Self-adaptive feeding method and device of cleaning agent, cleaning equipment and medium

Abstract

The invention discloses a cleaning agent self-adaptive feeding method and device, cleaning equipment and a medium, and belongs to the technical field of general cleaning. The method comprises the following steps: identifying a material parameter and a weight parameter of a to-be-cleaned article, and determining a first putting amount of a cleaning agent; continuously monitoring the turbid degree in the cleaning equipment within a preset duration of executing the washing operation to obtain turbid data, and drawing a turbid data curve; inputting the second input amount into a pre-constructed cleaning agent control model to obtain a second input amount; putting the cleaning agent for the second time; and modifying the duration of each cleaning program in the cleaning process according to the time point of the second putting. According to the technical scheme, through real-time monitoring and analysis of turbid data, additional putting of the cleaning agent can be conducted according to the smudginess condition of the to-be-cleaned object, the cleaning effect can be guaranteed, additional operation caused by too much cleaning agent is avoided, the cleaning effect of the cleaning equipment is improved, and the use experience of a user is improved.

Description

Technical Field

[0001] This application belongs to the field of general cleaning technology, and specifically relates to an adaptive dosing method, device, cleaning equipment and medium for a cleaning agent. Background Art

[0002] With the rapid development of the technology level, the production and use of various devices have greatly reduced the burden of manual operations. Taking cleaning equipment as an example, whether it is used in industrial production or household life, it can greatly reduce the amount of manual work, and the cleaning effect is good, so it has been developed and applied rapidly.

[0003] Regarding the control of cleaning equipment, it is often programmed at present. Especially for the use of cleaning agents, it often only considers the quantity of items to be cleaned for dosing. This will lead to inaccurate dosing of cleaning agents during actual use. On the one hand, less dosing of cleaning agents will affect the cleaning effect. On the other hand, when more cleaning agents are dosed, there will be some cleaning agent residues after cleaning, resulting in waste of cleaning agents and longer cleaning program duration, etc., which affects the operation efficiency of the cleaning equipment and even the industrial production efficiency or the user experience in life. Therefore, how to reasonably dose the cleaning agent is a technical problem that needs to be solved urgently by those skilled in the art. Summary of the Invention

[0004] The purpose of the embodiments of this application is to provide an adaptive dosing method, device, cleaning equipment and medium for a cleaning agent, aiming to solve the problems of poor cleaning effect or long cleaning program caused by improper use of cleaning agents. Through the adaptive dosing of the cleaning agent, the cleaning agent can be additionally dosed according to the dirt condition of the items to be cleaned, which can not only ensure the cleaning effect, but also avoid additional operations caused by excessive cleaning agents, improve the cleaning effect of the cleaning equipment, and enhance the user experience.

[0005] In the first aspect, the embodiments of this application provide an adaptive dosing method for a cleaning agent, and the method includes:

[0006] Identify the material parameters and weight parameters of the item to be cleaned, and determine the first dosing amount of the cleaning agent;

[0007] After the first dosing is completed, continuously monitor the turbidity inside the cleaning equipment within a preset duration of performing the washing operation, obtain turbidity data, and draw a turbidity data curve;

[0008] Input the turbidity data curve into a pre-constructed cleaning agent control model to obtain the second dosing amount of the cleaning agent;

[0009] Perform the second dosing of the cleaning agent according to the second dosing amount;

[0010] While keeping the total cleaning duration unchanged, modify the duration of each cleaning procedure during the cleaning process according to the time point of the second detergent delivery.

[0011] Furthermore, input the turbidity data curve into a pre-constructed detergent control model to obtain the second detergent delivery amount, including:

[0012] Input the turbidity data curve into a pre-constructed detergent control model, and extract the growth rate feature and / or increment feature of the turbidity data curve within a preset duration through the detergent control model;

[0013] The detergent control model outputs an additional coefficient of the detergent according to the growth rate feature and / or increment feature, so as to determine the second detergent delivery amount according to the additional coefficient and the first delivery amount.

[0014] Furthermore, input the turbidity data curve into a pre-constructed detergent control model to obtain the second detergent delivery amount, including:

[0015] Input the turbidity data curve into a pre-constructed detergent control model, and extract the growth rate change value of each observation period of the turbidity data curve within a preset duration through the detergent control model;

[0016] When the growth rate peak of the growth rate change value exceeds a first threshold and the growth rate decline speed of the growth rate change value is less than a second threshold, it is determined that additional delivery is required, and the second detergent delivery amount is determined according to the growth rate peak and the growth rate decline speed.

[0017] Furthermore, before inputting the turbidity data curve into a pre-constructed detergent control model to obtain the second detergent delivery amount, the method further includes:

[0018] Input the material parameters and weight parameters of the item to be cleaned into the detergent control model to configure the calculation parameters of the detergent control model.

[0019] Furthermore, the construction process of the detergent control model includes:

[0020] Obtain the material parameters and weight parameters of the item to be cleaned in historical cleaning operations, the historical delivery amounts of the detergents used, and use the cleaning effect evaluation after the historical cleaning operations as labels to construct a sample set;

[0021] Input the sample set into the basic model to train the basic model and obtain a cleaner control model; wherein, the cleaner control model is used to output the basic dosage of the cleaner corresponding to each material parameter and weight parameter, and an additional coefficient, and the additional coefficient is used to determine the additional dosage.

[0022] Further, the cleaner is stored in the form of a cleaner magazine;

[0023] After determining the first dosage of the cleaner, determine the number of cleaner encapsulated marbles to be dispensed according to the first dosage for the first dispensing;

[0024] After determining the second dosage of the cleaner, determine the number of cleaner encapsulated marbles to be dispensed according to the second dosage for the second dispensing.

[0025] Further, the method further includes:

[0026] When it is monitored that the number of remaining cleaner encapsulated marbles in the cleaner magazine is less than the set number, send a cleaner encapsulated marble replenishment prompt message to the client associated with the cleaning device.

[0027] In a second aspect, an embodiment of the present application provides an adaptive dispensing device for a cleaner, and the device includes:

[0028] A first dosage determination module, configured to identify the material parameter and weight parameter of the item to be cleaned and determine the first dosage of the cleaner;

[0029] A turbidity data monitoring module, configured to continuously monitor the turbidity inside the cleaning device within a preset duration of performing a washing operation after the first dispensing, obtain turbidity data, and draw a turbidity data curve;

[0030] A second dosage determination module, configured to input the turbidity data curve into a pre-constructed cleaner control model to obtain the second dosage of the cleaner;

[0031] An additional dispensing module, configured to perform a second dispensing of the cleaner according to the second dosage;

[0032] A cleaning program duration reallocation module, configured to modify the duration of each cleaning program during the cleaning process according to the time point of the second dispensing while keeping the total cleaning duration unchanged.

[0033] In a third aspect, an embodiment of the present application provides an electronic device, which includes a processor, a memory, and a program or instruction stored on the memory and executable on the processor. When the program or instruction is executed by the processor, the steps of the method described in the first aspect are implemented.

[0034] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instructions are stored, and when the program or instructions are executed by a processor, the steps of the method described in the first aspect are implemented.

