Data acquisition method, refrigerator, electronic equipment and program product

Abstract

The embodiment of the invention belongs to the refrigerator data acquisition technology, and provides a data acquisition method, a refrigerator, electronic equipment and a program product. The refrigerator comprises a receiving module, a data obtaining module and a sending module. The receiving module is used for receiving a data query instruction from the data acquisition equipment; the data query instruction is sent to the refrigerator by the data acquisition equipment in response to the fact that the time interval between the current moment and the previous acquisition moment is equal to the target time interval; the data acquisition module is used for responding to the data query instruction and acquiring a refrigerator operation data set; the refrigerator operation data set comprises operation data used for representing at least one operation state of the refrigerator at the current moment; and the sending module is used for sending the refrigerator operation data set to the data acquisition equipment, so that the data acquisition equipment obtains a sample refrigerator operation data set according to the refrigerator operation data set. According to the invention, occupation of refrigerator computing resources can be reduced, and the time sequence accuracy of refrigerator operation data acquisition is improved.

Description

Technical Field

[0001] This application relates to refrigerator data acquisition technology. More specifically, it relates to a data acquisition method, a refrigerator, an electronic device, and a software product. Background Technology

[0002] Refrigerators are used for refrigerating or freezing items. Therefore, if a refrigerator malfunctions, it will cause losses and a poor user experience. Thus, accurately predicting whether a refrigerator will malfunction is crucial. Currently, the main methods for refrigerator malfunction prediction are based on pre-trained refrigerator malfunction prediction models. The training of these models relies heavily on a large amount of sample refrigerator data.

[0003] Existing data acquisition methods for sample refrigerators primarily rely on the refrigerators actively uploading their operational data. However, this method requires the refrigerator to store a certain amount of data, consuming its computing resources. Furthermore, when network transmission is unstable, the timing accuracy of the refrigerator's operational data acquired through this method is poor. Summary of the Invention

[0004] This application provides a data acquisition method, a refrigerator, an electronic device, and a program product, which can reduce the occupation of the refrigerator's computing resources and improve the timing accuracy of refrigerator operation data acquisition.

[0005] In a first aspect, embodiments of this application provide a refrigerator, the refrigerator comprising: a receiving module, a data acquisition module, and a sending module;

[0006] The receiving module is used to receive a data query instruction from the data acquisition device; the data query instruction is sent by the data acquisition device to the refrigerator in response to a target time interval between the current time and the previous acquisition time.

[0007] The data acquisition module is used to respond to the data query command and acquire a refrigerator operation data set; the refrigerator operation data set includes: operation data that characterizes at least one operation status of the refrigerator at the current moment;

[0008] The sending module is used to send the refrigerator operation data set to the data acquisition device, so that the data acquisition device can obtain a sample refrigerator operation dataset based on the refrigerator operation data set.

[0009] Secondly, this application provides a data acquisition method, which is applied to a data acquisition device, and the method includes:

[0010] In response to the target time interval being equal to the current time and the previous acquisition time, a data query command is sent to at least one target refrigerator, so that the target refrigerator responds to the data query command and obtains a refrigerator operation data set; the refrigerator operation data set includes: operation data used to characterize at least one operation status of the target refrigerator at the current time;

[0011] Receive the refrigerator operation data set from the target refrigerator;

[0012] Based on the refrigerator operation data set, obtain the sample refrigerator operation dataset.

[0013] In some embodiments of this application, before sending a data query instruction to at least one target refrigerator in response to a target time interval equal to the current time and the previous acquisition time, the method further includes:

[0014] Determine the network transmission status between the data acquisition device and the target refrigerator;

[0015] The target time interval is determined based on the network transmission status.

[0016] In some embodiments of this application, obtaining the sample refrigerator operation dataset based on the refrigerator operation data set includes:

[0017] The refrigerator's operating data set is parsed to obtain initial operating data;

[0018] The integrity of the initial running data is verified, and if the integrity verification of the initial running data passes, it is determined whether there is any abnormality in the initial running data;

[0019] Since the initial operating data is normal, the initial operating data is used as the sample refrigerator operating data collected at the current moment;

[0020] The sample refrigerator operation dataset is obtained based on the sample refrigerator operation data collected at the current time and the sample refrigerator operation data collected at least one time prior to the current time.

[0021] In some embodiments of this application, the method further includes:

[0022] In response to the failure of the integrity verification of the initial operating data, or the anomaly of the initial operating data, the sample refrigerator operating data collected at the previous collection time is used as the sample refrigerator operating data collected at the current time.

[0023] In some embodiments of this application, the sample refrigerator operation dataset is used to train a refrigerator fault prediction model. Obtaining the sample refrigerator operation dataset based on the sample refrigerator operation data collected at the current time, and sample refrigerator operation data collected at least one time prior to the current time, includes:

[0024] For any one of the at least one operating states, a sample data sequence corresponding to that operating state is determined; the sample data sequence includes: operating data of the operating state corresponding to at least one collection time before the current time and in the sample refrigerator operating data;

[0025] Labels are added to the sample data sequence to obtain the sample refrigerator operation dataset; the labels are used to characterize whether the target refrigerator is fault-free or the type of fault of the target refrigerator.

