Clothes processing device, control method and equipment thereof and storage medium

Abstract

The invention provides a clothes treatment device and a control method and equipment thereof and a storage medium, a detection module is assembled on a drainage pipeline of the clothes treatment device, the detection module is used for collecting a water excitation image in the drainage pipeline, and the method comprises the following steps: obtaining the water excitation image collected by the detection module after rinsing is completed; calculating the residual index of the fluorescent agent in the water body according to the water body excitation image; according to a comparison result of the residual index and a preset threshold value, the rinsing action of the clothes processing device is controlled. According to the method, the health hidden dangers such as skin irritation and allergy caused by fluorescent agent residues due to insufficient rinsing are solved, accurate resource utilization is achieved, the intellectualization and credibility of user experience are improved, the operation is simpler, the result is more secure, a non-contact optical image analysis technology is adopted, and the method has the advantages of high reliability, low cost and strong anti-interference capability.

Description

Technical Field

[0001] This invention relates to the field of clothing processing technology, and in particular to a clothing processing device, its control method, equipment, and storage medium. Background Technology

[0002] Washing machines have become an indispensable household appliance in modern families. Their basic function is to remove stains and detergent from clothes through washing and rinsing processes. The core purpose of the rinsing process is to remove residual detergent, dirt particles, and chemical additives such as optical brighteners from the clothing fibers. Residual optical brighteners may cause health problems such as skin sensitivity and allergies, especially affecting infants and people with sensitive skin.

[0003] Currently, the rinsing control logic of mainstream washing machines is mainly based on preset programs and times. Common methods include: Fixed number of rinses / time: The user or a preset program selects the number of rinses (e.g., 1, 2, or 3). The washing machine finishes its fixed inlet and outlet cycles. This method relies entirely on experience and makes it impossible to perceive the actual rinsing effect. If the clothes are lightly soiled or the detergent dosage is low, it may lead to over-rinsing, wasting water, electricity, and time; conversely, it may lead to under-rinsing, resulting in excessive chemical residue.

[0004] Foam sensing technology: Some mid-to-high-end washing machines use photoelectric or electrode sensors to detect the foam concentration in the rinsing water. When the detected foam concentration is below a certain threshold, the rinsing is considered complete. This method is an improvement over a fixed number of rinses, but it has significant limitations: First, it detects foam, and the widespread use of modern high-efficiency low-foaming detergents makes the foam signal weak, leading to detection failure or delay; second, substances such as optical brighteners that dissolve in water but do not foam cannot be effectively detected, and even after the foam disappears, these substances may still remain in large quantities.

[0005] Water turbidity sensing: This method indirectly determines the degree of cleanliness by measuring the transmittance or scattering rate of water using optical sensors. However, turbidity mainly reflects the residue of insoluble particulate stains. For completely dissolved fluorescent whitening agents, its detection sensitivity is very low, and it cannot meet the requirements for precise control of chemical residues.

[0006] In recent years, with increasing health awareness, the market has placed higher demands on a truly clean and residue-free laundry experience. As a common detergent additive, optical brighteners have raised concerns about residue issues. Although some laboratory technologies (such as fluorescence spectrophotometry) can accurately quantify fluorescent substances in water, these technologies are expensive and complex to operate, making them unsuitable for integration into household washing machines for real-time, online detection and control.

[0007] Therefore, there is an urgent need for a low-cost, high-reliability solution that can detect fluorescent whitening agents in rinsing water in real time, directly and quantitatively, and dynamically and accurately control the rinsing process accordingly. Summary of the Invention

[0008] To achieve the above-mentioned objectives and other advantages of the present invention, a first objective of the present invention is to provide a control method for a garment processing device, wherein a detection module is installed on the drain pipe of the garment processing device, the detection module being used to acquire excitation images of water in the drain pipe, comprising the following steps: Acquire the water excitation image collected by the detection module after rinsing; The residual index of fluorescent agent in the water body is calculated based on the water body excitation image; The rinsing action of the garment processing device is controlled based on the comparison result between the residual index and the preset threshold.

[0009] Furthermore, the detection module includes an excitation light source and a camera, and before the step of acquiring the water excitation image collected by the detection module after rinsing, it further includes: Before starting the washing process, water is introduced through the inlet pipe to flush the water circuit, and the detection module is calibrated to zero. The excitation light source is activated to irradiate the water in the drainage pipe; The camera is activated to capture images of the water body.

[0010] Furthermore, the step of calculating the residual index of fluorescent agent in the water body based on the water body excitation image includes: Image features are extracted from the excitation image, the image features including at least one of intensity domain features, spatial domain features and frequency domain features; Based on the extracted image features, the residual index is determined through a predetermined calculation model.

[0011] Further, the step of extracting image features from the excited image includes: The excitation image is preprocessed, including denoising and background subtraction. In the preprocessed image, the region of interest is delineated; Extract the intensity domain features of the region of interest, wherein the intensity domain features include at least one of the region's average gray value, the region's maximum gray value, and the region's gray standard deviation.

[0012] Furthermore, the background subtraction processing step includes: Acquire a reference background image under conditions free from fluorescent interference; The excitation image is registered and aligned with the reference background image; The corresponding pixel values ​​of the registered reference background image are subtracted from the pixel values ​​of the excitation image to obtain the background-subtracted image.

[0013] Furthermore, the step of extracting image features from the excited image further includes: Spatial domain features are calculated based on the gray-level co-occurrence matrix of the excitation image, including at least one of contrast, uniformity, energy, and correlation. Frequency domain features are obtained by calculating the two-dimensional power spectrum of the excitation image, which are used to quantify the intensity of frequency components caused by periodic interference in the image.

[0014] Furthermore, the step of determining the residual index based on the extracted image features using a predetermined calculation model includes: The extracted image features are normalized. The normalized image features are input into a preset weighted coefficient model, and the residual index is obtained by weighted summation; or, The normalized image features are input into a pre-trained machine learning regression model, which then outputs the residual index.

[0015] Furthermore, the step of controlling the rinsing action of the garment treatment device based on the comparison result of the residual index and the preset threshold includes: If the residual index is greater than the preset threshold, it is determined that the fluorescent agent has not been cleaned properly, and a control command to increase rinsing is generated. The control commands are executed to dynamically adjust the parameters of the subsequent rinsing process.

[0016] Furthermore, the parameters for dynamically adjusting the subsequent rinsing process include at least one of the following: Increase the number of rinses; Switch rinsing modes, including pulse oscillation rinsing mode and continuous replacement rinsing mode; Adjust at least one of the following: water volume, water inlet rate, drainage timing, washing drum movement mode of the garment processing device, or water temperature for a single rinse.

[0017] Furthermore, the basis for switching rinsing modes includes the rate of decrease of the residual index: If the descent rate is lower than the preset value, the pulse oscillation rinsing mode is switched to. The pulse oscillation rinsing mode includes controlling the water inlet valve of the clothing treatment device to introduce water in a pulse manner and controlling the washing drum to rotate at high and low speeds in both directions. If the descent rate is not lower than the preset value, the system switches to the continuous replacement rinsing mode. The continuous replacement rinsing mode includes controlling the water inlet valve to continuously introduce water at a low speed and simultaneously controlling the drain pump of the clothing processing device to continuously drain water.

