Real-time monitoring method for smart refrigerator, and smart refrigerator

Abstract

A real-time monitoring method for a smart refrigerator, and a smart refrigerator. The method comprises: acquiring historical door opening / closing data of a refrigerator, and on the basis of the historical door opening / closing data, determining an opening time data set and a closing time data set; calculating the degree of matching between the current time period and the opening time data set and between the current time period and the closing time data set, and on the basis of the degree of matching, determining a target device for detecting the freshness of food stored in the refrigerator; and sending a control instruction to the target device, and on the basis of the detection data of the target device, determining the freshness of the food stored in the refrigerator. By using a camera device to detect the freshness of food ingredients in a refrigerator in some time periods, the detection load of a freshness detection device capable of emitting optical signals is effectively reduced; and since the detection principle of the camera device does not require emission of optical signals to food ingredients, the power consumption of the refrigerator can be effectively reduced.

Description

A real-time monitoring method for smart refrigerators and smart refrigerators Technical Field

[0001] This invention relates to the field of computer technology, and more specifically, to a real-time monitoring method for a smart refrigerator and a smart refrigerator. Background Technology

[0002] With the advancement of technology, more and more families are choosing smart refrigerators with food freshness monitoring functions. These refrigerators can analyze the freshness of the food stored inside and output the corresponding freshness analysis results to the user.

[0003] Existing methods for detecting the freshness of food ingredients typically include the following implementations: Existing patent document 1 (CN113218878A) discloses a method for judging the freshness of food ingredients in a refrigerator, comprising the following steps: scanning the spectral data of the same type of food ingredients in the refrigerator at different freshness levels; establishing a freshness model based on the spectral data, the freshness model including multiple freshness levels of the food ingredients; scanning the spectral data of new food ingredients of the same type in the refrigerator, and obtaining the measured freshness level through the freshness model; determining whether the actual freshness level of the new food ingredients matches the measured freshness level; if they match, increasing the weight of the spectral data as the measured freshness level; if they do not match, increasing the weight of the spectral data as the actual freshness; repeatedly placing the same type of food ingredients of multiple freshness levels in the refrigerator, scanning the spectral data, determining whether the actual freshness matches the measured freshness, and increasing the corresponding weight according to the results; adjusting the freshness model according to the correspondence between the spectral data with the highest weight and the freshness level.

[0004] Existing patent document 2 (CN116429733A) discloses a device for detecting the freshness of egg products, comprising: a fixing device for placing egg products; a light source module disposed on one side of the fixing device for emitting a light source signal; a light sensor disposed on the other side of the fixing device for receiving a transmitted light source passing through the egg products; and a controller configured to: in response to a freshness detection operation, control the light source module to emit an incident light source with a preset light intensity; acquire the light intensity of the transmitted light source detected by the light sensor; calculate the light transmittance of the egg products based on the light intensity of the incident light source and the light intensity of the transmitted light source; compare the light transmittance with a preset number of light transmittance intervals, and determine the freshness of the egg products based on the comparison results.

[0005] It is evident that current methods for detecting food freshness primarily rely on spectral and illumination data, specifically achieved through light source devices and photosensitive equipment placed within the refrigerator. However, none of the aforementioned patent documents optimize the timing of food freshness detection. The light source devices and photosensitive equipment must operate synchronously according to fixed rules to achieve the detection function, which increases the energy consumption of smart refrigerators. This is a technical problem that needs to be addressed. Technical issues

[0006] To address this issue, the present invention provides a real-time monitoring method for a smart refrigerator, a smart refrigerator, an electronic device, and a computer storage medium, thereby solving the aforementioned technical problems. Technical solutions

[0007] The first aspect of the present invention also discloses a real-time monitoring method for a smart refrigerator, comprising the following steps: acquiring historical data of the refrigerator door opening and closing; determining an opening time dataset and a closing time dataset based on the historical data of the door opening and closing; calculating the matching degree between the current time period and the opening time dataset and the closing time dataset; determining a target device for detecting the freshness of food stored in the refrigerator based on the matching degree; wherein the target device includes a camera device and a freshness detection device capable of emitting light signals; sending a control command to the target device; and determining the freshness of food stored in the refrigerator based on the detection data of the target device.

