Washing machine water inlet control method, device and washing machine

Abstract

A method, device, and washing machine for controlling water inlet of a washing machine are provided. The method comprises: S1: obtaining the actual weight of the laundry in the washing machine drum and calculating an estimated water inlet volume based on the actual weight of the laundry; S2: obtaining an image of the laundry in the washing machine drum after it has been scattered, preprocessing the image, and feeding the preprocessing result and the laundry weight into a laundry weight model to obtain a standard laundry weight; and S3: determining the actual laundry water inlet volume based on the actual laundry weight, the standard laundry weight, and the estimated water inlet volume. The solution of the present invention obtains the current laundry features and other accessory features through image recognition, obtains the laundry weight and related weight range based on the laundry weight model, and matches the weight with the current laundry weight, thereby reducing laundry weight errors, improving washing efficiency, reducing resource waste, and enhancing the user experience.

Description

Technical Field

[0001] The present invention relates to the field of automatic control, and more particularly to a water inlet control method and device for a washing machine, and the washing machine. Background Art

[0002] Washing machines have become a must-have household appliance. With the continuous development of technology, users have higher and higher requirements for automated laundry. The current water inflow mode of washing machines is generally as follows: (1) the user sets the washing program, and the maximum weight of clothes that can be washed at one time is fixed. If the weight of the user's laundry exceeds the rated maximum, the number of clothes must be reduced before the program can be started; (2) fuzzy weighing is performed, and a weight sensor is set to obtain the weight of the clothes, and the water inflow is determined based on the weight of the clothes. However, both of the above modes assume that the clothes put in are dry clothes, without considering the amount of water in the barrel or the water content of the clothes to be washed (and the weight of the clothes with water far exceeds its weight in the dry state). This results in a reduction in the number of clothes that can be washed or an excessive amount of water inflow, resulting in a waste of resources. It is also not conducive to the washing of clothes and affects the user experience. Therefore, achieving accurate control of the water inflow rate of clothes is an urgent problem that needs to be solved.

[0003] Therefore, the prior art requires a control solution that can determine the water intake of a washing machine.

[0004] The above information disclosed in this Background section is only for further understanding of the background of the invention and therefore it may contain information that does not constitute the prior art that is already known to a person of ordinary skill in the art. Summary of the Invention

[0005] The present invention relates to a water inlet control method, equipment, device and washing machine of a washing machine. The technical problems that the present invention can solve are: the washing machine defaults to a dry state of the clothes to be washed, so when the clothes to be washed contain water, the water content is counted in the current weight of the clothes to be washed, which will lead to the following two problems: (1) if the maximum weight of the clothes that can be washed at one time by the washing machine is constant, the weight of the clothes when the clothes to be washed contain water far exceeds the dry state, resulting in a decrease in the number of clothes that can be washed, low washing efficiency, and affecting user experience; (2) if the washing machine determines the water intake according to the weight of the clothes to be washed, the washing machine cannot accurately identify the actual weight of the clothes input, resulting in the water intake exceeding the normal washing amount, causing waste of resources such as water and detergent. The solution of the present invention can solve the above two problems.

[0006] A first aspect of the present invention provides a water inlet control method for a washing machine, characterized in that the method includes: S1: obtaining the actual weight of the clothes in the inner drum of the washing machine, and calculating the estimated water inlet amount based on the actual weight of the clothes; S2: obtaining an image of the clothes in the inner drum of the washing machine after being scattered, and preprocessing the image, and sending the preprocessing result and the weight of the clothes to a clothes weight model to obtain the standard weight of the clothes; S3: determining the actual water inlet amount of the washing machine based on the actual weight of the clothes, the standard weight of the clothes and the estimated water inlet amount.

[0007] According to one embodiment of the present invention, S3 includes: if the actual weight of the clothes is greater than the standard weight of the clothes, the water content of the clothes is: the actual weight of the clothes - the standard weight of the clothes, and the actual water intake of the washing machine is: the estimated water intake - the water content of the clothes; if the actual weight of the clothes is equal to the standard weight of the clothes, the actual water intake of the washing machine is the estimated water intake; if the actual weight of the clothes is less than the standard weight of the clothes, S2 is re-executed, the standard weight of the clothes is recalculated, the actual water intake of the laundry is controlled to be the water intake corresponding to the actual weight of the clothes, and the clothing weight model is adjusted.

