Dewatering control method and device of washing machine and computer readable storage medium

Abstract

The invention discloses a dehydration control method and device of a washing machine and a computer readable storage medium. The method comprises the steps of obtaining image data of an inner barrel and the weight of to-be-dewatered clothes under the condition that it is determined that the to-be-dewatered clothes in the inner barrel of the washing machine start to be dewatered; inputting the image data into a parameter determination model, and processing the image data by using the parameter determination model to obtain clothes state parameters of the to-be-dehydrated clothes in the inner drum; inputting the clothes state parameters and the clothes weight into a dehydration strategy determination model, and processing the clothes state parameters and the clothes weight by using the dehydration strategy determination model to obtain a dehydration control strategy for carrying out dehydration treatment on the washing machine; the washing machine is controlled to execute dewatering operation according to the dewatering control strategy, so that the water content in the inner barrel is lower than the water volume threshold value. According to the invention, the technical problem of poor dehydration efficiency caused by repeated eccentricity detection in the dehydration process 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 dehydration control method and device for a washing machine, and a computer-readable storage medium. Background Art

[0002] At present, the common way to optimize the dehydration process of a drum washing machine is often to inform the washing machine of the material information of the clothes to be washed by manually pre-inputting or installing an identification device before the start of washing, so that the user can place the clothes in front of the camera one by one for identification when putting them in, and finally optimize the dehydration process according to the material of the clothes, the quality before and after dehydration, etc., in order to quickly complete the dehydration process. However, if only referring to the material of the clothes without considering that when the amount of clothes and the distribution of clothes are different, the clothes will show different eccentricity when dehydrating, it is impossible to predict the dehydration speed increase curve of the washing machine in the pre-dehydration and main dehydration stages, and thus it is impossible to avoid repeated eccentricity detection processes, and it is impossible to effectively simplify the dehydration process. In addition, when the washing machine obtains the material of the clothes, whether it is manual pre-input or the installation of an identification device to inform the material information of the clothes, it will greatly increase the user's learning cost and usage cost, causing adverse effects.

[0003] With regard to the problem in the above-mentioned related technologies that eccentricity detection is usually required to be performed repeatedly during the dehydration process of the washing machine, resulting in poor dehydration efficiency, no effective solution has been proposed so far. Summary of the invention

[0004] The embodiments of the present invention provide a dehydration control method and device for a washing machine, and a computer-readable storage medium, so as to at least solve the technical problem in the related art that eccentricity detection is usually required to be repeatedly performed during the dehydration process of the washing machine, resulting in poor dehydration efficiency.

[0005] According to one aspect of an embodiment of the present invention, a dehydration control method for a washing machine is provided, comprising: a first acquisition step, in which, when it is determined that the dehydration process for the clothes to be dehydrated in the inner drum of the washing machine has started, image data of the inner drum and the weight of the clothes to be dehydrated are acquired; a second acquisition step, in which the image data is input into a parameter determination model, so as to process the image data using the parameter determination model to obtain clothing state parameters of the clothes to be dehydrated in the inner drum, wherein the parameter determination model is trained by a deep learning method using multiple groups of first training data, and each of the multiple groups of first training data comprises: sample image data, sample clothing state parameters corresponding to the sample image data, number; a third acquisition step, inputting the clothing state parameter and the clothing weight into a dehydration strategy determination model, so as to use the dehydration strategy determination model to process the clothing state parameter and the clothing weight to obtain a dehydration control strategy for dehydrating the washing machine, wherein the dehydration strategy determination model is trained by a deep learning method using multiple groups of second training data, and each of the multiple groups of second training data includes: sample clothing state parameters, sample clothing weights, and sample dehydration control strategies corresponding to the sample clothing state parameters and the sample clothing weights; a control step, controlling the washing machine to perform a dehydration operation according to the dehydration control strategy so that the water content in the inner drum is lower than a water content threshold.

[0006] Optionally, when it is determined that the dehydration treatment of the clothes to be dehydrated in the inner drum of the washing machine has started, the image data of the inner drum and the weight of the clothes to be dehydrated are obtained, including: when it is determined that the drainage operation of the washing machine has ended, it is determined that the dehydration treatment of the clothes to be dehydrated in the inner drum has started; the washing machine is controlled to perform a shaking operation to shake the clothes to be dehydrated in the inner drum, wherein the shaking operation is used to make the looseness of the clothes to be dehydrated higher than a loose threshold; the washing machine is controlled to perform the dehydration operation at a preset speed, and the cumulative time of the washing machine performing the dehydration operation at the preset speed is counted; when the cumulative time reaches a predetermined time, the washing machine is controlled to stop performing the dehydration operation at the preset speed, and the image data and the weight of the clothes are obtained.

[0007] Optionally, the image data includes first image data and second image data, and obtaining the image data of the inner drum and the weight of the clothes to be dehydrated includes: using a first image acquisition device to acquire the first image data of the inner drum, and using a second image acquisition device to acquire the second image data of the inner drum, wherein the first image acquisition device is an image acquisition device installed directly in front of the inner drum, and the second image acquisition device is the image acquisition device installed above the front or above the rear of the inner drum; using a built-in weighing module in the washing machine to weigh the clothes to be dehydrated to obtain the weight of the clothes to be dehydrated.

[0008] Optionally, the image data is input into a parameter determination model so as to process the image data using the parameter determination model to obtain clothing state parameters of the clothes to be dehydrated in the inner drum, including: inputting the first image data into the parameter determination model so as to process the first image data using the parameter determination model to obtain the stacking height of the clothes to be dehydrated in the inner drum; inputting the second image data into the parameter determination model so as to process the second image data using the parameter determination model to obtain the expansion area and distribution state of the clothes to be dehydrated in the inner drum, wherein the distribution state includes the position and uniformity of the distribution of the clothes to be dehydrated in the inner drum; integrating the stacking height, the expansion area and the distribution state to obtain the clothing state parameters of the clothes to be dehydrated in the inner drum.

[0009] Optionally, the dehydration operation includes a pre-spinning operation and a main dehydration operation, and controlling the washing machine to perform the dehydration operation according to the dehydration control strategy so that the water content in the inner drum is lower than a water content threshold value, including: dividing the dehydration control strategy to obtain a pre-spinning control strategy and a main dehydration control strategy, wherein the pre-spinning control strategy is used to control the pre-spinning stage in the dehydration process of the washing machine, and the main dehydration control strategy is used to control the main dehydration stage in the dehydration process of the washing machine, and the pre-spinning stage is a dehydration stage before the main dehydration stage; determining a pre-spinning speed-up curve of the rotation speed of the inner drum according to the pre-spinning control strategy, wherein the pre-spinning speed-up curve refers to The predicted speed increase curve of the speed in the pre-spinning stage; controlling the washing machine to perform the pre-spinning operation according to the pre-spinning control strategy to obtain the actual pre-spinning speed increase curve of the speed, wherein the pre-spinning operation refers to the spin operation performed in the pre-spinning stage; comparing the actual pre-spinning speed increase curve with the pre-spinning speed increase curve to obtain a comparison result; determining a target main spin control strategy for controlling the main spin stage according to the comparison result; controlling the washing machine to perform the main spin operation according to the target main spin control strategy to make the water content in the inner drum lower than the water content threshold, wherein the main spin operation refers to the spin operation performed in the main spin stage.