[0018] Furthermore, the method also includes a program recommendation step: After the washing cycle is completed and before the first rinse, an excitation image of the initial water body is acquired; Based on the excitation image of the initial water body, determine the initial degree of soiling of the clothing; Based on the initial level of contamination, the system recommends or automatically switches to the corresponding preset rinsing program, which includes an energy-saving rinsing program, a standard rinsing program, and a powerful rinsing program.

[0019] A second objective of the present invention is to provide a garment processing apparatus, comprising: Drainage pipes; The detection module is used to acquire images of the water body inside the drainage pipe. The main control unit is configured to execute the above method.

[0020] Furthermore, the detection module includes: Camera; The excitation light source emits ultraviolet light with a wavelength range of 355nm to 375nm, or blue light with a wavelength range of 440nm to 460nm. The camera and the excitation light source are integrated and encapsulated in a waterproof housing, and are provided with an installation structure for fixing them to the drainage pipe.

[0021] A third objective of the present invention is to provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described method.

[0022] A fourth objective of the present invention is to provide a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the above-described method.

[0023] Compared with the prior art, the beneficial effects of the present invention are: This invention provides a garment treatment device, its control method, equipment, and storage medium. By directly analyzing the residual index of fluorescent whitening agents in the rinsing water, the control logic is established based on objective and quantifiable cleanliness data. In consumer-grade products, it achieves online monitoring and closed-loop control of specific harmful chemical residues, ensuring that the rinsing effect of each wash meets preset health standards. This fundamentally solves the health hazards such as skin irritation and allergies caused by chemical residues due to insufficient rinsing, especially ensuring the clothing safety of infants and people with sensitive skin.

[0024] This invention abandons the traditional fixed rinsing mode and makes decisions based on real-time feedback of residual indicators. When the clothes are relatively clean or the detergent dosage is low, the system immediately stops rinsing after reaching the target, avoiding unnecessary water and electricity consumption and wasted time; conversely, it automatically increases rinsing until the target is reached, avoiding greater waste from secondary washing. This dynamic adjustment based on actual needs ensures that overall resource consumption is always kept at an optimal level.

[0025] This invention fully automates the complex judgment process. Users only need to start the washing process, and the system can automatically guarantee the cleaning result, achieving foolproof intelligent operation.

[0026] Unlike foam sensors that are susceptible to low-foaming detergents or turbidity sensors that are insensitive to dissolved substances, this invention utilizes a specific wavelength excitation light source to excite fluorescence and captures it with a camera, enabling direct and specific detection of the target substance. This results in high sensitivity and strong targeting. Image processing algorithms effectively eliminate common interferences such as water ripples, bubbles, and ambient light, ensuring stable and reliable detection signals. The detection module has a compact structure, no easily damaged moving parts or precision electrodes, long lifespan, and low maintenance costs, making it ideal for large-scale industrial production and integration.

[0027] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it according to the contents of the specification, the preferred embodiments of the present invention are described in detail below with reference to the accompanying drawings. Specific embodiments of the present invention are given in detail below with reference to the accompanying drawings. Attached Figure Description

[0028] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings: Figure 1 A flowchart of the control method for a garment handling device; Figure 2 A schematic diagram of the garment processing device; Figure 3 Image of the water body; Figure 4 Here is the control flowchart for the detection module; Figure 5 A flowchart for calculating residual indicators of fluorescent agents in water bodies; Figure 6 Here is a flowchart of the intensity domain feature extraction process; Figure 7 Background subtraction processing flowchart; Figure 8 Flowchart for spatial domain feature and frequency domain feature extraction; Figure 9 Procedure for determining residual indicators using a predetermined calculation model Figure 1 ; Figure 10 Procedure for determining residual indicators using a predetermined calculation model Figure 2 ; Figure 11 A flowchart for the rinsing action control of the garment handling unit; Figure 12 Flowchart for switching rinsing modes; Figure 13 Recommend a flowchart for the program; Figure 14 This is a schematic diagram of a computer device. Figure 15 This is a schematic diagram of a computer-readable storage medium.

[0029] In the diagram: 1. Detection module; 2. Drainage pipe. Detailed Implementation

[0030] The present invention will now be further described with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. It should be noted that, without conflict, the various embodiments or technical features described below can be arbitrarily combined to form new embodiments.

[0031] Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without inventive effort are within the scope of protection of this invention.

[0032] The drawing numbers in this application are only used to distinguish the steps in the scheme and are not used to limit the execution order of the steps. The specific execution order is as described in the specification.

[0033] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.

[0034] Optical brighteners (such as CBS and VBL) are common additives in detergents, designed to make clothes appear whiter through optical compensation. However, if they are not fully dissolved or rinsed thoroughly during washing, they can adhere to the clothing fibers. Visually, this may cause localized yellowing or uneven white spots on white clothing; under ultraviolet light, uneven blue-purple fluorescence can be observed, providing direct evidence of the residue.

[0035] Residual fluorescent whitening agents pose a clear threat to human health, and under the current mainstream washing machine rinsing control logic, residue problems are difficult to avoid. Most washing machines only perform a fixed number of rinses (such as 1-2 times) and cannot dynamically adjust according to the actual amount of residue. Existing foam and turbidity sensors cannot specifically detect dissolved fluorescent agents. Therefore, users can only passively follow vague experience such as "recommended to rinse ≥3 times," but when the number of rinses is insufficient, the residue rate will still increase significantly, creating a dilemma of both wasted water and electricity and health risks.

[0036] Therefore, there is an urgent need for a method and garment treatment device that can detect the concentration of fluorescent agent residue in rinsing water in real time and accurately, and use this as a basis for intelligent and precise rinsing control, so as to fundamentally eliminate fluorescent agent residue and achieve optimal resource utilization while ensuring health.

[0037] The clothing processing equipment can be configured as a washing machine, a washer-dryer combo, etc. For ease of description, this invention uses a drum washing machine as an example for illustration, and should not be construed as a limitation on the type of clothing processing equipment.

[0038] This method can be executed by the main control unit of the garment processing device. The main control unit can be implemented in the form of software and / or hardware, and is generally integrated into any electronic device with network communication capabilities, such as a mobile terminal, PC, or server.

[0039] Example 1 A control method for a garment handling device, such as Figure 2 As shown, a detection module 1 is installed on the drainage pipe 2 of the clothing processing device. The detection module 1 is used to collect images of the water in the drainage pipe 2, such as... Figure 3 As shown. Figure 1 As shown, the method includes the following steps: S100: Acquire the water excitation image collected by the detection module after rinsing is completed; To enable real-time monitoring of the water quality after rinsing, the detection module 1 is fixedly mounted on the drainage pipe 2. Specifically, the detection module 1 is preferably installed on the pipe section after the drainage pump, leading to the external drain outlet, to ensure that it collects the final rinse water that is about to be discharged and obtains a stable water sample that fills the pipe.

[0040] like Figure 2 As shown, the detection module is installed inside the corrugated water pipe. This location is close to the water flow, providing a concentrated field of view and minimizing interference from external light. This design requires waterproofing, anti-fogging, and anti-condensation features, while ensuring the camera window remains clean. The corrugated water pipe must be made of opaque material to create a dark environment and avoid ambient light interference.