[0008] Further, the refrigerator door opening and closing history data is acquired, and the opening time dataset and closing time dataset are determined based on the door opening and closing history data. This includes: acquiring the working signal data of the refrigerator door passive pressing button or the air pressure change data detected by the air pressure sensor inside the refrigerator contained in the door opening and closing history data; determining the door opening and closing state based on the working signal data or the air pressure change data; performing binary classification of the door opening and closing history data based on the opening and closing state; and generating the opening time dataset and the closing time dataset based on the classification data corresponding to the binary classification results.

[0009] Further, generating the opening time dataset and the closing time dataset based on the classification data corresponding to the binary classification results includes: performing clustering calculations on the two sets of classification data corresponding to the binary classification results to obtain a first opening time dataset and a first closing time dataset; wherein the clustering calculation is based on period characteristics; determining the corresponding first opening time data and first closing time data based on the period characteristics, and determining overlapping time data through overlap calculation, and determining second opening time data and second closing time data based on the overlapping time data; wherein the second opening time data has the overlapping time data added compared to the first opening time data, and the second closing time data is missing the overlapping time data compared to the first closing time data; repeating the above steps to obtain several second opening time data and second closing time data; constructing a second opening time dataset based on each second opening time data, and constructing a second closing time dataset based on each second closing time data, thus generating the opening time dataset and the closing time dataset.

[0010] Further, determining the second opening time data and the second closing time data based on the overlap time data includes: controlling the camera device to capture image data of the food inside the cabinet door, parsing the food image data to obtain the number of food types; determining a weighting coefficient based on the number of food types, multiplying the weighting coefficient by the overlap time data to obtain new overlap time data; and determining the second opening time data and the second closing time data based on the new overlap time data.

[0011] Further, determining the target device for detecting the freshness of food stored in the refrigerator based on the matching degree includes: if the matching degree characterizes any of the second closing time data in the closing time dataset, then the freshness detection device capable of emitting light signals is determined as the target device; if the matching degree characterizes any of the second opening time data in the opening time dataset, then the camera device is determined as the target device.

[0012] Furthermore, after sending the control command to the target device, the method further includes: when the refrigerator door is detected to be open, acquiring the opening rate of the door, determining the capture frequency based on the opening rate; controlling the camera device to capture several food image data based on the capture frequency; wherein the capture frequency is positively correlated with the opening rate.

[0013] Furthermore, controlling the camera device to capture several food image data according to the capture frequency includes: determining the capture waiting time according to the opening rate, and after the capture waiting time is reached, controlling the camera device to capture several food image data according to the capture frequency.

[0014] A second aspect of the present invention provides an intelligent refrigerator, comprising a communication device, a processing device, a storage device, a camera device, and a light-emitting freshness detection device. The processing device is electrically connected to the storage device, the communication device, the camera device, and the light-emitting freshness detection device. The communication device is configured to acquire historical data of the refrigerator door opening and closing, working signals of a passive door pressing button, or air pressure change data detected by an internal air pressure sensor, and detection data of the target device, and transmit these data to the processing device. The storage device is configured to store a computer program. The processing device is configured to retrieve and execute the computer program stored in the storage device to perform the method described in any of the preceding claims, to identify the camera device or the light-emitting freshness detection device as the target device, and to send a control command to the target device to control the target device to detect the freshness of food stored in the refrigerator; and to determine the freshness of the food stored in the refrigerator based on the detection data of the target device.

[0015] A third aspect of the present invention also discloses an electronic device comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, the processor executing the computer program to implement the method as described in any of the preceding claims.

[0016] A fourth aspect of the invention also discloses a computer storage medium storing a computer program that is executed by a processor to implement the method as described in any of the preceding claims.

