A refrigerator muting method

Abstract

The application provides a refrigerator mute method, which is applied to a mute refrigerator, the mute refrigerator comprises a mute mode and a normal mode, and the method comprises the following steps: acquiring real-time range data of a front preset area of a door body of the mute refrigerator; generating a detection result according to the real-time range data, the detection result is used to indicate whether a moving object is close to or far away from the mute refrigerator; and generating a control instruction according to the detection result, the control instruction is used to drive the mute refrigerator to operate in the mute mode or the normal mode. The application solves the problem that the existing refrigerator mute technology cannot simultaneously meet the refrigeration and mute requirements.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of smart home, in particular to a refrigerator mute method. BACKGROUND

[0002] Refrigerator noise, as one of the key indicators to measure the performance and user experience of the refrigerator, has long been the focus of consumers. With the rapid progress of technology, the electronic components inside the refrigerator have undergone significant technological upgrades, and the iterative updates of the intelligent control system have brought revolutionary changes to the energy efficiency and mute performance of the refrigerator. In recent years, major refrigerator manufacturers have claimed that the noise value of their products is decreasing year by year, which is not only due to the progress of material science, which makes the refrigerator body structure more solid and the sound insulation effect better, but also due to the continuous optimization of motor technology and variable frequency control strategy, which makes the compressor and fan run more smoothly and efficiently.

[0003] In order to meet the user's demand for an extremely quiet environment during a specific period, high-end refrigerators on the current market are generally equipped with an intelligent mute period function. This technology, through built-in sensors and advanced algorithms, can automatically identify and adapt to the user's work and rest habits, such as the night rest period, automatically adjusting the running speed of the compressor and fan of the refrigerator to the preset low-noise running mode. This mode ensures that the refrigerator maintains basic refrigeration function while minimizing noise emissions, providing a quiet rest environment for users. However, during the non-mute period, the refrigerator will flexibly adjust the speed of the compressor and fan according to the real-time monitored internal temperature and external environmental conditions to maintain the best refrigeration effect and energy efficiency ratio.

[0004] Although this intelligent mute period design alleviates the interference of refrigerator noise on user life to some extent, there are still some limitations. For example, when the user needs to frequently approach the refrigerator for some reason, even during the mute period, the low-speed running compressor and fan may still produce enough noise to attract the user's attention, especially in a quiet indoor environment, the impact is particularly obvious. In addition, in the face of some special situations, such as when the user just puts hot and humid food into the refrigerator, the refrigerator needs to quickly reduce the internal temperature to maintain the freshness of the food, but if the current environmental temperature is low, the compressor and fan will run at low speed according to the preset mute mode, the refrigerator may be difficult to quickly respond to this high heat load demand, resulting in a long time to reach the ideal refrigeration temperature, thereby affecting the normal refrigeration efficiency of the refrigerator and the quality of food preservation. SUMMARY

[0005] The present application provides a refrigerator mute method to solve the problem that the existing refrigerator mute technology cannot simultaneously meet the refrigeration and mute requirements.

[0006] The method is used for a silent refrigerator, the silent refrigerator comprising a silent mode and a regular mode, the method comprising:

[0007] acquiring real-time range data of a preset area in front of a door body of the silent refrigerator;

[0008] generating a detection result according to the real-time range data, the detection result being used to indicate whether a moving object is approaching or moving away from the silent refrigerator;

[0009] generating a control instruction according to the detection result, the control instruction being used to drive the silent refrigerator to operate in the silent mode or the regular mode.

[0010] Preferably, the step of acquiring the real-time range data of the preset area in front of the door body of the silent refrigerator comprises:

[0011] setting the preset area in front of the door body of the silent refrigerator;

[0012] recording object data in the preset area to obtain the real-time range data.

[0013] Preferably, the step of recording the object data in the preset area comprises:

[0014] recording the object data in the preset area by a video detection method and / or a heat source detection method.

