Refrigerator energy consumption abnormity early warning method and device, refrigerator and computer readable storage medium

Abstract

The invention relates to the technical field of intelligent household appliances, and discloses a refrigerator energy consumption abnormity early warning method, which comprises the following steps: acquiring historical energy consumption data and historical environment data of a refrigerator and a corresponding energy consumption abnormity judgment result; the historical environment data comprises historical refrigerator internal and external environment data and historical user behavior data; according to the acquired data, constructing a random forest model and a cuspidal point mutation model; inputting the current energy consumption data and the current environment data of the refrigerator into the random forest model and the cuspidal point mutation model respectively to obtain a prediction result corresponding to each model; and determining the energy consumption condition of the refrigerator according to the prediction result corresponding to each model. The method not only can realize energy consumption prediction based on the random forest model, but also can perform early warning on the refrigerator energy consumption abnormity in combination with the random forest model and the cuspidal point mutation model. The invention further discloses a device for refrigerator energy consumption abnormity early warning, the refrigerator and a computer readable storage medium.

Description

Technical Field

[0001] The present application relates to the technical field of smart home appliances, for example, to a method and device for warning abnormal energy consumption of a refrigerator, a refrigerator, and a computer-readable storage medium. Background Art

[0002] With the increasing awareness of energy conservation and environmental protection, refrigerator energy consumption anomaly detection technology has become increasingly important. Traditional energy consumption anomaly detection technology often has problems such as low prediction accuracy and inability to provide real-time energy consumption warning.

[0003] The related technology discloses a method for analyzing and rating electric energy efficiency based on random forests, including: 1) establishing an energy efficiency index system: selecting electric energy efficiency indexes of concern to electric power users according to the national electric power quality standard manual; 2) establishing energy efficiency grade standards: based on the national electric power quality standards and environmental protection standards, for the selected electric energy indexes, each electric energy efficiency index is divided into several energy efficiency grades according to the energy efficiency level of the electric power user; 3) establishing a random forest classifier: generating a theoretical sample set in each energy efficiency grade interval according to the principle of random distribution within the energy efficiency grade range, dividing the theoretical sample set into a training set and a test set according to a set ratio, training and verifying the random forest classifier, and the random forest classifier outputs the energy efficiency grade corresponding to each energy efficiency index; 4) inputting the actual test set data into the trained random forest classifier to directly obtain the corresponding energy efficiency grade, and the electric power user can analyze the energy efficiency grade corresponding to each energy efficiency index and formulate a local optimal plan for energy-saving transformation.

[0004] In the process of implementing the embodiments of the present disclosure, it is found that there are at least the following problems in the related art:

[0005] In the related art, only the evaluation of energy consumption level can be achieved, but the prediction of energy consumption situation, especially the early warning of abnormal energy consumption, is not achieved.

[0006] 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 application, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0007] 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.

[0008] The embodiments of the present disclosure provide a method and device for warning of abnormal energy consumption of a refrigerator, a refrigerator, and a computer-readable storage medium, so as to realize refrigerator energy consumption prediction and be able to warn of abnormal energy consumption.

[0009] In some embodiments, the method includes: obtaining historical energy consumption data, historical environmental data and corresponding energy consumption abnormality judgment results of the refrigerator; the historical environmental data includes historical internal and external environmental data of the refrigerator and historical user behavior data; based on the acquired data, constructing a random forest model and a cusp mutation model; inputting the current energy consumption data and current environmental data of the refrigerator into the random forest model and the cusp mutation model to obtain the corresponding prediction results of each model; and determining the energy consumption of the refrigerator based on the corresponding prediction results of each model.

[0010] In some embodiments, the device includes: a processor and a memory storing program instructions, and the processor is configured to execute the aforementioned method for warning of abnormal energy consumption of a refrigerator when running the program instructions.

[0011] In some embodiments, the refrigerator includes: a refrigerator body; and the device for warning of abnormal refrigerator energy consumption as described above, which is installed on the refrigerator body.

[0012] In some embodiments, the computer-readable storage medium stores program instructions, and when the program instructions are executed, the computer executes the aforementioned method for warning abnormal energy consumption of a refrigerator.

