034] According to a third aspect of the present disclosure, a collaborative control device for home appliances is provided, comprising a processor and a memory storing program instructions, wherein the processor is configured to execute the collaborative control method for home appliances provided by the first aspect of the present disclosure when running the program instructions.

[0035] According to a fourth aspect of the present disclosure, a storage medium is provided, in which computer program instructions are stored. When the computer program instructions are executed by a processor, the collaborative control method for home appliances provided in the first aspect of the present disclosure is executed.

[0036] The collaborative control method, device, and storage medium for home appliances provided by the embodiments of the present disclosure can achieve the following technical effects:

[0037] The collaborative control method for home appliances provided by the embodiments of the present disclosure can accurately predict the user's intention information through control reference data of multiple dimensions, and then generate an initial collaborative control strategy that meets the user's wishes based on the intention information and the control reference data. Then, further optimization is performed based on the evaluation index to obtain the target collaborative control strategy. The collaborative operation of multiple home appliances according to the target collaborative control strategy can make the environment created by the home appliances more in line with the user's actual wishes and current environmental conditions.

[0038] The foregoing general description and the following description are exemplary and explanatory only and are not intended to limit the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] One or more embodiments are exemplarily described by corresponding drawings, which do not limit the embodiments. Elements with the same reference numerals in the drawings are shown as similar elements, and the drawings do not constitute a scale limitation, and wherein:

[0040] Figure 1 is a flowchart of a collaborative control method for home appliances provided by an embodiment of the present disclosure;

[0041] Figure 2 is a flow chart of another collaborative control method for home appliances provided by an embodiment of the present disclosure;

[0042] Figure 3 is a flow chart of another collaborative control method for home appliances provided by an embodiment of the present disclosure;

[0043] Figure 4 is a flow chart of another collaborative control method for home appliances provided by an embodiment of the present disclosure;

[0044] Figure 5 is a flow chart of another collaborative control method for home appliances provided by an embodiment of the present disclosure;

[0045] Figure 6 is a structural schematic diagram of a collaborative control device for household appliances provided by an embodiment of the present disclosure;

[0046] Figure 7 It is a structural schematic diagram of another collaborative control device for home appliances provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0047] In order to be able to understand the features and technical contents of the embodiments of the present disclosure in more detail, the implementation of the embodiments of the present disclosure is described in detail below in conjunction with the accompanying drawings. The attached drawings are for reference only and are not used to limit the embodiments of the present disclosure. In the following technical description, for the convenience of explanation, a full understanding of the disclosed embodiments is provided through multiple details. However, one or more embodiments can still be implemented without these details. In other cases, to simplify the drawings, well-known structures and devices can be simplified for display.

[0048] The terms "first", "second", etc. in the specification and claims of the embodiments 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 terms used in this way can be interchanged where appropriate, so that the embodiments of the embodiments of the present disclosure described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions.

[0049] Unless otherwise stated, the term "plurality" means two or more.

[0050] In the embodiment of the present disclosure, the character " / " indicates that the preceding and following objects are in an "or" relationship. For example, A / B indicates: A or B.

[0051] The term "and / or" is a description of the association relationship between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or, A and B.

[0052] The term "correspondence" may refer to an association relationship or a binding relationship. The correspondence between A and B means that there is an association relationship or a binding relationship between A and B.

[0053] With the rapid development of science and technology, intelligent home appliances have gradually entered people's lives, and people's demand for the intelligence of home appliances has gradually increased. For example, users usually hope that multiple home appliances can jointly create the desired living environment through automated collaborative control.

[0054] In the related art, the potential needs and behavior patterns of users can be predicted, and then multiple home appliances can be linked and controlled according to the corresponding scene modes. However, the scene modes in the related art are relatively fixed, lacking flexibility and adaptability, and cannot relatively ideally meet the actual wishes of users.

[0055] An embodiment of the present disclosure provides a collaborative control device for home appliances. The collaborative control device can predict user intention information based on data features of control reference data, and generate a collaborative control strategy based on the intention information and the control reference data, and then control the collaborative operation of multiple home appliances based on the target collaborative control strategy.