[0015] Preferably, the step of generating the detection result according to the real-time range data comprises:

[0016] extracting real-time video images recorded by the video detection method;

[0017] generating a first analysis result according to the real-time video images, the first analysis result being used to indicate a moving object condition in the real-time video images;

[0018] extracting real-time heat source images recorded by the heat source detection method;

[0019] generating a second analysis result according to the real-time heat source images, the second analysis result being used to indicate a moving object condition in the real-time heat source images;

[0020] generating the detection result according to the first analysis result and the second analysis result, the detection result being used to indicate a moving object condition in superimposed visual detection and heat source detection.

[0021] Preferably, the step of generating the first analysis result according to the real-time video images comprises:

[0022] acquiring initial features of images at all positions in the preset area;

[0023] Real-time record the image real-time features of all positions in the preset area;

[0024] According to the image initial features and the image real-time features, feature comparison is performed to obtain the first analysis result.

[0025] Preferably, the step of generating a second analysis result according to the real-time heat source image comprises:

[0026] Obtain heat source initial features of all positions in the preset area;

[0027] Real-time record heat source real-time features of all positions in the preset area;

[0028] According to the heat source initial features and the heat source real-time features, feature comparison is performed to obtain the second analysis result.

[0029] Preferably, the step of performing feature comparison according to the image initial features and the image real-time features comprises:

[0030] Divide the preset area into a first area and a second area, the first area is the area close to the side of the silent refrigerator in the preset area, and the second area is the area away from the side of the silent refrigerator in the preset area;

[0031] According to the image real-time features and the image initial features located in the second area, feature comparison is performed to obtain a first sub-analysis result;

[0032] According to the image real-time features and the image initial features located in the first area, feature comparison is performed to obtain a second sub-analysis result, and the first analysis result comprises the first sub-analysis result and the second sub-analysis result.

[0033] Preferably, the step of performing feature comparison according to the heat source initial features and the heat source real-time features comprises:

[0034] According to the heat source real-time features and the heat source initial features located in the second area, feature comparison is performed to obtain a third sub-analysis result;

[0035] According to the heat source real-time features and the heat source initial features located in the first area, feature comparison is performed to obtain a fourth sub-analysis result, and the second analysis result comprises the third sub-analysis result and the fourth sub-analysis result.

[0036] Preferably, the step of generating a control instruction according to the detection result comprises:

[0037] extracting the first sub-analysis result, the second sub-analysis result, the third sub-analysis result and the fourth sub-analysis result according to the detection result respectively;

[0038] judging whether the feature difference overlap rate of the first sub-analysis result and the third sub-analysis result, and / or the second sub-analysis result and the fourth sub-analysis result is greater than an overlap threshold value;

[0039] If yes, generating a first control instruction or a second control instruction, the first control instruction being used for driving the silent refrigerator to operate according to a first power, the second control instruction being used for driving the silent refrigerator to operate according to a second power, the first power being less than the power size in the conventional mode, and the first power being greater than the second power.

[0040] Preferably, the method further comprises:

[0041] When the detection result represents the case that a moving object enters and leaves the preset area, acquiring a real-time temperature inside the silent refrigerator;

[0042] judging whether the real-time temperature is greater than a temperature threshold value;

[0043] If yes, maintaining the original refrigerator operation mode;

[0044] If no, generating a third control instruction, the real-time third control instruction being used for driving the silent refrigerator to operate according to the conventional mode.

[0045] From the above, the present application provides a refrigerator silent method, the method is applied to a silent refrigerator, the silent refrigerator comprises a silent mode and a conventional mode, the method comprises: acquiring real-time range data of a preset area in front of a door body of the silent refrigerator; generating a detection result according to the real-time range data, the detection result being used for representing whether a moving object is close to or away from the silent refrigerator; generating a control instruction according to the detection result, the control instruction being used for driving the silent refrigerator to operate in the silent mode or the conventional mode. The present application solves the problem that the existing refrigerator silent technology cannot simultaneously meet the refrigeration and silent demand through the above method. BRIEF DESCRIPTION OF DRAWINGS

[0046] In order to more clearly illustrate the technical solutions of the present application, the following will briefly introduce the drawings needed in the embodiments. Obviously, for those skilled in the art, other drawings can also be obtained without creative labor based on these drawings.