[0008] According to one embodiment of the present invention, in S2, the clothing weight model is a convolutional network learning model. When training the clothing training model, the input samples are images of dry clothing without water and the weight of the dry clothing, and the output is the standard weight corresponding to the dry clothing.

[0009] According to an embodiment of the present invention, in S2, the inner drum of the washing machine is rotated and the clothes are scattered to expose the clothes, and the material and accessory features of the clothes are obtained in image preprocessing.

[0010] According to one embodiment of the present invention, the training process of the clothing weight training model includes: S21: obtaining the actual weight of the clothing and performing data preprocessing; S22: marking the target area of ​​the clothing and obtaining a standard clothing weight data set; S23: determining the clothing weight model parameters and establishing a clothing weight model; S24: training the clothing weight model and calculating the deviation between the output target value and the actual value; S25: if the deviation is within the allowable range, the clothing weight training model ends and the relevant parameters of the clothing weight model are fixed; S26: if the deviation is not within the allowable range, the error of the model-related parameters is calculated, and the error gradient is obtained, the clothing weight model-related parameters are updated, and the return to S23 is performed to re-determine the parameters and establish the model.

[0011] According to one embodiment of the present invention, S2 also includes: feedback adjustment of the clothing weight model, and the feedback adjustment includes: adjusting the clothing weight model according to the personalized training of the clothing status, so that the clothing weight model can maintain a high fit with the clothing in subsequent use, and training and adjusting the clothing weight model for the specific user by continuously acquiring the clothing data of the specific user.

[0012] The second aspect of the present invention provides a water inlet control device for a washing machine, characterized in that the device includes: an acquisition device: acquiring the actual weight of the clothes in the inner drum of the washing machine, and calculating the estimated water inlet amount based on the actual weight of the clothes; an image preprocessing device: acquiring an image of the clothes in the inner drum of the washing machine after being scattered, and preprocessing the image; a clothes weight model: sending the preprocessing result and the clothes weight to the clothes weight model to obtain the standard weight of the clothes; a determination device: determining the actual water inlet amount of the washing machine based on the actual weight of the clothes, the standard weight of the clothes and the estimated water inlet amount.

[0013] According to one embodiment of the present invention, the determination device includes: if the actual weight of the clothes is greater than the standard weight of the clothes, the water content of the clothes is: the actual weight of the clothes - the standard weight of the clothes, and the actual water intake of the washing machine is: the estimated water intake - the water content of the clothes; if the actual weight of the clothes is equal to the standard weight of the clothes, the actual water intake of the washing machine is the estimated water intake; if the actual weight of the clothes is less than the standard weight of the clothes, the learning of the clothing weight model is re-executed, the standard weight of the clothes is recalculated, the actual water intake of the laundry is controlled to be the water intake corresponding to the actual weight of the clothes, and the clothing weight model is adjusted.

[0014] According to one embodiment of the present invention, the clothing weight model is a convolutional network learning model. When training the clothing training model, the input samples are images of dry clothing without water and the weight of the dry clothing, and the output is the standard weight corresponding to the dry clothing.

[0015] A third aspect of the present invention provides a washing machine, characterized in that it uses the water inlet control method of the washing machine described above, or includes the water inlet control device of the washing machine described above, or includes the water inlet control apparatus of the washing machine described above.

[0016] The present invention obtains the current clothing features and other accessory features through image recognition. According to the clothing weight model, the weight of the clothing and the related weight range can be obtained. The weight is matched with the current clothing weight. If it exceeds the range, the water content is calculated, which reduces the clothing weight error, improves washing efficiency, reduces resource waste, and improves the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solution of the present invention, the drawings required for use in the description of the embodiments will be briefly described below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 A flow chart of water inlet control for a washing machine according to an exemplary embodiment of the present invention is shown.

[0019] Figure 2 FIG. 4 is a flowchart of a water inlet control implementation of a washing machine according to an exemplary embodiment of the present invention.

[0020] Figure 3 is a flow chart of a clothing weight model training process according to one or more embodiments of the present invention.

[0021] Figure 4 is a block diagram of a water inlet control apparatus of a washing machine according to an exemplary embodiment of the present invention. Specific embodiments

[0022] As used herein, the words "first", "second", etc. may be used to describe elements in exemplary embodiments of the present invention. These words are only used to distinguish one element from another, and the inherent characteristics or order of the corresponding elements are not limited by the words. Unless otherwise defined, all terms used herein (including technical or scientific terms) have the same meaning as those commonly understood by those of ordinary skill in the art to which the present invention belongs. Terms such as those defined in commonly used dictionaries are interpreted as having the same meaning as the contextual meaning in the relevant technical field, and are not interpreted as having ideal or overly formal meanings, unless explicitly defined as having such meanings in the present invention.

