Fault processing method and device of household appliance and computer readable storage medium

Abstract

The invention discloses a household appliance fault processing method and device and a computer readable storage medium. The method comprises the following steps: acquiring historical operation data of a household appliance; determining a probability value corresponding to a fault type of the household appliance based on the historical operation data; and according to the probability value corresponding to the determined fault type, performing fault processing on the corresponding household appliance. According to the invention, corresponding household appliance fault processing can be carried out according to different severity degrees of the household appliance, and fault processing and maintenance of the household appliance are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of household electrical appliances, and in particular to a method and device for handling a fault of a household electrical appliance, and a computer-readable storage medium. Background Art

[0002] There is a risk of failure during the use of home appliances. In order to ensure the normal operation of home appliances, it is crucial to predict and handle the failures of home appliances. In related technologies, when a home appliance failure is detected, the failure is repaired according to the failure type. However, the same failure type has different failure severity levels. If a unified failure handling method is used for failure repair, it is not conducive to the failure handling of home appliances. Summary of the invention

[0003] The embodiments of the present application provide a method, device and computer-readable storage medium for troubleshooting of household appliances, aiming to perform corresponding troubleshooting of household appliances according to different severity levels of household appliances, thereby achieving troubleshooting and maintenance of household appliances.

[0004] The embodiment of the present application provides a method for handling a fault of a household appliance, the method for handling a fault of a household appliance comprising:

[0005] Obtain historical operation data of home appliances;

[0006] Determining a probability value corresponding to a fault type of the household appliance based on the historical operation data;

[0007] According to the probability value corresponding to the determined fault type, corresponding fault processing of the household appliance is performed.

[0008] Optionally, the performing corresponding fault processing of the household appliance according to the determined probability value corresponding to the fault type includes:

[0009] When the probability value of the fault type is less than the preset probability, no fault processing is performed on the household appliance;

[0010] When the probability value of the fault type is greater than or equal to the preset probability, the parameters corresponding to the fault type are modified according to the probability value.

[0011] Optionally, when the probability value of the fault type is greater than or equal to the preset probability, the step of correcting the parameter corresponding to the fault type according to the probability value includes:

[0012] When the probability value of the fault type is greater than or equal to the preset probability, determining a probability value interval corresponding to the probability value;

[0013] Based on the correction method corresponding to the probability value interval, the parameters corresponding to the fault type are corrected.

[0014] Optionally, when at least two fault types exist simultaneously, the step of correcting the parameters corresponding to the fault types according to the probability values ​​includes:

[0015] When the parameters corresponding to different fault types are the same parameter, the corrected target parameter value is determined based on the probability values ​​corresponding to the different fault types, and the household appliance is controlled to operate with the corrected target parameter value.

[0016] Optionally, the step of determining a corrected target parameter value based on probability values ​​corresponding to different fault types includes:

[0017] Obtain correction parameter values ​​corresponding to probability values ​​of each fault type;

[0018] The minimum parameter value among all the corrected parameter values ​​is determined as the corrected target parameter value.

[0019] Optionally, the historical operation data includes operation status data and environment data, and the step of determining the probability value corresponding to the fault type of the household appliance based on the historical operation data includes:

[0020] Determining the fault type and fault parameter of the household appliance according to the relationship between the operating status data, the environmental data, the fault type and fault parameter of the household appliance;

[0021] Probability mapping is performed based on the fault parameters to obtain a probability value corresponding to the fault type.

[0022] Optionally, before the step of determining the fault type and fault parameter of the household appliance according to the operating status data, the environmental data, and the relationship between the fault type and fault parameter of the household appliance, the step further includes:

[0023] Record the operating status data and environmental data of household appliances in each operating cycle, as well as the historical fault types and historical fault parameters of household appliances after each operating cycle;

[0024] Training is performed based on the recorded historical operation data of the household appliance to generate the relationship between the operation status data, the environmental data, the fault type and fault parameters of the household appliance, so as to determine the fault type and fault parameters of the household appliance based on the relationship.

