Detergent dispensing control method, system and electronic equipment

Abstract

The present application provides a control method, system, and electronic device for detergent dosing. The method includes: inputting a preset washing mode and the weight of the laundry into a preliminary detergent dosage prediction model to predict and output a theoretical detergent dosage, and using a first preset ratio of the theoretical detergent dosage as the initial detergent dosage; a detergent dosage adjustment step: obtaining the real-time foam volume during the washing process, and inputting the real-time foam volume, the preset washing mode, and the weight of the laundry into a detergent dosage optimization determination model to determine a result; if the determination result indicates that the real-time detergent dosage does not achieve the optimal washing effect for the laundry, adding a second preset ratio of the theoretical detergent dosage; and executing the detergent dosage adjustment step at least once until the real-time detergent dosage achieves the optimal washing effect for the laundry. This achieves precise control of the detergent dosage.

Description

Technical Field

[0001] The present application relates to the field of household appliances, and more specifically, to a method for controlling the dispensing of detergent, a control system for dispensing detergent, a computer-readable storage medium, and an electronic device. Background Art

[0002] As an important part of household appliances, washing machines have become an indispensable tool in modern life, greatly improving people's daily convenience. With the continuous advancement of technology, the intelligence level of washing machines has been continuously improved, and their functions have become more and more diverse.

[0003] During the use of a washing machine, chemical additives such as detergents and softeners are usually added to improve the washing effect. Currently, washing machines on the market mainly use two dispensing methods: one is manual dispensing by the user, and the other is through an automatic dispensing device. The manual dispensing method is limited by factors such as the user's personal habits, experience and judgment, and immediate environmental changes. It is often difficult to ensure that the amount of detergent dispensed each time can achieve the ideal washing effect. In contrast, automatic dispensing technology represents a technological innovation in the field of washing machines. Compared with manual dispensing, automatic dispensing technology can more accurately control the amount of detergent dispensed, thereby achieving better washing results.

[0004] Calculating the amount of detergent for automatic dispensing is crucial. Insufficient detergent may result in incomplete cleaning and stains, while excessive detergent can damage clothing, waste resources, and pollute the environment, significantly impacting the overall user experience.

[0005] Currently, the main strategy for automatic detergent dispensing in washing machines involves automatically determining the amount of detergent to be dispensed based on the user's preset wash mode and the weight of the laundry. However, this approach has certain limitations. Specifically, factors such as the material of the laundry, water temperature, and water quality can affect the foaming effect of the detergent during the wash process, which in turn affects the accuracy of detergent dispensing. Due to these variables, automatic dispensing systems still face challenges in ensuring accurate detergent dosage. Summary of the Invention

[0006] The main purpose of this application is to provide a control method for detergent dispensing, a control system for detergent dispensing, a computer-readable storage medium and an electronic device, so as to at least solve the problem that the current automatic detergent dispensing solution still has limitations and causes the detergent dosage to be inaccurate.

[0007] To achieve the above objectives, according to a first aspect of the present application, a method for controlling detergent dosage is provided, comprising: a prediction step of obtaining a preset washing mode and a weight of laundry, inputting the preset washing mode and the weight of the laundry into a preliminary detergent dosage prediction model to predict and output a theoretical detergent dosage, and using a first preset proportion of the theoretical detergent dosage as an initial detergent addition amount; a detergent dosage adjustment step of obtaining a real-time foam volume during a washing process, inputting the real-time foam volume, the preset washing mode, and the weight of the laundry into a detergent dosage optimization determination model to determine a result; if the determination result indicates that the real-time detergent addition amount does not achieve an optimal washing effect for the laundry, adding a second preset proportion of the theoretical detergent dosage; and executing the detergent dosage adjustment step at least once until the real-time detergent addition amount achieves an optimal washing effect for the laundry, wherein the real-time detergent addition amount when the detergent dosage adjustment step is executed for the first time is the initial detergent addition amount.

[0008] Optionally, obtaining the real-time foam amount during the washing process includes: obtaining the frequency characteristics and amplitude characteristics of the foam bursting sound signal; and determining the real-time foam amount in the drum based on the frequency characteristics and the amplitude characteristics of the foam bursting sound signal.

[0009] Optionally, before executing the prediction step, the method further includes: constructing a preliminary detergent dosage prediction model, wherein the preliminary detergent dosage prediction model is trained using multiple sets of training data, and any set of training data includes: historical preset washing modes, historically weighed weights of laundry, and historical theoretical detergent dosages corresponding to the historical preset washing modes and historically weighed weights of laundry, obtained within a historical time period; wherein any of the historical theoretical detergent dosages is obtained through multiple washing experiments, and the dosages of detergent added in any two washing experiments are different, and the historical theoretical detergent dosage is the detergent dosage with the smallest amount of dirt after washing among the multiple detergent dosages.

