Article storage equipment and method for determining working time length of vacuum pump
By setting pressure triggers and performance correction factors in the item storage equipment, combining the ambient air pressure, and using a predictive model to correct the vacuum pump working time under standard conditions, the problem of accurate grasp of the vacuum pump working time is solved, achieving more efficient vacuum control and cost reduction.
Patent Information
- Application Number
- CN202510726947.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-30
- Publication Date
- 2025-09-16
AI Technical Summary
The working time of the vacuum pump in existing storage equipment is difficult to accurately grasp, resulting in insufficient or excessive vacuuming, causing power loss, and high cost of training prediction models in different environments.
By setting a pressure trigger inside the drawer box, combining the vacuum pump's performance correction factor and ambient air pressure, and using a predictive model to calibrate the vacuum pump's operating time under standard conditions, we can ensure that the drawer box reaches the target vacuum level and reduce model training and deployment costs.
This improves the accuracy and reliability of predicting the operating time of the vacuum pump, ensures that the target vacuum level is achieved inside the drawer box, avoids power consumption loss, and reduces the training and deployment costs of the prediction model.
Smart Images

Figure CN120643028A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of household appliance technology, and in particular to a method for determining the working time of an item storage device and a vacuum pump. Background Art
[0002] To ensure the quality of items, specific storage conditions must be provided. Vacuumed storage is an effective method for lowering the air pressure and oxygen content in the storage environment, thereby better preserving items. Therefore, some storage devices (such as refrigerators) are currently equipped with vacuum drawers, which provide a vacuum storage environment for items. The vacuum drawers in storage devices use a vacuum pump to extract air from the drawer box, ensuring that the air inside the drawer meets vacuum conditions.
[0003] However, because the operating time required for a vacuum pump to achieve a vacuum storage environment is affected by a variety of factors, it is difficult to accurately predict the progress and effectiveness of vacuuming during the use of vacuum pumps in storage equipment. This can easily lead to insufficient vacuuming or excessive vacuuming time, resulting in power loss. Therefore, accurately predicting the operating time of vacuum pumps has become an urgent problem that needs to be solved. Summary of the Invention
[0004] The embodiment of the present application discloses a method for determining the working time of an item storage device and a vacuum pump, which can improve the accuracy and reliability of the item storage device in predicting the working time of the vacuum pump.
[0005] In a first aspect, an embodiment of the present application discloses an article storage device, including a vacuum drawer and a controller; the vacuum drawer includes: a drawer box, a vacuum pump, and a pressure trigger;
[0006] The drawer box is configured to store items;
[0007] The vacuum pump is configured to extract air from the drawer box;
[0008] The pressure trigger is disposed inside the drawer box and is configured to output a trigger signal when the air pressure inside the drawer box drops to an air pressure threshold;
[0009] The controller is configured to:
[0010] When the drawer box is in a loaded state, controlling the vacuum pump to evacuate the drawer box;
[0011] When a trigger signal output by the pressure trigger is obtained, determining a first trigger duration corresponding to the pressure trigger, where the first trigger duration is the time from when the vacuum pump starts to evacuate the drawer box to when the pressure trigger outputs the trigger signal;
[0012] Correcting the first trigger duration according to a performance correction factor corresponding to the vacuum pump, an actual ambient pressure corresponding to the item storage device, and a standard ambient pressure to obtain a corrected duration mapped to a standard environment;
[0013] According to the correction time and the target vacuum degree, the corresponding continuous working time of the vacuum pump is determined by a prediction model, and the prediction model is trained based on sample data corresponding to the standard environment.
[0014] In an embodiment of the present application, the controller calibrates the first triggering duration of the pressure triggering member when the drawer box is under load based on the performance calibration factor of the vacuum pump and the actual ambient air pressure and the standard ambient air pressure of the item storage device. The correction of the first triggering duration and mapping it to the standard environment can solve the problem of inaccurate predicted continuous working duration of the vacuum pump caused by the influence of the vacuum pump performance of the item storage device and the actual ambient air pressure on the triggering duration of the pressure triggering member. Since the prediction model is trained based on sample data corresponding to the standard environment, by mapping the first triggering duration to the standard environment, the correction duration is more compatible with the prediction model, thereby making the continuous working duration output by the prediction model more accurate, which can improve the accuracy and reliability of the item storage device's prediction of the vacuum pump working duration, ensure that the environment in the drawer box reaches the target vacuum degree, improve the storage effect of the items, and avoid the vacuum pump working time being too long and increasing power consumption loss. In addition, there is no need to construct prediction models for different environments separately, which improves the generalization of the prediction model and reduces the training cost and deployment cost of the prediction model.
[0015] As an optional implementation manner, in the first aspect of the embodiment of the present application, the controller is configured to:
[0016] The first trigger duration is corrected according to a first ratio between the standard ambient air pressure and the actual ambient air pressure, and the inverse of the performance correction factor, to obtain a corrected duration mapped to the standard environment.
[0017] In this embodiment, based on the first ratio between the standard ambient air pressure and the actual ambient air pressure, and the inverse of the performance correction factor, the first trigger duration in the actual environment can be more accurately mapped to the correction duration under the standard air pressure environment and the standard performance of the vacuum pump, eliminating the influence of different ambient air pressures and vacuum pump performance differences on the prediction of the working time of the vacuum pump, thereby improving the subsequent prediction accuracy of the continued working time of the vacuum pump using the prediction model.
[0018] As an optional implementation manner, in the first aspect of the embodiment of the present application, the controller is further configured to:
[0019] When the drawer box is in an unloaded state, controlling the vacuum pump to evacuate the drawer box;
[0020] When a trigger signal output by the pressure trigger component is obtained, determining a second trigger duration corresponding to the pressure trigger component;
[0021] The performance correction factor corresponding to the vacuum pump is calculated based on the second triggering duration and the standard triggering duration corresponding to the pressure triggering component; the standard triggering duration is the time from when the vacuum pump starts to evacuate the drawer box in an unloaded state to when the pressure triggering component outputs the triggering signal in the standard environment.
[0022] In this embodiment, since the vacuuming process is in a no-load state (there are no items in the drawer box), it only relies on the vacuuming capacity of the vacuum pump itself, and can eliminate interference from the volume and type of items, so that the measured second trigger duration can directly reflect the performance of the vacuum pump; and based on the standard trigger duration corresponding to the pressure trigger component, a reliable reference is provided for accurately measuring the difference between the actual performance of the vacuum pump and the standard performance, thereby obtaining a more accurate performance correction factor for the vacuum pump.
[0023] As an optional implementation manner, in the first aspect of the embodiment of the present application, the controller is further configured to:
[0024] Obtaining location information of the item storage device;
[0025] Based on the correspondence between the position and the ambient air pressure, the actual ambient air pressure corresponding to the position information is obtained.
[0026] In this embodiment, by obtaining the location information of the item storage device and directly deriving the actual ambient pressure based on the correspondence between the location and the ambient pressure, not only can the actual ambient pressure of the location of the item storage device be accurately obtained, but the installation of hardware equipment for measuring the ambient pressure can also be reduced, thereby reducing the manufacturing cost of the item storage device.
[0027] As an optional implementation, in the first aspect of the embodiment of the present application, the object storage device further includes a communication module;
[0028] The communication module is configured to communicate with the server;
[0029] The controller is also configured to:
[0030] An update request is sent to the server through the communication module, wherein the update request is used to instruct the server to obtain the correspondence between the position and the ambient air pressure according to the update request, and send the correspondence between the position and the ambient air pressure to the item storage device.
[0031] In this embodiment, the item storage device sends an update request to the server, which can ensure the timeliness and accuracy of the correspondence between the location stored in the item storage device and the ambient air pressure, thereby ensuring the accuracy of the actual ambient air pressure of the item storage device, and avoiding the problem of deviation in the prediction of the working time of the vacuum pump due to inaccurate actual ambient air pressure.
[0032] As an optional implementation manner, in the first aspect of the embodiment of the present application, the prediction model includes a volume share prediction sub-model and a continuation duration prediction sub-model;
[0033] The controller is further configured to:
[0034] Determining the volume share of the item in the drawer box according to the correction time using the volume share prediction sub-model;
[0035] The volume share and target authenticity output by the volume share prediction sub-model are input into the continuation duration prediction sub-model, and the continuation duration prediction sub-model determines the corresponding continuation duration of the vacuum pump based on the volume share and the target vacuum degree.
[0036] In this implementation, the volume share prediction sub-model is first used to determine the volume share of items in the drawer compartment based on the calibration duration. The continued operation duration prediction sub-model then combines the target vacuum level and volume share to output a continued operation duration tailored to the actual scenario. This ensures that the continued operation duration output by the continued operation duration prediction sub-model is more compatible with the currently stored items, improving storage efficiency. Furthermore, because the calibration duration is mapped to a standard environment, the accuracy of the volume share determined by the volume share prediction sub-model is improved, further enhancing the accuracy of the continued operation duration output by the continued operation duration prediction sub-model.
[0037] As an optional implementation manner, in the first aspect of the embodiment of the present application, the controller is further configured to:
[0038] Converting the continued operating time output by the prediction model according to the performance correction factor, the actual ambient air pressure, and the standard ambient air pressure to obtain the continued operating time of the vacuum pump corresponding to the actual environment;
[0039] The vacuum pump is controlled to evacuate the drawer box according to the continuous working time corresponding to the actual environment.
