Laundry equipment control method and device, washing machine and computer readable storage medium

Abstract

The invention provides a laundry equipment control method and device, a washing machine and a computer readable storage medium. The method comprises the steps that first clothes image information of target washed clothes in the washing process is acquired; determining first winding probability information of the target cleaning clothes according to the first clothes image information; and controlling the target laundry equipment according to the first winding probability information. According to the laundry equipment control method provided by the invention, the first clothes image information of the target clothes to be washed in the washing process can be firstly obtained, and the first winding probability information of the target clothes to be washed in the washing process is determined through image recognition. Afterwards, parameters related to rotation of the target laundry equipment and the like can be controlled according to the first winding probability information, and then the probability of clothes winding is reduced.

Description

Technical Field

[0001] The present application relates to the field of electrical appliance technology, and in particular to a laundry appliance control method and device, a washing machine, and a computer-readable storage medium. Background Art

[0002] In existing technology, after a laundry machine finishes washing clothes, the clothes that the user removes often become tangled. During the washing process, the clothes are agitated by the washing machine, causing them to gradually become tangled. For some fragile items, excessive tangling can easily damage them. Furthermore, tangled clothes can take a long time to untangle. Therefore, there is a need to prevent or reduce the degree of tangling during the washing process. Summary of the Invention

[0003] The present application provides a laundry appliance control method that can reduce the probability of clothes becoming entangled.

[0004] In a first aspect, the present application provides a laundry appliance control method, the method comprising:

[0005] Acquire first clothing image information of a target laundry during a washing process;

[0006] determining first entanglement probability information of the target laundry according to the first laundry image information;

[0007] The target laundry appliance is controlled according to the first entanglement probability information.

[0008] In some embodiments of the present application, determining first entanglement probability information of the target laundry according to the first laundry image information includes:

[0009] performing optical flow feature extraction on the first clothing image information to determine motion direction information corresponding to each clothing item in the target laundry;

[0010] Determining movement direction consistency information of the target laundry items based on movement direction information corresponding to each item of laundry and rolling direction information of the target laundry device during the washing process;

[0011] First entanglement probability information of the target laundry is determined according to the movement direction consistency information.

[0012] In some embodiments of the present application, the target laundry device includes a stirring device, and controlling the target laundry device according to the first entanglement probability information includes:

[0013] If the first entanglement probability information is greater than a first target probability threshold, the stirring device is controlled to stir the target laundry and the washing cavity of the target laundry device is controlled to roll in a manner to prevent entanglement.

[0014] In some embodiments of the present application, controlling the stirring device to disperse the target laundry includes:

[0015] determining, based on the first clothing image information, entanglement position information of the target laundry;

[0016] If the entanglement position information is target entanglement position information, the stirring device is controlled to disperse the target laundry and the washing cavity of the target laundry device is controlled to roll in a manner to prevent entanglement.

[0017] In some embodiments of the present application, the method further includes:

[0018] If the first entanglement probability information is less than or equal to the first target probability threshold, the target laundry device is controlled to operate in a non-entanglement state.

[0019] In some embodiments of the present application, before obtaining the first image information of the target laundry during the washing process, the method further includes:

[0020] Determining target material information of the target laundry;

[0021] determining second entanglement probability information of the target laundry according to the target material information;

[0022] The target laundry device is started to enter a washing process according to the second entanglement probability information.

[0023] In some embodiments of the present application, determining target material information of the target laundry includes:

[0024] Acquire second laundry image information of the target laundry;

[0025] Material recognition is performed on the second clothing image information to obtain target material information of the target laundry clothing.

[0026] In some embodiments of the present application, the method further includes:

[0027] If the first entanglement probability information and the second entanglement probability information are both less than or equal to a second target probability threshold, the target laundry appliance is controlled to enter an energy efficiency mode.

[0028] In some embodiments of the present application, after controlling the target laundry appliance according to the first entanglement probability information, the method further includes:

[0029] If the washing of the target laundry is completed, obtaining third laundry image information of the target laundry;

[0030] determining clothing distribution information of the target laundry according to the third clothing image information;

[0031] determining target dehydration parameters for the target laundry according to the laundry distribution information;

[0032] According to the target dehydration parameter, the target laundry device is controlled to dehydrate the target laundry.

[0033] In a second aspect, the present application further provides a laundry appliance control device, the device comprising:

[0034] An acquisition module, configured to acquire first image information of target laundry during a washing process;

[0035] a determination module, configured to determine first entanglement probability information of the target laundry according to the first laundry image information;

[0036] A control module is configured to control a target laundry device according to the first entanglement probability information.