[0056] In conjunction with the collaborative control device for home appliances provided in the embodiments of the present disclosure, the embodiments of the present disclosure provide a collaborative control method for home appliances, the execution subject of the method is a collaborative control device for home appliances (hereinafter referred to as the collaborative control device), such as Figure 1 As shown, the collaborative control method for home appliances includes:

[0057] S101, the collaborative control device obtains target data features of control reference data.

[0058] In the disclosed embodiment, the control reference data includes at least one or more of the following data types: user behavior data, environmental data, and operating status data of multiple home appliances. The user behavior data includes user voice commands and user movement trajectories, the environmental data includes temperature, humidity, and light intensity, and the operating status data includes start / stop status, operating mode, and operating power.

[0059] In the disclosed embodiment, user behavior data and environmental data can be obtained through corresponding sensors (such as human body sensors, cameras, and temperature and humidity sensors, etc.), and the operating status data uploaded by the home appliances can be received, and these data can be used as control reference data. The control reference data is then preprocessed (such as cleaning and normalization, etc.), and feature extraction is performed on the preprocessed control reference data to obtain target data features of the control reference data.

[0060] In some embodiments, the control reference data may further include time information, where the time information includes the current season and the time period to which the current moment belongs in a day.

[0061] S102, the collaborative control device predicts the user's intention information based on the target data characteristics, and generates an initial collaborative control strategy based on the intention information and control reference data.

[0062] In the disclosed embodiment, the target data features can be input into a pre-trained deep learning model, and the deep learning model can be used to predict the user's intention information. The intention information represents the user's upcoming needs and possible behaviors. The deep learning model can be a long short-term memory (LSTM) model, a gated recurrent unit (GRU) or a model based on the Transformer architecture.

[0063] In an embodiment of the present disclosure, an optimization algorithm (such as a genetic algorithm or a particle swarm optimization algorithm, etc.) is used to generate initial collaborative control strategy candidates based on intention information and control reference data.

[0064] S103, the collaborative control device obtains evaluation indicators of the initial collaborative control strategy, and determines a target collaborative control strategy based on the initial collaborative control strategy and its evaluation indicators.

[0065] In the embodiment of the present disclosure, the type of evaluation index to be obtained can be preset, for example, the evaluation index can include a user comfort index, an energy consumption index, and a device response speed index. It can be understood that the evaluation index of the initial collaborative control strategy can be any one of the above indicators, or the evaluation index of the initial collaborative control strategy can be a fusion value of the above multiple indicators.

[0066] The evaluation index can reflect the degree of matching between the initial collaborative control strategy and the actual intention of the matching user and the current environmental conditions. Based on the evaluation index, the initial collaborative control strategy can be screened or optimized to obtain a target collaborative control strategy that better matches the actual intention of the user and the current environmental conditions.

[0067] S104, the collaborative control device controls the collaborative operation of multiple home appliances based on the target collaborative control strategy.

[0068] In the disclosed embodiment, the target collaborative control strategy involves multiple home appliances. Here, based on the target collaborative control strategy, a corresponding control instruction can be sent to each home appliance for the control instruction of each home appliance involved, so that the home appliance operates according to the control instruction.

[0069] The collaborative control method for home appliances provided by the embodiments of the present disclosure can accurately predict the user's intention information through control reference data of multiple dimensions, and then generate an initial collaborative control strategy that meets the user's wishes based on the intention information and the control reference data. Then, further optimization is performed based on the evaluation index to obtain the target collaborative control strategy. The collaborative operation of multiple home appliances according to the target collaborative control strategy can make the environment created by the home appliances more in line with the user's actual wishes and current environmental conditions.

[0070] In some embodiments, obtaining target data features of control reference data includes: obtaining control reference data, extracting initial data features from the control reference data, enhancing the initial data features using a preset regression algorithm and variational random features, and obtaining target data features.

[0071] Combination Figure 2 As shown, the embodiment of the present disclosure provides another collaborative control method for home appliances, and the collaborative control method for home appliances includes:

[0072] S201, the collaborative control device obtains control reference data.

[0073] S202, the collaborative control device extracts initial data features from the control reference data.

[0074] S203, the collaborative control device uses a preset regression algorithm and variational random features to enhance the initial data features to obtain target data features.