[0017] The fifth aspect of the invention also discloses a computer program product that, when run on a terminal, causes the terminal to execute in order to implement the method described in any of the preceding claims. Beneficial effects

[0018] The beneficial effects of this invention are as follows: by using a camera device to detect the freshness of food in the refrigerator during certain periods, this invention effectively reduces the detection load of freshness detection devices that can emit light signals. Since the detection principle of the camera device does not require emitting light signals to the food, it can effectively reduce the power consumption of the refrigerator. Attached Figure Description

[0019] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 is a flowchart illustrating a real-time monitoring method for a smart refrigerator disclosed in an embodiment of the present invention.

[0021] Figure 2 is a structural schematic diagram of an intelligent refrigerator disclosed in an embodiment of the present invention. Embodiments of the present invention

[0022] The following specific embodiments illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0023] Furthermore, the technical features involved in the different embodiments of this application described below can be combined with each other as long as they do not conflict with each other.

[0024] As shown in Figure 1, this invention discloses a real-time monitoring method for a smart refrigerator. The method includes the following steps: acquiring historical data of the refrigerator door opening and closing; determining an opening time dataset and a closing time dataset based on the historical data; calculating the matching degree between the current time period and the opening time dataset and the closing time dataset; determining a target device for detecting the freshness of food stored in the refrigerator based on the matching degree; wherein the target device includes a camera device and a freshness detection device capable of emitting light signals; sending control commands to the target device; and determining the freshness of food stored in the refrigerator based on the detection data of the target device.

[0025] In this embodiment of the invention, the smart refrigerator is equipped with two types of freshness detection devices: a camera device and a light-emitting freshness detection device. The camera device is a conventional camera, while the light-emitting freshness detection device can be a combination of a spectrometer or a light source module and a light sensor, as described in the background art. In specific implementation, this invention performs in-depth analysis of the refrigerator door opening and closing history data to determine the opening time dataset and closing time dataset, thus obtaining the door opening and closing pattern. Based on this pattern, the two types of target devices can be scheduled to perform freshness detection operations at different times, thereby effectively reducing the workload of the light-emitting freshness detection device and thus reducing the refrigerator's energy consumption. Therefore, this invention effectively reduces the detection load of the light-emitting freshness detection device by using a camera device to detect the freshness of the food inside the refrigerator during certain periods. Since the detection principle of the camera device does not require emitting light signals to the food, it can effectively reduce the refrigerator's power consumption.

[0026] The two target devices described above in this invention are installed inside the storage compartments of a smart refrigerator, namely the refrigerator compartment and the freezer compartment. This invention does not limit the placement or specific installation method of these devices within the refrigerator.

[0027] Further, the refrigerator door opening and closing history data is acquired, and the opening time dataset and closing time dataset are determined based on the door opening and closing history data. This includes: acquiring the working signal data of the refrigerator door passive pressing button or the air pressure change data detected by the air pressure sensor inside the refrigerator contained in the door opening and closing history data; determining the door opening and closing state based on the working signal data or the air pressure change data; performing binary classification of the door opening and closing history data based on the opening and closing state; and generating the opening time dataset and the closing time dataset based on the classification data corresponding to the binary classification results.

[0028] A passive door press button is installed at the contact point between the refrigerator body and the door when it is closed. This button is extended when the door is open and pressed when the door is closed. The door's open / closed state can be determined based on the button's signal. Alternatively, each compartment of the refrigerator is equipped with a pressure sensor that detects the air pressure in that compartment. Opening and closing the door changes the pressure readings detected by these sensors. Specifically, the detected air pressure will briefly decrease or increase during the door opening and closing phases, respectively, thus determining the door's open / closed state.

[0029] After determining the opening and closing states of the door, the corresponding opening and closing time data can be obtained by appropriately expanding on the time of occurrence of these states (i.e. the time of detection) and finally constructing the dataset mentioned above.

