Refrigerator control method and device, refrigerator and storage medium

Abstract

The invention discloses a refrigerator control method and device, a refrigerator and a storage medium. The control method comprises the steps that historical door opening data and current time information of the refrigerator are obtained; inputting the historical door opening data and the time information into a door opening prediction model to obtain door opening probability information in a future first preset duration; and determining whether to control the refrigerator to start pre-cooling or not according to the door opening probability information. According to the control method, the door opening prediction model is trained or called by fusing the time information with the periodic characteristics and the historical door opening data, the use habit rule of the user can be learned more accurately, and the generated door opening probability information reflects the possibility of door opening in the future time period. The pre-cooling decision is made based on the possibility, so that triggering of the pre-cooling action is highly matched with the actual requirement of the user, blind pre-cooling is effectively avoided, and accurate energy saving is achieved on the premise that it is guaranteed that the temperature in the box is stable when the door is opened.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of refrigerators, in particular to a refrigerator control method and device, a refrigerator and a storage medium. BACKGROUND

[0002] With the development of smart homes, energy saving and intelligent level of refrigerators have become an important development direction. Traditional refrigerators usually control the start and stop of the compressor according to whether the temperature in the box reaches the set threshold. This reactive control mode has hysteresis. When the user frequently opens and closes the refrigerator door, a large amount of hot air will rush in, causing the temperature in the box to rise rapidly. The compressor needs to run at a high power for a long time after the door is closed to restore the set temperature, which not only causes an increase in energy consumption, but also may affect the preservation effect of food materials due to temperature fluctuations.

[0003] Pre-cooling of the refrigerator refers to pre-cooling to reserve cold energy before the user may use the refrigerator. However, the accuracy of existing refrigerator pre-cooling schemes is insufficient, often relying on a fixed schedule and failing to accurately adapt to the actual use habits of the user.

[0004] Therefore, the current technology still needs to be improved and enhanced. SUMMARY

[0005] The present application provides a refrigerator control method and device, a refrigerator and a storage medium, which can effectively improve the accuracy of the refrigerator predicting the user opening the door and improve the pre-cooling effect of the refrigerator.

[0006] A refrigerator control method, comprising: obtaining historical door opening data of the refrigerator and current time information; inputting the historical door opening data and the time information into a door opening prediction model to obtain door opening probability information within a first preset time period in the future; determining whether to control the refrigerator to start pre-cooling according to the door opening probability information.

[0007] In some embodiments, the door opening probability information within the first preset time period in the future is a door opening probability curve within the first preset time period in the future, and the determination of whether to control the refrigerator to start pre-cooling according to the door opening probability information comprises: determining a highest probability value within the first preset time period in the future according to the door opening probability curve; controlling the refrigerator to start pre-cooling after determining that the highest probability value exceeds a preset probability threshold.

[0008] In some embodiments, the control of the refrigerator to start pre-cooling comprises: determining a predicted time corresponding to when the door opening probability reaches a preset probability threshold according to the door opening probability curve; Based on the predicted time, the refrigerator is controlled to be turned on for precooling in advance by a second preset time length.

[0009] In some embodiments, before determining whether to control the refrigerator to be turned on for precooling according to the door opening probability information, the method further comprises: obtaining usage scenario information of the refrigerator, the usage scenario information comprising defrosting state, seasonal state and long-term drift state; determining the second preset time length and / or the preset probability threshold according to the usage scenario information.

[0010] In some embodiments, before controlling the refrigerator to be turned on for precooling, the method further comprises: obtaining temperature data of the refrigerator and working state information of a compressor, the temperature data comprising cabinet temperature and / or ambient temperature; determining a corresponding precooling amplitude based on a preset mapping relationship according to the preset probability threshold, the temperature data and the working state information; controlling the refrigerator to perform a precooling operation according to the precooling amplitude.