[0040] In this embodiment, since the prediction model is trained based on sample data of a standard environment, the continued working time output by the prediction model is also the time under the standard environment. The continued working time output by the prediction model is converted through the performance correction factor, the actual ambient air pressure and the standard ambient air pressure. The continued working time under the standard environment can be accurately mapped to the actual environment, so that the converted continued working time is more in line with the actual environmental requirements, thereby ensuring that the vacuum pump can achieve the target vacuum degree in the drawer box during actual vacuuming, thereby ensuring the storage effect of the items.
[0041] As an optional implementation manner, in the first aspect of the embodiment of the present application, the controller is further configured to:
[0042] According to the second ratio between the actual ambient air pressure and the standard ambient air pressure, and the performance correction factor, the continued working time output by the prediction model is converted to obtain the continued working time of the vacuum pump corresponding to the actual environment.
[0043] In this embodiment, based on the second ratio between the actual ambient air pressure and the standard ambient air pressure, and the performance correction factor, the continued working time in the standard environment can be more accurately mapped to the continued working time in the actual environment, eliminating the influence of different ambient air pressures and vacuum pump performance differences on the working time of the vacuum pump, so that the subsequent vacuum pump can complete the vacuum operation in the actual environment, thereby improving the reliability of the item storage equipment in predicting the working time of the vacuum pump.
[0044] As an optional implementation manner, in the first aspect of the embodiment of the present application, the controller is further configured to:
[0045] In response to the selection instruction, obtaining one or more selected item categories;
[0046] A target vacuum level is determined based on the one or more types of items.
[0047] In this embodiment, since different types of items have different requirements for vacuum levels, the target vacuum level can be determined based on one or more selected item types, so that the items stored in the drawer box can be in a suitable vacuum environment to meet the storage needs of different types of items.
[0048] In a second aspect, an embodiment of the present application discloses a method for determining the operating time of a vacuum pump, which is applied to an item storage device, wherein the item storage device includes a vacuum drawer, the vacuum drawer including a drawer box, a vacuum pump, and a pressure trigger; the method includes:
[0049] When the drawer box is in a loaded state, controlling the vacuum pump to evacuate the drawer box;
[0050] When a trigger signal output by the pressure trigger is obtained, a first trigger duration corresponding to the pressure trigger is determined, where the first trigger duration is the time from when the vacuum pump starts to evacuate the drawer box to when the pressure trigger outputs the trigger signal; the trigger signal is output by the pressure trigger when the air pressure in the drawer box drops to an air pressure threshold;
[0051] Correcting the first trigger duration according to a performance correction factor corresponding to the vacuum pump, the actual ambient pressure corresponding to the item storage device, and the standard ambient pressure to obtain a corrected duration mapped to a standard environment;
[0052] According to the correction time and the target vacuum degree, the corresponding continuous working time of the vacuum pump is determined by a prediction model, and the prediction model is trained based on sample data corresponding to the standard environment.
[0053] In an embodiment of the present application, the item storage device calibrates the first triggering duration of the pressure triggering member when the drawer box is under load based on the performance calibration factor of the vacuum pump and the actual ambient air pressure of the item storage device and the standard ambient air pressure. The first triggering duration is corrected and mapped to the standard environment, which can solve the problem of inaccurate predicted continuous working duration of the vacuum pump caused by the influence of the vacuum pump performance of the item storage device and the actual ambient air pressure on the triggering duration of the pressure triggering member. Since the prediction model is trained based on sample data corresponding to the standard environment, by mapping the first triggering duration to the standard environment, the correction duration is more compatible with the prediction model, thereby making the continuous working duration output by the prediction model more accurate, which can improve the accuracy and reliability of the item storage device's prediction of the vacuum pump working duration, ensure that the environment in the drawer box reaches the target vacuum degree, improve the storage effect of the items, and avoid the vacuum pump working time being too long and increasing power consumption loss. In addition, there is no need to construct prediction models for different environments separately, which improves the generalization of the prediction model and reduces the training cost and deployment cost of the prediction model. BRIEF DESCRIPTION OF THE DRAWINGS
[0054] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0055] Figure 1 This is a diagram of an application scenario of an item storage device in one embodiment;
[0056] Figure 2 This is a structural block diagram of an article storage device in one embodiment;
[0057] Figure 3 is a control flow chart of a controller in one embodiment;
[0058] Figure 4 is a control flow chart of a controller in another embodiment;
[0059] Figure 5A is a control flow chart of a controller in yet another embodiment;
[0060] Figure 5B is a schematic diagram of an interface of a user control terminal in one embodiment;
[0061] Figure 6 is a control flow chart of a controller in one embodiment;
[0062] Figure 7 is a structural block diagram of an article storage device in another embodiment;
[0063] Figure 8 is a control flow chart of a controller in one embodiment;
[0064] Figure 9 is a control flow chart of a controller in another embodiment;
[0065] Figure 10 is a control flow chart of a controller in one embodiment;
[0066] Figure 11 is a flow chart of a method for predicting power consumption in one embodiment;
[0067] Figure 12 is a flow chart of a power consumption prediction method according to another embodiment;
[0068] Figure 13 FIG. 4 is a block diagram of a power consumption prediction device in one embodiment. DETAILED DESCRIPTION
[0069] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.
[0070] It should be noted that the terms "including," "having," and any variations thereof in the embodiments and drawings of this application are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to the process, method, product, or apparatus.
[0071] It is understood that the terms "first," "second," and the like used herein may be used to describe various elements herein, but these elements are not limited by these terms. These terms are used solely to distinguish a first element from another element. For example, without departing from the scope of this application, a first trigger duration may be referred to as a second trigger duration, and similarly, a second trigger duration may be referred to as a first trigger duration. The first trigger duration and the second trigger duration may be of the same or different lengths.
[0072] Currently, the industry typically uses fixed artificial intelligence models to predict the operating hours of vacuum pumps in storage equipment. This prediction method has the following drawbacks:
[0073] 1. Due to differences in ambient air pressure caused by regions at different altitudes (such as plateaus and plains) or weather changes in the same region, there is a difference between the actual ambient air pressure of the storage equipment and the air pressure in the calibration environment of the artificial intelligence model. Moreover, in a non-calibrated environment, the operating time of the vacuum pump will be affected by the actual ambient air pressure, resulting in deviations in the prediction of the vacuum pump operating time.
[0074] Second, the vacuum pump performance corresponding to the training data used by the artificial intelligence model is usually fixed. However, during the long-term use of the vacuum pump, the vacuum pump is prone to aging problems, and there are differences in the performance of the vacuum pump. The performance of the vacuum pump will affect the working efficiency of the vacuum pump, and then affect the working time, resulting in deviations in the prediction of the working time of the vacuum pump.
[0075] Third, the operating characteristics of vacuum pumps may vary in different environments (e.g., different altitudes, different climate regions). Therefore, it is necessary to build separate AI models for different environments to predict the operating time of vacuum pumps in different environments. However, multiple different AI models require the collection of a large amount of sample data from different environments and targeted model training and optimization, resulting in high AI training and deployment costs.
[0076] An embodiment of the present application discloses a method for determining the working time of an item storage device and a vacuum pump. By correcting the first trigger time corresponding to the pressure trigger component when the drawer box is loaded, an accurate correction time under a standard environment is obtained, thereby improving the prediction accuracy of the corresponding continued working time of the vacuum pump.
[0077] Figure 1 FIG. 1 is an application scenario diagram of an article storage device in one embodiment. Figure 1 As shown, the power consumption prediction method provided in the embodiment of the present application can be applied to the item storage device 100, which may include but is not limited to refrigerators, vacuum sealers, vacuum preservation jars, vacuum preservation cabinets and other equipment with vacuuming requirements.
[0078] The object storage device 100 may include a vacuum drawer 110 , which may provide a vacuum storage space for storing objects.
[0079] Figure 2 FIG. 1 is a block diagram of an article storage device in one embodiment. Figure 2 As shown, the object storage device 100 may include a vacuum drawer 110 and a controller 120 .
[0080] The vacuum drawer 110 may include a drawer housing 111 , a vacuum pump 112 , and a pressure trigger 113 .
[0081] Taking the item storage device 100 as a refrigerator, for example, the vacuum drawer 110 can be a retractable compartment set in the refrigerator. Suppose a user needs to store a batch of fresh meat in the refrigerator's vacuum drawer 110. The user can pull out the drawer housing 111, place the meat inside the drawer housing 111, and close the drawer housing 111. When the vacuum drawer 110 detects that the drawer housing 111 is closed, the controller 120 controls the vacuum pump 112 to start and begin the vacuum operation. The vacuum pump 112 draws air from the drawer housing 111, reducing the air pressure inside the housing, thereby creating a low-oxygen, sealed storage environment for the meat and extending the shelf life of the meat.
[0082] The drawer box 111 is configured to store items.
[0083] Optionally, the items stored in the drawer box 111 may include but are not limited to fresh ingredients (such as vegetables, fruits, meat, seafood, dairy products, etc.), dry goods (such as nuts, dried fruits, tea, coffee beans, spices, etc.), cooked food and pre-prepared dishes, special items (such as medicines and health products, cosmetics, etc.), and other items that need to be stored in a low-oxygen environment.
[0084] In some embodiments, in order to better store items, the drawer box 111 can provide basic storage conditions for the items, wherein the basic storage conditions may include dry conditions, low temperature conditions, etc.