[0013] The method and device for warning abnormal energy consumption of a refrigerator, the refrigerator, and the computer-readable storage medium provided by the embodiments of the present disclosure can achieve the following technical effects:

[0014] In the disclosed embodiment, a random forest model and a cusp mutation model are constructed in combination with the historical data of the refrigerator. Then, the energy consumption of the current data of the refrigerator is predicted using the random forest model and the cusp mutation model. Among them, not only can energy consumption prediction be realized based on the random forest model, but also the abnormal energy consumption of the refrigerator can be warned in combination with the random forest model and the cusp mutation model.

[0015] The above general description and the following description are exemplary and explanatory only and are not intended to limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] 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:

[0017] Figure 1 is a schematic diagram of a method for warning abnormal energy consumption of a refrigerator provided by an embodiment of the present disclosure;

[0018] Figure 2 is a schematic diagram of another method for warning of abnormal energy consumption of a refrigerator provided by an embodiment of the present disclosure;

[0019] Figure 3 is a schematic diagram of a balance surface of a cusp catastrophe model provided by an embodiment of the present disclosure;

[0020] Figure 4 is a schematic diagram of another method for warning of abnormal energy consumption of a refrigerator provided by an embodiment of the present disclosure;

[0021] Figure 5 is a schematic diagram of another method for warning of abnormal energy consumption of a refrigerator provided by an embodiment of the present disclosure;

[0022] Figure 6 is a schematic diagram of a device for warning of abnormal energy consumption of a refrigerator provided by an embodiment of the present disclosure;

[0023] Figure 7 It is a schematic diagram of a refrigerator provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0024] 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.

[0025] 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 as to describe 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.

[0026] Unless otherwise stated, the term "plurality" means two or more.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] In the embodiment of the present disclosure, the refrigerator is a smart home appliance. Among them, smart home appliances refer to home appliances formed by introducing microprocessors, sensor technology, and network communication technology into home appliances, and have the characteristics of intelligent control, intelligent perception, and intelligent application. The operation process of smart home appliances often relies on the application and processing of modern technologies such as the Internet of Things, the Internet, and electronic chips. For example, smart home appliances can be connected to electronic devices to enable users to remotely control and manage smart home appliances.

[0031] Combination Figure 1 As shown, the embodiment of the present disclosure provides a method for warning abnormal energy consumption of a refrigerator, comprising:

[0032] S101, the processor obtains historical energy consumption data, historical environmental data and corresponding energy consumption abnormality judgment results of the refrigerator. The historical environmental data includes historical internal and external environment data of the refrigerator and historical user behavior data.

[0033] S102: The processor constructs a random forest model and a cusp mutation model according to the acquired data.

[0034] S103, the processor inputs the current energy consumption data and current environmental data of the refrigerator into the random forest model and the cusp mutation model respectively to obtain the prediction results corresponding to each model.

[0035] S104: The processor determines the energy consumption of the refrigerator according to the prediction results corresponding to each model.

[0036] Here, detection elements such as sensors are provided on the inner cavity and shell of the refrigerator to detect the environmental data of the refrigerator. The environmental data includes the environmental data inside and outside the refrigerator and the user behavior data. The environmental data inside the refrigerator includes the temperature of the refrigerator compartment, the relative humidity of the refrigerator compartment, the temperature of the freezer compartment, the relative humidity of the freezer compartment, etc., and the environmental data outside the refrigerator includes the external environmental temperature of the refrigerator and the external environmental relative humidity of the refrigerator (i.e., the temperature and relative humidity of the environment in which the refrigerator is located). User behavior data includes the number of times the refrigerator door is opened and closed, i.e., the duration of the door opening and closing. As an example, a door opening and closing detection switch and a counter are provided at the hinge of the refrigerator shell to detect the state of the refrigerator door and the duration of the door opening and closing. The abnormal energy consumption judgment result refers to whether the energy consumption corresponding to the data is abnormal, determined by an energy consumption expert based on the historical energy consumption data and historical environmental data of the refrigerator. That is, the abnormal energy consumption judgment result includes abnormal energy consumption or normal energy consumption. Among them, each piece of historical data of the refrigerator corresponds to a judgment result of whether the energy consumption is abnormal.

