Weighing method and device of washing machine, washing machine, storage medium, processor and program product

Abstract

The invention discloses a weighing method and device of a washing machine and the washing machine. The method comprises the steps of collecting a current value of a motor of the washing machine in the process that the washing machine runs according to a first speed; multiple target current values are extracted from the data set corresponding to the current values, and the multiple target current values are current values which completely describe at least one wave crest in the current values; acquiring a curve characteristic value of a current curve corresponding to the target current value; a weighing value corresponding to the curve characteristic value is determined through a weight prediction model, the weight prediction model is a model obtained by using multiple groups of training data through machine learning training, and each group in the multiple groups of training data comprises a sample curve characteristic value and a sample clothes weight corresponding to the sample curve characteristic value; and obtaining the weight of the clothes in the washing machine according to the weighing value. According to the invention, the technical problem of low weighing accuracy of the washing machine in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the field of household appliance control technology, and in particular to a washing machine weighing method and device, a washing machine, a storage medium, a processor, and a program product. Background Art

[0002] Machine learning (ML) is a branch of artificial intelligence that enables computers to learn from data and improve their performance without being explicitly programmed. By building mathematical models, machine learning algorithms can extract patterns and regularities from large amounts of data and use these regularities to make predictions or decisions. Common machine learning tasks include classification, regression, clustering, and dimensionality reduction.

[0003] Currently, washing machine weighing modes are divided into light, medium, and heavy load modes. However, the prediction of light loads and large eccentricity is inaccurate. Differences in electrical potential caused by different clothes under the same load can also lead to inaccurate weight predictions, affecting subsequent washing processes and the user experience.

[0004] Some existing AI technologies used in washing machines can only solve problems through deep learning. However, deep learning has very high hardware requirements and requires high hardware costs. Another way is to transfer data to a cloud server, but this method also increases costs or takes longer to respond.

[0005] To address the above-mentioned problems, no effective solutions have been proposed so far. Summary of the Invention

[0006] Embodiments of the present invention provide a washing machine weighing method and device, a washing machine, a storage medium, a processor, and a program product, to at least solve the technical problem of low accuracy in washing machine weighing in the related art.

[0007] According to one aspect of an embodiment of the present invention, a method for weighing a washing machine is provided, comprising: collecting a current value of a motor of the washing machine while the washing machine is operating at a first speed; extracting multiple target current values ​​from a data set corresponding to the current value; obtaining curve characteristic values ​​of a current curve corresponding to the target current value; determining a weighing value corresponding to the curve characteristic value through a weight prediction model; and obtaining the weight of clothes inside the washing machine based on the weighing value; wherein obtaining the curve characteristic value of the current curve corresponding to the target current value comprises: fitting the target current value through a least squares method to obtain a fifth-order fitting curve corresponding to the target current value; and obtaining the curve characteristic value based on the fifth-order fitting curve.

[0008] Optionally, while the washing machine is running at a first speed, the current value of the motor of the washing machine is collected, including: when it is detected that there are clothes in the washing machine, controlling the speed of the washing machine to increase to the first speed with a first acceleration; when it is detected that the speed reaches the first speed, performing a current value collection operation on the motor at a predetermined frequency; after determining that the current value collection operation continues for a predetermined period of time, obtaining the current value.

[0009] Optionally, multiple target current values ​​are extracted from the data set corresponding to the current value, including: normalizing the current value to obtain the normalized current value; extracting the current value corresponding to the data segment where the target current peak is located from the normalized current value as the multiple target current values.

[0010] Optionally, normalizing the current values ​​to obtain the normalized current values ​​includes: multiplying each of the current values ​​by a predetermined integer value to normalize the current values ​​to obtain the normalized current values.

[0011] Optionally, the curve characteristic value is obtained according to the fifth-order fitting curve, including: obtaining the mean of the fifth-order fitting curve according to the center position of the fifth-order fitting curve; obtaining the skewness of the fifth-order fitting curve according to the symmetry of the fifth-order fitting curve; obtaining the kurtosis of the fifth-order fitting curve according to the peak morphology of the fifth-order fitting curve; obtaining the standard deviation of the fifth-order fitting curve according to the extension degree of the fifth-order fitting curve; obtaining the peak value of the fifth-order fitting curve according to the maximum position of the fifth-order fitting curve; obtaining the phase of the fifth-order fitting curve according to the periodic information of the fifth-order fitting curve; and obtaining the entropy of the fifth-order fitting curve according to the complexity of the fifth-order fitting curve.

[0012] Optionally, before determining the weighing value corresponding to the curve characteristic value, the weighing method of the washing machine also includes: obtaining multiple groups of training data including multiple sample curve characteristic values ​​and multiple sample clothing weights; training the multiple groups of training data to obtain the weight prediction model.

[0013] According to another aspect of an embodiment of the present invention, a weighing device for a washing machine is provided, comprising: a collection unit for collecting the current value of a motor of the washing machine while the washing machine is operating at a first speed; an extraction unit for extracting multiple target current values ​​from a data set corresponding to the current values; a first acquisition unit for obtaining curve characteristic values ​​of a current curve corresponding to the target current values; a determination unit for determining a weighing value corresponding to the curve characteristic value through a weight prediction model; and a second acquisition unit for obtaining the weight of the clothes inside the washing machine based on the weighing value.

[0014] Optionally, the acquisition unit includes: a control module, used to control the speed of the washing machine to increase to the first speed at a first acceleration when detecting the presence of clothes in the washing machine; an acquisition module, used to perform a current value acquisition operation on the motor at a predetermined frequency when detecting that the speed reaches the first speed; and a first acquisition module, used to obtain the current value after determining that the current value acquisition operation continues for a predetermined period of time.