[0010] Optionally, determining a target main dehydration control strategy for controlling the main dehydration stage according to the comparison result includes: when the comparison result indicates that the actual pre-dehydration speed-up curve is the same as the pre-dehydration speed-up curve, determining that the main dehydration control strategy is the target main dehydration control strategy; when the comparison result indicates that the actual pre-dehydration speed-up curve is the same as the pre-dehydration speed-up curve, acquiring current image data of the inner drum and current weight of the clothes to be dehydrated, wherein the current image data refers to data of the inner drum after the washing machine performs the pre-dehydration operation, and the current weight of clothes refers to the weight of the clothes to be dehydrated after the washing machine performs the pre-dehydration operation; after updating the image data input into the parameter determination model to the current image data and updating the clothes weight input into the dehydration strategy determination model to the current clothes weight, sequentially executing the second acquisition step and the third acquisition step to obtain the target main dehydration control strategy for controlling the main dehydration stage.

[0011] Optionally, the dehydration control method of the washing machine also includes: each time after the parameter determination model is used to obtain the clothing state parameters corresponding to the image data, the parameter determination model is optimized according to the image data and the clothing state parameters to obtain the optimized parameter determination model; each time after the dehydration strategy determination model is used to obtain the dehydration control strategy corresponding to the clothing state parameters and the clothing weight, the dehydration strategy determination model is optimized according to the clothing state parameters, the clothing weight and the dehydration control strategy to obtain the optimized dehydration strategy determination model.

[0012] According to another aspect of an embodiment of the present invention, a dehydration control device for a washing machine is provided, comprising: a first acquisition unit, configured to execute a first acquisition step, and to acquire image data of the inner drum and the weight of the clothes to be dehydrated when it is determined that the clothes to be dehydrated in the inner drum of the washing machine have started to be dehydrated; a second acquisition unit, configured to execute a second acquisition step, and to input the image data into a parameter determination model, so as to process the image data using the parameter determination model, and obtain clothing state parameters of the clothes to be dehydrated in the inner drum, wherein the parameter determination model is trained by a deep learning method using multiple groups of first training data, and each of the multiple groups of first training data comprises: sample image data, sample clothing state parameters corresponding to the sample image data, parameters; a third acquisition unit, used to execute a third acquisition step, input the clothing state parameters and the clothing weight into a dehydration strategy determination model, so as to use the dehydration strategy determination model to process the clothing state parameters and the clothing weight to obtain a dehydration control strategy for dehydrating the washing machine, wherein the dehydration strategy determination model is trained using a plurality of groups of second training data through a deep learning method, and each of the plurality of groups of second training data includes: sample clothing state parameters, sample clothing weight, and a sample dehydration control strategy corresponding to the sample clothing state parameters and the sample clothing weight; a control unit, used to execute a control step, controlling the washing machine to perform a dehydration operation according to the dehydration control strategy, so that the water content in the inner drum is lower than a water content threshold.

[0013] Optionally, the first acquisition unit includes: a first determination module, used to determine to start dehydrating the clothes to be dehydrated in the inner drum when it is determined that the drainage operation of the washing machine is completed; a first control module, used to control the washing machine to perform a shaking operation to shake the clothes to be dehydrated in the inner drum, wherein the shaking operation is used to make the looseness of the clothes to be dehydrated higher than a loose threshold; a second control module, used to control the washing machine to perform the dehydration operation at a preset speed, and count the cumulative time of the washing machine performing the dehydration operation at the preset speed; a third control module, used to control the washing machine to stop performing the dehydration operation at the preset speed when the cumulative time reaches a predetermined time, and obtain the image data and the weight of the clothes.

[0014] Optionally, the image data includes first image data and second image data, and the first acquisition unit includes: an acquisition module, used to use a first image acquisition device to acquire the first image data of the inner drum, and use a second image device to acquire the second image data of the inner drum, wherein the first image acquisition device is an image acquisition device installed directly in front of the inner drum, and the second image acquisition device is the image acquisition device installed above the front or above the rear of the inner drum; a first acquisition module, used to use a built-in weighing module in the washing machine to weigh the clothes to be dehydrated to obtain the weight of the clothes to be dehydrated.

[0015] Optionally, the second acquisition unit includes: a second acquisition module, used to input the first image data into the parameter determination model, so as to process the first image data using the parameter determination model to obtain the stacking height of the clothes to be dehydrated in the inner drum; a third acquisition module, used to input the second image data into the parameter determination model, so as to process the second image data using the parameter determination model to obtain the expansion area and distribution state of the clothes to be dehydrated in the inner drum, wherein the distribution state includes the position and uniformity of the distribution of the clothes to be dehydrated in the inner drum; and a fourth acquisition module, used to integrate the stacking height, the expansion area and the distribution state to obtain the clothing state parameters of the clothes to be dehydrated in the inner drum.

[0016] Optionally, the dehydration operation includes a pre-dehydration operation and a main dehydration operation, and the control unit includes: a fifth acquisition module, used to divide the dehydration control strategy to obtain a pre-dehydration control strategy and a main dehydration control strategy, wherein the pre-dehydration control strategy is used to control the pre-dehydration stage in the dehydration process of the washing machine, and the main dehydration control strategy is used to control the main dehydration stage in the dehydration process of the washing machine, and the pre-dehydration stage is the previous dehydration stage of the main dehydration stage; a second determination module, used to determine the pre-dehydration speed-up curve of the rotation speed of the inner drum according to the pre-dehydration control strategy, wherein the pre-dehydration speed-up curve refers to the predicted speed-up curve of the rotation speed in the pre-dehydration stage; a fourth control module , used to control the washing machine to perform the pre-spinning operation according to the pre-spinning control strategy, and obtain the actual pre-spinning speed-up curve of the speed, wherein the pre-spinning operation refers to the spin operation performed in the pre-spinning stage; a sixth acquisition module, used to compare the actual pre-spinning speed-up curve with the pre-spinning speed-up curve to obtain a comparison result; a third determination module, used to determine a target main spin control strategy for controlling the main spin stage according to the comparison result; a fifth control module, used to control the washing machine to perform the main spin operation according to the target main spin control strategy, so that the water content in the inner drum is lower than the water content threshold, wherein the main spin operation refers to the spin operation performed in the main spin stage.

[0017] Optionally, the third determination module includes: a first determination submodule, used for determining that the main dehydration control strategy is the target main dehydration control strategy when the comparison result indicates that the actual pre-dehydration speed-up curve is the same as the pre-dehydration speed-up curve; a first acquisition submodule, used for acquiring the current image data of the inner drum and the current weight of the clothes to be dehydrated when the comparison result indicates that the actual pre-dehydration speed-up curve is the same as the pre-dehydration speed-up curve, wherein the current image data refers to the data of the inner drum after the washing machine performs the pre-dehydration operation, and the current weight of the clothes refers to the weight of the clothes to be dehydrated after the washing machine performs the pre-dehydration operation; a second acquisition submodule, used for updating the image data input into the parameter determination model to the current image data, and updating the clothes weight input into the dehydration strategy determination model to the current clothes weight, and then sequentially executing the second acquisition step and the third acquisition step to obtain the target main dehydration control strategy for controlling the main dehydration stage.

[0018] Optionally, the dehydration control device of the washing machine also includes: a first optimization unit, which is used to optimize the parameter determination model according to the image data and the clothing state parameters after the clothing state parameters corresponding to the image data are obtained by using the parameter determination model each time, so as to obtain the optimized parameter determination model; and a second optimization unit, which is used to optimize the dehydration strategy determination model according to the clothing state parameters, the clothing weight and the dehydration control strategy after the dehydration strategy determination model is used each time to obtain the dehydration control strategy corresponding to the clothing state parameters and the clothing weight, so as to obtain the optimized dehydration strategy determination model.

[0019] According to another aspect of the embodiments of the present invention, a dehydration control system of a washing machine is provided. The dehydration control system of the washing machine uses any one of the above-mentioned dehydration control methods of the washing machine.

[0020] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is further provided, wherein the computer-readable storage medium includes a stored program, wherein the program executes any one of the above-mentioned dehydration control methods for a washing machine.