[0010] Optionally, after constructing the preliminary detergent dosage prediction model, the method further includes: constructing a model for determining whether the detergent dosage is optimal, wherein the model for determining whether the detergent dosage is optimal is obtained by training using multiple sets of training data, and any set of training data includes input parameters and output parameters obtained within a historical time period, wherein the input parameters include historical preset washing modes, historical weighed weights of laundry, and historical foam volumes, and the output parameters are historical detergent addition amounts selected for the corresponding optimal washing effects, wherein the historical detergent addition amounts are obtained based on historical theoretical detergent dosages.

[0011] Optionally, the parameters in the preset washing mode include at least one of the following: washing time, clothing material, water temperature, and set water level.

[0012] According to a second aspect of the present application, a method for controlling detergent addition is provided, comprising: sending a preset washing mode and the weight of laundry to a remote server, so that the remote server performs a prediction step: obtaining the preset washing mode and the weight of laundry, inputting the preset washing mode and the weight of laundry into a preliminary detergent dosage prediction model to predict and output a theoretical detergent dosage, and using a first preset ratio of the theoretical detergent dosage as an initial detergent addition amount; sending a real-time amount of foam during washing to the remote server, so that the remote server performs a detergent dosage adjustment step: during washing, During the process, a real-time foam amount is obtained, and the real-time foam amount, the preset washing mode, and the weight of the laundry are input into a detergent dosage optimization judgment model to obtain a judgment result. If the judgment result indicates that the real-time detergent addition amount does not achieve the optimal washing effect for the laundry, the theoretical detergent dosage of a second preset proportion is added; and the detergent dosage adjustment step is performed at least once until the real-time detergent addition amount achieves the optimal washing effect for the laundry, wherein the real-time detergent addition amount when the detergent dosage adjustment step is performed for the first time is the initial detergent addition amount.

[0013] Optionally, the process of obtaining the real-time foam amount during washing includes: obtaining a foam bursting sound signal; performing time domain to frequency domain conversion processing on the foam bursting sound signal to obtain frequency characteristics and amplitude characteristics of the foam bursting sound signal.

[0014] Optionally, obtaining the foam bursting sound signal includes: receiving the foam bursting sound signal collected by a plurality of sound sensors installed at multiple locations.

[0015] According to a third aspect of the present application, a control system for dispensing detergent is provided, comprising: a remote server for executing any one of the above-mentioned methods for controlling dispensing detergent; a washing machine end for communicating with the remote server for executing any one of the above-mentioned methods for controlling dispensing detergent;

[0016] According to a fourth aspect of the present application, a computer-readable storage medium is provided, which includes a stored program, wherein when the program is run, the device where the computer-readable storage medium is located is controlled to execute any one of the control methods for adding detergent.

[0017] According to the fifth aspect of the present application, an electronic device is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include a control method for executing any one of the detergent delivery methods.

[0018] The technical solution of the present application is applied, through a prediction step: obtaining a preset washing mode and the weight of the laundry, inputting the preset washing mode and the weight of the laundry into a preliminary detergent dosage prediction model to predict and output a theoretical detergent dosage, and using a first preset ratio of the theoretical detergent dosage as the initial detergent addition amount; a detergent dosage adjustment step: obtaining a real-time foam volume during the washing process, and inputting the real-time foam volume, the preset washing mode, and the weight of the laundry into a detergent dosage optimization judgment model to obtain a judgment result; if the judgment result indicates that the real-time detergent addition amount does not achieve the optimal washing effect for the laundry, adding a second preset ratio of the theoretical detergent dosage; applying the preliminary detergent dosage prediction model and the detergent dosage optimization judgment model to achieve precise control of the detergent dosage, and the preliminary detergent dosage prediction model takes into account both the preset washing mode and the weight of the laundry, while the detergent dosage optimization judgment model takes into account the preset washing mode, the weight of the laundry, and the real-time foam volume. The consideration of multiple factors achieves precise control of the detergent dosage. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The drawings that constitute part of this application are used to provide a further understanding of this application. The illustrative embodiments of this application and their descriptions are used to explain this application and do not constitute an improper limitation on this application. In the drawings:

[0020] Figure 1 A schematic flow chart of a first method for controlling the dispensing of detergent according to an embodiment of the present application is shown;

[0021] Figure 2 A schematic diagram showing the functional steps of a remote server implemented according to an embodiment of the present application is shown;

[0022] Figure 3 A schematic flow chart of a second method for controlling the dispensing of detergent according to an embodiment of the present application is shown;

[0023] Figure 4 A schematic diagram showing the functional steps specifically implemented by a washing machine according to an embodiment of the present application is shown;

[0024] Figure 5 A schematic diagram of the model structure according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0025] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in this application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0026] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0027] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0028] As introduced in the background technology, the automatic detergent dosing solutions in the prior art still have limitations, resulting in inaccurate detergent dosage. To solve the problem that the automatic detergent dosing solutions still have limitations, resulting in inaccurate detergent dosage, the embodiments of the present application provide a detergent dosing control method, a detergent dosing control system, a computer-readable storage medium, and an electronic device.

[0029] The technical solutions in the embodiments of the present invention will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present invention.