[0075] In the disclosed embodiment, the preset regression algorithm may be kernel ridge regression, which is introduced as a basic learner. Kernel ridge regression maps initial data features to a high-dimensional feature space by using a kernel function, thereby being able to handle nonlinear relationships. At the same time, variational random features are combined to enhance the ability to extract and represent initial data features, thereby obtaining target data features.

[0076] In the embodiment of the present disclosure, the preset regression algorithm is kernel ridge regression. The kernel function used by kernel ridge regression consists of an exponential decay kernel and a cosine kernel. The exponential decay kernel is used to capture the local characteristics in the data, and the cosine kernel is used to capture the periodicity or rotational invariance in the data. The expression of the kernel function is as follows:

[0077]

[0078] In the above expression, K(x,x′) is a kernel function used to measure the similarity between two input vectors x and x′. exp(-β||xx′||p) is an exponential decay kernel. is the cosine kernel. |||xx′||p is the Euclidean distance, which represents the distance between x and x′ in multidimensional space, where p can be any positive number. β is a scalar parameter that controls the width or smoothness of the Gaussian kernel function. θ is another scalar parameter that determines the weight of the cosine term in the kernel function. D is the number of cosine terms, which indicates how many cosine waves of different frequencies are superimposed together. w k and are the frequency and phase offset of the kth cosine term, respectively.

[0079] In the disclosed embodiment, the expression of the lower bound of the evidence of the variational random feature is composed of the expectation term, the KL divergence (Kullback-Leibler divergence) and the variational free energy term. The expectation term is used to measure the predictive ability of the observed data, the KL divergence is used to measure the degree of difference between the variational distribution and the prior distribution, and the variational free energy term is used to improve the quality of the variational posterior distribution. The expression of the lower bound of the evidence of the variational random feature is as follows:

[0080]

[0081] In the above expression, ELBO is the lower bound of evidence, E q(θ) [logp(y|x,θ)] is the expectation term, KL(q(θ)||p(θ)) is the KL divergence, is the variational free energy term. q(θ) is the variational distribution, p(θ) is the prior distribution, p(y|x,θ) is the conditional likelihood function, the probability of observing output y given input x and parameters θ, and M is the number of parameters. Assume that the parameters θ are decomposed into independent parts θ j ,...,θ j ,...,θ M , and each part has its own variational distribution and thus prior distribution.

[0082] S204, the collaborative control device predicts the user's intention information based on the target data characteristics, and generates an initial collaborative control strategy based on the intention information and the control reference data.

[0083] S205: The collaborative control device obtains evaluation indicators of the initial collaborative control strategy, and determines a target collaborative control strategy based on the initial collaborative control strategy and its evaluation indicators.

[0084] S206, the collaborative control device controls the collaborative operation of multiple home appliances based on the target collaborative control strategy.

[0085] In some embodiments, the initial data features are enhanced using a preset regression algorithm and variational random features to obtain target data features, including: enhancing the initial data features using a preset regression algorithm and variational random features to obtain intermediate data features; and diversifying the intermediate data features using a conditional normalization flow to obtain target data features.

[0086] Combination Figure 3 As shown, the embodiment of the present disclosure provides another collaborative control method for home appliances, and the collaborative control method for home appliances includes:

[0087] S301, the collaborative control device obtains control reference data.

[0088] S302, the collaborative control device extracts initial data features from the control reference data.

[0089] S303, the collaborative control device uses a preset regression algorithm and variational random features to enhance the initial data features to obtain intermediate data features.

[0090] In the disclosed embodiment, the preset regression algorithm may be kernel ridge regression, which is introduced as a basic learner. Kernel ridge regression maps initial data features to a high-dimensional feature space by using a kernel function, thereby being able to handle nonlinear relationships. At the same time, variational random features are combined to enhance the extraction and representation capabilities of initial data features, thereby obtaining intermediate data features.

[0091] S304, the collaborative control device uses the conditional normalization flow to diversify the intermediate data features to obtain the target data features.

[0092] In the disclosed embodiment, conditional normalization flow is used to diversify the intermediate data features and enrich the random features, thereby improving the system's ability to capture complex user behavior patterns and dynamic environments. Through a series of reversible transformations, the original simple random feature distribution is converted into a more expressive and complex distribution, providing strong support for more accurate control strategy generation.

