Control method and device of washing equipment, washing equipment and medium
By acquiring physical and water state information of the washing equipment, constructing feature vectors, and using a decision model to determine washing parameters, the problem of user experience dependence is solved, and a more reliable and efficient washing process is achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-23
- Publication Date
- 2026-03-20
AI Technical Summary
Existing washing equipment relies heavily on user experience, resulting in poor washing results or damage to clothes, which affects the user experience.
By acquiring the physical state information of the laundry and the water state information in the washing equipment, feature vectors are constructed, and washing parameters, including water temperature, soaking time, and washing speed, are determined using a preset washing parameter decision model, reducing reliance on user experience.
It improves the reliability of washing equipment operation and user experience, and ensures the accuracy and safety of clothing washing results.
Smart Images
Figure CN121700637A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of smart home device technology, and in particular to a control method, apparatus, washing device, and readable storage medium for a washing machine. Background Technology
[0002] Laundry equipment is automated electrical equipment that uses water, detergent, and mechanical action to clean clothes. It is widely used in homes, hotels, and other settings. Its core function is to remove stains and dust from clothes through processes such as soaking, agitation, and rinsing. With the rapid development of the times, people have increasingly higher demands for the intelligence and automation of laundry equipment.
[0003] In related technologies, washing equipment such as washing machines are mainly controlled by preset fixed programs. Users need to judge the condition of the clothes and select the appropriate program themselves. Then the washing machine performs the washing task according to preset fixed parameters such as time, water temperature, and spin speed.
[0004] The above methods rely heavily on user experience. If users make inappropriate choices, it can easily lead to poor washing results or unnecessary damage to clothing, affecting the user experience. Summary of the Invention
[0005] In view of the above problems, embodiments of the present invention are proposed to provide a control method, apparatus, washing equipment, and readable storage medium for a washing device that overcomes or at least partially solves the above problems.
[0006] In a first aspect, embodiments of the present invention provide a control method for a washing device, the method comprising: Obtain the physical state information of the laundry in the washing equipment; During the water intake stage, the water state information in the washing equipment is acquired, including turbidity information and water color information. Based on the physical state information and the water state information, the washing parameters are determined; The washing equipment is controlled to operate according to the washing parameters.
[0007] Optionally, determining the washing parameters based on the physical state information and the water state information includes: Based on the physical state information and the water state information, a feature vector is constructed to describe the washing status. The feature vector is input into a preset washing parameter decision model to obtain the washing parameters.
[0008] Optionally, the turbidity information includes multiple turbidity values collected at a preset frequency within a preset time period; The step of constructing a feature vector to describe the washing status based on the physical state information and the water state information includes: The multiple turbidity values collected within a preset time period are analyzed and processed to determine the characteristics of turbidity changes; The water color information is subjected to color conversion processing to determine color component characteristics; Based on the characteristics of turbidity changes and color components, the type and degree of staining are determined.
[0009] Optionally, the physical state information of the laundry includes the weight and material of the laundry; The step of constructing a feature vector to describe the washing status based on the physical state information and the water state information includes: The turbidity change characteristics, color component characteristics, stain type, degree of contamination, weight of the laundry, and material of the laundry are used to construct a feature vector to describe the washing condition.
[0010] Optionally, the washing parameters include: water temperature, soaking time, washing time, washing speed, and rinsing times.
[0011] Optionally, the method further includes: After the washing process is completed, obtain the user's rating for the washing process; The score and the washing parameters of this washing operation are used as training samples to train the washing parameter decision model.
[0012] Optionally, the method further includes: During the washing process, the operating status information of the washing equipment is continuously monitored, including power information and vibration information; If the running status information is abnormal, the operation will be interrupted.
[0013] Optionally, the method further includes: The operating status information is input into a preset health status prediction model to obtain the health score and remaining usage count output by the health status prediction model; When the health score is lower than a preset score threshold and / or the remaining usage count is lower than a preset usage count threshold, a warning message is output to the user.
[0014] Optionally, the warning information includes maintenance suggestion text; When the health score is lower than a preset score threshold and / or the remaining usage count is lower than a preset usage count threshold, a warning message is output to the user, including: Identify anomalous data features related to the health score and / or remaining usage count; The abnormal data features are matched with a preset fault knowledge base to determine the abnormal components and maintenance methods corresponding to the abnormal data features, and maintenance suggestion text is generated. Output the maintenance suggestion text to the user.
[0015] Secondly, embodiments of the present invention provide a control device for a washing machine, the device comprising: The physical state information acquisition module is used to acquire the physical state information of the laundry in the washing equipment; The water state information acquisition module is used to acquire water state information in the washing equipment during the water intake stage. The water state information includes turbidity information and water color information. The washing parameter determination module is used to determine the washing parameters based on the physical state information and the water state information; The washing equipment operation control module is used to control the washing equipment to operate according to the washing parameters.