[0025] Optionally, the step of performing probability mapping based on the fault parameter to obtain a probability value corresponding to the fault type includes:

[0026] Based on a probability mapping algorithm, the fault parameter is mapped to a preset probability interval to obtain a probability value corresponding to the fault type. The probability mapping algorithm includes: one of: a sigmoid function algorithm, a tanh function algorithm, a relu function algorithm, a softmax algorithm, and a normalization algorithm. The larger the probability value, the higher the severity of the fault of the household appliance.

[0027] In addition, to achieve the above-mentioned purpose, the present invention also provides a fault handling device for household appliances, including: a memory, a processor, and a fault handling program for the household appliance stored on the memory and executable on the processor, wherein the fault handling program for the household appliance implements the steps of the above-mentioned fault handling method for the household appliance when executed by the processor.

[0028] In addition, to achieve the above-mentioned purpose, the present invention also provides a storage medium on which a fault handling program of a household appliance is stored, and when the fault handling program of the household appliance is executed by a processor, the steps of the fault handling method of the household appliance are implemented.

[0029] The technical solution of a method, device and computer-readable storage medium for handling faults of household appliances provided in the embodiments of the present application adopts a method of obtaining historical operation data of household appliances, predicting faults based on the historical operation data of household appliances, obtaining the fault type of household appliances and the probability value corresponding to the fault type, and finally performing corresponding fault handling on the household appliances according to the probability value corresponding to the fault type. Compared with the related art that uses the same fault handling method for the same fault type, the present application can perform corresponding fault handling for the probability values ​​corresponding to different fault types because different probability values ​​correspond to different fault severity, thereby improving the fault handling and maintenance capabilities of household appliances. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 A schematic diagram of a flow chart of a first embodiment of a method for troubleshooting household electrical appliances according to the present invention;

[0031] Figure 2 A schematic diagram of a flow chart of a second embodiment of a method for troubleshooting household electrical appliances according to the present invention;

[0032] Figure 3 A schematic diagram of a flow chart of a third embodiment of a method for troubleshooting household electrical appliances according to the present invention;

[0033] Figure 4 A schematic diagram of a flow chart of a fourth embodiment of a method for troubleshooting household electrical appliances according to the present invention;

[0034] Figure 5 It is a schematic diagram of the structure of the hardware operating environment involved in the embodiment of the present invention.

[0035] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. The above-mentioned drawings are only an embodiment diagram, not the entire invention. DETAILED DESCRIPTION

[0036] At present, there is a risk of failure during the use of household appliances. In order to enable the normal operation of household appliances, it is crucial to predict and handle the failures of household appliances. In the related art, when a household appliance failure is detected, the failure is usually repaired accordingly according to the type of failure. However, there are different degrees of failure severity. For example, when the severity of the failure of a household appliance is low, it does not affect the use of the household appliance. The household appliance can continue to work without troubleshooting. When the severity of the failure of a household appliance is high, there may be a risk that the household appliance cannot continue to work. At this time, the household appliance needs to be troubleshooted. The related art uses a unified fault handling method to repair the failure, and it is impossible to carry out corresponding fault handling for the different fault severities of the household appliances, which reduces the effect of the fault handling of the household appliances and seriously affects the use of the household appliances.

[0037] In response to the above problems, the present application proposes a method for handling faults of household appliances, which includes: obtaining historical operation data of the household appliances; determining the probability value corresponding to the fault type of the household appliances based on the historical operation data; and performing corresponding fault handling of the household appliances according to the probability value corresponding to the determined fault type. Compared with the related art that uses the same fault handling method for the same fault type, the present application can handle the faults according to the probability values ​​corresponding to different fault types because different probability values ​​correspond to different fault severity, thereby improving the fault handling and maintenance capabilities of household appliances.

[0038] In addition, in order to improve the prediction accuracy of fault types, the present application proposes a fault prediction model, which can be used to predict different fault types. The fault prediction model is trained by the operating status data and environmental data of the household appliance in each operating cycle, and the relationship between the historical fault type and the historical fault parameters of the household appliance after each cycle of operation. The present application inputs the historical operating data of the household appliance into the fault prediction model, which can accurately identify the specific fault type.