[0030] First aspect embodiment

[0031] In this embodiment, a control method for dispensing detergent running on a remote server is provided, wherein the remote server communicates with the washing machine. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0032] Figure 1FIG. 1 is a flow chart of a method for controlling the addition of detergent according to an embodiment of the present application. Figure 1 As shown, the method includes the following steps:

[0033] Step S101, prediction step: obtaining a preset washing mode and the weight of the laundry, inputting the preset washing mode and the weight of the laundry into a preliminary detergent dosage prediction model to predict and output a theoretical detergent dosage, and using a first preset ratio of the theoretical detergent dosage as the initial detergent addition amount;

[0034] Among them, the parameters in the preset washing mode include at least one of the following: washing time, clothing material, water temperature, and set water level.

[0035] In some cases, the parameters in the preset washing mode may also include water quality.

[0036] The first preset ratio may be selected as 80% or 85%. Of course, the first preset ratio may be adjusted according to actual needs. However, it generally does not exceed 90% to leave room for subsequent adjustment processes.

[0037] Step S102, detergent dosage adjustment step: during the washing process, the real-time foam volume is obtained, and the real-time foam volume, the preset washing mode, and the weight of the laundry are input into a detergent dosage optimization judgment model to obtain a judgment result. If the judgment result indicates that the real-time detergent addition amount does not achieve the optimal washing effect for the laundry, a theoretical detergent dosage of a second preset ratio is added;

[0038] Whether the optimal washing effect is achieved can be evaluated using the following parameters:

[0039] 1) Cleaning Ratio: The cleaning ratio refers to the ratio of the degree of stain removed from clothes during the washing process to the initial stain. It is one of the important indicators for measuring the cleaning effect of a washing machine. The higher the cleaning ratio value, the more effectively the washing machine can remove stains from clothes during the washing process.

[0040] 2) Water consumption and power consumption: Water consumption and power consumption are important indicators to measure the economy and environmental protection of washing machines, and they directly affect the cost of using washing machines.

[0041] The real-time foam amount is obtained during the washing process, including:

[0042] Acquiring frequency characteristics and amplitude characteristics of the foam bursting sound signal; specifically, the remote server receives the frequency characteristics and amplitude characteristics of the foam bursting sound signal sent by the washing machine;

[0043] The real-time foam amount in the cylinder is determined based on the frequency and amplitude characteristics of the foam bursting sound signal.

[0044] Specifically, the mapping relationship between the frequency characteristics and amplitude characteristics and the real-time foam volume is obtained through a large number of experiments.

[0045] Step S103, executing the detergent dosage adjustment step at least once until the real-time detergent addition amount reaches the optimal washing effect suitable for the laundry, wherein the real-time detergent addition amount when the detergent dosage adjustment step is executed for the first time is the initial detergent addition amount.

[0046] Additionally, before performing the prediction step, the method further comprises:

[0047] Construct a preliminary prediction model for detergent dosage,

[0048] Among them, the preliminary detergent dosage prediction model is trained using multiple sets of training data. Any set of training data includes the following: historical preset washing modes, historically weighed weights of laundry, and historical theoretical detergent dosages corresponding to the historically preset washing modes and historically weighed weights of laundry, obtained within a historical time period. Among them, any historical theoretical detergent dosage is obtained through multiple washing experiments, and the detergent dosages added in any two washing experiments are different. The historical theoretical detergent dosage is the detergent dosage that produces the smallest amount of dirt after washing among the multiple detergent dosages.

[0049] In addition, after constructing the preliminary detergent dosage prediction model, the method further includes:

[0050] Construct a model to judge whether the detergent dosage is optimal.

[0051] Among them, the detergent dosage judgment model is trained using multiple sets of training data. Any set of training data includes input parameters and output parameters obtained within a historical time period. The input parameters include historical preset washing modes, historical weighed weights of laundry, and historical foam volumes. The output parameters are historical detergent addition amounts selected for the corresponding optimal washing effect. Among them, the historical detergent addition amounts are obtained based on historical theoretical detergent dosages.

[0052] The detergent dosage control method of the present application comprises a prediction step: obtaining a preset washing mode and the weight of the laundry, inputting the preset washing mode and the weight of the laundry into a preliminary detergent dosage prediction model to predict and output a theoretical detergent dosage, and using a first preset ratio of the theoretical detergent dosage as the initial detergent addition amount; and a detergent dosage adjustment step: obtaining a real-time foam volume during the washing process, and inputting the real-time foam volume, the preset washing mode, and the weight of the laundry into a detergent dosage optimization judgment model to obtain a judgment result. If the judgment result indicates that the real-time detergent addition amount does not achieve the optimal washing effect for the laundry, adding a second preset ratio of the theoretical detergent dosage. The preliminary detergent dosage prediction model and the detergent dosage optimization judgment model are applied to achieve precise control of the detergent dosage. The preliminary detergent dosage prediction model takes into account both the preset washing mode and the weight of the laundry, while the detergent dosage optimization judgment model takes into account the preset washing mode, the weight of the laundry, and the real-time foam volume. The consideration of multiple factors enables precise control of the detergent dosage.