[0037] In a third aspect, the present application also provides a washing machine, which includes a processor, a memory, and a computer program stored in the memory and runnable on the processor, wherein the processor executes the computer program to implement the steps in any one of the laundry device control methods.

[0038] In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored. The computer program is executed by a processor to implement the steps in any one of the laundry appliance control methods.

[0039] The laundry appliance control method provided herein can first obtain first image information of target laundry during the washing process and, through image recognition, determine first entanglement probability information of the target laundry during the washing process. Rotation-related parameters of the target laundry appliance can then be controlled based on the first entanglement probability information, thereby reducing the probability of entanglement. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0041] Figure 1 Schematic diagram of a laundry appliance control system provided in an embodiment of the present application;

[0042] Figure 2 This is a flow chart of an embodiment of a method for controlling a laundry appliance according to an embodiment of the present application;

[0043] Figure 3 This is a schematic diagram of a functional module of a laundry appliance control device according to an embodiment of the present application;

[0044] Figure 4 It is a structural diagram of the washing machine in an embodiment of the present application. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.

[0046] In the description of this application, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise specifically defined.

[0047] In this application, the word "exemplary" is used to mean "serving as an example, illustration, or illustration." Any embodiment described in this application as "exemplary" is not necessarily to be construed as being preferred or advantageous over other embodiments. At the same time, it is understood that in the specific implementation of this application, when user information, user data, and other related data are involved, when the above embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use, and processing of relevant data must comply with relevant laws, regulations, and standards of relevant countries and regions.

[0048] The following description is presented to enable any person skilled in the art to practice the application as claimed. Details are set forth in the following description for purpose of explanation. It should be appreciated that one of ordinary skill in the art will realize and / or be aware that the application can be practiced without the use of these specific details. In other instances, well-known structures and processes are not elaborated as they would be appreciated reported by those with skill in the art. The application is not intended to be limited in scope by the

[0049] The application provides a laundry equipment control method, device, equipment and storage medium, which are described in detail below.

[0050] Please refer to Figure 1 , Figure 1 The scene diagram of the laundry equipment control system provided by the embodiment of the application can include a washing machine 100. As shown in Figure 1 , the washing machine 100 can obtain the related control logic stored in the washing machine 100 to execute the laundry equipment control method in the application.

[0051] In the embodiment of the application, the washing machine 100 can be a drum washing machine, an impeller washing machine or the like.

[0052] It should be noted that Figure 1 The scene diagram of the laundry equipment control system shown in the figure is only an example, and the laundry equipment control system and the scene described in the embodiment of the application are used to more clearly illustrate the technical solution of the embodiment of the application, and do not constitute a limitation on the technical solution provided by the embodiment of the application. Those skilled in the art can know that, with the evolution of the laundry equipment control system and the appearance of new business scenarios, the technical solution provided by the embodiment of the application is also applicable to similar technical problems.

[0053] As shown in Figure 2 , Figure 2 The embodiment of the laundry equipment control method in the application is an embodiment flowchart, and specifically includes the following steps 201-203.

[0054] 201, obtaining first clothes image information of target clothes to be washed in a washing process.

[0055] In the embodiment of the application, an image sensor can be installed in the target laundry equipment. The current washing state of the target clothes to be washed is obtained through the image sensor. The installation position of the image sensor is adaptively adjusted according to the space structure of the washing cavity of different models of laundry equipment, and the specific embodiment of the application is not limited.

[0056] Furthermore, the above embodiment provides an implementation in which the laundry appliance itself serves as the execution entity. In this case, the laundry appliance's processor can acquire the first clothing image information sent by the image sensor. Of course, in some cases, the execution entity can also be a cloud server. In this case, the cloud server can acquire the first clothing image information acquired and sent by the laundry appliance and perform image recognition using the server's more powerful computing capabilities. Specifically, this embodiment of the present application is not limited thereto.

[0057] 202. Determine first entanglement probability information of the target laundry according to the first laundry image information.

[0058] In the embodiment of the present application, whether the processor of the laundry appliance or the cloud server obtains the first clothing image information, it can identify the state of the clothing in the current image through image recognition, thereby determining the current first entanglement probability information of the clothing.