[0011] In some embodiments, after determining whether to control the refrigerator to be turned on for precooling according to the door opening probability information, the method further comprises: after detecting that the door of the refrigerator is opened, obtaining temperature rise information of a compartment and door opening information within a third preset time length; adjusting operating parameters of the refrigerator according to the temperature rise information and the door opening information.

[0012] In some embodiments, the control method of the refrigerator further comprises: obtaining actual door opening data and predicted door opening data of a recent cycle of the refrigerator; determining a deviation between the actual door opening data and the predicted door opening data; if the deviation exceeds a preset deviation threshold, training the door opening prediction model according to the actual door opening data.

[0013] The application also provides a control device of a refrigerator, comprising: an obtaining module configured to obtain historical door opening data of the refrigerator and current time information; a prediction module configured to input the historical door opening data and the time information into a door opening prediction model to obtain door opening probability information within a first preset time length in the future; a control module configured to determine whether to control the refrigerator to be turned on for precooling according to the door opening probability information.

[0014] The application also provides a refrigerator configured to perform the control method of the refrigerator described above.

[0015] The application also provides a storage medium having a computer program stored thereon, the computer program being configured to execute the control method of the refrigerator.

[0016] The control method of the refrigerator, the control device, the refrigerator and the storage medium provided by the application can more accurately learn the usage habit of the user by fusing the time information with the periodic characteristics and the historical door opening data, and generate door opening probability information reflecting the possibility of door opening in the future period. The precooling decision is made based on the possibility, so that the triggering of the precooling action is highly matched with the actual demand of the user, and blind precooling is effectively avoided. On the premise of ensuring the stable temperature in the refrigerator when the door is opened, precise energy saving is achieved. BRIEF DESCRIPTION OF DRAWINGS

[0017] The technical solutions and other beneficial effects of the application will become apparent through the following detailed description of the specific embodiments of the application in conjunction with the accompanying drawings.

[0018] Figure 1 The structural schematic diagram of the control method of the refrigerator provided by the application is shown.

[0019] Figure 2 Another flowchart of the control method of the refrigerator provided by the application is shown.

[0020] Figure 3 Another flowchart of the control method of the refrigerator provided by the application is shown.

[0021] Figure 4 The structural schematic diagram of the control device provided by the application is shown.

[0022] Figure 5 The structural schematic diagram of the refrigerator provided by the application is shown. DETAILED DESCRIPTION

[0023] The technical solutions in the embodiments of the application will be described clearly and completely in conjunction with the accompanying drawings in the embodiments of the application. Obviously, the described embodiments are only some of the embodiments of the application, but not all the embodiments. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the application.

[0024] In addition, the terms "first", "second" are only used for description purpose, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features, so that the features with "first" and "second" can explicitly or implicitly include one or more features. In the description of the application, the meaning of "multiple" is two or more, unless otherwise specifically limited.

[0025] The embodiment of the present application provides a refrigerator control method, and an example is shown in the following Figure 1 , Figure 1 The structure diagram of the refrigerator control method provided by the embodiment of the present application. The control method is executed by the controller of the refrigerator, and comprises the following steps S101-S103: Step S101: obtaining historical door opening data of the refrigerator and current time information; It should be noted that the historical door opening data comprises a time stamp of each door opening event in the past period, for example, the past 2-4 weeks. The current time information comprises a week time feature and an intra-day time feature. The week time feature is, for example, the day of the week, which is used to distinguish weekdays, weekends and holidays. The intra-day time feature is, for example, a time period to which the current time belongs, such as morning, noon, evening and midnight.

[0026] Step S102: inputting the historical door opening data and the time information into a door opening prediction model to obtain door opening probability information in a first preset time period in the future; The first preset time period is, for example, 120 minutes in the future. The door opening prediction model is obtained by training a large amount of historical data in advance, and can learn the periodicity of the user's door opening behavior in the week and the day. The door opening probability information is preferably a continuous door opening probability curve, where t is the future time, p(t) represents the predicted probability of the door opening event at t, and the value range is, for example, 0 to 1.