[0030] Further, generating the opening time dataset and the closing time dataset based on the classification data corresponding to the binary classification results includes: performing clustering calculations on the two sets of classification data corresponding to the binary classification results to obtain a first opening time dataset and a first closing time dataset; wherein the clustering calculation is based on period characteristics; determining the corresponding first opening time data and first closing time data based on the period characteristics, and determining overlapping time data through overlap calculation, and determining second opening time data and second closing time data based on the overlapping time data; wherein the second opening time data has the overlapping time data added compared to the first opening time data, and the second closing time data is missing the overlapping time data compared to the first closing time data; repeating the above steps to obtain several second opening time data and second closing time data; constructing a second opening time dataset based on each second opening time data, and constructing a second closing time dataset based on each second closing time data, thus generating the opening time dataset and the closing time dataset.

[0031] In this embodiment of the invention, based on the aforementioned determined opening and closing status of the refrigerator door, the historical data of door opening and closing can be divided into two groups of data: opening time periods and closing time periods. Meanwhile, the patterns of users opening and closing the refrigerator door vary significantly across different periods. Therefore, this invention performs clustering calculations on the two groups of data (i.e., the two groups of categorized data corresponding to the binary classification results) based on period characteristics. Taking weekdays and non-weekdays as an example, the following explanation is provided: ;in, This is a data matrix showing when users opened and closed refrigerator doors during a specific time period (e.g., 10:00-12:00). Indicates the first Refrigerator door opening times data for weekdays. Indicates the first Data on refrigerator door opening times on non-working days (i.e., weekends) of the week will be used to... These data are obtained through clustering calculations This represents the pattern of users opening the refrigerator door during the aforementioned time period on weekdays (e.g., 10:00-12:00), thus obtaining the first opening time dataset (which contains multiple datasets corresponding to different time periods). For example, corresponding to 8:00-10:00, 10:00-12:00, 12:00-17:00, and 17:00-22:00 respectively); and, will These data are obtained through clustering calculations This represents the pattern of users closing the refrigerator door during the aforementioned time period (e.g., 10:00-12:00) on non-working days, i.e., weekends, thus obtaining the first closing time dataset (which contains multiple datasets corresponding to different time periods). For example, these correspond to 8:00-10:00, 10:00-12:00, 12:00-17:00, and 17:00-22:00 respectively.

[0032] The clustering calculation involved in this invention can be achieved by directly obtaining multiple clusters. , While the average value is used, the unsupervised ML clustering algorithm DBSCAN (Density-Based Noise Applied Spatial Clustering) is preferred, as it avoids the influence of outliers compared to the traditional K-means clustering algorithm. The process of clustering the two sets of classification data corresponding to the binary classification results using the DBSCAN algorithm is roughly as follows: First, a random point is selected that has at least minPts (minimum points) within its radius. Then, each point in the neighborhood of the core point is evaluated to determine whether it has minPts (minPts including the point itself) within the epsilon distance (maximum community radius). If the point meets the minPts criterion, it becomes another core point, and the cluster expands. If a point does not meet the minPts criterion, it becomes a boundary point. When a cluster is surrounded by boundary points, the cluster search is complete because there are no more points within the distance. A new random point is selected, and the process is repeated to identify the next cluster until clustering of each set of classification data is completed.

[0033] Furthermore, the period characteristics in this invention are not limited to different times of the week or day, but can also be different months of the year, or even weekdays, weekends, holidays, etc.

[0034] Meanwhile, since users do not have an absolute understanding of the opening and closing patterns of the refrigerator door, there is a high possibility of overlapping time periods. To address this, this invention identifies the overlapping regions in the initial opening and closing time datasets, assigning these overlapping regions to the first opening and closing time data. This results in the generation of more accurate opening and closing time datasets.

[0035] Further, determining the second opening time data and the second closing time data based on the overlap time data includes: controlling the camera device to capture image data of the food inside the cabinet door, parsing the food image data to obtain the number of food types; determining a weighting coefficient based on the number of food types, multiplying the weighting coefficient by the overlap time data to obtain new overlap time data; and determining the second opening time data and the second closing time data based on the new overlap time data.