[0016] Optionally, the washing parameter determination module includes the following sub-modules: The feature vector construction submodule is used to construct a feature vector describing the washing status based on the physical state information and the water state information. The washing parameter determination submodule is used to input the feature vector into a preset washing parameter decision model to obtain the washing parameters.
[0017] Optionally, the turbidity information includes multiple turbidity values collected at a preset frequency within a preset time period; The feature vector construction submodule includes the following units: The turbidity change characteristic determination unit is used to analyze and process multiple turbidity values collected within a preset time period to determine the turbidity change characteristics. The color component feature determination unit is used to perform color conversion processing on the water color information and determine the color component features; The stain type and degree of contamination determination unit is used to determine the stain type and degree of contamination based on turbidity change characteristics and color component characteristics.
[0018] Optionally, the physical state information of the laundry includes the weight and material of the laundry; The feature vector construction submodule includes the following units: The feature vector construction unit is used to construct a feature vector describing the washing condition from the turbidity change feature, the color component feature, the stain type, the degree of contamination, the weight of the laundry, and the material of the laundry.
[0019] Optionally, the device further includes the following modules: The rating acquisition module is used to obtain the user's rating for the washing process after it is completed. The training module is used to train the washing parameter decision model by using the score and the washing parameters of the current washing operation as training samples.
[0020] Optionally, the device further includes the following modules: The operating status information detection module is used to continuously detect the operating status information of the washing equipment during the washing process. The operating status information includes power information and vibration information. The operation interruption module is used to interrupt operation if the operation status information is abnormal.
[0021] Optionally, the device further includes the following modules: The health status prediction module is used to input the operating status information into a preset health status prediction model to obtain the health score and remaining usage times output by the health status prediction model. The warning information output module is used to output warning information to the user when the health score is lower than a preset score threshold and / or the remaining usage times are lower than a preset number of times threshold.
[0022] Optionally, the warning information includes maintenance suggestion text; The early warning information output module includes the following sub-modules: An abnormal data feature determination submodule is used to determine abnormal data features related to the health score and / or remaining usage count; The maintenance suggestion text generation submodule is used to match the abnormal data features with a preset fault knowledge base, determine the abnormal components and maintenance methods corresponding to the abnormal data features, and generate maintenance suggestion text. The maintenance suggestion text output submodule is used to output the maintenance suggestion text to the user.
[0023] Thirdly, embodiments of the present invention provide a washing device, which includes a processor, a memory, and a program or instructions stored in the memory and executable on the processor. When the program or instructions are executed by the processor, they implement the steps of the control method for the washing device as described in the first aspect.
[0024] Fourthly, embodiments of the present invention provide a readable storage medium storing a program or instructions that, when executed by a processor, implement the steps of the control method for the washing device as described in the first aspect.
[0025] The embodiments of the present invention have the following advantages: This invention acquires the physical state information of the laundry in the washing equipment and the water state information, including turbidity and color, during the water intake stage. The turbidity and color information can be used to predict the type and degree of soiling on the laundry. Then, combined with the physical state information of the laundry, washing parameters more suitable for the current laundry condition are determined, and the washing equipment is controlled to operate according to these parameters. Determining washing parameters using objective information from both physical and water state dimensions improves the reliability of the washing equipment operation, reduces reliance on user experience, and enhances the user experience. Attached Figure Description
[0026] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying 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 effort.
[0027] Figure 1 This is a flowchart of the steps of a control method for a washing device provided in an embodiment of the present invention; Figure 2 This is an application flowchart of a control method for a washing device provided in an embodiment of the present invention; Figure 3 This is a structural block diagram of a control device for a washing machine provided in an embodiment of the present invention. Detailed Implementation
[0028] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0029] The terms "first," "second," etc., used in the specification and claims of this invention are used to distinguish similar objects and are not used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention can be implemented in orders other than those illustrated or described herein. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.
[0030] Laundry equipment is automated electrical equipment that uses water, detergent, and mechanical action to clean clothes. It is widely used in homes, hotels, and other settings. Its core function is to remove stains and dust from clothes through processes such as soaking, agitation, and rinsing. With the rapid development of the times, people have increasingly higher demands for the intelligence and automation of laundry equipment.
[0031] In related technologies, washing equipment such as washing machines are mainly controlled through preset fixed programs. Users need to judge the condition of the clothes and select the appropriate program themselves. Then, the washing machine performs the washing task according to preset fixed parameters such as time, water temperature, and spin speed. This method relies heavily on user experience. If the user makes an inappropriate selection, it can easily lead to poor washing results or unnecessary damage to clothes, affecting the user experience.
[0032] One of the core concepts of this invention is to determine washing parameters by using objective information from two dimensions: physical state information and water state information. This improves the reliability of the washing equipment while reducing reliance on user experience and enhancing the user experience.