[0027] Step S103: determining whether the refrigerator is controlled to start precooling according to the door opening probability information.

[0028] An example is shown in the following

[0029] The refrigerator control method provided by the embodiment of the present application can more accurately learn the user's usage habit by fusing the time information with periodic characteristics and the historical door opening data, training or calling the door opening prediction model, and generating the door opening probability information reflecting the possibility of door opening in the future period. The precooling decision is made based on the possibility, so that the triggering of the precooling action is highly matched with the actual demand of the user, and the blind precooling is effectively avoided. On the premise of ensuring the stable temperature in the refrigerator when the door is opened, precise energy saving is realized.

[0030] An example is shown in the following Figure 2 , Figure 2Another flowchart of the control method of the refrigerator provided in the embodiments of the present application. The generating of the door opening probability information in step S102 can include the following sub-steps: S1021: processing the historical door opening data to obtain processed target door opening data; Specifically, the processing of the historical door opening data includes bucket statistics and / or smoothing processing of the historical door opening data. For example, 24 hours in a day are divided into multiple time buckets at a fixed interval such as 5 minutes, the number of times or days of door opening in each time bucket in the historical data is counted to obtain an original "time-frequency" distribution; and the above distribution is smoothed, such as using Gaussian filtering or moving average, to eliminate noise and random fluctuations, to form a smooth reference probability curve.

[0031] S1022: determining the corresponding target prediction model according to the current time information.

[0032] Due to the significant difference in the habits of users on weekdays, weekends and holidays, the system can maintain multiple prediction models, such as "weekday model", "weekend model" and "holiday model". The controller selects the corresponding model according to the current date type.

[0033] S1023: inputting the processed target door opening data into the target prediction model, and the model outputs a door opening probability curve in a first preset time period in the future.

[0034] In some embodiments, please refer to Figure 3 , Figure 3 Another flowchart of the control method of the refrigerator provided in the embodiments of the present application. The door opening probability information in the first preset time period in the future is a door opening probability curve in the first preset time period in the future, and the decision making according to the curve in step S103 can include: S1031: determining the highest probability value in the first preset time period in the future according to the door opening probability curve; For example, on the door opening probability curve, the highest probability value and its corresponding predicted time in the first preset time period in the future from the current time are searched, that is, the time point most likely to open the door is determined.

[0035] S1032: determining whether the highest probability value exceeds a preset probability threshold; If the highest probability value does not reach the preset probability threshold, no pre-cooling is performed; if the highest probability value is equal to or exceeds the preset probability threshold, step S1033 is entered.

[0036] S1033: determining the predicted time corresponding to the time when the door opening probability exceeds the preset probability threshold according to the door opening probability curve; Optionally, the predicted time when the preset probability threshold is reached is determined according to a preset function or a lookup table.

[0037] S1034: controlling the refrigerator to start precooling in advance by a second preset time length based on the predicted time.

[0038] The second preset time length is, for example, between 10-30 minutes. It can be understood that the starting time of precooling is a time point that is the second preset time length before the predicted time.

[0039] For how to further intelligently determine the precooling amplitude after determining that precooling is needed, the present application provides the following embodiments. Before controlling the refrigerator to start precooling, the control method further comprises: obtaining temperature data of the refrigerator and working state information of the compressor, the temperature data including the cabinet temperature and / or the ambient temperature; determining a corresponding precooling amplitude based on a preset mapping relationship, a preset probability threshold, the temperature data and the working state information; controlling the refrigerator to perform a precooling operation according to the precooling amplitude.

[0040] The preset mapping relationship can be a function or a multidimensional query table. For example, the higher the prediction probability, the higher the ambient temperature, and the higher the current temperature of the cabinet, the greater the calculated precooling amplitude, meaning that a greater amplitude of cooling is needed to reserve more cold energy. The compressor state can be used to determine whether it can immediately respond to the precooling instruction. Controlling the refrigerator to perform a precooling operation according to the precooling amplitude includes, for example, temporarily lowering the set temperature of the compartment, and the controller will control the compressor and other components to work accordingly until the temporary target temperature is reached or a predetermined time length is reached.