[0026] In some embodiments of this application, before adding labels to the sample data sequence to obtain the sample refrigerator operation dataset, the method further includes:

[0027] For any of the sample data sequences, in response to the fact that none of the operational data in the sample data sequence includes a fault identifier, the label of the sample data sequence is determined based on the operational data of at least one operational state of the target refrigerator at at least one acquisition time;

[0028] In response to the presence of a fault identifier in the operational data within the sample data sequence, a label for the sample data sequence is determined based on the fault identifier.

[0029] In some embodiments of this application, determining the label of the sample data sequence based on operational data of at least one operational state of the target refrigerator at at least one collection time includes:

[0030] Based on the operating data of at least one operating state of the target refrigerator at at least one collection time, the initial label of the sample data sequence is determined;

[0031] Display the sample data sequence, and the initial label of the sample data sequence;

[0032] In response to a user's modification of the initial label based on the sample data sequence, the label of the sample data sequence is determined.

[0033] Thirdly, this application provides an electronic device, including: a processor and a memory; the processor is communicatively connected to the memory;

[0034] The memory stores computer instructions;

[0035] The processor executes computer instructions stored in the memory to implement the method as described in any one of the first and / or second aspects.

[0036] Fourthly, this application provides a computer program product, including a computer program or instructions, which, when executed by a processor, implement the method described in any one of the first and / or second aspects.

[0037] Fifthly, this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of the first and / or second aspects.

[0038] The data acquisition method, refrigerator, electronic device, and program product provided in this application determine whether the current time and the previous acquisition time have reached a target time interval through the data acquisition device. When the target time interval is reached, a data query command is sent to the target refrigerator, triggering the target refrigerator to acquire a refrigerator operation data set. This method avoids the accumulation of large amounts of operation data by the target refrigerator. Furthermore, by acquiring a refrigerator operation data set that represents at least one operational state of the target refrigerator at the current time, the time corresponding to the operation data is clearly identified, reducing the impact of network status on the temporal accuracy of the sample refrigerator operation dataset. Therefore, this method enables the refrigerator to be instructed to acquire data when the target time interval is reached, ensuring the temporal accuracy of the acquired sample refrigerator operation dataset and reducing the consumption of refrigerator computing resources, thereby ensuring the accuracy of subsequent data processing using the sample refrigerator operation dataset. Attached Figure Description

[0039] To more clearly illustrate the implementation methods in the embodiments of this application or related technologies, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings.

[0040] Figure 1 A schematic diagram illustrating an application scenario of the data acquisition method provided in this application;

[0041] Figure 2 This application provides a schematic diagram of the structure of a refrigerator;

[0042] Figure 3 A flowchart illustrating a data acquisition method provided in this application;

[0043] Figure 4A flowchart illustrating another data acquisition method provided in this application;

[0044] Figure 5 A flowchart illustrating yet another data acquisition method provided in this application;

[0045] Figure 6 A flowchart illustrating a method for determining labels for a sample data sequence provided in this application;

[0046] Figure 7 A schematic diagram of the structure of a data acquisition device provided in this application;

[0047] Figure 8 This is a schematic diagram of the structure of an electronic device 110 provided in an embodiment of this application. Detailed Implementation

[0048] To make the objectives, implementation methods and advantages of this application clearer, the exemplary implementation methods of this application will be clearly and completely described below with reference to the accompanying drawings of the exemplary embodiments of this application. Obviously, the described exemplary embodiments are only some embodiments of this application, and not all embodiments.

[0049] It should be noted that the brief descriptions of terms in this application are only for the convenience of understanding the embodiments described below, and are not intended to limit the embodiments of this application. Unless otherwise stated, these terms should be understood in their ordinary and common meaning.

[0050] Furthermore, the terms “comprising” and “having”, and any variations thereof, are intended to cover but not exclusively include, for example, a product or device that includes a series of components is not necessarily limited to those that are explicitly listed, but may include other components that are not explicitly listed or that are inherent to such product or device.

[0051] To improve the user experience of refrigerators, accurately predicting whether a refrigerator will malfunction is crucial. In some embodiments, a pre-trained refrigerator malfunction prediction model can be used to predict whether a refrigerator will malfunction. The training of this model relies heavily on a large amount of sample refrigerator data.

[0052] Currently, existing methods for collecting data from sample refrigerators primarily rely on the refrigerators actively uploading their operational data. For example, a refrigerator needs to store its own operational data and uploads it to its corresponding backend server when a pre-set upload time arrives. However, refrigerator data storage resources are typically scarce, and storing a certain amount of data consumes the refrigerator's computing resources. Furthermore, if the network transmission between the refrigerator and the backend server is unstable, this method can lead to errors in the time interval of the refrigerator's operational data uploads, resulting in poor accuracy in the timing of the collected data.