[0093] In the embodiment of the present disclosure, the expression of the transformation function of the conditional normalization flow is as follows:

[0094] s(z,x)=α(x)·sin(β(z)),

[0095] t(z,x)=γ(x)·cos(δ(z)).

[0096] In the above expressions, s(z,x) and t(z,x) are used to change the input feature z, α(x) and γ(x) are coefficients that depend on the conditional variable x, and β(z) and δ(z) are angular factors that depend on the input feature z.

[0097] S305, the collaborative control device predicts the user's intention information based on the target data characteristics, and generates an initial collaborative control strategy based on the intention information and the control reference data.

[0098] S306: The collaborative control device obtains evaluation indicators of the initial collaborative control strategy, and determines a target collaborative control strategy based on the initial collaborative control strategy and its evaluation indicators.

[0099] S307, the collaborative control device controls the collaborative operation of multiple home appliances based on the target collaborative control strategy.

[0100] In some embodiments, predicting user intention information based on target data features includes:

[0101] The target data features are input into the long short-term memory model, and the long short-term memory model is used to predict the user's intention information. The degree of attention of the long short-term memory model to different time steps is dynamically adjusted by the attention mechanism.

[0102] Combination Figure 4 As shown, the embodiment of the present disclosure provides another collaborative control method for home appliances, and the collaborative control method for home appliances includes:

[0103] S401, the collaborative control device obtains target data features of control reference data.

[0104] S402, the collaborative control device inputs the target data features into the long short-term memory model, and uses the long short-term memory model to predict the user's intention information.

[0105] Here, the LSTM model is a task context inference model based on the LSTM network. It makes full use of the LSTM network's ability to process time series data and places the control task of home appliances in the context of related historical tasks. By capturing the time series characteristics of user behavior and environmental changes, it can more accurately infer users' potential needs and future behavior trends, providing more forward-looking guidance for the collaborative control of home appliances.

[0106] Specifically, the LSTM model contains an input gate, a forget gate, and an output gate. The target data feature is used as the input sequence x t , where t represents the time step, first calculate the value of the input gate i by the following formula t :i t =σ(W xi x t +W hi h t-1 +b i ), in the above formula, σ is the sigmoid function, W xi and W hi is the weight matrix, b i is the bias term, h t-1 is the hidden state at the previous time step.

[0107] The value of the forget gate f is calculated by the following formula t :f t =σ(W xf x t +W hf h t-1 +b f ), in the above formula, σ is the sigmoid function, W xf and W hf is the weight matrix, b f is the bias term, h t-1 is the hidden state at the previous time step.

[0108] The cell state c is calculated by the following formula t :

[0109]

[0110] In the above formula, ⊙ represents element-wise multiplication, W xc and W hc is the weight matrix, b c is the bias term, h t-1 is the hidden state at the previous time step.

[0111] The value of the output gate o is calculated by the following formula t and the hidden state h t :

[0112] o t =σ(W xo x t +W ho h t-1 +b o ),

[0113] h t =o t ⊙tanh(c t ).

[0114] In the above formula, ⊙ represents element-wise multiplication, W xo and W ho is the weight matrix, b o is the bias term.

[0115] After getting the hidden state h t Afterwards, based on the hidden state h t Determine the user's intent information.

[0116] In the disclosed embodiment, the attention degree of the long short-term memory model to different time steps is dynamically adjusted by the attention mechanism. Here, the attention weight can reflect the attention degree of the long short-term memory model to the time step. The attention weight a t It can be calculated by the following formula:

[0117] e t =v T tanh(W h h t +b h ), where v T , W h and b h are learnable parameters.

[0118] The final output of the long short-term memory model is h att ,h att Calculated by the following formula:

[0119]

[0120] S403, the collaborative control device generates an initial collaborative control strategy based on the intention information and the control reference data.

[0121] S404, the collaborative control device obtains an evaluation index of the initial collaborative control strategy, and determines a target collaborative control strategy based on the initial collaborative control strategy and its evaluation index.

[0122] S405, the collaborative control device controls the collaborative operation of multiple home appliances based on the target collaborative control strategy.