[0015] Optionally, the extraction unit includes: a normalization processing module, used to normalize the current value to obtain the normalized current value; an extraction module, used to extract the current value corresponding to the data segment where the target current peak is located from the normalized current value as the multiple target current values.

[0016] Optionally, the normalization processing module includes: a normalization processing submodule, configured to multiply each of the current values ​​by a predetermined integer value to perform normalization processing on the current value to obtain the normalized current value.

[0017] Optionally, the first acquisition unit includes: a fitting processing module, used to fit the target current value through the least squares method to obtain a fifth-order fitting curve corresponding to the target current value; and a second acquisition module, used to obtain the curve characteristic value according to the fifth-order fitting curve.

[0018] Optionally, the second acquisition module includes: a first acquisition submodule, used to obtain the mean of the fifth-order fitting curve according to the center position of the fifth-order fitting curve; a second acquisition submodule, used to obtain the skewness of the fifth-order fitting curve according to the symmetry of the fifth-order fitting curve; a third acquisition submodule, used to obtain the kurtosis of the fifth-order fitting curve according to the peak morphology of the fifth-order fitting curve; a fourth acquisition submodule, used to obtain the standard deviation of the fifth-order fitting curve according to the extension degree of the fifth-order fitting curve; a fifth acquisition submodule, used to obtain the peak value of the fifth-order fitting curve according to the maximum position of the fifth-order fitting curve; a sixth acquisition submodule, used to obtain the phase of the fifth-order fitting curve according to the periodic information of the fifth-order fitting curve; and a seventh acquisition submodule, used to obtain the entropy of the fifth-order fitting curve according to the complexity of the fifth-order fitting curve.

[0019] Optionally, the weighing device of the washing machine also includes: a third acquisition unit, used to obtain multiple sets of training data including multiple sample curve characteristic values ​​and multiple sample clothing weights before determining the weighing value corresponding to the curve characteristic value; a training unit, used to train the multiple sets of training data to obtain the weight prediction model.

[0020] According to another aspect of the embodiments of the present invention, a washing machine is provided, wherein the washing machine uses any one of the above-described weighing methods for washing machines.

[0021] According to another aspect of the embodiments of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium includes a stored program, wherein the program executes any one of the above-mentioned weighing methods for a washing machine.

[0022] According to another aspect of the embodiments of the present invention, a processor is provided, which is configured to run a program, wherein the program executes any one of the above-mentioned washing machine weighing methods when running.

[0023] According to another aspect of the embodiments of the present invention, a computer program product is provided, comprising computer instructions, wherein when the computer instructions are executed by a processor, any one of the above-mentioned washing machine weighing methods is executed.

[0024] In an embodiment of the present invention, while a washing machine is operating at a first speed, the current value of the washing machine's motor is collected; multiple target current values ​​are extracted from a data set corresponding to the current values; curve characteristic values ​​of the current curve corresponding to the target current values ​​are obtained; a weight prediction model is used to determine a weighing value corresponding to the curve characteristic value; and the weight of the clothing inside the washing machine is obtained based on the weighing value. The technical solution provided by the present invention achieves the purpose of obtaining the weight of the clothing inside the washing machine by collecting current data from the washing machine's motor during operation, extracting a portion of the collected current data, and obtaining the characteristic values ​​of the current curve corresponding to this portion of current data. These characteristic values ​​are then used as input to a pre-trained model, thereby achieving the technical effect of improving washing machine weighing accuracy and thereby resolving the technical problem of low accuracy in washing machine weighing in the related art. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0026] Figure 1 This is a hardware structure block diagram of a mobile terminal for a washing machine weighing method according to an embodiment of the present invention;

[0027] Figure 2 is a flow chart of a weighing method for a washing machine according to an embodiment of the present invention;

[0028] Figure 3 is a flow chart of an optional washing machine weighing method according to an embodiment of the present invention;

[0029] Figure 4 is a current scatter plot corresponding to multiple current values ​​according to an embodiment of the present invention;

[0030] Figure 5 is a graph of weight differences between groups according to an embodiment of the present invention;

[0031] Figure 6 is a current fitting curve diagram according to an embodiment of the present invention;

[0032] Figure 7 2 is a schematic diagram of a weighing device for a washing machine according to an embodiment of the present invention. DETAILED DESCRIPTION

[0033] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0034] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0035] As described in the background art, the related art has the disadvantage of low accuracy in weighing washing machines. Embodiments of the present invention provide a washing machine weighing method and apparatus, a washing machine, a computer-readable storage medium, a processor, and a computer program product.

[0036] The technical solutions in the embodiments of the present invention will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present invention.

[0037] The method embodiments provided in the embodiments of the present invention can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 FIG. 1 is a hardware structure block diagram of a mobile terminal for a washing machine weighing method according to an embodiment of the present invention. Figure 1As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown) a processor 102 (the processor 102 may include but is not limited to a microprocessor MCU or a programmable logic device FPGA and other processing devices) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input and output device 108 for communication functions. It will be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the mobile terminal. Figure 1 More or fewer components than shown, or with Figure 1 Different configurations shown.

[0038] The memory 104 can be used to store computer programs, such as software programs and modules of application software, such as the computer program corresponding to the weighing method of the washing machine in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer programs stored in the memory 104, thereby implementing the above-mentioned method. The memory 104 may include high-speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of such networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof. The transmission device 106 is used to receive or send data via a network. Specific examples of such networks may include a wireless network provided by the mobile terminal's telecommunications provider. In one example, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0039] Example 1

[0040] According to an embodiment of the present invention, a method embodiment of a weighing method for a washing machine is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0041] Figure 2 FIG. 1 is a flow chart of a weighing method for a washing machine according to an embodiment of the present invention. Figure 2 As shown, the weighing method of the washing machine includes the following steps:

[0042] Step S202 : While the washing machine is running at a first speed, the current value of the motor of the washing machine is collected.