[0035] In a fifth aspect, an embodiment of the present application provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor, and the processor is configured to run a program or instructions to implement the method described in the first aspect.

[0036] In an embodiment of the present application, the material parameters and weight parameters of the item to be cleaned are identified to determine the first dosage of the cleaning agent; after the first dosage is completed, the turbidity inside the cleaning device is continuously monitored within a preset duration of the washing operation to obtain turbidity data, and a turbidity data curve is plotted; the turbidity data curve is input into a pre-constructed cleaning agent control model to obtain the second dosage of the cleaning agent; the cleaning agent is secondarily dosed according to the second dosage; and the duration of each cleaning program during the cleaning process is modified according to the time point of the second dosage while keeping the total cleaning duration unchanged. The above-described method for adaptively dosing the cleaning agent can, through real-time monitoring and analysis of the turbidity data in some stages of the washing process, add additional dosing of the cleaning agent according to the dirt condition of the item to be cleaned, which can not only ensure the cleaning effect but also avoid additional operations caused by excessive cleaning agent, improve the cleaning effect of the cleaning device, and enhance the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 is a schematic flowchart of the method for adaptively dosing the cleaning agent provided in Embodiment 1 of the present application;

[0038] Figure 2 is a schematic flowchart of the method for adaptively dosing the cleaning agent provided in Embodiment 2 of the present application;

[0039] Figure 3 is a schematic structural diagram of the device for adaptively dosing the cleaning agent provided in Embodiment 3 of the present application;

[0040] Figure 4 is a schematic structural diagram of the cleaning device provided in Embodiment 4 of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0041] To make the objectives, technical solutions, and advantages of this application clearer, the following further describes the specific embodiments of this application in detail with reference to the accompanying drawings. It can be understood that the specific embodiments described herein are only for explaining this application and not for limiting this application. Additionally, it should be noted that for ease of description, only the parts related to this application rather than all the content are shown in the drawings. Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe the operations (or steps) as sequential processes, many of the operations can be implemented in parallel, concurrently, or simultaneously. In addition, the order of the operations can be rearranged. When the operations are completed, the process can be terminated, but there can also be additional steps not included in the drawings. The process can correspond to a method, function, procedure, subroutine, subprogram, etc.

[0042] The following will clearly describe the technical solutions in the embodiments of this application with reference to the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are some but not all of the embodiments of this application. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art belong to the scope of protection of this application.

[0043] The terms "first", "second", etc. in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of this application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are generally of the same category, and the number of objects is not limited. For example, the first object can be one or multiple. In addition, "and / or" in the specification and claims means at least one of the connected objects, and the character " / " generally indicates an "or" relationship between the associated objects before and after.

[0044] The following, with reference to the accompanying drawings, through specific embodiments and their application scenarios, details the self-adaptive dosing method, device, cleaning equipment, and medium of the cleaner provided in the embodiments of this application.

[0045] Embodiment 1

[0046] Figure 1 is a schematic flowchart of the self-adaptive dosing method of the cleaner provided in Embodiment 1 of this application. As Figure 1 shown, it specifically includes the following steps:

[0047] S101, identify the material parameters and weight parameters of the item to be cleaned, and determine the first dosing amount of the cleaner;

[0048] First, this application is applicable to industrial cleaning scenarios or the usage scenarios of household cleaning equipment. Based on the above usage scenarios, it can be understood that the execution entity of this application can be the main control PC (Printed Circuit) board. Specifically, the determination of the unit dosage and the target dosage of the cleaning agent, as well as the generation of the cleaning agent dosing instruction, etc., can be executed by the main control PC board, and the cleaning equipment executes the cleaning agent dosing instruction according to the target dosage of the cleaning agent to meet the cleaning requirements.

[0049] The cleaning equipment is a device used for cleaning operations and can be equipped with advanced sensing and control technologies, such as industrial cleaning equipment, washing machines, and dishwashers.

[0050] Among them, the items to be cleaned can include various objects that need to be cleaned, such as electronic devices, including wafers, plastic parts, metal parts, glass products, etc., clothing, including textiles made of natural fibers such as cotton, linen, and wool, and chemical fibers such as polyester and nylon, and tableware, including tableware items made of materials such as ceramics, glass, stainless steel, and plastic, and household items, including wooden tables and chairs, leather sofas, etc.

[0051] The material parameters can be obtained by means of a multi-spectral fusion detection array and include the chemical composition of the item. For example, through micro X-ray photoelectron spectroscopy detection, such as the chemical composition elements and ratios of clothing fibers, scanned with an atomic force microscope to analyze physical structures such as the thickness and arrangement of fibers and the density of fabrics, using a millimeter-wave resonant cavity to measure water absorption, detecting surface smoothness with a surface roughness meter, and analyzing surface characteristics such as hydrophilicity or hydrophobicity of the item.

[0052] The weight parameter can be obtained by using weight measurement technology, which can obtain the overall mass of the item and also the dynamic load distribution. For large or irregular items, it can more accurately reflect their weight information.

[0053] The first dosage can be the basic dosage of the cleaning agent obtained by mapping and calculating the material characteristics and weight characteristics based on a neural network.

[0054] This technical solution can utilize multi-modal sensor fusion technology, such as combining laser-induced breakdown spectroscopy and terahertz time-domain spectroscopy for non-contact detection, and analyze and classify the acquired data using artificial intelligence algorithms to determine the material parameters and weight parameters of the items to be cleaned. Input the identified parameters into a pre-established cleaning agent dosage calculation model, and calculate the first dosage of the cleaning agent through the model.

[0055] S102, after the first dosing is completed, continuously monitor the turbidity inside the cleaning equipment within the preset duration of the washing operation to obtain turbidity data and draw a turbidity data curve;

[0056] Among them, the first dosing can be an operation of dosing a cleaning agent into a cleaning device using an intelligent dosing device according to the first dosing amount determined in S101.

[0057] The washing operation can be a cleaning action performed by the cleaning device according to a preset program and mode, such as the agitation, tumbling, spraying, etc. of a washing machine, or the water spraying and rinsing of a dishwasher, etc., to remove stains on the items to be cleaned by means of the action of water flow and the cleaning agent. It can be understood that the washing operation is often a relatively early operation in the cleaning process of the items to be cleaned and is a key link for removing dirt on the items to be cleaned. During this process, the turbidity can be monitored, and additional dosing of the cleaning agent can be performed when necessary to ensure the cleaning effect.

[0058] In this solution, the preset duration can be a washing time length obtained by dynamically adjusting according to different cleaning tasks and item types, such as the first 1 / 5 of the entire washing duration. For example, the washing duration of lightly soiled clothes may be 20 minutes, and the preset duration can be the first 4 minutes; the preset duration for washing heavily soiled tableware may be 30 minutes, and the preset duration can be the first 6 minutes.

[0059] The turbidity can represent the content of impurities, stain particles, etc. in the liquid inside the cleaning device. The turbidity is quantified by a multi-wavelength transmittance matrix, such as synchronous acquisition of 650nm / 850nm dual frequencies, and real-time monitoring of the change in the refractive index of the fluid by an optical fiber Bragg grating array.

