Refrigerator control method, device and equipment and storage medium
Through the deep learning model combined with the self-attention mechanism, the low-power operation strategy of the refrigerator is adaptively adjusted, which solves the problem of insufficient intelligence of the refrigerator and achieves flexible adjustment of energy consumption and improved operation efficiency.
Patent Information
- Application Number
- CN202411200998.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-29
- Publication Date
- 2024-11-08
AI Technical Summary
The existing refrigerator energy consumption adjustment method cannot meet the needs of different users and scenarios, and the intelligence is insufficient, resulting in insufficient flexibility in energy consumption adjustment.
The refrigerator energy consumption big data model based on deep learning is adopted, combined with the self-attention mechanism, obtain refrigerator status and user habit information, and adaptively adjust the refrigerator's low-power operation strategy, including target temperature, compressor operation frequency and defrost strategy.
Significantly reduce refrigerator energy consumption, improve operating efficiency, extend service life, enhance user experience, and reduce unnecessary energy waste by dynamically adjusting temperature and compressor operating frequency.
Smart Images

Figure CN118912803A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of smart device technology, for example, to methods, devices, equipment and storage media for refrigerator control. Background Art
[0002] A refrigerator is a refrigeration device that keeps a constant low temperature. It is also a civilian product that keeps food or other items at a constant low temperature. With the development of smart technology, refrigerators have also added many functions, and similarly, requirements have been put forward for the energy consumption of refrigerators.
[0003] In the related art, refrigerators can use energy-saving mode and frequency conversion technology to reduce the energy consumption of refrigerators. However, some of these methods reduce the energy consumption of refrigerators according to pre-set strategies; some adjust the energy consumption of refrigerators according to the temperature inside and outside the refrigerator, food information and other parameters obtained by the detection device configured in the refrigerator. However, the users of refrigerators are different, and the application scenarios of refrigerators are also different. These refrigerator energy consumption adjustment methods cannot make adaptive energy consumption adjustments, and the intelligence of refrigerators needs to be improved.
[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 application, 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 method, device, equipment and storage medium for controlling a refrigerator to solve the technical problem that the intelligence of a refrigerator needs to be improved. An energy consumption measuring device is configured in the refrigerator.
[0007] In some embodiments, the method comprises:
[0008] Acquire the current state information and operation information of the refrigerator, and the usage habit information of the user corresponding to the current refrigerator, wherein the operation information includes: the energy consumption information of the current refrigerator obtained by the energy consumption measuring device;
[0009] According to the status information, operation information, and usage habit information, based on the refrigerator energy consumption big data model, the current low-power operation strategy of the current refrigerator is obtained, wherein the refrigerator energy consumption big data model is constructed based on deep learning;
[0010] According to the current low power operation strategy, the current refrigerator is controlled to operate.
[0011] In this way, based on the refrigerator energy consumption big data model, the refrigerator energy consumption can be adaptively adjusted according to the refrigerator status information, operation information, and user usage habit information, thereby improving the flexibility and intelligence of the refrigerator.
[0012] In some embodiments, it also includes:
[0013] Obtain status sample information and operation sample information of refrigerators of different models, as well as usage habit sample information of different users;
[0014] Based on the deep learning model architecture that introduces the self-attention mechanism, minimizing the energy consumption of the refrigerator is taken as the main objective function. Training and learning are carried out according to the state sample information, operation sample information and usage habit sample information to obtain the refrigerator energy consumption big data model.
[0015] In this way, based on the deep learning model architecture that introduces the self-attention mechanism, the refrigerator energy consumption big data model is learned and trained. It is obtained based on the core technology of artificial intelligence (AI). It is not only accurate and reliable, but also the introduction of the self-attention mechanism can greatly improve the efficiency and effect of data processing.
[0016] In some embodiments, it also includes:
[0017] Adjust the refrigerator energy consumption big data model according to the state information and operation information after the refrigerator runs the current low-power operation strategy, the user's usage habit information, and the corresponding current low-power operation strategy;
[0018] Obtain the energy consumption information of the current refrigerator after running the current low-power operation strategy, as well as the current user's evaluation information, and optimize the refrigerator energy consumption big data model.
[0019] It can be seen that the refrigerator energy consumption big data model can be adjusted and optimized in time, which further improves the reliability of the refrigerator energy consumption big data model output, and then improves the reliability of refrigerator energy-saving control.
[0020] In some embodiments, obtaining the current low power consumption operation strategy of the current refrigerator includes:
[0021] According to the current state information and current operation information of the current refrigerator, based on the refrigerator energy consumption big data model, the current target operating temperature of the current refrigerator is generated, wherein the current state operation information includes: the current internal temperature, the current external temperature, and the current stored food information; and / or,
[0022] According to the usage habit information of the user corresponding to the current refrigerator, based on the refrigerator energy consumption big data model, predict the peak usage time period of the current refrigerator; and / or,
[0023] According to the current state information, current operation information and usage habit information, based on the refrigerator energy consumption big data model, the current compressor operation frequency of the current refrigerator is obtained; and / or,
[0024] According to the current state information and current operation information of the current refrigerator, based on the refrigerator energy consumption big data model, the defrost strategy of the current refrigerator is obtained, wherein the current operation information includes the current frosting state information obtained by the frost detection device in the current refrigerator.
[0025] Based on the refrigerator energy consumption big data model, one or more specific low-power operation plans can be obtained, and the refrigerator can be energy-efficiently controlled from multiple aspects such as target temperature, compressor operating frequency, and defrost strategy, further improving the effect of refrigerator energy-saving control.
[0026] In some embodiments, controlling the current refrigerator to operate includes:
[0027] If the current time is not in the peak usage period, the current target operating temperature is sent to the refrigerator for operation;
[0028] When the current moment is within the peak usage time period, the current target operating temperature is adjusted to the first target operating temperature according to the current internal temperature and the current external temperature, and the first target operating temperature is sent to the refrigerator for operation.
[0029] It can be seen that during peak usage periods, the target operating temperature of the refrigerator will be appropriately adjusted to reduce the temperature difference inside and outside the refrigerator, thereby reducing the temperature interaction inside and outside the refrigerator and reducing the energy consumption of the refrigerator.