[0043] Optionally, the first speed is a stable speed set by the washing machine's drum during the weighing process. This speed is chosen to ensure even distribution of clothing within the washing machine and facilitate stable measurement of motor current, thereby obtaining accurate current data for machine learning model analysis. It is typically set somewhere between the washing machine's minimum speed and the normal wash speed, ensuring sufficient movement of clothing within the drum to reflect its weight and distribution, but not too high to cause unnecessary energy consumption or equipment wear.

[0044] That is, it refers to a specific rotational speed of the washing machine drum. This speed is chosen to ensure that the clothes in the drum are evenly distributed and to produce predictable fluctuations in the motor current, which facilitates the subsequent extraction and analysis of eigenvalues.

[0045] For example, after starting a washing machine, the user can place laundry into the drum. The washing machine then runs at the aforementioned first speed. During this process, motor current data (i.e., current value) can be collected. For example, at a stable speed, motor current data can be collected at a certain frequency (e.g., 100 Hz) for approximately 2 seconds to ensure sufficient data reflecting the weight and distribution of the laundry.

[0046] Step S204 : extracting a plurality of target current values ​​from the data set corresponding to the current values, wherein the plurality of target current values ​​are current values ​​that completely describe at least one peak in the current values.

[0047] Optionally, the at least one peak current value is a value that represents the regular fluctuations in the motor current value during operation of the washing machine due to factors such as the distribution and texture of the laundry. The peak current value is the value at which the current reaches its peak and begins to decrease, and these values ​​contain important information about the weight of the laundry.

[0048] In this embodiment, current values ​​that fully describe at least one peak can be screened out from the collected current value data set. These current values ​​are considered to be target current values ​​because they contain the most critical information reflecting the weight and distribution of the clothes.

[0049] Step S206: Obtain a curve characteristic value of the current curve corresponding to the target current value.

[0050] Alternatively, the current curve reflects the temporal trend of the motor current in the washing machine's weighing system. During operation, the motor drives the drum. When the drum is loaded with laundry of varying weights and distribution, the current required by the motor changes. These changes can be monitored and recorded in real time by a current sensor, generating a current curve.

[0051] Optionally, the curve characteristic values ​​are a series of numerical values ​​obtained by mathematically analyzing the target current value data curve. They reflect the shape and distribution characteristics of the current curve and are the basis for training and prediction of the machine learning model.

[0052] In this embodiment, the current curve formed by the target current value can be deeply analyzed to extract numerical indicators representing the characteristics of the current curve. These indicators are called curve characteristic values ​​and may include but are not limited to statistical characteristics such as mean, standard deviation, and peak value.

[0053] Step S208: Determine the weighing value corresponding to the curve characteristic value through the weight prediction model, wherein the weight prediction model is a model obtained by machine learning training using multiple sets of training data, and each set of the multiple sets of training data includes: a sample curve characteristic value and a sample clothing weight corresponding to the sample curve characteristic value.

[0054] Here, the extracted curve eigenvalues ​​are used as input and sent to a model that has been trained by machine learning. The model is based on multiple sets of training data, where each set of data contains sample curve eigenvalues ​​and their corresponding sample clothing weights. Through the model's calculations, the estimated weight of the clothing corresponding to the eigenvalues ​​is obtained.

[0055] Step S210: Obtain the weight of the clothes in the washing machine according to the weighing value.

[0056] In this embodiment, the weighing value obtained above is determined to be the weight of the clothes in the washing machine.

[0057] As can be seen from the above, in an embodiment of the present invention, when the washing machine is running at a first speed, the current value of the motor of the washing machine is collected; multiple target current values ​​are extracted from the data set corresponding to the current value, wherein the multiple target current values ​​are current values ​​that fully describe at least one peak in the current value; the curve characteristic value of the current curve corresponding to the target current value is obtained; the weighing value corresponding to the curve characteristic value is determined through a weight prediction model, wherein the weight prediction model is a model obtained by machine learning training using multiple groups of training data, and each group of the multiple groups of training data includes: a sample curve characteristic value and a sample clothing weight corresponding to the sample curve characteristic value; the weight of the clothes inside the washing machine is obtained according to the weighing value, thereby realizing the purpose of obtaining the weight accuracy of the clothes inside the washing machine by collecting the current data of the motor of the washing machine during operation, extracting part of the current data from the collected current data, and obtaining the characteristic value of the current curve corresponding to this part of the current data, and using these characteristic values ​​as input of the pre-trained model to obtain the weight of the clothes inside the washing machine, thereby achieving the technical effect of providing weighing accuracy of the washing machine.

[0058] Therefore, the technical solution provided by the embodiment of the present invention solves the technical problem of low accuracy in washing machine weighing in the related art.

[0059] According to the above embodiment of the present invention, while the washing machine is running at a first speed, collecting the current value of the motor of the washing machine may include: when detecting the presence of clothes in the washing machine, controlling the speed of the washing machine to increase to the first speed with a first acceleration; when the detection speed reaches the first speed, performing a current value collection operation on the motor at a predetermined frequency; after determining that the current value collection operation continues for a predetermined period of time, obtaining the current value.

[0060] In this embodiment, the process of collecting the motor current value is described in detail, including the specific steps of starting the washing machine, accelerating to the first speed, running stably, and collecting the current value.

[0061] For example, after a washing machine detects the presence of laundry, it controls the drum to accelerate at an acceleration a1 (i.e., a first acceleration) (e.g., 0.7 rpm / s) to a first speed V1 (e.g., 90 rpm). Once the drum stabilizes at speed V1, it collects the motor's current at a predetermined frequency (e.g., 200 Hz). This current collection continues for a predetermined period (e.g., 5 seconds) to obtain multiple current values.