[0059] Specifically, the entanglement recognition model can be used to determine the position and posture of each item of clothing in the first clothing image information. Subsequently, under normal circumstances, if the degree of clothing entanglement is high, the visual effect presented is a high degree of interlacing of different colored clothing items. For example, if the number of color alternations per unit area exceeds a certain threshold. Therefore, based on this concept, the alternation of different clothing colors in the first clothing image information can be determined, thereby determining the specific first entanglement probability information. For example, if the number of color alternations per unit area exceeds a target threshold, it is determined to have a high entanglement probability; otherwise, it is determined to have a low entanglement probability.

[0060] In addition, the training method of the entanglement recognition model can be trained by any model method. At the same time, the model architecture of the entanglement recognition model can be any model architecture or any model, including CNN, RNN, YOLOv8, LSTM, etc., which is not limited by the specific embodiments of this application.

[0061] 203. Control the target laundry device according to the first entanglement probability information.

[0062] According to the above steps, the first entanglement probability information of the target laundry during the current washing process can be obtained. If the entanglement probability is high, the target laundry appliance can be controlled to operate in a gentle washing mode, such as by reducing the rotation speed. Alternatively, the target laundry appliance can be controlled to reverse its previous rotation direction, causing the laundry to move in the opposite direction, thereby achieving untangling before it is completely entangled. The specific control method is not limited in this embodiment of the application.

[0063] The laundry appliance control method provided herein can first obtain first image information of target laundry during the washing process and, through image recognition, determine first entanglement probability information of the target laundry during the washing process. Rotation-related parameters of the target laundry appliance can then be controlled based on the first entanglement probability information, thereby reducing the probability of entanglement.

[0064] To better implement the embodiments of the present application, in one embodiment of the present application, determining first entanglement probability information of target laundry based on first laundry image information includes:

[0065] Optical flow feature extraction is performed on the first clothing image information to determine the movement direction information corresponding to each clothing item in the target laundry; based on the movement direction information corresponding to each clothing item and the rolling direction information of the target laundry device during the washing process, the movement direction consistency information of the target laundry items is determined; based on the movement direction consistency information, the first entanglement probability information of the target laundry items is determined.

[0066] The above embodiment provides a solution for determining whether clothes are entangled based on image recognition. In order to improve the ability to determine whether clothes are entangled, the embodiment of the present application also provides a determination method.

[0067] Specifically, since the image sensor can acquire the first clothing image information of the target laundry in real time and continuously. In other words, the acquired first clothing image information, after being combined according to the time sequence information, is a washing video of the target laundry. Therefore, the motion direction information of each piece of clothing in the first clothing image information can be determined by identifying the first clothing image information of adjacent frames. Among them, the motion direction information of each piece of clothing can be determined by an optical flow algorithm. The optical flow calculation process can refer to any optical flow algorithm, and the embodiments of the present application will not be described in detail. Specifically, the motion vectors of the pixel points corresponding to different clothes can be calculated, including the motion direction and speed information.

[0068] Next, after determining the movement direction information of the clothes, the rotation direction of the drum inside the washing chamber can be determined based on the control parameters of the current laundry device. At this time, if the movement direction information of the clothes is inconsistent with the rotation direction, the movement direction consistency information (CDI, Consistency Direction Index) of the target laundry is inconsistent, and at this time it can be determined that the probability of entanglement is high; alternatively, if the movement direction information of the clothes is consistent with the rotation direction, the movement direction consistency information of the target laundry is consistent, and at this time it can be determined that the probability of entanglement is low. Alternatively, the motion vectors of each piece of clothing can be classified according to direction, and the distribution of each direction can be statistically analyzed. The proportion of the main movement direction is calculated. If the proportion exceeds a set threshold (such as 70%) and the main movement direction is consistent with the rotation direction, it is considered that the movement direction consistency is high and the entanglement probability is low. Alternatively, if the proportion does not exceed the set threshold and the main movement direction is inconsistent with the rotation direction, it is considered that the movement direction consistency is low and the entanglement probability is high. The specific probability value can be trained according to the training method of the actual model, and then a specific probability value is output. After determining the probability value, if it exceeds 50%, the entanglement probability is considered high, and if it is less than 50%, the entanglement probability is considered low. The laundry appliance can then be controlled in accordance with the above-described embodiment, which will not be further described here. Furthermore, the CDI value calculation may include defining the ratio of the primary movement direction of all clothing items to the total movement direction distribution. The CDI value ranges from 0 to 1, with values ​​closer to 1 indicating more consistent movement directions.