[0041] The core function of the detection module 1 is to acquire excitation images of the water flowing through the drainage pipe 2. It integrates an excitation light source: preferably an ultraviolet light source with an emission center wavelength range of 355nm to 375nm, or a blue light source with an emission center wavelength range of 440nm to 460nm, used to irradiate the water flow in the pipe and excite any fluorescent whitening agents it may contain to produce fluorescence; a camera: preferably a CMOS or CCD camera; a sealed housing and a light-transmitting window: the entire module is sealed within a waterproof and moisture-proof housing, with a light-transmitting window at the corresponding position of the light path. This window is made of a corrosion-resistant, high-transmittance material (such as quartz glass or optical-grade acrylic) and may have an anti-fouling coating, allowing it to be used as an upgrade kit for retrofitting old washing machines or as an optional accessory for new machines. The detection module 1 is electrically connected to the main control unit of the clothing processing device via a cable or wireless communication module for transmitting image data and receiving control commands.

[0042] When the washing machine completes its final rinse cycle, the rinse water flows into the drain pipe 2 and passes through the detection area of ​​the detection module 1. At this time, the main control unit triggers the detection module 1 to operate: the excitation light source is turned on, and the camera simultaneously acquires images of the excited water (i.e., water excitation images). This image data is transmitted to the processing unit (which can be integrated into the detection module 1 or the main control unit) for analysis and processing, ultimately calculating the fluorescent agent residue index and making an intelligent decision on whether to add a rinse cycle based on this.

[0043] To selectively enhance the target signal (fluorescence) while greatly suppressing ambient interference light. In some embodiments, such as Figure 4 As shown, before the step of acquiring the water excitation image collected by the detection module after rinsing, the method further includes: S110. Before starting the washing process, flush the water circuit with water through the water inlet pipe and perform data calibration and zeroing on the detection module. In this embodiment, before the washing process officially begins, the water inlet valve is opened, and a certain amount of clean water is injected into the washing drum through the water inlet pipe to flush out any detergent foam or contaminants that may remain in the drain pipe from the previous washing cycle. This ensures that the optical window of the detection module is clean and provides a clean water sample for obtaining a reference background image.

[0044] During or after water intake, the main control unit sends a reset command to the detection module. The detection module responds to this command to reset the data acquisition to zero.

[0045] Optionally, after completing the water flushing and data zeroing, an excitation image of the clean water in the drainage pipe can be captured and stored as a reference background image under conditions free from fluorescent interference. This reference background image will be used in subsequent calculations to eliminate inherent system noise and fixed background interference, thereby extracting the signal generated by the fluorescent agent more accurately.

[0046] S120. Activate the excitation light source to irradiate the water in the drainage pipe; The acquisition of water excitation images relies on the excitation light source inside the detection module 1. Its core function is to emit light of a specific wavelength to excite any fluorescent whitening agents that may be present in the water. In this embodiment, a 365nm UVA ultraviolet lamp or a 450nm blue lamp is preferably used as the excitation light source. Its wavelength is precise and can effectively excite most commercial fluorescent whitening agents, generating a high signal-to-noise ratio fluorescence signal.

[0047] The timing of the excitation light source's activation must be synchronized with the camera's exposure with millisecond-level precision. Before each acquisition, the main control unit sends a pulse signal to first turn on the light source and wait for its output to stabilize (typically 0.5-2 milliseconds) before triggering the camera's exposure. After the exposure is complete, the light source is immediately turned off to save energy and extend the LED's lifespan.

[0048] S130. Start the camera to capture images of the water body.

[0049] Preferably, a monochrome (black and white) CMOS / CCD industrial camera sensitive to blue-violet light is used to obtain higher contrast and sensitivity. Optionally, a 2-megapixel waterproof CMOS camera is used.

[0050] In this embodiment, the completion of the final rinsing is used as the precise control node. When the main control unit starts the drainage pump to begin discharging the rinsing water, a synchronization trigger signal is sent to detection module 1. This hardware synchronization method ensures precise timing of data acquisition, strictly corresponding to the water flow state. To avoid the possibility of residual water or air bubbles from the initial drainage stage, a short delay (e.g., 2-5 seconds) can be preset after the trigger signal. Data acquisition is initiated only after the drainage stabilizes and the water flow fills the transparent pipe section of the detection area. The camera can be configured to continuously acquire frames during the drainage process (e.g., 10 frames per second), or capture single or multiple representative frames within a preset stable time window. Continuous acquisition helps in selecting the best-quality images for subsequent analysis, avoiding acquisition failures caused by instantaneous air bubbles or turbulence.

[0051] This active optical detection mechanism selectively enhances the target signal (fluorescence) while greatly suppressing ambient interference. Combined with subsequent image processing algorithms, it effectively overcomes optical interference caused by water ripples, bubbles, and impurities during drainage. This enables stable water composition analysis with laboratory-level precision in the complex and dynamic environment inside the washing machine, solving the industry problem of poor reliability of household sensors.

[0052] Optionally, a preliminary quality verification can be performed before using the water image for calculations: check whether the overall average brightness of the image is within a reasonable range to rule out light source failure or serious exposure parameter errors. Simple edge detection is used to determine whether the region of interest (ROI) representing the water body in the image is complete (i.e., whether the water flow fills the field of view). To eliminate the effects of inherent system noise and fixed contaminants on the pipe walls, a "dark field reference image" (acquired in a state of no water flow and with the light source off) and / or a "clear water background image" (acquired in a state of clear water under light illumination without fluorescent agents) pre-stored in memory can be subtracted from the currently acquired image in real time. This preprocessing can greatly improve the quality of the image data at the front end.

[0053] After preliminary verification and preprocessing, the image data (or raw data along with preprocessing parameters) is encapsulated into a predefined data packet. This data packet is sent to the main control unit or cloud processing unit via a wired (e.g., UART, CAN) or wireless (e.g., Wi-Fi, Bluetooth) communication interface for subsequent calculations of fluorescent agent residue indicators, etc.

[0054] S200. Calculate the residual index of fluorescent agent in the water body based on the water body excitation image; To convert water excitation images into stable, reliable, and quantitative values ​​that characterize fluorescent agent concentration. In some embodiments, such as Figure 5 As shown, the step of calculating the residual index of fluorescent agents in the water body based on the water body excitation image includes: S210. Extract image features from the excitation image, wherein the image features include at least one of intensity domain features, spatial domain features, and frequency domain features; In some embodiments, such as Figure 6 As shown, the steps for extracting image features from the excitation image include: S211. Preprocess the excitation image, the preprocessing including noise reduction and background subtraction; After acquiring the raw water excitation image, preprocessing is performed to improve the signal-to-noise ratio and extract the effective analysis region. For example, median filtering, Gaussian filtering, or nonlocal mean denoising algorithms are used to perform spatial domain denoising on the image to eliminate pixel-level interference from random noise from the camera and minor turbulence in the water flow.

[0055] Specifically, such as Figure 7 As shown, the background subtraction processing steps include: S2111. Acquire a reference background image under conditions free from fluorescent interference; Optionally, one or more “zero-reference” images (such as an anhydrous cavity state or an ideal clear water state without fluorescent agents) are taken before each test or periodically to calibrate the baseline.

[0056] S2112. Register and align the excitation image with the reference background image; To eliminate pixel-level positional deviations caused by water flow fluctuations, the ROI of the current image can be registered at the sub-pixel level with a pre-stored standard background image (acquired and calibrated in clean water without fluorescent agents).