[0062] For example, in a home environment, when parents need to quickly finish washing clothes before their children get home from school, the washing machine can quickly start and accelerate to the first speed (V1rpm), such as 60rpm, to minimize the impact of the weighing process on the overall washing time. After the washing machine detects the presence of clothes and begins accelerating to V1rpm at a first acceleration (for example, 0.5rpm / s), once the set speed is reached, it immediately begins collecting motor current values ​​at a predetermined frequency (for example, 100Hz) until the duration (for example, 2 seconds) is over. This process is fast and efficient, eliminating the need to wait for a long time to collect data, meeting the needs of home users for fast laundry.

[0063] Figure 3 : is a flow chart of an optional washing machine weighing method according to an embodiment of the present invention, such as Figure 3 As shown in the figure, a drum washing machine is used as an example. After the drum washing machine is turned on, the door is opened and clothes are loaded. The machine is controlled to accelerate from a static state at an acceleration of a1 rpm / s to V1 rpm. The machine is allowed to maintain a constant speed of V1 rpm for a period of time, and a large number of scattered current values ​​of the motor are collected at a frequency of f.

[0064] It's important to note that the speed and acceleration values ​​here are specific to the specific machine model. Different weighing strategies can give different values, depending on the programmer's design. Specifically, the acceleration value can be set anywhere within a reasonable range, typically by the washing machine's main control developer based on the machine's operating stage; 30 rpm / s is a common setting. The speed value is determined by the different weighing strategies.

[0065] In addition, it should be noted that the predetermined frequency f and duration (predetermined duration) t here are freely controllable quantities. When the frequency f is higher, more current values ​​are collected per second. Similarly, when the duration is longer, more current values ​​are collected when the frequency is constant. The predetermined frequency f and duration t are determined according to Figure 4 ( Figure 4 The calculation is performed based on 20,000 current scatter points in a current scatter diagram corresponding to multiple current values ​​according to an embodiment of the present invention. The execution time (in seconds) at a frequency of 50 Hz is: total number of points / number of points per second = 20,000 / 50 = 400 seconds.

[0066] By precisely controlling the washing machine's acceleration process and collecting data at a stable speed, the representativeness of the current values ​​is ensured, thereby improving the accuracy and reliability of the model prediction.

[0067] The standardization and precise control of this process enable the machine learning model to receive high-quality input data, thereby improving the accuracy and speed of weighing and reducing dependence on hardware performance.

[0068] According to the above embodiment of the present invention, extracting multiple target current values ​​from a data set corresponding to the current value may include: normalizing the current value to obtain a normalized current value; extracting the current value corresponding to the data segment where the target current peak is located from the normalized current value as multiple target current values.

[0069] Optionally, the target current peak value is a current peak value in a current curve segment displayed on an oscilloscope that can fully describe a wave crest.

[0070] In this embodiment, the collected multiple current values ​​can be amplified and a current scatter plot corresponding to the amplified multiple current values ​​can be generated. That is, the measured current value scatter points are plotted in the coordinate system as Figure 4 In the current scatter plot, the horizontal axis represents the number of scatter points, and the vertical axis represents the current value after amplification. Different colors in the figure represent the values ​​obtained from four experiments. It mainly represents the scatter points of each current value measured in the coordinate system. Figure 4 It can be seen that the difference in the scatter curves of the same weight is very small.

[0071] For example, the collected current value is amplified, and then a scatter plot of the amplified current is generated. The peak position in the scatter plot is determined, and the current value corresponding to the peak interval is extracted as the target current value.

[0072] For example, when a laundry room processes large quantities of clothing of varying weights and types, the washing machine generates a current scatter plot by amplifying the processing current value (for example, multiplying it by n=1000) to accurately identify the distribution of clothing in the drum. After generating the scatter plot, the system automatically analyzes and identifies the peaks, accurately distinguishing between clothing of varying weights. This ensures weighing accuracy even in environments where clothing types and weights fluctuate frequently. Extracting the current value corresponding to the peak as target data significantly reduces the time required to adjust washing programs due to incorrect weighing, significantly improving efficiency for laundries processing clothing in batches.

[0073] The amplification process here helps to improve the resolution of the data, facilitates subsequent peak identification and feature extraction, and solves the problem of insufficient accuracy of the original data.

[0074] By amplifying the current value and extracting the peak current, the analyzability of the current data and the clarity of the features are improved, further enhancing the predictive ability of the model.

[0075] According to the above embodiment of the present invention, normalizing the current value to obtain the normalized current value includes: multiplying each of the multiple current values ​​by a predetermined integer value to normalize the current value to obtain the normalized current value.

[0076] In this embodiment, the collected current values ​​are amplified, for example, by multiplying them by n (i.e., a predetermined integer value) (e.g., 1200) to ensure that all current values ​​are integers. A scatter plot of the amplified current is generated, the peak position in the scatter plot is determined, and the current value corresponding to the peak is extracted as the target current value.

[0077] That is, for each collected current value, directly multiply it by n (such as 1200) to obtain the amplified current value. This operation ensures that all current data can be represented as integer values, which is convenient for subsequent calculations and model input.

[0078] For example, in an automated production line for industrial washing machines, to ensure simple and efficient data processing, each current value collected is multiplied by a predetermined integer value (for example, n = 1200) to ensure that all collected data can be represented as integer values. This processing method is particularly important in industrial environments, because the high speed of the production line requires data analysis and processing to be fast and accurate, avoiding calculation delays and errors caused by data formatting issues.

[0079] It should be noted that the predetermined integer value here can enable the current value to always remain an integer value while amplifying the current value, so that the difference between the currents is more obvious and easier to observe in the figure.