[0053] In this patent, a sound sensor is used to determine the real-time foam amount while washing, and whether the current detergent dosage has reached the target value is determined based on the real-time foam amount. If the target value has not been reached, detergent continues to be added. This can achieve dynamic adjustment of the detergent without affecting the overall washing process.

[0054] See Figure 2 ,The remote server collects the preset washing mode and the weight of the laundry to be ,inputted into the preliminary detergent dosage prediction model to obtain ,the theoretical detergent dosage;

[0055] The remote server collects the preset washing mode, the weight of the laundry, the frequency characteristics, and the amplitude characteristics, and inputs them into the detergent dosage optimization model to determine whether more detergent needs to be added. In other words, the preset washing mode, the weight of the laundry, the frequency characteristics, and the amplitude characteristics can be input into the detergent dosage optimization model to determine whether more detergent needs to be added.

[0056] Second aspect embodiment

[0057] In this embodiment, a control method for adding detergent running on the washing machine end is provided, wherein a remote server communicates with the washing machine end. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0058] Figure 3FIG. 1 is a flow chart of a method for controlling the addition of detergent according to an embodiment of the present application. Figure 3 As shown, the method includes the following steps:

[0059] Step S301: Sending the preset washing mode and the weight of the laundry to a remote server, so that the remote server performs a prediction step: obtaining the preset washing mode and the weight of the laundry, inputting the preset washing mode and the weight of the laundry into a preliminary detergent dosage prediction model to predict and output a theoretical detergent dosage, and using a first preset ratio of the theoretical detergent dosage as an initial detergent addition amount;

[0060] In step S302, the real-time amount of foam is transmitted to a remote server during the washing process, so that the remote server executes a detergent dosage adjustment step: obtaining the real-time amount of foam during the washing process, and inputting the real-time amount of foam, the preset washing mode, and the weight of the laundry into a detergent dosage optimization judgment model to obtain a judgment result; if the judgment result indicates that the real-time amount of detergent added does not achieve the optimal washing effect for the laundry, adding the theoretical detergent dosage of a second preset ratio; and executing the detergent dosage adjustment step at least once until the real-time amount of detergent added achieves the optimal washing effect for the laundry, wherein the real-time amount of detergent added when the detergent dosage adjustment step is executed for the first time is referred to as the initial amount of detergent added.

[0061] Among them, the process of obtaining the real-time foam amount during the washing process includes: obtaining the foam bursting sound signal; performing time domain to frequency domain conversion processing on the above foam bursting sound signal to obtain the frequency characteristics and amplitude characteristics of the above foam bursting sound signal.

[0062] The step of obtaining the foam bursting sound signal includes receiving the foam bursting sound signal collected by a plurality of sound sensors installed at multiple locations.

[0063] Specifically, the sound sensor uses a piezoelectric ceramic hydrophone as a sound sensor with a sensitivity of ≥-166.5dBVre:1V / μPascal (that is, when the sound pressure changes by 1 microPascal, the output voltage of the sensor changes by 1 volt), and an operating frequency range of 20Hz-20KHz.

[0064] The sound sensor is installed between the inner drum and the outer drum and fixed at the upper part of the outer drum. Because in the washing process of the washing machine, the clothes will be soaked in water and at the bottom in the initial state, and the foam will float on the water surface and have a certain contact with the clothes. When the washing machine rotates during washing, the rotation of the inner drum will throw the clothes and foam into the air, and the foam will burst when it is thrown into the air. At this time, collecting the frequency and amplitude of the foam bursting can minimize the influence of water flow, clothing friction, etc.

[0065] The detergent dosage control method of this embodiment applies a preliminary detergent dosage prediction model and an optimal detergent dosage judgment model to achieve precise control of the detergent dosage. The preliminary detergent dosage prediction model takes into account two factors: the preset washing mode and the weight of the laundry to be washed. The optimal detergent dosage judgment model takes into account the preset washing mode, the weight of the laundry to be washed, and the real-time foam volume. The consideration of multiple factors enables precise control of the detergent dosage.

[0066] See Figure 4 ,The main functions of the washing machine are to input relevant ,information into the corresponding model, respond to the output results of the ,model, and process the signals collected by the sound sensor.

[0067] The detergent dosage preliminary prediction model and the detergent dosage optimal judgment model in the embodiment of the present application can be used. Figure 5 The neural network model in .

[0068] The various embodiments of the present application offer advantages over solutions that only determine the amount of detergent to be added once before washing, which place high demands on the accuracy of the predicted detergent amount and require exhaustive consideration of all factors affecting the washing process. They also offer advantages over solutions that can more accurately control the total amount of detergent added but require multiple washes and waiting periods after each wash, which not only increases the overall washing time but also increases the risk of wear and tear on clothing during extended washes.

