Drying control method and device of washing machine and drying management system

Abstract

The invention provides a drying control method and device of a washing machine and a drying management system, and the method comprises the steps: obtaining an image of to-be-dried clothes and the clothes quality of the to-be-dried clothes under the condition that the washing machine is in a drying stage, the image of the to-be-dried clothes comprises the images of all the to-be-dried clothes, and the image of the to-be-dried clothes comprises the images of all the to-be-dried clothes; the mass of the clothes is the sum of the mass of all the to-be-dried clothes; an identification step: carrying out image identification on the to-be-dried clothes image to obtain a forward stacking height value, an expansion area and a distribution state parameter of the to-be-dried clothes; the clothes mass, the forward stacking height value, the unfolding area and the distribution state are input into a drying parameter control model, a drying parameter set is obtained, and the drying parameter set comprises the inner barrel rotating speed, the fan rotating speed and the heating time; and controlling the washing machine to dry according to the drying parameter group. The problem of poor drying quality of the washing machine in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of drying, and in particular to a drying control method, device, computer program product and drying management system for a washing machine. Background Art

[0002] In the prior art, clothes dryers or washing machines with drying functions are one of the indispensable household appliances in modern families. They provide people with a solution for drying clothes quickly and evenly, especially in humid or cold seasons. However, the clothes drying process faces a common problem in practical applications, that is, the drying effect is not ideal due to unreasonable drying time setting. This problem is mainly reflected in two aspects: insufficient drying degree and over-drying.

[0003] First, insufficient drying is usually caused by the drying time of the clothes dryer being set too short, which may be due to the user's inaccurate assessment of the type and humidity of the clothes, or the dryer itself being overloaded (too many clothes) and unable to complete effective drying within the preset time. As a result, the clothes fail to reach the ideal dry state and may retain a certain amount of moisture, which not only affects the comfort and durability of the clothes, but may also cause the clothes to mold or produce odors.

[0004] Secondly, overdrying is a problem caused by drying clothes for too long. When the clothes dryer is run for longer than necessary, the clothes will be affected by overheating and overdrying. In this case, the fiber structure of the clothes may be damaged, causing the clothes to shrink, harden, deform or fade, reducing the quality and life of the clothes. Overdrying may also cause energy waste, increase electricity consumption, and place unnecessary burden on the environment.

[0005] The drying process of a traditional washing machine usually starts after the dehydration stage and a certain shaking process, and before the drying starts, the speed and overall drying process are determined based on the weight of the clothes in the barrel as a single reference. In the entire macroscopic drying process, the parameters are only determined once before the start, and the washing machine will continue to operate according to the parameters until the end of the drying stage. Analyzing its process, it can be found that first, it cannot accurately determine the optimal drying parameters for the current amount of clothes and the state of the clothes. Secondly, since it only determines the parameters once before the start, it is impossible to dynamically adjust the drying parameters during the drying process in order to set the most appropriate drying parameters at different stages of drying. Summary of the invention

[0006] The main purpose of the present application is to provide a drying control method, device, computer program product and drying management system for a washing machine, so as to at least solve the problem of poor drying quality of washing machines in the prior art.

[0007] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a drying control method for a washing machine is provided, comprising: an acquisition step, when the washing machine is in a drying stage, acquiring an image of clothes to be dried and a mass of the clothes to be dried, wherein the image of clothes to be dried includes images of all the clothes to be dried, and the mass of the clothes is the sum of the masses of all the clothes to be dried; an identification step, performing image recognition on the image of clothes to be dried to obtain a positive stacking height value, an expanded area and distribution state parameters of the clothes to be dried, wherein the positive stacking height value is the height of the whole of the clothes to be dried in the vertical direction, and the expanded area is the whole of the clothes to be dried. The area occupied by the contour, the distribution state parameter is the distribution ratio of the to-be-dried clothes in multiple equally divided areas on the to-be-dried clothes image; the clothes mass, the forward stacking height value, the unfolded area and the distribution state are input into a drying parameter control model to obtain a drying parameter group, the drying parameter group includes an inner drum speed, a fan speed and a heating time, the drying parameter control model is trained with multiple groups of training data, each group of the training data includes historical clothes mass, corresponding historical forward stacking height value, corresponding historical unfolded area, corresponding historical distribution state parameter and corresponding historical drying parameter group; the washing machine is controlled to dry according to the drying parameter group.