[0037] Here, the random forest model is an integrated learning method. Therefore, when constructing the random forest model, the historical energy consumption data, historical environmental data of the refrigerator and the corresponding energy consumption anomaly judgment results are required. Through a sufficient number of samples, the random forest model is constructed, so that the expert's judgment on energy consumption anomalies can be replaced by the random forest model. The mutation theory of the cusp mutation model describes the relationship between the control factor and the state factor in the dynamic system. The control factor is composed of input variables, and the state factor is composed of output variables. The factors affecting energy consumption mainly include the internal and external environmental data of the refrigerator and the user behavior data. Therefore, the internal and external environmental data of the refrigerator and the user behavior data are input variables, and the energy consumption data is the output variable. In this way, the cusp mutation model can determine whether there is a mutation in energy consumption through changes in environmental data.

[0038] Furthermore, the current energy consumption data and current environmental data of the refrigerator are input into the random forest model and the cusp mutation model respectively to obtain the prediction results corresponding to each model. Among them, the prediction results of the random forest model include two results: normal energy consumption and abnormal energy consumption. The prediction results of the cusp mutation model include stable and unstable (instability means that there is a trend of mutation in energy consumption). Combining the prediction results of the two models, energy consumption can be predicted, and early warning of energy consumption can be achieved, that is, early warning of energy consumption with a mutation trend. In addition, the combination of the two models improves the accuracy of the prediction, and the early warning helps users take timely measures to achieve energy saving.

[0039] The method for warning abnormal energy consumption of refrigerators provided by the embodiment of the present disclosure is adopted, and the historical data of the refrigerator is combined to construct a random forest model and a cusp mutation model. Then, the energy consumption of the current data of the refrigerator is predicted using the random forest model and the cusp mutation model. Among them, not only can energy consumption prediction be realized based on the random forest model, but also the abnormal energy consumption of the refrigerator can be warned in combination with the random forest model and the cusp mutation model.

[0040] Optionally, in step S101, the processor obtains historical energy consumption data, historical environmental data and corresponding abnormal energy consumption judgment results of the refrigerator, including:

[0041] The processor obtains the historical static energy consumption data, historical static environmental data and corresponding energy consumption abnormality judgment results of the refrigerator. And,

[0042] The processor obtains the historical dynamic energy consumption data and historical dynamic environmental data of the refrigerator.

[0043] Among them, the historical static energy consumption data, historical static environmental data and the corresponding energy consumption anomaly judgment results are historical data of fixed time; the historical dynamic energy consumption data and historical dynamic environmental data are historical data updated in real time based on the acquisition time series.

[0044] Here, in order to ensure the best prediction results of the model, the data of the cusp mutation model is updated in real time. Among them, real-time update refers to updating according to a set period or time. As an example, the data acquisition and update are performed every hour. More specifically, if the refrigerator data of several hours before the current moment of the refrigerator is obtained, the refrigerator data of several hours before the latest moment is obtained every hour. As an example, the current time is 10:00 am, and the refrigerator data of 168 hours before this moment is obtained. Then when the time is 11:00, the refrigerator data of 168 hours before 11:00 is obtained. In this way, the real-time nature of the construction of the cusp mutation model is guaranteed, especially when the historical data changes greatly, which helps to improve the accuracy of the prediction. In addition, because the random forest model is mainly used for abnormal judgment, the data required for model establishment can be static data. And the amount of static data is much greater than the amount of dynamic data. Optionally, the sliding time window method is used to obtain data. Set the time period, and obtain one side of the data in each time period. This method has a good processing ability for time series data and can capture the changing trend of time series. Auxiliary cusp catastrophe model better predicts energy consumption.

[0045] Optionally, in step S102, the processor constructs a random forest model according to the acquired data, including:

[0046] The processor establishes multiple decision tree models according to the historical static energy consumption data, historical static environmental data and corresponding energy consumption abnormality judgment results of the refrigerator.

[0047] The processor treats an ensemble of multiple decision tree models as a random forest model.