[0069] Third aspect embodiment

[0070] This embodiment relates to a remote server, including:

[0071] a prediction unit configured to: obtain a preset washing mode and the weight of the laundry, input the preset washing mode and the weight of the laundry into a preliminary detergent dosage prediction model to predict and output a theoretical detergent dosage, and use a first preset ratio of the theoretical detergent dosage as an initial detergent addition amount;

[0072] an adjustment unit for a detergent dosage adjustment step, wherein the step comprises obtaining a real-time amount of foam during washing, inputting the real-time amount of foam, the preset washing mode, and the weight of the laundry into a detergent dosage optimization judgment model to obtain a judgment result; and if the judgment result indicates that the real-time amount of detergent added does not achieve an optimal washing effect for the laundry, adding a second preset ratio of the theoretical detergent dosage;

[0073] an execution unit, configured to execute the detergent dosage adjustment step at least once until the real-time detergent addition amount reaches an optimal washing effect suitable for the laundry, wherein the real-time detergent addition amount when the detergent dosage adjustment step is executed for the first time is the initial detergent addition amount.

[0074] The adjustment unit includes an acquisition module, which is used to obtain the real-time foam amount during the washing process, wherein the acquisition module includes an acquisition submodule and a determination submodule, the acquisition submodule is used to obtain the frequency characteristics and amplitude characteristics of the foam bursting sound signal; the determination submodule is used to determine the above-mentioned real-time foam amount in the drum based on the above-mentioned frequency characteristics and the above-mentioned amplitude characteristics of the above-mentioned foam bursting sound signal.

[0075] The remote server also includes a first construction unit, which is used to construct the above-mentioned preliminary detergent dosage prediction model before executing the above-mentioned prediction step, wherein the above-mentioned preliminary detergent dosage prediction model is obtained by training using multiple sets of training data, and any set of the above-mentioned training data includes: historical preset washing modes, historically weighed weights of laundry, and historical theoretical detergent dosages corresponding to the above-mentioned historical preset washing modes and historically weighed weights of laundry, obtained within a historical time period, wherein any of the above-mentioned historical theoretical detergent dosages is obtained through multiple washing experiments, the detergent dosages added in any two washing experiments are different, and the above-mentioned historical theoretical detergent dosage is the detergent dosage that corresponds to the smallest amount of dirt after washing among the multiple detergent dosages.

[0076] The remote server also includes a second construction unit, which is used to construct the above-mentioned detergent dosage optimization judgment model after constructing the above-mentioned preliminary detergent dosage prediction model, wherein the above-mentioned detergent dosage optimization judgment model is obtained by training using multiple groups of training data, and any group of the above-mentioned training data includes input parameters and output parameters obtained within a historical time period, the above-mentioned input parameters include historical preset washing modes, historical weighed weights of laundry, and historical foam amounts, and the above-mentioned output parameters are historical detergent addition amounts selected for the corresponding optimal washing effect, wherein the above-mentioned historical detergent addition amounts are obtained based on historical theoretical detergent dosages.

[0077] Optionally, the parameters in the above-mentioned preset washing mode include at least one of the following: washing time, clothing material, water temperature, and set water level.

[0078] Fourth aspect embodiment

[0079] This embodiment relates to a washing machine end, comprising:

[0080] a first sending unit, configured to send a preset washing mode and the weight of the laundry to a remote server, so that the remote server performs a prediction step: obtaining the preset washing mode and the weight of the laundry, inputting the preset washing mode and the weight of the laundry into a preliminary detergent dosage prediction model to predict and output a theoretical detergent dosage, and using a first preset ratio of the theoretical detergent dosage as an initial detergent addition amount;

[0081] The second sending unit is configured to send the real-time foam amount to a remote server during the washing process, so that the remote server executes a detergent dosage adjustment step: obtaining the real-time foam amount during the washing process, and inputting the real-time foam amount, the preset washing mode, and the weight of the laundry into a detergent dosage optimization judgment model to obtain a judgment result; if the judgment result indicates that the real-time detergent addition amount does not achieve the optimal washing effect for the laundry, adding the theoretical detergent dosage of a second preset proportion; and executing the detergent dosage adjustment step at least once until the real-time detergent addition amount achieves the optimal washing effect for the laundry, wherein the real-time detergent addition amount when the detergent dosage adjustment step is executed for the first time is referred to as the initial detergent addition amount.

[0082] The washing machine end also includes an acquisition unit and a processing unit. The acquisition unit is used to obtain the foam bursting sound signal; the processing unit is used to perform time domain to frequency domain conversion on the above foam bursting sound signal to obtain the frequency characteristics and amplitude characteristics of the above foam bursting sound signal.

[0083] Fifth aspect embodiment

[0084] This embodiment provides a control system for dispensing detergent, including: a remote server for executing the control method for dispensing detergent in the first embodiment; and a washing machine end for communicating with the remote server for the control method for dispensing detergent in the second embodiment.

[0085] Remote server specific implementation Figure 2 The steps shown are specifically performed by the washing machine Figure 4 In the steps shown, the entire system is divided into three stages: parameter acquisition stage, model training stage and model application stage.