[0123] In some embodiments, an evaluation indicator of an initial collaborative control strategy is obtained, and a target collaborative control strategy is determined based on the initial collaborative control strategy and its evaluation indicator, including: iteratively executing a control strategy optimization process until an evaluation indicator that reaches a maximum value is determined to be searched, wherein the control strategy optimization process includes: obtaining an evaluation indicator of the initial collaborative control strategy, and determining whether an evaluation indicator that reaches a maximum value is searched; when it is determined that an evaluation indicator that reaches a maximum value is not searched, adjusting a strategy parameter of the initial collaborative control strategy; when it is determined that an evaluation indicator that reaches a maximum value is searched, determining the initial collaborative control strategy corresponding to the evaluation indicator that reaches the maximum value as the target collaborative control strategy.

[0124] Combination Figure 5 As shown, the embodiment of the present disclosure provides another collaborative control method for home appliances, and the collaborative control method for home appliances includes:

[0125] S501, the collaborative control device obtains target data features of control reference data.

[0126] S502, the collaborative control device predicts the user's intention information based on the target data characteristics, and generates an initial collaborative control strategy based on the intention information and control reference data.

[0127] S503, the collaborative control device obtains evaluation indicators of the initial collaborative control strategy.

[0128] Optionally, the evaluation indicators of the initial collaborative control strategy include a user comfort indicator, an energy consumption indicator, and a device response speed indicator.

[0129] In the embodiment of the present disclosure, the environmental parameters that can be achieved by the initial collaborative control strategy can be determined, and the user comfort index of the initial collaborative control strategy can be determined according to the environmental parameters.

[0130] In the disclosed embodiment, the initial collaborative control strategy involves multiple home appliances. The information of the initial collaborative control strategy includes the power and working time required for each home appliance when running according to the initial collaborative control strategy. Therefore, the power consumption required for all home appliances involved in the initial collaborative control strategy when running according to the initial collaborative control strategy can be determined based on the various home appliances involved in the initial collaborative control strategy and their corresponding power and working time, and the energy consumption index can be determined based on the power consumption.

[0131] In the disclosed embodiment, the initial collaborative control strategy involves multiple home appliances. The information of the initial collaborative control strategy includes the response time required for each home appliance when running according to the initial collaborative control strategy, and the maximum response time of all home appliances is determined, and the maximum response time is used as the device response speed indicator of the initial collaborative control strategy.

[0132] Optionally, the evaluation index of the initial collaborative control strategy may be any one of a user comfort index, an energy consumption index, and a device response speed index.

[0133] Optionally, the evaluation index of the initial collaborative control strategy may be a fusion value of multiple indexes including a user comfort index, an energy consumption index, and a device response speed index.

[0134] In some embodiments, the evaluation index of the initial collaborative control strategy may be the sum or average of a user comfort index, an energy consumption index, and a device response speed index.

[0135] In some embodiments, corresponding weights can be configured for the user comfort index, energy consumption index, and device response speed index, and the user comfort index, energy consumption index, and device response speed index configuration of the initial collaborative control strategy and their corresponding weights are weighted summed to obtain the evaluation index of the initial collaborative control strategy. Specifically, the evaluation index can be calculated by the following formula:

[0136] F(S)=w1×U(S)+w2×E(S)+w3×R(S).

[0137] In the above formula, U(S) represents the user comfort index, E(S) represents the energy consumption index, R(S) represents the device response speed index, w1 represents the weight of the user comfort index, w2 represents the weight of the energy consumption index, and w3 represents the weight of the device response speed index.

[0138] In some embodiments, the higher the user comfort index, the higher the comfort brought to the user by the initial collaborative control strategy; the higher the energy consumption index, the higher the energy consumption required by the initial collaborative control strategy; the higher the device response speed index, the faster the device response speed required by the initial collaborative control strategy. The weights of the user comfort index, the energy consumption index, and the device response speed index are determined according to the duration and urgency level of the task corresponding to the initial collaborative control strategy. The weight of the user comfort index is negatively correlated with both the duration and the urgency level; the weight of the energy consumption index is positively correlated with the duration, and the weight of the energy consumption index is negatively correlated with the urgency level; the weight of the device response speed index is positively correlated with the duration, and the weight of the device response speed index is negatively correlated with the urgency level.