[0021] According to another aspect of an embodiment of the present invention, a processor is further provided, wherein the processor is used to run a program, wherein when the program is run, any one of the above-mentioned dehydration control methods for a washing machine is executed.

[0022] According to another aspect of an embodiment of the present invention, a computer program product is further provided, comprising computer instructions, wherein when the computer instructions are executed by a processor, any one of the above-mentioned dehydration control methods for a washing machine is executed.

[0023] In an embodiment of the present invention, in a first acquisition step, when it is determined that the clothes to be dehydrated in the inner drum of the washing machine have started to be dehydrated, image data of the inner drum and the weight of the clothes to be dehydrated are acquired; in a second acquisition step, the image data is input into a parameter determination model, so as to process the image data using the parameter determination model to obtain clothing state parameters of the clothes to be dehydrated in the inner drum, wherein the parameter determination model is trained using a plurality of groups of first training data by a deep learning method, and each of the plurality of groups of first training data includes: sample image data and sample clothing state parameters corresponding to the sample image data; in a third acquisition step, The clothing state parameters and clothing weight are input into a dehydration strategy determination model, and the clothing state parameters and clothing weight are processed by the dehydration strategy determination model to obtain a dehydration control strategy for dehydrating the washing machine, wherein the dehydration strategy determination model is trained by a deep learning method using multiple groups of second training data, and each of the multiple groups of second training data includes: sample clothing state parameters, sample clothing weight, and sample dehydration control strategies corresponding to the sample clothing state parameters and the sample clothing weight; a control step of controlling the washing machine to perform a dehydration operation according to the dehydration control strategy so that the water content in the inner drum is lower than a water content threshold. Through the above technical scheme, the purpose of obtaining and identifying images of the clothes in the inner drum before formally controlling the dehydration of the washing machine is achieved, analyzing and processing them using the corresponding model, obtaining a dehydration control strategy, and controlling the washing machine to perform dehydration according to the strategy is achieved. The technical effect of directly analyzing and determining the dehydration control strategy before dehydration is achieved to avoid repeated eccentricity detection during the dehydration process of the washing machine, thereby improving the dehydration efficiency of the washing machine, and further solving the technical problem in the related art that it is usually necessary to perform repeated eccentricity detection during the dehydration process of the washing machine, resulting in poor dehydration efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] 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:

[0025] Figure 1 It is a hardware structure block diagram of a mobile terminal of a dehydration control method for a washing machine according to an embodiment of the present invention;

[0026] Figure 2 is a flow chart of a dehydration control method of a washing machine according to an embodiment of the present invention;

[0027] Figure 3 is a flow chart of an optional dehydration control method of a washing machine according to an embodiment of the present invention;

[0028] Figure 4is a schematic diagram of an original image of clothes to be dehydrated according to an embodiment of the present invention;

[0029] Figure 5 is a schematic diagram of identifying and marking clothes to be dehydrated according to an embodiment of the present invention;

[0030] Figure 6 is a schematic diagram of a training dehydration strategy determination model according to an embodiment of the present invention;

[0031] Figure 7 2 is a schematic diagram of a dehydration control device of a washing machine according to an embodiment of the present invention. DETAILED DESCRIPTION

[0032] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme 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 described embodiments 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 creative work should fall within the scope of protection of the present invention.

[0033] It should be noted that the terms "first", "second", etc. in the specification 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 data 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 that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0034] As introduced in the background art, the related art usually requires repeated eccentricity detection during the dehydration process of the washing machine, resulting in poor dehydration efficiency. In view of the above defects, a dehydration control method and device for a washing machine and a computer readable storage medium are provided in an embodiment of the present invention.

[0035] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0036] 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 1FIG. 1 is a hardware structure block diagram of a mobile terminal of a washing machine dehydration control method according to an embodiment of the present invention. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can 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 as shown, or with Figure 1 Different configurations shown.

[0037] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the dehydration control 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 program stored in the memory 104, that is, the above method is implemented. The memory 104 may include a high-speed random access memory, and may also include a 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 arranged relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. The transmission device 106 is used to receive or send data via a network. The above-mentioned specific example of the network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate 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.

[0038] According to an embodiment of the present invention, a method embodiment of a dehydration control 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.

[0039] Figure 2: is a flow chart of a dehydration control method for a washing machine according to an embodiment of the present invention. Figure 2 As shown, the method comprises the following steps:

[0040] Step S202, a first acquisition step, in which, when it is determined to start dehydrating the clothes to be dehydrated in the inner drum of the washing machine, image data of the inner drum and the weight of the clothes to be dehydrated are acquired.

[0041] Optionally, the above-mentioned image data may include but is not limited to: first image data and second image data.

[0042] The first image data and the second image data are obtained by taking pictures of image acquisition devices arranged at different positions in the inner drum of the washing machine.

[0043] According to the above embodiment of the present invention, in the above step S202, when it is determined that the dehydration treatment of the clothes to be dehydrated in the inner drum of the washing machine has started, the image data of the inner drum and the weight of the clothes to be dehydrated are obtained, including: when it is determined that the drainage operation of the washing machine has ended, it is determined that the dehydration treatment of the clothes to be dehydrated in the inner drum has started; the washing machine is controlled to perform a shaking operation to shake the clothes to be dehydrated in the inner drum, wherein the shaking operation is used to make the looseness of the clothes to be dehydrated higher than the loose threshold; the washing machine is controlled to perform a dehydration operation at a preset speed, and the cumulative time of the washing machine performing the dehydration operation at the preset speed is counted; when the cumulative time reaches a predetermined time, the washing machine is controlled to stop performing the dehydration operation at the preset speed, and the image data and the weight of the clothes are obtained.

[0044] Combine the following Figure 3 The above embodiments of the present invention are described in detail. Figure 3 is a flow chart of an optional dehydration control method of a washing machine according to an embodiment of the present invention.

[0045] like Figure 3 As shown, after the drainage is completed and before the dehydration stage begins, a dehydration pre-processing stage is first required to execute a low-speed shaking program to shake the clothes in the drum as much as possible, and uniformly execute a low-speed dehydration program for a period of time (i.e., a predetermined duration) to reduce the impact of other irrelevant or redundant features when analyzing subsequent processes.

[0046] According to the above embodiment of the present invention, in the above step S202, the image data of the inner drum and the weight of the clothes to be dehydrated are obtained, including: using a first image acquisition device to acquire first image data of the inner drum, and using a second image acquisition device to acquire second image data of the inner drum, wherein the first image acquisition device is an image acquisition device installed directly in front of the inner drum, and the second image acquisition device is an image acquisition device installed above the front or above the rear of the inner drum; using a built-in weighing module in the washing machine to weigh the clothes to be dehydrated to obtain the weight of the clothes to be dehydrated.

[0047] Optionally, the above-mentioned image acquisition device may include but is not limited to: a camera, an infrared sensor and other devices that can be used to acquire images.

[0048] Combine the following Figure 4 The above embodiments of the present invention are described in detail. Figure 4 is a schematic diagram of an original image of clothes to be dehydrated according to an embodiment of the present invention.

[0049] As above Figure 3 As shown, after the pre-processing stage is finished, the two cameras in the inner drum can be controlled to shoot the clothes in the drum to obtain the following Figure 4 The image data shown can also control a built-in weighing module in the washing machine to weigh the clothes to be dehydrated to obtain the weight g of the clothes to be dehydrated.

[0050] It should be noted that Figure 4 The image data shown is only the data taken by one of the two cameras. The two cameras are set at different positions in the inner tube and are both used to obtain the distribution state of the clothes in the tube. The only difference is the shooting angle.