[0030] In some embodiments, controlling the current refrigerator to operate includes:
[0031] When the defrost time corresponding to the defrost strategy is within the peak usage time period, the defrost time is adjusted to a first defrost time, and when the first defrost time is reached, the refrigerator is controlled to perform defrost operation, wherein the first defrost time is not within the peak usage time period.
[0032] Not defrosting during peak usage periods can reduce the number of defrosts and perform defrosting at the most reasonable time, which can also reduce the energy consumption of the refrigerator.
[0033] In some embodiments, controlling the current refrigerator to operate includes:
[0034] The current compressor operating frequency is sent to the current refrigerator, so that the refrigerator controls the compressor operation according to the current compressor operating frequency.
[0035] Therefore, the speed of the variable frequency compressor can be adjusted according to actual needs, which improves the energy efficiency ratio of the compressor and reduces the energy consumption of the refrigerator.
[0036] In some embodiments, the device for controlling a refrigerator is provided with an energy consumption measuring device in the refrigerator, and the device comprises:
[0037] The acquisition module is configured to acquire the status information and operation information of the current refrigerator, and the usage habit information of the user corresponding to the current refrigerator, wherein the operation information includes: the energy consumption information of the current refrigerator acquired through the energy consumption measuring device;
[0038] A determination module is configured to obtain a current low-power operation strategy of the current refrigerator based on the refrigerator energy consumption big data model according to the state information, the operation information, and the usage habit information, wherein the refrigerator energy consumption big data model is constructed based on deep learning;
[0039] The control module is configured to control the current refrigerator to operate according to the current low power consumption operation strategy.
[0040] In some embodiments, the device for refrigerator control includes a processor and a memory storing program instructions, and the processor is configured to execute the above-mentioned method for refrigerator control when executing the program instructions.
[0041] In some embodiments, the device includes a device body; the above-mentioned device for controlling a refrigerator is installed in the device body, wherein an energy consumption measuring device is configured in the refrigerator.
[0042] In some embodiments, the storage medium stores program instructions, and when the program instructions are run, the above-mentioned method for refrigerator control is executed.
[0043] The method, device and apparatus for refrigerator control provided by the embodiments of the present disclosure can achieve the following technical effects:
[0044] After building a refrigerator energy consumption big data model based on deep learning, the current low-power operation strategy of the current refrigerator can be obtained and corresponding refrigerator control can be performed based on the refrigerator energy consumption big data model, according to the current refrigerator status information and operation information, as well as the usage habit information of the user corresponding to the current refrigerator. In this way, the big data model can be applied to conduct in-depth analysis and intelligent optimization of the refrigerator status data, operation data, usage data, etc., which can significantly reduce the energy consumption of the refrigerator, improve the operating efficiency of the refrigerator, extend the service life of the refrigerator, and further improve the user experience.
[0045] 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
[0046] 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:
[0047] Figure 1 is a structural schematic diagram of a refrigerator control system provided by an embodiment of the present disclosure;
[0048] Figure 2 is a flow chart of a refrigerator control method provided by an embodiment of the present disclosure;
[0049] Figure 3 It is a flow chart of a refrigerator energy consumption big data model provided by an embodiment of the present disclosure;
[0050] Figure 4 is a flow chart of a refrigerator control method provided by an embodiment of the present disclosure;
[0051] Figure 5 is a structural schematic diagram of a refrigerator control device provided by an embodiment of the present disclosure;
[0052] Figure 6 is a structural schematic diagram of a refrigerator control device provided by an embodiment of the present disclosure;
[0053] Figure 7 is a structural schematic diagram of a refrigerator control device provided by an embodiment of the present disclosure;
[0054] Figure 8 It is a schematic diagram of a device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION
[0055] 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.
[0056] 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.
[0057] Unless otherwise stated, the term "plurality" means two or more.
[0058] 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.
[0059] 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.
[0060] Deep learning is a machine learning method that uses multi-layer neural networks to automatically extract features and make predictions from data. It is the core technology of modern artificial intelligence AI and is widely used in various tasks, such as image recognition, speech recognition, natural language processing, etc. The deep learning model is trained by multi-layer neural networks (such as convolutional neural networks CNN, recurrent neural networks RNN, feedforward neural networks, etc.). These networks convert input data into output results through layer-by-layer calculations. In the embodiment of the present disclosure, a refrigerator energy consumption big data model can be constructed based on deep learning. Then, based on the refrigerator energy consumption big data model, according to the current refrigerator status information, operation information, and the usage habits of the current refrigerator corresponding to the user, the current low-power operation strategy of the current refrigerator can be obtained and the corresponding refrigerator control can be performed. In this way, the big data model can be applied to conduct in-depth analysis and intelligent optimization of the refrigerator status data, operation data, usage data, etc., which can significantly improve the operating efficiency of the refrigerator, extend the service life of the refrigerator, and further improve the user experience.
[0061] Figure 1 FIG. 1 is a schematic diagram of an architecture for a refrigerator control system provided by an embodiment of the present disclosure. Figure 1 As shown, the refrigerator control system may include: a cloud server 100 and a refrigerator 200, wherein the cloud server 100 has constructed a refrigerator energy consumption big data model based on deep learning, so that the refrigerator 200 can upload the refrigerator status information and operation information, as well as the corresponding user's usage habit information to the cloud server 100, so that the cloud server 100 can obtain the low-power operation strategy of the refrigerator based on the refrigerator energy consumption big data model according to the status information, operation information, and usage habit information, and push the low-power operation strategy to the refrigerator 200, thereby controlling the refrigerator 200 to perform corresponding operations.
[0062] The refrigerator 200 is equipped with an energy consumption measuring device, for example, a device for measuring power consumption, which can measure the power consumed by the refrigerator in any time period as needed. In this way, the energy consumption information of the refrigerator can be obtained through the energy consumption measuring device. Therefore, the operation information includes: the energy consumption information of the current refrigerator obtained through the energy consumption measuring device. In some embodiments, the state information may include refrigerator equipment information, for example, refrigerator volume information, refrigerator model type information, etc. One or more, and the operation information may also include: refrigerator temperature information, refrigerator temperature information, refrigerator memory food type information, refrigerator memory food quantity information, refrigerator frost state information, refrigerator defrosting time, etc. One or more, and the use habit information includes: user door opening time information, user door opening duration information, door opening and closing frequency information, stored food quantity information, taken food quantity information, etc.