[0033] Figure 1 This is a flowchart of the steps of a control method for a washing device provided in an embodiment of the present invention.
[0034] like Figure 1 As shown, the method may specifically include the following steps: Step 101: Obtain the physical state information of the laundry in the washing equipment; In practical applications, the washing equipment can be a smart washing machine. As an example, this smart washing machine should use a main control board with edge computing capabilities as its core hardware, integrating multiple types of sensor interfaces and a large-capacity storage unit. The computing power of the main control board needs to support the local execution of lightweight machine learning models to determine subsequent washing parameters. In some embodiments, the physical state information of the laundry includes at least one of the following: laundry weight, laundry material, and laundry distribution state.
[0035] It is understandable that the weight of the laundry can serve as a valid basis for determining the amount of water and detergent needed for washing. As an example, the weight of the laundry can be directly measured using a weighing sensor located at the bottom of the washing machine.
[0036] Different fabric materials have varying tolerances to water temperature and mechanical force. Determining the most suitable washing parameters based on the fabric material can prevent unnecessary damage. In practical applications, directly identifying the specific material composition is difficult. In some embodiments, the user can input the types of clothing included in the wash to determine the fabric material. In other embodiments, the volume of the laundry can be estimated by pre-rotating the inner drum of the washing machine, and then the bulk density of the laundry can be determined by combining this with the weight of the laundry. The fabric material can then be determined based on the bulk density; for example, low density might indicate down, while high density might indicate cotton or linen. Furthermore, image information of the laundry can be acquired to further determine the fabric material.
[0037] Furthermore, the uniformity of the laundry distribution is crucial to the evenness of the washing process and the safety of the spin-drying stage. In some embodiments, a low-speed pre-rotation can be performed, followed by analysis of the amplitude, standard deviation, or energy percentage in a specific direction from the triaxial accelerometer signal to determine the uniformity of the laundry distribution. For example, if the laundry is heavily biased to one side, a periodic centrifugal force signal will be generated in that specific axis that is significantly stronger than in other directions. By determining the laundry distribution in advance, corrective measures can be taken, such as adjusting the distribution or notifying the user in case of severe abnormalities, and a more conservative upper limit for the spin-drying stage can be preset, thereby preventing safety hazards caused by severe vibrations.
[0038] Step 102: During the water intake stage, obtain the water state information in the washing equipment, including turbidity information and water color information; In practical applications, optical sensor modules can be used to acquire real-time information about the water state in the washing equipment. As an example, an optical sensor module may include a multispectral light source array, a photodiode detector, and a CMOS image sensor.
[0039] For turbidity information, a multispectral light source array emits incident light, such as infrared LEDs of a specific wavelength. A photodiode is positioned at a fixed angle to the incident light, and a detector measures the intensity of the scattered light from the water. Combined with a standard calibration curve, the current NTU (turbidity unit) value of the water is calculated. NTU values are collected multiple times at a preset frequency within a preset time period after water inflow, forming a sequence of turbidity values changing over time, i.e., turbidity information.
[0040] To obtain water color information, white LED illumination is used, and a CMOS image sensor captures images of the water after the clothes release pollutants during the initial soaking process, i.e., the water color information.
[0041] Step 103: Determine the washing parameters based on the physical state information and the water state information; In some embodiments, step 103 specifically includes the following sub-steps: Sub-step S11: Based on the physical state information and the water state information, construct a feature vector to describe the washing status; It is understandable that sub-step S11 is a core preliminary step in determining the washing parameters. Its purpose is to transform the raw data collected by the sensors, including physical state information and water state information, into a set of digital features, i.e., feature vectors, that can represent the washing status. These feature vectors serve as a unified input for subsequent machine learning models, helping them to understand, judge, and make decisions regarding the washing status.
[0042] In some embodiments, the turbidity information includes multiple turbidity values collected at a preset frequency over a preset time period.
[0043] In some embodiments, sub-step S11 specifically includes the following detailed steps: The multiple turbidity values collected within a preset time period are analyzed and processed to determine the characteristics of turbidity changes; The water color information is subjected to color conversion processing to determine color component characteristics; Based on the characteristics of turbidity changes and color components, the type and degree of staining are determined.
[0044] As an example, time-series analysis was performed on NTU data collected during the first 60 seconds of the influent phase to determine turbidity variation characteristics, including: the linear slope of the NTU values within the first 30 seconds as the rate of rise k. turb The time it takes for the NTU to reach a stable value is taken as the peak time t. peak .
[0045] According to k turb By analyzing the numerical range of k and the curve shape, we can make a preliminary judgment on the physical properties of pollutants. For example, k turb A rapid ascent mode of >5 NTU / s often corresponds to easily soluble stains such as dirt and bloodstains; while k turb A slow increase of <2 NTU / s may correspond to contaminants that emulsify slowly, such as oil stains.