[0053] In view of the aforementioned problems with existing refrigerators, this application proposes a data acquisition method that uses a data acquisition device to instruct the refrigerator to acquire data at a target time interval, thereby ensuring the timing accuracy of the acquired data and reducing the consumption of the refrigerator's computing resources.

[0054] Figure 1 This is a schematic diagram illustrating an application scenario of the data acquisition method provided in this application. For example... Figure 1 As shown, the execution subject of this method can be a data acquisition device. This data acquisition device can be, for example, any existing electronic device with processing capabilities, such as a terminal or a server. The target refrigerator can be any existing refrigerator capable of acquiring its own operational data. In some embodiments, the refrigerator can also be called a smart refrigerator.

[0055] It should be understood that Figure 1 This application uses only one target refrigerator as an example to illustrate the application scenario of this data acquisition method. This application does not limit the number of target refrigerators for which refrigerator operation data sets can be obtained through this data acquisition device.

[0056] The technical solutions of this application will be described in detail below with reference to specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0057] For example, Figure 2 This is a structural schematic diagram of a refrigerator provided in this application. Figure 2 As shown, the refrigerator may include: a receiving module 21, a data acquisition module 22, and a sending module 23.

[0058] The receiving module 21 can be used to receive data query commands from the data acquisition device. These data query commands are sent by the data acquisition device to the refrigerator in response to a target time interval between the current time and the previous acquisition time.

[0059] The data acquisition module 22 can be used to respond to data query commands and acquire a set of refrigerator operation data. This set of refrigerator operation data may include operation data characterizing at least one operating state of the refrigerator at the current moment.

[0060] The sending module 23 can be used to send a set of refrigerator operation data to the data acquisition device so that the data acquisition device can obtain a sample refrigerator operation dataset based on the set of refrigerator operation data.

[0061] Among them, such as Figure 2 The refrigerator shown can be the target refrigerator described in any of the following embodiments. Based on this refrigerator, Figure 3 This is a flowchart illustrating a data acquisition method provided in this application. Figure 3 As shown, the method includes the following steps:

[0062] S101, the data acquisition device responds to the target time interval between the current time and the previous acquisition time by sending a data query command to at least one target refrigerator.

[0063] Correspondingly, the target refrigerator can receive the data query command through the receiving module 21.

[0064] Optionally, this application does not limit the duration of the aforementioned target time interval.

[0065] Optionally, this application does not limit the number of target refrigerators. That is, the data acquisition device can acquire a set of refrigerator operation data for one or more target refrigerators.

[0066] Optionally, the aforementioned data query instruction can be used, for example, to instruct the target refrigerator to collect refrigerator operation data and feed it back to the data acquisition device. In some embodiments, the data query instruction may include, for example, the unique identifier and / or IP address of the data acquisition device, as well as the aforementioned current time. Through this data query instruction, the target refrigerator can determine the set of refrigerator operation data to be acquired at the "current time," improving the timing accuracy of data acquisition.

[0067] Optionally, the data acquisition device may record, for example, the moment when the data query command was last sent to the target refrigerator, and use that moment as the aforementioned previous acquisition moment. Alternatively, the previously fed-back refrigerator operation data set from the target refrigerator may include the acquisition moment of the operation data within that previously fed-back refrigerator operation data set. The data acquisition device can determine the acquisition moment of the operation data by parsing the previously fed-back refrigerator operation data set, and use that acquisition moment as the aforementioned previous acquisition moment.

[0068] S102, the target refrigerator responds to the data query command through the data acquisition module 22 and obtains the refrigerator operation data set.

[0069] The aforementioned refrigerator operation data set may include, for example, operation data characterizing at least one operating state of the target refrigerator at the current moment. For example, this operating state may include, for instance, the temperature of at least one compartment of the target refrigerator, the preset temperature of the corresponding compartment, the operating frequency of the target refrigerator's compressor, and the operating frequency of the target refrigerator's fan.

[0070] It should be understood that this application does not limit how the data acquisition module 22 acquires the refrigerator operation data set. For example, taking the operating status including the compartment temperature as an example, the target refrigerator may include a compartment temperature detection device. The data acquisition module 22 may, for example, respond to the data query command and trigger the compartment temperature detection device (e.g., a temperature sensor) to feed back the current compartment temperature to the data acquisition module 22. Then, the data acquisition module 22 can acquire the refrigerator operation data set based at least on the current compartment temperature.

[0071] S103, the target refrigerator sends the aforementioned refrigerator operation data set to the data acquisition device through the sending module 33.

[0072] Correspondingly, the data acquisition device can receive the refrigerator operation data set from the target refrigerator.

[0073] S104. The data acquisition device obtains the sample refrigerator operation dataset based on the refrigerator operation data set.

[0074] Optionally, the sample refrigerator operation dataset can be used, for example, to train a refrigerator fault prediction model. Obtaining the sample refrigerator operation dataset using the data acquisition method provided in this application improves the temporal accuracy of the data in the sample refrigerator operation dataset, thus enhancing the accuracy of training the refrigerator fault prediction model based on this sample refrigerator operation dataset.