[0023] Those skilled in the art will understand that the apparatus and methods of the present invention described herein and illustrated in the accompanying drawings are non-limiting exemplary embodiments, and that the scope of the present invention is defined solely by the claims. Features illustrated or described in conjunction with one exemplary embodiment may be combined with features of other embodiments. Such modifications and variations are within the scope of the present invention.

[0024] Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. In the accompanying drawings, detailed descriptions of related known functions or configurations are omitted to avoid unnecessarily obscuring the technical key points of the present invention. Throughout the description, the same reference numerals will always refer to the same circuits, modules, or units, and for the sake of brevity, repeated descriptions of the same circuits, modules, or units will be omitted.

[0025] Furthermore, it should be understood that one or more of the following methods or aspects thereof can be performed by at least one control unit or controller. The terms "control unit," "controller," "control module," or "main control module" can refer to a hardware device including a memory and a processor. The memory or computer-readable storage medium is configured to store program instructions, while the processor is specifically configured to execute the program instructions to perform one or more processes described further below. Furthermore, it should be understood that, as will be appreciated by one of ordinary skill in the art, the following methods can be performed by including a processor in combination with one or more other components.

[0026] This system uses deep learning to output a clothing weight model, estimate the standard weight of clothing based on characteristics such as the fabric, and control water intake based on the estimated standard weight. A user feedback adjustment mechanism is established to continuously train and adjust the model based on the user's specific clothing conditions during subsequent use.

[0027] According to one or more embodiments of the present invention, clothing weight model training involves obtaining several sample clothing images and their corresponding weights, preprocessing the images and data, marking the target area (to ensure model readability), and obtaining a standard clothing sample and weight dataset. The clothing weight model is then designed, and clothing features and corresponding weights are trained. The deviation between the target value and the actual output is calculated. If the deviation is within an acceptable range, the weights and other parameters are fixed, and the model is output.

[0028] According to one or more embodiments of the present invention, the present invention also provides a feedback adjustment mechanism: the clothing weight model is adjusted according to personalized training based on the user's clothing status. Since an increase in the number of times clothing is washed will cause clothing wear and loss of weight, etc., and considering that the standard model can maintain a high fit with the user's clothing in subsequent use, clothing data is continuously obtained during use, and the clothing weight model of the user is trained and adjusted to improve the accuracy of the output results.

[0029] Figure 1 A flow chart of water inlet control for a washing machine according to an exemplary embodiment of the present invention is shown.

[0030] like Figure 1 As shown, in S1: obtaining the actual weight of the clothes in the inner drum of the washing machine, and calculating the estimated water intake according to the actual weight of the clothes;

[0031] In S2: an image of the scattered clothes in the inner drum of the washing machine is obtained, and the image is preprocessed, and the preprocessing result and the weight of the clothes are input into a clothes weight model to obtain the standard weight of the clothes;

[0032] In S3 : the actual water intake of the washing machine is determined according to the actual weight of the laundry, the standard weight of the laundry and the estimated water intake.

[0033] In S3, if the actual weight of the laundry is greater than the standard weight, the moisture content of the laundry is calculated as: actual weight - standard weight, and the actual water intake of the washing machine is calculated as: estimated water intake - moisture content. If the actual weight of the laundry is equal to the standard weight, the actual water intake of the washing machine is the estimated water intake. If the actual weight of the laundry is less than the standard weight, S2 is re-executed, the standard weight is recalculated, the actual water intake is controlled to the water intake corresponding to the actual weight, and the laundry weight model is adjusted. Specifically, in the case where the actual weight G < the standard weight Gn, the present invention takes into account that the user's laundry weight may decrease due to frequent changes, thinning of the fabric, or other factors. Therefore, the water intake of the laundry needs to be estimated based on the actual weight. If the water intake is still estimated based on the model standard weight, the water intake will be greater than the actual required amount. Furthermore, the inclusion of the laundry weight model adjustment here is also intended to continuously improve the model accuracy and adapt it to the user's laundry weight. If a user's clothes become thinner, the weight model for that user's clothes will be adjusted accordingly. When the user washes the clothes again, the standard weight of the clothes when dried will be directly output. Otherwise, the user's clothes will become thinner and thinner with each wash, and the weight will decrease. However, if the output weight model remains unchanged, the model output error will increase, resulting in more and more wasted resources.