[0046] Image processing and color space conversion are performed on the water color information captured by the CMOS image sensor, i.e., the original water image, to extract accurate color component features.
[0047] As an example, the original water image is first white-balanced to eliminate light source color cast, and then denoised using methods such as Gaussian filtering. Subsequently, a region of interest (ROI) extraction algorithm is used to focus on the effective area of the flowing water, eliminating interference from foam, clothing, and other obstructions.
[0048] The RGB pixel data of the processed image is converted to the CIE-Lab color space to obtain the lightness (L), which reflects the clarity or turbidity of the water; the red-green component (a), which represents the color shift along the red-green axis; a value greater than zero indicates a reddish tint, while a value less than zero indicates a greenish tint; and the yellow-blue component (b), which represents the color change along the yellow-blue axis; positive values represent a yellowish or brownish-yellow tint, while negative values represent a bluish tint. Then, the weighted average of the a and b components over the entire water area is used to obtain the overall color characteristic value of the water in this washing process, thus determining its comprehensive performance in both the red-green and yellow-blue dimensions.
[0049] To further improve the accuracy of stain identification, RGB data can be converted to the HSV color space, and the hue (H) component can be extracted after conversion. Hue (H) represents color type using angle values (0°, 360°), which can more intuitively distinguish different types of staining contaminants. When water exhibits a distinct red hue, its H value set is near 0°, and combined with a positive a component, it can be preliminarily identified as blood stains, red wine, or organic stains containing hemoglobin. If the H value is between 30° and 60°, corresponding to orange-yellow to yellowish-brown, and the b value is high, it usually indicates the presence of oily contaminants or food residues, such as cooking oil or sauces.
[0050] By jointly analyzing the a and b components of the CIE-Lab space with the hue H of the HSV space, it is possible not only to identify the color tendency of water bodies, but also to determine the intensity of pollution by combining the lightness L*, thereby achieving a preliminary classification of more diverse stains.
[0051] After independently analyzing turbidity change characteristics and color component characteristics, multi-dimensional feature fusion inference can be further performed to achieve more accurate identification of stain type and degree of contamination. In some embodiments, this can be determined using a preset lightweight stain recognition model. This module is integrated into the edge computing system of the washing machine's main control unit, eliminating the need for cloud computing and thus ensuring response speed and protecting user privacy.
[0052] Specifically, the rising slope k of the NTU value within the first 30 seconds can be considered. turb The time t for turbidity to reach a stable state peak The average a and b values in the CIE-Lab color space, and the dominant hue H in the HSV color space, are used as a joint input feature vector and input into a pre-built stain recognition model. This model has been trained and validated with a large number of standard stain samples, such as simulated bloodstains, vegetable oil, mud, and juice, before leaving the factory, forming a set of classification criteria with physical interpretability.
[0053] For example, when the turbidity increases at a rate k turbWhen the concentration of chromatic dyes is >5 NTU / s, a>10, and the hue H is concentrated in the range of 300° to 330°, and a is greater than 10, the model determines that there is a high concentration of purple-red soluble dye pollutants in the water. Typical scenarios are the discoloration of dyed fabrics or the dissolution of fruit juice stains during the washing of clothes. Based on this, the stain type is marked as: dye, and the pollution level is: high pollution.
[0054] When k turb If the turbidity is >6 NTU / s, a>10 and b>15, it indicates that the water body has high turbidity and a mixed red and yellow color in a short period of time, which is consistent with the characteristics of mixed pollution of silt and organic matter. This is commonly seen in the washing of outdoor clothing or children's clothing. Based on this, the stain type is marked as: silt, and the pollution level is: high pollution.
[0055] The stain type and degree of contamination determined by the above combined analysis will also serve as input for the machine learning model, providing a comprehensive and accurate digital description for the washing parameter decisions in subsequent steps.
[0056] In some embodiments, the physical state information of the laundry includes the weight and material of the laundry.
[0057] In some embodiments, sub-step S11 specifically includes the following detailed steps: The turbidity change characteristics, color component characteristics, stain type, degree of contamination, weight of the laundry, and material of the laundry are used to construct a feature vector to describe the washing condition.
[0058] By constructing feature vectors, data such as turbidity change features, color component features, stain type, degree of contamination, weight of laundry, and material of laundry—which have completely different physical meanings and reflect the washing status from various dimensions—are normalized into a form that the washing parameter decision model can understand and calculate.
[0059] In addition, using all the above data as input features provides high-fidelity and high-completeness data support for the washing parameter decision model, avoiding the impact of missing information in a certain dimension on the accuracy and reliability of washing parameters.
[0060] Sub-step S12: Input the feature vector into a preset washing parameter decision model to obtain washing parameters.
[0061] In some embodiments, the washing parameters include: water temperature, soaking time, washing time, washing speed, and number of rinses.