[0057] S2113. Subtract the corresponding pixel value of the registered reference background image from the pixel value of the excitation image to obtain the background-subtracted image.

[0058] This embodiment performs pixel-level subtraction (i.e., subtracting the registered background image from the detection image pixel by pixel), subtracting the registered background image from the current image to obtain a "differential image" with a background that is basically zero and only highlights the difference in fluorescence signal, thereby improving detection sensitivity.

[0059] S212. In the preprocessed image, delineate the region of interest; Optionally, a fixed mask method or a dynamic edge detection method can be used to extract the region of interest (ROI) and identify a continuous region in the image filled with water flow and with uniform brightness. This region is dynamically defined as the ROI to exclude interference from pipe wall shadows, fixed reflective points, and image edge distortion. This achieves the goal of analyzing only the effective image region that represents the water body. Specifically, the fixed mask method excludes edge reflections and pipe wall interference by pre-setting a rectangular or circular area in the center of the image; in the dynamic edge detection method, if the water flow is stable, the boundaries of the water body can be detected, focusing on the water body portion.

[0060] S213. Extract the intensity domain features of the region of interest, wherein the intensity domain features include at least one of the region average gray value, the region maximum gray value, and the region gray standard deviation.

[0061] This embodiment extracts a set of feature vectors from the preprocessed differential image ROI that comprehensively reflects the fluorescence intensity and distribution characteristics. The intensity domain features can be extracted by calculating the average gray value of all pixels within the ROI, which serves as the core indicator of overall fluorescence intensity and directly reflects the overall fluorescence brightness; or by calculating the maximum gray value within the ROI, which reflects the area with the highest local fluorescent agent concentration and is highly sensitive to detecting local high residues (such as undissolved detergent clumps); or by calculating the gray standard deviation of the ROI, reflecting the uniformity of fluorescence distribution in space. If completely dissolved fluorescent agent is uniformly distributed, the standard deviation will be smaller.

[0062] Because fluorescent agents, after dissolution, are typically uniformly dispersed with a soft texture, while the specular reflection caused by water ripples presents high-contrast bright spots and dark stripes, the two can be distinguished by their texture characteristics. Furthermore, water ripples have specific spatial frequencies (related to water flow velocity and bellows diameter), forming distinct bright rings or lines on the power spectrum. Uniform fluorescence, on the other hand, is concentrated at low frequencies in the frequency domain. By analyzing the high-frequency components, the intensity of ripple interference can be quantified, allowing it to be subtracted from performance metrics. In some embodiments, such as... Figure 8 As shown, the step of extracting image features from the excitation image further includes: S214. Based on the gray-level co-occurrence matrix of the excitation image, spatial domain features are calculated, including at least one of contrast, uniformity, energy, and correlation. Uniform fluorescence distribution in water exhibits high uniformity and low contrast; while non-specific bright spots caused by water ripples or impurities exhibit low uniformity and high contrast. This characteristic is used to distinguish target signals from optical interference.

[0063] S215. Frequency domain features are obtained by calculating the two-dimensional frequency domain power spectrum of the excitation image, which are used to quantify the intensity of frequency components caused by periodic interference in the image.

[0064] In this embodiment, a two-dimensional fast Fourier transform (2D-FFT) is performed on the ROI image to obtain its frequency domain power spectrum. The energy of the frequency band corresponding to the known water ripple frequency in the power spectrum is analyzed. By calculating the ratio of this frequency band energy to the total energy, the ripple interference index is obtained. This index will be used in subsequent fusion to compensate for or eliminate the influence of periodic flow stripes on intensity measurements.

[0065] S220. Based on the extracted image features, the residual index is determined using a predetermined calculation model.

[0066] In some embodiments, such as Figure 9 , Figure 10 As shown, the step of determining the residual index based on the extracted image features using a predetermined calculation model includes: S221. Normalize the extracted image features; S222. Input the normalized multiple image features into a preset weight coefficient model, and calculate the residual index by weighted summation; or, S223. Input the normalized multiple image features into a pre-trained machine learning regression model, and output the residual index from the regression model.

[0067] To fuse multiple extracted feature values ​​into a single scalar residual index, a weighted linear fusion model can be used. After normalizing each feature value to the [0,1] interval, a weighted sum is performed according to pre-calibrated weights: Residual Index RI = W1 * Normalized Average Intensity + W2 * Maximum Intensity - W3 * Standard Deviation - W4 * Ripple Interference Index. The weighting coefficients W1 to W4 were determined through regression analysis using a large amount of experimental data (tested using standard solutions of fluorescent agents with known concentrations). The minus sign indicates that the interference features have a negative corrective effect on the final residual index.

[0068] Alternatively, a more accurate machine learning regression model capable of handling complex nonlinearities can be employed. By collecting a massive number of water excitation images under varying concentrations and disturbance conditions (different water temperatures, flow rates, and bubble formations), the aforementioned multi-dimensional features are extracted and labeled with their corresponding true fluorescent agent concentrations (calibrated using laboratory instruments), forming a training dataset. This dataset is then used to train a lightweight regression model, such as a gradient boosting decision tree or a small neural network. The real-time extracted feature vectors are input into the trained model, which directly outputs the predicted fluorescent agent concentration estimate (in μg / L or ppb), which serves as the residual indicator.

[0069] This embodiment removes interference through precise image preprocessing, extracts image features strongly correlated with fluorescence intensity from multiple dimensions, and finally maps these features into a stable, reliable, and interpretable quantitative index through a (rule-based or data-based) fusion model, providing accurate data input for subsequent intelligent decision-making.

[0070] S300. Based on the comparison result between the residual index and the preset threshold, control the rinsing action of the clothing treatment device.

[0071] In some embodiments, such as Figure 11 As shown, the step of controlling the rinsing action of the clothing treatment device based on the comparison result of the residual index and the preset threshold includes: S310. If the residual index is greater than the preset threshold, it is determined that the fluorescent agent has not been cleaned, and a control command to increase rinsing is generated; that is, the washing machine is controlled to add one or more complete rinsing cycles (water inlet-stirring / soaking-draining).

[0072] S320. Execute the control command to dynamically adjust the parameters of the subsequent rinsing process.

[0073] Optionally, the selection can also be based on the intensity of the residue level. If the cleanliness compliance threshold is less than the residue index and less than the light residue threshold, then a standard supplementary rinsing should be performed.

[0074] If the residual index exceeds the heavy residue threshold, the deep intensive rinsing mode is triggered. In this mode, the system may automatically increase the rinsing water temperature (e.g., to 40°C to promote dissolution), extend the rinsing soaking time, or add an extra pre-rinse.

[0075] It can also switch modes based on the rate of decline (i.e., adaptive optimization). During the drainage phase of the supplementary rinsing, the system acquires images again and calculates new residual indicators, while simultaneously calculating the rate of decline of indicators for this rinsing cycle.

[0076] If the descent rate is lower than the expected descent rate threshold, it indicates that the current water flow rinsing mode is inefficient. In the next rinsing cycle, the main control unit will switch the mode from conventional soaking rinsing to pulse oscillation rinsing. In this mode, the controller pulses to control the opening and closing of the inlet valve and simultaneously controls the inner drum to rotate in opposite directions for a short time at high speed to generate a strong oscillating water flow to remove residue deep within the fibers.