[0086] Parameter collection stage:

[0087] When the amount of detergent is constant, the length of washing time, the characteristics of the clothing material, the water temperature, the total weight of the clothing, and the set amount of water are all key variables that affect the foaming effect and foam stability of the detergent during the washing process. Therefore, these key parameters must be covered in the parameter collection stage. First, the washing mode of the washing machine (that is, the preset washing mode) is recorded during parameter collection. The washing mode includes the preset washing time, the material of the clothing, the temperature, and the set water level (the water level data directly represents the amount of water required during the washing process). During the weighing stage of the washing process, the built-in weighing system of the washing machine or external auxiliary equipment is used to weigh the clothes placed in the drum to obtain the weight of the clothes. And after the washing is completed, the amount of detergent used for this wash is recorded.

[0088] In a washing machine, the generation of foam is closely related to the vibration and propagation of sound. When foam forms inside the washing machine, the bursting and movement of the foam produces a characteristic sound. These acoustic signals can be captured by sound sensors and converted into electrical signals. The frequency of the sound produced by the bursting of foam depends on a variety of factors, including the size and material of the foam, and the method of bursting. Generally speaking, the frequency of the sound produced by the bursting of smaller bubbles is relatively high, perhaps around a few thousand hertz (kHz). For example, the frequency of the bursting of soap bubbles several millimeters in diameter may be between 2 and 5 kHz. The amplitude reflects the loudness of the sound. The amplitude of the bursting sound is also affected by various factors. From an energy perspective, the bursting of smaller bubbles releases less energy, resulting in a smaller amplitude. For example, the amplitude of the sound produced by the bursting of a small soap bubble may be between 0.01 and 0.1 Pascals (where 0.1 Pascals of sound pressure is approximately equivalent to a sound pressure level of 74 decibels).

[0089] The principle of the sound sensor detecting the amount of foam: (1) Capturing the sound signal: The sound sensor has a built-in sound-sensitive capacitive electret microphone that can capture the sound signal generated by the bursting and flow of foam inside the washing machine. (2) Signal conversion and transmission: The captured sound signal vibrates through the electret film inside the microphone, causing a change in capacitance, thereby generating a small voltage that changes accordingly. This voltage is then converted into an electrical signal and transmitted to the processing system. (3) Signal processing and analysis: After receiving the electrical signal, the processing system analyzes and processes it through appropriate algorithms. Since different amounts of foam will cause changes in the frequency, amplitude and other characteristics of the sound signal, the processing system can determine the current amount of foam in the washing machine based on these characteristics. Table 1 shows the relationship between the amount of foam and the frequency and amplitude.

[0090] Table 1 Relationship between foam volume, frequency and amplitude

[0091]

[0092] During the rinse cycle, a sound sensor captures the specific sound signals generated by foam within the washing machine's drum with high sensitivity. These signals are then processed using a highly efficient digital signal processing technique called FFT, converting the time-domain signal into a frequency-domain representation. This allows for precise analysis of the characteristic frequency and amplitude corresponding to the current foam level. This process not only enables real-time monitoring of the foam state but also provides a basis for intelligent adjustments to subsequent wash cycles.

[0093] The FFT transform is essentially the Fast Discrete Fourier Transform. The Fourier principle states that any continuously measured time series or signal can be represented as an infinite superposition of sinusoidal signals of varying frequencies. The Fourier transform algorithm, based on this principle, uses the directly measured original signal to cumulatively calculate the frequency, amplitude, and phase of the various sinusoidal signals within it.

[0094] Model training phase:

[0095] Model description: The model training phase mainly trains two models: the preliminary prediction model for detergent dosage and the model for determining whether the detergent dosage is optimal. For the preliminary prediction model for detergent dosage, its input items are the washing mode (washing time, clothing material, water temperature, set water level) and clothing weight, and the output is the predicted detergent dosage corresponding to the current amount of clothing; while the model for determining whether the detergent dosage is optimal uses the washing mode (washing time, clothing material, water temperature, set water level), clothing weight and its current foam content range (i.e., specific frequency and amplitude) as the network input items, and the output item is whether the current foam amount range is the optimal range for detergent usage; although the above two models have different input and output items, they both belong to prediction problems, so a feedforward neural network (BP) is used in this patent to implement its functions.

[0096] 2. A massive and diverse data set, encompassing the optimal detergent dosage and foam content range (i.e., specific frequency and amplitude) for optimal washing results across different wash modes and clothing weight ranges, is transmitted to a remote high-performance computing server via a network transmission protocol. This strategy effectively reduces the processing burden on the local controller, significantly lowering hardware costs, while leveraging the powerful computing power of the cloud to accelerate data processing and analysis.

[0097] 3. On the server side, a machine learning model is deployed. This model is trained using the collected wash mode, laundry weight, and the corresponding optimal detergent dosage (preliminary detergent dosage prediction model), as well as the frequency and amplitude of the optimal foam volume range (detergent dosage determination model) as input features. The core goal of model training is to establish a mapping relationship between wash mode, laundry load, optimal detergent dosage, and the frequency and amplitude of the optimal foam volume range.