[0041] To improve the adaptability of the system in different scenarios and improve the precooling effect of the refrigerator, before determining whether to control the refrigerator to start precooling according to the door opening probability information, the control method of the refrigerator further comprises: obtaining use scenario information of the refrigerator, the use scenario information including defrosting state, seasonal state and long-term drift state; determining or adjusting at least one of the second preset time length, the preset probability threshold and the preset mapping relationship according to the use scenario information.

[0042] It should be noted that the defrosting state is used to determine whether the refrigerator has just completed defrosting. The seasonal state can be determined by the ambient temperature or the calendar whether it is summer / winter. The long-term drift state can be determined by monitoring long-term running data whether the sensor performance or user habits have changed slowly.

[0043] For example, the preset probability threshold can be appropriately lowered and the second preset time length can be increased in summer; the second preset time length can be slightly increased after defrosting; the prediction model can be triggered to retrain after detecting long-term drift.

[0044] For how to quickly and stably stabilize the temperature in the box after the predicted door opening event actually occurs, the application provides the following embodiments, in addition to determining whether to control the refrigerator to start pre-cooling according to the door opening probability information, the application also comprises: After detecting that the refrigerator door body is opened, temperature rise information of the compartment and door opening information within a third preset time period are obtained. The running parameters of the refrigerator are adjusted according to the temperature rise information and the door opening information.

[0045] The temperature rise information may include, for example, a temperature change rate, an absolute temperature rise value, or other data capable of reflecting the temperature rise situation. The door opening information within the third preset time period may include, for example, a duration of the current door opening, a number of door openings. The running parameters may include, but are not limited to, a compressor duty cycle or a running frequency of the refrigerator, a fan gear, and a damper angle. For example, when the temperature rises quickly and the door is opened for a long time, the compressor power may be increased, or the air speed may be increased to accelerate heat exchange between the air in the box and the evaporator, and the air distribution of each compartment may also be adjusted to concentrate cold air on the compartment with a significant temperature rise.

[0046] Preferably, the temperature rise suppression control is constrained by two parameters, a maximum overshoot and a maximum recovery time period. The maximum overshoot is used to prevent excessive refrigeration from causing the temperature to be too low, and the maximum recovery time period requires the system to stabilize the temperature near the set value within a specified time. In this way, the ability to quickly pull back the temperature in the long door opening or repeated door opening scenario is ensured, and the frequent start-stop and noise mutation of the compressor are suppressed, thereby optimizing the user experience and equipment reliability. For example, a minimum evaporation temperature may be set. In this way, when the system enters the fast temperature rise suppression stage, the compressor duty cycle, the fan gear, the damper angle, and other running parameters may be adjusted according to the temperature rise information and the duration and number of door openings, so as to quickly and smoothly pull back the temperature to the set value under the constraints of the maximum overshoot and the maximum recovery time period.

[0047] In some embodiments, the control method of the refrigerator further comprises a model and parameter updating process, for example, comprising: Actual door opening data and predicted door opening data of a recent cycle of the refrigerator are obtained. An offset between the actual door opening data and the predicted door opening data is determined. If the offset exceeds a preset offset threshold, the door opening prediction model is trained according to the actual door opening data.

[0048] The recent cycle may be, for example, the last week. There are various ways to calculate the offset, for example, comparing the deviation of the peak period of the actual door opening and the peak period of the predicted door opening on the time axis, or calculating the probability of false pre-cooling, i.e., the probability of triggering pre-cooling but the period actually not being opened, or calculating the probability of missed pre-cooling, i.e., the probability of not triggering pre-cooling but the period actually being opened.