[0047] Figure 1 A flowchart of a refrigerator silent method of the present application;

[0048] Figure 2 Flow chart for acquiring real-time range data in a refrigerator mute method of the present application;

[0049] Figure 3 Flow chart for generating detection results in a refrigerator mute method of the present application;

[0050] Figure 4 Flow chart for generating first analysis results in a refrigerator mute method of the present application;

[0051] Figure 5 Flow chart for generating second analysis results in a refrigerator mute method of the present application;

[0052] Figure 6 Planar schematic diagram of embodiment one in a refrigerator mute method of the present application;

[0053] Figure 7 Planar schematic diagram of embodiment two in a refrigerator mute method of the present application;

[0054] Figure 8 Planar schematic diagram of a preset area in a refrigerator mute method of the present application. DETAILED DESCRIPTION

[0055] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0056] It should be noted that the brief description of the terms in the present application is only for the convenience of understanding the following described embodiments, and is not intended to limit the embodiments of the present application. Unless otherwise specified, these terms should be understood according to their ordinary and general meanings.

[0057] It should be noted that in the present application, the words such as "exemplary" or "for example" are used to represent an example, illustration or description. Any embodiment or design scheme described as "exemplary" or "for example" in the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the words such as "exemplary" or "for example" are intended to present the relevant concepts in a specific manner.

[0058] The refrigerator noise has been an important indicator for consumers to evaluate the quality of the refrigerator. With the technology upgrading of the electronic components of the refrigerator and the iteration of the intelligent control means, the noise value of the refrigerator is claimed to show a downward trend year by year. In order to avoid the noise interference of the refrigerator to the user during the period when the user needs silence, the prior art sets a corresponding silence period, controls the running speed of the compressor and the fan of the refrigerator in a low noise running mode, and then adjusts the speed according to the temperature during the non-silence period. Although this method can reduce the noise of the refrigerator during the period when the user needs silence, it causes noise interference to the user when the user is close to the refrigerator, or the speed of the compressor and the fan corresponding to the current ambient temperature of the refrigerator is low, causing the refrigerator to be placed in a high heat load situation such as hot and humid food that needs the refrigerator to quickly pull the temperature, and the target temperature cannot be reached for a long time, which cannot meet the normal refrigeration demand of the refrigerator.

[0059] Therefore, although the prior art can reduce the noise of the refrigerator during the period when the user needs silence, it causes noise interference to the user when the user is close to the refrigerator, or the speed of the compressor and the fan corresponding to the current ambient temperature of the refrigerator is low, causing the refrigerator to be placed in a high heat load situation such as hot and humid food that needs the refrigerator to quickly pull the temperature, and the target temperature cannot be reached for a long time, which cannot meet the normal refrigeration demand of the refrigerator.

[0060] Based on the above problems, the present application provides the following embodiments.

[0061] Figure 1 A flowchart of a refrigerator silence method of the present application.

[0062] Referring to Figure 1 It can be seen that the present embodiment provides a refrigerator silence method, which is applied to a silent refrigerator, the silent refrigerator comprising a silence mode and a normal mode, and the method comprising:

[0063] S100, acquiring real-time range data of a preset area in front of a door body of the silent refrigerator, specifically, in the present embodiment, the silence processing of the refrigerator is performed when the user is close to the refrigerator, and it is necessary to judge whether the user is close to the refrigerator before the silence processing of the refrigerator is performed, so the data around the silent refrigerator needs to be acquired before the silence processing is performed, and the silence of the refrigerator is realized through the data.