[0098] 4. The optimal detergent dosage, foam frequency, and amplitude parameters used in model training are derived from the parameter collection phase of the initial design. This phase involves extensive repetitive experiments and data recording, aiming to capture and quantify subtle variations in washing performance and foam characteristics under different conditions, providing a solid data foundation for subsequent model training. For example, 20ml of detergent is used to wash 1kg of laundry, with mode X selected. During the rinse phase of the washing machine, an acoustic sensor identifies the signal generated by foam in the drum and converts it to its frequency F and amplitude A. Finally, at the end of the wash phase, the laundry is checked to see if it is clean. If not, the detergent dosage is increased and the experiment is repeated until the laundry is clean. After the laundry is clean, all experimental parameters and results are recorded. By collecting a large amount of similar experimental data and feeding it into the predictive model for training, this process continuously improves the model's prediction accuracy and generalization capabilities, providing strong support for the practical application of intelligent detergent dispensing systems.

[0099] 3. Model application stage:

[0100] 1. The user-selected wash program and the actual load are used as initial inputs to implement the intelligent detergent dosing control system. Before the wash cycle begins, the current wash mode and load weight are sent to a remote server. A preliminary detergent dosage prediction model on the server calculates the theoretical optimal dosage, and this value multiplied by 80% is used as the initial detergent dosage. Secondly, after the wash cycle begins and a certain amount of washing has passed, the optimal dosage determination model begins. During this stage, an acoustic sensor captures the frequency and amplitude of the foam in the drum in real time and transmits this information, along with the current wash mode and load weight, to a pre-trained model. The model quickly analyzes the input data to determine whether the current detergent dosage achieves the optimal wash result for the current load. If the model determines that the current detergent dosage is not optimal, the system automatically triggers an adjustment mechanism to increase the detergent dosage appropriately. The system then re-evaluates whether the increased dosage achieves the optimal wash result until the optimal wash result is achieved. See Table 2 for a sample parameter comparison.

[0101] Table 2 Parameter comparison example table

[0102]

[0103] 2. Application Example: The weight of the laundry is β, the user selects the wash type X, and the predicted initial detergent dosage is R. 0.8R is used as the initial detergent dosage. After the wash cycle begins, the sensor first detects a foam frequency of F1 and an amplitude of A1. β, X, F1, and A1 are input into the system, which calculates whether the current detergent dosage is optimal. If not, the system automatically adds a small amount of detergent. The sensor then detects frequency F2 and amplitude A2 again, and inputs these values ​​along with β and X into the system. The system repeats this process until it determines the current detergent dosage is optimal. At this point, detergent addition ends and the wash cycle continues.

[0104] The prediction model is constructed through C++ or Python code, and its network architecture is shown in the following figure: Figure 5 As shown in the figure, the neural network architecture used in the model is BP neural network.

[0105] The two models have a sequential order, and the output of the first model (preliminary prediction of detergent dosage R) needs to be part of the basis for the input of the second model (detergent addition starting from 80% R).

[0106] Before the prediction model is used, it needs to be trained. The model training process is as follows: After the model is built, the preliminary detergent dosage prediction model is trained in the laboratory. In the experiment, five parameter groups (recorded as θ1) are collected for each experiment: washing time of the washing machine, clothing material, water temperature, set water level, and clothing weight. At the same time, different amounts of detergent are added to observe the cleanliness of the laundry corresponding to different amounts of detergent. The detergent dosage corresponding to the cleanest washing is selected and recorded. The above data (including the five parameters θ1 and the detergent dosage corresponding to the cleanest washing) are fed as input parameters to the built prediction model to train the model. The trained model can infer the corresponding predicted detergent dosage R after inputting the five parameters represented by θ.

[0107] In order to eliminate the influence of actual washing, in the second model, detergent is added gradually starting from 80% R. When training the model to judge whether the detergent dosage is optimal, six parameters θ2 are used: washing time, clothing material, water temperature, set water level, clothing weight, and foam content range (that is, the frequency and amplitude of the foam bursting in the barrel when washing after adding detergent). At the same time, all input parameters when the clothes reach the optimal washing effect are recorded. All the above data (including the six parameters θ2 corresponding to the optimal washing effect) are used as input parameters to train the model. The trained model can infer whether the optimal washing effect has been achieved after inputting the six parameters represented by θ2, and thus stop adding detergent.

[0108] In addition, the above model training phase needs to last for at least three months of experimental period and obtain as much relevant data as possible.

[0109] Sixth aspect embodiment

[0110] This embodiment provides an electronic device, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include a method for executing any one of the above-mentioned control methods for dispensing detergent.

[0111] Seventh aspect embodiment

[0112] An embodiment of the present invention provides a computer-readable storage medium, which includes a stored program. When the program is executed, the device where the computer-readable storage medium is located is controlled to execute the detergent adding control method.

[0113] An embodiment of the present invention provides a processor, which is used to run a program, wherein the control method for adding detergent is executed when the program is run.

[0114] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing the program in the control method of initializing the addition of detergent.