[0063] In this way, the cloud server 100 can conduct in-depth analysis and intelligent optimization of the refrigerator status data, operation data, usage data, etc. based on the refrigerator energy consumption big data model, thereby significantly reducing the energy consumption of the refrigerator and improving the operating efficiency of the refrigerator.
[0064] In some implementations, the cloud server constructs a refrigerator energy consumption big data model based on deep learning, which may include: obtaining status sample information and operation sample information of refrigerators of different models, as well as usage habit sample information of different users; based on a deep learning model architecture that introduces a self-attention mechanism, with minimizing refrigerator energy consumption as the main objective function, training and learning are performed based on the status sample information, operation sample information, and usage habit sample information to obtain a refrigerator energy consumption big data model.
[0065] Transformer is a deep learning model architecture for natural language processing tasks. It introduces the self-attention mechanism, which greatly improves the efficiency and effect of processing sequence data. In addition, it allows parallel processing of input data, and its training and reasoning speed is faster than that of traditional RNN models. Here, the state operation sample information of refrigerators of different models and the usage habit sample information of different users can be obtained. Similarly, the operation sample information may include: refrigerator energy consumption information, and may also include: refrigerator temperature information, refrigerator temperature information, refrigerator memory food type information, refrigerator memory food quantity information, refrigerator frosting state information, refrigerator defrosting time, etc. One or more, the state information may include refrigerator equipment information, such as: refrigerator volume information, refrigerator model type information, etc. One or more, and the usage habit sample information includes: user door opening time information, user door opening time information, door opening frequency information, storage food quantity information, take food quantity information, etc. Then, the acquired information is preprocessed, including: cleaning data, processing missing values, standardizing and normalizing, etc. In this way, the Transformer deep learning model can be used to automatically extract useful features from the preprocessed information, and the refrigerator energy consumption minimization is used as the main objective function for training and learning to obtain a refrigerator energy consumption big data model. Of course, in some embodiments, the objective function can also take into account user comfort and food preservation effects while minimizing refrigerator energy consumption as the main objective.
[0066] In some embodiments, the refrigerator energy consumption big data model can be adjusted according to the state information and operation information after the refrigerator runs the current low-power operation strategy, the user's usage habit information, and the corresponding current low-power operation strategy. In this way, new information can be received online, and the refrigerator energy consumption big data model can be learned and adaptively adjusted online, thereby improving the reliability of the refrigerator energy consumption big data model output.
[0067] In some embodiments, the energy consumption information of the current refrigerator after running the current low-power operation strategy and the evaluation information of the current user can be obtained to optimize the refrigerator energy consumption big data model. For example, the energy consumption information may include the energy consumption reduction ratio, and the user's evaluation information includes: user satisfaction score. In this way, attention is paid to the energy consumption reduction ratio and the user satisfaction score, and the Adam optimizer is used to set appropriate learning rate and regularization parameters to optimize the refrigerator energy consumption big data model. In this way, the reliability of the output of the refrigerator energy consumption big data model can be further improved, thereby improving the reliability of the refrigerator energy-saving control.
[0068] Therefore, after the refrigerator energy consumption big data model is configured in the cloud server, the corresponding refrigerator energy-saving control can be carried out. Figure 2is a flow chart of a refrigerator control method provided by an embodiment of the present disclosure, wherein an energy consumption measuring device is configured in the refrigerator, such as Figure 2 As shown, the refrigerator control process includes:
[0069] Step 201: Obtain status information and operation information of the current refrigerator, as well as usage habit information of the user corresponding to the current refrigerator, wherein the operation information includes: energy consumption information of the current refrigerator obtained through an energy consumption measuring device.
[0070] The current internal temperature, current external temperature, current internal humidity, and current stored food information of the current refrigerator can be obtained through the temperature acquisition device, humidity acquisition device, and image acquisition device configured in the current refrigerator, wherein the food information may include: food type information and quantity information. The current energy consumption information of the current refrigerator can also be obtained through the energy consumption measurement device. Therefore, the operation information includes: the energy consumption information of the current refrigerator, and may also include: the current internal temperature, the current external temperature, the current stored food information, and so on. The current refrigerator also records the usage habits of each user, including: user door opening time information, user door opening duration information, door opening and closing frequency information, stored food quantity information, taken food quantity information, and so on.
[0071] The refrigerator can report the current refrigerator operation information and the usage habit information of the user corresponding to the current refrigerator to the cloud server, so that the cloud server can obtain the current refrigerator operation information and the usage habit information of the user corresponding to the current refrigerator. The refrigerator status information includes one or more of: refrigerator volume information, refrigerator model type information, etc. The refrigerator can also report the current refrigerator status information to the cloud server, or the server can obtain the current refrigerator status information from the recorded refrigerator information.
[0072] Step 202: According to the state information, operation information, and usage habit information, based on the refrigerator energy consumption big data model, obtain the current low-power operation strategy of the current refrigerator, wherein the refrigerator energy consumption big data model is constructed based on deep learning.
[0073] The cloud server can build a refrigerator energy consumption big data model based on the deep learning model architecture that introduces the self-attention mechanism, and the refrigerator energy consumption big data model takes minimizing the refrigerator energy consumption as the main objective function.
[0074] In some embodiments, the refrigerator energy consumption big data model includes an input layer, a hidden layer, and an output layer, wherein the input layer includes: the type of items stored in the refrigerator (value), the volume of the refrigerator (value), the model of the refrigerator (value), the time of opening the refrigerator door (time series data), the daily refrigerator energy consumption (value), the time of each door opening (time series data), the active defrosting time (time series data), etc. One, two or more. The hidden layer may include: a multi-layer Transformer encoder for capturing the long-term and short-term dependencies of the time series data, and a fully connected layer for integrating different features and extracting high-level feature representations. The output layer includes: a low-power operation strategy, wherein different classification tasks output different low-power operation strategies, which may include: energy-saving operation instructions, energy-saving operation parameters, etc. In this way, after obtaining the state information, operation information, and usage habit information, data preprocessing is performed and input into the trained refrigerator energy consumption big data model, and then high-level features are extracted from the input data, and feature vectors can be generated according to the state operation information and usage habit information, thereby obtaining the current low-power operation strategy of the matching current refrigerator.