[0077] If the rate of descent is higher than or equal to the threshold, the system will maintain or switch to a high-efficiency continuous displacement rinsing mode. In this mode, the controller simultaneously opens the inlet valve (normally open at low flow rate) and the drain pump, creating an overflow state where water is simultaneously entering and exiting the system, continuously displacing the dissolved fluorescent agent with a minimum water volume.

[0078] S330. If the residual index is not greater than the preset threshold, the rinsing is deemed qualified. Immediately stop the current water inlet or drainage process (if it is in progress) and control the washing machine to enter the next process (such as the spin-drying program or the final drainage end program). At the same time, a "Rinsing complete, cleanliness meets standards" prompt can be displayed through the user interface.

[0079] Optionally, to ensure system robustness, the control logic can also include safety mechanisms. For example, to prevent infinite loops due to camera malfunction or extreme dirt, the system has a maximum limit on the number of rinses (e.g., 6 times). Once the limit is reached, the rinsing process is forcibly terminated regardless of the indicators, and an alarm suggesting manual handling is issued to the user. If residual indicator data is detected abnormally multiple times consecutively (e.g., no change, drastic fluctuations), the system can determine that the detection module may have experienced a temporary malfunction (e.g., mirror surface damage). In this case, the control system can automatically degrade to a time-based conservative rinsing mode (e.g., adding 2 more rinses) and prompt the user for maintenance.

[0080] While the control actions are being executed, the system provides transparent feedback to the user through a display screen or a connected app. For example, it may display "Fluorescent agent residue detected, performing the Xth enhanced rinse...", "Due to heavy residue, hot water rinse has been automatically activated", or "To improve efficiency, it has switched to dynamic water flow mode".

[0081] After washing, a visual report can be generated that includes information such as initial residual value, final residual value, total number of rinses, and water savings compared to a fixed program.

[0082] In some embodiments, such as Figure 12 As shown, the parameters for dynamically adjusting the subsequent rinsing process include at least one of the following: Increase the number of rinses; Switch rinsing modes, including pulse oscillation rinsing mode and continuous replacement rinsing mode; During a single rinsing cycle, the system can monitor the rate of decrease of residual indicators and compare it with a preset expected rate of decrease threshold to dynamically adjust the rinsing mode. In some embodiments, the basis for switching rinsing modes includes the rate of decrease of the residual indicators: S321. If the descent rate is lower than the preset value, switch to the pulse oscillation rinsing mode (for adhesive residues). The pulse oscillation rinsing mode includes controlling the water inlet valve of the clothing treatment device to introduce water in a pulse manner and controlling the washing drum to rotate at high and low speeds in both directions. When the rate of decrease in residual indicators is slow, it indicates that the fluorescent agent is stubbornly adhered deep within the fibers. The main control unit controls the water inlet valve to generate rapid pulses, controls the washing drum to rotate alternately at high and low speeds, and keeps the drain pump on standby, quickly injecting a small amount of water (e.g., for 3 seconds). Combined with the vigorous forward and reverse rotation of the washing drum, this creates a strong oscillating water flow, beating and shaking out the residue inside the clothing fibers. This process is repeated several times, forming an oscillating soaking stage. After oscillation, the garment is left to stand for a moment, and the detection module samples the data. If the data shows significant improvement, a regular rinse is initiated; if the improvement is not significant, the oscillation is repeated or the process is switched to a stronger mode.

[0083] S322. If the descent rate is not lower than the preset value, then switch to the continuous replacement rinsing mode (for dissolved residues). The continuous replacement rinsing mode includes controlling the water inlet valve to continuously introduce water at a low speed and simultaneously controlling the drain pump of the clothing treatment device to continuously drain water.

[0084] When the residual index rate shows a linear decrease, it indicates that the residue has been fully dissolved in the water, and the issue is mainly dilution. The main control unit controls the inlet valve to be open at a low speed, controls the drain pump to be open synchronously, and controls the washing drum to rotate at a low and uniform speed, achieving an overflow mode of simultaneous water intake and drainage. This acts like a fine stream of water, continuously displacing dissolved contaminants with a constant flow of fresh water. Because it is a fine stream, this mode has controllable water consumption and high efficiency, avoiding the problem of water saturation in the later stages of the traditional water storage-drainage mode.

[0085] This embodiment can also achieve adaptive multi-stage composite rinsing. Assuming a high initial level of contamination is detected, the first stage (powerful stripping) involves two rounds of pulse oscillation rinsing. Then, if the residual rate of decrease is greater than a first threshold, the second stage (efficient displacement) begins, continuously displacing and rinsing until the detected value is less than a second threshold. If the detected residual rate of decrease is not greater than or below the threshold, it is determined to be an extremely stubborn stain, triggering a powerful rinsing program. This may require increasing the water temperature or adding a small amount of clean water for a second rinse.

[0086] Adjust at least one of the following: water volume, water inlet rate, drainage timing, washing drum movement mode of the garment processing device, or water temperature for a single rinse.

[0087] In this embodiment, the detection module communicates deeply with the main control board, which not only controls the number of rinses, but also dynamically adjusts the water inlet valve / drain pump to achieve more efficient pulse or continuous rinsing, and recommends or automatically switches to powerful rinsing, energy-saving rinsing or sensitive skin rinsing mode based on the degree of contamination detected after the first wash.

[0088] To achieve global optimization before rinsing begins, in some embodiments, such as Figure 13 As shown, the method further includes S400, recommended program steps: S410. After the washing program is completed and before the first rinse, acquire an excitation image of the initial water body; In this embodiment, at the beginning of the first rinse cycle's drainage stage after the main washing program (including detergent dispensing, main wash, and drainage) is completely finished, the main control unit controls the detection module to operate. The discharged water at this time is the initial contaminated liquid containing a high concentration of detergent, suspended dirt, and fluorescent whitening agents washed off the clothes. The same operation as described above is performed: the excitation light source is activated to illuminate the water flow, and the camera is activated to capture an excitation image of this initial water volume. This image contains key optical information about the initial contamination load of the clothes.

[0089] S420. Determine the initial degree of soiling of clothing based on the excitation image of the initial water body; In this embodiment, the wastewater is sampled and analyzed after washing and before the first rinse to calculate the initial pollution index. Similarly, the fluorescence intensity is extracted, and the calculated initial fluorescence intensity is compared with the preset pollution level threshold range. The main control unit then performs intelligent program planning based on this comparison.

[0090] If the fluorescence intensity is extremely low, it is considered to be mild contamination, such as from everyday clothing.

[0091] If the fluorescence intensity is in the medium range, it is considered standard contamination, such as routine dirt.

[0092] If the fluorescence intensity exceeds the high threshold, it is judged as severe contamination, such as work clothes with a lot of stains or excessive detergent.

[0093] S430. Based on the initial level of contamination, recommend or automatically switch to the corresponding preset rinsing program, which includes an energy-saving rinsing program, a standard rinsing program, and a powerful rinsing program.