[0036] In this embodiment of the invention, the refrigerator can store various types of food. The more types of food there are, the higher the probability that the user will take food outside the statistically derived opening time dataset. Conversely, the fewer types of food there are, the higher the probability that a particular refrigerator compartment or freezer compartment is dedicated to the user, such as specifically for storing fruit, tomatoes, or fresh meat. In this case, the probability that the user will take food outside the statistically derived opening time dataset is lower. Therefore, this invention uses a camera device installed in the refrigerator to capture images of the food inside. By analyzing the food images, the number of types of food stored can be statistically determined, for example, identifying apples, tomatoes, and carrots. Then, a weighting coefficient is determined based on the number of food types, and the weighting coefficient (greater than 1) is positively correlated with the number of food types. Finally, the aforementioned overlap time data is adjusted based on the weighting coefficient, thereby achieving adaptive expansion of the overlap time data. This adapts to situations where the user takes food outside the statistically derived opening time dataset, making the switching timing of the camera device more appropriate.

[0037] It should be noted that the camera device can capture images of the food inside the refrigerator door when the door is open, thus eliminating the need for lighting to assist in capturing images of the food after the door is closed, which can further reduce the refrigerator's power consumption.

[0038] Further, determining the target device for detecting the freshness of food stored in the refrigerator based on the matching degree includes: if the matching degree characterizes any of the second closing time data in the closing time dataset, then the freshness detection device capable of emitting light signals is determined as the target device; if the matching degree characterizes any of the second opening time data in the opening time dataset, then the camera device is determined as the target device.

[0039] In this embodiment of the invention, when the determined matching degree indicates that the current time period falls within the refrigerator door's regular closing period, a freshness detection device capable of emitting light signals can be identified as the target device. During this door-closed period, the light inside the refrigerator is dim, making it difficult to accurately detect freshness using a camera. Therefore, the aforementioned type of device capable of emitting light signals is preferentially used to detect the freshness of the food inside the refrigerator. Conversely, when the determined matching degree indicates that the current time period falls within the refrigerator door's regular opening period, a camera can be identified as the target device. During this door-opening period, the light inside the refrigerator is sufficient, allowing the camera to accurately detect freshness. In this time period, the freshness detection device capable of emitting light signals is paused to switch to the camera, effectively reducing power consumption during light signal emission.

[0040] It should be noted that the two existing patent documents attached to the background section have already explained in detail the basic principle of the freshness detection device that can emit light signals to detect the freshness of food. The contents of the detection principle involved in this invention are incorporated into this invention and will not be repeated here. In addition, the technology of using camera equipment to analyze the freshness of food is relatively mature. Generally, it is done by matching the appearance image features of the food with preset freshness template images of different freshness levels to determine the corresponding freshness level. The specifics will not be repeated here either.

[0041] Furthermore, after sending the control command to the target device, the method further includes: when the refrigerator door is detected to be open, acquiring the opening rate of the door, determining the capture frequency based on the opening rate; controlling the camera device to capture several food image data based on the capture frequency; wherein the capture frequency is positively correlated with the opening rate.

[0042] In this embodiment of the invention, to avoid the camera device encroaching on the storage space inside the refrigerator, it is preferable to place the camera device inside the door. This is because the inside of the door generally has a concave structure, which is beneficial for placing a relatively small camera device there without taking up too much space inside the refrigerator. However, when the camera device is placed in this way, the shooting angle of the camera device will change as the door is opened. The camera device needs to capture as many images as possible to obtain more suitable images of the food, but too many captures are also not beneficial, and a trade-off needs to be made.

[0043] To address this, when determining that the current time period corresponds to the opening time dataset, the refrigerator can be controlled to enter a door opening monitoring state. For example, the aforementioned passive door press button or the internal air pressure sensor can be controlled to enter a continuous monitoring state. Based on the working signal data of the passive door press button or the air pressure data detected by the internal air pressure sensor, it is possible to accurately detect whether the refrigerator door has been opened. Then, the capture rate of the camera is determined based on the opening rate of the refrigerator door. Obviously, the faster the door opens, the higher the capture frequency of the camera, thus increasing the probability of capturing more complete and clearer images of the food inside the refrigerator. Conversely, the slower the door opens, the lower the capture frequency of the camera. This ensures a higher probability of capturing more complete and clearer images of the food inside the refrigerator while effectively reducing unnecessary captures.