[0085] Alternatively, the drawer box 111 can be made of a material with good sealing performance, such as a rubber sealing strip, a silicone sealing pad, etc. These sealing materials can prevent moisture from entering the box, maintain a dry environment in the box, and help to vacuum the drawer box 111.
[0086] Specifically, if the item storage device 100 itself has a refrigeration function, such as a refrigerator, the drawer box 111 can be connected to the refrigeration system of the item storage device 100, and the drawer box 111 can be cooled by the refrigeration system to reach a set low temperature; for some relatively independent drawer boxes or small item storage devices, semiconductor refrigeration sheets can be used to achieve cooling by utilizing the Peltier effect after power is applied.
[0087] Optionally, the shape and material of the drawer box 111 are not limited here.
[0088] The vacuum pump 112 is configured to extract air from the drawer box 111 .
[0089] Many items undergo oxidation reactions in the air, causing degradation in quality. For example, the oxidation of fat in fresh meat produces an unpleasant odor, affecting its taste and nutritional value; and the oxidation of metal products causes rust, shortening their service life. The vacuum pump 112 extracts air from the drawer housing 111, reducing the oxygen content within the drawer housing 111 and inhibiting microbial growth and oxidation reactions on the stored items, thereby extending the shelf life of the items and maintaining their original quality and performance.
[0090] The vacuum pump 112 may include but is not limited to a rotary vane vacuum pump, a piston vacuum pump, a vortex vacuum pump, a diaphragm vacuum pump, etc. Different types of vacuum pumps have different principles of air extraction and are suitable for different items. Therefore, the corresponding vacuum pump can be selected according to the items stored in the item storage device 100.
[0091] Taking item storage device 100 as an example, a refrigerator is typically used to store fresh food. Therefore, the vacuum pump used in refrigerators is a diaphragm vacuum pump. A diaphragm vacuum pump achieves vacuum through the reciprocating motion of a diaphragm, changing the volume of the pump chamber. The diaphragm in a diaphragm vacuum pump separates the pump chamber from the drive mechanism, preventing the pumped gas from coming into contact with the pump's lubrication system and other components. Furthermore, diaphragm vacuum pumps require no lubricating oil, eliminating the risk of oil vapor contamination of stored items. They also offer excellent sealing and cleanability.
[0092] The pressure trigger 113 is disposed inside the drawer box 111 . The pressure trigger 113 is configured to output a trigger signal when the air pressure inside the drawer box 111 drops to an air pressure threshold.
[0093] In some embodiments, the pressure trigger 113 typically contains an elastic element (e.g., a spring, a diaphragm) and contacts. When the air pressure within the drawer housing 111 changes, the elastic element deforms accordingly. For example, the diaphragm bends or expands under the action of the air pressure, and this deformation drives the movement of the mechanical structure connected to it.
[0094] For example, inside the drawer housing 111, the elastic element of the pressure trigger 113 is directly exposed to the gas environment and can sense changes in the air pressure inside the drawer housing 111. When the air pressure changes, the elastic element will deform accordingly, and the degree of deformation is proportional to the change in air pressure. The greater the drop in air pressure, the greater the deformation of the diaphragm. When the air pressure drops to a certain level, that is, when the air pressure inside the drawer housing 111 drops to the air pressure threshold, the deformation of the elastic element reaches or exceeds a certain critical value, and the contacts of the pressure trigger 113 will switch, and the originally open contacts will close or the originally closed contacts will open, generating an electrical signal, thereby outputting a trigger signal.
[0095] In some embodiments, the pressure threshold is generally less than 1 standard atmosphere and greater than the target pressure of the drawer box 111 when the vacuum pump 112 finally completes vacuuming. For example, the pressure threshold may be 0.9 standard atmosphere.
[0096] like Figure 3 As shown, the controller 120 is configured to execute the following steps 310 to 340.
[0097] Step 310 : When the drawer box is in a loaded state, control the vacuum pump to evacuate the drawer box.
[0098] The loaded state of the drawer box 111 refers to that items to be stored are placed in the drawer box 111 , and these items occupy the internal space of the box, so that the interior of the box is no longer a simple cavity state.
[0099] Optionally, when the vacuum pump 112 starts to evacuate the drawer box 111 , the initial air pressure in the drawer box 111 is equivalent to the actual ambient air pressure of the object storage device 100 .
[0100] In some embodiments, the object storage device 100 may further include a sealing detection module configured to detect the sealing condition of the drawer box 111 and output a vacuuming signal when it is detected that the drawer box 111 is in a sealed state.
[0101] The drawer box 111 is in a sealed state, which means that there is no obvious gas leakage channel between the drawer box 111 and the external environment, and its air tightness meets certain threshold requirements.
[0102] Optionally, if the airtightness detection module detects that the air pressure change or gas leakage of the drawer box 111 within a period of time (e.g., several minutes) is within a preset threshold range, it can confirm that the drawer box 111 is in a sealed state. For example, in the pressure change detection, the air pressure change within the drawer box 111 within 5 minutes is set as the threshold for the sealed state. If the airtightness detection module detects that the air pressure inside the drawer box 111 drops by more than 0.5 kPa, it is determined that the drawer box 111 is not in a sealed state, and there may be an air leak or the drawer box 111 is not closed.
[0103] The controller 120 may also be configured to control the vacuum pump 112 to evacuate the drawer box 111 when the drawer box 111 is in a loaded state and a vacuuming signal output by the airtightness detection module is obtained.
[0104] Since vacuuming needs to be performed in a relatively closed space, the gas in the space is extracted by a vacuum pump, thereby reducing the air pressure in the space and forming a vacuum environment. If the drawer box 111 is not in a sealed state, that is, the air inside the drawer box 111 can smoothly exchange with the air in the external environment, at this time, even if the vacuum pump 112 evacuates the drawer box 111, the air in the external environment will continue to be replenished into the drawer box 111, filling the gas space extracted by the vacuum pump 112, so that the air pressure in the drawer box 111 can never be reduced to the target vacuum degree. The vacuum pump 112 cannot actually extract the gas in the drawer box 111, which is equivalent to doing useless work. This not only fails to achieve the expected item storage effect, but also causes a waste of energy. Therefore, the controller 120 controls the vacuum pump 112 to evacuate the drawer box 111 only when the drawer box 111 is in a loaded state and obtains the vacuuming signal output by the airtight detection module, thereby ensuring the effective extraction of the vacuum pump 112.
[0105] Step 320: When a trigger signal output by the pressure trigger component is obtained, a first trigger duration corresponding to the pressure trigger component is determined.
[0106] The first triggering duration is the time from when the vacuum pump 112 starts to evacuate the drawer box 111 to when the pressure triggering member 113 outputs a triggering signal.
[0107] The controller 120 obtains the trigger signal output by the pressure trigger 113, indicating that the air pressure in the drawer box 111 has dropped from the actual ambient pressure to the preset pressure threshold, which means that the vacuum pump 112 has successfully extracted part of the gas in the drawer box 111 during operation.
[0108] Taking the item storage device 100 as a refrigerator as an example, assuming that the initial air pressure in the drawer box 111 is 1 standard atmosphere, and the air pressure threshold is set to 0.9 standard atmospheres. After the vacuum pump 112 begins to evacuate the drawer box 111, as the gas is continuously extracted, the air pressure in the drawer box 111 gradually decreases. When the air pressure in the drawer box 111 decreases to 0.9 standard atmospheres, the pressure trigger 113 in the drawer box 111 will output a trigger signal. After the controller 120 receives the trigger signal, it indicates that the air pressure in the drawer box 111 has reached the preset air pressure threshold. The controller 120 can then obtain the first trigger time used for the air pressure in the drawer box 111 to decrease from 1 standard atmosphere to 0.9 standard atmospheres.
[0109] In some embodiments, since the higher the altitude, the lower the air pressure, the actual ambient air pressure may be less than or equal to the air pressure threshold in some high-altitude areas. At this time, the pressure trigger 113 cannot output the trigger signal normally, resulting in the controller 120 being unable to determine the first trigger duration after controlling the vacuum pump 112 to evacuate the drawer box 111, resulting in the inability to predict the subsequent continued working duration of the vacuum pump; therefore, the controller 120 can also be configured to determine the first trigger duration as the default trigger duration if the trigger signal output by the pressure trigger 113 is not obtained within a preset time period after controlling the vacuum pump 112 to evacuate the drawer box 111.
[0110] Optionally, because the actual ambient air pressure of the object storage device 100 is less than or equal to the air pressure threshold, the pressure trigger 113 quickly outputs a trigger signal when the vacuum pump 112 begins to evacuate the drawer box 111. Therefore, the controller 120 may also be configured to determine the first trigger duration as the default trigger duration if a trigger signal output by the pressure trigger 113 is obtained while the vacuum pump 112 is controlling the drawer box 111 to evacuate the drawer box 111.
[0111] Step 330 : Correct the first trigger duration according to the performance correction factor corresponding to the vacuum pump, the actual ambient pressure corresponding to the item storage device, and the standard ambient pressure to obtain a corrected duration mapped to the standard environment.
[0112] When the actual ambient air pressure of the item storage device 100 is different, since the air pressure threshold is a preset fixed value, the vacuum pump performs air extraction under different actual ambient air pressures, causing the time for the air pressure in the drawer box 111 to drop from the actual ambient air pressure to the air pressure threshold to be different. Therefore, the actual ambient air pressure will affect the above-mentioned first trigger duration.