[0080] In addition, it should be noted that, in the embodiment of the present invention, normalizing the current value is an operation of amplifying the current value.

[0081] This operation solves the problem that the current value may be a decimal, which is not conducive to processing by embedded systems.

[0082] The converted integer-valued current data simplifies the computational burden of embedded chips, improves the speed and efficiency of data processing, and makes model training and application smoother.

[0083] According to the above embodiment of the present invention, obtaining the curve characteristic value of the current curve corresponding to the target current value may include: fitting the target current value by the least squares method to obtain a fifth-order fitting curve corresponding to the target current value; and obtaining the curve characteristic value according to the fifth-order fitting curve.

[0084] In this embodiment, the target current value is fitted using the least squares method to obtain a fifth-order polynomial curve. Feature values ​​are extracted from this curve, including mean, skewness, kurtosis, standard deviation, peak value, phase, and entropy. Using a fifth-order fitting curve more accurately describes the fluctuation characteristics of the current data, thereby improving the accuracy of feature value extraction.

[0085] Figure 5is a weight difference diagram between groups according to an embodiment of the present invention, which is a curve diagram of weight every 100g, Figure 5 It can be seen that the difference in the scatter curves between different weights is large. Figure 4 and Figure 5 It can be seen that in the range of about 35%-55% of the entire scatter curve, a peak of the scatter curve can be fully reflected, and the peak can also distinguish scatter curves of different weights. Therefore, among all the scatter points, if Figure 3 As shown, extract the 35%-55% interval (i.e., Figure 5 The curve part in the area of ​​7500-10000 in the middle horizontal coordinate. Figure 6 This is a current fitting curve diagram according to an embodiment of the present invention (Original Data in the figure represents original data, Polynomial Fit (degree = 5): polynomial fitting (order = 5)). Figure 6 The curve obtained by fitting the current scatter data obtained in the experiment with a weight of 1000g by a 5th-order polynomial is shown, that is, ,here are the coefficients to be determined. It should be noted that the goal of curve fitting is to find a polynomial that minimizes the error of the polynomial at a given data point. This is usually accomplished using the least squares method, which minimizes the sum of squares of the residuals, which is the difference between the true y-value of each data point and the y-value predicted by the polynomial.

[0086] For example, in high-end washing machines where users require precise control of detergent dosage, the system uses the least squares method to fit the target current value, generating a highly accurate fifth-order fitting curve. Based on this curve, the system accurately calculates multiple curve characteristics, including mean, skewness, kurtosis, and standard deviation, enabling more precise prediction of laundry weight. For high-end washing machines, precise detergent dosage control is crucial to the user experience. The high accuracy of the fitting curve ensures accurate adjustment of the wash cycle, meeting users' high expectations for wash results.

[0087] The extracted eigenvalues ​​fully reflect the distribution of current data, providing richer information for the machine learning model and helping to improve the model's prediction accuracy.

[0088] According to the above embodiment of the present invention, the curve characteristic value is obtained according to the fifth-order fitting curve, including: obtaining the mean of the fifth-order fitting curve according to the center position of the fifth-order fitting curve; obtaining the skewness of the fifth-order fitting curve according to the symmetry of the fifth-order fitting curve; obtaining the kurtosis of the fifth-order fitting curve according to the peak shape of the fifth-order fitting curve; obtaining the standard deviation of the fifth-order fitting curve according to the extension degree of the fifth-order fitting curve; obtaining the peak value of the fifth-order fitting curve according to the maximum position of the fifth-order fitting curve; obtaining the phase of the fifth-order fitting curve according to the periodic information of the fifth-order fitting curve; and obtaining the entropy of the fifth-order fitting curve according to the complexity of the fifth-order fitting curve.

[0089] In this embodiment, Figure 3 As shown, based on the fifth-order fitting curve, the mean, skewness, kurtosis, standard deviation, peak value, phase, and entropy are calculated by calculating the center position, symmetry, peak shape, extent, maximum position, periodic displacement, and complexity, respectively. The extracted eigenvalues ​​cover multiple dimensions of the current data, ensuring the model's effective recognition of different clothing loads and types. After obtaining the eigenvalues ​​of the above curve, the seven eigenvalues ​​are input into the trained machine learning model to infer the current weight of the clothes, allowing the washing machine to obtain the specific weight of the clothes.

[0090] For example, in a smart home appliance integration system, when a washing machine needs to communicate with a smart home hub to report its washing status, it uses a trained machine learning model to accurately infer the current weight of the laundry by calculating curve characteristics (e.g., mean, skewness, kurtosis, standard deviation, peak value, phase, and entropy). This information is then used to adjust the washing program, detergent dosage, and communication protocol with the smart home hub, enabling smarter home appliance management.

[0091] like Figure 6As shown, after obtaining the curve, the following 7 eigenvalues ​​that can represent the characteristics of the curve are calculated from the fitting curve through the calculation method of each eigenvalue: mean: describes the center position of the distribution and is independent of the shape. Specifically, the average value of the ordinate value (y value) of the fitting curve is calculated, which is the mean; skewness: describes the symmetry of the distribution. Asymmetry will lead to different tail behaviors. A skewness of 0 indicates symmetry, positive skewness indicates a longer right tail, and negative skewness indicates a longer left tail; kurtosis: describes the peak shape of the distribution and distinguishes fat-tailed or peaked distributions. A kurtosis of 0 indicates a normal distribution, a kurtosis greater than 0 indicates a sharper peak, and a kurtosis less than 0 indicates a flatter peak; standard deviation: describes the discreteness of the data and quantifies the degree of expansion of the distribution; peak: describes the position of the maximum value of the distribution, with the focus on the highest point in the distribution; phase: describes the periodicity or periodic displacement of the distribution and is independent of the position. Find the first zero crossing point of the fitting curve (that is, the point where the curve crosses the x-axis) and use the x value of this point as the phase value. If there is no zero crossing point, the phase value is set to 0; Entropy: describes the complexity of the distribution, quantifies uncertainty, and emphasizes the randomness of the distribution information. It can be directly obtained through the entropy function in the Python library.