[0075] In the disclosed embodiment, the current low-power operation strategy includes: one, two or more of the current target operating temperature of the current refrigerator, the peak usage time period of the current refrigerator, the current compressor operating frequency of the current refrigerator, and the defrost strategy of the current refrigerator.
[0076] Therefore, in some embodiments, obtaining the current low-power operation strategy of the current refrigerator includes: generating the current target operating temperature of the current refrigerator based on the current state information and current operation information of the current refrigerator and based on a refrigerator energy consumption big data model, wherein the current operation information includes: current internal temperature, current external temperature, and current stored food information.
[0077] In some embodiments, obtaining the current low-power operation strategy of the current refrigerator includes: predicting the peak usage time period of the current refrigerator based on the refrigerator energy consumption big data model according to the usage habit information of the user corresponding to the current refrigerator.
[0078] In some embodiments, obtaining the current low-power operation strategy of the current refrigerator includes: obtaining the current compressor operation frequency of the current refrigerator based on the refrigerator energy consumption big data model according to current state information, current operation information and usage habit information.
[0079] In some embodiments, obtaining the current low-power operation strategy of the current refrigerator includes: obtaining the defrosting strategy of the current refrigerator based on the refrigerator energy consumption big data model according to the current state and current operation information of the current refrigerator, wherein the current operation information includes the current frosting state information. The current frosting state information can be determined based on the coil temperature, the temperature inside the refrigerator, the humidity inside the refrigerator, etc. obtained by the temperature acquisition device, the humidity acquisition device, and other detection devices. Alternatively, it can be directly obtained through the frosting detection device configured in the current refrigerator, that is, the current state operation information includes the current frosting state information obtained by the frosting detection device in the current refrigerator.
[0080] Step 203: Control the current refrigerator to operate according to the current low power consumption operation strategy.
[0081] The current low power operation strategy includes one, two or more of: the current target operating temperature of the current refrigerator, the peak usage time period of the current refrigerator, the current compressor operating frequency of the current refrigerator, and the defrost strategy of the current refrigerator.
[0082] Therefore, in some embodiments, controlling the current refrigerator to operate includes: when the current moment is not in the peak usage time period, sending the current target operating temperature to the refrigerator for operation; when the current moment is in the peak usage time period, adjusting the current target operating temperature to a first target operating temperature based on the current internal temperature and the current external temperature, and sending the first target operating temperature to the refrigerator for operation.
[0083] For example: the current low-power operation strategy includes: the current target operating temperature of the current refrigerator, the peak usage time period of the current refrigerator, and the current target operating temperatures include: refrigeration target temperature 3°C, freezing target temperature -21°C, the peak usage time period of the current refrigerator is 11:30-12:30, and 17:00-18:30, then, if the current time is 10:00, which is not between 11:30-12:30 and 17:00-18:30, the current target operating temperatures in the current low-power operation strategy still include: refrigeration target temperature 3°C, freezing target temperature -21°C. The cloud server sends the current target operating temperature to the refrigerator, and the refrigerator performs corresponding operations according to the current target operating temperature. If the current time is 12:00, between 11:30-12:30 and 17:00-18:30, the current target operating temperature can be adjusted to the first target operating temperature according to the current internal temperature and the current external temperature. For example, when the current external temperature is greater than or equal to the current internal temperature, the current target operating temperature in the current low-power operation strategy can be increased to the first target operating temperature. The first target operating temperature includes: refrigeration target temperature 5°C, freezing target temperature -18°C. The current low-power operation strategy sent by the cloud server to the refrigerator includes the first target operating temperature, and the refrigerator performs corresponding operations according to the first target operating temperature.
[0084] Of course, there are many ways to increase the current target operating temperature to the first target operating temperature, such as increasing a fixed value or setting a ratio, which will not be listed in detail.
[0085] Of course, at the current moment during the peak usage time period, if the current external temperature is lower than the current internal temperature, the current target operating temperature can be lowered to the first target operating temperature. Similarly, there are many ways to lower the current target operating temperature to the first target operating temperature, such as lowering a fixed value, or setting a ratio, etc.
[0086] It can be seen that during the peak usage period, after the refrigerator operates accordingly according to the first target operating temperature, the temperature difference between the inside and outside of the refrigerator will become smaller, thereby reducing the temperature interaction inside and outside the refrigerator, and further reducing the energy consumption of the refrigerator.
[0087] In this way, the target temperature of the refrigerator can be adjusted dynamically, and the refrigerator can adjust the target temperature in real time according to the internal and external temperatures, the food information in the refrigerator, etc., to ensure the lowest energy consumption while ensuring the refrigeration function. In addition, during the peak period when users frequently open and close the refrigerator, the refrigerator will adjust the target temperature appropriately to reduce the temperature interaction between the inside and outside of the refrigerator by reducing the temperature difference between the inside and outside of the refrigerator.
[0088] In some embodiments, controlling the current refrigerator to operate includes: when the defrost time corresponding to the defrost strategy is within the peak usage time period, adjusting the defrost time to a first defrost time, and when the first defrost time is reached, controlling the refrigerator to perform defrost operation, wherein the first defrost time is not within the peak usage time period.