[0034] Figure 2 FIG. 4 is a flowchart of a water inlet control implementation of a washing machine according to an exemplary embodiment of the present invention.

[0035] like Figure 2 As shown, in step 1: the user puts clothes into the inner drum of the washing machine;

[0036] Step 2: The weight sensor near the washing machine drum obtains the estimated weight G of the clothes put in;

[0037] Step 3: Preliminary calculation of estimated water intake H based on actual weight of clothes 衣

[0038] Step 4: The inner drum rotates to scatter the clothes, expose the obscured clothes, and obtain the image of the clothes in the drum;

[0039] Step 5: Perform image preprocessing, including marking clothing material features, accessories features, etc., estimate the weight of the clothes in the barrel based on the current clothing weight model, and calculate the estimated standard total weight G of the clothes in the barrel 标 ;

[0040] Step 6: Compare the estimated weight of the clothes in the bucket G with the estimated standard total weight of the clothes G 标 For comparison:

[0041] If the weight G in the bucket is greater than the model's estimated standard weight G 标 , then remove the water content of the clothes, the water content H 含 =GG 标 , control the water intake H=H according to the standard weight of the clothes G 衣 -H 含 ;

[0042] If the weight G in the bucket is equal to the model's estimated standard weight G 标 , then the water inlet H=H 衣 ;

[0043] If the weight G in the bucket is less than the standard weight G estimated by the model 标 , then return to step 3, make the inner drum roll again, expose the clothes in the barrel, capture the clothes image during the rolling process, re-acquire the image recognition, confirm whether there are unrecognized clothes, and calculate the standard weight. If the recognition is completed, G 标 If it remains unchanged, the water inlet is controlled to be H=H 衣 , record the error, perform model learning adjustments, and readjust the output model to reduce the error in clothing weight.

[0044] According to one or more embodiments of the present invention, the image of the clothes in the washing machine drum is preprocessed to extract key features, and the standard weight is calculated based on the clothing fabric and clothing accessories, and the weight is corrected to obtain the standard weight G of a single piece of clothing. i Get the actual weight G of the clothes in the barrel and the standard total weight Make a comparison;

[0045] If G>G n , then the water content H 含 =G-Gn, based on the standard total weight of clothing G n Control water inlet H=H 衣 -H 含 (H 衣 : Estimated water intake calculated based on the actual weight of the clothes, H 含 is the water content in the clothes);

[0046] If G <G n , then turn over the clothes in the bucket, re-acquire the image and recognize it, and calculate the weight. If G n If it does not change, record the error, perform model learning and adjustment, reduce the error in clothing weight, and control the water intake H=H 衣 ,H 衣 is the amount of water intake corresponding to the actual weight of the clothes. Figure 2In the first verification, it is mainly to distinguish whether model adjustment is required. When the user puts in the clothes, the washing machine obtains the standard weight and the actual weight of the clothes for comparison. This is the first verification. If it is found in the first verification that G < Gn, then the standard weight Gn of the clothes is recalculated and compared with the actual weight (this is the second verification). If it is found in the second verification that G is still < Gn, then the model is adjusted (the model is not adjusted in the first verification, and if G < Gn is still shown in the second verification, the model is adjusted).

[0047] Figure 3 It is a flowchart of the clothing weight model training process according to one or more embodiments of the present invention.

[0048] As Figure 3 shown, corresponding to Figure 1 the operation process in, the clothing weight model needs to be trained in advance to accurately estimate the clothing weight. And during daily use, as the number of clothing washes increases, situations such as damage to the clothing fabric resulting in a decrease in clothing weight may occur, all of which will cause a large error in the estimated standard weight of the clothing and lead to the water inlet control not reaching the ideal state. In view of the above situations, an adjustment mechanism that continuously learns and updates during use is adopted to ensure the accuracy of the estimation. Based on the clothing weight and the clothing weight obtained during actual use, the model is continuously updated and adjusted to ensure the accuracy of the clothing weight estimation. The specific clothing weight training model is as Figure 3 shown:[[]]END]]

[0049] S21: Obtain clothing and weight data, and perform data preprocessing to facilitate subsequent model reading;

[0050] S22: Perform target area marking to obtain a standard clothing weight data set;

[0051] S23: Determine model parameters and establish a clothing weight model;

[0052] S24: Perform clothing model training to obtain the deviation between the target value and the actual output;

[0053] S25: If the output deviation is within the allowable range, the training ends, fix relevant parameters such as weights, and output the clothing weight model;

[0054] S26: If the output deviation is not within the allowable range, calculate the parameter error, obtain the error gradient, update the weights, return to step S23, and re-determine the parameters and establish the model.