[0039] In addition, the related technology obtains the final fault probability based on the statistical fault frequency, which leads to the problem of low efficiency in determining the fault probability. The present application can perform probability mapping based on the fault type output by the above fault type model, accurately and quickly obtain the probability value corresponding to the fault type, and improve the efficiency of identifying the severity of the fault.

[0040] In order to better understand the above technical solution, exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0041] like Figure 1 As shown, in the first embodiment of the present application, the fault handling method of the household appliance of the present application is applied to the fault handling device of the household appliance, and the fault handling device of the household appliance can be a smart phone, a computer, a notebook or other device with the fault handling capability of the household appliance. The household appliance sends the historical operation data to the fault handling device, and the fault handling device predicts the fault of the household appliance and controls the household appliance to perform the corresponding fault handling of the household appliance. Optionally, the fault handling method of the household appliance of the present application can also be applied to the household appliance itself, and the household appliance stores the fault handling program of the household appliance, and when offline, executes the fault handling program locally.

[0042] The method for troubleshooting household appliances of the present application comprises the following steps:

[0043] Step S110, obtaining historical operation data of the household appliance.

[0044] In this embodiment, the household appliances include but are not limited to kitchen appliances, household appliances, household appliances, office appliances and new energy appliances. Among them, kitchen appliances can be microwave ovens, rice cookers, induction cookers, etc. Household appliances can be televisions, air conditioners, washing machines, electric fans, refrigerators, etc. Household appliances can be electric heaters, massagers, massage chairs, etc. Office appliances can be computers, copiers, printers, etc. New energy appliances can be solar water heaters, solar chargers, etc. This application takes the household appliance as an air conditioner as an example.

[0045] In this embodiment, the historical operation data refers to the operation status data and environmental data generated by the household appliance during its historical operation. Specifically, the historical operation data of the air conditioner includes, but is not limited to, indoor and outdoor ambient temperature, indoor and outdoor ambient humidity, wind speed, rotation speed, compressor operating frequency, etc. During operation, the air conditioner will store the collected operation data in a local database or upload it to a cloud server for storage in real time. When predicting a subsequent fault, the stored historical operation data is obtained for analysis. The historical operation data can also be classified and stored based on different dimensions, such as by region, space, season, etc., so that when performing a subsequent fault analysis, accurate fault prediction can be performed based on the data characteristics of different dimensions.

[0046] Optionally, the fault handling device of the household appliance can obtain the historical operation data of the household appliance in real time for fault prediction. The fault handling device of the household appliance can also obtain the historical operation data of the household appliance at regular intervals for fault prediction. The timing time can be set. When the timing time arrives, the historical operation data of the household appliance is obtained for fault prediction. The historical operation data of the household appliance can also be obtained according to actual conditions. For example, when a fault prediction instruction is received, the historical operation data of the household appliance is obtained for fault prediction. Other methods can also be used to obtain the historical operation data of the household appliance.

[0047] Optionally, after obtaining the historical operation data of the household appliance, in order to improve the accuracy of the fault prediction results, it is also necessary to process the historical operation data of the household appliance to filter out some interference data and duplicate data in the historical operation data, and then perform fault prediction of the household appliance based on the processed historical operation data to improve the accuracy of the fault prediction results.

[0048] Optionally, after obtaining the historical operation data of the household appliance, the data features of the historical operation data are extracted, and subsequent fault prediction is performed based on the data features. The historical operation data may be the average value, maximum value, minimum value, median value, etc. of the household appliance in a certain period of time. By extracting the data features of the historical operation data and then performing subsequent fault prediction based on the data features, the accuracy of the fault prediction result is improved.

[0049] Step S120: determining a probability value corresponding to the fault type of the household appliance based on the historical operation data.

[0050] In this embodiment, different household appliances have different fault types, and each fault type has a different probability value. Different probability values ​​represent different fault severity. When the probability value is larger, the fault severity is higher, and when the probability value is smaller, the fault severity is lower.

[0051] Optionally, the fault types of the household appliance include but are not limited to current frequency limiting, voltage frequency limiting, E-side fault, system pressure, over-temperature, over-temperature, etc.