[0060] The turbidity data is the data obtained by measuring the turbidity inside the cleaning device, such as the multi-wavelength transmittance values and refractive index change values at different time points.

[0061] The turbidity data curve can be a curve with time as the abscissa and turbidity data as the ordinate, constructed to visually display the change in the turbidity inside the cleaning device over time during the washing process, and can reflect the turbidity fluctuation characteristics at different scales.

[0062] In this technical solution, when the cleaning device is started, washing operations can be carried out according to preset programs and modes, using technologies such as motor drive and water flow control. After accurately dispensing the cleaning agent into the cleaning device through the intelligent dispensing device according to the first dispensing amount, a multi-physical field sensing system is used. For example, a dual-frequency laser interferometer penetrates the liquid to detect the particle movement speed, and a fiber Bragg grating array monitors the refractive index change to continuously measure and observe the turbidity inside the cleaning device. Data is collected by sensors and processed, such as filtering, amplification, and digital conversion, to obtain turbidity data representing the turbidity. Furthermore, data processing software can be used to draw a turbidity data curve based on the obtained turbidity data and time information.

[0063] S103. Input the turbidity data curve into a pre-constructed cleaning agent control model to obtain the second dispensing amount of the cleaning agent.

[0064] The cleaning agent control model can be a model constructed based on a temporal convolutional network with attention mechanism (TCN-Attention), which integrates prior knowledge of fluid dynamics. Through training and optimization with a large amount of experimental data, it can analyze and judge the amount of cleaning agent that still needs to be dispensed under the current washing state based on information such as the input turbidity data curve.

[0065] The second dispensing amount is the amount of cleaning agent that needs to be dispensed again after analysis and calculation of the turbidity data curve by the cleaning agent control model.

[0066] This solution can transmit the characteristics of the processed turbidity data curve to the cleaning agent control model as input parameters for model calculation. The cleaning agent control model analyzes the characteristics of the input processed turbidity data curve. For example, an adversarial generative network can be used to simulate the turbidity evolution path under different dispensing amounts, combined with the dynamic tracking of the critical micelle concentration of surfactants, and output the second dispensing amount of the cleaning agent.

[0067] S104. Dispense the cleaning agent for the second time according to the second dispensing amount.

[0068] The second dispensing amount is the amount of cleaning agent that needs to be dispensed again after model calculation in S103 and considering various factors. According to the second dispensing amount, the cleaning agent is dispensed again into the cleaning device using intelligent dispensing technology.

[0069] In this solution, by adding and dispensing the cleaning agent in the cleaning device, the corresponding amount of cleaning agent is evenly dispensed into the liquid inside the cleaning device, which can complete the adaptive dispensing of the cleaning agent. Even when the weight of the items to be cleaned is the same, for different degrees of dirtiness, different doses of cleaning agent can be adaptively dispensed to ensure the cleaning effect.

[0070] S105. While keeping the total cleaning duration unchanged, modify the durations of the respective cleaning procedures during the cleaning process according to the time point of the second dosing.

[0071] Among them, the total cleaning duration can be the total time length required to complete the entire cleaning task set in advance. This duration is determined by comprehensively considering various factors such as the type of the item to be cleaned, the degree of stains, and the performance of the cleaning equipment. For example, for washing ordinary clothes, the total cleaning duration of the washing machine may be set to 40 minutes; for washing tableware with heavy oil stains, the total cleaning duration of the dishwasher may be set to 60 minutes.

[0072] The respective cleaning procedures during the cleaning process can be a series of steps or stages with different functions performed by the cleaning equipment during the cleaning task. Taking the washing machine as an example, it may include procedures such as pre-washing, main washing, rinsing, and dehydration; for the dishwasher, it may have procedures such as pre-rinsing, main washing, spray rinsing, and drying. Each procedure has its specific role and purpose, and they work together to complete the cleaning task.

[0073] The duration modification can be to adjust and change the time lengths allocated to the respective cleaning procedures during the cleaning process. Since the time points of the second dosing of the cleaning agent are different, in order to reasonably utilize the cleaning agent and achieve the best cleaning effect while keeping the total cleaning duration unchanged, it is necessary to make corresponding modifications to the durations of the respective cleaning procedures.

[0074] This solution can ensure that the total time length from the start to the end of the entire cleaning task does not change through the control system of the cleaning equipment after the second dosing of the cleaning agent. The control system will manage and control the subsequent cleaning operations according to the preset total cleaning duration parameter to maintain the stability of the total cleaning duration. Specifically, the control system of the cleaning equipment determines how to adjust the durations of the respective cleaning procedures during the cleaning process based on the specific time point of the second dosing of the cleaning agent. For example, it provides an important reference basis for the duration modification according to the progress of stain dissolution and cleaning during the cleaning process. The control system of the cleaning equipment redistributes the durations of the respective cleaning procedures during the cleaning process according to certain algorithms and rules. For example, if the second dosing time is relatively late, the duration of the rinsing procedure may be appropriately shortened, while the duration of the remaining part of the main washing procedure may be increased to ensure that the cleaning agent can fully play its role; if the second dosing time is relatively early, the durations of multiple subsequent procedures may be finely adjusted to balance the action time of the cleaning agent and the overall cleaning effect. During the modification process, the control system will monitor and adjust the execution times of the respective cleaning procedures in real time to ensure that the total cleaning duration remains unchanged.

[0075] This solution can modify the duration of each cleaning program during the cleaning process according to the time point of the second detergent injection while keeping the total cleaning duration unchanged. First of all, this solution can respond more flexibly to the actual situation during the cleaning process. Since different items to be cleaned and stain conditions may lead to different time points for the second detergent injection, by dynamically adjusting the duration of each cleaning program, the detergent can play its role at the best time, improving the cleaning effect. For example, in the case of heavy stains and a late second detergent injection, extending the main washing time can allow the detergent more time to remove the stains. Secondly, this method ensures the cleaning efficiency and does not extend the entire cleaning time due to the second detergent injection, meeting the user's demand for cleaning timeliness. At the same time, reasonable duration modification can also optimize the energy consumption of the cleaning equipment, avoid unnecessary energy waste, and improve the energy utilization efficiency of the equipment. In addition, it enhances the intelligence level of the cleaning equipment, making the cleaning process more scientific and reasonable, and improving the user's usage experience and satisfaction.

[0076] In the embodiment of the present application, the material parameters and weight parameters of the item to be cleaned are identified to determine the first injection amount of the detergent; after the first injection is completed, the turbidity inside the cleaning equipment is continuously monitored within the preset duration of the washing operation to obtain turbidity data and draw a turbidity data curve; the turbidity data curve is input into a pre-constructed detergent control model to obtain the second injection amount of the detergent; the detergent is injected for the second time according to the second injection amount; during the period of keeping the total cleaning duration unchanged, the duration of each cleaning program during the cleaning process is modified according to the time point of the second injection. This technical solution can realize the intelligent and precise control of detergent injection and achieve the purpose of adaptive injection. By accurately identifying the material and weight of the item to be cleaned to determine the first injection amount, the waste and shortage of the detergent are avoided. During the washing process, advanced sensing technology is used to monitor the turbidity in real time and draw a curve with multi-scale characteristics, providing data for the detergent control model. Through the detergent control model, the second injection amount can be accurately obtained and the detergent can be additionally injected. The overall solution improves the cleaning effect, reduces the usage amount of the detergent, lowers the cost, is more environmentally friendly at the same time, and can adapt to different types and pollution levels of items to be cleaned, performing reasonable injection amount control and improving the accuracy and adaptability of detergent injection.