[0049] Optionally, the second preset time length, the preset probability threshold, and the preset mapping relationship, and the like control parameters can be updated by rolling optimization based on the recent operation effect evaluation, so that the system continuously adapts to the change of the user habit, and the prediction accuracy is ensured, and the precooling effect is improved.

[0050] The control method of the refrigerator provided in the embodiments of the present application can more accurately learn the use habit rule of the user by fusing the time information with the periodic characteristic and the historical door opening data, and training or calling the door opening prediction model, and the generated door opening probability information reflects the possibility of door opening in the future period. The precooling decision is made based on the possibility, so that the triggering of the precooling action is highly matched with the actual demand of the user, and blind precooling is effectively avoided. Under the premise of ensuring the stable temperature in the refrigerator when the door is opened, precise energy saving is achieved. Moreover, the precooling time and amplitude determined dynamically and the rapid hierarchical inhibition control after the door is opened make the temperature in the refrigerator more stable, the food preservation better, and the user experience better. In addition, the refrigerator of the present application has the parameter self-adjustment and model self-update capabilities, can adapt to the change of the season and the user habit for a long time, maintains the best performance, and at the same time, the operation safety and reliability are ensured through multiple constraints.

[0051] The embodiments of the present application further provide a control device of a refrigerator. For example, refer to Figure 4 , Figure 4 The structural schematic diagram of the control device provided in the embodiments of the present application is shown. The control device 200 includes an acquisition module 210, a prediction module 220, and a control module 230.

[0052] The acquisition module 210 is configured to acquire the historical door opening data of the refrigerator and the current time information. The prediction module is configured to input the historical door opening data and the time information into a door opening prediction model to obtain the door opening probability information in a first preset time length in the future. The control module is configured to determine whether to control the refrigerator to start precooling according to the door opening probability information.

[0053] Optionally, the control device 200 further includes an update module configured to adaptively train and update the prediction model and the control parameters.

[0054] The control device of the refrigerator provided in the embodiments of the present application can more accurately learn the use habit rule of the user by fusing the time information with the periodic characteristic and the historical door opening data, and training or calling the door opening prediction model, and the generated door opening probability information reflects the possibility of door opening in the future period. The precooling decision is made based on the possibility, so that the triggering of the precooling action is highly matched with the actual demand of the user, and blind precooling is effectively avoided. Under the premise of ensuring the stable temperature in the refrigerator when the door is opened, precise energy saving is achieved.

[0055] The embodiments of the present application further provide a refrigerator. For example, refer to Figure 5 ,Figure 5 A structural schematic diagram of a refrigerator is provided in the embodiments of the present application. The refrigerator 300 comprises a detection device 310, a prediction device 320 and a controller 330. The controller 330 is electrically connected with the detection device 310 and the prediction device 320.

[0056] The detection device 310 comprises a sensor for detecting the opening and closing state of the refrigerator door body, and sensors for detecting the ambient temperature and the cabinet temperature. The prediction device 320 is configured with a door opening prediction model. The controller 330 is configured to: acquire historical door opening data of the refrigerator and current time information; input the historical door opening data and the time information into the door opening prediction model to obtain door opening probability information within a first preset time period in the future; and determine whether to control the refrigerator to start pre-cooling according to the door opening probability information.

[0057] The refrigerator provided in the embodiments of the present application can more accurately learn the usage habit of the user by fusing the time information with periodic characteristics and the historical door opening data, training or calling the door opening prediction model, and the generated door opening probability information reflects the possibility of door opening in the future time period. The pre-cooling decision is made based on the possibility, so that the triggering of the pre-cooling action is highly matched with the actual demand of the user, and blind pre-cooling is effectively avoided. On the premise of ensuring the stable temperature in the cabinet when the door is opened, precise energy saving is achieved.