[0008] Optionally, after performing image recognition on the image of the clothes to be dried to obtain the forward stacking height value, the unfolding area and the distribution state parameters of the clothes to be dried, the method further comprises: an analysis step, inputting the clothes mass, the forward stacking height value, the unfolding area and the distribution state into the drying parameter control model to obtain the drying parameter group, the drying parameter group comprising the clothes quantity type, the number of cycles, the inner drum speed, the fan speed and the heating time, the clothes quantity type being one of a plurality of types of clothes quantity from low to high, the number of cycles being the number of cycles expected to be experienced in the drying process, and the drying parameter control model being trained by a plurality of sets of the training data, each set of the training data comprising the historical clothes mass, the corresponding historical forward stacking height value, the unfolding area and the distribution state The stacking height value, the corresponding historical unfolding area, the corresponding historical distribution state parameter and the corresponding historical drying parameter group; a drying step, controlling the washing machine to dry for one cycle according to the inner drum speed, the fan speed and the single-cycle heating time, wherein the single-cycle heating time is the ratio of the heating time to the number of cycles; repeating the acquiring step, the identifying step, the analyzing step and the drying step at least once in sequence, and in each repeated drying step, updating the value of the drying parameter group of the current cycle to the average value of the drying parameter group of the current cycle and the value of the drying parameter group of the previous cycle, until the current number of cycles is 1 or the number of cycles reaches the maximum number of cycles.

[0009] Optionally, the training process of the drying parameter control model includes: obtaining multiple drying records with qualified drying quality, the drying records including a historical input parameter group and a corresponding historical drying parameter group, the historical input parameter group including the historical clothing mass, the corresponding historical forward stacking height value, the corresponding historical unfolding area, and the corresponding historical distribution state parameter; inputting each of the historical input parameter groups into a neural network model to obtain multiple predicted drying parameter groups; adjusting the parameters of the neural network model according to the errors between each of the predicted drying parameter groups and the corresponding historical drying parameter groups until all of the errors are less than the corresponding predetermined thresholds to obtain the drying parameter control model.

[0010] Optionally, obtaining a plurality of drying records with qualified drying quality includes: obtaining a plurality of original drying records with qualified drying quality; preprocessing the original drying records to obtain the drying records, wherein the preprocessing is used to remove noise, outliers and redundant information.

[0011] Optionally, image recognition is performed on the image of the clothes to be dried to obtain the forward stacking height value, the unfolded area and the distribution state parameters of the clothes to be dried, including: performing image segmentation on the clothes to be dried and the washing machine in the image of the clothes to be dried to obtain the overall contour of the clothes to be dried, wherein the overall contour of the clothes to be dried is the overall contour of all the clothes to be dried; measuring the forward stacking height value according to the overall contour of the clothes to be dried; calculating the unfolded area according to the overall contour of the clothes to be dried; dividing the image of the clothes to be dried into a plurality of equal areas; calculating the ratio of the area occupied by the overall contour of the clothes to be dried in each of the areas to the unfolded area to obtain a plurality of the distribution state parameters.

[0012] Optionally, before the washing machine enters the drying stage, the method further includes: deploying the drying parameter control model on a remote server, so that the remote server performs drying control on all the washing machines of the same type.

[0013] Optionally, before the washing machine enters the drying stage, the method further includes: controlling the washing machine to execute a shaking program, wherein the shaking program is a program for controlling the washing machine to shake so that the clothes to be dried are loosened.