[0055] According to one or more embodiments of the present invention, the clothing weight model of the present invention adopts a convolutional network learning model, and the input samples are images of dry clothing without water and their weight (without water); the actual output is a data set of clothing and corresponding standard weights; wherein, in the clothing weight model, the target value is a known quantity, which is the standard weight corresponding to the clothing (similar to the standard group, based on the comparison between the standard weight and the weight estimated by the model, the deviation between the two is checked. If the output estimated weight of the clothing is significantly different from the standard weight, retraining is required).

[0056] Figure 4 is a block diagram of a water inlet control apparatus of a washing machine according to an exemplary embodiment of the present invention.

[0057] like Figure 4 As shown, the water inlet control device includes:

[0058] Acquisition device: acquires the actual weight of the clothes in the inner drum of the washing machine and calculates the estimated water intake according to the actual weight of the clothes;

[0059] Image preprocessing device: obtains the image of the clothes in the inner drum of the washing machine after being scattered, and preprocesses the image;

[0060] Clothes weight model: sending the preprocessing result and the clothes weight into the clothes weight model to obtain the standard weight of the clothes;

[0061] Determining device: determines the actual water intake of the washing machine according to the actual weight of the clothes, the standard weight of the clothes and the estimated water intake

[0062] Among them, the determination device includes: if the actual weight of the clothes is greater than the standard weight of the clothes, the water content of the clothes is: the actual weight of the clothes - the standard weight of the clothes, and the actual water intake of the washing machine is: the estimated water intake - the water content of the clothes; if the actual weight of the clothes is equal to the standard weight of the clothes, the actual water intake of the washing machine is the estimated water intake; if the actual weight of the clothes is less than the standard weight of the clothes, the learning of the clothing weight model is re-executed, the standard weight of the clothes is recalculated, the actual water intake of the laundry is controlled to be the water intake corresponding to the actual weight of the clothes, and the clothing weight model is adjusted.

[0063] The present invention also provides a washing machine, which uses the above-mentioned washing machine water inlet control method, or includes the above-mentioned washing machine water inlet control device, or includes the above-mentioned washing machine water inlet control equipment.

[0064] According to one or more embodiments of the present invention, the control logic of the present invention can use coded instructions (e.g., computer and / or machine readable instructions) stored on a non-transitory computer and / or machine readable medium (e.g., a hard drive, flash memory, read-only memory, optical disk, digital versatile disk, cache, random access memory and / or any other storage device or storage disk) to implement the processing of the process in the above system of the present invention, and store information for any time period (e.g., an extended period of time, permanent, transient instance, temporary cache and / or information cache) in the non-transitory computer and / or machine readable medium. As used herein, the term "non-transitory computer readable medium" is expressly defined to include any type of computer readable storage device and / or storage disk, and excludes propagating signals and excludes transmission media.

[0065] According to one or more embodiments of the present invention, the logic in the system of the present invention may be implemented using a control circuit (control logic, a main control system or a control module), which may include one or more processors and may also include a non-transitory computer-readable medium internally. Specifically, the main control system or the control module may include a microcontroller MCU. The processor used to implement the processing of the logic in the system of the present invention may be, for example, but not limited to, one or more single-core or multi-core processors. The (one or more) processors may include any combination of general-purpose processors and special-purpose processors (e.g., graphics processors, application processors, etc.). The processor may be coupled thereto and / or may include a memory / storage device, and may be configured to execute instructions stored in the memory / storage device to implement various applications and / or operating systems running on the controller in the present invention.

[0066] The accompanying drawings and detailed description of the present invention referred to above as examples of the present invention are used to explain the present invention, but do not limit the meaning or scope of the present invention described in the claims. Therefore, those skilled in the art can easily realize modifications from the above description. In addition, those skilled in the art can delete some of the components described herein without degrading performance, or can add other components to improve performance. In addition, those skilled in the art can change the order of the steps of the method described herein according to the environment of the process or equipment. Therefore, the scope of the present invention should not be determined by the embodiments described above, but by the claims and their equivalents.