[0113] When the performance of the vacuum pump 112 is different, the efficiency of the vacuum pump 112 in exhausting air is different. Therefore, assuming that the actual ambient air pressure is constant, the time it takes for the air pressure in the drawer box 111 to drop from the actual ambient air pressure to the air pressure threshold due to exhaustion by vacuum pumps 112 with different performances is different. Therefore, the performance of the vacuum pump 112 will affect the above-mentioned first triggering duration.
[0114] In an embodiment of the present application, the controller 120 can obtain the performance correction factor corresponding to the vacuum pump and the actual ambient air pressure, and correct the first trigger duration according to the performance correction factor corresponding to the vacuum pump 112, the actual ambient air pressure corresponding to the item storage device 100, and the standard ambient air pressure to obtain the corrected duration mapped to the standard environment.
[0115] The performance correction factor refers to a coefficient used to correct the deviation between the actual and ideal pumping performance of the vacuum pump 112. As the vacuum pump 112 is used for a longer period of time, its internal parts will experience a certain degree of wear or aging, resulting in a decrease in the pumping performance of the vacuum pump 112. For example, after the blades of the vacuum pump are worn, the pumping capacity is weakened, and this performance degradation needs to be compensated by the performance correction factor. For example, the worse the performance of the vacuum pump 112, the larger the performance correction factor, indicating a greater need for performance compensation; the better the performance of the vacuum pump 112, the smaller the performance correction factor, indicating a less need for performance compensation.
[0116] The actual ambient air pressure refers to the actual ambient air pressure at the location of the item storage device 100. The standard ambient air pressure refers to a pre-set pressure value used as a reference. The standard ambient air pressure can be the air pressure of the item storage device 100 under a standard environment. This standard ambient air pressure can be understood as the calibration environment, that is, the environment corresponding to the training data used by the prediction model. It can also be understood as the air pressure value when the item storage device 100 is tested during equipment manufacturing. For example, the standard ambient air pressure can be taken as 1 standard atmosphere (approximately 101.3 kPa).
[0117] In some embodiments, the standard environment may also be referred to as a calibration environment or a laboratory environment, which refers to the environment in which the object storage device 100 is located during the process of determining the accurate values of the device parameters, performance indicators or working status of the object storage device 100.
[0118] The controller 120 may correct the first trigger duration according to the performance correction factor corresponding to the vacuum pump, the actual ambient pressure corresponding to the item storage device, and the standard ambient pressure to obtain a corrected duration mapped to the standard environment.
[0119] When the performance correction factor is determined (e.g., a performance correction factor of 1 indicates that no performance correction is required), the lower the actual ambient pressure, the shorter the first trigger duration. This means that the first trigger duration in the actual environment is shorter than the trigger duration of the pressure trigger element 113 in the standard environment. Therefore, the correction duration mapped to the standard environment is greater than the first trigger duration. Furthermore, the correction duration mapped to the standard environment may be negatively correlated with the actual ambient pressure; the lower the actual ambient pressure, the greater the correction duration mapped to the standard environment.
[0120] When the actual ambient pressure is determined (e.g., the actual ambient pressure is the standard ambient pressure), the larger the performance correction factor, the worse the performance of the vacuum pump 112, the worse its pumping efficiency, and the longer the first trigger duration. That is, the first trigger duration in the actual environment is longer than the trigger duration of the pressure trigger member 113 in the standard environment. Therefore, the corrected duration obtained by correction is less than the first trigger duration. Furthermore, the corrected duration obtained by correction can be negatively correlated with the performance correction factor, such that the larger the performance correction factor, the smaller the corrected duration obtained by correction.
[0121] In some embodiments, the controller 120 may be configured to correct the first trigger duration according to a first ratio between the standard ambient pressure and the actual ambient pressure and the inverse of the performance correction factor to obtain a corrected duration mapped to the standard environment.
[0122] In some specific embodiments, the controller 120 may be configured to set the standard ambient pressure P 标准环境气压 and the actual ambient pressure P 实际环境气压 The first ratio between the two is multiplied by the inverse of the performance correction factor F and then multiplied by the first trigger time T 第一触发时长 Multiply them to get the correction time T 校正时长 , complete the first trigger duration T 第一触发时长 Specifically, the correction time T can be calculated by formula (1): 校正时长 .
[0123]
[0124] Because the actual ambient air pressure varies at different altitudes, at high altitudes, the actual ambient air pressure is lower, making it easier for vacuum pump 112 to pump air, resulting in a shorter first trigger duration. Meanwhile, at low altitudes, the actual ambient air pressure is higher, making it more difficult for vacuum pump 112 to pump air, resulting in a longer first trigger duration. Therefore, through calibration, the first trigger durations measured at different actual ambient air pressures can be mapped to the standard ambient air pressure to eliminate the impact of different ambient air pressures on the estimated vacuum pump operating time.
[0125] Step 340 : Determine the corresponding continuous working time of the vacuum pump through a prediction model according to the correction time and the target vacuum degree.
[0126] The target vacuum level refers to the vacuum level that is expected to be achieved inside the drawer box 1111 during the storage process, and is usually expressed as an air pressure value. The target vacuum level is less than the air pressure threshold.
[0127] The target vacuum level of the storage device 100 depends on the items stored in the drawer 111. Alternatively, the controller 120 may determine an intersection of vacuum level ranges corresponding to the items stored in the drawer 111 and select a vacuum level within the intersection as the target vacuum level.
[0128] The prediction model can establish a correlation between the correction time and target vacuum degree, and the continued working time of the vacuum pump 112 by learning and analyzing a large amount of sample data. When a new correction time and target vacuum degree value are given, this correlation can be used to predict the corresponding continued working time of the vacuum pump 112.
[0129] The continued operation duration of the vacuum pump 112 refers to the time, after the first trigger duration has elapsed, that the vacuum pump 112 needs to continue operating in order for the air pressure in the drawer housing 111 to reach the target vacuum level from the current state. For example, when the first trigger duration is 10 minutes, the air pressure in the drawer housing 111 has dropped to the air pressure threshold, and the target vacuum level is less than the air pressure threshold. The prediction model calculates that the vacuum pump 112 needs to continue operating for 5 minutes to reach the target vacuum level. These 5 minutes are the continued operation duration of the vacuum pump.
[0130] In some embodiments, the prediction model is trained based on sample data corresponding to a standard environment. The prediction model to be trained can be trained using the sample data corresponding to the standard environment. During the training process, the prediction model continuously adjusts its internal model parameters to minimize the error between the predicted sample duration corresponding to the sample data output by the prediction model and the actual duration, thereby obtaining a trained prediction model.
[0131] Since the prediction model is trained based on sample data corresponding to the standard environment, but there are differences between the actual environment when the item storage device 100 stores items and the standard environment, it is necessary to first map the first trigger duration in the actual environment to the correction duration in the standard environment through the performance correction factor, the actual ambient air pressure and the standard ambient air pressure, so as to eliminate the influence of the ambient air pressure difference and the equipment performance change on the first trigger duration, so that it can reflect the time required for the vacuum pump to reach the same air pressure threshold in the standard environment, and then obtain the accurate continued working time corresponding to the vacuum pump 112 according to the correction duration and the target vacuum degree through the prediction model.
[0132] In an embodiment of the present application, the controller 120 corrects the first triggering time of the pressure triggering member 113 triggered by the drawer box 111 under load according to the performance calibration factor of the vacuum pump and the actual ambient pressure and the standard ambient pressure of the item storage device 100. Correcting the first triggering time and mapping it to the standard environment can solve the problem of inaccurate predicted continued working time of the vacuum pump 112 caused by the influence of the vacuum pump performance of the item storage device 100 and the actual ambient pressure on the triggering time of the pressure triggering member. Since the prediction model is trained based on the sample data corresponding to the standard environment, by mapping the first triggering time to the standard environment, the correction time is more adapted to the prediction model, thereby making the continued working time output by the prediction model more accurate, which can improve the accuracy and reliability of the item storage device 100 in predicting the working time of the vacuum pump, thereby ensuring that the environment in the drawer box 111 reaches the target vacuum degree, improving the storage effect of items, and avoiding the vacuum pump 112 working too long and increasing power consumption loss. In addition, there is no need to build prediction models for different environments, which improves the generalization of the prediction model and reduces the training and deployment costs of the prediction model.
[0133] In some embodiments, the prediction model may include a volume occupancy prediction sub-model and a duration prediction sub-model.
[0134] In some embodiments, as Figure 4 As shown, the controller 120 is further configured to execute the following steps 402 to 404.
[0135] Step 402: Determine the volume share of the items in the drawer according to the calibration duration using the volume share prediction sub-model.
[0136] The volume share prediction sub-model is used to predict the volume share of items stored in the drawer 111 when the air pressure in the drawer 111 reaches the air pressure threshold. The volume share refers to the ratio of the volume of the items stored in the drawer 111 to the total volume of the drawer 111. For example, if the total volume of the drawer is 100 liters and the volume of the items stored is 30 liters, the volume share is 30%.
[0137] During the actual operation of the vacuum pump 112, factors such as the placement of items in the drawer box 111, irregular shapes, and possible slight deformations of the items themselves will affect the direct measurement of the actual space occupied by the items (i.e., the volume of the items). The volume share prediction sub-model is trained based on a large amount of sample data under standard environments. The volume share prediction sub-model is used to determine the volume share of the items in the drawer box 111, which can fully combine the actual dynamic information during the operation of the vacuum pump 112, eliminate measurement errors caused by factors such as item placement, deformation, and air pressure changes, so that the obtained volume share is more accurate and more in line with the actual situation.