[0064] Figure 2 A flowchart of acquiring real-time range data in a refrigerator silence method of the present application.

[0065] Further, referring to Figure 2 It can be seen that further, in some embodiments, the step of acquiring real-time range data of a preset area in front of a door body of the silent refrigerator comprises:

[0066] S110, setting the preset area in front of the door body of the silent refrigerator;

[0067] S120, record the object data in the preset area to obtain the real-time range data.

[0068] Specifically, in the embodiment, before the refrigerator mute processing is performed, a specific mute range needs to be set for the mute refrigerator, that is, the preset area is set for the mute refrigerator, and the definition range of the area is a certain area in front of the refrigerator door of the mute refrigerator.

[0069] It should be noted that the preset area can be set by the user, and it can be understood that the preset area is set according to different needs of the user, such as the size of the empty space in front of the refrigerator, such as setting the preset area to a 1-meter trapezoidal area or a 2-meter fan-shaped area. The setting of the preset area can be referred to in Figure 6 、 Figure 7 and / or Figure 8 .

[0070] The acquisition method of the real-time range data can be to set a sensing device on the mute refrigerator and acquire data through the sensing device. The specific data content of the real-time range data can include heat source data and video data.

[0071] The method of recording the object data in the preset area can be to record the object data in the preset area by a video detection method and / or a heat source detection method.

[0072] For example, the video detection method can be used alone, that is, whether a moving object enters the preset area in front of the mute refrigerator is monitored in real time through a visual method, and when a moving object exists, the situation is determined as a user approaching the mute refrigerator, and subsequent refrigerator mute is performed.

[0073] For example, the heat source detection method can be used alone, that is, whether a heat source changes in the real-time preset area in front of the real-time mute refrigerator is monitored in real time, and when a heat source changes, the situation is determined as a user approaching the mute refrigerator, and subsequent refrigerator mute is performed.

[0074] For example, considering that some users have a situation such as a floor cleaning robot or a pet in their homes, and these objects are not the mute demand of the mute refrigerator even if they are in the preset area of the mute refrigerator, but the single setting of the video detection method or the heat source detection method cannot effectively avoid these situations, therefore, the video detection method and the heat source detection method can be used in combination, and the overlapping detection of the two can further improve the effectiveness of the refrigerator mute.

[0075] The method further comprises:

[0076] S200, generating a detection result according to the real-time range data, the detection result being used to represent whether a moving object is approaching or moving away from the silent refrigerator.

[0077] Specifically, in the present embodiment, after the real-time range data is acquired, a moving object detection needs to be performed according to the real-time range data, so as to know in real time whether a user is approaching or moving away from the silent refrigerator.

[0078] Figure 3 A flowchart for generating a detection result in the refrigerator silent method of the present application.

[0079] Referring to Figure 3 It can be known that, further, in some embodiments, the step of generating a detection result according to the real-time range data comprises:

[0080] S210, extracting a real-time video image recorded by the video detection method;

[0081] S220, generating a first analysis result according to the real-time video image, the first analysis result being used to represent a moving object situation in the real-time video image.

[0082] Specifically, in the present embodiment, since the real-time range data comprises a plurality of data, and different processing needs to be performed for each different data, after the real-time range data is acquired, different data needs to be extracted from the real-time range data according to different processing, and corresponding processing needs to be performed.

[0083] In the step S210 to the step S220, the real-time video image corresponding to the video detection method is extracted from the real-time range data, and a moving object detection is performed on the real-time video image in the image level, and the first analysis result used to represent a moving object situation in the real-time video image is obtained.

[0084] Figure 4 A flowchart for generating a first analysis result in the refrigerator silent method of the present application.

[0085] Referring to Figure 4 It can be known that, further, in some embodiments, the step of generating a first analysis result according to the real-time video image comprises:

[0086] S221, acquiring image initial features of all positions in the preset area;

[0087] S222, recording image real-time features of all positions in the preset area in real time;

[0088] S223, perform feature comparison based on the initial features of the image and the real-time features of the image to obtain the first analysis result.