[0062] As an example, the washing parameter decision model can adopt the Deep Deterministic Policy Gradient (DDPG) framework, deployed locally on the washing machine, supporting real-time inference and online incremental learning in an edge computing environment. It has been pre-trained using a simulated dataset before leaving the factory, and users can continue to learn incrementally during subsequent use.
[0063] The washing parameter decision model contains two deep neural networks working together: an actor network and a critic network.
[0064] The actor network, acting as a policy network, directly determines and outputs a continuous action vector *at*, representing the specific combination of washing parameters, based on the input state vector *St*. This network typically consists of an input layer, several hidden layers, and an output layer. The output layer uses a sigmoid activation function to normalize the final output to the [0,1] interval, and then linearly maps these values to the actual physical range of each washing parameter. For example, the output vector *at* can be mapped to: water temperature, main wash spin speed, soaking time, washing time, and number of rinses.
[0065] The critic network, acting as a value network, evaluates the long-term expected reward of taking action at in a specific state St. It takes the concatenated state St and action at as input, processes them through the network, and finally outputs a scalar Q(St,at), which is the value score of the state-action pair. This score guides the parameter updates of the critic network, causing it to tend to select actions that yield higher cumulative rewards; this is the "washing parameter" in this method.
[0066] Step 104: Control the washing equipment to operate according to the washing parameters.
[0067] In practical applications, the system receives washing parameters from step 103, including: water temperature, main wash speed, soaking time, washing time, and washing speed. The control unit parses and verifies these parameters to ensure they are all within the safe operating range of the equipment before operation.
[0068] In some embodiments, the method further includes: After the washing process is completed, obtain the user's rating for the washing process; The score and the washing parameters of this washing operation are used as training samples to train the washing parameter decision model.
[0069] In practical applications, after each complete washing cycle, the system proactively sends an evaluation request to the user regarding the washing effect through the local user interface of the washing device or its associated mobile terminal application, in order to obtain the user's rating for the washing cycle.
[0070] The user ratings are used as reward signals for reinforcement learning, and together with the current washing data, they form a training sample used to incrementally update the policy network of the local washing parameter decision model. Through multiple iterations, the model gradually learns the unique preferences of specific user households, forming personalized washing parameter decisions.
[0071] In some embodiments, the method further includes: During the washing process, the operating status information of the washing equipment is continuously monitored, including power information and vibration information; If the running status information is abnormal, the operation will be interrupted.
[0072] In practical applications, during the entire operation of the washing equipment, key operating status information, including power information and vibration information, is continuously collected through the built-in sensor array.
[0073] For power information, the system uses a current sensor and voltage sampling circuit to calculate and monitor the instantaneous power and operating current waveforms of the main motor in real time. A normal power curve should match the load and current speed; abnormal power spikes, continuous overload, or excessively low power may indicate abnormalities such as motor stall or electrical faults. For vibration information, a triaxial accelerometer collects acceleration data of the equipment in the X, Y, and Z directions in real time. This data can be used to determine the overall vibration intensity of the machine.
[0074] The real-time collected power and vibration information is compared with safety thresholds to determine whether any abnormalities have occurred or whether operation has been interrupted, thus ensuring the safety of the washing equipment.
[0075] In some embodiments, the method further includes: The operating status information is input into a preset health status prediction model to obtain the health score and remaining usage count output by the health status prediction model; When the health score is lower than a preset score threshold and / or the remaining usage count is lower than a preset usage count threshold, a warning message is output to the user.
[0076] In practical applications, dedicated machine learning models can be trained in the cloud or locally. For example, isolated forests can be used for anomaly detection, and time-series regression models can be combined for lifespan prediction, serving as a preset health status prediction model.
[0077] Throughout all operating phases of the washing equipment, real-time sensor data is continuously input into the health status prediction model. For example, this could include operating status information such as power and vibration data. The model outputs a health score and remaining usage count. When the health score falls below a preset threshold and / or the remaining usage count falls below a preset threshold, a warning message is sent to the user. For example, the system immediately pushes a warning message through the user interface, such as: "Slight wear detected in the inner drum bearing; maintenance recommended. Expected remaining usage: 100 more uses." By setting up a health status prediction model, the maintenance mode of the equipment is transformed into anomaly prevention. By continuously analyzing the condition of the washing equipment, early warnings are provided before a failure occurs, thereby avoiding downtime caused by sudden failures, improving the reliability of the washing equipment, and reducing the cost of the washing equipment: preventive maintenance is usually less expensive than repair after a failure, and timely maintenance can prevent damage to the lifespan of core components.
[0078] In some embodiments, the warning information includes maintenance suggestion text; When the health score is lower than a preset score threshold and / or the remaining usage count is lower than a preset usage count threshold, a warning message is output to the user, including: Identify anomalous data features related to the health score and / or remaining usage count; The abnormal data features are matched with a preset fault knowledge base to determine the abnormal components and maintenance methods corresponding to the abnormal data features, and maintenance suggestion text is generated. Output the maintenance suggestion text to the user.