[0044] It should be noted that the opening rate of the cabinet door can be determined based on the lifting rate of the door being passively pressed, the rate of change of air pressure data, or the angular velocity data transmitted from the Hall sensor on the door hinge.

[0045] Furthermore, controlling the camera device to capture several food image data according to the capture frequency includes: determining the capture waiting time according to the opening rate, and after the capture waiting time is reached, controlling the camera device to capture several food image data according to the capture frequency.

[0046] In this embodiment of the invention, besides the shooting angle, another prerequisite for the camera device to capture better food images is that the refrigerator door is opened to a sufficient angle (allowing enough light to enter) to ensure adequate lighting inside the refrigerator. To this end, the present invention determines the capture waiting time based on the detected door opening rate. When this waiting time is reached, the refrigerator door opening angle is large enough (e.g., 10°), and the refrigerator's internal lighting has been activated, ensuring sufficient lighting inside the refrigerator. At this point, controlling the camera to capture food images at the determined capture frequency results in more high-quality images being captured, and the shooting angle at this time is also most advantageous, facilitating the subsequent selection of better food images.

[0047] As shown in Figure 2, this embodiment of the invention also discloses an intelligent refrigerator, including a communication device, a processing device, a storage device, a camera device, and a freshness detection device capable of emitting light signals. The processing device is electrically connected to the storage device, the communication device, the camera device, and the freshness detection device capable of emitting light signals. The communication device is used to acquire historical data of the refrigerator door opening and closing, working signals of the door passive pressing button, or air pressure change data detected by the air pressure sensor inside the refrigerator, and detection data of the target device, and transmit them to the processing device. The storage device is used to store a computer program. The processing device is used to retrieve and execute the computer program in the storage device to execute the method described in the foregoing embodiment, to identify the camera device or the freshness detection device capable of emitting light signals as the target device, and to send a control command to the target device to control the target device to detect the freshness of the food stored in the refrigerator; and to determine the freshness of the food stored in the refrigerator based on the detection data of the target device.

[0048] This invention also discloses an electronic device, comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the method described in the foregoing embodiments.

[0049] This invention also discloses a computer storage medium storing a computer program that is executed by a processor to implement the methods described in the foregoing embodiments.

[0050] This invention also discloses a computer program product that, when run on a terminal, causes the terminal to execute the method described in the foregoing embodiments.

[0051] The steps of the methods or algorithms described in this application can be implemented in hardware or by a processor executing software instructions. The software instructions can consist of corresponding software modules, which can be stored in random access memory (RAM), flash memory, read-only memory (ROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, hard disks, portable hard disks, CD-ROMs, or any other form of storage medium known in the art. An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and storage medium can reside in an ASIC. Alternatively, the ASIC can reside in a core network interface device. Of course, the processor and storage medium can also exist as discrete components in the core network interface device.

[0052] In the several embodiments provided in this application, it should be understood that the disclosed methods and apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical or other forms.

[0053] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network devices. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0054] Furthermore, in the various embodiments of the present invention, the functional units can be integrated into one processing unit, or each functional unit can exist independently, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0055] Through the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware, and of course, it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a readable storage medium, such as a computer floppy disk, hard disk, or optical disk, and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0056] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A real-time monitoring method for a smart refrigerator, characterized in that, The process includes the following steps: acquiring historical data of refrigerator door opening and closing; determining an opening time dataset and a closing time dataset based on the historical data; calculating the matching degree between the current time period and the opening time dataset and the closing time dataset; determining a target device for detecting the freshness of food stored in the refrigerator based on the matching degree; wherein the target device includes a camera device and a freshness detection device capable of emitting light signals; sending control commands to the target device; and determining the freshness of food stored in the refrigerator based on the detection data of the target device.