[0089] Specifically, in this embodiment, steps S221 to S223 can be understood as “distinction detection” of video images, that is, the initial features of all locations within the preset area are obtained in advance, and then the area is monitored in real time. The real-time features of the image obtained in each monitoring are compared with the initial features of the image, so that the difference between the two can be obtained, that is, the first analysis result used to characterize the feature difference is obtained.

[0090] Wherein, all positions within the preset area are determined according to user customization; if the preset area is a reference... Figure 6 or Figure 7 If the preset area is a trapezoidal region, then all positions within the preset area are each position within the trapezoidal region. Similarly, if the preset area is as shown in the reference... Figure 8 If the fan-shaped region is defined as such, then all positions within the preset region are each position within the fan-shaped region.

[0091] The step of generating detection results based on the real-time range data further includes:

[0092] S230, Extract the real-time heat source image recorded by the heat source detection method;

[0093] S240, a second analysis result is generated based on the real-time heat source image, the second analysis result being used to represent the movement of objects in the real-time heat source image.

[0094] Specifically, in this embodiment, in steps S230 to S240, the real-time heat source image corresponding to the heat source detection method is extracted from the real-time range data, and moving objects are detected at the heat source level on the real-time heat source image, thereby obtaining the second analysis result used to characterize the moving objects in the real-time heat source image.

[0095] It should be noted that steps S210 to S220 and steps S230 to S240 are performed simultaneously, and steps S210 and S220 are not performed first and then steps S230 and S240.

[0096] Figure 5 This is a flowchart illustrating the generation of the second analysis result in a refrigerator noise reduction method according to this application.

[0097] See Figure 5 It can be seen that, further, in some embodiments, the step of generating a second analysis result based on the real-time heat source image includes:

[0098] S241, obtaining initial features of heat sources at all positions in the preset area;

[0099] S242, recording real-time features of heat sources at all positions in the preset area in real time;

[0100] S243, comparing the initial features of heat sources with the real-time features of heat sources to obtain the second analysis result.

[0101] Specifically, in the embodiment, steps S241 to S243 can be understood as "differential detection" of heat source images, that is, the initial features of heat sources at all positions in the preset area are obtained in advance, real-time heat source monitoring is performed on the area, and the real-time features of heat sources obtained each time are compared with the initial features of heat sources to obtain the difference between them, that is, the second analysis result for characterizing the difference in features.

[0102] It should be noted that both the initial features of images and the initial features of heat sources are determined according to the layout of the user's home, and therefore can be understood as that the initial features of images and the initial features of heat sources can be set by the user or adjusted over time.

[0103] For example, the heat source image in winter and the heat source image in summer are completely different, and therefore the initial features of heat sources need to be adjusted adaptively.

[0104] The step of generating a detection result according to the real-time range data further comprises:

[0105] S250, generating the detection result according to the first analysis result and the second analysis result, the detection result being used to represent the moving object condition in the superimposed visual detection and the heat source detection.

[0106] Specifically, in the embodiment, the combination scheme of the video detection method and the heat source detection method is taken as an example, that is, the detection data of the video detection method and the heat source detection method are combined, and the two different reference data in the detection result are superimposed to detect the moving object, so that the intervention of factors such as a sweeping robot in the silent processing of the refrigerator can be avoided.

[0107] The method further comprises:

[0108] S300, generating a control instruction according to the detection result, the control instruction being used to drive the silent refrigerator to operate in a silent mode or a regular mode.

[0109] Specifically, in the embodiment, the control instructions are generated according to the detection result, and the operation mode of the silent refrigerator is regulated by the control instructions, so that the silent refrigerator can be automatically switched between the silent mode and the normal mode, and the silent refrigerator is silent when a user approaches the silent refrigerator and is normal when the user is away from the silent refrigerator, so that the silent refrigerator is silent and the normal operation of the refrigerator is ensured.