[0052] In this embodiment, after obtaining the historical operation data of the household appliance, the fault type of the household appliance is determined, and then the probability value corresponding to the fault type is determined.

[0053] Determining the type of fault in a home appliance includes any of the following options:

[0054] Example 1: The historical operation data of the household appliance is input into a pre-trained fault prediction model, where the fault prediction model is trained by the relationship between different fault types and the historical operation data corresponding to the fault types. The historical operation data of the household appliance is input into the fault prediction model, and a mapping relationship with the highest similarity to the historical operation data is matched. The preset fault type corresponding to the mapping relationship is determined as the fault type of the household appliance.

[0055] Example 2: Determining the fault type of the household appliance also includes: performing cluster analysis based on the historical operation data of the household appliance to obtain the fault type of the household appliance. Specifically, the data features of the historical operation data of the household appliance are extracted, and the data features of the historical operation data corresponding to the time when the fault occurs are used as cluster centers. Each cluster center is used to characterize a fault type, and multiple cluster centers can be set. The Euclidean distance between the data features of the historical operation data of the household appliance and each cluster center can be calculated, and the fault type of the cluster center corresponding to the shortest Euclidean distance is determined as the fault type of the household appliance. Therefore, the historical operation data is classified by the clustering algorithm and the characteristics of the historical operation data to accurately determine the fault type of the household appliance.

[0056] Example three: The correspondence between different fault codes and fault types may also be pre-set; when a fault is detected in a home appliance, the fault code is obtained, and the fault type of the smart home appliance is determined based on the obtained fault code and the correspondence between the fault code and the fault type.

[0057] Other methods can also be used to determine the fault type of the household appliance, which are not listed here.

[0058] Optionally, after obtaining the fault type, the fault type is probability mapped to obtain a probability value corresponding to the fault type. Specifically, each fault type has a corresponding fault parameter, and different fault parameters under the same fault type can be mapped to different probability values, so that the severity of the fault can be accurately known. For example, when the fault type is too high temperature, the fault parameter can be a specific temperature value, and the temperature value can be probability mapped to obtain a probability value corresponding to the fault type.

[0059] In other embodiments, in addition to using probability values ​​to characterize the fault severity of household appliances, different fault levels may be set, and different fault levels correspond to different fault severity levels. The higher the fault level, the higher the corresponding fault severity, and the lower the fault level, the lower the corresponding fault severity. Specifically, each fault type has a corresponding fault parameter, and different fault parameters under the same fault type correspond to different parameter intervals, and each parameter interval corresponds to a different fault level. The fault parameters can be divided into different parameter intervals in advance, and different fault levels can be set for each parameter interval. For example, the fault parameter is 80°C, the corresponding parameter interval is the second parameter interval, and the corresponding fault level is fault level two. Thereby, the fault severity of the fault can be determined.

[0060] Step S130 , performing corresponding fault processing on the household appliance according to the determined probability value corresponding to the fault type.

[0061] In this embodiment, different probability values ​​correspond to different fault severity levels, and this application sets corresponding fault handling methods for different fault severity levels. It is possible to perform corresponding fault handling for probability values ​​corresponding to different fault types, thereby improving the fault handling and maintenance capabilities of household appliances.

[0062] In this embodiment, after determining the fault handling method of the home appliance, the fault handling device of the home appliance controls the home appliance to perform corresponding fault handling. At this time, the fault handling device of the home appliance establishes a communication connection relationship with the home appliance, and sends control information corresponding to the corresponding fault handling method to the home appliance, thereby realizing control and fault handling of the home appliance.

[0063] This application can predict the faults of home appliances in a timely manner and sense whether the home appliances are faulty in advance. It can also divide the probability of the fault types of home appliances into different areas and promptly inform the severity of the faults of home appliances. Finally, it can carry out corresponding targeted processing according to the severity of the faults of home appliances and can handle them in a timely manner to reduce the harm of the faults.