[0014] According to another aspect of the present application, a drying control device for a washing machine is provided, comprising: an acquisition unit, configured to execute an acquisition step, to acquire an image of clothes to be dried and a mass of the clothes to be dried when the washing machine is in a drying stage, wherein the image of clothes to be dried includes images of all the clothes to be dried, and the mass of the clothes is the sum of the masses of all the clothes to be dried; and a recognition unit, configured to execute a recognition step, to perform image recognition on the image of clothes to be dried, and to obtain a positive stacking height value, an expanded area, and a distribution state parameter of the clothes to be dried, wherein the positive stacking height value is the height of the whole of the clothes to be dried in the vertical direction, and the expanded area is the area occupied by the overall outline of the clothes to be dried. area, the distribution state parameter is the distribution ratio of the to-be-dried clothes in multiple equally divided areas on the to-be-dried clothes image; a first analysis unit, used to input the clothes mass, the forward stacking height value, the unfolded area and the distribution state into a drying parameter control model to obtain a drying parameter group, the drying parameter group includes an inner drum speed, a fan speed and a heating time, the drying parameter control model is trained with multiple groups of training data, each group of the training data includes a historical clothes mass, a corresponding historical forward stacking height value, a corresponding historical unfolded area, a corresponding historical distribution state parameter and a corresponding historical drying parameter group; a first control unit, used to control the washing machine to dry according to the drying parameter group.

[0015] According to another aspect of the present application, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, any one of the methods described above is implemented.

[0016] According to another aspect of the present application, a drying management system is provided, comprising: a plurality of washing machines of the same type, a remote server, 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 methods for executing any one of the described methods.

[0017] By applying the technical solution of the present application, in the drying control method of the above-mentioned washing machine, by acquiring the image of the clothes to be dried and the clothes mass of the clothes to be dried, image recognition is performed on the image of the clothes to be dried, and the forward stacking height value, the unfolding area and the distribution state parameters of the clothes to be dried are obtained. The clothes mass, the forward stacking height value, the unfolding area and the distribution state are input into the input parameters of the drying parameter control model, and a drying parameter group is obtained by analysis, including the inner drum speed, the fan speed and the heating time. The washing machine can be controlled to dry according to the drying parameter group. Compared with the prior art that uses a single parameter of clothes mass to analyze the drying parameters, the present application uses clothes mass, the forward stacking height value, the unfolding area and the distribution state to analyze the drying parameter group suitable for the clothes to be dried from multiple dimensions, so as to facilitate the training of a drying parameter control model that accurately predicts the drying parameters, thereby greatly improving the drying quality of the washing machine and solving the problem of poor drying quality of the washing machine in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A hardware structure block diagram of a mobile terminal for executing a drying control method for a washing machine provided in an embodiment of the present application is shown;

[0019] Figure 2 A schematic flow chart of a drying control method for a washing machine provided according to an embodiment of the present application is shown;

[0020] Figure 3 A schematic diagram of a neural network of a drying parameter control model provided according to an embodiment of the present application is shown;

[0021] Figure 4 A schematic diagram showing the overall outline of clothes to be dried provided according to an embodiment of the present application is shown;

[0022] Figure 5 A structural block diagram of a drying control device for a washing machine provided according to an embodiment of the present application is shown.

[0023] The above drawings include the following reference numerals:

[0024] 102, processor; 104, memory; 106, transmission device; 108, input and output devices. DETAILED DESCRIPTION

[0025] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present 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 solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present 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 comprising 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 drying quality of washing machines in the prior art is poor. To solve this technical problem, the embodiments of the present application provide a drying control method, device, computer program product and drying management system for a washing machine.

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

[0030] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 FIG. 1 is a hardware structure block diagram of a mobile terminal of a washing machine drying control method according to an embodiment of the present invention. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0031] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the drying control method of the washing machine in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, the above method is implemented. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. The transmission device 106 is used to receive or send data via a network. The above-mentioned specific examples of the network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0032] In this embodiment, a drying control method for a washing machine running on a mobile terminal, a computer terminal or a similar computing device is provided. 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.