[0077] In one embodiment, optionally, inputting the turbidity data curve into a pre-constructed detergent control model to obtain the second injection amount of the detergent includes:

[0078] Input the turbidity data curve into a pre-constructed detergent control model, and extract the growth rate feature and / or increment feature of the turbidity data curve within the preset duration through the detergent control model;

[0079] The cleaning agent control model outputs an additional coefficient of the cleaning agent according to the growth rate feature and / or the increment feature, so as to determine the second dosage of the cleaning agent according to the additional coefficient and the first dosage.

[0080] Among them, the growth rate feature may refer to the relevant feature of the change speed of the turbidity data curve within a preset time period. For example, the slope of a certain point on the curve can be used to represent the change speed of that point. The larger the slope, the faster the change speed, which reflects how fast the turbidity changes with time. For example, during the washing process, if the growth rate is large, it means that the stains are quickly dissolved in water in a short time, which may mean that there are more stains or the cleaning difficulty is greater; on the contrary, if the growth rate feature is small, it means that the stain dissolution speed is slow. The growth rate feature, such as the average growth rate and the maximum growth rate, can be analyzed by performing a derivative operation on the turbidity data curve to obtain the change rate at different time points.

[0081] The increment feature may refer to the relevant feature of the increase in the value of the turbidity data curve within a preset time period. It reflects the overall change range of the turbidity during the entire preset time period. For example, a larger increment feature indicates that more stains are immersed in the water within the preset time period, and the increase in turbidity during the cleaning process is obvious; a smaller increment feature means that relatively fewer stains are washed out. The increment feature can be obtained by calculating the difference in turbidity data between the starting moment and the ending moment within a set time period, such as 1 second, and the increment distribution within different time periods.

[0082] The additional coefficient may be a coefficient calculated by the cleaning agent control model according to the growth rate feature and / or the increment feature. This coefficient is used to adjust the first dosage to determine the second dosage. If the additional coefficient is greater than 1, it means that the dosage of the cleaning agent needs to be increased on the basis of the first dosage; if the additional coefficient is less than 1, it may indicate that no additional dosage is required or the dosage should be appropriately reduced. For example, an appropriate amount can be precipitated. Specifically, on the basis of the original amount of liquid in the cleaning device, the injection amount of water can be increased. After the cleaning device continues to operate for a certain duration or a certain number of times, the corresponding amount of water with the cleaning agent is discharged, so as to achieve the effect of reducing the dosage. For example, 2L of water is injected during the washing process, and after the cleaning device rotates 5 times, or rotates for 30 seconds, 2L of water is discharged. In addition, if the additional coefficient is equal to 1, it means that no adjustment is made according to the first dosage.

[0083] As described above, the cleaning agent control model can be trained using technologies such as machine learning or deep learning, combined with a large amount of experimental data and cleaning knowledge. The model can analyze the input turbid data curve, extract the growth rate features and / or increment features therein, and calculate the additional coefficient based on these features. The model can adopt architectures such as the Temporal Convolutional Network with Attention Mechanism (TCN-Attention) to integrate the prior knowledge of fluid field dynamics, so as to improve the understanding and prediction ability of the cleaning process.

[0084] This solution can use the cleaning agent control model to extract the growth rate features and / or increment features from the input turbid data curve. For the extraction of the growth rate features of the turbid data, specifically, the numerical change of the curve within a preset time period can be found through methods such as data comparison and statistical analysis. Furthermore, the internal feature extraction layer can be used to automatically learn and extract these features, and the attention mechanism is combined to highlight the important feature information. After the cleaning agent control model completes the analysis of the growth rate features and / or increment features, it calculates the additional coefficient according to the preset rules and algorithms, and outputs it as a result. This process involves parameter operations and logical judgments within the model. For example, according to different combinations of growth rates and increments, the corresponding additional coefficient is obtained through a pre-trained mapping relationship. According to the additional coefficient output by the cleaning agent control model and the previously determined first dosage, the second dosage of the cleaning agent is calculated through simple mathematical operations. For example, it is calculated using the following formula:

[0085] Second dosage = First dosage × Additional coefficient;

[0086] In this way, the accurate quantity of the cleaning agent that needs to be additionally added after the first dosage is determined.

[0087] In this technical solution, by extracting the growth rate features and / or increment features of the turbid data curve and using the cleaning agent control model to calculate the additional coefficient to determine the second dosage, the dynamic adjustment of the cleaning agent dosage is realized. Compared with the traditional fixed dosage method, it can more accurately supplement the cleaning agent according to the actual stain situation during the cleaning process. When there are more stains and the dissolution speed is fast, the cleaning agent dosage is increased in a timely manner to ensure the cleaning effect; when there are fewer stains and the dissolution speed is slow, excessive dosing of the cleaning agent is avoided, reducing the waste of the cleaning agent, lowering the cost, and being more environmentally friendly. Moreover, this real-time adjustment method based on actual cleaning data improves the intelligence level and adaptability of the cleaning process, can handle different types and degrees of pollution of items to be cleaned, and ensures the cleaning effect.

[0088] In one embodiment, optionally, inputting the turbid data curve into a pre-constructed cleaning agent control model to obtain the second dosage of the cleaning agent includes:

[0089] Inputting the turbidity data curve into a pre-built detergent control model, and extracting the growth rate change value of the turbidity data curve in each observation period within a preset time period through the detergent control model;

[0090] When the growth rate peak value of the growth rate change value exceeds the first threshold value and the growth rate fallback speed of the growth rate change value is less than the second threshold value, it is determined that additional dosage is required, and the second dosage amount of the detergent is determined according to the growth rate peak value and the growth rate fallback speed.

[0091] The observation period can be a smaller time interval divided within the preset time, which is used for more detailed analysis of the turbidity data curve. For example, if the preset time is 5 minutes, every 10 seconds or 30 seconds can be used as an observation period to more accurately capture the changes in turbidity in different time periods. Different observation period lengths can be reasonably set according to the characteristics of the cleaning task and the performance of the cleaning equipment.

[0092] The growth rate change value may refer to the change in the rate of increase of turbid objects in the turbidity data curve in each observation period. It reflects the difference in the rate of increase of turbid objects between adjacent observation periods. For example, the rate of increase of turbid objects in the previous observation period is 5 units per minute, and the rate of increase of turbid objects in the current observation period is 3 units per minute, then the change in the rate of increase of turbid objects is -2 units, which means that the growth rate is decreasing. The growth rate change value is obtained by calculating the difference in the growth rates of adjacent observation periods.

[0093] The growth rate peak value can be the maximum value reached by the growth rate of the turbidity data curve within a preset time period. It indicates the moment when the turbidity increases fastest in a certain period of time during the entire cleaning process. For example, in the process of washing clothes, the turbidity may increase rapidly in a certain period of time due to the dissolution of a large amount of stains. The growth rate at this time is the growth rate peak value. By comparing and analyzing the growth rates of each observation period, the maximum value is found to be the growth rate peak value.