2. The real-time monitoring method for a smart refrigerator according to claim 1, characterized in that: Acquiring historical data on the opening and closing of the refrigerator door, and determining an opening time dataset and a closing time dataset based on the historical data, includes: acquiring working signal data of the refrigerator door passive pressing button or air pressure change data detected by the air pressure sensor inside the refrigerator contained in the historical data on the opening and closing of the door; determining the opening and closing state of the door based on the working signal data or the air pressure change data; performing binary classification of the historical data on the opening and closing of the door based on the opening and closing state; and generating the opening time dataset and the closing time dataset based on the classification data corresponding to the binary classification results.

3. The real-time monitoring method for a smart refrigerator according to claim 2, characterized in that: The process of generating the opening time dataset and the closing time dataset based on the classification data corresponding to the binary classification results includes: performing clustering calculations on the two sets of classification data corresponding to the binary classification results to obtain a first opening time dataset and a first closing time dataset; wherein the clustering calculation is based on period characteristics; determining the corresponding first opening time data and first closing time data based on the period characteristics, and determining overlapping time data through overlap calculation, and determining second opening time data and second closing time data based on the overlapping time data; wherein the second opening time data includes the overlapping time data compared to the first opening time data, and the second closing time data lacks the overlapping time data compared to the first closing time data; repeating the above steps to obtain several sets of second opening time data and second closing time data; constructing a second opening time dataset based on each set of second opening time data, and constructing a second closing time dataset based on each set of second closing time data, thus generating the opening time dataset and the closing time dataset.

4. A real-time monitoring method for a smart refrigerator according to claim 3, characterized in that: Determining the second opening time data and the second closing time data based on the overlap time data includes: controlling the camera device to capture image data of the food inside the cabinet door, parsing the food image data to obtain the number of food types; determining a weighting coefficient based on the number of food types, multiplying the weighting coefficient by the overlap time data to obtain new overlap time data; and determining the second opening time data and the second closing time data based on the new overlap time data.

5. A real-time monitoring method for a smart refrigerator according to claim 4, characterized in that: Determining a target device for detecting the freshness of food stored in a refrigerator based on the matching degree includes: if the matching degree characterizes any of the second closing time data in the closing time dataset, then the freshness detection device capable of emitting light signals is determined as the target device; if the matching degree characterizes any of the second opening time data in the opening time dataset, then the camera device is determined as the target device.

6. A real-time monitoring method for a smart refrigerator according to claim 1, characterized in that: After sending a control command to the target device, the method further includes: when the refrigerator door is detected to be open, acquiring the opening rate of the door, determining the capture frequency based on the opening rate; controlling the camera device to capture several food image data based on the capture frequency; wherein the capture frequency is positively correlated with the opening rate.

7. A real-time monitoring method for a smart refrigerator according to claim 6, characterized in that: Controlling the camera device to capture several food image data according to the capture frequency includes: determining the capture waiting time according to the opening rate, and after the capture waiting time is reached, controlling the camera device to capture several food image data according to the capture frequency.

8. A smart refrigerator, comprising a communication device, a processing device, a storage device, a camera device, and a freshness detection device capable of emitting light signals, wherein the processing device is electrically connected to the storage device, the communication device, the camera device, and the freshness detection device capable of emitting light signals; the communication device is used to acquire historical data of the smart refrigerator's door opening and closing, working signals of the door passive pressing button, or air pressure change data detected by the refrigerator's internal air pressure sensor, and detection data of the target device, and transmit them to the processing device; the storage device is used to store computer programs; characterized in that: The processing device is configured to retrieve and execute a computer program in the storage device to perform the method as described in any one of claims 1-7, to identify the camera device or the light-emitting freshness detection device as the target device, and to send a control command to the target device for controlling the target device to detect the freshness of food stored in the refrigerator; and to determine the freshness of food stored in the refrigerator based on the detection data of the target device.

9. An electronic device, comprising: At least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, characterized in that: the processor executes the computer program to implement the method as claimed in any one of claims 1-7.

10. A computer storage medium storing a computer program, characterized in that: The computer program is executed by a processor to implement the method as described in any one of claims 1-7.

Images