[0075] Alternatively, in some embodiments, the sample refrigerator operation dataset can also be used to train other neural network models, such as training a refrigerator refrigerant ratio prediction model. It should be understood that this application does not limit the application scenarios of the sample refrigerator operation dataset.

[0076] In this embodiment, the data acquisition device determines whether the current time and the previous acquisition time have reached the target time interval. When the target time interval is reached, a data query command is sent to the target refrigerator, triggering the target refrigerator to acquire a refrigerator operation data set. This method avoids the accumulation of large amounts of operation data by the target refrigerator. Furthermore, by acquiring a refrigerator operation data set that represents at least one operational state of the target refrigerator at the current time, the target refrigerator clarifies the time corresponding to the operation data, reducing the impact of network status on the temporal accuracy of the sample refrigerator operation dataset. Therefore, this method enables the refrigerator to be instructed to acquire data when the target time interval is reached, ensuring the temporal accuracy of the acquired sample refrigerator operation dataset and reducing the consumption of refrigerator computing resources, thereby ensuring the accuracy of subsequent data processing using the sample refrigerator operation dataset.

[0077] The target time intervals mentioned above are explained in detail below:

[0078] As one possible implementation, the target time interval can be pre-stored in the data acquisition device. In some embodiments, the data acquisition device can also update the target time interval in response to user modifications.

[0079] Optionally, the data acquisition device may receive the target time interval configured by user input, for example, through an application programming interface (API) or a graphical user interface (GUI).

[0080] The target time interval can be set and changed using the above method, which improves the flexibility of data collection and thus the flexibility of the sample refrigerator operation dataset. This allows the sample refrigerator operation dataset to meet the time interval requirements of subsequent use scenarios for the operation data in the sample refrigerator operation dataset.

[0081] As another possible implementation, before sending a data query command to at least one target refrigerator in response to a target time interval between the current time and the previous acquisition time, the data acquisition device may, for example, first determine the network transmission status between the data acquisition device and the target refrigerator. Then, the data acquisition device may, for example, determine the aforementioned target time interval based on this network transmission status.

[0082] For example, the aforementioned network transmission status can be characterized by at least one existing network transmission parameter, such as network bandwidth, that can characterize whether the network transmission between the data acquisition device and the target refrigerator is smooth. For instance, the data acquisition device can obtain the network bandwidth of the network transmission between the data acquisition device and the target refrigerator (this network bandwidth can be used to characterize the network transmission status between the data acquisition device and the target refrigerator), and then determine the aforementioned target time interval based on this network bandwidth and the mapping relationship between network bandwidth and time interval.

[0083] In some embodiments, the better the network transmission status between the data acquisition device and the target refrigerator, the shorter the target time interval can be, thereby reducing network waste and improving the richness of the sample refrigerator operation dataset. Conversely, the worse the network transmission status between the data acquisition device and the target refrigerator, the longer the target time interval can be, thereby reducing the lag in the transmission of the refrigerator operation data set and improving the timing accuracy of the sample refrigerator operation dataset.

[0084] The above method can automatically determine the target time interval, improving the automation level of the data acquisition method. Furthermore, the target time interval matches the network transmission status between the data acquisition device and the target refrigerator, further improving the accuracy of the target time interval. It also further reduces the impact of the network transmission status on the timing accuracy of the sample refrigerator's operating data, thus further improving the accuracy of the sample refrigerator's operating data set.

[0085] As another possible implementation, the data acquisition device can, for example, determine the target time interval based on the time period of the previous acquisition time and the mapping relationship between time periods and time intervals.

[0086] For example, assuming the previous data collection time occurred during daytime, the target time interval can be relatively short. Conversely, assuming the previous data collection time occurred during nighttime, the target time interval can be relatively long.

[0087] The following section details how the data acquisition device obtains a sample refrigerator operation dataset based on the refrigerator operation data set:

[0088] As one possible implementation, the data acquisition device can, for example, parse the refrigerator's operating data set to obtain initial operating data.

[0089] For example, the data acquisition device can parse the aforementioned refrigerator operating data set using a preset data parsing protocol to obtain initial operating data. In some embodiments, this initial operating data may also be referred to as raw operating data.

[0090] Then, the data acquisition device can, for example, perform an integrity check on the initial running data, and if the integrity check of the initial running data passes, determine whether there is any abnormality in the initial running data.

[0091] If the integrity check of the initial operating data passes, it means that the refrigerator operating data set, including the initial operating data, did not lose any data during network transmission. If the integrity check of the initial operating data fails, it means that some data was lost from the refrigerator operating data set, including the initial operating data, during network transmission.

[0092] For example, the data acquisition device can perform integrity verification on the initial operating data using any existing integrity verification method. For instance, the data acquisition device can calculate a checksum of the initial operating data and determine the integrity of the initial operating data based on that checksum.

[0093] For example, if the integrity verification of the initial operating data passes, the data acquisition device can, for instance, use a limiting value filtering method to determine whether the initial operating data is abnormal. For example, the data acquisition device can determine the difference between the initial operating data at the current moment and the operating data at the previous acquisition moment, and compare this difference with a preset limit. If the difference is less than or equal to the preset limit, it indicates that the initial operating data is not abnormal. If the difference is greater than the preset limit, it indicates that the initial operating data is abnormal.