[0048] Here, the historical static energy consumption data and the historical static environmental data are used to form a sample set with the corresponding energy consumption anomaly judgment results, and a certain number of samples are extracted by sampling with replacement. Several features are randomly selected from the extracted samples. Based on the extracted samples and the selected features, a decision tree model is established. Repeat the above steps until the number of decision trees constructed reaches the set number. A collection of multiple (i.e., a set number) decision tree models is used as a random forest model. As an example, the sample set includes 10,000 data, and 8,000 data can be extracted from the sample library each time. Three features are randomly selected from the 8,000 data to construct a decision tree model. Repeat the above steps until the number of decision tree models constructed reaches 100. The collection of 100 constructed decision tree models is used as a random forest model. The data in the embodiments of the present disclosure are only examples and can be set based on specific circumstances.

[0049] Combination Figure 2 As shown, the embodiment of the present disclosure provides another method for warning abnormal energy consumption of a refrigerator, comprising:

[0050] S111, the processor obtains historical static energy consumption data, historical static environment data and corresponding abnormal energy consumption judgment results of the refrigerator, wherein the historical static energy consumption data, historical static environment data and corresponding abnormal energy consumption judgment results are historical data of a fixed time.

[0051] S121, the processor establishes multiple decision tree models according to the historical static energy consumption data, historical static environmental data and corresponding energy consumption abnormality judgment results of the refrigerator, and uses the set of multiple decision tree models as a random forest model. Then, S103 is executed.

[0052] S112, the processor obtains historical dynamic energy consumption data and historical dynamic environmental data of the refrigerator, wherein the historical dynamic energy consumption data and historical dynamic environmental data are historical data updated in real time based on the acquisition time series.

[0053] S122, the processor uses the historical dynamic environmental data of the refrigerator as input variables and the historical dynamic energy consumption data as output variables, and constructs a first linear function of the control factor and the input variable and a second linear function of the state factor and the output variable; wherein the control factor and the state factor constitute a cusp mutation model.

[0054] S123, the processor solves the estimated values ​​of the parameters in the first linear function and the second linear function by the maximum likelihood method to obtain the control factor.

[0055] S124, the processor obtains a determination formula composed of control factors to predict the energy consumption of the current environmental data of the refrigerator.

[0056] S103, the processor inputs the current energy consumption data and current environmental data of the refrigerator into the random forest model and the cusp mutation model respectively to obtain the prediction results corresponding to each model.

[0057] S104: The processor determines the energy consumption of the refrigerator according to the prediction results corresponding to each model.

[0058] Here, the cusp catastrophe model consists of two control factors α, β and a state factor z, and the canonical form of its potential function is:

[0059]

[0060] In the case of fixed control factors, the dynamic system always seeks a balanced state until it reaches the minimum or maximum value of the potential function. The dynamic system expression is used to describe the change of the state factor z of the system under the influence of control factors α and β with time t (the equilibrium equation of the cusp mutation model):

[0061]

[0062] Assume that the input variables of refrigerator environment data are {X1,X2,…,X n}, the energy consumption of the refrigerator is Y. i represents the i-th data in the environmental data, such as the temperature of the refrigerator. Since there are multiple factors affecting energy consumption, α and β are set as n-dimensional input variables {X1, X2, …, X n}, z is the linear transformation of the output variable Y, expressed as:

[0063]

[0064] In formula (3), the functions of α and β are the first linear functions, and the function of z is the second linear function. The stochastic differential equation is introduced to describe the distribution of z under the condition that α and β are fixed in the form of probability density function, which is expressed as:

[0065]

[0066] Parameters θ={w0,w1,a0,…,a n ,b1,…,b n} is estimated by the maximum likelihood method. Given N samples, the log-likelihood function of the parameter θ is as follows:

[0067]

[0068] Maximizing the log-likelihood function of the observed sample yields an estimate of the parameter θ. This leads to the linear function of the control factor, i.e., the function of α and β in formula (3).

[0069] Then, the determination formula composed of control factors can be obtained:

[0070] δ=27a 2 -4β 3 (6)

[0071] The above judgment formula (6) is a formula about the input variable, namely the refrigerator environment parameter. After the refrigerator environment parameter is input, the size of δ can be determined, and then it can be determined whether there is a sudden change trend in the refrigerator energy consumption.