[0139] In some embodiments, the first weights of the user comfort index, energy consumption index, and device response speed index are determined according to the duration of the task corresponding to the initial collaborative control strategy, and the second weights of the user comfort index, energy consumption index, and device response speed index are determined according to the urgency level of the task corresponding to the initial collaborative control strategy. The average of the first weight and the second weight of the user comfort index is used as the final weight of the user comfort index; the average of the first weight and the second weight of the energy consumption index is used as the final weight of the energy consumption index; the average of the first weight and the second weight of the device response speed index is used as the final weight of the device response speed index.

[0140] S504, the collaborative control device determines whether an evaluation index that reaches a maximum value is found.

[0141] In the embodiment of the present disclosure, when it is determined that the evaluation index reaching the maximum value is not searched, S505 is executed; when it is determined that the evaluation index reaching the maximum value is searched, S506 is executed.

[0142] S505: The collaborative control device adjusts the strategy parameters of the initial collaborative control strategy.

[0143] In the embodiment of the present disclosure, after S505 , the process returns to execute S503 .

[0144] S506: The collaborative control device determines the initial collaborative control strategy corresponding to the evaluation index that reaches the maximum value as the target collaborative control strategy.

[0145] In the embodiment of the present disclosure, after S506 , S507 is executed.

[0146] S507, the collaborative control device controls the collaborative operation of multiple home appliances based on the target collaborative control strategy.

[0147] Combination Figure 6 As shown, an embodiment of the present disclosure provides a collaborative control device 600 for home appliances, and the collaborative control device 600 includes a feature acquisition module 601, a strategy generation module 602, a strategy optimization module 603 and a device control module 604.

[0148] The feature acquisition module 601 is configured to acquire target data features of control reference data, where the control reference data includes at least one or more of the following data types: user behavior data, environmental data, and operating status data of multiple home appliances.

[0149] The strategy generation module 602 is configured to predict the user's intention information based on the target data features, and generate an initial collaborative control strategy based on the intention information and the control reference data.

[0150] The strategy optimization module 603 is configured to obtain the evaluation index of the initial collaborative control strategy, and determine the target collaborative control strategy based on the initial collaborative control strategy and its evaluation index.

[0151] The device control module 604 is configured to control the coordinated operation of multiple home appliances based on the target coordinated control strategy.

[0152] The collaborative control device for home appliances provided by the embodiment of the present disclosure can accurately predict the user's intention information through control reference data of multiple dimensions, and then generate an initial collaborative control strategy that meets the user's wishes based on the intention information and the control reference data. Then, further optimization is performed based on the evaluation index to obtain the target collaborative control strategy. The collaborative operation of multiple home appliances according to the target collaborative control strategy can make the environment created by the home appliances more in line with the user's actual wishes and current environmental conditions.

[0153] In some embodiments, the feature acquisition module 601 is configured to: acquire control reference data; extract initial data features from the control reference data; and enhance the initial data features using a preset regression algorithm and variational random features to obtain target data features.

[0154] In some embodiments, the preset regression algorithm is kernel ridge regression, and the kernel function used by kernel ridge regression is composed of an exponential decay kernel and a cosine kernel. The exponential decay kernel is used to capture local characteristics in the data, and the cosine kernel is used to capture periodicity or rotational invariance in the data.

[0155] In some embodiments, the expression of the evidence lower bound of the variational random feature consists of an expectation term, a KL divergence, and a variational free energy term. The expectation term is used to measure the predictive ability of the observed data, the KL divergence is used to measure the degree of difference between the variational distribution and the prior distribution, and the variational free energy term is used to improve the quality of the variational posterior distribution.

[0156] In some embodiments, the feature acquisition module 601 is configured to:

[0157] The initial data features are enhanced using the preset regression algorithm and variational random features to obtain intermediate data features;

[0158] The conditional normalization flow is used to diversify the intermediate data features to obtain the target data features.

[0159] In some embodiments, the strategy generation module 602 is configured to: input the target data features into the long short-term memory model, and use the long short-term memory model to predict the user's intention information, wherein the long short-term memory model's attention level to different time steps is dynamically adjusted by the attention mechanism.