[0079] When the health score output by the health status prediction model is lower than a preset score threshold and / or the remaining usage count is lower than a preset number of times threshold, a diagnostic analysis process is initiated. This process traces back and analyzes the original sensor data that triggered the warning to determine abnormal data features directly related to it. For example, abnormal data features such as "the drain pump motor current is consistently 20% higher than the normal baseline during the working cycle" may be extracted.
[0080] The system has a pre-built structured fault knowledge base. This knowledge base can be a rule base storing multi-dimensional correspondences between abnormal data features, potential faulty components, fault mechanisms, and standardized maintenance measures. The abnormal data features are matched against the pre-built fault knowledge base to determine the corresponding abnormal components and maintenance methods. Then, using a natural language template, the determined abnormal components and maintenance methods are filled into the corresponding positions in the template to obtain maintenance suggestion text, which is then output to the user. Finally, the generated maintenance suggestion text is pushed to the user through the washing machine's user interface or its associated mobile application.
[0081] This maintenance suggestion text mechanism provides users with specific maintenance recommendations and estimated remaining lifespan, helping them clearly assess the urgency of problems and take appropriate action. This avoids delays in repairs due to unclear information and improves the user experience.
[0082] This invention acquires the physical state information of the laundry in the washing equipment and the water state information, including turbidity and color, during the water intake stage. The turbidity and color information can be used to predict the type and degree of soiling on the laundry. Then, combined with the physical state information of the laundry, washing parameters more suitable for the current laundry condition are determined, and the washing equipment is controlled to operate according to these parameters. Determining washing parameters using objective information from both physical and water state dimensions improves the reliability of the washing equipment operation, reduces reliance on user experience, and enhances the user experience.
[0083] It should be noted that, for the sake of simplicity, the method embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.
[0084] Figure 2 This is an application flowchart of a control method for a washing device provided in an embodiment of the present invention.
[0085] To enable those skilled in the art to better understand the embodiments of the present invention, see below. Figure 2 An example will be used to illustrate an embodiment of the present invention: 1) Acquire multimodal data Collect physical state information of the laundry, including weight, material, and distribution. Collect water state information from the washing equipment, including turbidity and color.
[0086] The physical state information and water state information are used to construct a feature vector describing the washing status. This feature vector serves as a unified input for subsequent machine learning models, helping the washing parameter decision model to understand and judge the washing status, thereby deciding on appropriate washing parameters.
[0087] The system collects operational status information from the washing equipment, including power and vibration data. This operational status information is used for subsequent anomaly detection and health prediction.
[0088] 2) Washing program self-optimization The turbidity information, namely multiple turbidity values collected within a preset time period, is analyzed and processed to determine the turbidity change characteristics; the water color information is processed by color conversion to determine the color component characteristics; and based on the turbidity change characteristics and color component characteristics, the type of stain and the degree of pollution are determined.
[0089] The turbidity change features, color component features, stain type, degree of contamination, weight of the laundry, and material of the laundry are fused together to construct a feature vector for describing the washing condition.
[0090] The fused feature vectors are input into the local washing parameter decision model. This model combines historical washing data with the current objective to output a set of optimized washing parameter decisions, including but not limited to: water temperature setting, main wash speed, soaking time, and washing time. After each wash cycle, the system proactively sends a simple rating request (1-5 stars) to the user via the washing machine control panel or a linked mobile app. The user's rating serves as a reward signal for reinforcement learning, and together with the sensor data from that wash cycle, forms a training sample used to incrementally update the policy network of the local reinforcement learning model. Through multiple iterations, the model gradually learns the unique preferences of a specific user's household, forming personalized washing parameter decisions. 3) Washing equipment health prediction Dedicated machine learning models, such as isolated forests for anomaly detection and time-series regression models for lifespan prediction, are trained in the cloud or locally to predict the health status of critical components like motor bearings and drainage pumps. These models use vibration spectrum characteristics and current harmonic components as health indicators as input. Throughout all stages of the washing machine's operation, real-time sensor data is continuously input into the health status prediction model. The model outputs a health score and remaining usage count. When the health score falls below a preset score threshold and / or the remaining usage count falls below a preset usage count threshold, an early warning message is immediately pushed through the user interface, such as: "Slight wear detected in the inner drum bearing; maintenance is recommended; estimated remaining usage count is 200 times." When the health score output by the health status prediction model is lower than a preset score threshold and / or the remaining usage count is lower than a preset number of times threshold, a diagnostic analysis process is initiated. This process traces back and analyzes the original sensor data that triggered the warning to determine abnormal data features directly related to it. For example, abnormal data features such as "the drain pump motor current is consistently 20% higher than the normal baseline during the working cycle" may be extracted.