[0089] For example, the current low power operation strategy includes: the current peak usage time period of the refrigerator and the current defrost strategy of the refrigerator. If the current peak usage time period of the refrigerator is 11:30-12:30 and 17:00-18:30, the current defrost time included in the current defrost strategy of the refrigerator is after 2 hours. Then, if the current time is 10:00, the corresponding defrost time is 12:00. Between 11:30-12:30 and 17:00-18:30, the defrost time needs to be adjusted to the first defrost time. Similarly, there are many ways to adjust the defrost time to the first defrost time, which can be delayed by a fixed value, or adjusted to a set time, etc. Here, the delayed first defrost time can be 14:00, and 14:00 is not in the peak usage time period of 11:30-12:30 and 17:00-18:30. Therefore, the current low-power operation strategy sent to the refrigerator by the cloud server includes the first defrost time of 14:00. After the refrigerator receives the current low-power operation strategy, the refrigerator can perform defrost operation when it reaches 14:00.
[0090] In this way, the refrigerator can defrost intelligently. After the refrigerator monitors the frost status information of the refrigerator, it can analyze it through the big data model and avoid the peak usage period. It can automatically defrost at a more suitable time, reducing unnecessary energy waste, reducing the energy consumption of the refrigerator, and improving the intelligence of the refrigerator.
[0091] In some embodiments, controlling the current refrigerator to operate includes: controlling the current refrigerator to operate includes: sending the current compressor operating frequency to the current refrigerator, so that the refrigerator controls the compressor operation according to the current compressor operating frequency.
[0092] The refrigerator compressor can be a variable frequency compressor. Therefore, the current low-power operation strategy includes the current compressor operating frequency of the current refrigerator. The current compressor operating frequency can be sent to the current refrigerator, so that the refrigerator controls the compressor operation according to the current compressor operating frequency. In this way, the speed of the variable frequency compressor is adjusted according to actual needs, which improves the energy efficiency ratio of the compressor and thereby reduces the energy consumption of the refrigerator.
[0093] It can be seen that after building a refrigerator energy consumption big data model based on deep learning, the current low-power operation strategy of the current refrigerator can be obtained and the corresponding refrigerator control can be performed based on the refrigerator energy consumption big data model according to the current refrigerator status information, operation information, and the usage habits information of the user corresponding to the current refrigerator. In this way, the big data model can be applied to conduct in-depth analysis and intelligent optimization of the refrigerator status data, operation data, usage data, etc., which can significantly reduce the energy consumption of the refrigerator, improve the operating efficiency of the refrigerator, extend the service life of the refrigerator, and further improve the user experience.
[0094] After the current refrigerator operates according to the received current low-power operation strategy, it can continue to report the current status information and operation information of the refrigerator to the cloud server. In this way, the refrigerator energy consumption big data model in the cloud server is updated and adjusted. In this way, the refrigerator energy consumption big data model can be adjusted in time, further improving the reliability of the refrigerator energy consumption big data model output, thereby improving the reliability of the refrigerator energy-saving control.
[0095] The operation flow is collected into a specific embodiment below to illustrate the refrigerator control process provided by the embodiment of the present invention.
[0096] In one embodiment of the present disclosure, Figure 1 As shown, the cloud server needs to build a big data model of refrigerator energy consumption.
[0097] Figure 3 FIG. 1 is a flow chart of a refrigerator energy consumption big data model provided by an embodiment of the present disclosure. Figure 3 As shown in FIG. 1 , the construction process of the refrigerator energy consumption big data model includes:
[0098] Step 301: The cloud server collects status sample information and operation sample information of different models of refrigerators, as well as usage habit sample information of different users from the daily use of different models of refrigerators and different users.
[0099] Among them, the status sample information may include: refrigerator volume information, refrigerator model type information, etc., the operation sample information may include: refrigerator energy consumption information, and may also include: refrigerator memory food information, refrigerator defrost time, etc. One or more, and the usage habit sample information includes: user door opening time information, user door opening time information, door opening and closing frequency information, stored food quantity information, taken food quantity information, etc.
[0100] Step 302: The cloud server performs data preprocessing on the collected status sample information, operation sample information and usage habit sample information.
[0101] The preprocessing process includes: cleaning data, handling missing values, standardization and normalization, etc.
[0102] Step 303: The cloud server uses a Transformer-based deep learning model to minimize the main objective function of energy consumption while taking into account user comfort and food preservation effects. The data information obtained after data preprocessing is trained and learned to obtain a refrigerator energy consumption big data model.
[0103] The refrigerator energy consumption big data model includes an input layer, a hidden layer, and an output layer, wherein the input layer includes: the type of items stored in the refrigerator (value), the volume of the refrigerator (value), the model of the refrigerator (value), the time when the refrigerator door is opened (time series data), the daily refrigerator energy consumption (value), the time when the door is opened each time (time series data), the active defrosting time (time series data), etc. One, two or more. The hidden layer may include: a multi-layer Transformer encoder for capturing the long-term and short-term dependencies of the time series data, and a fully connected layer for integrating different features and extracting high-level feature representations. The output layer includes: a low-power operation strategy, wherein different classification tasks output different low-power operation strategies, which may include: energy-saving operation instructions, energy-saving operation parameters, etc.
[0104] Step 304: When the operating status information of the current refrigerator according to the current low-power operation policy is obtained, the cloud server adjusts the refrigerator energy consumption big data model according to the obtained status information, operating information, user usage habit information, and the corresponding current low-power operation policy.
[0105] Step 305: After obtaining the energy consumption information of the current refrigerator after running the current low-power operation strategy and the user's evaluation information, the cloud server uses the Adam optimizer to set appropriate learning rate and regularization parameters to optimize the refrigerator energy consumption big data model.
[0106] It can be seen that a refrigerator energy consumption big data model is configured in the cloud server, and an energy consumption measuring device is configured in the refrigerator, so that energy-saving control of the refrigerator is performed based on the refrigerator energy consumption big data model.
[0107] Figure 4 FIG. 1 is a flow chart of a refrigerator control method provided by an embodiment of the present disclosure. Figure 4 As shown, the refrigerator control process includes:
[0108] Step 401: The cloud server obtains status information, operation information, and usage habit information of the user corresponding to the current refrigerator, wherein the operation information includes: energy consumption information of the current refrigerator obtained through an energy consumption measuring device.
[0109] Step 402: The cloud server obtains the current low-power operation strategy of the current refrigerator based on the refrigerator energy consumption big data model according to the status information, operation information, and usage habit information.