[0115] Obviously, those skilled in the art will appreciate that the various modules or steps of the present invention described above can be implemented using a general-purpose computing device, can be centralized on a single computing device, or can be distributed across a network of multiple computing devices. They can be implemented using program code executable by the computing device, and thus, can be stored in a storage device and executed by the computing device. In some cases, the steps shown or described herein can be performed in a different order than that shown, or can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0116] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0117] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0118] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0119] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0120] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0121] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0122] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0123] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0124] The above description is merely a preferred embodiment of the present application and is not intended to limit the present application. Various modifications and variations are possible for those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present application shall be included within the scope of protection of the present application.

Claims

1. A method for controlling the dosage of detergent, characterized in that: include: Prediction step: obtaining a preset washing mode and the weight of the laundry, inputting the preset washing mode and the weight of the laundry into a preliminary detergent dosage prediction model to predict and output a theoretical detergent dosage, and using a first preset ratio of the theoretical detergent dosage as an initial detergent addition amount; a detergent dosage adjustment step: obtaining a real-time foam amount during the washing process, and inputting the real-time foam amount, the preset washing mode, and the weight of the laundry into a detergent dosage optimization judgment model to obtain a judgment result; if the judgment result indicates that the real-time detergent addition amount does not achieve the optimal washing effect for the laundry, adding the theoretical detergent dosage of a second preset ratio; The detergent dosage adjustment step is performed at least once until the real-time detergent addition amount reaches an optimal washing effect suitable for the laundry, wherein the real-time detergent addition amount when the detergent dosage adjustment step is performed for the first time is the initial detergent addition amount.

2. The method according to claim 1, characterized in that Get real-time suds levels during washing, including: Obtaining frequency characteristics and amplitude characteristics of foam burst sound signals; The real-time foam amount in the cylinder is determined according to the frequency characteristic and the amplitude characteristic of the foam bursting sound signal.

3. The method according to claim 1, characterized in that Before performing the prediction step, the method further includes: Constructing the preliminary prediction model of the detergent dosage, The preliminary detergent dosage prediction model is trained using multiple sets of training data, and any set of training data includes the following: historical preset washing modes, historically weighed weights of laundry, and historical theoretical detergent dosages corresponding to the historically preset washing modes and historically weighed weights of laundry, obtained within a historical time period. Any of the historical theoretical detergent dosages is obtained through multiple washing experiments, with different detergent dosages added in any two washing experiments. The historical theoretical detergent dosage is the detergent dosage that produces the smallest amount of dirt after washing among the multiple detergent dosages.

4. The method according to claim 3, characterized in that After constructing the preliminary detergent dosage prediction model, the method further includes: Constructing a model to determine whether the detergent dosage is optimal, The model for determining whether the detergent dosage is optimal is trained using multiple sets of training data, wherein any set of training data includes input parameters and output parameters obtained within a historical time period, wherein the input parameters include historical preset washing modes, historical weighed weights of laundry, and historical foam volumes, and the output parameters are historical detergent addition amounts selected for the corresponding optimal washing effect, wherein the historical detergent addition amounts are obtained based on historical theoretical detergent dosages.

5. The method according to any one of claims 1 to 4, characterized in that The parameters in the preset washing mode include at least one of the following: Washing time, clothing material, water temperature, set water level.

6. A method for controlling the dosage of detergent, characterized in that: include: The preset washing mode and the weight of the laundry are transmitted to a remote server, so that the remote server performs a prediction step: obtaining the preset washing mode and the weight of the laundry, inputting the preset washing mode and the weight of the laundry into a preliminary detergent dosage prediction model to predict and output a theoretical detergent dosage, and using a first preset ratio of the theoretical detergent dosage as an initial detergent addition amount; During the washing process, the real-time amount of foam is transmitted to a remote server so that the remote server executes a detergent dosage adjustment step: during the washing process, the real-time amount of foam is obtained, and the real-time amount of foam, the preset washing mode, and the weight of the laundry are input into a detergent dosage optimization judgment model to obtain a judgment result; if the judgment result indicates that the real-time amount of detergent added does not achieve the optimal washing effect for the laundry, the theoretical detergent dosage of a second preset proportion is added; and the detergent dosage adjustment step is executed at least once until the real-time amount of detergent added achieves the optimal washing effect for the laundry, wherein the real-time amount of detergent added when the detergent dosage adjustment step is executed for the first time is referred to as the initial amount of detergent added.

7. The method according to claim 6, characterized in that The process of obtaining real-time foam volume during washing includes: Acquire the sound signal of foam bursting; The foam bursting sound signal is converted from time domain to frequency domain to obtain frequency characteristics and amplitude characteristics of the foam bursting sound signal.

8. The method according to claim 7, characterized in that Acquire bubble burst sound signals, including: The foam bursting sound signal collected by a plurality of sound sensors installed at multiple locations is received.

9. A control system for dispensing detergent, characterized in that: include: A remote server, configured to execute the detergent dispensing control method according to any one of claims 1 to 5; The washing machine end communicates with the remote server and is used to execute the control method for adding detergent according to any one of claims 6 to 8.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the method for controlling the addition of detergent according to any one of claims 1 to 5 or any one of claims 6 to 8.

11. An electronic device, characterized in that: include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include a control method for executing the detergent delivery method described in any one of claims 1 to 5 or any one of claims 6 to 8.

Images