[0069] To better implement the embodiments of the present application, in one embodiment of the present application, the target laundry device includes a stirring device, and controlling the target laundry device according to the first entanglement probability information includes:

[0070] If the first entanglement probability information is greater than a first target probability threshold, the stirring device is controlled to stir up the target laundry and the washing cavity of the target laundry device is controlled to roll in a manner to prevent entanglement.

[0071] The above embodiment provides a control solution for disentanglement. In order to improve the probability of disentanglement, the embodiment of the present application also provides an implementation method.

[0072] Specifically, a stirring device, such as a stirring rod, can be installed inside the washing chamber of the laundry device. Furthermore, according to the above embodiment, if the first entanglement probability information is greater than a set threshold, the stirring device is controlled to loosen the target laundry. At this point, the stirring condition of the stirring device can be captured by an image sensor, and then an image of the completed stirring can be captured. Based on the image of the completed stirring, it can be determined whether the laundry is loosened. If not, the stirring device is controlled to continue loosening until the loosening task is completed. Alternatively, a certain failure threshold can be set, and if the loosening fails three times, the stirring is stopped. At the same time, regardless of whether the loosening is successful or unsuccessful, the washing chamber can be controlled to roll in a manner to prevent entanglement, including slowing down the rolling, or alternating forward and reverse rolling, etc., without specific limitations. Furthermore, the first target probability threshold can be 70%, 60%, 50%, etc., and can be set specifically according to actual conditions.

[0073] To better implement the embodiments of the present application, in one embodiment of the present application, controlling the stirring device to stir up the target laundry includes:

[0074] According to the first clothing image information, the entanglement position information of the target laundry is determined; if the entanglement position information is the target entanglement position information, the stirring device is controlled to stir the target laundry and the washing cavity of the target laundry device is controlled to roll in a manner to prevent entanglement.

[0075] The above embodiment provides a solution for stirring by controlling the stirring device. Furthermore, the purpose of stirring is to prevent damage to the clothes, so the embodiment of the present application also provides an implementation method. Specifically, if the entanglement position belongs to a vulnerable position of the clothes, the stirring operation is performed again. For example: if the entanglement position identified according to the first clothing image information is the entanglement position information of the sleeve, collar, etc. of the clothes, it can be determined as the target entanglement position information. At this time, the stirring device is controlled to stir and the washing cavity of the target laundry device is controlled to roll in a manner to prevent entanglement. For example, the system automatically switches to the "targeted untangling mode": the impeller rotates 30° clockwise and then immediately rotates 60° counterclockwise, while the stirring rod vibrates vertically at a frequency of 8Hz for 15 seconds to untangle. The specific embodiment of the present application is not limited to it.

[0076] In order to better implement the embodiments of the present application, in one embodiment of the present application, the method further includes:

[0077] If the first entanglement probability information is less than or equal to the first target probability threshold, the target laundry appliance is controlled to operate in a non-entanglement state.

[0078] The above embodiments provide a control scheme of the laundry equipment by unwinding when the entangling probability is high or the entangling has occurred. Therefore, there are also cases where the entangling probability of the laundry is low and no entangling phenomenon exists. Therefore, in this case, the target laundry equipment is controlled to operate in a non-entangling state. The target laundry equipment operating in a non-entangling state can include operating according to the user-set laundry parameters or automatic control of the laundry equipment, which is not limited in the embodiments of the present application.

[0079] To better implement the embodiments of the present application, in an embodiment of the present application, before obtaining the first laundry image information of the target laundry in the cleaning process, the method further comprises:

[0080] determining target material information of the target laundry; determining second entangling probability information of the target laundry according to the target material information; and starting the target laundry equipment to enter the cleaning process according to the second entangling probability information.

[0081] The above embodiments provide a scheme for controlling the laundry equipment according to the entangling probability in the laundry cleaning process. To further reduce the probability of entangling, the embodiments of the present application also provide a scheme for determining the laundry parameters during cleaning to further reduce the probability of entangling.

[0082] Specifically, according to experimental data, it can be obtained that materials with lighter unit mass are more likely to entangle, such as silk and other materials. Therefore, when the target laundry is put into the laundry cavity, the material of the target laundry can be identified first. If the target material information of the target laundry is an easy-to-entangle material, the corresponding entangling probability can be determined according to the specific material information. Preferably, assuming that the target material information of the target laundry is a mixed material including cotton clothes, silk clothes, etc., the proportion of the easy-to-entangle material can be determined, and the corresponding second entangling probability information can be determined according to the specific proportion. For example, assuming that there are a total of 10 pieces of laundry, and the proportion of silk clothes is 80%, the second entangling probability information can be output as 80%, 75%, 85%, etc. When the second entangling probability information exceeds a certain threshold, the easy-to-entangle cleaning mode is started; or when the second entangling probability information does not exceed a certain threshold, it can be started normally. For example, the easy-to-entangle cleaning mode can include a cleaning control scheme of "soft rotation - static stop - micro vibration" cycle.