[0072] In addition, it should be noted that the refrigerator data for constructing the cusp mutation model is dynamic historical data, so α and β are also functions based on dynamic historical data. In other words, after each data update, the parameter θ needs to be recalculated to obtain new α and β functions.

[0073] Optionally, in step S103, the processor inputs the current energy consumption data and the current environment data of the refrigerator into a random forest model to obtain a prediction result, including:

[0074] The processor inputs the current energy consumption data and the current environment data into all decision tree models constituting the random forest model to obtain corresponding decision results.

[0075] When the abnormal proportion in the decision result is greater than or equal to a preset proportion, the processor determines that the prediction result is abnormal.

[0076] When the proportion of abnormalities in the decision result is less than a preset ratio, the processor determines that the prediction result is normal.

[0077] Here, the random forest model is a collection of multiple decision tree models. Inputting the current energy consumption data and the current environment into each decision tree model can obtain a decision result. The proportion of abnormalities in all decision results is counted. If the proportion is greater than or equal to the preset proportion, the prediction result is determined to be abnormal, otherwise the prediction result is normal. As an example, the random forest model includes 100 decision tree models, and the preset proportion can be 80%. That is, when the proportion of abnormal results is greater than or equal to 80%, the prediction result of the random forest model is determined to be abnormal.

[0078] Optionally, at S103, the processor inputs the current energy consumption data and the current environment data of the refrigerator into the cusp catastrophe model to obtain a corresponding prediction result, including:

[0079] The processor inputs the current energy consumption data and current environmental data of the refrigerator into the determination formula and calculates the size of the determination formula result δ.

[0080] When δ<0, the processor determines that the prediction result is abnormal, that is, there is a mutation trend.

[0081] In the case of δ≥0, the processor determines that the prediction result is normal.

[0082] Combination Figure 3 As shown in the figure, the equilibrium surface of the cusp mutation model is composed of an upper lobe, a middle lobe, and a lower lobe. The upper and lower lobes correspond to the parts with stable energy consumption, and the middle lobe corresponds to the part with unstable energy consumption. The bifurcation set is the projection of the unstable part of energy consumption on α and β. If the control factors α and β change along trajectory A, the state factor z will mutate in the bifurcation set, jumping directly from the lower lobe of the equilibrium surface to the upper lobe without passing through the middle lobe; if the control factors α and β change along trajectory B, the state factor z will not mutate. Therefore, when α and β composed of energy consumption data are observed to enter the bifurcation area, an energy consumption warning is issued. Specifically, when δ < 0, the energy consumption of the refrigerator changes from a sharp increase trend to a mutation trend.

[0083] Combination Figure 4 As shown, the embodiment of the present disclosure provides another method for warning abnormal energy consumption of a refrigerator, comprising:

[0084] S101, the processor obtains historical energy consumption data, historical environmental data and corresponding energy consumption abnormality judgment results of the refrigerator. The historical environmental data includes historical internal and external environment data of the refrigerator and historical user behavior data.

[0085] S102: The processor constructs a random forest model and a cusp mutation model according to the acquired data.

[0086] S103, the processor inputs the current energy consumption data and current environmental data of the refrigerator into the random forest model and the cusp mutation model respectively to obtain the prediction results corresponding to each model.

[0087] S141, when the prediction result of the random forest model is abnormal, the processor determines that the energy consumption of the refrigerator is abnormal.

[0088] S142, when the prediction result of the random forest model is normal and the prediction result of the cusp mutation model is abnormal, the processor determines that there is an abnormal tendency in the energy consumption of the refrigerator and outputs energy consumption warning information.

[0089] S143: When the prediction results of the random forest model and the cusp mutation model are both normal, the processor determines that the energy consumption of the refrigerator is normal.

[0090] Here, the prediction results of the random forest model and the cusp mutation model are combined to output whether the energy consumption is abnormal and to give an early warning of energy consumption. The specific prediction results of energy consumption are shown in Table 1.