[0094] Based on the judgment result of step S420, the main control unit executes different control strategies, including a user-confirmed recommendation mode, which pops up a prompt on the user interface (such as a panel or APP): "Slight soiling of clothes detected. We recommend using an energy-saving rinsing program to save water and electricity. Do you want to switch?" After user confirmation, the system adjusts the subsequent rinsing parameters (such as number of rinses, water level, and water flow intensity) to the preset energy-saving optimization mode.

[0095] And a fully automatic automatic switching mode, where the system switches directly to the corresponding optimal program without being prompted. For light pollution, an energy-saving rinsing program is executed, such as using a minimum number of continuous replacement rinsing cycles (1-2 times), with the goal of achieving the testing standards with minimal water and electricity.

[0096] To address standard contamination, a standard rinsing procedure is performed, such as a pre-set, balanced routine rinsing process that may combine one agitation rinsing with one displacement rinsing.

[0097] For heavily soiled areas, a powerful rinsing program is executed. For example, the main control unit activates the heater to raise the initial rinse water temperature to around 40°C to aid dissolution. At least three cycles of agitation rinsing and displacement rinsing are performed to ensure thorough dissolution and displacement. The screen / app may also display: "Heavy stains detected. Deep rinsing program initiated. Expected duration: 30 minutes." This embodiment provides a control method for a clothing handling device, achieving a fundamental leap from process control to result assurance, thus ensuring the ultimate goal of healthy washing. Traditional washing machines mechanically execute preset rinsing cycles or times, while this embodiment directly analyzes the residual index of fluorescent whitening agents in the rinsing water, establishing the control logic based on objective and quantifiable cleanliness data. This enables online monitoring and closed-loop control of specific harmful chemical residues in consumer-grade products, ensuring that the rinsing effect of each wash meets preset health standards. It fundamentally solves the health risks such as skin irritation and allergies caused by chemical residues due to insufficient rinsing, especially protecting the clothing safety of infants and people with sensitive skin.

[0098] This embodiment achieves precise resource utilization, resulting in significant water, electricity, and time savings. It abandons fixed rinsing modes and makes decisions based on real-time feedback of residual detergent levels. When clothes are relatively clean or detergent usage is low, the system immediately stops rinsing after reaching the target level, avoiding unnecessary water and electricity consumption and wasted time; conversely, it automatically increases rinsing until the target level is reached, avoiding greater waste from secondary washing. This dynamic adjustment based on actual needs ensures that overall resource consumption remains at an optimal level.

[0099] This embodiment enhances the intelligence and trustworthiness of the user experience, making operation simpler and results more reliable. Users no longer need to guess the number of rinses based on experience. This embodiment fully automates the complex judgment process; users only need to start the wash cycle, and the system can autonomously guarantee a clean result, achieving foolproof intelligent operation.

[0100] This embodiment innovatively employs non-contact optical image analysis technology, combining high reliability, low cost, and strong anti-interference capabilities. Unlike foam sensors susceptible to low-foaming detergents or turbidity sensors insensitive to dissolved substances, this embodiment utilizes a specific wavelength excitation light source to excite fluorescence and capture it with a camera, directly targeting the specific substance for specific detection, resulting in high sensitivity and strong targeting. Through image processing algorithms (such as background subtraction, ROI analysis, and frequency domain filtering), common interferences such as water ripples, bubbles, and ambient light can be effectively eliminated, ensuring the stability and reliability of the detection signal. This detection module has a compact structure, no easily damaged moving parts or precision electrodes, long lifespan, and low maintenance costs, making it ideal for large-scale industrial production and integration.

[0101] In summary, this embodiment, by deeply integrating optical sensing, image analysis, and intelligent control technologies, not only completely solves the industry pain point of uncontrollable rinsing effects and achieves reliable protection for healthy washing, but also brings multi-dimensional and disruptive benefits in terms of energy conservation, environmental protection, user experience, and intelligent ecosystem construction, representing a clear direction for the development of garment processing technology towards precision and intelligence.

[0102] Example 2 Based on the same concept, this embodiment also provides a clothing handling device that applies the control method provided in Embodiment 1. A detailed description of the control method provided in Embodiment 1 can be found in the corresponding descriptions in the above method embodiments, and will not be repeated here. In some embodiments, the clothing handling device can be applied as a washing machine, and in other embodiments as a washer-dryer combo.

[0103] It is understood that the garment processing device provided in this embodiment includes hardware structures and / or software modules corresponding to each function in order to achieve the above-mentioned functions. In conjunction with the units and algorithm steps of the various examples disclosed in this embodiment, this embodiment can be implemented in hardware or a combination of hardware and computer software. Whether a certain function is executed by hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the technical solution of this embodiment.

[0104] A garment processing device, such as Figure 2 As shown, it includes: Drainage pipe 2; Detection module 1 is used to acquire excitation images of the water body within the drainage pipe 2, such as... Figure 3 As shown; The main control unit is configured to execute the above method.

[0105] To enable real-time monitoring of the water quality after rinsing, the detection module 1 is fixedly mounted on the drainage pipe 2. Specifically, the detection module 1 is preferably installed on the pipe section after the drainage pump, leading to the external drain outlet, to ensure that it collects the final rinse water that is about to be discharged and obtains a stable water sample that fills the pipe.

[0106] like Figure 2 As shown, the detection module is installed inside the corrugated water pipe. This location is close to the water flow, providing a concentrated field of view and minimizing interference from external light. This design requires waterproofing, anti-fogging, and anti-condensation features, while ensuring the camera window remains clean. The corrugated water pipe must be made of opaque material to create a dark environment and avoid ambient light interference.

[0107] The core function of the detection module 1 is to acquire excitation images of the water flowing through the drainage pipe 2. It integrates an excitation light source that emits ultraviolet light with a wavelength range of 355nm to 375nm, or blue light with a wavelength range of 440nm to 460nm, to irradiate the water flow in the pipe and excite any fluorescent whitening agents it may contain to produce fluorescence. A camera, preferably a CMOS or CCD camera, is also included. The camera and the excitation light source are integrated and encapsulated in a waterproof housing, with a mounting structure for fixing them to the drainage pipe. The housing has a light-transmitting window at the corresponding optical path position. This window is made of a corrosion-resistant, high-transmittance material (such as quartz glass or optical-grade acrylic) and may have an anti-fouling coating, making it suitable as an upgrade kit for retrofitting old washing machines or as an option for new machines. The detection module 1 is electrically connected to the main control unit of the clothing handling device via a cable or wireless communication module for transmitting image data and receiving control commands.

[0108] When the washing machine completes its final rinse cycle, the rinse water flows into the drain pipe 2 and passes through the detection area of ​​the detection module 1. At this time, the main control unit triggers the detection module 1 to operate: the excitation light source is turned on, and the camera simultaneously acquires images of the excited water (i.e., water excitation images). This image data is transmitted to the processing unit (which can be integrated into the detection module 1 or the main control unit) for analysis and processing, ultimately calculating the fluorescent agent residue index and making an intelligent decision on whether to add a rinse cycle based on this.

[0109] The clothing processing device of this embodiment may include the following process: The image acquisition module is used to acquire the water excitation image collected by the detection module after rinsing is completed; The residual index calculation module is used to calculate the residual index of fluorescent agents in the water body based on the water body excitation image; The rinsing action control module is used to control the rinsing action of the clothing treatment device based on the comparison result of the residual index and the preset threshold.