[0083] In addition, in the embodiments of the present application, to better implement the embodiments of the present application, the target material information of the target laundry is determined, comprising:

[0084] Acquire second clothing image information of the target laundry; perform material recognition on the second clothing image information to obtain target material information of the target laundry.

[0085] The above embodiment provides a method of using image recognition to identify the entanglement of clothes during the washing process. Similarly, before the clothes are placed in the washing chamber, the material information of the clothes can also be identified by image recognition. Specifically, a corresponding material recognition model can be set up to obtain the second image information of the clothes before the clothes enter the washing chamber and the water is added. This can avoid the problem of changing the color and material texture of the clothes after the washing water is injected into the washing chamber, resulting in inaccurate material recognition. After that, it can be identified according to the material. The specific material recognition can refer to any material recognition scheme, such as using the ResNet50 deep learning model to perform spectral analysis on the clothes and extract reflectance features (such as cotton reflectance > 85%). Output result: Accurately identify the material of the clothes (silk, cotton, wool, etc.), with an accuracy rate of > 95%. It can prevent high-value clothes (such as silk) from being damaged due to improper parameters. The specific embodiments of this application will not be described in detail.

[0086] In order to better implement the embodiments of the present application, in one embodiment of the present application, the method further includes:

[0087] If the first entanglement probability information and the second entanglement probability information are both less than or equal to the second target probability threshold, the target laundry appliance is controlled to enter the energy efficiency mode.

[0088] The above embodiment provides a method for controlling the operation of a laundry appliance based on the second entanglement probability information before washing and the first entanglement probability information during washing. Based on this, there may be situations where both the first and second entanglement probability information are less than or equal to a lower second target probability threshold. In this case, the target laundry appliance can be controlled to operate in energy-efficiency mode, achieving energy savings and avoiding frequent stirring of the agitator, which would otherwise waste energy.

[0089] To better implement the embodiments of the present application, in one embodiment of the present application, after controlling the target laundry device according to the first entanglement probability information, the method further includes:

[0090] If the washing of the target laundry is completed, third laundry image information of the target laundry is obtained; based on the third laundry image information, laundry distribution information of the target laundry is determined; based on the laundry distribution information, target dehydration parameters of the target laundry are determined; based on the target dehydration parameters, the target laundry device is controlled to dehydrate the target laundry.

[0091] The above embodiments provide a method for controlling a laundry machine based on the probability of entanglement before and during laundry washing. However, laundry machines typically also include a dehydration process. Assuming no entanglement or untangling occurs during the washing process, uneven distribution of laundry can cause eccentric vibration during the dehydration process, leading to collisions between the drum and the inner wall of the laundry machine. Therefore, embodiments of the present application also provide a method for preventing collisions between the drum and the inner wall of the laundry machine.

[0092] Specifically, when the target laundry is finished washing, the image sensor can be controlled to capture a third image of the laundry. At this point, since the laundry is stationary, the third image can be used to identify the distribution of the target laundry within the washing chamber. If the distribution is uniform, there will be no eccentricity during dehydration, preventing collisions between the drum and the inner wall. If the distribution is uneven, the drum can be controlled to shake the laundry evenly, or the dehydration speed can be low to reduce eccentricity and prevent collisions between the drum and the inner wall.