[0094] The data acquisition device can respond to the absence of abnormalities in the initial operating data and use that initial operating data as the sample refrigerator operating data collected at the current moment.

[0095] In some embodiments, if the integrity verification of the initial operating data fails (indicating that the refrigerator operating data set including the initial operating data has lost some data during network transmission), or if the initial operating data is abnormal, the data acquisition device can use the "sample refrigerator operating data acquired at the previous acquisition time" as the sample refrigerator operating data acquired at the current time.

[0096] Optionally, the data acquisition device can obtain the "sample refrigerator operation data at the previous acquisition time" in a manner similar to the method for obtaining the sample refrigerator operation dataset corresponding to the current time as described in any embodiment of this application, and will not be repeated here. After obtaining the "sample refrigerator operation dataset corresponding to the previous acquisition time," the data acquisition device can, for example, store the "sample refrigerator operation dataset corresponding to the previous acquisition time." Accordingly, the data acquisition device can, for example, obtain the sample refrigerator operation dataset corresponding to the previous acquisition time from its own stored data, and obtain the "sample refrigerator operation data collected at the previous acquisition time" from the sample refrigerator operation dataset corresponding to the previous acquisition time.

[0097] After acquiring the sample refrigerator operation data collected at the current moment, the data acquisition device can obtain a sample refrigerator operation dataset based on the sample refrigerator operation data collected at the current moment, as well as the sample refrigerator operation data collected at least one acquisition moment before the current moment.

[0098] In some embodiments, taking the sample refrigerator operation dataset for training a refrigerator fault prediction model as an example, the data acquisition device can, for example, determine the sample data sequence corresponding to any one of the at least one operating states. This sample data sequence may include, for example, the operating data corresponding to that operating state at the current time and at least one acquisition time prior to the current time in the aforementioned sample refrigerator operation data.

[0099] For example, taking the temperature of a compartment as an example, the sample data sequence may include: the temperature of the compartment at the current moment, and the temperature of the compartment at at least one acquisition moment before the current moment.

[0100] Then, the data acquisition device can add labels to the sample data sequence to obtain a sample refrigerator operation dataset. These labels can be used to characterize whether the target refrigerator is fault-free or has a fault type.

[0101] For example, the above-mentioned fault types may include at least one type such as refrigerator compressor failure or refrigerator evaporator failure.

[0102] By adding the aforementioned label "used to characterize whether the target refrigerator is fault-free or the type of fault in the target refrigerator" to the sample data sequence, the sample data sequence can be used to train a refrigerator fault prediction model. This allows the refrigerator fault prediction model trained on the sample refrigerator operation dataset to predict whether the refrigerator will malfunction and, if so, the type of fault when it does.

[0103] It should be understood that this application does not limit how the aforementioned sample refrigerator running dataset is used to train the refrigerator failure prediction model. Optionally, the sample refrigerator running dataset can be used to train the refrigerator failure prediction model, for example, by referring to any existing model training method, which will not be elaborated here.

[0104] In some embodiments, the data acquisition device can receive labels input by the user for each sample data sequence, and then use the labels to add labels to the sample data sequence to obtain a sample refrigerator running dataset.

[0105] In some embodiments, before adding labels to the sample data sequences to obtain the sample refrigerator running dataset, the data acquisition device may automatically determine the labels of the sample data sequences, for example.

[0106] For example, for any sample data sequence, the data acquisition device can determine the label of the sample data sequence based on the operating data of at least one operating state of the target refrigerator at at least one acquisition time, in response to the fact that no operating data in the sample data sequence includes a fault identifier.

[0107] For example, assuming the sample data sequence corresponds to the compressor frequency, and taking the at least one operating state including the compressor frequency, fan frequency, and the difference between the actual temperature and the set temperature of the compartment as an example, the data acquisition device can determine, based on the aforementioned "compressor frequency, fan frequency, and the difference between the actual temperature and the set temperature of the compartment" at at least one acquisition time, whether the target refrigerator is fault-free or has a target type of fault when the sample data sequence was generated. Then, the data acquisition device can determine the label of the sample data sequence based on the judgment result of whether the target refrigerator is fault-free or has a target type of fault.

[0108] Optionally, the data acquisition device may first determine the initial label of the sample data sequence based on the operating data of at least one operating state of the target refrigerator at at least one acquisition time. Optionally, the method for determining the initial label of the sample data sequence can refer to the method described in the above embodiments, and will not be repeated here.

[0109] Then, the data acquisition device can, for example, display the sample data sequence, as well as the initial label of the sample data sequence.

[0110] Taking a data acquisition device that includes a display device as an example, the data acquisition device can display the aforementioned sample data sequence and its initial label through its own display device. Taking a data acquisition device that does not include a display device as an example, the data acquisition device can output the aforementioned sample data sequence and its initial label to a target display device, and display the sample data sequence and its initial label through the target display device.