[0160] In some embodiments, the strategy optimization module 603 is configured to iteratively execute the control strategy optimization process until it is determined that the evaluation index that reaches the maximum value is searched, wherein the control strategy optimization process includes:

[0161] Obtaining the evaluation index of the initial collaborative control strategy, and determining whether the evaluation index reaching the maximum value is searched;

[0162] When it is determined that the evaluation index that reaches the maximum value has not been searched, the strategy parameters of the initial collaborative control strategy are adjusted;

[0163] When it is determined that the evaluation index that has reached the maximum value is searched, the initial collaborative control strategy corresponding to the evaluation index that has reached the maximum value is determined as the target collaborative control strategy.

[0164] In some embodiments, the evaluation indicators include: user comfort indicators, energy consumption indicators, and device response speed indicators.

[0165] Combination Figure 7 As shown, the embodiment of the present disclosure provides another collaborative control device 700 for home appliances, and the collaborative control device 700 for home appliances includes a processor (processor) 701 and a memory (memory) 702. Optionally, the collaborative control device 700 for home appliances may also include a communication interface (Communication Interface) 703 and a bus 704. Among them, the processor 701, the communication interface 703, and the memory 702 can communicate with each other through the bus 704. The communication interface 703 can be used for information transmission. The processor 701 can call the logic instructions in the memory 702 to execute the collaborative control method for home appliances of the above embodiment.

[0166] In addition, the logic instructions in the memory 702 described above may be implemented in the form of software functional units and when sold or used as independent products, may be stored in a computer-readable storage medium.

[0167] The memory 702 is a computer-readable storage medium that can be used to store software programs and computer executable programs, such as program instructions / modules corresponding to the method in the embodiment of the present disclosure. The processor 701 executes the functional application and data processing by running the program instructions / modules stored in the memory 702, that is, the collaborative control method for home appliances in the above embodiment is implemented.

[0168] The memory 702 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function; the data storage area may store data created according to the use of the terminal device, etc. In addition, the memory 702 may include a high-speed random access memory and may also include a non-volatile memory.

[0169] An embodiment of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured to execute the above-mentioned collaborative control method for home appliances.

[0170] The technical solution of the embodiment of the present disclosure can be embodied in the form of a software product, which is stored in a storage medium and includes one or more instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the embodiment of the present disclosure. The aforementioned storage medium may be a non-transient storage medium, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, and other media that can store program codes.

[0171] The above description and the accompanying drawings fully illustrate the embodiments of the present disclosure so that those skilled in the art can practice them. Other embodiments may include structural, logical, electrical, process and other changes. The embodiments represent only possible changes. Unless explicitly required, separate components and functions are optional, and the order of operation may vary. The parts and features of some embodiments may be included in or replace the parts and features of other embodiments. Moreover, the words used in this application are only used to describe the embodiments and are not used to limit the claims. As used in the description of the embodiments and the claims, unless the context clearly indicates, the singular forms of "a", "an" and "the" are intended to include plural forms as well. Similarly, the term "and / or" as used in this application refers to any and all possible combinations of listings containing one or more associated ones. In addition, when used in the present application, the term "comprise" and its variants "comprises" and / or comprising refer to the presence of stated features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or groups thereof. In the absence of further restrictions, the elements defined by the sentence "comprising a ..." do not exclude the presence of other identical elements in the process, method or device comprising the elements. In this article, each embodiment may focus on the differences from other embodiments, and the same and similar parts between the various embodiments may refer to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method part disclosed in the embodiments, then the relevant parts can refer to the description of the method part.

[0172] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software may depend on the specific application and design constraints of the technical solution. The technicians may use different methods for each specific application to implement the described functions, but such implementations should not be considered to exceed the scope of the embodiments of the present disclosure. The technicians may clearly understand that, for the convenience and simplicity of description, the specific working processes of the systems, devices and units described above may refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.

[0173] In the embodiments disclosed herein, the disclosed methods and products (including but not limited to devices, equipment, etc.) can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units can be only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between each other shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms. The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to implement this embodiment. In addition, each functional unit in the embodiment of the present disclosure may be integrated in a processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit.

[0174] The flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to the embodiment 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 the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. 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, which can depend on the functions involved. In the description corresponding to the flowchart and the block diagram in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in a different order from the order disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.