[0092] It should be noted that, generally speaking, the higher the order of the fitting curve, the closer the curve is to the actual situation. However, in actual use, it is impossible to use a curve with too high an order to represent the situation.

[0093] Specifically, low-order polynomials (such as 1st or 2nd order) may fail to capture complex patterns in the data, leading to underfitting. Higher-order polynomials (such as 6th order and above), while more accurately fitting the training data, are prone to overfitting, meaning the model becomes overly sensitive to noise and outliers, resulting in poor performance on new data. Polynomials of order 3-5, on the other hand, can capture data trends to a certain extent while avoiding overly complex fitting. Therefore, conventionally, fitted curves are typically represented using orders 3-5.

[0094] The use of multi-dimensional eigenvalues ​​enhances the generalization ability of the model, enabling it to make accurate weight judgments when faced with clothes of different materials and weights.

[0095] According to the above embodiment of the present invention, before determining the weighing value corresponding to the curve characteristic value, the weighing method of the washing machine also includes: obtaining multiple groups of training data including multiple sample curve characteristic values ​​and multiple sample clothing weights; training the multiple groups of training data to obtain a weight prediction model.

[0096] In this embodiment, before weight prediction is performed, training data including multiple sets of sample curve feature values ​​and sample clothing weights are collected. Machine learning training is performed on these data to construct a weight prediction model. The machine learning model is obtained by conducting a large number of experiments in the early stage and collecting a large number of curve feature training, and then the model is transplanted to the motor control chip of the washing machine. Specifically, the transplantation method is: the mathematical formulas and processing procedures used above can be implemented through C language; deployment method: model simplification; feature selection: reduce the number of input features through correlation analysis or L1 regularization (Lasso). Reduce complexity: Linear regression: reduce redundant features (such as collinear features). Decision tree regression: limit the tree depth (such as max_depth=3) and the number of leaf nodes. Quantization and fixed-point:

[0097] Convert floating-point weights to fixed-point numbers (such as Q8.8 format) to save storage space. Example: Convert linear regression weights from float32 to int16 with manageable precision loss. Model format conversion: Export to C / C++ compatible formats: Linear regression: Directly export weight matrices and bias terms (such as W[] and b arrays). Tree models: Convert to if-else rules or lookup tables.

[0098] For example, when upgrading and testing a washing machine manufacturer's products, the manufacturer needs to obtain multiple sets of training data containing multiple sample curve feature values ​​and sample clothing weights. This data is then used to train a machine learning model. To ensure the model's effectiveness and adaptability, the manufacturer may need to collect training datasets (for example, 10,000 sets) covering a wide range of variables, such as clothing weight, type, and moisture content, covering clothing weights from 0.5 kg to 20 kg. This process is crucial to ensuring the model's accuracy under a variety of real-world usage conditions.

[0099] Through a large amount of training data, the machine learning model is able to learn the current distribution patterns corresponding to different clothing weights and types.

[0100] This training process enables the model to quickly adapt to new data and maintain high prediction accuracy even when the clothing load changes or the clothing types are diverse.

[0101] The technical solution provided by the above embodiment of the present invention is as follows: first, the drum washing machine is turned on, the drum door of the drum washing machine is opened, and the clothes to be washed are smoothly placed into the inner drum of the washing machine. Then, the speed is increased from a standstill to V1rpm at an acceleration of a1 rpm / s, and then the speed is kept constant at V1rpm for a period of time. When the speed of the drum washing machine reaches V1rpm, the current value of the motor at this time is collected. The current is collected at a frequency of f, and data of approximately t seconds is collected to obtain a large number of current scatter points. Weighing is performed using machine learning, and the obtained weighing results are faster and more accurate. Here, machine learning is introduced into edge devices to improve the accuracy of weighing, and deep learning is replaced by machine learning to solve the problem of insufficient edge resources.

[0102] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application.

[0103] Through the description of the above embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus the necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the existing technology, can be embodied in the form of a software product. The computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0104] Example 2

[0105] According to an embodiment of the present invention, a washing machine weighing device for implementing the above-mentioned washing machine weighing method is also provided. Figure 7 Schematic diagram of a weighing device for a washing machine according to an embodiment of the present invention. Figure 7 As shown, the weighing device of the washing machine includes: a collection unit 701, an extraction unit 703, a first acquisition unit 705, a determination unit 707 and a second acquisition unit 709. The device is described below.

[0106] The collecting unit 701 is configured to collect the current value of the motor of the washing machine when the washing machine is running at a first speed.

[0107] The extraction unit 703 is configured to extract a plurality of target current values ​​from the data set corresponding to the current values, wherein the plurality of target current values ​​are current values ​​that completely describe at least one peak in the current values.

[0108] The first acquiring unit 705 is configured to acquire a curve characteristic value of the current curve corresponding to the target current value.

[0109] The determination unit 707 is used to determine the weighing value corresponding to the curve characteristic value through a weight prediction model, wherein the weight prediction model is a model obtained by machine learning training using multiple sets of training data, and each set of the multiple sets of training data includes: a sample curve characteristic value and a sample clothing weight corresponding to the sample curve characteristic value.

[0110] The second obtaining unit 709 is configured to obtain the weight of the clothes in the washing machine according to the weighing value.