[0110] Based on the technical solution of the above embodiments, optionally, the detection module includes an excitation light source and a camera, and before the step of acquiring the water excitation image collected by the detection module after rinsing, it further includes: Before starting the washing process, water is introduced through the inlet pipe to flush the water circuit, and the detection module is calibrated to zero. The excitation light source is activated to irradiate the water in the drainage pipe; The camera is activated to capture images of the water body.

[0111] Based on the technical solution of the above embodiments, optionally, the step of calculating the residual index of fluorescent agent in the water body based on the water body excitation image includes: Image features are extracted from the excitation image, the image features including at least one of intensity domain features, spatial domain features and frequency domain features; Based on the extracted image features, the residual index is determined through a predetermined calculation model.

[0112] Based on the technical solution of the above embodiments, optionally, the step of extracting image features from the excitation image includes: The excitation image is preprocessed, including denoising and background subtraction. In the preprocessed image, the region of interest is delineated; Extract the intensity domain features of the region of interest, wherein the intensity domain features include at least one of the region's average gray value, the region's maximum gray value, and the region's gray standard deviation.

[0113] Based on the technical solutions of the above embodiments, optionally, the background subtraction processing step includes: Acquire a reference background image under conditions free from fluorescent interference; The excitation image is registered and aligned with the reference background image; The corresponding pixel values ​​of the registered reference background image are subtracted from the pixel values ​​of the excitation image to obtain the background-subtracted image.

[0114] Based on the technical solution of the above embodiments, optionally, the step of extracting image features from the excitation image further includes: Spatial domain features are calculated based on the gray-level co-occurrence matrix of the excitation image, including at least one of contrast, uniformity, energy, and correlation. Frequency domain features are obtained by calculating the two-dimensional power spectrum of the excitation image, which are used to quantify the intensity of frequency components caused by periodic interference in the image.

[0115] Based on the technical solutions of the above embodiments, optionally, the step of determining the residual index based on the extracted image features using a predetermined calculation model includes: The extracted image features are normalized. The normalized image features are input into a preset weighted coefficient model, and the residual index is obtained by weighted summation; or, The normalized image features are input into a pre-trained machine learning regression model, which then outputs the residual index.

[0116] Based on the technical solution of the above embodiments, optionally, the step of controlling the rinsing action of the clothing treatment device according to the comparison result of the residual index and the preset threshold includes: If the residual index is greater than the preset threshold, it is determined that the fluorescent agent has not been cleaned properly, and a control command to increase rinsing is generated. The control commands are executed to dynamically adjust the parameters of the subsequent rinsing process.

[0117] Based on the technical solutions of the above embodiments, optionally, the parameters for dynamically adjusting the subsequent rinsing process include at least one of the following: Increase the number of rinses; Switch rinsing modes, including pulse oscillation rinsing mode and continuous replacement rinsing mode; Adjust at least one of the following: water volume, water inlet rate, drainage timing, washing drum movement mode of the garment processing device, or water temperature for a single rinse.

[0118] Based on the technical solutions of the above embodiments, optionally, the basis for switching the rinsing mode includes the rate of decrease of the residual index: If the descent rate is lower than the preset value, the pulse oscillation rinsing mode is switched to. The pulse oscillation rinsing mode includes controlling the water inlet valve of the clothing treatment device to introduce water in a pulse manner and controlling the washing drum to rotate at high and low speeds in both directions. If the descent rate is not lower than the preset value, the system switches to the continuous replacement rinsing mode. The continuous replacement rinsing mode includes controlling the water inlet valve to continuously introduce water at a low speed and simultaneously controlling the drain pump of the clothing processing device to continuously drain water.

[0119] Based on the technical solutions of the above embodiments, the method may optionally further include a program recommendation step: After the washing cycle is completed and before the first rinse, an excitation image of the initial water body is acquired; Based on the excitation image of the initial water body, determine the initial degree of soiling of the clothing; Based on the initial level of contamination, the system recommends or automatically switches to the corresponding preset rinsing program, which includes an energy-saving rinsing program, a standard rinsing program, and a powerful rinsing program.

[0120] This embodiment provides a clothing treatment device that achieves a fundamental leap from process control to result assurance, ensuring the ultimate goal of healthy washing. Traditional washing machines mechanically execute preset rinsing cycles or times, while this embodiment directly analyzes the residual index of fluorescent whitening agents in the rinsing water, establishing the control logic based on objective and quantifiable cleanliness data. It achieves online monitoring and closed-loop control of specific harmful chemical residues in consumer-grade products, ensuring that the rinsing effect of each wash meets preset health standards. This fundamentally solves the health hazards such as skin irritation and allergies caused by chemical residues due to insufficient rinsing, especially ensuring the clothing safety of infants and people with sensitive skin.

[0121] This embodiment achieves precise resource utilization, resulting in significant water, electricity, and time savings. It abandons fixed rinsing modes and makes decisions based on real-time feedback of residual detergent levels. When clothes are relatively clean or detergent usage is low, the system immediately stops rinsing after reaching the target level, avoiding unnecessary water and electricity consumption and wasted time; conversely, it automatically increases rinsing until the target level is reached, avoiding greater waste from secondary washing. This dynamic adjustment based on actual needs ensures that overall resource consumption remains at an optimal level.

[0122] This embodiment enhances the intelligence and trustworthiness of the user experience, making operation simpler and results more reliable. Users no longer need to guess the number of rinses based on experience. This embodiment fully automates the complex judgment process; users only need to start the wash cycle, and the system can autonomously guarantee a clean result, achieving foolproof intelligent operation.

[0123] This embodiment innovatively employs non-contact optical image analysis technology, combining high reliability, low cost, and strong anti-interference capabilities. Unlike foam sensors susceptible to low-foaming detergents or turbidity sensors insensitive to dissolved substances, this embodiment utilizes a specific wavelength excitation light source to excite fluorescence and capture it with a camera, directly targeting the specific substance for specific detection, resulting in high sensitivity and strong targeting. Through image processing algorithms (such as background subtraction, ROI analysis, and frequency domain filtering), common interferences such as water ripples, bubbles, and ambient light can be effectively eliminated, ensuring the stability and reliability of the detection signal. This detection module has a compact structure, no easily damaged moving parts or precision electrodes, long lifespan, and low maintenance costs, making it ideal for large-scale industrial production and integration.

[0124] In summary, this embodiment, by deeply integrating optical sensing, image analysis, and intelligent control technologies, not only completely solves the industry pain point of uncontrollable rinsing effects and achieves reliable protection for healthy washing, but also brings multi-dimensional and disruptive benefits in terms of energy conservation, environmental protection, user experience, and intelligent ecosystem construction, representing a clear direction for the development of garment processing technology towards precision and intelligence.

[0125] Example 3 A computer device 400, such as Figure 14 As shown, the device includes a memory 410, a processor 420, and a computer program 430 stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of a control method for a garment handling device. For a detailed description of the method, please refer to the corresponding description in the above method embodiments; it will not be repeated here.

[0126] Example 4 A computer-readable storage medium, such as Figure 15As shown, a computer program is stored thereon, which, when executed by a processor, implements the steps of a control method for a garment handling device. For a detailed description of the method, please refer to the corresponding description in the above method embodiments, and will not be repeated here.

[0127] The number of devices and processing scale described herein are for the purpose of simplifying the description of the invention. Applications, modifications, and variations of the invention will be readily apparent to those skilled in the art.