[0091] The system has a pre-built structured fault knowledge base, which can be a rule base storing multi-dimensional correspondences between abnormal data features, potential faulty components, fault mechanisms, and standardized maintenance measures. The abnormal data features are matched against the pre-built fault knowledge base to determine the corresponding abnormal components and maintenance methods. Then, using a natural language generation template, the determined abnormal components and maintenance methods are filled into the corresponding positions in the template to obtain maintenance suggestion text, which is then output to the user. Finally, the generated maintenance suggestion text is pushed to the user through the washing machine's user interface or its associated mobile application.
[0092] This invention acquires the physical state information of the laundry in the washing equipment and the water state information, including turbidity and color, during the water intake stage. The turbidity and color information can be used to predict the type and degree of soiling on the laundry. Then, combined with the physical state information of the laundry, washing parameters more suitable for the current laundry condition are determined, and the washing equipment is controlled to operate according to these parameters. Determining washing parameters using objective information from both physical and water state dimensions improves the reliability of the washing equipment operation, reduces reliance on user experience, and enhances the user experience.
[0093] It should be noted that the control method for the washing equipment provided in this embodiment of the invention can be executed by a control device of the washing equipment, or a control module within the control device of the washing equipment for executing the control method for loading the washing equipment. This embodiment of the invention uses the execution of the control method for loading the washing equipment by the control device of the washing equipment as an example to illustrate the control method for the washing equipment provided in this embodiment of the invention.
[0094] Figure 3 This is a structural block diagram of a control device for a washing machine provided in an embodiment of the present invention.
[0095] like Figure 3 As shown in the figure, the control device for a washing equipment provided in this embodiment of the invention may specifically include the following modules: The physical state information acquisition module 301 is used to acquire the physical state information of the laundry in the washing equipment; The water state information acquisition module 302 is used to acquire water state information in the washing equipment during the water intake stage. The water state information includes turbidity information and water color information. The washing parameter determination module 303 is used to determine washing parameters based on the physical state information and the water state information; The washing equipment operation control module 304 is used to control the washing equipment to operate according to the washing parameters.
[0096] In some embodiments, the washing parameter determination module includes the following sub-modules: The feature vector construction submodule is used to construct a feature vector describing the washing status based on the physical state information and the water state information. The washing parameter determination submodule is used to input the feature vector into a preset washing parameter decision model to obtain the washing parameters.
[0097] In some embodiments, the turbidity information includes multiple turbidity values collected at a preset frequency over a preset time period; The feature vector construction submodule includes the following units: The turbidity change characteristic determination unit is used to analyze and process multiple turbidity values collected within a preset time period to determine the turbidity change characteristics. The color component feature determination unit is used to perform color conversion processing on the water color information and determine the color component features; The stain type and degree of contamination determination unit is used to determine the stain type and degree of contamination based on turbidity change characteristics and color component characteristics.
[0098] In some embodiments, the physical state information of the laundry includes the weight and material of the laundry; The feature vector construction submodule includes the following units: The feature vector construction unit is used to construct a feature vector describing the washing condition from the turbidity change feature, the color component feature, the stain type, the degree of contamination, the weight of the laundry, and the material of the laundry.
[0099] In some embodiments, the device further includes the following modules: The rating acquisition module is used to obtain the user's rating for the washing process after it is completed. The training module is used to train the washing parameter decision model by using the score and the washing parameters of the current washing operation as training samples.
[0100] In some embodiments, the device further includes the following modules: The operating status information detection module is used to continuously detect the operating status information of the washing equipment during the washing process. The operating status information includes power information and vibration information. The operation interruption module is used to interrupt operation if the operation status information is abnormal.
[0101] In some embodiments, the device further includes the following modules: The health status prediction module is used to input the operating status information into a preset health status prediction model to obtain the health score and remaining usage times output by the health status prediction model. The warning information output module is used to output warning information to the user when the health score is lower than a preset score threshold and / or the remaining usage times are lower than a preset number of times threshold.
[0102] In some embodiments, the warning information includes maintenance suggestion text; The early warning information output module includes the following sub-modules: An abnormal data feature determination submodule is used to determine abnormal data features related to the health score and / or remaining usage count; The maintenance suggestion text generation submodule is used to match the abnormal data features with a preset fault knowledge base, determine the abnormal components and maintenance methods corresponding to the abnormal data features, and generate maintenance suggestion text. The maintenance suggestion text output submodule is used to output the maintenance suggestion text to the user.
[0103] This invention acquires the physical state information of the laundry in the washing equipment and the water state information, including turbidity and color, during the water intake stage. The turbidity and color information can be used to predict the type and degree of soiling on the laundry. Then, combined with the physical state information of the laundry, washing parameters more suitable for the current laundry condition are determined, and the washing equipment is controlled to operate according to these parameters. Determining washing parameters using objective information from both physical and water state dimensions improves the reliability of the washing equipment operation, reduces reliance on user experience, and enhances the user experience.