[0058] The embodiments of the present application also provide a storage medium having a computer program stored thereon, and the computer program performs the control method of the refrigerator described above. The integrated modules / units, if realized in the form of software function units and sold or used as independent products, can be stored in a computer readable storage medium. Based on such understanding, the computer program can instruct the relevant hardware to complete all or part of the processes of the above-mentioned embodiments, and the computer program can be stored in a computer readable storage medium, and the computer program can implement the steps of the above-mentioned control method embodiments of the refrigerator when executed by a processor.

[0059] In the above embodiments, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0060] The antenna device provided in the embodiments of the present application has been described in detail, and the principles and implementation manners of the present application are described by applying specific examples. The above description of the embodiments is only used to help understand the technical solutions and core ideas of the present application; those skilled in the art should understand that the technical solutions recorded in the above embodiments can be modified, or some technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A control method of a refrigerator, characterized by, The method comprises: obtaining historical door opening data of the refrigerator and current time information; inputting the historical door opening data and the time information into a door opening prediction model to obtain door opening probability information within a first preset time period in the future; determining whether to control the refrigerator to start pre-cooling according to the door opening probability information. 2.The control method of a refrigerator according to claim 1, characterized in that, The door opening probability information within the first preset time period in the future is a door opening probability curve within the first preset time period in the future, and the determination of whether to control the refrigerator to start pre-cooling according to the door opening probability information comprises: determining a highest probability value within the first preset time period in the future according to the door opening probability curve; controlling the refrigerator to start pre-cooling after determining that the highest probability value exceeds a preset probability threshold. 3.The control method of a refrigerator according to claim 2, characterized in that, The control of the refrigerator to start pre-cooling comprises: determining a predicted time when the door opening probability reaches the preset probability threshold according to the door opening probability curve; and controlling the refrigerator to start pre-cooling in advance by a second preset time period based on the predicted time. 4.The control method of a refrigerator according to claim 3, characterized in that, Before the determination of whether to control the refrigerator to start pre-cooling according to the door opening probability information, the method further comprises: obtaining usage scenario information of the refrigerator, the usage scenario information comprising defrosting state, seasonal state and long-term drift state; determining the second preset time period and / or the preset probability threshold according to the usage scenario information. 5.The control method of a refrigerator according to claim 2, characterized in that, Before the control of the refrigerator to start pre-cooling, the method further comprises: obtaining temperature data of the refrigerator and working state information of a compressor, the temperature data comprising cabinet temperature and / or ambient temperature; determining a corresponding pre-cooling amplitude based on a preset mapping relationship, the preset probability threshold, the temperature data and the working state information; and controlling the refrigerator to perform a pre-cooling operation according to the pre-cooling amplitude.

6. The control method of a refrigerator according to any one of claims 1 to 5, characterized by, After the determination of whether to control the refrigerator to start pre-cooling according to the door opening probability information, the method further comprises: after detecting that a door body of the refrigerator is opened, obtaining temperature rise information of a compartment and door opening information within a third preset time period; adjusting running parameters of the refrigerator according to the temperature rise information and the door opening information.

7. The control method of a refrigerator according to any one of claims 1 to 5, characterized by, The method further comprises: obtaining actual door opening data and predicted door opening data of a recent cycle of the refrigerator; determining an offset between the actual door opening data and the predicted door opening data; and if the offset exceeds a preset offset threshold, training the door opening prediction model according to the actual door opening data.

8. A control device of a refrigerator, characterized by comprising: The method comprises: an obtaining module configured to obtain historical door opening data of the refrigerator and current time information; a prediction module configured to input the historical door opening data and the time information into a door opening prediction model to obtain door opening probability information within a first preset time period in the future; and a control module configured to determine whether to control the refrigerator to start pre-cooling according to the door opening probability information.

9. A refrigerator characterized by comprising: A control method for a refrigerator as claimed in any one of claims 1-7.

10. A storage medium, characterized by A computer program stored thereon, which, when executed, performs a control method for a refrigerator as claimed in any one of claims 1-7. A computer program stored thereon, which, when executed, performs a control method for a refrigerator as claimed in any one of claims 1-7.

Images