[0093] In summary, the laundry appliance control solution provided in this application can reduce the probability of clothing entanglement. Generally speaking, the overall architecture of this solution can include: A visual recognition module: Relying on a wide-angle camera to capture high-frequency images, which are processed by the NVIDIA Jetson Nano edge computing chip, it analyzes dynamic characteristics such as clothing distribution and agitator coverage. It also uses a ResNet50 model to perform material spectrum recognition, providing basic data for subsequent control. A prediction module: This module integrates multiple sources of data, including visual recognition results, motor torque fluctuations, and water level change rates, and inputs them into an LSTM neural network model to predict the probability and location of clothing entanglement within a target time period. It then outputs a risk level and intervention recommendations, enabling proactive "anti-entanglement" predictions. A multimodal control module: Based on the AI ​​prediction results, the policy decision unit triggers different control logics. Preventive untangling (spiral water flow) is initiated when the risk of entanglement is high; after identifying the clothing material, it matches a differentiated untangling program (e.g., soft spin for silk, strong rinse for cotton); and switches to energy efficiency priority mode when the risk is low. By planning the motion trajectories of the impeller and agitator, the drive unit executes precisely. It also supports pre-balancing water flow control before dehydration to ensure a stable washing process. System collaboration: The system master control dispatches each module to update data and adjust parameters every 2 seconds. Before washing is completed, torque monitoring and visual uniformity verification are performed to ensure dehydration safety, forming a closed-loop process of "identification-prediction-control-verification" to cover the anti-entanglement needs of the entire clothing washing cycle.

[0094] In addition, in the embodiment of the present application, the training method of the model may also include:

[0095] Input data preprocessing:

[0096] Multi-source data fusion: Integrate multi-dimensional data such as image features of the visual recognition module (clothing distribution density, stirring rod coverage, CDI index), motor torque fluctuation curve, water level change rate, etc.

[0097] Time series data reconstruction: Use a sliding window (such as 10 seconds / window) to convert the original data into a sequence format that can be processed by the LSTM model, preserving time dependencies.

[0098] Normalization and dimensionality reduction: Normalize the features of numerical data such as torque and water level, extract key features through principal component analysis, and reduce computational complexity.

[0099] LSTM network training:

[0100] Network Architecture: Uses multi-layer LSTM units (e.g., 3 layers, 128 neurons per layer) to capture long-term dependencies in clothing movement, combined with Dropout (0.2) to prevent overfitting. By capturing the temporal characteristics of clothing movement through LSTM, entanglement risk can be proactively predicted.

[0101] Training strategy:

[0102] Input layer: processes multi-feature time series data (e.g. 30 dimensions × 100 time steps);

[0103] Hidden layer: LSTM units learn the temporal evolution of entanglement risk;

[0104] Output layer: dual output structure (entanglement probability + position heat map).

[0105] Optimizer: Adam optimizer (learning rate 0.001), loss function is binary cross entropy (probability prediction) + mean square error (position prediction).

[0106] Model validation and evaluation:

[0107] Cross-validation: 5-fold cross-validation is used to ensure the generalization ability of the model and avoid overfitting.

[0108] Evaluation Metrics:

[0109] Accuracy: the degree of match between the predicted entanglement probability and the actual entanglement event (e.g., greater than 90%);

[0110] Positioning error: the spatial deviation between the predicted winding position and the actual winding position (e.g. less than 5%);

[0111] Lead time: Accurately predict entanglement risks 30 seconds in advance on average.

[0112] Iterative optimization and deployment:

[0113] Parameter tuning: Automatically search for optimal hyperparameters (such as the number of LSTM layers, learning rate, and window size) through Bayesian optimization.

[0114] Real-time prediction: The trained model is deployed to an edge computing chip (such as NVIDIA Jetson Nano), and the prediction results are updated every 2 seconds, driving the multimodal control module to dynamically adjust the motion trajectory of the impeller and stirring rod.

[0115] In order to better implement the laundry equipment control method in the embodiment of the present application, in addition to the laundry equipment control method, the embodiment of the present application further provides a laundry equipment control device, such as Figure 3 As shown, the apparatus 300 includes:

[0116] An acquisition module 301 is configured to acquire first image information of target laundry during a washing process;

[0117] A determination module 302 is configured to determine first entanglement probability information of target laundry based on the first laundry image information;

[0118] The control module 303 is configured to control the target laundry device according to the first entanglement probability information.

[0119] The laundry appliance control device provided herein can first acquire first image information of a target laundry item during the washing process via acquisition module 301, allowing determination module 302 to determine first entanglement probability information of the target laundry item during the washing process through image recognition. Control module 303 can then control rotation-related parameters of the target laundry item based on the first entanglement probability information, thereby reducing the probability of entanglement.

[0120] In some embodiments of the present application, the determination module 302 is specifically configured to:

[0121] Performing optical flow feature extraction on the first clothing image information to determine motion direction information corresponding to each clothing item in the target laundry;

[0122] Determining the consistency of movement directions of target laundry items based on movement direction information corresponding to each item of laundry and rolling direction information of the target laundry device during the washing process;

[0123] First entanglement probability information of the target laundry is determined according to the motion direction consistency information.