[0111] By displaying the above sample data sequence and its initial label, users can view the sample data sequence and its initial label.

[0112] Then, the data acquisition device can, for example, determine the label of the sample data sequence in response to the user's modification operation on the initial label based on the sample data sequence.

[0113] Optionally, the data acquisition device can receive user modifications to the initial labels via a GUI or API.

[0114] Alternatively, the data acquisition device may, for example, respond to a user-triggered operation to determine that the initial label of the sample data sequence is correct, and directly use the initial label of the sample data sequence as the label of the sample data sequence.

[0115] Using the above method, users only need to verify the initial label of the sample data sequence, and the data acquisition device can obtain the label of the sample data sequence. Users do not need to perform a lot of data analysis to determine the label of the sample data sequence, which improves the efficiency of the data acquisition device in obtaining the label of the sample data sequence.

[0116] If the above sample data sequence contains operational data including fault identifiers, the data acquisition device can determine the label of the sample data sequence based on the fault identifiers.

[0117] For example, the data acquisition device can determine the fault type to which the fault identifier belongs based on the aforementioned fault identifier and the mapping relationship between the fault identifier and the fault type. Then, the data acquisition device can generate a label corresponding to the fault type of the target refrigerator for the sample data sequence based on the fault type to which the fault identifier belongs in the operational data contained in the sample data sequence.

[0118] In this embodiment, the aforementioned sample refrigerator operation dataset can be used to train a refrigerator fault prediction model, enabling subsequent predictions of refrigerator fault types or whether a fault has occurred based on this model. Compared to existing fault diagnosis methods that rely on logical judgments and convert human experience into logical rules, which are inefficient and have unstable accuracy due to their dependence on human experience, this application uses the sample refrigerator operation dataset to train a refrigerator fault prediction model. This allows the model to be used to predict refrigerator faults based on historical refrigerator operation data, eliminating the need for a sophisticated analytical model and improving the accuracy and efficiency of refrigerator fault prediction.

[0119] Figure 4 A flowchart illustrating another data acquisition method provided in this application. Figure 4 As shown, exemplarily, the method includes the following steps:

[0120] After the data acquisition device is powered on (start process), it first performs initialization, which may include serial port initialization, WiFi initialization, display interface UI initialization, etc.

[0121] The data acquisition device receives the user-set data acquisition interval (i.e., the aforementioned target time interval) and the user-triggered operation to open the serial port connected to the refrigerator through the UI interface. When the "Open Serial Port" button is clicked, the data acquisition device sends a handshake data command to the refrigerator to perform a handshake operation with the refrigerator control board.

[0122] The data acquisition device can receive and parse the data packets returned by the refrigerator to determine if the handshake was successful. If the verification passes, the data acquisition device and the refrigerator have successfully completed the handshake, and the device proceeds to the data display thread and the data acquisition thread. If the verification fails, it indicates that the handshake failed, and the device must re-establish the handshake with the refrigerator.

[0123] In the data display thread, the data acquisition device can display historically collected refrigerator operating data and detect the status of the end button. If the end button is pressed, the program exits, reaching the end of the process. If the user does not press the end button, the program runs to determine if the time interval since the last data collection is equal to the set collection interval. If the time interval since the last data collection is equal to the set collection interval, the program runs the data acquisition thread to collect the refrigerator's operating data and performs operations such as parsing, automatic annotation, and data saving. After the data acquisition thread has executed, the data on the display interface can be updated.

[0124] Figure 5 This is a flowchart illustrating yet another data acquisition method provided in this application. Figure 5 As shown, exemplarily, the method includes the following steps:

[0125] For example, the data acquisition device can load a data display window (displaying text data), a temperature curve, and an end button, and set labels, etc. It determines whether the time interval since the last data acquisition is equal to the set acquisition interval. If the time interval is equal to the set acquisition interval, the data acquisition thread sends a query command to the refrigerator. After receiving the query command and verifying its validity, the refrigerator packages the running data and sends it to the data acquisition device.

[0126] Correspondingly, the data acquisition device receives data returned by the refrigerator. Then, the data acquisition device can calculate the checksum of the initial running data and determine if the data is abnormal. If the checksum is successful and the data is not abnormal, the original data is saved, for example, to document A (filtered abnormal data). Then, the data acquisition device can parse the original data, extract the data to be collected (e.g., the aforementioned sample data sequence), and add tags. Then, the data acquisition device can package the parsed data and tags together and save them, for example, to document B. If the original data checksum fails or is abnormal, the data from the previous moment can be copied to the current moment; that is, the data saved at the current moment is the data received at the previous moment. After the data is saved, the data in the display window can be updated (missing value imputation).

[0127] Figure 6 This is a flowchart illustrating a method for determining labels for a sample data sequence provided in this application. Figure 6 As shown, the data acquisition device can iterate through the fault flag bits in the parsed data to determine whether the data contains fault information. If it does, the device will label the data and add a tag value corresponding to the fault type.