[0110] Further, in some embodiments, the method further comprises: when the detection result represents that a moving object enters and leaves the preset area, obtaining a real-time temperature inside the silent refrigerator; determining whether the real-time temperature is greater than a temperature threshold; if yes, maintaining the original operation mode of the refrigerator; if no, generating a third control instruction, the third control instruction being used to drive the silent refrigerator to operate in the normal mode.

[0111] Specifically, in the embodiment, considering that the temperature inside the silent refrigerator may be too high or too low when the refrigerator is adjusted between the silent mode and the normal mode, the temperature factor is introduced in the adjustment of the silent refrigerator, and it is determined whether the temperature inside the silent refrigerator is greater than a temperature threshold when a user approaches the silent refrigerator and leaves, and the operation of the refrigerator is further adjusted by the temperature.

[0112] The power adjustment of the silent refrigerator can be understood as adjusting the power of the compressor and / or the refrigeration fan of the silent refrigerator.

[0113] Figure 6 A plan view of an embodiment one of the refrigerator silencing method of the application.

[0114] Figure 7 A plan view of an embodiment two of the refrigerator silencing method of the application.

[0115] Referring to Figure 6 and Figure 7 It can be seen that the preset area is also divided in the embodiment, and the silent regulation in different preset areas is also different, so the following two embodiments are provided as a reference.

[0116] Embodiment one:

[0117] Before the silent regulation, the division of the preset area needs to be explained first, the preset area is divided into the first area and the second area in the embodiment, wherein the first area is the area close to the silent refrigerator on one side of the preset area, and the second area is the area away from the silent refrigerator on the other side of the preset area.

[0118] Since different areas are different distances from the silent refrigerator, the noise generated has different effects on the user, so different silent adjustments are needed for areas at different distances, and the first area closer to the silent refrigerator is used for silent processing in this embodiment.

[0119] The image real-time features and the image initial features in the first area are compared to obtain a second sub-analysis result.

[0120] The heat source real-time features and the heat source initial features in the first area are compared to obtain a fourth sub-analysis result.

[0121] It is judged whether the feature difference overlap rate of the second sub-analysis result and the fourth sub-analysis result is greater than an overlap threshold.

[0122] If so, a second control instruction is generated, which is used to drive the silent refrigerator to operate at a second power.

[0123] Embodiment two:

[0124] The second area away from the silent refrigerator is used for silent processing in this embodiment.

[0125] The image real-time features and the image initial features in the second area are compared to obtain a first sub-analysis result.

[0126] The heat source real-time features and the heat source initial features in the second area are compared to obtain a third sub-analysis result.

[0127] It is judged whether the feature difference overlap rate of the first sub-analysis result and the third sub-analysis result is greater than an overlap threshold.

[0128] If so, a first control instruction is generated, which is used to drive the silent refrigerator to operate at a first power.

[0129] It should be noted that the first power is less than the power size in the conventional mode, and the first power is greater than the second power.

[0130] The embodiment has the following advantages:

[0131] The embodiment solves the problem of automatic silent refrigerator when the user is close to the refrigerator by using a close-type silent method, and switches to the conventional mode when the user is away from the refrigerator, ensuring the original refrigeration effect of the refrigerator and avoiding the problem of damage or loss of preservation effect of the items stored in the refrigerator due to the conventional low-power silent mode.

[0132] For the sake of convenience, the foregoing description has been presented in terms of specific implementations. However, the foregoing discussion is not intended to limit the disclosure to the particular implementations described. Various modifications and changes can be made thereto by those of ordinary skill in the art having the benefit of the teachings presented herein. The implementations described above are chosen and described in order to best explain the principles of the disclosure and its best mode of operation.