[0110] Among them, the current low power consumption operation strategy includes: the current target operating temperature of the current refrigerator, the peak usage time period of the current refrigerator, the current compressor operation frequency of the current refrigerator, and the defrosting strategy of the current refrigerator.
[0111] Step 403: Determine whether the current time is within the peak usage time period corresponding to the current low power consumption operation strategy. If yes, execute step 404; otherwise, execute step 405.
[0112] Step 404: The cloud server adjusts the current target operating temperature in the current low power consumption operation strategy to a first target operating temperature according to the current internal temperature and the current external temperature, and sends the first target operating temperature to the refrigerator for operation.
[0113] Step 405: The cloud server may send the current target operating temperature to the refrigerator for operation.
[0114] Step 406: Determine whether the corresponding defrosting time in the current low power consumption operation strategy is within the peak usage time period. If yes, execute step 407; otherwise, execute step 408.
[0115] Step 407: The cloud server postpones the defrost time to the first defrost time, and sends the defrost strategy including the first defrost time to the current refrigerator, so that the refrigerator performs defrost operation when the first defrost time is reached, wherein the first defrost time is not within the peak usage time period.
[0116] Step 408: The cloud server sends the defrost strategy including the defrost time to the current refrigerator, so that when the defrost time is reached, the refrigerator performs a defrost operation.
[0117] Step 409: The cloud server sends the current compressor operating frequency corresponding to the current low power consumption operation strategy to the current refrigerator, so that the refrigerator controls the compressor operation according to the current compressor operating frequency.
[0118] There is no limitation on the order of steps 403-405, steps 406-408, and step 409, and they may be executed in parallel.
[0119] It can be seen that in this embodiment, after constructing the refrigerator energy consumption big data model based on deep learning, the current low-power operation strategy of the current refrigerator can be obtained and the corresponding refrigerator control can be performed based on the refrigerator energy consumption big data model according to the current refrigerator status information, operation information, and the usage habit information of the user corresponding to the current refrigerator. In this way, the big data model can be applied to conduct in-depth analysis and intelligent optimization of the refrigerator status data, operation data, usage data, etc., and the energy-saving control of the refrigerator can be performed from multiple aspects such as dynamic temperature adjustment, delayed defrosting, and compressor operating frequency adjustment, which can significantly reduce the energy consumption of the refrigerator, improve the operating efficiency of the refrigerator, and extend the service life of the refrigerator, further improving the user experience.
[0120] According to the above-mentioned process for refrigerator control, an apparatus for refrigerator control can be constructed.
[0121] Figure 5 Schematic diagram of a refrigerator control device provided by an embodiment of the present disclosure. The refrigerator is equipped with an energy consumption measuring device, such as Figure 5 As shown, the device includes: an acquisition module 510, a determination module 520, and a control module 530.
[0122] The acquisition module 510 is configured to obtain the status information and operation information of the current refrigerator, and the usage habit information of the user corresponding to the current refrigerator, wherein the operation information includes: the energy consumption information of the current refrigerator obtained through the energy consumption measuring device.
[0123] The determination module 520 is configured to obtain the current low-power operation strategy of the current refrigerator based on the state information, operation information, and usage habit information and based on the refrigerator energy consumption big data model, wherein the refrigerator energy consumption big data model is constructed based on deep learning.
[0124] The control module 530 is configured to control the current refrigerator to operate according to the current low power consumption operation strategy.
[0125] In some embodiments, it also includes:
[0126] The configuration module is configured to obtain state sample information and operation sample information of refrigerators of different models, as well as usage habit sample information of different users; based on the deep learning model architecture that introduces the self-attention mechanism, with minimizing the energy consumption of the refrigerator as the main objective function, training and learning are performed according to the state sample information, operation sample information and usage habit sample information to obtain a big data model of refrigerator energy consumption.
[0127] In some embodiments, the configuration module is also configured to adjust the refrigerator energy consumption big data model based on the status information and operation information after the current refrigerator runs the current low-power operation strategy, the user's usage habit information, and the corresponding current low-power operation strategy; obtain the energy consumption information after the current refrigerator runs the current low-power operation strategy, and the current user's evaluation information, and optimize the refrigerator energy consumption big data model.
[0128] In some embodiments, the determination module 520 includes: one, two or more of: a first determination unit, a second determination unit, a third determination unit, a fourth determination unit, and the like.
[0129] The first determination unit is configured to generate a current target operating temperature of the current refrigerator based on the current state information and current operating information of the current refrigerator and based on the refrigerator energy consumption big data model, wherein the current operating information includes: current internal temperature, current external temperature, and current stored food information.
[0130] The second determination unit is configured to predict the peak usage time period of the current refrigerator based on the usage habit information of the user corresponding to the current refrigerator and based on the refrigerator energy consumption big data model.
[0131] The third determination unit is configured to obtain the current compressor operation frequency of the current refrigerator based on the refrigerator energy consumption big data model according to the current state information, the current operation information and the usage habit information.
[0132] The fourth determination unit is configured to obtain the defrost strategy of the current refrigerator based on the current state information and current operation information of the current refrigerator and based on the refrigerator energy consumption big data model, wherein the current state operation information includes the current frosting state information obtained by the frost detection device in the current refrigerator.
[0133] In some embodiments, the control module 530 includes:
[0134] The first control unit is configured to adjust the current target operating temperature to a first target operating temperature according to the current internal temperature and the current external temperature when the current moment is not within the peak usage time period, and send the first target operating temperature to the refrigerator for operation.
[0135] In some embodiments, the control module 530 includes:
[0136] The second control unit is configured to adjust the defrost time to a first defrost time when the defrost time corresponding to the defrost strategy is within the peak usage time period, and to control the refrigerator to perform defrost operation when the first defrost time is reached, wherein the first defrost time is not within the peak usage time period.
[0137] In some embodiments, the control module 530 includes:
[0138] The third control unit is configured to send the current compressor operating frequency to the current refrigerator, so that the refrigerator controls the compressor operation according to the current compressor operating frequency.