[0064] According to the above technical solution, this embodiment adopts a technical solution of obtaining the historical operation data of the home appliance, predicting the fault based on the historical operation data of the home appliance, obtaining the fault type of the home appliance and the probability value corresponding to the fault type, and finally performing corresponding fault processing on the home appliance according to the probability value corresponding to the fault type. Compared with the related art that uses the same fault processing method to process the same fault type, the present application can perform corresponding fault processing for the probability values ​​corresponding to different fault types because different probability values ​​correspond to different fault severity, thereby improving the fault processing and maintenance capabilities of the home appliance.

[0065] Further, refer to Figure 2 Based on the first embodiment, in the second embodiment of the present application, step S130 includes the following steps:

[0066] Step S131: when the probability value of the fault type is less than a preset probability, no fault processing is performed on the household appliance.

[0067] In this embodiment, the preset probability can be set according to actual conditions, for example, according to the type of household appliances, fault types, etc. Different household appliances correspond to different preset probabilities or different fault types are set to different preset probabilities.

[0068] In this embodiment, when the probability value of the fault type is less than the preset probability, it indicates that the fault severity of the home appliance is low and does not affect the normal use of the home appliance. The home appliance can continue to work without performing fault processing.

[0069] Step S132: when the probability value of the fault type is greater than or equal to the preset probability, modify the parameters corresponding to the fault type according to the probability value.

[0070] In this embodiment, when the probability value of the fault type is greater than or equal to the preset probability, the fault severity of the household appliance is high, and there may be a risk that the household appliance cannot continue to work. At this time, it is necessary to perform fault processing on the household appliance to resolve the fault of the household appliance.

[0071] In this embodiment, when the probability value of a fault type is greater than or equal to a preset probability, the probability value of the fault type of the household appliance is partitioned, that is, different probability value divisions correspond to different correction methods, and the corresponding correction method can be determined for different fault severities. The severity of the fault of the household appliance can be informed in time, and corresponding fault processing can be performed, thereby realizing refined adjustment and processing of the fault of the household appliance.

[0072] In this embodiment, when a fault occurs, the fault type and the corresponding parameters are obtained, and the parameters are corrected. The parameters can be the control parameters of the household appliance when the fault occurs, hereinafter referred to as fault parameters. The parameters here include but are not limited to the expansion valve angle, compressor operating frequency, fan speed, etc.

[0073] According to the above technical solution, this embodiment can divide the probability values ​​of the fault types of household appliances into different zones, determine corresponding correction methods according to different fault severities, promptly inform the fault severity of the household appliances, and perform corresponding fault processing, thereby realizing refined adjustment and processing of the faults of the household appliances.

[0074] Further, refer to Figure 3Based on the second embodiment, in the third embodiment of the present application, step S132 includes the following steps:

[0075] Step S1321: when the probability value of the fault type is greater than or equal to the preset probability, determine the probability value interval corresponding to the probability value.

[0076] Step S1322: Correct the parameters corresponding to the fault type based on the correction method corresponding to the probability value interval.

[0077] In this embodiment, each probability value has a corresponding probability value interval. The probability value of this application is between 0 and 1, so the probability value interval is obtained by dividing 0 to 1. Different probability value intervals can be divided into different probability value intervals in advance, and each probability value interval has a corresponding correction method. Based on the correction method, the parameters corresponding to the fault type are corrected.

[0078] For example, the correction methods corresponding to different probability value intervals are shown in Table 1:

[0079] Table 1

[0080]

[0081] According to Table 1, the specific troubleshooting methods are as follows:

[0082] For the current frequency limiting fault, if the probability value interval is greater than 0.2 and less than 0.6, then it can be seen from Table 1 that the current fault will not be processed;

[0083] For voltage frequency limiting fault, if the probability value interval is greater than 0.6 and less than 0.8, then it can be seen from Table 1 that the compressor frequency must be corrected and the current compressor frequency must be corrected to the f3 value;

[0084] For system pressure failure, if the probability value interval is greater than 0.8 and less than 0.9, then it can be seen from Table 1 that the expansion valve angle needs to be corrected and the expansion valve angle is adjusted to the c value.

[0085] The preset probability of this application can be set to 0.6.