Claims

1. A refrigerator muting method, characterized by, The method is applied to a silent refrigerator, the silent refrigerator comprising a silent mode and a regular mode, the method comprising: acquiring real-time range data of a preset area in front of a door body of the silent refrigerator; generating a detection result according to the real-time range data, the detection result being used to indicate whether a moving object is approaching or moving away from the silent refrigerator; generating a control instruction according to the detection result, the control instruction being used to drive the silent refrigerator to operate in the silent mode or the regular mode; the step of acquiring the real-time range data of the preset area in front of the door body of the silent refrigerator comprises: setting the preset area in front of the door body of the silent refrigerator; recording object data in the preset area to obtain the real-time range data; the step of recording the object data in the preset area comprises: recording the object data in the preset area by a video detection method and / or a heat source detection method.

2. The refrigerator muting method of claim 1, wherein, the step of generating the detection result according to the real-time range data comprises: extracting real-time video images recorded by the video detection method; generating a first analysis result according to the real-time video images, the first analysis result being used to indicate a moving object condition in the real-time video images; extracting real-time heat source images recorded by the heat source detection method; generating a second analysis result according to the real-time heat source images, the second analysis result being used to indicate a moving object condition in the real-time heat source images; generating the detection result according to the first analysis result and the second analysis result, the detection result being used to indicate a moving object condition in superimposed visual detection and heat source detection.

3. The refrigerator muting method of claim 2, wherein, the step of generating the first analysis result according to the real-time video images comprises: acquiring image initial features of all positions in the preset area; recording image real-time features of all positions in the preset area in real time; performing feature comparison according to the image initial features and the image real-time features to obtain the first analysis result.

4. The refrigerator muting method of claim 3, wherein the step of generating the second analysis result according to the real-time heat source images comprises: acquiring heat source initial features of all positions in the preset area; recording heat source real-time features of all positions in the preset area in real time; performing feature comparison according to the heat source initial features and the heat source real-time features to obtain the second analysis result.

5. The refrigerator muting method of claim 4, wherein, the step of performing feature comparison according to the image initial features and the image real-time features comprises: dividing the preset area into a first area and a second area, the first area being an area close to the silent refrigerator in the preset area, and the second area being an area away from the silent refrigerator in the preset area; performing feature comparison according to the image real-time features and the image initial features located in the second area to obtain a first sub-analysis result; performing feature comparison according to the image real-time features and the image initial features located in the first area to obtain a second sub-analysis result, the first analysis result comprising the first sub-analysis result and the second sub-analysis result.

6. The refrigerator muting method of claim 5, wherein, the step of performing feature comparison according to the heat source initial features and the heat source real-time features comprises: According to the real-time feature of the heat source located in the second region and the initial feature of the heat source, a feature comparison is performed to obtain a third sub-analysis result; According to the real-time feature of the heat source located in the first region and the initial feature of the heat source, a feature comparison is performed to obtain a fourth sub-analysis result, and the second analysis result includes the third sub-analysis result and the fourth sub-analysis result.

7. The refrigerator muting method of claim 6, wherein, The step of generating a control instruction according to the detection result includes: According to the detection result, the first sub-analysis result, the second sub-analysis result, the third sub-analysis result, and the fourth sub-analysis result are extracted respectively; It is judged whether the feature difference overlap rate of the first sub-analysis result and the third sub-analysis result, and / or the second sub-analysis result and the fourth sub-analysis result is greater than an overlap threshold value; If yes, a first control instruction or a second control instruction is generated, the first control instruction is used to drive the silent refrigerator to operate at a first power, and the second control instruction is used to drive the silent refrigerator to operate at a second power, the first power is less than the power size in the conventional mode, and the first power is greater than the second power.

8. The refrigerator muting method of claim 1, wherein, The method further includes: When the detection result represents that a moving object enters and leaves the preset region, a real-time temperature inside the silent refrigerator is obtained; It is judged whether the real-time temperature is greater than a temperature threshold value; If yes, the original refrigerator operation mode is maintained; If not, a third control instruction is generated, and the third control instruction is used to drive the silent refrigerator to operate in a conventional mode.

Images