[0128] Although embodiments of the present invention have been disclosed above, they are not limited to the applications listed in the specification and embodiments. They can be applied to various fields suitable for the present invention. For those skilled in the art, other modifications can be easily made. Therefore, without departing from the general concept defined by the claims and their equivalents, the present invention is not limited to the specific details and illustrations shown and described herein.

[0129] The apparatus, computer device, and non-volatile computer storage medium and method provided in the embodiments of this specification are corresponding. Therefore, the apparatus, computer device, and non-volatile computer storage medium also have similar beneficial technical effects as the corresponding method. Since the beneficial technical effects of the method have been described in detail above, the beneficial technical effects of the corresponding apparatus, computer device, and non-volatile computer storage medium will not be repeated here.

[0130] Those skilled in the art will also know that, besides implementing the controller in the form of purely computer-readable program code, the same functions can be achieved by logically programming the method steps, making the controller take the form of logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers (PLCs), and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the devices included within it for implementing various functions can also be considered structures within that hardware component. Alternatively, the devices for implementing various functions can be considered as both software units implementing the method and structures within a hardware component.

[0131] The systems, apparatuses, or units described in the above embodiments can be implemented by computer chips or physical entities, or by products with certain functions. For ease of description, the above apparatuses are described separately as various units based on their functions. Of course, when implementing one or more embodiments of this specification, the functions of each unit can be implemented in one or more software and / or hardware.

[0132] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the embodiments of this specification can take the form of a computer program product 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.

[0133] This specification is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this specification. It will be understood that each block of the flowchart illustrations and / or block diagrams, and 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 apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, 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.

[0134] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function 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.

[0135] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable 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.

[0136] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus 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 apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0137] This specification may be described in the general context of computer-executable instructions, such as program units, that are executed by a computer. Generally, program units include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This specification may also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program units may reside in local and remote computer storage media, including storage devices.

[0138] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0139] The above description is merely an embodiment of this specification and is not intended to limit the scope of one or more embodiments of this specification. Various modifications and variations can be made to one or more embodiments of this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of one or more embodiments of this specification should be included within the scope of the claims of one or more embodiments of this specification.

Claims

1. A control method for a garment handling device, characterized in that, A detection module is installed on the drain pipe of the garment processing device. The detection module is used to acquire images of the water in the drain pipe, including the following steps: Acquire the water excitation image collected by the detection module after rinsing; The residual index of fluorescent agent in the water body is calculated based on the water body excitation image; The rinsing action of the garment processing device is controlled based on the comparison result between the residual index and the preset threshold.

2. The control method for a garment handling device as described in claim 1, characterized in that, The detection module includes an excitation light source and a camera, and before the step of acquiring the water excitation image collected by the detection module after rinsing, it also includes: Before starting the washing process, water is introduced through the inlet pipe to flush the water circuit, and the detection module is calibrated to zero. The excitation light source is activated to irradiate the water in the drainage pipe; The camera is activated to capture images of the water body.

3. The control method for a garment processing device as described in claim 1, characterized in that, The step of calculating the residual index of fluorescent agent in the water body based on the water body excitation image includes: Image features are extracted from the excitation image, the image features including at least one of intensity domain features, spatial domain features and frequency domain features; Based on the extracted image features, the residual index is determined through a predetermined calculation model.

4. The control method for a garment handling device as described in claim 3, characterized in that, The steps for extracting image features from the excitation image include: The excitation image is preprocessed, including denoising and background subtraction. In the preprocessed image, the region of interest is delineated; Extract the intensity domain features of the region of interest, wherein the intensity domain features include at least one of the region's average gray value, the region's maximum gray value, and the region's gray standard deviation.

5. The control method for a garment handling device as described in claim 4, characterized in that, The background subtraction processing steps include: Acquire a reference background image under conditions free from fluorescent interference; The excitation image is registered and aligned with the reference background image; The corresponding pixel values ​​of the registered reference background image are subtracted from the pixel values ​​of the excitation image to obtain the background-subtracted image.

6. The control method of a garment handling device as described in claim 3 or 4, characterized in that, The step of extracting image features from the excited image further includes: Spatial domain features are calculated based on the gray-level co-occurrence matrix of the excitation image, including at least one of contrast, uniformity, energy, and correlation. Frequency domain features are obtained by calculating the two-dimensional frequency domain power spectrum of the excitation image, which are used to quantify the intensity of frequency components caused by periodic interference in the image.

7. The control method for a garment handling device as described in claim 3, characterized in that, The step of determining the residual index based on the extracted image features using a predetermined calculation model includes: The extracted image features are normalized. The normalized image features are input into a preset weighted coefficient model, and the residual index is obtained by weighted summation; or, The normalized image features are input into a pre-trained machine learning regression model, which then outputs the residual index.

8. The control method for a garment handling device as described in claim 1, characterized in that, The step of controlling the rinsing action of the garment treatment device based on the comparison result of the residual index and the preset threshold includes: If the residual index is greater than the preset threshold, it is determined that the fluorescent agent has not been cleaned properly, and a control command to increase rinsing is generated. The control commands are executed to dynamically adjust the parameters of the subsequent rinsing process.

9. The control method for a garment handling device as described in claim 8, characterized in that, The parameters for dynamically adjusting the subsequent rinsing process include at least one of the following: Increase the number of rinses; Switch rinsing modes, including pulse oscillation rinsing mode and continuous replacement rinsing mode; Adjust at least one of the following: water volume, water inlet rate, drainage timing, washing drum movement mode of the garment processing device, or water temperature for a single rinse.

10. The control method of the garment handling device as described in claim 9, characterized in that, The basis for switching rinsing modes includes the rate of decrease of the residual index: If the descent rate is lower than the preset value, the pulse oscillation rinsing mode is switched to. The pulse oscillation rinsing mode includes controlling the water inlet valve of the clothing treatment device to introduce water in a pulse manner and controlling the washing drum to rotate at high and low speeds in both directions. If the descent rate is not lower than the preset value, the system switches to the continuous replacement rinsing mode. The continuous replacement rinsing mode includes controlling the water inlet valve to continuously introduce water at a low speed and simultaneously controlling the drain pump of the clothing processing device to continuously drain water.

11. The control method of the garment handling device as described in claim 1, characterized in that, The method also includes a program recommendation step: After the washing cycle is completed and before the first rinse, an excitation image of the initial water body is acquired; Based on the excitation image of the initial water body, determine the initial degree of soiling of the clothing; Based on the initial level of contamination, the system recommends or automatically switches to the corresponding preset rinsing program, which includes an energy-saving rinsing program, a standard rinsing program, and a powerful rinsing program.

12. A garment processing device, characterized in that, include: Drainage pipes; The detection module is used to acquire images of the water body inside the drainage pipe. The main control unit is configured to perform the method as described in any one of claims 1 to 11.

13. The garment processing apparatus as described in claim 12, characterized in that, The detection module includes: Camera; The excitation light source emits ultraviolet light with a wavelength range of 355nm to 375nm, or blue light with a wavelength range of 440nm to 460nm. The camera and the excitation light source are integrated and encapsulated in a waterproof housing, and are provided with an installation structure for fixing them to the drainage pipe.

14. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 11.

15. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 11.

Images