[0094] The first threshold value may be a pre-set numerical standard for determining whether the peak value of the growth rate is too high. When the peak value of the growth rate exceeds the first threshold value, it indicates that the turbidity level is increasing too fast, that is, there may be more stains on the items to be cleaned. In this case, additional detergent may be added. The specific value of the first threshold value may be reasonably set according to factors such as the type of cleaning equipment, the performance of the detergent, and the stain conditions of common items to be cleaned.

[0095] The speed of the growth rate decline can refer to the speed at which the growth rate of the turbidity data curve decreases after reaching its peak. It reflects how quickly the decline occurs after the stain dissolution speed reaches its maximum. For example, if the growth rate peak is an increase of 10 units per minute and then it decreases by 2 units per minute, the speed of the growth rate decline is 2 units per minute. The speed of the growth rate decline is determined by calculating the change in the growth rate during adjacent observation periods after the peak value.

[0096] The second threshold can be a pre-set numerical criterion used to determine whether the speed of the growth rate decline is too slow. When the speed of the growth rate decline is less than the second threshold, it indicates that although the turbidity level starts to decrease, the rate of decrease is slow, and additional detergent may still need to be added to ensure the cleaning effect. The setting of the second threshold also needs to comprehensively consider various factors, such as the working mode of the cleaning equipment and the cleaning efficiency of the detergent.

[0097] In this solution, during the cleaning process, the turbidity data curve obtained by real-time monitoring and mapping through the multi-physical field sensing system is transmitted to the pre-constructed detergent control model. The detergent control model uses corresponding algorithms to analyze the input turbidity data curve and calculate the change value of the growth rate for each observation period within a preset time duration. When the change value of the growth rate satisfies the two conditions that the growth rate peak exceeds the first threshold and the speed of the growth rate decline is less than the second threshold, it is concluded that additional detergent needs to be added. At the same time, according to the specific values of the growth rate peak and the speed of the growth rate decline, through pre-set calculation rules or algorithms, the second dosage of the detergent is determined. For example, a mathematical model can be established, taking the growth rate peak and the speed of the growth rate decline as input parameters, and after a series of operations, the second dosage is output. This determination process is an intelligent decision-making by the model based on the actual data and preset rules during the cleaning process.

[0098] In this technical solution, by analyzing the change value of the growth rate for each observation period within a preset time duration of the turbidity data curve, combined with the judgment conditions of the growth rate peak and the speed of the growth rate decline, it is possible to more accurately determine whether additional detergent needs to be added and to determine the additional dosage. This method fully considers the dynamic changes in stain dissolution during the cleaning process, avoiding the limitations of judgment based on a single indicator. When the growth rate peak is too high and the speed of the growth rate decline is too slow, additional detergent is added in a timely manner to ensure that the stains can be effectively removed, improving the cleaning effect. At the same time, unnecessary detergent dosing is avoided, reducing detergent waste and usage costs. Also, the cleaning effect of the cleaning tasks of the cleaning equipment is improved, realizing the adaptive dosing of the detergent.

[0099] In one embodiment, optionally, before inputting the turbidity data curve into the pre-constructed detergent control model to obtain the second dosage of the detergent, the method further includes:

[0100] Input the material parameters and weight parameters of the item to be cleaned into the cleaning agent control model to configure the calculation parameters of the cleaning agent control model.

[0101] Among them, the calculation parameters can be various numerical values based on which the cleaning agent control model performs operations. These parameters can be stored in a set location and extracted and used when needed. The calculation parameters will affect the turbidity data curve and the second dosage output by the cleaning agent control model. The calculation parameters may include the cleaning coefficient corresponding to different materials and weights, the relationship coefficient between the stain dissolution rate and the cleaning agent dosage, the weight coefficient for different observation periods, etc. They are important bases for the model to perform mathematical operations and logical judgments internally.

[0102] This solution can transmit the obtained material parameters and weight parameters of the item to be cleaned to the cleaning agent control model in a specific data format, such as digital coding, vector representation, etc. After receiving the material parameters and weight parameters of the item to be cleaned, the cleaning agent control model adjusts and sets its own calculation parameters according to this information. For example, if the item to be cleaned is cotton and has a large weight, the model will increase the corresponding cleaning coefficient according to the pre-learned knowledge to increase the calculated value of the cleaning agent dosage; if it is a chemical fiber material and has a light weight, the relevant coefficient may be decreased. The configuration process is a process in which the model dynamically adjusts its own operation rules according to the input new information to ensure that the second dosage of the cleaning agent suitable for the current item to be cleaned can be calculated more accurately.

[0103] In this technical solution, by inputting the material parameters and weight parameters of the item to be cleaned into the cleaning agent control model and configuring the calculation parameters, the cleaning agent control model can fully consider the individual differences of the item to be cleaned. Different materials have different requirements and reactions to the cleaning agent, and different weights also have different requirements for the cleaning agent dosage, and perform adaptive control. Through this configuration, the second dosage of the cleaning agent can be calculated more accurately. Compared with the fixed calculation method that does not consider these factors, this solution can avoid waste and environmental pollution caused by excessive cleaning agent dosage, and at the same time prevent the problem of poor cleaning effect due to insufficient dosage. It improves the efficiency of cleaning agent use and ensures the cleaning effect.

[0104] Embodiment 2

[0105] Figure 2It is a schematic flowchart of the adaptive dispensing method of the cleaning agent provided in the second embodiment of the present application. This solution makes a better improvement to the above embodiment. The specific improvement is as follows: The construction process of the cleaning agent control model includes: obtaining the material parameters and weight parameters of the item to be cleaned in the historical cleaning operation, the historical dispensing amount of the cleaning agent used, and using the cleaning effect evaluation after the historical cleaning operation is completed as a label to construct a sample set; inputting the sample set into the basic model to train the basic model to obtain a cleaning agent control model; wherein, the cleaning agent control model is used to output the basic dispensing amount of the cleaning agent corresponding to each material parameter and weight parameter and an additional coefficient, and the additional coefficient is used to determine the additional dispensing amount. As Figure 2 shown, it specifically includes the following steps:

[0106] S201, obtain the material parameters and weight parameters of the item to be cleaned in the historical cleaning operation, the historical dispensing amount of the cleaning agent used, and use the cleaning effect evaluation after the historical cleaning operation is completed as a label to construct a sample set;

[0107] Among them, the historical cleaning operation can refer to various completed cleaning tasks, such as industrial equipment cleaning or household daily cleaning, etc. At the same time, the historical cleaning operation can also include cleaning operations on different cleaning objects, such as mechanical parts, clothes, and tableware. These operations record various data and situations in the actual cleaning process.