[0139] Figure 6 Schematic diagram of a refrigerator control device provided by an embodiment of the present disclosure. Figure 6 As shown, the refrigerator control device 500 includes: an acquisition module 510, a determination module 520, a control module 530, and a configuration module 540, wherein the determination module 520 includes: a first determination unit 521, a second determination module 522, a third determination unit 523, and a fourth determination unit 524. The control module 530 includes: a first control unit 531, a second control unit 532, and a third control unit 533.
[0140] Among them, the configuration module 540 collects status sample information and operation sample information of different models of refrigerators, as well as usage habit sample information of different users from the daily use of different models of refrigerators and different users, and then performs data preprocessing on the collected status sample information, operation sample information and usage habit sample information, and adopts a Transformer-based deep learning model to minimize the main objective function of energy consumption while taking into account user comfort and food preservation effects. The data information obtained after data preprocessing is trained and learned to obtain a big data model of refrigerator energy consumption.
[0141] Of course, if the state operation information of the current refrigerator according to the current low-power operation strategy is obtained, the configuration module 540 can also adjust the refrigerator energy consumption big data model according to the obtained state information, operation information, user usage habit information, and the corresponding current low-power operation strategy. And if the energy consumption information of the current refrigerator after running the current low-power operation strategy and the user's evaluation information are obtained, the configuration module 540 can also use the Adam optimizer to set the appropriate learning rate and regularization parameters to optimize the refrigerator energy consumption big data model.
[0142] After the configuration module 540 constructs a refrigerator energy consumption big data model based on deep learning, if the acquisition module 510 acquires the current refrigerator status information, operation information, and usage habit information of the user corresponding to the current refrigerator, wherein the operation information includes: the energy consumption information of the current refrigerator acquired through the energy consumption measurement device, the determination module 520 can obtain the current low-power operation strategy of the current refrigerator based on the refrigerator energy consumption big data model according to the status information, operation information, and usage habit information. Among them, the current low-power operation strategy includes: the current target operating temperature of the current refrigerator, the peak usage time period of the current refrigerator, the current compressor operating frequency of the current refrigerator, and the defrosting strategy of the current refrigerator.
[0143] Among them, the first determination unit 521 in the determination module 520 can generate the current target operating temperature of the current refrigerator based on the current state information and current operation information of the current refrigerator and based on the refrigerator energy consumption big data model, wherein the current state operation information includes: the current internal temperature, the current external temperature, and the current stored food information. The second determination unit 522 can predict the peak usage time period of the current refrigerator based on the refrigerator energy consumption big data model according to the usage habit information of the user corresponding to the current refrigerator. The third determination unit 523 obtains the current compressor operation frequency of the current refrigerator based on the refrigerator energy consumption big data model according to the current state information, current operation information and usage habit information. And, the fourth determination unit 524 can obtain the defrosting strategy of the current refrigerator based on the current state information and current operation information of the current refrigerator and based on the refrigerator energy consumption big data model, wherein the current operation information includes the current frosting state information obtained by the frosting detection device in the current refrigerator.
[0144] In this way, if the current moment is within the peak usage time period corresponding to the current low power operation strategy, the first control unit 531 in the control module 530 can adjust the current target operating temperature to the first target operating temperature according to the current internal temperature and the current external temperature, and send the first target operating temperature to the refrigerator for operation. If the current moment is not within the peak usage time period, the first control unit 531 directly sends the current target operating temperature to the refrigerator for operation.
[0145] If the corresponding defrost time in the current low power operation strategy is within the peak usage time period, the second control unit 532 may postpone the defrost time to the first defrost time, and send the defrost strategy including the first defrost time to the current refrigerator, so that when the first defrost time is reached, the refrigerator performs defrost operation, wherein the first defrost time is not within the peak usage time period. If the defrost time is not within the peak usage time period, the second control unit 532 may directly send the defrost strategy including the defrost time to the current refrigerator, so that when the defrost time is reached, the refrigerator performs defrost operation.
[0146] Of course, the third control unit 533 can send the current compressor operating frequency corresponding to the current low power consumption operation strategy to the current refrigerator, so that the refrigerator controls the compressor operation according to the current compressor operating frequency.
[0147] It can be seen that in this embodiment, after constructing the refrigerator energy consumption big data model based on deep learning, the device for refrigerator control can be based on the refrigerator energy consumption big data model, according to the current refrigerator status information and operation information, as well as the usage habit information of the user corresponding to the current refrigerator, to obtain the current low-power operation strategy of the current refrigerator and perform corresponding refrigerator control. In this way, the big data model can be applied to conduct in-depth analysis and intelligent optimization of the refrigerator status data, operation data, usage data, etc., and can perform energy-saving control of the refrigerator from multiple aspects such as dynamic temperature adjustment, delayed defrosting, and compressor operating frequency adjustment, significantly reduce the energy consumption of the refrigerator, improve the operating efficiency of the refrigerator, and extend the service life of the refrigerator, further improving the user experience.
[0148] Combination Figure 7 The present disclosure provides a device 700 for controlling a refrigerator, which can be applied to Figure 1 The cloud server shown includes:
[0149] The processor 1000 and the memory 1001 may also include a communication interface 1002 and a bus 1003. The processor 1000, the communication interface 1002, and the memory 1001 may communicate with each other through the bus 1003. The communication interface 1002 may be used for information transmission. The processor 1000 may call the logic instructions in the memory 1001 to execute the method for controlling the refrigerator in the above embodiment.
[0150] In addition, the logic instructions in the above-mentioned memory 1001 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product.
[0151] The memory 1001 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 1000 executes the function application and data processing by running the program instructions / modules stored in the memory 1001, that is, the method for refrigerator control in the above method embodiment is implemented.
[0152] The memory 1001 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 1001 may include a high-speed random access memory and may also include a non-volatile memory.
[0153] An embodiment of the present disclosure provides a refrigerator control device, comprising: a processor and a memory storing program instructions, wherein the processor is configured to execute a refrigerator control method when executing the program instructions.
[0154] Combination Figure 8 , the embodiment of the present disclosure provides a device, which can be a cloud server, including: a device body, a refrigerator control device 500 (700) is installed on the device body, wherein an energy consumption measuring device is configured in the refrigerator. 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 refrigerator control device 500 (700) can be adapted to a feasible device body, thereby realizing other feasible embodiments.