Claims

1. A collaborative control method for home appliances, characterized in that: include: Acquire target data features of control reference data, where the control reference data includes at least one or more of the following data types: user behavior data, environmental data, and operating status data of a plurality of home appliances; Predict the user's intention information based on the target data features, and generate an initial collaborative control strategy based on the intention information and control reference data; Obtaining evaluation indicators of the initial collaborative control strategy, and determining a target collaborative control strategy based on the initial collaborative control strategy and its evaluation indicators; Control the collaborative operation of multiple home devices based on target collaborative control strategy.

2. The collaborative control method for home appliances according to claim 1, characterized in that: Obtain target data characteristics for control reference data, including: Obtain control reference data; Extracting initial data features from control reference data; The preset regression algorithm and variational random features are used to enhance the initial data features to obtain the target data features.

3. The collaborative control method for household appliances according to claim 2, characterized in that: The default regression algorithm is kernel ridge regression. The kernel function used by kernel ridge regression consists of an exponential decay kernel and a cosine kernel. The exponential decay kernel is used to capture the local characteristics of the data, and the cosine kernel is used to capture the periodicity or rotational invariance of the data. And / or, the expression of the evidence lower bound of the variational random feature consists of an expectation term, a KL divergence, and a variational free energy term, wherein the expectation term is used to measure the predictive ability of the observed data, the KL divergence is used to measure the degree of difference between the variational distribution and the prior distribution, and the variational free energy term is used to improve the quality of the variational posterior distribution.

4. The collaborative control method for home appliances according to claim 2, characterized in that: The initial data features are enhanced using the preset regression algorithm and variational random features to obtain the target data features, including: The initial data features are enhanced using the preset regression algorithm and variational random features to obtain intermediate data features; The conditional normalization flow is used to diversify the intermediate data features to obtain the target data features.

5. The collaborative control method for household appliances according to any one of claims 1 to 4, characterized in that: Predict user intent information based on target data features, including: The target data features are input into the long short-term memory model, and the long short-term memory model is used to predict the user's intention information. The degree of attention of the long short-term memory model to different time steps is dynamically adjusted by the attention mechanism.

6. The collaborative control method for household appliances according to any one of claims 1 to 4, characterized in that: Obtain the evaluation index of the initial collaborative control strategy, and determine the target collaborative control strategy based on the initial collaborative control strategy and its evaluation index, including: The control strategy optimization process is iterated until the evaluation index that reaches the maximum value is determined. The control strategy optimization process includes: Obtaining the evaluation index of the initial collaborative control strategy, and determining whether the evaluation index reaching the maximum value is searched; When it is determined that the evaluation index that reaches the maximum value has not been searched, the strategy parameters of the initial collaborative control strategy are adjusted; When it is determined that the evaluation index that has reached the maximum value is searched, the initial collaborative control strategy corresponding to the evaluation index that has reached the maximum value is determined as the target collaborative control strategy.

7. The collaborative control method for household appliances according to any one of claims 1 to 4, characterized in that: Evaluation metrics include: User comfort indicators, energy consumption indicators and equipment response speed indicators.

8. A collaborative control device for household appliances, characterized in that: include: a feature acquisition module configured to acquire target data features of control reference data, wherein the control reference data includes at least one or more of the following data types: user behavior data, environmental data, and operating status data of a plurality of home appliances; A strategy generation module is configured to predict the user's intention information based on the target data characteristics, and generate an initial collaborative control strategy based on the intention information and the control reference data; A strategy optimization module is configured to obtain an evaluation index of an initial collaborative control strategy and determine a target collaborative control strategy based on the initial collaborative control strategy and its evaluation index; The device control module is configured to control the coordinated operation of multiple home appliances based on a target collaborative control strategy.

9. A cooperative control device for household appliances, comprising a processor and a memory storing program instructions, characterized in that: The processor is configured to execute the collaborative control method for home appliances as described in any one of claims 1 to 7 when running program instructions.

10. A storage medium, characterized in that: The storage medium stores computer program instructions, and when the computer program instructions are executed by the processor, the collaborative control method for home appliances as described in any one of claims 1 to 7 is executed.

Images