[0128] If the parsed data does not contain fault information, the data acquisition device can, for example, calculate the rate of change of the compartment temperature, the difference between the actual temperature of the compartment and the set temperature, and combine the cooling status of the compartment with the frequency of the compressor and fan to determine whether the refrigerator corresponding to the data is faulty. Based on the judgment result, the data is labeled and the corresponding label value is added to the data.

[0129] In this embodiment, the above method can realize the automatic collection and labeling of sample refrigerator operation data. The target time interval can be set according to actual needs, so that the data collection is strictly carried out according to the set target time interval. This solves the problems of excessively long time intervals or unstable collection timing of existing smart refrigerators' uploaded operation data, and improves the integrity and timeliness of sample refrigerator operation data.

[0130] Figure 7 This is a schematic diagram of a data acquisition device provided in this application. This device can be applied to data acquisition equipment. Figure 7 As shown, the device includes: a transmitting module 71, a receiving module 72, and a processing module 73. Among them,

[0131] The sending module 71 is configured to send a data query command to at least one target refrigerator in response to a target time interval between the current time and the previous acquisition time, so that the target refrigerator responds to the data query command and obtains a refrigerator operation data set. The refrigerator operation data set includes operation data characterizing at least one operating state of the target refrigerator at the current time.

[0132] The receiving module 72 is used to receive the refrigerator operation data set from the target refrigerator.

[0133] Processing module 73 is used to obtain a sample refrigerator operation dataset based on the refrigerator operation data set.

[0134] Optionally, the processing module 73 is further configured to determine the network transmission status between the data acquisition device and the target refrigerator before sending a data query instruction to at least one target refrigerator in response to a target time interval equal to the current time and the previous acquisition time; and to determine the target time interval based on the network transmission status.

[0135] Optionally, the processing module 73 is specifically configured to parse the refrigerator operation data set to obtain initial operation data; perform integrity verification on the initial operation data, and determine whether the initial operation data is abnormal when the integrity verification of the initial operation data passes; in response to the initial operation data being normal, use the initial operation data as the sample refrigerator operation data collected at the current time; and obtain the sample refrigerator operation dataset based on the sample refrigerator operation data collected at the current time and the sample refrigerator operation data collected at least one time prior to the current time.

[0136] Optionally, the processing module 73 is further configured to, in response to the failure of the integrity verification of the initial operating data or the existence of an anomaly in the initial operating data, use the sample refrigerator operating data collected at the previous collection time as the sample refrigerator operating data collected at the current time.

[0137] Taking the sample refrigerator operation dataset as an example for training a refrigerator fault prediction model, optionally, the processing module 73 is specifically used to determine the sample data sequence corresponding to any one of the at least one operation states; add labels to the sample data sequence to obtain the sample refrigerator operation dataset; the labels are used to characterize whether the target refrigerator is fault-free or the fault type of the target refrigerator. The sample data sequence includes: operation data corresponding to the operation state at least once before the current time and in the sample refrigerator operation data.

[0138] Optionally, the processing module 73 is further configured to, before adding labels to the sample data sequence to obtain the sample refrigerator operation dataset, for any sample data sequence, in response to any operation data in the sample data sequence not including a fault identifier, determine the label of the sample data sequence based on the operation data of at least one operation state of the target refrigerator at at least one acquisition time; and in response to the existence of operation data in the sample data sequence including a fault identifier, determine the label of the sample data sequence based on the fault identifier.

[0139] Optionally, the processing module 73 is specifically configured to determine the initial label of the sample data sequence based on the operating data of at least one operating state of the target refrigerator at at least one acquisition time; display the sample data sequence and the initial label of the sample data sequence; and determine the label of the sample data sequence in response to a user's modification operation on the initial label based on the sample data sequence.

[0140] The data acquisition device provided in this application embodiment can execute the data acquisition method in the above method embodiment, and its implementation principle and technical effect are similar, so it will not be described again here. It should be noted that the above... Figure 7 The division of modules shown is merely illustrative. This application does not limit the division of modules or the naming of modules.

[0141] Figure 8 This is a schematic diagram of the structure of an electronic device 110 provided in an embodiment of this application. Optionally, the electronic device may be, for example, the aforementioned refrigerator or data acquisition device. Figure 8 As shown, the electronic device 110 may include at least one processor 111 and a memory 112.

[0142] The memory 112 is used to store programs. Specifically, the program may include program code, which includes computer operation instructions.

[0143] The memory 112 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0144] The processor 111 is used to execute computer execution instructions stored in the memory 112 to implement the data acquisition method described in the foregoing method embodiments. The processor 111 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0145] The electronic device 110 may also include a communication interface 113, through which it can communicate and interact with external devices, such as other electronic devices (e.g., mobile phones, navigators) or servers. In specific implementations, if the communication interface 113, memory 112, and processor 111 are implemented independently, they can be interconnected via a bus to complete communication. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc., but this does not imply that there is only one bus or one type of bus.

[0146] Optionally, in a specific implementation, if the communication interface 113, memory 112 and processor 111 are integrated on a single chip, then the communication interface 113, memory 112 and processor 111 can communicate through an internal interface.