[0108] The label can be manually marked by the staff and can be used as the target value of supervised learning during the machine learning process. In this solution, the cleaning effect evaluation after the historical cleaning operation is used as a label, which is a quantitative index reflecting the quality of the cleaning result. For example, the cleaning degree can be represented by scores from 0 to 100, and the higher the score, the better the cleaning effect. Or, a score below 10 represents a poor cleaning effect caused by insufficient cleaning agent, and reaching 10 means the best cleaning degree. Then, scores from 10 to 20 represent the situation where there is residue of the cleaning agent due to excessive cleaning agent, and reaching 20 means there is more residue of the cleaning agent, which affects the subsequent use of the item and requires re - rinsing or bleaching.

[0109] The sample set can be a set composed of multiple samples, and each sample includes the material parameters, weight parameters of the item to be cleaned, the historical dispensing amount of the cleaning agent, and the corresponding cleaning effect evaluation. The sample set is the basic data for training the model, and its quality and quantity will affect the performance of the model.

[0110] This solution can utilize a big data storage system and data mining techniques to collect information. Specifically, it can extract data on historical cleaning operations from the built-in log recording system of the cleaning device, or obtain relevant data from the cloud database. By using a data acquisition interface and a data transmission protocol, it ensures accurate and complete acquisition of information such as the material parameters, weight parameters of the item to be cleaned, and the historical dosage of the cleaning agent. After obtaining the relevant information, data preprocessing techniques can be used to clean, transform, and integrate the acquired data to remove noise and outliers in the data, and uniformly convert data in different formats into a format suitable for model processing.

[0111] S202, input the sample set into the basic model to train the basic model and obtain a cleaning agent control model; wherein, the cleaning agent control model is used to output the basic dosage of the cleaning agent corresponding to each material parameter and weight parameter, and an additional coefficient, and the additional coefficient is used to determine the additional dosage.

[0112] Among them, the basic model is a pre-designed machine learning model framework. For example, it can be a multilayer perceptron (MLP), convolutional neural networks (CNN), or decision tree model, etc. in deep learning. The basic model has a certain structure and parameters, but has not been trained for the problem of cleaning agent dosage, and needs to be learned and optimized through a sample set.

[0113] The basic dosage can be calculated by the model based on the material parameters and weight parameters of the item to be cleaned, and is the initially determined cleaning agent dosage at the beginning of the cleaning operation. It can be a reasonable initial value obtained based on historical data and the rules learned by the model.

[0114] The additional coefficient can be a coefficient used to adjust the cleaning agent dosage. During the cleaning process, according to the actual situation, such as the change in turbidity inside the cleaning device, the additional coefficient can be used to determine whether it is necessary to additionally add a cleaning agent on the basis of the basic dosage and the specific quantity to be added.

[0115] This solution can use the data loading module to deliver the constructed sample set to the basic model in a suitable data format. During the input process, it may be necessary to perform further preprocessing on the data, such as normalization, standardization, etc., to improve the training effect of the model. After receiving the sample set, the basic model uses optimization algorithms, such as stochastic gradient descent, Adam optimizer, etc., to continuously adjust its own parameters. Through multiple iterations, the error between the predicted values of the detergent dosage and the cleaning effect output by the model and the labels in the sample set gradually decreases, thereby learning the mapping relationship between the input data and the output results. When the training of the model reaches a certain convergence standard, such as the error is within an acceptable range, the training process ends, and at this time, the basic model is transformed into a detergent control model.

[0116] The technical solution provided in this embodiment constructs a sample set by collecting data on historical cleaning operations and trains a basic model to obtain a detergent control model. The detergent control model can accurately output the basic dosage and additional coefficient of the detergent according to the material and weight of the item to be cleaned. This solution realizes the intelligence and precision of detergent dosing, avoiding the problems of excessive or insufficient detergent dosing in traditional cleaning methods. And through the use of the detergent control model, the adaptive dosing of the detergent can be realized, reducing the workload of the staff and improving the cleaning efficiency.

[0117] Based on the above embodiments, optionally, the detergent is stored in the form of a detergent magazine;

[0118] After determining the first dosage of the detergent, determine the number of detergent encapsulated marbles to be dispensed according to the first dosage for the first dispensing;

[0119] After determining the second dosage of the detergent, determine the number of detergent encapsulated marbles to be dispensed according to the second dosage for the second dispensing.

[0120] Among them, a detergent magazine is a device for storing detergent, and its structure is similar to a box-shaped magazine that can eject detergent encapsulated marbles. It can be designed in various shapes and specifications and is usually made of durable materials, such as high-strength plastic or metal, and can hold a certain amount of detergent. The detergent magazine can be easily installed on the cleaning equipment and can cooperate with the dispensing system of the equipment to achieve accurate dispensing of the detergent. For example, in a washing machine, the detergent magazine may be installed in the position of the detergent box to facilitate the cleaning equipment to extract detergent encapsulated marbles as needed.

[0121] Cleaning agent encapsulated marbles can be made by encapsulating cleaning agents in small marble-shaped containers. These marble containers can be made of dissolvable or breakable materials, such as special water-soluble plastics or gel materials. Each marble contains a certain amount of cleaning agent, and its dosage is a pre-determined standard value. For example, each marble may contain 5 milliliters of cleaning agent, which is convenient for determining the number of marbles to be used according to the required dosage.

[0122] The first dosage is the amount of cleaning agent that needs to be dispensed at the start of cleaning, calculated through a cleaning agent control model based on information such as the material parameters and weight parameters of the item to be cleaned. It is the value of the first cleaning agent dosage during the cleaning process.

[0123] The second dosage is the amount of cleaning agent that needs to be re-dispensed during the cleaning process, further calculated through the cleaning agent control model based on subsequent monitoring data such as the turbidity level inside the cleaning device. It is the value of the additional cleaning agent dosage after the first dispensing.

[0124] This solution stores the cleaning agent by using a cleaning agent magazine. During the design and manufacturing process of the cleaning device, it is decided to use a cleaning agent magazine as the storage device for the cleaning agent to achieve orderly storage and convenient dispensing of the cleaning agent. This may involve the evaluation and comparison of different storage methods, and finally it is determined that the cleaning agent magazine is the most suitable choice. Correspondingly, after determining the first dosage, based on the first dosage and the dosage of the cleaning agent contained in each encapsulated marble of the cleaning agent, the number of encapsulated marbles of the cleaning agent to be dispensed is determined through mathematical calculations. For example, if the first dosage is 20 milliliters and each marble contains 5 milliliters of cleaning agent, then the determined number of marbles to be dispensed is 4. Similarly, after determining the second dosage, in the same way, based on the second dosage and the dosage of each marble, the number of encapsulated marbles of the cleaning agent required for the second dispensing is calculated and determined. According to the determined number of encapsulated marbles of the cleaning agent to be dispensed, the corresponding number of marbles is put into the cleaning area inside the cleaning device through the dispensing system of the cleaning device. For example, in a washing machine, marbles may be pushed out of the cleaning agent magazine and sent into the drum of the washing machine through a mechanical device; in a dishwasher, marbles may be transported to the cavity of the dishwasher through a specific pipeline and valve system.