[0091] Table 1

[0092]

[0093] As shown in Table 2, when the prediction result of the random forest model is abnormal, no matter what the result of the cusp mutation model is, the final result is abnormal. When the prediction result of the random forest model is normal, if the prediction result of the cusp mutation model is abnormal (δ<0), it indicates that there is a tendency for energy consumption to mutate, and an early warning is issued for energy consumption. Otherwise, the final prediction result is normal.

[0094] Optionally, when it is determined that the refrigerator energy consumption has an abnormal tendency or is abnormal, the rule base is searched to determine data that affects the abnormal energy consumption or abnormal tendency of the refrigerator, and energy-saving suggestions are provided based on the influencing data.

[0095] Here, the rule base is stored in the refrigerator server, and the normal range of factors affecting the energy consumption of the refrigerator is stored in the rule base. The current refrigerator energy consumption data can be compared with the data in the rule base to determine the data affecting the energy consumption. Then, energy-saving suggestions are provided for the influencing data. As an example, if the number of refrigerator door openings and closings is abnormal, the user is reminded to reduce unnecessary door openings. In addition, if the refrigerator energy consumption continues to be abnormal within a period of time, a refrigerator maintenance message is output. The period of time can be 12 to 24 hours.

[0096] Combination Figure 5 As shown, the embodiment of the present disclosure provides another method for warning abnormal energy consumption of a refrigerator, comprising:

[0097] S101, the processor obtains historical energy consumption data, historical environmental data and corresponding energy consumption abnormality judgment results of the refrigerator. The historical environmental data includes historical internal and external environment data of the refrigerator and historical user behavior data.

[0098] S205, the processor pre-processes the historical energy consumption data, the historical environment data and the corresponding energy consumption abnormality judgment results to convert the same type of data into the same order of magnitude.

[0099] S102: The processor constructs a random forest model and a cusp mutation model according to the acquired data.

[0100] S103, the processor inputs the current energy consumption data and current environmental data of the refrigerator into the random forest model and the cusp mutation model respectively to obtain the prediction results corresponding to each model.

[0101] S104: The processor determines the energy consumption of the refrigerator according to the prediction results corresponding to each model.

[0102] Here, the Z-Score standardization technology is used in preprocessing to convert data of different magnitudes into data of the same magnitude. Then, the model is built based on the preprocessed data. The preprocessing process is as follows:

[0103]

[0104] Among them, x* is the data after processing, x is the data before processing, is the mean of the data, and σ is the variance. In this way, not only can the comparability between data be guaranteed, but also the robustness and learning effect of the model can be improved. Table 2 gives the preprocessed data samples.

[0105] Table 2

[0106]

[0107] Combination Figure 6As shown, the embodiment of the present disclosure provides a device 200 for warning of abnormal energy consumption of a refrigerator, including a processor 100 and a memory 101. Optionally, the device may also include a communication interface 102 and a bus 103. The processor 100, the communication interface 102, and the memory 101 may communicate with each other through the bus 103. The communication interface 102 may be used for information transmission. The processor 100 may call the logic instructions in the memory 101 to execute the method for warning of abnormal energy consumption of a refrigerator of the above embodiment.

[0108] In addition, the logic instructions in the memory 101 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.

[0109] The memory 101 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 100 executes the function application and data processing by running the program instructions / modules stored in the memory 101, that is, the method for abnormal warning of refrigerator energy consumption in the above embodiment is implemented.

[0110] The memory 101 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 101 may include a high-speed random access memory and may also include a non-volatile memory.

[0111] Combination Figure 7 As shown, the embodiment of the present disclosure provides a refrigerator 300, including: a product body, and the above-mentioned device 200 for warning of abnormal energy consumption of the refrigerator. The device 200 for warning of abnormal energy consumption of the refrigerator is installed in the refrigerator body. The installation relationship described here is not limited to placement inside the product, but also includes installation connections with other components of the product, including but not limited to physical connections, electrical connections or signal transmission connections. It can be understood by those skilled in the art that the device 200 for warning of abnormal energy consumption of the refrigerator can be adapted to a feasible product body, thereby realizing other feasible embodiments.