[0051] The first camera (i.e., the first image acquisition device) here can be installed directly in front of the inner drum of the washing machine to capture the situation of the clothes in the inner drum of the washing machine. The second camera (i.e., the second image acquisition device) can be installed at a higher position in the front or rear of the inner drum of the washing machine to capture the image data of the inner drum of the washing machine from an oblique downward direction.

[0052] Step S204, a second acquisition step, inputs the image data into a parameter determination model to process the image data using the parameter determination model to obtain clothing state parameters of the clothing to be dehydrated in the inner drum, wherein the parameter determination model is trained using a plurality of groups of first training data through a deep learning method, and each of the plurality of groups of first training data includes: sample image data, and sample clothing state parameters corresponding to the sample image data.

[0053] Combine the following Figure 5 The above embodiments of the present invention are described in detail. Figure 5Schematic diagram of identifying and marking clothes to be dehydrated according to an embodiment of the present invention.

[0054] In this embodiment, the trained parameters can be used to determine the model pair Figure 4 The image data shown is analyzed to mark it and obtain corresponding clothing state parameters.

[0055] The parameter determination model here uses a large number of similar Figure 5 The Mobi leU-net model is trained with the labeled images shown in the figure. A large number of labeled images are used to train the Mobi leU-net model. The trained model can Figure 4 The original image of the clothes in the inner drum of the washing machine is used for model calculation to identify the stacking height h, the expanded area s and the distribution state parameter θ of the clothes in the inner drum, so as to facilitate the subsequent prediction of the speed-up node curve of the inner drum dehydration.

[0056] In the above embodiment of the present invention, the image data is input into the parameter determination model, and the image data is processed by the parameter determination model to obtain the clothing state parameters of the clothes to be dehydrated in the inner drum, including: inputting the first image data into the parameter determination model, and processing the first image data by the parameter determination model to obtain the stacking height of the clothes to be dehydrated in the inner drum; inputting the second image data into the parameter determination model, and processing the second image data by the parameter determination model to obtain the expansion area and distribution state of the clothes to be dehydrated in the inner drum, wherein the distribution state includes the position and uniformity of the distribution of the clothes to be dehydrated in the inner drum; and integrating the stacking height, expansion area and distribution state to obtain the clothing state parameters of the clothes to be dehydrated in the inner drum.

[0057] Specifically, a first camera is installed at the front of the washing machine to shoot the front of the washing machine's inner drum. Based on the image captured by the first camera, a large number of images are labeled based on the semantic segmentation technology of computer vision, and the labeled images are made into a data set; the data set is trained on the Mobile U-net model of the convolutional neural network (CNN), and the training results can identify the parts of the clothes and the washing machine that are respectively segmented and the current stacking thickness h of the clothes in the washing machine for the real-time pictures; the second camera is installed at a higher position at the front or rear of the washing machine's inner drum to shoot the image of the washing machine's inner drum from an oblique downward direction. Based on the image captured by the second camera, a large number of images are labeled based on the semantic segmentation technology of computer vision, and the labeled images are made into a data set; the data set is trained on the Mobile U-net model of the convolutional neural network (CNN). leU-net model training, the training result can identify the parts of the clothes and the washing machine respectively, and the current expanded area s of the clothes in the side wall of the inner drum of the washing machine for the real-time pictures; it is worth noting that when the clothes in the drum have the same stacking height h and expanded area s, it is not possible to uniquely determine the state of the clothes in the inner drum, and different distribution states of clothes will also have different effects on the subsequent dehydration control process; in addition to the stacking height and the expanded area, it is necessary to introduce another variable to describe the current distribution state of the clothes in the inner drum. Therefore, the clothing distribution state parameter θ is introduced in the embodiment of the present invention. In addition to obtaining the area parameter through the second camera, the distribution state parameter θ of the clothes in the drum needs to be calculated using the semantic segmentation technology.

[0058] Step S206, the third acquisition step, inputs the clothing state parameters and the clothing weight into the dehydration strategy determination model, so as to use the dehydration strategy determination model to process the clothing state parameters and the clothing weight, and obtain a dehydration control strategy for dehydrating the washing machine, wherein the dehydration strategy determination model is trained using a plurality of groups of second training data through a deep learning method, and each of the plurality of groups of second training data includes: sample clothing state parameters, sample clothing weight, and sample dehydration control strategies corresponding to the sample clothing state parameters and the sample clothing weight.

[0059] In this embodiment, the trained dehydration strategy determination model can be used to analyze and process the stacking height h, unfolding area s, distribution state θ and clothing weight g of the clothes obtained in the above steps, so as to predict the speed-up node process of the pre-dehydration and main dehydration stages of the clothes in the current drum through the calculation of multi-layer neurons, that is, the dehydration control strategy for controlling the washing machine to perform dehydration processing.

[0060] Combine the following Figure 6 The training process of the dehydration strategy determination model in the above embodiment of the present invention is described in detail. Figure 6is a schematic diagram of a training dehydration strategy determination model according to an embodiment of the present invention.

[0061] In addition, the convolutional neural network needs to be processed on a remote server when performing image segmentation and feature point extraction, mainly because the remote server can provide high-performance computing resources, efficient data processing capabilities, flexible scalability, high stability and reliability, strict security and efficient network connections, thereby meeting the needs of large-scale image processing and analysis; therefore, in the embodiment of the present invention, the convolutional neural network (CNN) Mobi can be completed by deploying a server at a remote end. The preliminary model training of leU-net and the recognition tasks during the actual operation of the washing machine are also used to complete the training and calculation of the BP neural network. In actual use, after the pre-processing is completed, the clothes in the drum are photographed through the two built-in cameras. After obtaining the photos in the drum, the photos are transmitted to the remote server. Relying on the high performance of the remote server, the photos can be quickly processed. After receiving the photos, the remote server inputs them into the semantic segmentation model. Through the segmentation processing of the model, the stacking height h, unfolding area s and distribution state θ of the clothes in the current photo in the drum of the washing machine are obtained. The weight g of the clothes in the drum can be calculated locally through the weighing module in the washing machine body, and the weight g of the clothes in the drum is also sent to the remote server. After receiving the parameter g, it inputs the other three parameters obtained by itself into the prediction model BP neural network. The prediction model predicts the speed-up node process of the pre-dehydration and main dehydration stages of the current clothes in the drum through the calculation of multi-layer neurons based on the four parameters passed in.

[0062] Specifically, the historical operation data of the washing machine can be collected and a large number of inner drum images can be input as a data set. Figure 4 The MobileU-net convolutional neural network shown in the figure is used to train the network. The trained network can calculate the stacking height h, unfolding area s, mass g in the drum, and distribution state parameter θ of the clothes in the drum and obtain the subsequent program execution process corresponding to the above related parameters (including: speed-up node process prediction in the pre-dehydration and main dehydration stages); the stacking height h, unfolding area s, weight g of the clothes in the drum and the current distribution state θ of the clothes in the drum are regarded as a data point, and then the collected data is cleaned and preprocessed to remove noise, outliers and redundant information. Finally, the data is labeled to clarify the subsequent execution process corresponding to each data point. Then a data set consisting of a large number of data points is input into Figure 6 The BP neural network shown is used to train the network and adjust the model parameters to optimize the prediction performance.

[0063] Step S208, a control step, controls the washing machine to perform a dehydration operation according to a dehydration control strategy so that the water content in the inner drum is lower than a water content threshold.

[0064] In this embodiment, the washing machine can be controlled to perform dehydration processing according to the dehydration control strategy obtained in the above steps to complete the dehydration operation.