[0125] This technical solution stores and dispenses the cleaning agent by using a cleaning agent magazine and cleaning agent encapsulated marbles, and has various beneficial effects. First, the design of the cleaning agent magazine makes the storage of the cleaning agent more convenient and safe, and can effectively prevent the leakage and volatilization of the cleaning agent. Second, the use of cleaning agent encapsulated marbles enables accurate quantitative dispensing of the cleaning agent. According to the calculated first dispensing amount and second dispensing amount, the number of marbles to be dispensed is accurately determined, avoiding waste or insufficient dispensing of the cleaning agent. This can not only improve the cleaning effect, ensure that the items to be cleaned are fully cleaned, but also save the usage amount of the cleaning agent and reduce the usage cost. In addition, this dispensing method facilitates the automatic control of the cleaning equipment, improves the intelligent level of the cleaning process, and makes the cleaning operation more convenient and efficient.

[0126] Based on the above embodiments, optionally, the method further includes:

[0127] When it is monitored that the number of remaining cleaning agent encapsulated marbles in the cleaning agent magazine is less than the set number, a replenishment prompt message for the cleaning agent encapsulated marbles is sent to the client associated with the cleaning equipment.

[0128] Among them, the remaining cleaning agent encapsulated marbles can be the number of cleaning agent encapsulated marbles that have not been dispensed and used in the cleaning agent magazine and still remain in the magazine. Each cleaning agent encapsulated marble is pre-encapsulated with a certain dose of cleaning agent, and the remaining marble number reflects the amount of cleaning agent available for use in the cleaning agent magazine.

[0129] The set number can be a pre-set threshold value used to determine whether the number of remaining cleaning agent encapsulated marbles in the cleaning agent magazine is small. The setting of this value will comprehensively consider factors such as the usage frequency of the cleaning equipment, the average usage amount of the cleaning agent per cleaning, and the capacity of the cleaning agent magazine. For example, for a commonly used washing machine, the set number may be set to 5. When the remaining marble number is less than 5, it is considered that the cleaning agent needs to be replenished.

[0130] The client can be the user's intelligent terminal device, such as a smart phone, a tablet computer, a smart watch, etc., or a specific application installed on the computer. The client is associated with the cleaning equipment through the network, used to receive various information sent by the cleaning equipment and display it to the user.

[0131] The replenishment prompt message for the cleaning agent encapsulated marbles can be a notification message sent by the cleaning equipment to the client when the number of remaining cleaning agent encapsulated marbles in the cleaning agent magazine is less than the set number. The form of this message can be a text prompt, such as "The number of cleaning agent marbles is insufficient, please replenish in time", a sound reminder or an icon warning, etc. The purpose is to inform the user that the cleaning agent encapsulated marbles need to be replenished in time to ensure the normal use of the cleaning equipment.

[0132] This solution can install sensors in the cleaning device, such as photoelectric sensors, weight sensors, etc., to continuously detect and monitor the number of remaining cleaning agent encapsulated marbles in the cleaning agent magazine. The photoelectric sensor can determine the remaining quantity by detecting the occlusion of the marbles in the magazine, and the weight sensor can estimate the remaining number of marbles by measuring the weight change of the magazine. These sensors will collect data in real time and transmit the data to the control system of the cleaning device for analysis and processing. When the control system of the cleaning device determines that the remaining cleaning agent encapsulated marbles are less than the set quantity based on the data monitored by the sensors, it sends a replenishment reminder message for the cleaning agent encapsulated marbles to the client associated with the cleaning device through the network communication module. The sending process follows a specific communication protocol and data format to ensure that the client can correctly receive and parse the information. This solution can establish a connection between the cleaning device and the client, enabling the two to perform data interaction. Users can bind the cleaning device to the client by operating on the client. This association can be a one-to-one relationship, or a one-to-many or many-to-one relationship, depending on the device design and user needs.

[0133] In this technical solution, by monitoring the number of remaining cleaning agent encapsulated marbles in the cleaning agent magazine and sending a replenishment reminder message to the client when it is less than the set quantity, this technical solution brings many beneficial effects. First of all, it improves the convenience of users using the cleaning device. Users do not need to constantly pay attention to the remaining situation of the cleaning agent magazine. When replenishment is needed, they can receive a prompt in time, avoiding the situation where the cleaning task cannot be completed or the cleaning effect is not good due to insufficient cleaning agent. Secondly, this intelligent monitoring and prompting function helps to optimize the use experience of the cleaning device and improve user satisfaction with the device. From the perspective of device management, it can ensure that the cleaning device is always in a state with sufficient cleaning agent, reducing the situation where the cleaning task cannot be performed due to insufficient cleaning agent.

[0134] Embodiment III

[0135] Figure 3 is a schematic structural diagram of the adaptive dosing device for cleaning agents provided in Embodiment III of the present application. As Figure 3 shown, the device includes:

[0136] A first dosing amount determination module 301, configured to identify the material parameters and weight parameters of the item to be cleaned and determine the first dosing amount of the cleaning agent;

[0137] A turbidity data monitoring module 302, configured to continuously monitor the turbidity inside the cleaning device within a preset duration of the washing operation after the first dosing, obtain turbidity data, and draw a turbidity data curve;

[0138] The second dosage determination module 303 is configured to input the turbidity data curve into a pre-constructed cleaner control model to obtain the second dosage of the cleaner;

[0139] The additional dosage module 304 is configured to perform a second dosage of the cleaner according to the second dosage;

[0140] The cleaning program duration reallocation module 305 is configured to modify the duration of each cleaning program during the cleaning process according to the time point of the second dosage while keeping the total cleaning duration unchanged.

[0141] In the embodiment of the present application, the first dosage determination module is configured to identify the material parameter and weight parameter of the item to be cleaned and determine the first dosage of the cleaner; the turbidity data monitoring module is configured to continuously monitor the turbidity degree inside the cleaning device within a preset duration of performing the washing operation after the first dosage to obtain turbidity data and draw a turbidity data curve; the second dosage determination module is configured to input the turbidity data curve into a pre-constructed cleaner control model to obtain the second dosage of the cleaner; the additional dosage module is configured to perform a second dosage of the cleaner according to the second dosage; the cleaning program duration reallocation module is configured to modify the duration of each cleaning program during the cleaning process according to the time point of the second dosage while keeping the total cleaning duration unchanged. The above-mentioned adaptive dosage device of the cleaner can, through real-time monitoring and analysis of the turbidity data in some stages of the washing, perform additional dosage of the cleaner according to the dirt condition of the item to be cleaned, which can not only ensure the cleaning effect but also avoid additional operations caused by excessive cleaner, improve the cleaning effect of the cleaning device, and enhance the user experience.

[0142] The adaptive dosage device of the cleaner in the embodiment of the present application can be a device, or a component, an integrated circuit, or a chip in a terminal. The device can be a mobile electronic device or a non-mobile electronic device. Exemplarily, the mobile electronic device can be a mobile phone, a tablet computer, a laptop computer, a handheld computer, a vehicle-mounted electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA), etc., and the non-mobile electronic device can be a server, a Network Attached Storage (NAS), a personal computer (PC), a television (TV), a teller machine, or a self-service machine, etc. The embodiment of the present application does not make specific limitations.

[0143] The adaptive dosing device for the cleaning agent in the embodiments of the present application can be a device with an operating system. The operating system can be the Android operating system, the IOS operating system, or other possible operating systems, which are not specifically limited in the embodiments of the present application.