[0138] In step 404, the volume share and target authenticity output by the volume share prediction sub-model are input into the continuation time prediction sub-model. The continuation time prediction sub-model determines the corresponding continuation time of the vacuum pump based on the volume share and the target vacuum degree.
[0139] The continuation duration prediction sub-model is used to predict the length of time that the vacuum pump 112 needs to continue running in order for the air pressure in the drawer box 111 to reach the target vacuum level after the correction duration has elapsed.
[0140] The volume ratio reflects the amount of space available for vacuuming in the drawer box 111. When the volume ratio increases, meaning that items occupy more of the box space 111, the remaining space becomes relatively small. The vacuum pump 112 extracts gas from this remaining space to achieve the target vacuum level, requiring less air to be pumped out, resulting in a shorter continuous operation time. Conversely, when the volume ratio is small, the remaining space is large, the air to be pumped out is greater, and the continuous operation time is longer.
[0141] The prediction model is broken down into two sub-models: a volume share prediction model and a duration prediction model. Each sub-model focuses on a specific prediction objective, enabling deeper learning and understanding of the data characteristics associated with that objective, thereby improving the accuracy and expertise of the predictions. For example, the volume share prediction sub-model focuses more on the relationship between the duration of air pressure change and the space occupied by the stored objects, resulting in a more accurate volume share; while the duration prediction sub-model focuses more on the relationship between the speed of air pressure change and the duration of the change, resulting in a more accurate duration of the operation.
[0142] Furthermore, the two sub-models, the volume share prediction model and the duration prediction model, are independent of each other, allowing them to be trained separately, resulting in more accurate training results. If the prediction results of either sub-model are unsatisfactory, it can be optimized and adjusted independently without affecting the use and performance of the other sub-model, eliminating the need for large-scale modifications to the entire prediction model. This reduces the scale of data processing, the complexity of model training, and the cost of adjustment.
[0143] In the embodiment of the present application, the volume share prediction sub-model is first used to determine the volume share of the items in the drawer compartment based on the calibration duration. The continued operation duration prediction sub-model then combines the target vacuum level and volume share to output a continued operation duration tailored to the actual scenario. This ensures that the continued operation duration output by the continued operation duration prediction sub-model is more compatible with the currently stored items, improving the storage efficiency of the items. Furthermore, because the calibration duration is mapped to a standard environment, the accuracy of the volume share determined by the volume share prediction sub-model is improved, further improving the accuracy of the continued operation duration output by the continued operation duration prediction sub-model.
[0144] In some embodiments, as Figure 5A As shown, the controller 120 is further configured to execute the following steps 502 to 506.
[0145] Step 502: When the drawer box is in an unloaded state, control the vacuum pump to evacuate the drawer box.
[0146] The drawer box 111 is in an empty state, which means that there is no object placed in the drawer box 111, that is, the drawer box 111 is a complete air space, and there is no influence of objects on the air pressure, gas distribution and vacuum formation process in the drawer box 111.
[0147] Since there is no interference from any objects in the drawer box 111 when the drawer box 111 is in an unloaded state, the vacuum pump 112 only needs to evacuate the air in the drawer box 111. The performance indicators of the vacuum pump 112, such as the evacuation speed and the time required to reach the pressure threshold, can be more accurately and directly reflected.
[0148] Step 504 : When a trigger signal output by the pressure trigger component is obtained, a second trigger duration corresponding to the pressure trigger component is determined.
[0149] The second triggering duration refers to the duration from when the vacuum pump 112 starts to evacuate the drawer box 111 to when the pressure triggering member 113 outputs a triggering signal when the drawer box 111 is in an unloaded state.
[0150] For the description related to determining the second trigger duration in step 504 , reference may be made to the description related to determining the first trigger duration in step 320 in the above embodiment, which will not be repeated here.
[0151] Step 506 : Calculate a performance correction factor corresponding to the vacuum pump according to the second triggering duration and the standard triggering duration corresponding to the pressure triggering element.
[0152] The standard triggering time is the time from when the vacuum pump 112 starts to evacuate the drawer box 111 in an unloaded state to when the pressure triggering member outputs a triggering signal in a standard environment.
[0153] When the second trigger duration is longer than the standard trigger duration, since the standard trigger duration is relatively fixed, the second trigger duration in the actual environment is longer than the trigger duration of the pressure trigger member 113 in the standard environment. This means that, when the vacuum pump pumps the same amount of gas, the operating duration of the vacuum pump 112 in the actual environment is longer than the operating duration of the vacuum pump 112 in the standard environment. In other words, the vacuum pump 112 has aged. Furthermore, the second trigger duration is proportional to the degree of aging of the vacuum pump 112. The longer the second trigger duration, the higher the degree of aging of the vacuum pump 112, and the more severe the correction required, that is, the larger the performance correction factor.
[0154] In some specific embodiments, the controller 120 may be configured to set the second triggering time T 第二触发时长 With the standard trigger time T 标准触发时长 The ratio of is used as the performance correction factor F corresponding to the vacuum pump 112. Specifically, the performance correction factor F can be calculated using formula (2).
[0155]
[0156] Among them, if F>1, it means that in the actual environment, the time from the start of vacuum pumping to obtaining the trigger signal output by the pressure trigger component is longer than in the standard environment, which means that the vacuum pump 112's pumping speed in actual work slows down and its performance is reduced; if F≤1, it means that the actual pumping speed of the vacuum pump 112 is faster than that in the standard environment, and the performance of the vacuum pump 112 is better.
[0157] In some embodiments, during the manufacture of the object storage device 100, the drawer housing 111 is completely open and empty, with no items placed inside. At this point, the air pressure within the drawer housing 111 is consistent with the external atmospheric pressure, and there are fewer interfering factors. The resistance and other conditions faced by the vacuum pump 112 in this empty state are more stable and easier to quantify, making it easier to calculate the initial performance correction factor. Therefore, the performance correction factor corresponding to the vacuum pump 112 of the object storage device 100 can be calculated based on the second trigger duration of the vacuum pump 112 in the empty state and the standard trigger duration when the object storage device 100 leaves the factory, and stored in the memory chip of the object storage device 100.
[0158] In some embodiments, since the components of the vacuum pump 112 may wear out and age over time, and changes in usage scenarios may also affect the performance of the vacuum pump, the value of the performance correction factor changes dynamically over time. To ensure the accuracy and effectiveness of the performance correction factor, after the object storage device 100 has been used for a target period of time (e.g., 3 months, 6 months, etc., which may be determined based on the device characteristics and usage scenarios), a reminder message may be sent to the user via the device control panel or the app on the user terminal device to remind the user to recalculate the current performance correction factor of the vacuum pump 112.
[0159] Optionally, before resetting the performance correction factor corresponding to the vacuum pump 112 of the item storage device 100, the user may empty the items in the drawer box 111 and operate directly on the control panel of the item storage device 100 by pressing the corresponding reset button on the control panel, or use a terminal device to operate the APP (Application) corresponding to the item storage device 100 on the terminal device to control the item storage device 100 to recalculate the current performance correction factor of the vacuum pump 112.
[0160] Figure 5B This is the display interface of a terminal device in one embodiment. For example, the user can use his own terminal device (such as a mobile phone, tablet computer, etc.) to find and open the APP corresponding to the item storage device 100 on the terminal device. After opening the APP, the user will usually enter the main interface of the device, which will display the basic information, current status, etc. of the device; in the APP main interface or related function menu, the user carefully searches for the function options related to resetting the performance correction factor. Figure 5BAs shown, in display interface 500, the relevant function option area 510 may display text such as "Vacuum Pump Performance Calibration" and "Reset Calibration Factor." A user may touch the relevant function option area 510, and the terminal device may send a reset instruction to the storage device 100, causing the storage device 100 to recalculate the performance calibration factor of the vacuum pump 112. During the calculation process, the app's display area 520 may update and display the calculation progress in real time, allowing the user to remotely monitor the performance calibration factor reset status.
[0161] In the embodiment of the present application, since the vacuuming process is in a no-load state (there are no items in the drawer box), it only relies on the vacuuming capacity of the vacuum pump itself, and can eliminate interference from the volume and type of items, so that the measured second trigger duration can directly reflect the performance of the vacuum pump; and based on the standard trigger duration corresponding to the pressure trigger component, a reliable reference is provided for accurately measuring the difference between the actual performance and the standard performance of the vacuum pump, and a more accurate performance correction factor of the vacuum pump is obtained, thereby accurately correcting the first trigger duration.
[0162] In some embodiments, as Figure 6 As shown, the controller 120 is further configured to execute the following steps 602 to 604.
[0163] Step 602: Acquire location information of the item storage device.
[0164] The location information of the object storage device 100 refers to the physical location of the object storage device 100 on the earth.
[0165] Optionally, in addition to using the common global positioning representation such as longitude and latitude, the location information can also be represented by the relative position of the item storage device in a specific geographical area, such as each city in a certain country.
[0166] In some embodiments, the object storage device 100 can obtain its current location information through network positioning. For example, the object storage device 100 can have a built-in GPS (Global Positioning System) receiver module. By receiving signals from multiple GPS satellites and using the principle of triangulation, it can calculate the distance between the object storage device and the satellites, thereby determining the object storage device's exact location on the earth.