[0065] According to the above embodiment of the present invention, in the above step S208, the dehydration operation includes a pre-dehydration operation and a main dehydration operation, and the washing machine is controlled to perform the dehydration operation according to the dehydration control strategy so that the water content in the inner drum is lower than the water content threshold, including: dividing the dehydration control strategy to obtain the pre-dehydration control strategy and the main dehydration control strategy, wherein the pre-dehydration control strategy is used to control the pre-dehydration stage in the dehydration process of the washing machine, and the main dehydration control strategy is used to control the main dehydration stage in the dehydration process of the washing machine, and the pre-dehydration stage is the previous dehydration stage of the main dehydration stage; determining the pre-dehydration speed increase of the inner drum according to the pre-dehydration control strategy Curve, wherein the pre-spin speed-up curve refers to the predicted speed-up curve of the speed in the pre-spin stage; controlling the washing machine to perform the pre-spin operation according to the pre-spin control strategy to obtain the actual pre-spin speed-up curve of the speed, wherein the pre-spin operation refers to the spin operation performed in the pre-spin stage; comparing the actual pre-spin speed-up curve with the pre-spin speed-up curve to obtain a comparison result; determining a target main spin control strategy for controlling the main spin stage according to the comparison result; controlling the washing machine to perform the main spin operation according to the target main spin control strategy to make the water content in the inner drum lower than the water content threshold, wherein the main spin operation refers to the spin operation performed in the main spin stage.

[0066] Specifically, according to the method of the above steps of the present invention, when the dehydration work is actually performed, the actually captured picture inside the drum can be transmitted to the Mobile-net network model, and after the model calculation, h, s, θ and the obtained g value can be input into the BP neural network for prediction, so as to obtain the pre-dehydration speed-up process curve corresponding to the current amount of clothes and the state of clothes; then, according to the predicted speed-up node process, the speed-up curve in the pre-dehydration stage is determined (for example, assuming that the predicted speed-up curve has three speed adjustment nodes: 200 rpm -> 400 rpm -> 500 rpm). After the pre-dehydration stage is completed, the actual operation result can be compared with the predicted result to further determine the control method for the main dehydration stage.

[0067] In the above embodiment of the present invention, determining a target main dehydration control strategy for controlling the main dehydration stage according to the comparison result includes: when the comparison result indicates that the actual pre-dehydration speed-up curve is the same as the pre-dehydration speed-up curve, determining the main dehydration control strategy as the target main dehydration control strategy; when the comparison result indicates that the actual pre-dehydration speed-up curve is the same as the pre-dehydration speed-up curve, acquiring current image data of the inner drum and current weight of the clothes to be dehydrated, wherein the current image data refers to data of the inner drum after the washing machine performs a pre-dehydration operation, and the current weight of the clothes refers to the weight of the clothes to be dehydrated after the washing machine performs a pre-dehydration operation; after updating the image data input into the parameter determination model to the current image data and updating the weight of the clothes input into the dehydration strategy determination model to the current weight of the clothes, sequentially executing the second acquisition step and the third acquisition step to obtain the target main dehydration control strategy for controlling the main dehydration stage.

[0068] Specifically, if the actual operation result of the pre-spinning stage is consistent with the predicted result (it is necessary to consider that the eccentricity effect may cause the actual speed-up process to differ from the predicted process), the speed-up node process of the main spin stage is directly started according to the previous predicted result (for example, assuming that the predicted speed-up curve has four speed adjustment nodes: 600 rpm -> 800 rpm -> 1000 rpm -> 1200 rpm) until the spin stage ends (the pre-spinning and main spin speed-up node process curves may contain n speed adjustment nodes); if the actual operation result of the pre-spinning stage is different from the predicted result, the pre-processing, image shooting, remote processing, process prediction and other stages are repeatedly executed according to the current state of the clothes in the inner drum, and the pre-spinning is directly skipped to directly execute the newly predicted speed-up node process of the main spin stage until the spin stage ends.

[0069] In an optional embodiment of the present invention, the dehydration control method of the washing machine also includes: after each time the parameter determination model is used to obtain the clothing state parameters corresponding to the image data, the parameter determination model is optimized according to the image data and the clothing state parameters to obtain the optimized parameter determination model; after each time the dehydration strategy determination model is used to obtain the dehydration control strategy corresponding to the clothing state parameters and the clothing weight, the dehydration strategy determination model is optimized according to the clothing state parameters, the clothing weight and the dehydration control strategy to obtain the optimized dehydration strategy determination model.

[0070] Specifically, in the process of using the trained parameter determination model and the dehydration strategy determination model to control the dehydration process of the washing machine, the two models can be continuously adaptively optimized using the actual data used in each control process to improve the performance of the model.

[0071] As can be seen from the above, through the technical solution provided by the above embodiments of the present invention, in the first acquisition step, when it is determined to start dehydrating the clothes to be dehydrated in the inner drum of the washing machine, the image data of the inner drum and the clothes weight of the clothes to be dehydrated can be acquired; in the second acquisition step, the image data is input into the parameter determination model, so as to process the image data by using the parameter determination model to obtain the clothes state parameters of the clothes to be dehydrated in the inner drum, wherein the parameter determination model is trained by using a deep learning method using multiple groups of first training data, and each of the multiple groups of first training data includes: sample image data, and sample clothes state parameters corresponding to the sample image data; in the third acquisition step, the clothes state parameters and the clothes weight are input into the dehydration strategy determination model, so as to process the clothes state parameters and the clothes weight by using the dehydration strategy determination model to obtain the clothes state parameters and the clothes weight of the washing machine for dehydration. The invention discloses a dehydration control strategy for processing, wherein the dehydration strategy determination model is obtained by training with a plurality of groups of second training data by a deep learning method, and each of the plurality of groups of second training data includes: sample clothing state parameters, sample clothing weights, and sample dehydration control strategies corresponding to the sample clothing state parameters and the sample clothing weights; a control step, controlling the washing machine to perform a dehydration operation according to the dehydration control strategy, so that the water content in the inner drum is lower than a water content threshold value, achieving the purpose of obtaining a dehydration control strategy by acquiring and identifying images of the clothing in the inner drum before formally controlling the dehydration of the washing machine, analyzing and processing the images using a corresponding model, and controlling the washing machine to perform dehydration processing according to the strategy, achieving the technical effect of directly analyzing and determining the dehydration control strategy before dehydration, so as to avoid repeated eccentricity detection during the dehydration process of the washing machine, thereby improving the dehydration efficiency of the washing machine.

[0072] Therefore, the technical solution provided by the above-mentioned embodiment of the present invention solves the technical problem in the related art that eccentricity detection is usually required to be performed repeatedly during the dehydration process of the washing machine, resulting in poor dehydration efficiency.

[0073] 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 the present application is not limited by the described order of actions, because according to the present 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 the present application.

[0074] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for 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.

[0075] According to an embodiment of the present invention, a dehydration control device for a washing machine is provided for implementing the dehydration control method for the washing machine. Figure 7 Schematic diagram of a dehydration control device for a washing machine according to an embodiment of the present invention. Figure 7 As shown, the device comprises: a first acquisition unit 71, a second acquisition unit 73, a third acquisition unit 75 and a control unit 77. The dehydration control device of the washing machine is described in detail below.

[0076] The first acquisition unit 71 is used to execute a first acquisition step, and when it is determined to start dehydrating the clothes to be dehydrated in the inner drum of the washing machine, acquire the image data of the inner drum and the weight of the clothes to be dehydrated.

[0077] The second acquisition unit 73 is used to execute the second acquisition step, input the image data into the parameter determination model, and use the parameter determination model to process the image data to obtain clothing state parameters of the clothes to be dehydrated in the inner drum, wherein the parameter determination model is trained by a deep learning method using multiple groups of first training data, and each of the multiple groups of first training data includes: sample image data, and sample clothing state parameters corresponding to the sample image data.