[0147] This application also provides a computer-readable storage medium, which may include various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk. Specifically, the computer-readable storage medium stores program instructions, which are used in the methods described in the above embodiments.

[0148] This application also provides a program product including executable instructions stored in a readable storage medium. At least one processor of an electronic device can read the executable instructions from the readable storage medium, and the at least one processor executes the executable instructions to cause the electronic device to implement the data acquisition methods provided in the various embodiments described above.

[0149] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

[0150] For ease of explanation, the above description has been provided in conjunction with specific embodiments. However, the above exemplary discussion is not intended to be exhaustive or to limit the embodiments to the specific forms disclosed above. Various modifications and variations can be obtained based on the above teachings. The selection and description of the above embodiments are for the purpose of better explaining the principles and practical applications, thereby enabling those skilled in the art to better utilize the described embodiments and various different variations of embodiments suitable for specific use considerations.

Claims

1. A refrigerator, characterized in that, The refrigerator includes: a receiving module, a data acquisition module, and a sending module; The receiving module is used to receive a data query instruction from the data acquisition device; the data query instruction is sent by the data acquisition device to the refrigerator in response to a target time interval between the current time and the previous acquisition time. The data acquisition module is used to respond to the data query command and acquire a refrigerator operation data set; the refrigerator operation data set includes: operation data that characterizes at least one operation status of the refrigerator at the current moment; The sending module is used to send the refrigerator operation data set to the data acquisition device, so that the data acquisition device can obtain a sample refrigerator operation dataset based on the refrigerator operation data set.

2. A data acquisition method, characterized in that, The method is applied to a data acquisition device, and the method includes: In response to the target time interval being equal to the current time and the previous acquisition time, a data query command is sent to at least one target refrigerator, so that the target refrigerator responds to the data query command and obtains a refrigerator operation data set; the refrigerator operation data set includes: operation data used to characterize at least one operation status of the target refrigerator at the current time; Receive the refrigerator operation data set from the target refrigerator; Based on the refrigerator operation data set, obtain the sample refrigerator operation dataset.

3. The method according to claim 2, characterized in that, Before sending a data query command to at least one target refrigerator in response to a time interval equal to the target time interval between the current time and the previous data acquisition time, the method further includes: Determine the network transmission status between the data acquisition device and the target refrigerator; The target time interval is determined based on the network transmission status.

4. The method according to claim 2 or 3, characterized in that, The step of obtaining a sample refrigerator operation dataset based on the refrigerator operation data set includes: The refrigerator's operating data set is parsed to obtain initial operating data; The integrity of the initial running data is verified, and if the integrity verification of the initial running data passes, it is determined whether there is any abnormality in the initial running data; Since the initial operating data is normal, the initial operating data is used as the sample refrigerator operating data collected at the current moment; The sample refrigerator operation dataset is obtained based on the sample refrigerator operation data collected at the current time and the sample refrigerator operation data collected at least one time prior to the current time.

5. The method according to claim 4, characterized in that, The method further includes: In response to the failure of the integrity verification of the initial operating data, or the anomaly of the initial operating data, the sample refrigerator operating data collected at the previous collection time is used as the sample refrigerator operating data collected at the current time.

6. The method according to claim 4, characterized in that, The sample refrigerator operation dataset is used to train a refrigerator fault prediction model. The process of obtaining the sample refrigerator operation dataset based on the sample refrigerator operation data collected at the current time, and the sample refrigerator operation data collected at least one time prior to the current time, includes: For any one of the at least one operating states, a sample data sequence corresponding to that operating state is determined; the sample data sequence includes: operating data of the operating state corresponding to at least one collection time before the current time and the sample refrigerator operating data; Labels are added to the sample data sequence to obtain the sample refrigerator operation dataset; the labels are used to characterize whether the target refrigerator is fault-free or the type of fault of the target refrigerator.

7. The method according to claim 6, characterized in that, Before adding labels to the sample data sequence to obtain the sample refrigerator running dataset, the method further includes: For any of the sample data sequences, in response to the fact that none of the operational data in the sample data sequence includes a fault identifier, the label of the sample data sequence is determined based on the operational data of at least one operational state of the target refrigerator at at least one acquisition time; In response to the presence of a fault identifier in the operational data within the sample data sequence, a label for the sample data sequence is determined based on the fault identifier.

8. The method according to claim 7, characterized in that, The step of determining the label of the sample data sequence based on operational data of at least one operational state of the target refrigerator at at least one acquisition time includes: Based on the operating data of at least one operating state of the target refrigerator at at least one collection time, the initial label of the sample data sequence is determined; Display the sample data sequence, and the initial label of the sample data sequence; In response to a user's modification of the initial label based on the sample data sequence, the label of the sample data sequence is determined.

9. An electronic device, characterized in that, include: Processor and memory; The processor is communicatively connected to the memory; The memory stores computer instructions; The processor executes computer instructions stored in the memory to implement the method as described in any one of claims 2-8.

10. A computer program product, characterized in that, It includes a computer program or instructions that, when executed by a processor, implement the method of any one of claims 2-8.

Images