[0167] Step 604 : Based on the correspondence between the position and the ambient air pressure, obtain the actual ambient air pressure corresponding to the position information.
[0168] The correspondence between location and ambient air pressure refers to the correlation between different geographical locations and the actual ambient air pressure at the locations.
[0169] Optionally, the item storage device 100 may obtain the correspondence between locations and ambient air pressures around the world through a professional meteorological data platform.
[0170] In some embodiments, the controller 120 is further configured to obtain current season information; and based on the correspondence between the position, season and ambient air pressure, obtain the actual ambient air pressure corresponding to the position information and monsoon information.
[0171] Among them, seasonal information includes not only the four seasons of the year, but also seasonal climate, such as dry season / rainy season, sandstorm season, typhoon season, Mediterranean climate, marine climate, etc.
[0172] Due to seasonal shifts in the sun's direct point on the Earth's surface, global atmospheric circulation patterns change. These shifts can lead to significant differences in air pressure distribution within the same region during different seasons. By combining geographic location with seasonal factors, we can more accurately simulate and predict seasonal changes in ambient air pressure at different locations, thereby obtaining a more accurate estimate of the actual ambient air pressure within the object storage device 100.
[0173] In an embodiment of the present application, the controller 120 obtains the location information of the item storage device 100 and directly derives the actual ambient pressure based on the correspondence between the location and the ambient pressure. This not only accurately obtains the actual ambient pressure at the location of the item storage device 100, but also reduces the installation of hardware equipment for measuring the ambient pressure, thereby reducing the manufacturing cost of the item storage device 100.
[0174] Figure 7 FIG. 1 is a block diagram of an article storage device in one embodiment. Figure 7 As shown, the object storage device 100 may include a vacuum drawer 110 , a controller 120 , and a communication module 130 .
[0175] The communication module 130 is configured to communicate with the server.
[0176] Optionally, the server 700 connected to the communication module 130 may be a meteorological server, which can provide a correspondence between the location of each location and the ambient air pressure.
[0177] In some embodiments, as Figure 8 As shown, the controller 120 is further configured to perform the following steps 802 .
[0178] Step 802: Send an update request to the server through the communication module.
[0179] The update request is used to instruct the server to obtain the correspondence between the position and the ambient air pressure according to the update request, and send the correspondence between the position and the ambient air pressure to the item storage device.
[0180] In some embodiments, after the server 700 receives the update request sent by the item storage device 100 through the communication module 130, it can query the database of the correspondence between the position and the ambient air pressure stored internally in the server 700, and send the latest correspondence between the position and the ambient air pressure to the item storage device 100, so that the controller 120 of the item storage device 100 can obtain the actual ambient air pressure corresponding to the location information of the item storage device 100 based on the latest correspondence between the position and the ambient air pressure, and the actual ambient air pressure is closer to and more realistic than the air pressure around the current item storage device 100.
[0181] In an embodiment of the present application, the item storage device 100 can ensure the timeliness and accuracy of the correspondence between the location stored in the item storage device 100 and the ambient air pressure by sending an update request to the server, thereby ensuring the accuracy of the actual ambient air pressure of the item storage device 100, and avoiding the problem of deviation in the prediction of the working time of the vacuum pump due to inaccurate actual ambient air pressure.
[0182] In some embodiments, as Figure 9 As shown, the controller 120 is further configured to execute the following steps 902 to 904.
[0183] Step 902 : converting the continuous working time output by the prediction model according to the performance correction factor, the actual ambient air pressure, and the standard ambient air pressure to obtain the continuous working time corresponding to the vacuum pump and the actual environment.
[0184] Since the prediction model is trained based on sample data corresponding to a standard environment, however, in actual applications, the ambient air pressure of the item storage device 100 and the performance of the vacuum pump 112 are often different from those in the standard environment. Therefore, it is necessary to convert the continued working time output by the prediction model in a standard environment back to the actual environment.
[0185] In some embodiments, the controller 120 can also be configured to convert the continued working time output by the prediction model based on a second ratio between the actual ambient air pressure and the standard ambient air pressure, and a performance correction factor, to obtain the continued working time corresponding to the vacuum pump in the actual environment.
[0186] When the performance correction factor is determined (e.g., a performance correction factor of 1 indicates that no performance correction is required), the operating time of vacuum pump 112 in the actual environment is shorter than the operating time of vacuum pump 112 in the standard environment as the actual ambient pressure decreases. Therefore, the continued operating time after switching to the actual environment is shorter than the continued operating time output by the prediction model. Furthermore, the continued operating time after switching to the actual environment may be positively correlated with the actual ambient pressure; the lower the actual ambient pressure, the shorter the continued operating time after switching to the actual environment.
[0187] When the actual ambient pressure is determined (e.g., the actual ambient pressure is the standard ambient pressure), the larger the performance correction factor, the worse the performance of the vacuum pump 112, and the worse its vacuum efficiency in the actual environment. Therefore, the corresponding continuous operation time of the vacuum pump 112 in the actual environment is longer than the continuous operation time output by the prediction model in the standard environment. Furthermore, the continuous operation time in the actual environment may be positively correlated with the performance correction factor, such that the larger the performance correction factor, the longer the continuous operation time in the actual environment.
[0188] In some specific embodiments, the controller 120 may be configured to convert the actual ambient air pressure P 实际环境气压 With standard ambient pressure P 标准环境气压 The second ratio between them is multiplied by the performance correction factor F and then multiplied by the continued working time T output by the prediction model. 预测继续工作时长 Multiply them to get the continuous working time T of the vacuum pump corresponding to the actual environment 实际继续工作时长 Specifically, the vacuum pump's continuous working time T corresponding to the actual environment can be calculated by formula (3): 实际继续工作时长 .
[0189]
[0190] Step 904: Control the vacuum pump to evacuate the drawer box according to the continuous working time corresponding to the actual environment.
[0191] In an embodiment of the present application, based on the second ratio between the actual ambient air pressure and the standard ambient air pressure, and the performance correction factor, the continued working time in the standard environment can be more accurately mapped to the continued working time in the actual environment, eliminating the influence of different ambient air pressures and vacuum pump performance differences on the working time of the vacuum pump, so that the subsequent vacuum pump can complete the vacuum operation in the actual environment, thereby improving the reliability of the item storage equipment in predicting the working time of the vacuum pump.
[0192] In some embodiments, as Figure 10 As shown, the controller 120 is further configured to execute the following steps 1002 to 1004.
[0193] Step 1002: In response to a selection instruction, obtain one or more selected item categories.
[0194] The selection instruction refers to a signal sent by the user to the object storage device 100 to specify the type of object corresponding to the object stored in the drawer box 111.
[0195] In some embodiments, the control panel of the storage device 100 may display a series of touchable controls, each corresponding to a different item category. A user may touch a corresponding control to initiate a selection. For example, a user may touch a control labeled "Fresh Ingredients," and the controller 120 may determine that the items stored in the drawer 111 are of the fresh ingredient category.
[0196] Optionally, the user may select the item category corresponding to the items stored in the drawer box 111 through an APP corresponding to the item storage device 100 on the terminal device.
[0197] In some embodiments, the item categories corresponding to an item may include major categories and minor categories. Major categories refer to broad classifications of items based on some common characteristics of the items, such as fresh food, dry goods, prepared food, and specialty items. Minor categories refer to more detailed classifications of items that can more accurately reflect the characteristics of the items, such as seafood, vegetables, fruits, meat, tea, spices, health products, cosmetics, etc.
[0198] In some embodiments, the object storage device 100 may further include an image acquisition module. The image acquisition module is configured to capture images of the objects stored in the drawer to obtain object images. The controller 120 is further configured to identify the types of objects in the object images based on the object images captured by the image acquisition module to determine one or more types of objects stored in the drawer.
[0199] Optionally, the controller 120 can also be configured to, when no selection instruction is received, identify the type of item in the item image based on the item image captured by the image acquisition module, and determine one or more types of items stored in the drawer box, so that the controller 120 can automatically obtain the type of item stored in the drawer box 111, thereby automatically adjusting the target vacuum degree of the item storage device 100, which can improve the operational convenience and intelligence of the item storage device 100.
[0200] Step 1004 : Determine a target vacuum level based on one or more types of items.
[0201] In some embodiments, if there are multiple types of items, the controller 120 may determine a target vacuum range corresponding to each type of item, and find a target vacuum degree that can simultaneously meet the storage requirements of most types of items by finding the intersection of these target vacuum ranges.
[0202] Optionally, if there are multiple types of items, the controller 120 can also determine the value corresponding to each type of item, and based on the value corresponding to each type of item, use the target vacuum degree corresponding to the highest-valued type of item as the target vacuum degree of the item storage device 100, so as to prioritize the storage effect of high-value items, thereby reducing economic losses caused by improper storage.
[0203] Optionally, the user may directly input the target vacuum degree through the control panel of the object storage device 100 or the APP of the terminal device.
[0204] In some embodiments, if no selection instruction is detected, that is, the user does not select an item type or directly input a target vacuum level, the controller 120 may obtain historical storage data and determine the target vacuum level based on the historical storage data.
[0205] Specifically, the controller 120 can select the target vacuum degree corresponding to the last time the item storage device 100 stored items from the historical storage data, or it can select the target vacuum degree corresponding to the type of item stored the most times in the historical storage data. In this way, without explicit user instructions, the controller 120 can use the historical storage data as a reference to quickly determine a relatively appropriate target vacuum degree, thereby ensuring the basic operation of the item storage device 100 and the storage quality of the items, while also reducing the complexity of user operations.