[0078] The third acquisition unit 75 is used to execute the third acquisition step, input the clothing state parameters and the clothing weight into the dehydration strategy determination model, and use the dehydration strategy determination model to process the clothing state parameters and the clothing weight to obtain a dehydration control strategy for dehydrating the washing machine, wherein the dehydration strategy determination model is trained using multiple groups of second training data through a deep learning method, and each of the multiple groups of second training data includes: sample clothing state parameters, sample clothing weight, and sample dehydration control strategies corresponding to the sample clothing state parameters and the sample clothing weight.

[0079] The control unit 77 is used to execute the control step to control the washing machine to perform a dehydration operation according to the dehydration control strategy so that the water content in the inner drum is lower than the water content threshold.

[0080] It should be noted here that the above-mentioned first acquisition unit 71, second acquisition unit 73, third acquisition unit 75 and control unit 77 correspond to steps S202 to S208 in the above-mentioned embodiments, and the four units and the corresponding steps implement the same instances and application scenarios, but are not limited to the contents disclosed in the above-mentioned embodiments.

[0081] As can be seen from the above, in the scheme recorded in the above-mentioned embodiment of the present invention, the first acquisition unit can be used to perform the first acquisition step, and when it is determined to start dehydrating the clothes to be dehydrated in the inner drum of the washing machine, the image data of the inner drum and the clothes weight of the clothes to be dehydrated are acquired; then the second acquisition unit is used to perform the second acquisition step, and the image data is input into the parameter determination model, so as to process the image data using the parameter determination model to obtain the clothes state parameters of the clothes to be dehydrated in the inner drum, wherein the parameter determination model is trained by a deep learning method using multiple groups of first training data, and each of the multiple groups of first training data includes: sample image data, and sample clothes state parameters corresponding to the sample image data; then the third acquisition unit is used to perform the third acquisition step, and the clothes state parameters and the clothes weight are input into the dehydration strategy determination model, so as to process the clothes state parameters and the clothes weight using the dehydration strategy determination model, A dehydration control strategy for dehydrating a washing machine is obtained, wherein a dehydration strategy determination model is obtained by training with a plurality of groups of second training data by a deep learning method, and each of the plurality of groups of second training data includes: sample clothing state parameters, sample clothing weights, and sample dehydration control strategies corresponding to the sample clothing state parameters and the sample clothing weights; finally, a control unit is used to execute a control step to control the washing machine to perform a dehydration operation according to the dehydration control strategy, so that the water content in the inner drum is lower than a water content threshold value, thereby achieving the purpose of acquiring and identifying images of the clothing in the inner drum before formally controlling the dehydration of the washing machine, analyzing and processing the images with a corresponding model, obtaining a dehydration control strategy, and controlling the washing machine to perform dehydration according to the strategy, thereby achieving a technical effect of directly analyzing and determining a dehydration control strategy before dehydration, so as to avoid repeated eccentricity detection during the dehydration process of the washing machine, thereby improving the dehydration efficiency of the washing machine.

[0082] Therefore, the technical solution provided by the above-mentioned embodiment of the present invention solves the technical problem in the related art that eccentricity detection is usually required to be performed repeatedly during the dehydration process of the washing machine, resulting in poor dehydration efficiency.

[0083] In an optional embodiment of the present invention, a first acquisition unit includes: a first determination module, used to determine to start dehydrating the clothes to be dehydrated in the inner drum when it is determined that the drainage operation of the washing machine is completed; a first control module, used to control the washing machine to perform a shaking operation to shake the clothes to be dehydrated in the inner drum, wherein the shaking operation is used to make the looseness of the clothes to be dehydrated higher than a loose threshold; a second control module, used to control the washing machine to perform a dehydration operation at a preset speed, and count the cumulative time of the washing machine performing the dehydration operation at the preset speed; a third control module, used to control the washing machine to stop performing the dehydration operation at the preset speed when the cumulative time reaches a predetermined time, and obtain image data and clothing weight.

[0084] In an optional embodiment of the present invention, the image data includes first image data and second image data, and the first acquisition unit includes: an acquisition module, used to use a first image acquisition device to acquire first image data of the inner drum, and use a second image device to acquire second image data of the inner drum, wherein the first image acquisition device is an image acquisition device installed directly in front of the inner drum, and the second image acquisition device is an image acquisition device installed above the front or above the rear of the inner drum; the first acquisition module is used to use a built-in weighing module in the washing machine to weigh the clothes to be dehydrated to obtain the weight of the clothes to be dehydrated.

[0085] In an optional embodiment of the present invention, the second acquisition unit includes: a second acquisition module, which is used to input the first image data into a parameter determination model, so as to process the first image data using the parameter determination model to obtain the stacking height of the clothes to be dehydrated in the inner drum; a third acquisition module, which is used to input the second image data into the parameter determination model, so as to process the second image data using the parameter determination model to obtain the expansion area and distribution state of the clothes to be dehydrated in the inner drum, wherein the distribution state includes the position and uniformity of the distribution of the clothes to be dehydrated in the inner drum; and a fourth acquisition module, which is used to integrate the stacking height, expansion area and distribution state to obtain the clothing state parameters of the clothes to be dehydrated in the inner drum.

[0086] In an optional embodiment of the present invention, the dehydration operation includes a pre-dehydration operation and a main dehydration operation, and the control unit includes: a fifth acquisition module, which is used to divide the dehydration control strategy to obtain the pre-dehydration control strategy and the main dehydration control strategy, wherein the pre-dehydration control strategy is used to control the pre-dehydration stage in the dehydration process of the washing machine, and the main dehydration control strategy is used to control the main dehydration stage in the dehydration process of the washing machine, and the pre-dehydration stage is a dehydration stage before the main dehydration stage; a second determination module, which is used to determine the pre-dehydration speed-up curve of the rotation speed of the inner drum according to the pre-dehydration control strategy, wherein the pre-dehydration speed-up curve refers to the predicted speed-up curve of the rotation speed in the pre-dehydration stage. line; a fourth control module, used to control the washing machine to perform a pre-spinning operation according to the pre-spinning control strategy, and obtain an actual pre-spinning speed-up curve of the rotation speed, wherein the pre-spinning operation refers to a spin operation performed in the pre-spinning stage; a sixth acquisition module, used to compare the actual pre-spinning speed-up curve with the pre-spinning speed-up curve to obtain a comparison result; a third determination module, used to determine a target main spin control strategy for controlling the main spin stage according to the comparison result; a fifth control module, used to control the washing machine to perform a main spin operation according to the target main spin control strategy, so that the water content in the inner drum is lower than the water content threshold, wherein the main spin operation refers to a spin operation performed in the main spin stage.

[0087] In an optional embodiment of the present invention, the third determination module includes: a first determination submodule, which is used to determine that the main dehydration control strategy is the target main dehydration control strategy when the comparison result indicates that the actual pre-dehydration speed-up curve is the same as the pre-dehydration speed-up curve; a first acquisition submodule, which is used to acquire the current image data of the inner drum and the current weight of the clothes to be dehydrated when the comparison result indicates that the actual pre-dehydration speed-up curve is the same as the pre-dehydration speed-up curve, wherein the current image data refers to the data of the inner drum after the washing machine performs the pre-dehydration operation, and the current clothes weight refers to the weight of the clothes to be dehydrated after the washing machine performs the pre-dehydration operation; a second acquisition submodule, which is used to update the image data input into the parameter determination model to the current image data, and update the clothes weight input into the dehydration strategy determination model to the current clothes weight, and then sequentially execute the second acquisition step and the third acquisition step to obtain the target main dehydration control strategy for controlling the main dehydration stage.