[0111] It should be noted here that the above-mentioned acquisition unit 701, extraction unit 703, first acquisition unit 705, determination unit 707 and second acquisition unit 709 correspond to steps S202 to S210 in the above-mentioned embodiment. The five units and the corresponding steps implement the same instances and application scenarios, but are not limited to the contents disclosed in the above-mentioned embodiment.

[0112] As can be seen from the above, in the scheme recorded in the above embodiment of the present invention, a collection unit can be used to collect the current value of the washing machine's motor while the washing machine is running at a first speed; an extraction unit can be used to extract multiple target current values ​​from a data set corresponding to the current value, wherein the multiple target current values ​​are current values ​​that fully describe at least one peak in the current value; a first acquisition unit is used to obtain curve characteristic values ​​of the current curve corresponding to the target current value; a determination unit is used to determine a weighing value corresponding to the curve characteristic value through a weight prediction model, wherein the weight prediction model is a model obtained by machine learning using multiple sets of training data, each of the multiple sets of training data including: a sample curve characteristic value and a sample clothing weight corresponding to the sample curve characteristic value; and a second acquisition unit is used to obtain the weight of the clothes inside the washing machine based on the weighing value. This achieves the purpose of obtaining the weight of the clothes inside the washing machine by collecting the current data of the motor of the washing machine during operation, extracting part of the current data from the collected current data, obtaining the characteristic values ​​of the current curve corresponding to this part of the current data, and using these characteristic values ​​as input to a pre-trained model, thereby achieving the technical effect of improving the weighing accuracy of the washing machine.

[0113] Therefore, the technical solution provided by the embodiment of the present invention solves the technical problem of low accuracy in washing machine weighing in the related art.

[0114] Optionally, the acquisition unit includes: a control module, used to control the speed of the washing machine to increase to a first speed at a first acceleration when detecting the presence of clothes in the washing machine; an acquisition module, used to perform a current value acquisition operation on the motor at a predetermined frequency when the detection speed reaches the first speed; and a first acquisition module, used to obtain multiple current values ​​after determining that the current value acquisition operation continues for a predetermined period of time.

[0115] Optionally, the extraction unit includes: a normalization processing module for normalizing the current value to obtain a normalized current value; an extraction module for extracting the current value corresponding to the data segment where the target current peak is located from the normalized current value as multiple target current values.

[0116] Optionally, the normalization processing module includes: a normalization processing submodule, configured to multiply each of the multiple current values ​​by a predetermined integer value to perform normalization processing on the current value to obtain a normalized current value.

[0117] Optionally, the first acquisition unit includes: a fitting processing module, which is used to fit the target current value through the least squares method to obtain a fifth-order fitting curve corresponding to the target current value; and a second acquisition module, which is used to obtain a curve characteristic value according to the fifth-order fitting curve.

[0118] Optionally, the second acquisition module includes: a first acquisition sub-module, used to obtain the mean of the fifth-order fitting curve according to the center position of the fifth-order fitting curve; a second acquisition sub-module, used to obtain the skewness of the fifth-order fitting curve according to the symmetry of the fifth-order fitting curve; a third acquisition sub-module, used to obtain the kurtosis of the fifth-order fitting curve according to the peak morphology of the fifth-order fitting curve; a fourth acquisition sub-module, used to obtain the standard deviation of the fifth-order fitting curve according to the extension degree of the fifth-order fitting curve; a fifth acquisition sub-module, used to obtain the peak value of the fifth-order fitting curve according to the maximum position of the fifth-order fitting curve; a sixth acquisition sub-module, used to obtain the phase of the fifth-order fitting curve according to the periodic information of the fifth-order fitting curve; and a seventh acquisition sub-module, used to obtain the entropy of the fifth-order fitting curve according to the complexity of the fifth-order fitting curve.

[0119] Optionally, the weighing device of the washing machine also includes: a third acquisition unit, used to obtain multiple sets of training data including multiple sample curve characteristic values ​​and multiple sample clothing weights before determining the weighing value corresponding to the curve characteristic value; a training unit, used to train the multiple sets of training data to obtain a weight prediction model.

[0120] According to another aspect of the embodiments of the present invention, a washing machine is provided. The washing machine uses any one of the above-mentioned weighing methods for washing machines.

[0121] According to another aspect of an embodiment of the present invention, a processor is further provided, and the processor is configured to run a program, wherein when the program is run, any one of the above-mentioned washing machine weighing methods is executed.

[0122] According to another aspect of an embodiment of the present invention, a computer program product is provided, comprising computer instructions, wherein when the computer instructions are executed by a processor, any one of the above-mentioned washing machine weighing methods is executed.

[0123] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium includes a stored program, wherein the program executes any one of the above-mentioned weighing methods for a washing machine.

[0124] Optionally, in this embodiment, the computer-readable storage medium may be located in any one of the computer terminals in a computer terminal group in a computer network, or in any one of the communication devices in a communication device group.

[0125] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for executing the following steps: collecting the current value of the washing machine's motor while the washing machine is running at a first speed; extracting multiple target current values ​​from a data set corresponding to the current value, wherein the multiple target current values ​​are current values ​​that fully describe at least one peak in the current value; obtaining curve characteristic values ​​of the current curve corresponding to the target current values; determining a weighing value corresponding to the curve characteristic value through a weight prediction model, wherein the weight prediction model is a model obtained by machine learning training using multiple sets of training data, each set of the multiple sets of training data including: a sample curve characteristic value and a sample clothing weight corresponding to the sample curve characteristic value; and obtaining the weight of the clothing inside the washing machine according to the weighing value.

[0126] Optionally, in this embodiment, the computer-readable storage medium is configured to store program codes for executing the following steps: when it is detected that there are clothes in the washing machine, controlling the speed of the washing machine to increase to a first speed at a first acceleration; when the detection speed reaches the first speed, performing a current value acquisition operation on the motor at a predetermined frequency; after determining that the current value acquisition operation continues for a predetermined period of time, obtaining multiple current values.