[0104] As the apparatus embodiment is basically similar to the method embodiment, it is described in a relatively simple manner. For relevant details, please refer to the description of the method embodiment.
[0105] This invention also provides a washing device, including a processor, a memory, and a program or instructions stored in the memory and executable on the processor. When the program or instructions are executed by the processor, they implement the various processes of the control method embodiment of the washing device described above and achieve the same technical effect. To avoid repetition, they will not be described again here.
[0106] It should be noted that the washing equipment in the embodiments of the present invention includes the mobile washing equipment and non-mobile washing equipment described above.
[0107] This invention also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the control method embodiment of the washing device described above and achieve the same technical effect. To avoid repetition, they will not be described again here.
[0108] The processor mentioned above is the processor in the washing device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.
[0109] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.
[0110] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, embodiments of the present invention can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of the present invention can take the form of computer program products implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0111] Embodiments of the present invention are described with reference to flowchart illustrations and / or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, as well as combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0112] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0113] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal equipment, causing a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0114] Although preferred embodiments of the present invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present invention.
[0115] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.
[0116] The control method, apparatus, washing equipment, and readable storage medium of a washing device provided by the present invention have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.
Claims
1. A control method for a washing machine, characterized in that, The method includes: Obtain the physical state information of the laundry in the washing equipment; During the water intake stage, the water state information in the washing equipment is acquired, including turbidity information and water color information. Based on the physical state information and the water state information, the washing parameters are determined; The washing equipment is controlled to operate according to the washing parameters.
2. The control method for the washing equipment according to claim 1, characterized in that, The step of determining the washing parameters based on the physical state information and the water state information includes: Based on the physical state information and the water state information, a feature vector is constructed to describe the washing status. The feature vector is input into a preset washing parameter decision model to obtain the washing parameters.
3. The control method for the washing equipment according to claim 2, characterized in that, The turbidity information includes multiple turbidity values collected at a preset frequency within a preset time period; The step of constructing a feature vector to describe the washing status based on the physical state information and the water state information includes: The multiple turbidity values collected within a preset time period are analyzed and processed to determine the characteristics of turbidity changes; The water color information is subjected to color conversion processing to determine color component characteristics; Based on the characteristics of turbidity changes and color components, the type and degree of staining are determined.
4. The control method for the washing equipment according to claim 3, characterized in that, The physical state information of the laundry includes the weight and material of the laundry; The step of constructing a feature vector to describe the washing status based on the physical state information and the water state information includes: The turbidity change characteristics, color component characteristics, stain type, degree of contamination, weight of the laundry, and material of the laundry are used to construct a feature vector to describe the washing condition.
5. The control method for the washing equipment according to claim 1, characterized in that, The washing parameters include: water temperature, soaking time, washing time, washing speed, and number of rinses.
6. The control method for the washing equipment according to claim 1, characterized in that, The method further includes: After the washing process is completed, obtain the user's rating for the washing process; The score and the washing parameters of this washing operation are used as training samples to train the washing parameter decision model.
7. The control method for the washing equipment according to claim 1, characterized in that, The method further includes: During the washing process, the operating status information of the washing equipment is continuously monitored, including power information and vibration information; If the running status information is abnormal, the operation will be interrupted.
8. The control method for the washing equipment according to claim 7, characterized in that, The method further includes: The operating status information is input into a preset health status prediction model to obtain the health score and remaining usage count output by the health status prediction model; When the health score is lower than a preset score threshold and / or the remaining usage count is lower than a preset usage count threshold, a warning message is output to the user.
9. The control method for the washing equipment according to claim 8, characterized in that, The warning information includes maintenance suggestion text; When the health score is lower than a preset score threshold and / or the remaining usage count is lower than a preset usage count threshold, a warning message is output to the user, including: Identify anomalous data features related to the health score and / or remaining usage count; The abnormal data features are matched with a preset fault knowledge base to determine the abnormal components and maintenance methods corresponding to the abnormal data features, and maintenance suggestion text is generated. Output the maintenance suggestion text to the user.
10. A control device for a washing machine, characterized in that, The device includes: The physical state information acquisition module is used to acquire the physical state information of the laundry in the washing equipment; The water state information acquisition module is used to acquire water state information in the washing equipment during the water intake stage. The water state information includes turbidity information and water color information. The washing parameter determination module is used to determine the washing parameters based on the physical state information and the water state information; The washing equipment operation control module is used to control the washing equipment to operate according to the washing parameters.
11. A washing device, characterized in that, It includes a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the control method for the washing apparatus as described in claims 1-9.
12. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement the steps of the control method for the washing apparatus as described in claims 1-9.