[0088] In an optional embodiment of the present invention, the dehydration control device of the washing machine also includes: a first optimization unit, which is used to optimize the parameter determination model according to the image data and the clothing state parameters after the clothing state parameters corresponding to the image data are obtained by using the parameter determination model each time, so as to obtain an optimized parameter determination model; and a second optimization unit, which is used to optimize the dehydration strategy determination model according to the clothing state parameters, clothing weight and dehydration control strategy after the dehydration strategy determination model is used to obtain a dehydration control strategy corresponding to the clothing state parameters and clothing weight each time, so as to obtain an optimized dehydration strategy determination model.

[0089] According to another aspect of the embodiments of the present invention, a dehydration control system of a washing machine is provided. The dehydration control system of the washing machine uses any one of the above-mentioned dehydration control methods of the washing machine.

[0090] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is further provided, the computer-readable storage medium comprising a stored program, wherein the program executes any one of the above-mentioned dehydration control methods for a washing machine.

[0091] 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.

[0092] Optionally, in this embodiment, the computer-readable storage medium is configured to store program codes for executing the following steps: a first acquisition step, in which, when it is determined that the laundry to be dehydrated in the inner drum of the washing machine has started to be dehydrated, image data of the inner drum and the laundry weight of the laundry to be dehydrated are acquired; a second acquisition step, in which the image data is input into a parameter determination model, so as to process the image data using the parameter determination model to obtain laundry state parameters of the laundry to be dehydrated in the inner drum, wherein the parameter determination model is trained using a plurality of sets of first training data by a deep learning method, and each of the plurality of sets of first training data includes: sample image data, sample data corresponding to the sample image data, and a plurality of sample data corresponding to the sample image data. The clothing state parameters; a third acquisition step, inputting the clothing state parameters and the clothing weight into a dehydration strategy determination model, so as to use the dehydration strategy determination model to process the clothing state parameters and the clothing weight, and obtain a dehydration control strategy for dehydrating the washing machine, wherein the dehydration strategy determination model is trained using multiple groups of second training data through a deep learning method, and each of the multiple groups of second training data includes: sample clothing state parameters, sample clothing weight, and a sample dehydration control strategy corresponding to the sample clothing state parameters and the sample clothing weight; a control step, controlling the washing machine to perform a dehydration operation according to the dehydration control strategy, so that the water content in the inner drum is lower than the water content threshold.

[0093] Optionally, in this embodiment, the computer-readable storage medium is configured to store program codes for executing the following steps: when it is determined that the drainage operation of the washing machine is completed, determining to start dehydrating the clothes to be dehydrated in the inner drum; controlling the washing machine to perform a shaking operation to shake the clothes to be dehydrated in the inner drum, wherein the shaking operation is used to make the looseness of the clothes to be dehydrated higher than a loose threshold; controlling the washing machine to perform a dehydration operation at a preset speed, and counting the cumulative time the washing machine performs the dehydration operation at the preset speed; when the cumulative time reaches a predetermined time, controlling the washing machine to stop performing the dehydration operation at the preset speed, and obtaining image data and clothing weight.

[0094] Optionally, in this embodiment, the computer-readable storage medium is configured to store program codes for executing the following steps: using a first image acquisition device to acquire first image data of the inner drum, and using a second image acquisition device to acquire second image data of the inner drum, wherein the first image acquisition device is an image acquisition device installed directly in front of the inner drum, and the second image acquisition device is an image acquisition device installed above the front or above the rear of the inner drum; using a built-in weighing module in the washing machine to weigh the clothes to be dehydrated to obtain the weight of the clothes to be dehydrated.

[0095] Optionally, in this embodiment, the computer-readable storage medium is configured to store program codes for executing the following steps: inputting the first image data into a parameter determination model to process the first image data using the parameter determination model to obtain the stacking height of the clothes to be dehydrated in the inner drum; inputting the second image data into the parameter determination model to process the second image data using the parameter determination model to obtain the expanded area and distribution state of the clothes to be dehydrated in the inner drum, wherein the distribution state includes the position and uniformity of the distribution of the clothes to be dehydrated in the inner drum; integrating the stacking height, expanded area and distribution state to obtain clothing state parameters of the clothes to be dehydrated in the inner drum.

[0096] Optionally, in this embodiment, the computer-readable storage medium is configured to store program codes for executing the following steps: dividing the dehydration control strategy to obtain a pre-dehydration control strategy and a main dehydration control strategy, wherein the pre-dehydration control strategy is used to control the pre-dehydration stage in the dehydration process of the washing machine, and the main dehydration control strategy is used to control the main dehydration stage in the dehydration process of the washing machine, and the pre-dehydration stage is a dehydration stage before the main dehydration stage; determining a pre-dehydration speed-up curve of the rotation speed of the inner drum according to the pre-dehydration control strategy, wherein the pre-dehydration speed-up curve refers to the rotation speed in the pre-dehydration stage. The invention relates to a method for controlling the washing machine to perform a pre-spin operation according to the pre-spin control strategy to obtain an actual pre-spin speed increase curve of the rotation speed, wherein the pre-spin operation refers to a spin operation performed in the pre-spin stage; comparing the actual pre-spin speed increase curve with the pre-spin speed increase curve to obtain a comparison result; determining a target main spin control strategy for controlling the main spin stage according to the comparison result; controlling the washing machine to perform a main spin operation according to the target main spin control strategy to make the water content in the inner drum lower than the water content threshold, wherein the main spin operation refers to a spin operation performed in the main spin stage.

[0097] Optionally, in this embodiment, the computer-readable storage medium is configured to store program codes for executing the following steps: when the comparison result indicates that the actual pre-spin speed-up curve is the same as the pre-spin speed-up curve, determining that the main spin control strategy is the target main spin control strategy; when the comparison result indicates that the actual pre-spin speed-up curve is the same as the pre-spin speed-up curve, obtaining current image data of the inner drum and current weight of the clothes to be spinned, wherein the current image data refers to data of the inner drum after the washing machine performs a pre-spin operation, and the current weight of the clothes refers to the weight of the clothes to be spinned after the washing machine performs a pre-spin operation; after updating the image data input into the parameter determination model to the current image data and updating the weight of the clothes input into the dehydration strategy determination model to the current weight of the clothes, sequentially executing the second acquisition step and the third acquisition step to obtain the target main spin control strategy for controlling the main spin stage.

[0098] Optionally, in this embodiment, the computer-readable storage medium is configured to store program codes for executing the following steps: each time after the parameter determination model is used to obtain the clothing state parameters corresponding to the image data, the parameter determination model is optimized according to the image data and the clothing state parameters to obtain the optimized parameter determination model; each time after the dehydration strategy determination model is used to obtain the dehydration control strategy corresponding to the clothing state parameters and the clothing weight, the dehydration strategy determination model is optimized according to the clothing state parameters, the clothing weight and the dehydration control strategy to obtain the optimized dehydration strategy determination model.

[0099] According to another aspect of an embodiment of the present invention, a processor is further provided, and the processor is used to run a program, wherein when the program is run, any one of the above-mentioned dehydration control methods for a washing machine is executed.

[0100] According to another aspect of an embodiment of the present invention, a computer program product is further provided, comprising computer instructions, and when the computer instructions are executed by a processor, any one of the above-mentioned dehydration control methods for a washing machine is executed.

[0101] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0102] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0103] 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 schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, 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.