[0112] 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 method for warning of abnormal energy consumption of a refrigerator.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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 method for warning abnormal energy consumption of a refrigerator, characterized in that: include: Obtain the refrigerator's historical energy consumption data, historical environmental data, and corresponding energy consumption anomaly judgment results; the historical environmental data includes historical refrigerator internal and external environmental data and historical user behavior data; Based on the acquired data, a random forest model and a cusp mutation model are constructed; The current energy consumption data and current environmental data of the refrigerator are input into the random forest model and the cusp mutation model respectively to obtain the prediction results corresponding to each model; Determine the energy consumption of the refrigerator based on the prediction results corresponding to each model.

2. The method according to claim 1, characterized in that Obtaining the refrigerator's historical energy consumption data, historical environmental data, and corresponding energy consumption anomaly judgment results includes: Obtaining historical static energy consumption data, historical static environmental data, and corresponding energy consumption abnormality judgment results of the refrigerator; and, Obtain the historical dynamic energy consumption data and historical dynamic environmental data of the refrigerator; Among them, the historical static energy consumption data, historical static environmental data and the corresponding energy consumption anomaly judgment results are historical data of fixed time; the historical dynamic energy consumption data and historical dynamic environmental data are historical data updated in real time based on the acquisition time series.

3. The method according to claim 2, characterized in that Based on the acquired data, a random forest model is constructed, including: Establish multiple decision tree models based on the refrigerator's historical static energy consumption data, historical static environmental data, and corresponding energy consumption anomaly judgment results; An ensemble of multiple decision tree models is used as a random forest model.

4. The method according to claim 3, characterized in that The current energy consumption data of the refrigerator and the current environmental data are input into the random forest model to obtain prediction results, including: Input the current energy consumption data and the current environmental data into all decision tree models constituting the random forest model to obtain the corresponding decision results; When the abnormal proportion in the decision result is greater than or equal to the preset proportion, the prediction result is determined to be abnormal; or, When the proportion of abnormalities in the decision results is less than the preset proportion, the prediction result is determined to be normal.

5. The method according to claim 2, characterized in that: Based on the acquired data, a cusp mutation model is constructed, including: The historical dynamic environmental data of the refrigerator is used as the input variable and the historical dynamic energy consumption data is used as the output variable, and the first linear function of the control factor and the input variable and the second linear function of the state factor and the output variable are constructed; wherein the control factor and the state factor constitute a cusp catastrophe model; Solving the estimated values ​​of the parameters in the first linear function and the second linear function by the maximum likelihood method to obtain the first linear function of the control factor; The determination formula of the cusp catastrophe model composed of control factors is obtained to predict the energy consumption of the current environmental data of the refrigerator.

6. The method according to claim 1, characterized in that According to the prediction results of each model, the energy consumption of the refrigerator is determined, including: When the prediction result of the random forest model is abnormal, it is determined that the energy consumption of the refrigerator is abnormal; When the prediction result of the random forest model is normal and the prediction result of the cusp mutation model is abnormal, it is determined that the energy consumption of the refrigerator has an abnormal tendency, and energy consumption warning information is output; When the prediction results of the random forest model and the cusp mutation model are both normal, it is determined that the energy consumption of the refrigerator is normal.

7. The method according to any one of claims 1 to 6, characterized in that: Based on the acquired data, before constructing the random forest model and the cusp mutation model, it also includes: Pre-process historical energy consumption data, historical environmental data, and corresponding energy consumption anomaly judgment results to convert the same type of data into the same magnitude.

8. A device for warning abnormal energy consumption of a refrigerator, comprising a processor and a memory storing program instructions, characterized in that: The processor is configured to execute the method for warning abnormal energy consumption of a refrigerator as described in any one of claims 1 to 7 when running the program instructions.

9. A refrigerator, characterized in that: include: Refrigerator body; The device for warning of abnormal energy consumption of a refrigerator as described in claim 8 is installed on the refrigerator body.

10. A computer-readable storage medium storing program instructions, characterized in that: When the program instructions are executed, the computer is used to execute the method for warning of abnormal energy consumption of a refrigerator as described in any one of claims 1 to 7.

Images