[0155] An embodiment of the present disclosure provides a storage medium storing program instructions, which, when run, execute the above-mentioned method for controlling a refrigerator.
[0156] An embodiment of the present disclosure provides a computer program product, which includes a computer program stored on a storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer executes the above-mentioned refrigerator control method.
[0157] The above-mentioned storage medium may be a transient computer-readable storage medium or a non-transitory computer-readable storage medium.
[0158] 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 enabling a computer device (which may be a personal computer, a server, or a network device, etc.) to perform 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, including: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes, or a transient storage medium.
[0159] 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, individual components and functions are optional, and the order of operation may vary. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. The scope of the embodiments of the present disclosure includes the entire scope of the claims, and all available equivalents of the claims. When used in this application, although the terms "first", "second", etc. may be used in this application to describe each element, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, without changing the meaning of the description, the first element can be called the second element, and similarly, the second element can be called the first element, as long as all occurrences of the "first element" are renamed consistently and all occurrences of the "second element" are renamed consistently. The first element and the second element are both elements, but may not be the same element. 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 claims, unless the context clearly indicates, the singular forms "a", "an" and "the" are intended to include the plural forms as well. Similarly, the term "and / or" as used in this application refers to any and all possible combinations of one or more associated listings. In addition, when used in this 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 of these. In the absence of further restrictions, the elements defined by the sentence "including one..." do not exclude the presence of other identical elements in the process, method or device including the elements. In this article, each embodiment may focus on the differences from other embodiments, and the same and similar parts between the 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.
[0160] 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.
[0161] 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.
[0162] 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 controlling a refrigerator, characterized in that: The refrigerator is equipped with an energy consumption measuring device, and the method comprises: Acquire the current state information and operation information of the refrigerator, and the usage habit information of the user corresponding to the current refrigerator, wherein the operation information includes: the energy consumption information of the current refrigerator obtained by the energy consumption measuring device; According to the status information, operation information, and usage habit information, based on the refrigerator energy consumption big data model, the current low-power operation strategy of the current refrigerator is obtained, wherein the refrigerator energy consumption big data model is constructed based on deep learning; According to the current low power operation strategy, the current refrigerator is controlled to operate.
2. The method according to claim 1, characterized in that Also includes: Obtain status sample information and operation sample information of refrigerators of different models, as well as usage habit sample information of different users; Based on the deep learning model architecture that introduces the self-attention mechanism, minimizing the energy consumption of the refrigerator is taken as the main objective function. Training and learning are carried out according to the state sample information, operation sample information and usage habit sample information to obtain the refrigerator energy consumption big data model.
3. The method according to claim 2, characterized in that Also includes: Adjust the refrigerator energy consumption big data model according to the state information and operation information after the refrigerator runs the current low-power operation strategy, the user's usage habit information, and the corresponding current low-power operation strategy; Obtain the energy consumption information of the current refrigerator after running the current low-power operation strategy, as well as the current user's evaluation information, and optimize the refrigerator energy consumption big data model.
4. The method according to claim 1, characterized in that: The obtaining of the current low power consumption operation strategy of the refrigerator includes: According to the current state information and current operation information of the current refrigerator, based on the refrigerator energy consumption big data model, the current target operating temperature of the current refrigerator is generated, wherein the current operation information includes: the current internal temperature, the current external temperature, and the current stored food information; and / or, According to the usage habit information of the user corresponding to the current refrigerator, based on the refrigerator energy consumption big data model, predict the peak usage time period of the current refrigerator; and / or, According to the current state information, current operation information and usage habit information, based on the refrigerator energy consumption big data model, the current compressor operation frequency of the current refrigerator is obtained; and / or, According to the current state information and current operation information of the current refrigerator, based on the refrigerator energy consumption big data model, the defrost strategy of the current refrigerator is obtained, wherein the current operation information includes the current frosting state information obtained by the frost detection device in the current refrigerator.
5. The method according to claim 4, characterized in that The controlling of the current refrigerator to operate includes: If the current time is not in the peak usage period, the current target operating temperature is sent to the refrigerator for operation; When the current moment is within the peak usage time period, the current target operating temperature is adjusted to the first target operating temperature according to the current internal temperature and the current external temperature, and the first target operating temperature is sent to the refrigerator for operation.
6. The method according to claim 4, characterized in that The controlling of the current refrigerator to operate includes: When the defrost time corresponding to the defrost strategy is within the peak usage time period, the defrost time is adjusted to a first defrost time, and when the first defrost time is reached, the refrigerator is controlled to perform defrost operation, wherein the first defrost time is not within the peak usage time period.
7. The method according to claim 4, characterized in that The controlling of the current refrigerator to operate includes: The current compressor operating frequency is sent to the current refrigerator, so that the refrigerator controls the compressor operation according to the current compressor operating frequency.
8. A device for controlling a refrigerator, characterized in that: The refrigerator is equipped with an energy consumption measurement device, which includes: The acquisition module is configured to acquire the status information and operation information of the current refrigerator, and the usage habit information of the user corresponding to the current refrigerator, wherein the operation information includes: the energy consumption information of the current refrigerator acquired through the energy consumption measuring device; A determination module is configured to obtain a current low-power operation strategy of the current refrigerator based on the refrigerator energy consumption big data model according to the state information, the operation information, and the usage habit information, wherein the refrigerator energy consumption big data model is constructed based on deep learning; The control module is configured to control the current refrigerator to operate according to the current low power consumption operation strategy.
9. A device for controlling a refrigerator, the device comprising a processor and a memory storing program instructions, characterized in that: The processor is configured to perform the method for refrigerator control as claimed in any one of claims 1 to 7 when executing the program instructions.
10. A device, characterized in that: include: Equipment body; The device for refrigerator control as described in claim 8 or 9 is installed on the device body, wherein an energy consumption measuring device is configured in the refrigerator.
11. A storage medium storing program instructions, characterized in that: When the program instructions are executed, the method for controlling a refrigerator as described in any one of claims 1 to 7 is executed.