[0086] According to the above technical solution, in this embodiment, when the probability value is greater than or equal to the preset probability, a corresponding correction method is determined for the probability value interval corresponding to the probability value, so as to achieve refined adjustment and fault handling of the household appliance.

[0087] Further, refer to Figure 4 Based on the second embodiment, in the fourth embodiment of the present application, step S130 includes the following steps:

[0088] Step S231, when the parameters corresponding to different fault types are the same parameter, a corrected target parameter value is determined based on the probability values ​​corresponding to the different fault types, and the home appliance is controlled to operate with the corrected target parameter value.

[0089] In this embodiment, since the household appliance may have at least two faults at the same time, that is, at least two fault types may exist at the same time. Since the parameters corresponding to different fault types may be the same parameter but the parameter values ​​corresponding to the parameters are different, that is, two faults occur at the same time and the parameters that need to be corrected are of the same type, it is necessary to adjust the parameter values ​​to parameter values ​​that can meet the correction requirements of these faults. Based on the probability values ​​corresponding to different fault types, the corrected target parameter value can be determined, and the household appliance can be controlled to operate with the corrected target parameter value. Specifically, the probability values ​​corresponding to different fault types are determined, the correction methods corresponding to different probability values ​​are determined, the parameters and parameter values ​​associated with the correction methods are obtained, and when the parameters are the same parameter, the target parameter value is determined from the parameter values ​​corresponding to all parameters, and the household appliance is controlled to be corrected to the target parameter value, and the household appliance is controlled to operate with the corrected target parameter value.

[0090] Optionally, obtain the correction parameter value corresponding to the probability value of each fault type, and determine the minimum parameter value among all the corrected parameter values ​​as the corrected target parameter value. For example, if the probability values ​​of current frequency limiting and voltage frequency limiting occurring at the same time are both greater than 0.6 and less than 0.8, it can be seen from Table 1 that the compressor operating frequency needs to be adjusted, then it is necessary to determine the corrected compressor operating frequency value, and the corrected compressor operating frequency value can solve the faults corresponding to the above-mentioned fault types at the same time. At this time, the compressor operating frequency value should select the smaller value between f1 and f3. Selecting the minimum compressor operating frequency can avoid sudden changes in the cooling or heating temperature of household appliances, achieve stable operation of household appliances, and improve comfort.

[0091] Further, based on the first embodiment, in the fifth embodiment of the present application, step S120 includes the following steps:

[0092] Step S121, determining the fault type and fault parameters of the household appliance according to the operating status data, the environmental data, and the relationship between the fault type and fault parameters of the household appliance;

[0093] Step S122: performing probability mapping based on the fault parameters to obtain a probability value corresponding to the fault type.

[0094] In this embodiment, the historical operation data of the present application includes operation status data and environmental data. The environmental data includes but is not limited to: indoor and outdoor environmental temperature and indoor and outdoor environmental humidity. The operation status data includes but is not limited to: wind speed, rotation speed, compressor operating frequency, etc. The historical operation data of the air conditioner includes but is not limited to indoor and outdoor environmental temperature, indoor and outdoor environmental humidity, wind speed, rotation speed, compressor operating frequency, etc.

[0095] Optionally, the operation status data and environmental data of the household appliance in each operation cycle, as well as the historical fault types and historical fault parameters of the household appliance after each cycle of operation are recorded; training is performed based on the recorded historical operation data of the household appliance to generate a relationship between the operation status data, the environmental data, the fault type and fault parameters of the household appliance, so as to determine the fault type and fault parameters of the household appliance based on the relationship. Thus, a fault prediction model capable of predicting different fault types is obtained.

[0096] In this embodiment, after the fault parameters are obtained, probability mapping is performed on the fault parameters to obtain probability values ​​corresponding to the fault types.

[0097] Optionally, the fault parameter is mapped to a preset probability interval based on a probability mapping algorithm to obtain a probability value corresponding to the fault type, and the probability mapping algorithm includes: one of a sigmoid function algorithm, a tanh function algorithm, a relu function algorithm, a softmax algorithm, and a normalization algorithm. The larger the probability value, the higher the severity of the fault of the household appliance. Among them, the preset probability interval is 0 to 1. The corresponding probability mapping algorithm can be selected according to the actual situation to map the fault parameter to between 0 and 1 to obtain the probability value corresponding to the fault type. The way in which different probability mapping algorithms map probability values ​​is not repeated here.