[0206] In the embodiment of the present application, since different types of items have different requirements for vacuum levels, the target vacuum level can be determined based on one or more selected types of items, so that the items stored in the drawer box can be in a suitable vacuum environment to meet the storage needs of different types of items.
[0207] like Figure 11 In one embodiment, a method for calculating the operating time of a vacuum pump is provided, which can be applied to the aforementioned object storage device. The object storage device includes a vacuum drawer, which includes a drawer body, a vacuum pump, and a pressure trigger. The method may include the following steps 1110 to 1140.
[0208] Step 1110: When the drawer box is in a loaded state, control the vacuum pump to evacuate the drawer box.
[0209] Step 1120, when the trigger signal output by the pressure trigger component is obtained, the first trigger duration corresponding to the pressure trigger component is determined. The first trigger duration is the duration from the vacuum pump starting to evacuate the drawer box to the pressure trigger component outputting the trigger signal; the trigger signal is output by the pressure trigger component when the air pressure in the drawer box drops to the air pressure threshold.
[0210] Step 1130 , correcting the first trigger duration according to the performance correction factor corresponding to the vacuum pump, the actual ambient pressure corresponding to the item storage device, and the standard ambient pressure to obtain a corrected duration mapped to the standard environment.
[0211] Step 1140 , based on the calibration time and the target vacuum degree, the corresponding continuous working time of the vacuum pump is determined by a prediction model, where the prediction model is trained based on sample data corresponding to a standard environment.
[0212] In some embodiments, the step of correcting the first trigger duration according to the performance correction factor corresponding to the vacuum pump, the actual ambient air pressure corresponding to the item storage device, and the standard ambient air pressure to obtain the corrected duration mapped to the standard environment includes: correcting the first trigger duration according to a first ratio between the standard ambient air pressure and the actual ambient air pressure, and the inverse of the performance correction factor to obtain the corrected duration mapped to the standard environment.
[0213] In some embodiments, the above method also includes: when the drawer box is in an unloaded state, controlling the vacuum pump to evacuate the drawer box; when a trigger signal output by the pressure trigger is obtained, determining the second trigger duration corresponding to the pressure trigger; according to the second trigger duration and the standard trigger duration corresponding to the pressure trigger, calculating the performance correction factor corresponding to the vacuum pump; the standard trigger duration is the time from the vacuum pump starting to evacuate the drawer box in an unloaded state to the pressure trigger outputting the trigger signal in a standard environment.
[0214] In some embodiments, the above method further includes: obtaining location information of the item storage device; and obtaining the actual ambient air pressure corresponding to the location information based on the corresponding relationship between the location and the ambient air pressure.
[0215] In some embodiments, the above method also includes: sending an update request to the server through the communication module, the update request is used to instruct the server to obtain the correspondence between the position and the ambient air pressure according to the update request, and send the correspondence between the position and the ambient air pressure to the item storage device.
[0216] In some embodiments, the steps include determining the corresponding continued working time of the vacuum pump through a prediction model based on the correction time and the target vacuum degree, including: determining the volume ratio of the items in the drawer box based on the correction time through a volume ratio prediction sub-model; inputting the volume ratio and target truth output by the volume ratio prediction sub-model into the continued working time prediction sub-model, and determining the corresponding continued working time of the vacuum pump based on the volume ratio and the target vacuum degree through the continued working time prediction sub-model.
[0217] In some embodiments, the above method also includes: converting the continued working time output by the prediction model according to the performance correction factor, the actual ambient air pressure and the standard ambient air pressure to obtain the continued working time of the vacuum pump corresponding to the actual environment; controlling the vacuum pump to evacuate the drawer box according to the continued working time corresponding to the actual environment.
[0218] Optionally, the step converts the continued working time output by the prediction model according to the performance correction factor, the actual ambient air pressure and the standard ambient air pressure to obtain the continued working time of the vacuum pump corresponding to the actual environment, including: converting the continued working time output by the prediction model according to the second ratio between the actual ambient air pressure and the standard ambient air pressure, and the performance correction factor to obtain the continued working time of the vacuum pump corresponding to the actual environment.
[0219] In some embodiments, the method further includes: obtaining one or more selected item categories in response to a selection instruction; and determining a target vacuum degree based on the one or more item categories.
[0220] In some specific embodiments, Figure 12 As shown, the calculation of the actual continuous working time of the vacuum pump may include the following steps.
[0221] When the drawer box is in an empty state, the controller of the article storage device obtains the second triggering time T from when the vacuum pump starts to evacuate the drawer box to when the pressure triggering member outputs the triggering signal. 第二触发时长 , and the standard triggering time T when the drawer box is in an empty state 标准触发时长 , the performance correction factor F of the vacuum pump is calculated according to the above formula (2).
[0222] When the drawer box is in a loaded state, the controller of the article storage device obtains the first triggering time T from when the vacuum pump starts to evacuate the drawer box to when the pressure triggering member outputs a triggering signal. 第一触发时长 , and standard ambient pressure P 标准环境气压 ; and obtain the address of the item storage device, and determine the actual ambient pressure P of the item storage device based on the correspondence between the location and the ambient pressure 实际环境气压 ; According to the above formula (1), the correction time T is calculated校正时长 .
[0223] The volume share prediction sub-model is used according to the correction time T 校正时长 , determine the volume ratio V of the items in the drawer box; input the volume ratio V and the target truth B into the continuation time prediction sub-model, and determine the corresponding continuation time T of the vacuum pump through the continuation time prediction sub-model. 预测继续工作时长 ; And according to the above formula (3), the continuous working time T of the vacuum pump corresponding to the actual environment is calculated 实际继续工作时长 .
[0224] For example, assuming that the pressure in the drawer box drops to 0.9 standard atmospheric pressure, the pressure trigger outputs a trigger signal; the target vacuum degree B is 0.75 standard atmospheric pressure; T 第二触发时长 =120s; T 标准触发时长 =100s;P 标准环境气压 is one standard atmospheric pressure; P 实际环境气压 is 0.95 standard atmospheres; T 第一触发时长 =120s. Then according to the above formula (2), the performance correction factor of the vacuum pump is calculated as F = 120 / 100 = 1.2; according to the above formula (1), The volume ratio prediction sub-model yields V = 30%; the duration prediction sub-model yields T 预测继续工作时长 =200s; calculated according to the above formula (3)
[0225] In an embodiment of the present application, the item storage device 100 corrects the first triggering duration of the pressure triggering member 113 triggered by the drawer box 111 under load based on the performance calibration factor of the vacuum pump 112 and the actual ambient pressure and the standard ambient pressure of the item storage device 100. Correcting the first triggering duration and mapping it to the standard environment can solve the problem of inaccurate predicted continued working duration of the vacuum pump 112 due to the influence of the vacuum pump performance of the item storage device 100 and the actual ambient pressure on the triggering duration of the pressure triggering member 113. Since the prediction model is trained based on sample data corresponding to the standard environment, by mapping the first triggering duration to the standard environment, the correction duration is more adapted to the prediction model, thereby making the continued working duration output by the prediction model more accurate, which can improve the accuracy and reliability of the item storage device 100 in predicting the working duration of the vacuum pump 112, thereby ensuring that the environment in the drawer box 111 reaches the target vacuum degree, improving the storage effect of items, and avoiding the vacuum pump 112 working for too long and increasing power consumption loss. In addition, there is no need to build prediction models for different environments, which improves the generalization of the prediction model and reduces the training and deployment costs of the prediction model.
[0226] like Figure 13 As shown, in one embodiment, a vacuum pump operating duration determination device 1300 is provided, which can be applied to the above-mentioned item storage device. The vacuum pump operating duration determination device 1300 may include a vacuum pump control module 1310, a trigger duration determination module 1320, a duration correction module 1330, and an operating duration determination module 1340.
[0227] The vacuum pump control module 1310 is used to control the vacuum pump to evacuate the drawer box when the drawer box is in a loaded state.
[0228] The trigger duration determination module 1320 is used to determine the first trigger duration corresponding to the pressure trigger component when a trigger signal output by the pressure trigger component is obtained. The first trigger duration is the duration from the vacuum pump starting to evacuate the drawer box to the pressure trigger component outputting a trigger signal; the trigger signal is output by the pressure trigger component when the air pressure in the drawer box drops to the air pressure threshold.
[0229] The duration correction module 1330 is configured to correct the first trigger duration according to the performance correction factor corresponding to the vacuum pump, the actual ambient pressure corresponding to the item storage device, and the standard ambient pressure, to obtain a corrected duration mapped to the standard environment.
[0230] The working time determination module 1340 is used to determine the corresponding continuous working time of the vacuum pump based on the correction time and the target vacuum degree through a prediction model, where the prediction model is trained based on sample data corresponding to a standard environment.
[0231] In some embodiments, the duration correction module 1330 is further used to correct the first trigger duration based on a first ratio between the standard ambient air pressure and the actual ambient air pressure, and the inverse of the performance correction factor, to obtain a corrected duration mapped to the standard environment.
[0232] In some embodiments, the device 1300 for determining the operating duration of the vacuum pump may further include a correction factor determination module.