[0124] In some embodiments of the present application, the control module 303 is specifically configured to:

[0125] If the first entanglement probability information is greater than a first target probability threshold, the stirring device is controlled to stir up the target laundry and the washing cavity of the target laundry device is controlled to roll in a manner to prevent entanglement.

[0126] In some embodiments of the present application, the control module 303 is further configured to:

[0127] determining entanglement position information of the target laundry according to the first laundry image information;

[0128] If the entanglement position information is target entanglement position information, the stirring device is controlled to stir up the target laundry and the washing cavity of the target laundry device is controlled to roll in a manner to prevent entanglement.

[0129] In some embodiments of the present application, the control module 303 is further configured to:

[0130] If the first entanglement probability information is less than or equal to the first target probability threshold, the target laundry appliance is controlled to operate in a non-entanglement state.

[0131] In some embodiments of the present application, before obtaining first image information of a target laundry item during a washing process, the determination module 302 is specifically configured to: determine target material information of the target laundry item; determine second entanglement probability information of the target laundry item based on the target material information;

[0132] The control module 303 is specifically configured to start the target laundry device to enter a washing process according to the second entanglement probability information.

[0133] In some embodiments of the present application, the determining module 302 is further configured to:

[0134] Acquire second laundry image information of target laundry;

[0135] Material recognition is performed on the second clothing image information to obtain target material information of the target laundry clothing.

[0136] In some embodiments of the present application, the control module 303 is further configured to:

[0137] If the first entanglement probability information and the second entanglement probability information are both less than or equal to the second target probability threshold, the target laundry appliance is controlled to enter the energy efficiency mode.

[0138] In some embodiments of the present application, the control module 303 is further configured to:

[0139] If the target laundry is completed, obtaining third laundry image information of the target laundry;

[0140] determining clothing distribution information of target laundry based on the third clothing image information;

[0141] Determining target dehydration parameters for target laundry based on the laundry distribution information;

[0142] According to the target dehydration parameters, the target laundry equipment is controlled to dehydrate the target laundry.

[0143] The present application also provides a washing machine, which includes a processor, a memory, and a computer program stored in the memory and executable on the processor. The processor executes the computer program to implement the steps of any one of the laundry device control methods provided in the embodiments of the present application. Figure 4 , which shows a schematic structural diagram of a washing machine involved in an embodiment of the present application, specifically:

[0144] The washing machine may include one or more processing core processors 401, one or more computer readable storage media memories 402, a power supply 403, an input unit 404 and other components. Those skilled in the art will understand that Figure 4 The structure of the washing machine shown in the figure does not constitute a limitation to the washing machine, and the washing machine may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0145] in:

[0146] Processor 401 is the control center of the washing machine. It connects all parts of the washing machine using various interfaces and circuits. By running or executing software programs and / or modules stored in memory 402 and accessing data stored in memory 402, it performs various functions of the washing machine and processes data, thereby providing overall monitoring of the washing machine. Optionally, processor 401 may include one or more processing cores. Processor 401 may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor. Preferably, processor 401 may integrate an application processor and a modem processor, wherein the application processor primarily processes the operating system, user interface, and application programs, while the modem processor primarily handles wireless communications. It is understood that the modem processor may not be integrated into processor 401.

[0147] The memory 402 can be used to store software programs and modules. The processor 401 executes various functional applications and data processing by running the software programs and modules stored in the memory 402. The memory 402 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.); the data storage area may store data created according to the use of the washing machine, etc. In addition, the memory 402 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage device. Accordingly, the memory 402 may also include a memory controller to provide the processor 401 with access to the memory 402.

[0148] The washing machine also includes a power supply 403 for supplying power to various components. Preferably, the power supply 403 can be logically connected to the processor 401 via a power management system, thereby enabling the power management system to manage charging, discharging, and power consumption. The power supply 403 can also include one or more DC or AC power supplies, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and other arbitrary components.

[0149] The washing machine may further include an input unit 404, which may be configured to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function controls.

[0150] Although not shown, the washing machine may further include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 401 in the washing machine will load the executable files corresponding to one or more application processes into the memory 402 according to the following instructions, and the processor 401 will run the application stored in the memory 402 to implement various functions, such as:

[0151] Acquire first clothing image information of a target laundry during a washing process;

[0152] determining first entanglement probability information of the target laundry according to the first laundry image information;

[0153] The target laundry appliance is controlled according to the first entanglement probability information.