[0098] Taking the air conditioner as an example, the following will introduce the training process of the fault prediction model in detail:

[0099] (1) Count the historical operation data of the air conditioner, take the fault type as the target value Y, and the historical operation data as the input value X;

[0100] (2) In order for the subsequent model to converge quickly, the input values ​​need to be normalized, that is, each value is subtracted from its mean and divided by its standard deviation;

[0101] (3) To increase the speed of model training, we can also perform principal component analysis (PCA) on the X data set to reduce its dimensionality, that is, convert the original N*M matrix into N*K, where K <M;

[0102] (4) Use a machine learning model or neural network to train X and Y;

[0103] (5) To prevent overfitting and improve robustness, the following measures can be taken: use batch normalization for X, select a dropout network structure in the neural network, use L2 regularization to penalize the loss function, select more X data sets, and gradually change the learning rate from large to small.

[0104] (6) The target value fault Y is a set of faults, consisting of a number of y, that is, Y = {y1, y2, y3, ..., yn}, where y1~yn represent n faults of the air conditioner;

[0105] (7) Model each fault, that is, establish n fault prediction models. The X used may or may not be shared.

[0106] Thus, a fault prediction model that can be used to predict different fault types is obtained through training, thereby realizing the prediction of different types of faults.

[0107] The embodiments of the present invention provide an embodiment of a method for troubleshooting a household appliance. It should be noted that although a logical sequence is shown in the flowchart, in some cases, the steps shown or described may be executed in an order different from that shown here.

[0108] like Figure 5 As shown, Figure 5 The present invention is a schematic diagram of the structure of the hardware operating environment of the fault handling device of the household appliance involved in the embodiment of the present invention. The fault handling device of the household appliance may include: a processor 1001, such as a CPU, a memory 1005, a user interface 1003, a network interface 1004, and a communication bus 1002. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen, an input unit such as a keyboard, and the user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface). The memory 1005 may be a high-speed RAM memory or a stable memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0109] Those skilled in the art will understand that Figure 5 The structure of the fault handling device for household appliances shown in the figure does not constitute a limitation on the fault handling device for household appliances, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0110] like Figure 5As shown, the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and a fault handling program of a home appliance. The operating system is a program for managing and controlling the hardware and software resources of the fault handling device of the home appliance, the operation of the fault handling program of the home appliance, and other software or programs.

[0111] exist Figure 5 In the fault handling device for household appliances shown, the user interface 1003 is mainly used to connect to the terminal and communicate data with the terminal; the network interface 1004 is mainly used for the background server and communicates data with the background server; the processor 1001 can be used to call the fault handling program of the household appliance stored in the memory 1005.

[0112] In this embodiment, the fault handling device of the household appliance includes: a memory 1005, a processor 1001, and a fault handling program of the household appliance stored in the memory and executable on the processor, wherein:

[0113] When the processor 1001 calls the fault handling program of the household appliance stored in the memory 1005, the following operations are performed:

[0114] Obtain historical operation data of home appliances;

[0115] Determining a probability value corresponding to a fault type of the household appliance based on the historical operation data;

[0116] According to the probability value corresponding to the determined fault type, corresponding fault processing of the household appliance is performed.

[0117] Based on the same inventive concept, an embodiment of the present application also provides a computer-readable storage medium, which stores a fault handling program for a household appliance. When the fault handling program for the household appliance is executed by a processor, the various steps of the fault handling method for the household appliance as described above are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0118] Since the storage medium provided in the embodiments of the present application is the storage medium used to implement the method of the embodiments of the present application, based on the method introduced in the embodiments of the present application, the person skilled in the art can understand the specific structure and deformation of the storage medium, so it is not repeated here. All storage media used in the methods of the embodiments of the present application belong to the scope of protection of this application.