[0144] The adaptive dosing device for the cleaning agent provided in the embodiments of the present application can implement each process achieved in the above-mentioned Embodiments 1 to 4. To avoid repetition, it will not be elaborated here.

[0145] Embodiment 4

[0146] Figure 4 is a schematic structural diagram of the cleaning device provided in Embodiment 4 of the present application. As Figure 4 shown, the embodiments of the present application also provide a cleaning device 400, including a processor 401, a memory 402, a program or instruction stored on the memory 402 and executable on the processor 401. When the program or instruction is executed by the processor 401, it implements each process of the above-mentioned embodiment of the adaptive dosing method for the cleaning agent and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0147] It should be noted that the electronic devices in the embodiments of the present application include the above-mentioned mobile electronic devices and non-mobile electronic devices.

[0148] Embodiment 5

[0149] The embodiments of the present application also provide a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, it implements each process of the above-mentioned embodiment of the adaptive dosing method for the cleaning agent and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0150] Among them, the processor is the processor in the electronic 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 disks, or optical discs, etc.

[0151] Embodiment 6

[0152] The embodiments of the present application further provide a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run a program or instruction to implement each process of the above-mentioned embodiment of the adaptive dosing method for the cleaning agent and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0153] It should be understood that the chip mentioned in the embodiments of the present application may also be referred to as a system-on-chip, system chip, chip system, or system-on-chip, etc.

[0154] It should be noted that in this document, the term "including", "comprising", or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article, or device including a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or device. Without further limitation, an element defined by the phrase "including a..." does not exclude the presence of additional identical elements in the process, method, article, or device including such element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in a reverse order according to the functions involved. For example, the described methods may be performed in an order different from that described, and various steps may be added, omitted, or combined. Additionally, the features described with reference to certain examples may be combined in other examples.

[0155] Through the description of the above embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases, the former is a better implementation. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. The computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disc) and includes several instructions for causing a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present application.

[0156] The embodiments of the present application have been described above in conjunction with the accompanying drawings. However, the present application is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Under the inspiration of the present application, those of ordinary skill in the art can also make many forms without departing from the purpose of the present application and the scope protected by the claims, and all of them fall within the protection scope of the present application.

[0157] The above are only the preferred embodiments of the present application and the technical principles applied. The present application is not limited to the specific embodiments described herein. Various obvious changes, re-adjustments, and substitutions that can be made by those skilled in the art will not depart from the protection scope of the present application. Therefore, although the present application has been described in more detail through the above embodiments, the present application is not limited to the above embodiments. Without departing from the concept of the present application, it may also include more other equivalent embodiments, and the scope of the present application is determined by the scope of the claims.

Claims

1. A method for adaptively dispensing a cleaning agent, characterized in that: The method comprises: Identify material parameters and weight parameters of the object to be cleaned, and determine a first dosage of the cleaning agent; After the first placement is completed, the turbidity level inside the cleaning device is continuously monitored within a preset time period of the washing operation to obtain turbidity data and draw a turbidity data curve; Inputting the turbidity data curve into a pre-built detergent control model to obtain a second dosage of the detergent; Dispensing the cleaning agent for a second time according to the second dosage; While keeping the total cleaning time unchanged, the duration of each cleaning program in the cleaning process is modified according to the time point of the second delivery.

2. The method for adaptively dispensing cleaning agent according to claim 1, characterized in that: Inputting the turbidity data curve into a pre-built detergent control model to obtain a second dosage of the detergent, comprising: Inputting the turbidity data curve into a pre-built detergent control model, and extracting the speed increase characteristic and / or increment characteristic of the turbidity data curve within a preset time length through the detergent control model; The detergent control model outputs an additional coefficient of the detergent according to the speed-up characteristic and / or the increment characteristic, so as to determine a second dosage amount of the detergent according to the additional coefficient and the first dosage amount.

3. The method for adaptively dispensing cleaning agent according to claim 1, characterized in that: Inputting the turbidity data curve into a pre-built detergent control model to obtain a second dosage of the detergent, comprising: Inputting the turbidity data curve into a pre-built detergent control model, and extracting the growth rate change value of the turbidity data curve in each observation period within a preset time period through the detergent control model; When the growth rate peak value of the growth rate change value exceeds the first threshold value and the growth rate fallback speed of the growth rate change value is less than the second threshold value, it is determined that additional dosage is required, and the second dosage amount of the detergent is determined according to the growth rate peak value and the growth rate fallback speed.

4. The method for adaptively dispensing cleaning agent according to claim 1, characterized in that: Before inputting the turbidity data curve into a pre-built detergent control model to obtain a second dosage of the detergent, the method further includes: The material parameters and weight parameters of the object to be cleaned are input into the detergent control model to configure the calculation parameters of the detergent control model.

5. The method for adaptively dispensing a cleaning agent according to any one of claims 1 to 4, characterized in that: The cleaner controls the model building process, including: Obtain the material parameters and weight parameters of the items to be cleaned in historical cleaning operations, the historical amount of cleaning agents used, and use the cleaning effect evaluation after the historical cleaning operations are completed as labels to construct a sample set; The sample set is input into a basic model to train the basic model and obtain a detergent control model; wherein the detergent control model is used to output a basic dosage of detergent corresponding to each material parameter and weight parameter and an additional coefficient, and the additional coefficient is used to determine the additional dosage.

6. The method for adaptively dispensing cleaning agent according to claim 1, characterized in that: The cleaning agent is stored in a cleaning agent cartridge; After determining a first dosage of the cleaning agent, determining the number of cleaning agent-encapsulated marbles to be dispensed according to the first dosage to perform a first dosage; After determining the second dosage of the detergent, the number of detergent-packaged marbles to be dosed is determined based on the second dosage to perform the second dosage.

7. The method for adaptively dispensing cleaning agent according to claim 6, characterized in that: The method further comprises: When it is detected that the remaining detergent packaged marbles in the detergent cartridge are less than the set number, a detergent packaged marble replenishment reminder message is sent to the client associated with the cleaning device.

8. An adaptive detergent delivery device, characterized in that: The device comprises: A first dosage determination module, used for identifying material parameters and weight parameters of the object to be cleaned, and determining a first dosage of the cleaning agent; A turbidity data monitoring module is used to continuously monitor the turbidity level inside the cleaning device within a preset duration of the washing operation after the first placement is completed, obtain turbidity data, and draw a turbidity data curve; A second dosage determination module, used for inputting the turbidity data curve into a pre-built detergent control model to obtain a second dosage of the detergent; An additional delivery module, used for delivering the cleaning agent for a second time according to the second delivery amount; The cleaning program duration reallocation module is used to modify the duration of each cleaning program in the cleaning process according to the time point of the second delivery while keeping the total cleaning duration unchanged.

9. An electronic device, characterized in that: The method comprises a processor, a memory and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the method for adaptively delivering a cleaning agent as described in any one of claims 1 to 7.

10. A readable storage medium, characterized in that: The readable storage medium stores a program or an instruction, and when the program or the instruction is executed by the processor, the steps of the method for adaptively dispensing a detergent according to any one of claims 1 to 7 are implemented.

Images