[0154] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be accomplished by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0155] To this end, embodiments of the present application provide a computer-readable storage medium, which may include a read-only memory (ROM), a random access memory (RAM), a disk, or an optical disk. A computer program is stored on the computer-readable storage medium, and the computer program is loaded by a processor to execute the steps of any of the laundry device control methods provided in embodiments of the present application. For example, the computer program loaded by the processor may execute the following steps:

[0156] Acquire first clothing image information of a target laundry during a washing process;

[0157] determining first entanglement probability information of the target laundry according to the first laundry image information;

[0158] The target laundry appliance is controlled according to the first entanglement probability information.

[0159] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, please refer to the detailed description of other embodiments above and will not be repeated here.

[0160] In specific implementation, the above units or structures can be implemented as independent entities, or can be arbitrarily combined to be implemented as the same or several entities. The specific implementation of the above units or structures can be referred to the previous method embodiments and will not be repeated here.

[0161] The specific implementation of the above operations can be found in the previous embodiments and will not be repeated here.

[0162] The above is a detailed introduction to a laundry appliance control method and device provided in an embodiment of the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for those skilled in the art, according to the idea of ​​the present application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present application.

Claims

1. A laundry equipment control method, characterized in that: The method comprises: Acquire first clothing image information of a target laundry during a washing process; determining first entanglement probability information of the target laundry according to the first laundry image information; The target laundry appliance is controlled according to the first entanglement probability information.

2. The laundry equipment control method according to claim 1, wherein: The determining, based on the first clothing image information, first entanglement probability information of the target laundry includes: performing optical flow feature extraction on the first clothing image information to determine motion direction information corresponding to each clothing item in the target laundry; Determining movement direction consistency information of the target laundry items based on movement direction information corresponding to each item of laundry and rolling direction information of the target laundry device during the washing process; First entanglement probability information of the target laundry is determined according to the movement direction consistency information.

3. The laundry equipment control method according to claim 2, wherein: The target laundry device includes a stirring device, and controlling the target laundry device according to the first entanglement probability information includes: If the first entanglement probability information is greater than a first target probability threshold, the stirring device is controlled to stir the target laundry and the washing cavity of the target laundry device is controlled to roll in a manner to prevent entanglement.

4. The laundry equipment control method according to claim 3, wherein: The controlling the stirring device to disperse the target laundry includes: determining, based on the first clothing image information, entanglement position information of the target laundry; If the entanglement position information is target entanglement position information, the stirring device is controlled to disperse the target laundry and the washing cavity of the target laundry device is controlled to roll in a manner to prevent entanglement.

5. The laundry equipment control method according to claim 4, characterized in that: The method further comprises: If the first entanglement probability information is less than or equal to the first target probability threshold, the target laundry device is controlled to operate in a non-entanglement state.

6. The laundry equipment control method according to claim 1, wherein: Before obtaining the first image information of the target laundry during the washing process, the method further includes: Determining target material information of the target laundry; determining second entanglement probability information of the target laundry according to the target material information; The target laundry device is started to enter a washing process according to the second entanglement probability information.

7. The laundry equipment control method according to claim 6, characterized in that: The determining target material information of the target laundry includes: Acquire second laundry image information of the target laundry; Material recognition is performed on the second clothing image information to obtain target material information of the target laundry clothing.

8. The laundry equipment control method according to claim 6, wherein: The method further comprises: If the first entanglement probability information and the second entanglement probability information are both less than or equal to a second target probability threshold, the target laundry appliance is controlled to enter an energy efficiency mode.

9. The laundry equipment control method according to claim 1, wherein: After controlling the target laundry appliance according to the first entanglement probability information, the method further includes: If the washing of the target laundry is completed, obtaining third laundry image information of the target laundry; determining clothing distribution information of the target laundry according to the third clothing image information; determining target dehydration parameters for the target laundry according to the laundry distribution information; According to the target dehydration parameter, the target laundry device is controlled to dehydrate the target laundry.

10. A laundry equipment control device, characterized in that: The device comprises: An acquisition module, configured to acquire first image information of target laundry during a washing process; a determination module, configured to determine first entanglement probability information of the target laundry according to the first laundry image information; A control module is configured to control a target laundry device according to the first entanglement probability information.

11. A washing machine, characterized in that: The washing machine includes a processor, a memory, and a computer program stored in the memory and executable on the processor. The processor executes the computer program to implement the steps of the laundry device control method according to any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the steps in the laundry device control method according to any one of claims 1 to 9.

Images