[0119] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0120] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0121] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for enabling a terminal home appliance (which can be a mobile phone, computer, server, TV, or network home appliance, etc.) to execute the methods described in each embodiment of the present invention.

[0122] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for troubleshooting household electrical appliances, characterized in that: The method for handling a fault of a household appliance comprises: Obtain historical operation data of home appliances; Determining a probability value corresponding to a fault type of the household appliance based on the historical operation data; According to the probability value corresponding to the determined fault type, corresponding fault processing of the household appliance is performed.

2. The method for troubleshooting household electrical appliances according to claim 1, characterized in that: The method of performing corresponding fault processing of the household appliance according to the determined probability value corresponding to the fault type includes: When the probability value of the fault type is less than the preset probability, no fault processing is performed on the household appliance; When the probability value of the fault type is greater than or equal to the preset probability, the parameters corresponding to the fault type are modified according to the probability value.

3. The method for troubleshooting household electrical appliances according to claim 2, characterized in that: When the probability value of the fault type is greater than or equal to the preset probability, the step of correcting the parameter corresponding to the fault type according to the probability value comprises: When the probability value of the fault type is greater than or equal to the preset probability, determining a probability value interval corresponding to the probability value; Based on the correction method corresponding to the probability value interval, the parameters corresponding to the fault type are corrected.

4. The method for troubleshooting household electrical appliances according to claim 2, characterized in that: When at least two fault types exist simultaneously, the step of correcting the parameters corresponding to the fault types according to the probability values ​​includes: When the parameters corresponding to different fault types are the same parameter, the corrected target parameter value is determined based on the probability values ​​corresponding to the different fault types, and the household appliance is controlled to operate with the corrected target parameter value.

5. The method for troubleshooting household electrical appliances according to claim 4, characterized in that: The step of determining the corrected target parameter value based on the probability values ​​corresponding to different fault types includes: Obtain correction parameter values ​​corresponding to probability values ​​of each fault type; The minimum parameter value among all the corrected parameter values ​​is determined as the corrected target parameter value.

6. The method for troubleshooting household electrical appliances according to claim 1, characterized in that: The historical operation data includes operation status data and environment data. The step of determining the probability value corresponding to the fault type of the household appliance based on the historical operation data includes: Determining the fault type and fault parameter of the household appliance according to the relationship between the operating status data, the environmental data, the fault type and fault parameter of the household appliance; Probability mapping is performed based on the fault parameters to obtain a probability value corresponding to the fault type.

7. The method for troubleshooting household electrical appliances according to claim 6, characterized in that: Before the step of determining the fault type and fault parameter of the household appliance according to the relationship between the operating status data, the environmental data, the fault type and the fault parameter of the household appliance, the step further includes: Record the operating status data and environmental data of household appliances in each operating cycle, as well as the historical fault types and historical fault parameters of household appliances after each operating cycle; Training is performed based on the recorded historical operation data of the household appliance to generate the relationship between the operation status data, the environmental data, the fault type and fault parameters of the household appliance, so as to determine the fault type and fault parameters of the household appliance based on the relationship.

8. The method for troubleshooting household electrical appliances according to claim 6, characterized in that: The step of performing probability mapping based on the fault parameters to obtain the probability value corresponding to the fault type comprises: Based on a probability mapping algorithm, the fault parameter is mapped to a preset probability interval to obtain a probability value corresponding to the fault type. The probability mapping algorithm includes: one of: a sigmoid function algorithm, a tanh function algorithm, a relu function algorithm, a softmax algorithm, and a normalization algorithm. The larger the probability value, the higher the severity of the fault of the household appliance.

9. A fault handling device for household appliances, characterized in that: The fault handling device of the household appliance comprises: a memory, a processor, and a fault handling program of the household appliance stored in the memory and running on the processor. When the fault handling program of the household appliance is executed by the processor, the steps of the fault handling method of the household appliance as described in any one of claims 1 to 8 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a fault handling program for a household appliance, and when the fault handling program for the household appliance is executed by a processor, the steps of the fault handling method for a household appliance according to any one of claims 1 to 8 are implemented.

Images