[0233] The correction factor determination module is used to control the vacuum pump to evacuate the drawer box when the drawer box is in an unloaded state; when the trigger signal output by the pressure trigger is obtained, the second trigger duration corresponding to the pressure trigger is determined; according to the second trigger duration and the standard trigger duration corresponding to the pressure trigger, the performance correction factor corresponding to the vacuum pump is calculated; the standard trigger duration is the time from the vacuum pump starting to evacuate the drawer box in an unloaded state in a standard environment to the pressure trigger outputting the trigger signal.
[0234] In some embodiments, the device 1300 for determining the operating time of a vacuum pump may further include an ambient pressure determination module and a communication module.
[0235] The ambient air pressure determination module is used to obtain the location information of the item storage device; based on the corresponding relationship between the location and the ambient air pressure, obtain the actual ambient air pressure corresponding to the location information.
[0236] The communication module is used to communicate with the server.
[0237] Optionally, the ambient pressure determination module is also used to send an update request to the server through the communication module, and the update request is used to instruct the server to obtain the correspondence between the position and the ambient pressure according to the update request, and send the correspondence between the position and the ambient pressure to the item storage device.
[0238] In some embodiments, the working time determination module 1340 is also used to determine the volume share of the items in the drawer box according to the correction time through the volume share prediction sub-model; the volume share and target authenticity output by the volume share prediction sub-model are input into the continuation time prediction sub-model, and the continuation time prediction sub-model is used to determine the corresponding continuation time of the vacuum pump according to the volume share and the target vacuum degree.
[0239] In some embodiments, the working time determination module 1340 is also used to convert the continued working time output by the prediction model according to the performance correction factor, the actual ambient air pressure and the standard ambient air pressure to obtain the continued working time of the vacuum pump corresponding to the actual environment; and control the vacuum pump to evacuate the drawer box according to the continued working time corresponding to the actual environment.
[0240] Optionally, the working time determination module 1340 is also used to convert the continued working time output by the prediction model based on a second ratio between the actual ambient air pressure and the standard ambient air pressure, and a performance correction factor, to obtain the continued working time of the vacuum pump corresponding to the actual environment.
[0241] In some embodiments, the device 1300 for determining the operating time of the vacuum pump may further include a target vacuum degree determination module.
[0242] The target vacuum degree determination module is configured to obtain one or more selected item categories in response to a selection instruction and determine a target vacuum degree based on the one or more item categories.
[0243] In an embodiment of the present application, the item storage device calibrates the first triggering duration of the pressure triggering member when the drawer box is under load based on the performance calibration factor of the vacuum pump and the actual ambient air pressure of the item storage device and the standard ambient air pressure. The first triggering duration is corrected and mapped to the standard environment, which can solve the problem of inaccurate predicted continuous working duration of the vacuum pump caused by the influence of the vacuum pump performance of the item storage device and the actual ambient air pressure on the triggering duration of the pressure triggering member. Since the prediction model is trained based on sample data corresponding to the standard environment, by mapping the first triggering duration to the standard environment, the correction duration is more compatible with the prediction model, thereby making the continuous working duration output by the prediction model more accurate, which can improve the accuracy and reliability of the item storage device's prediction of the vacuum pump working duration, ensure that the environment in the drawer box reaches the target vacuum degree, improve the storage effect of the items, and avoid the vacuum pump working time being too long and increasing power consumption loss. In addition, there is no need to construct prediction models for different environments separately, which improves the generalization of the prediction model and reduces the training cost and deployment cost of the prediction model.
[0244] An embodiment of the present application discloses a computer-readable storage medium storing a computer program, wherein the computer program implements the methods described in the above embodiments when executed by a processor.
[0245] The embodiments of the present application disclose a computer program product, including a computer program, and the computer program can be executed by a processor to implement the methods described in the above embodiments.
[0246] It should be understood that the references to "one embodiment" or "an embodiment" throughout the specification mean that the specific features, structures, or characteristics associated with the embodiment are included in at least one embodiment of the present application. Therefore, the references to "in one embodiment" or "in an embodiment" throughout the specification do not necessarily refer to the same embodiment. In addition, these specific features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. Those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required for the present application.
[0247] In the various embodiments of the present application, it should be understood that the size of the serial numbers of the above-mentioned processes does not necessarily mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
[0248] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0249] The above describes in detail the article storage device and the method for determining the operating time of a vacuum pump disclosed in the embodiments of this application. Specific examples are used herein to illustrate the principles and implementation methods of this application. The description of the above embodiments is intended only to help understand the method and core concept of this application. At the same time, those skilled in the art will find that the specific implementation methods and scope of application may vary based on the concepts of this application. In summary, the contents of this specification should not be construed as limiting this application.
Claims
1. An article storage device, characterized in that: The article storage device includes a vacuum drawer and a controller: The vacuum drawer comprises: a drawer box, a vacuum pump and a pressure trigger; The drawer box is configured to store items; The vacuum pump is configured to extract air from the drawer box; The pressure trigger is disposed inside the drawer box and is configured to output a trigger signal when the air pressure inside the drawer box drops to an air pressure threshold; The controller is configured to: When the drawer box is in a loaded state, controlling the vacuum pump to evacuate the drawer box; When a trigger signal output by the pressure trigger is obtained, determining a first trigger duration corresponding to the pressure trigger, where the first trigger duration is the time from when the vacuum pump starts to evacuate the drawer box to when the pressure trigger outputs the trigger signal; Correcting the first trigger duration according to a performance correction factor corresponding to the vacuum pump, an actual ambient pressure corresponding to the item storage device, and a standard ambient pressure to obtain a corrected duration mapped to a standard environment; According to the correction time and the target vacuum degree, the corresponding continuous working time of the vacuum pump is determined by a prediction model, and the prediction model is trained based on sample data corresponding to the standard environment.
2. The article storage device according to claim 1, characterized in that: The controller is configured to: The first trigger duration is corrected according to a first ratio between the standard ambient air pressure and the actual ambient air pressure, and the inverse of the performance correction factor, to obtain a corrected duration mapped to the standard environment.
3. The article storage device according to claim 1, characterized in that: The controller is further configured to: When the drawer box is in an unloaded state, controlling the vacuum pump to evacuate the drawer box; When a trigger signal output by the pressure trigger component is obtained, determining a second trigger duration corresponding to the pressure trigger component; The performance correction factor corresponding to the vacuum pump is calculated based on the second triggering duration and the standard triggering duration corresponding to the pressure triggering component; the standard triggering duration is the time from when the vacuum pump starts to evacuate the drawer box in an unloaded state to when the pressure triggering component outputs the triggering signal in the standard environment.
4. The article storage device according to claim 1, characterized in that: The controller is further configured to: Obtaining location information of the item storage device; Based on the correspondence between the position and the ambient air pressure, the actual ambient air pressure corresponding to the position information is obtained.
5. The article storage device according to claim 4, characterized in that: The article storage device further includes a communication module; The communication module is configured to communicate with the server; The controller is also configured to: An update request is sent to the server through the communication module, wherein the update request is used to instruct the server to obtain the correspondence between the position and the ambient air pressure according to the update request, and send the correspondence between the position and the ambient air pressure to the item storage device.
6. The article storage device according to claim 1, characterized in that: The prediction model includes a volume share prediction sub-model and a continuation duration prediction sub-model; The controller is further configured to: Determining the volume share of the item in the drawer box according to the correction time using the volume share prediction sub-model; The volume share and target authenticity output by the volume share prediction sub-model are input into the continuation duration prediction sub-model, and the continuation duration prediction sub-model determines the corresponding continuation duration of the vacuum pump based on the volume share and the target vacuum degree.
7. The article storage device according to claim 1, characterized in that: The controller is further configured to: Converting the continued operating time output by the prediction model according to the performance correction factor, the actual ambient air pressure, and the standard ambient air pressure to obtain the continued operating time of the vacuum pump corresponding to the actual environment; The vacuum pump is controlled to evacuate the drawer box according to the continuous working time corresponding to the actual environment.
8. The article storage device according to claim 7, characterized in that: The controller is further configured to: According to the second ratio between the actual ambient air pressure and the standard ambient air pressure, and the performance correction factor, the continued working time output by the prediction model is converted to obtain the continued working time of the vacuum pump corresponding to the actual environment.
9. The article storage device according to any one of claims 1 to 8, characterized in that: The controller is further configured to: In response to the selection instruction, obtaining one or more selected item categories; A target vacuum level is determined based on the one or more types of items.
10. A method for determining the working time of a vacuum pump, characterized in that: Applied to an item storage device, the item storage device includes a vacuum drawer, the vacuum drawer includes a drawer box, a vacuum pump, and a pressure trigger; the method includes: When the drawer box is in a loaded state, controlling the vacuum pump to evacuate the drawer box; When a trigger signal output by the pressure trigger is obtained, a first trigger duration corresponding to the pressure trigger is determined, where the first trigger duration is the time from when the vacuum pump starts to evacuate the drawer box to when the pressure trigger outputs the trigger signal; the trigger signal is output by the pressure trigger when the air pressure in the drawer box drops to an air pressure threshold; Correcting the first trigger duration according to a performance correction factor corresponding to the vacuum pump, the actual ambient pressure corresponding to the item storage device, and the standard ambient pressure to obtain a corrected duration mapped to a standard environment; According to the correction time and the target vacuum degree, the corresponding continuous working time of the vacuum pump is determined by a prediction model, and the prediction model is trained based on sample data corresponding to the standard environment.