[0104] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0105] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0106] If the integrated unit is implemented in the form of 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, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0107] 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 principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A dehydration control method for a washing machine, characterized in that: include: A first acquisition step, when it is determined to start dehydrating the clothes to be dehydrated in the inner drum of the washing machine, acquiring image data of the inner drum and the weight of the clothes to be dehydrated; A second acquisition step is to input the image data into a parameter determination model, so as to process the image data using the parameter determination model to obtain clothing state parameters of the clothing to be dehydrated in the inner drum, wherein the parameter determination model is trained by a deep learning method using multiple groups of first training data, and each of the multiple groups of first training data includes: sample image data and sample clothing state parameters corresponding to the sample image data; A third acquisition step is to input the clothing state parameter and the clothing weight into a dehydration strategy determination model, so as to process the clothing state parameter and the clothing weight using the dehydration strategy determination model to obtain a dehydration control strategy for dehydrating the washing machine, wherein the dehydration strategy determination model is obtained by training with a deep learning method using multiple sets of second training data, each of the multiple sets of second training data comprising: sample clothing state parameters, sample clothing weight, and sample dehydration control strategies corresponding to the sample clothing state parameters and the sample clothing weight; A control step is to control the washing machine to perform a dehydration operation according to the dehydration control strategy so that the water content in the inner drum is lower than a water content threshold.

2. The dehydration control method of a washing machine according to claim 1, characterized in that: When it is determined to start dehydrating the laundry in the inner drum of the washing machine, acquiring image data of the inner drum and the weight of the laundry, including: When it is determined that the drainage operation of the washing machine is finished, determining to start dehydrating the clothes to be dehydrated in the inner drum; Controlling the washing machine to perform a shaking operation to shake out the clothes to be dehydrated in the inner drum, wherein the shaking operation is used to make the degree of looseness of the clothes to be dehydrated higher than a loosening threshold; Controlling the washing machine to perform the dehydration operation at a preset speed, and counting the cumulative time for which the washing machine performs the dehydration operation at the preset speed; When the accumulated time reaches a predetermined time, the washing machine is controlled to stop performing the dehydration operation at the preset rotation speed, and the image data and the laundry weight are acquired.

3. The dehydration control method of a washing machine according to claim 1, characterized in that: The image data includes first image data and second image data, and acquiring the image data of the inner drum and the weight of the clothes to be dehydrated includes: Using a first image acquisition device to acquire the first image data of the inner cylinder, and using a second image acquisition device to acquire the second image data of the inner cylinder, wherein the first image acquisition device is an image acquisition device installed directly in front of the inner cylinder, and the second image acquisition device is an image acquisition device installed above the front part or above the rear part of the inner cylinder; The laundry to be dehydrated is weighed using a weighing module built into the washing machine to obtain the laundry weight of the laundry to be dehydrated.

4. The dehydration control method of a washing machine according to claim 3, characterized in that: Inputting the image data into a parameter determination model, and using the parameter determination model to process the image data to obtain clothing state parameters of the clothing to be dehydrated in the inner drum, comprises: Inputting the first image data into the parameter determination model, so as to process the first image data using the parameter determination model to obtain the stacking height of the clothes to be dehydrated in the inner drum; Inputting the second image data into the parameter determination model, so as to process the second image data using the parameter determination model to obtain the expansion area and distribution state of the clothes to be dehydrated in the inner drum, wherein the distribution state includes the position and uniformity of the clothes to be dehydrated in the inner drum; The stacking height, the unfolded area and the distribution state are integrated to obtain the clothing state parameters of the clothing to be dehydrated in the inner drum.

5. The dehydration control method of a washing machine according to claim 1, characterized in that: The dehydration operation includes a pre-dehydration operation and a main dehydration operation, and controlling the washing machine to perform the dehydration operation according to the dehydration control strategy so that the water content in the inner drum is lower than the water content threshold value includes: The dehydration control strategy is divided into a pre-dehydration control strategy and a main dehydration control strategy, wherein the pre-dehydration control strategy is used to control the pre-dehydration stage in the dehydration process of the washing machine, and the main dehydration control strategy is used to control the main dehydration stage in the dehydration process of the washing machine, and the pre-dehydration stage is a dehydration stage before the main dehydration stage; Determine a pre-dehydration speed-up curve of the rotation speed of the inner drum according to the pre-dehydration control strategy, wherein the pre-dehydration speed-up curve refers to a predicted speed-up curve of the rotation speed in the pre-dehydration stage; Controlling the washing machine to perform the pre-spinning operation according to the pre-spinning control strategy to obtain an actual pre-spinning speed increase curve of the rotation speed, wherein the pre-spinning operation refers to the spin operation performed in the pre-spinning stage; Comparing the actual pre-dehydration speed-up curve with the pre-dehydration speed-up curve to obtain a comparison result; Determining a target main dehydration control strategy for controlling the main dehydration stage according to the comparison result; The washing machine is controlled to perform a main dehydration operation according to the target main dehydration control strategy so that the water content in the inner drum is lower than a water content threshold, wherein the main dehydration operation refers to the dehydration operation performed in the main dehydration stage.

6. The dehydration control method of a washing machine according to claim 5, characterized in that: Determining a target main dehydration control strategy for controlling the main dehydration stage according to the comparison result includes: When the comparison result indicates that the actual pre-dehydration speed-up curve is the same as the pre-dehydration speed-up curve, determining the main dehydration control strategy as the target main dehydration control strategy; When the comparison result indicates that the actual pre-spin speed increasing curve is the same as the pre-spin speed increasing curve, obtaining current image data of the inner drum and current weight of the clothes to be spun, wherein the current image data refers to data of the inner drum after the washing machine performs the pre-spin operation, and the current weight of the clothes refers to the weight of the clothes to be spun after the washing machine performs the pre-spin operation; After updating the image data input into the parameter determination model to the current image data and updating the clothing weight input into the dehydration strategy determination model to the current clothing weight, the second acquisition step and the third acquisition step are sequentially performed to obtain the target main dehydration control strategy for controlling the main dehydration stage.

7. The dehydration control method of a washing machine according to claim 1, characterized in that: Also includes: After obtaining the clothing state parameter corresponding to the image data by using the parameter determination model each time, optimizing the parameter determination model according to the image data and the clothing state parameter to obtain the optimized parameter determination model; After the dehydration strategy determination model is used each time to obtain the dehydration control strategy corresponding to the clothing state parameter and the clothing weight, the dehydration strategy determination model is optimized according to the clothing state parameter, the clothing weight and the dehydration control strategy to obtain the optimized dehydration strategy determination model.

8. A dehydration control device for a washing machine, characterized in that: include: A first acquisition unit is used to execute a first acquisition step, and when it is determined to start dehydrating the clothes to be dehydrated in the inner drum of the washing machine, acquire the image data of the inner drum and the weight of the clothes to be dehydrated; a second acquisition unit, configured to execute a second acquisition step, input the image data into a parameter determination model, and process the image data using the parameter determination model to obtain clothing state parameters of the clothing to be dehydrated in the inner drum, wherein the parameter determination model is obtained by training with a plurality of groups of first training data by a deep learning method, and each of the plurality of groups of first training data includes: sample image data and sample clothing state parameters corresponding to the sample image data; a third acquisition unit, configured to execute a third acquisition step, input the clothing state parameter and the clothing weight into a dehydration strategy determination model, and use the dehydration strategy determination model to process the clothing state parameter and the clothing weight to obtain a dehydration control strategy for dehydrating the washing machine, wherein the dehydration strategy determination model is obtained by training with a plurality of groups of second training data by a deep learning method, and each of the plurality of groups of second training data includes: a sample clothing state parameter, a sample clothing weight, and a sample dehydration control strategy corresponding to the sample clothing state parameter and the sample clothing weight; The control unit is used to execute a control step to control the washing machine to perform a dehydration operation according to the dehydration control strategy so that the water content in the inner drum is lower than a water content threshold.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein the program executes the dehydration control method of the washing machine according to any one of claims 1 to 7.

10. A computer program product comprising computer instructions, characterized in that: When the computer instructions are executed by the processor, the dehydration control method of the washing machine according to any one of claims 1 to 7 is performed.

Images