[0127] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for executing the following steps: normalizing the current value to obtain a normalized current value; extracting the current value corresponding to the data segment where the target current peak is located from the normalized current value as multiple target current values.

[0128] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for executing the following steps: multiplying each of the multiple current values ​​by a predetermined integer value to normalize the current value to obtain a normalized current value.

[0129] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for executing the following steps: fitting the target current value by the least squares method to obtain a fifth-order fitting curve corresponding to the target current value; and obtaining a curve characteristic value according to the fifth-order fitting curve.

[0130] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for executing the following steps: obtaining the mean of the fifth-order fitting curve based on the center position of the fifth-order fitting curve; obtaining the skewness of the fifth-order fitting curve based on the symmetry of the fifth-order fitting curve; obtaining the kurtosis of the fifth-order fitting curve based on the peak morphology of the fifth-order fitting curve; obtaining the standard deviation of the fifth-order fitting curve based on the degree of expansion of the fifth-order fitting curve; obtaining the peak value of the fifth-order fitting curve based on the maximum position of the fifth-order fitting curve; obtaining the phase of the fifth-order fitting curve based on the periodic information of the fifth-order fitting curve; and obtaining the entropy of the fifth-order fitting curve based on the complexity of the fifth-order fitting curve.

[0131] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: before determining the weighing value corresponding to the curve characteristic value, obtaining multiple sets of training data including multiple sample curve characteristic values ​​and multiple sample clothing weights; training the multiple sets of training data to obtain a weight prediction model.

[0132] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0133] In the above embodiments of the present invention, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0134] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only exemplary. For example, the division of the units can be a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0135] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0136] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0137] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), a mobile hard drive, a magnetic disk, or an optical disk.

[0138] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as within the scope of protection of the present invention.

Claims

1. A method for weighing a washing machine, characterized in that: include: While the washing machine is running at a first speed, collecting a current value of a motor of the washing machine; extracting a plurality of target current values ​​from a data set corresponding to the current values; Obtaining a curve characteristic value of a current curve corresponding to the target current value; Determining a weighing value corresponding to the characteristic value of the curve by a weight prediction model; Obtaining the weight of the clothes in the washing machine according to the weighing value; Wherein, obtaining the curve characteristic value of the current curve corresponding to the target current value includes: Fitting the target current value using a least squares method to obtain a fifth-order fitting curve corresponding to the target current value; The curve characteristic value is obtained according to the fifth-order fitting curve.

2. The weighing method of a washing machine according to claim 1, characterized in that: While the washing machine is running at a first speed, collecting a current value of a motor of the washing machine includes: When detecting that there are clothes in the washing machine, controlling the speed of the washing machine to increase to the first speed at a first acceleration; When detecting that the speed reaches the first speed, performing a current value acquisition operation on the motor at a predetermined frequency; After determining that the current value acquisition operation continues for a predetermined time period, the current value is obtained.

3. The weighing method of a washing machine according to claim 1, characterized in that: Extracting a plurality of target current values ​​from a data set corresponding to the current value includes: performing normalization processing on the current value to obtain the normalized current value; The current value corresponding to the data segment where the target current peak value is located is extracted from the normalized current value as the multiple target current values.

4. The weighing method of a washing machine according to claim 3, characterized in that: Normalizing the current value to obtain the normalized current value includes: Each of the current values ​​is multiplied by a predetermined integer value to perform normalization processing on the current value to obtain the normalized current value.

5. The weighing method of a washing machine according to claim 1, characterized in that: Obtaining the curve characteristic value according to the fifth-order fitting curve includes: Obtaining a mean value of the fifth-order fitting curve according to the center position of the fifth-order fitting curve; Obtaining the skewness of the fifth-order fitting curve according to the symmetry of the fifth-order fitting curve; Obtaining the kurtosis of the fifth-order fitting curve according to the peak shape of the fifth-order fitting curve; Obtaining a standard deviation of the fifth-order fitting curve according to an expansion degree of the fifth-order fitting curve; Obtaining a peak value of the fifth-order fitting curve according to a maximum position of the fifth-order fitting curve; Obtaining the phase of the fifth-order fitting curve according to the period information of the fifth-order fitting curve; The entropy of the fifth-order fitting curve is obtained according to the complexity of the fifth-order fitting curve.

6. The weighing method of a washing machine according to claim 1, characterized in that: Before determining the weighing value corresponding to the characteristic value of the curve, the method further includes: Acquire multiple sets of training data including multiple sample curve feature values ​​and multiple sample clothing weights; The multiple sets of training data are trained to obtain the weight prediction model.

7. A weighing device for a washing machine, characterized in that: include: a collecting unit, configured to collect a current value of a motor of the washing machine while the washing machine is running at a first speed; an extraction unit, configured to extract a plurality of target current values ​​from a data set corresponding to the current value; a first acquiring unit, configured to acquire a curve characteristic value of a current curve corresponding to the target current value; a determining unit, configured to determine a weighing value corresponding to the characteristic value of the curve by using a weight prediction model; The second obtaining unit is configured to obtain the weight of the clothes in the washing machine according to the weighing value.

8. A washing machine, characterized in that: The washing machine uses the washing machine weighing method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored program, wherein the program executes the weighing method for a washing machine according to any one of claims 1 to 6.

10. A processor, characterized in that: The processor is configured to run a program, wherein the program, when running, executes the washing machine weighing method according to any one of claims 1 to 6.

11. A computer program product comprising computer instructions, characterized in that When the computer instructions are executed by a processor, the washing machine weighing method according to any one of claims 1 to 6 is executed.

Images