[0067] While the invention has been described in connection with what are presently considered to be capable embodiments, it is to be understood that the invention is not limited to the disclosed embodiments, but on the contrary is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.

Claims

1. A method for controlling water inlet of a washing machine, characterized in that: The method comprises: S1: Obtaining the actual weight of the clothes in the inner drum of the washing machine, and calculating the estimated water intake according to the actual weight of the clothes; S2: Acquire an image of the scattered clothes in the inner drum of the washing machine, preprocess the image, and input the preprocessing result into a clothes weight model to obtain the standard weight of the clothes; S3: determining the actual water intake of the washing machine according to the actual weight of the clothes, the standard weight of the clothes, and the estimated water intake; Wherein S3 includes: if the actual weight of the clothes is less than the standard weight of the clothes, re-execute S2, recalculate the standard weight of the clothes, control the actual water intake of the washing machine to be the water intake corresponding to the actual weight of the clothes, and adjust the clothes weight model; if the actual weight of the clothes is greater than the standard weight of the clothes, the water content of the clothes is: the actual weight of the clothes - the standard weight of the clothes, and the actual water intake of the washing machine is: the estimated water intake - the water content of the clothes; If the actual weight of the clothes is equal to the standard weight of the clothes, the actual amount of water taken into the washing machine is the estimated amount of water taken into the washing machine.

2. The method according to claim 1, characterized in that In S2, the clothing weight model is a convolutional network learning model. When training the clothing training model, the input samples are images of dry clothing without water and the weight of the dry clothing, and the output is the standard weight corresponding to the dry clothing.

3. The method according to claim 1, characterized in that In S2, the inner drum of the washing machine is rotated and the clothes are scattered to expose the clothes, and the material and accessory features of the clothes are obtained in image preprocessing.

4. The method according to claim 2, characterized in that The training process of the clothing weight training model includes: S21: Obtain the actual weight of the clothes and perform data preprocessing; S22: Marking target areas of clothing to obtain a standard clothing weight dataset; S23: Determine clothing weight model parameters and establish a clothing weight model; S24: Perform clothing weight model training and calculate the deviation between the output target value and the actual value; S25: If the deviation is within the allowable range, the clothing weight model training ends and the relevant parameters of the clothing weight model are fixed; S26: If the deviation is not within the allowable range, the errors of the model-related parameters are calculated, and the error gradient is obtained. The parameters related to the clothing weight model are updated, and the process returns to S23 to redetermine the parameters and establish the model again.

5. The method according to claim 1, wherein Wherein, S2 further includes: feedback adjustment of the clothing weight model, wherein the feedback adjustment includes: The clothing weight model is adjusted according to the personalized training of the clothing status so that the clothing weight model can maintain a high fit with the clothing in subsequent use, and the clothing weight model for the specific user is trained and adjusted by continuously acquiring the clothing data of the specific user.

6. A water inlet control device for a washing machine, characterized in that: The device comprises: Acquisition device: acquires the actual weight of the clothes in the inner drum of the washing machine and calculates the estimated water intake according to the actual weight of the clothes; Image preprocessing device: obtains the image of the clothes in the inner drum of the washing machine after being scattered, and preprocesses the image; Clothing weight model: sending the preprocessing result to the clothing weight model to obtain the standard weight of the clothing; Determining device: determines the actual water intake of the washing machine based on the actual weight of the clothes, the standard weight of the clothes, and the estimated water intake; if the actual weight of the clothes is less than the standard weight of the clothes, re-executing the learning of the clothes weight model, recalculating the standard weight of the clothes, controlling the actual water intake of the washing machine to be the water intake corresponding to the actual weight of the clothes, and adjusting the clothes weight model; if the actual weight of the clothes is greater than the standard weight of the clothes, the water content of the clothes is: the actual weight of the clothes - the standard weight of the clothes, and the actual water intake of the washing machine is: the estimated water intake - the water content of the clothes; If the actual weight of the clothes is equal to the standard weight of the clothes, the actual amount of water taken into the washing machine is the estimated amount of water taken into the washing machine.

7. The device according to claim 6, characterized in that in, The clothing weight model is a convolutional network learning model. When training the clothing training model, the input samples are images of dry clothing without water and the weight of the dry clothing, and the output is the standard weight corresponding to the dry clothing.

8. A washing machine, characterized in that: It uses the water inlet control method of the washing machine according to any one of claims 1-5, or includes the water inlet control device of the washing machine according to any one of claims 6-7.

Images