[0033] Figure 2 1 is a flow chart of a drying control method for a washing machine according to an embodiment of the present application. Figure 2 As shown, the method comprises the following steps:

[0034] Step S201, an acquisition step, in which, when the washing machine is in a drying stage, an image of the clothes to be dried and the mass of the clothes to be dried are acquired, wherein the image of the clothes to be dried includes all images of the clothes to be dried, and the mass of the clothes is the sum of the masses of all the clothes to be dried;

[0035] Step S202, a recognition step, performing image recognition on the image of the clothes to be dried to obtain a positive stacking height value, an expanded area and a distribution state parameter of the clothes to be dried, wherein the positive stacking height value is a height of the clothes to be dried as a whole in a vertical direction, the expanded area is an area occupied by the overall outline of the clothes to be dried, and the distribution state parameter is a distribution ratio of the clothes to be dried in a plurality of equally divided areas on the image of the clothes to be dried;

[0036] Step S203, inputting the above-mentioned clothing mass, the above-mentioned forward stacking height value, the above-mentioned unfolding area and the above-mentioned distribution state into a drying parameter control model to obtain a drying parameter group, wherein the above-mentioned drying parameter group includes an inner drum speed, a fan speed and a heating time, and the above-mentioned drying parameter control model is obtained by training with multiple groups of training data, and each group of the above-mentioned training data includes a historical clothing mass, a corresponding historical forward stacking height value, a corresponding historical unfolding area, a corresponding historical distribution state parameter and a corresponding historical drying parameter group;

[0037] Step S204, controlling the washing machine to dry according to the drying parameter group.

[0038] In the drying control method of the above-mentioned washing machine, by obtaining the image of the clothes to be dried and the clothes mass of the clothes to be dried, image recognition is performed on the image of the clothes to be dried, and the forward stacking height value, the unfolding area and the distribution state parameters of the above-mentioned clothes to be dried are obtained. The clothes mass, the forward stacking height value, the unfolding area and the distribution state are input into the input parameters of the drying parameter control model, and the drying parameter group is obtained by analysis, including the inner drum speed, the fan speed and the heating time. The above-mentioned washing machine can be controlled to dry according to the drying parameter group. Compared with the prior art that uses a single parameter of clothes mass to analyze the drying parameters, the present application uses clothes mass, the forward stacking height value, the unfolding area and the distribution state to analyze the drying parameter group suitable for the clothes to be dried from multiple dimensions, so as to facilitate the training of a drying parameter control model that accurately predicts the drying parameters, thereby greatly improving the drying quality of the washing machine and solving the problem of poor drying quality of the washing machine in the prior art.

[0039] In order to further improve the drying quality, in an optional implementation manner, after performing image recognition on the above-mentioned image of the clothes to be dried to obtain the forward stacking height value, the unfolded area and the distribution state parameters of the above-mentioned clothes to be dried, the above-mentioned method further includes:

[0040] Step S301, an analysis step, inputting the above-mentioned clothing mass, the above-mentioned forward stacking height value, the above-mentioned unfolding area and the above-mentioned distribution state into the above-mentioned drying parameter control model to obtain the above-mentioned drying parameter group, the above-mentioned drying parameter group includes clothing amount type, cycle number, the above-mentioned inner drum speed, the above-mentioned fan speed and the above-mentioned heating time, the above-mentioned clothing amount type is one of multiple types of clothing amount from low to high, the above-mentioned cycle number is the number of cycles expected to be experienced in the drying process, and the above-mentioned drying parameter control model is obtained by training with multiple groups of the above-mentioned training data, and each group of the above-mentioned training data includes historical clothing mass, corresponding historical forward stacking height value, corresponding historical unfolding area, corresponding historical distribution state parameter and corresponding historical drying parameter group;

[0041] Step S302, a drying step, controlling the washing machine to dry for one cycle according to the inner drum speed, the fan speed and the single-cycle heating time, wherein the single-cycle heating time is the ratio of the heating time to the number of cycles;

[0042] Step S303, repeat the above-mentioned acquisition step, the above-mentioned identification step, the above-mentioned analysis step and the above-mentioned drying step in sequence at least once, and in each repeated drying step, update the value of the above-mentioned drying parameter group of the current cycle to the average value of the above-mentioned drying parameter group of the current cycle and the value of the above-mentioned drying parameter group of the previous cycle, until the current number of cycles is 1 or the number of cycles reaches the maximum number of cycles.

[0043] In the above implementation mode, if Figure 3 As shown, the above-mentioned clothing mass g, the above-mentioned forward stacking height value h, the above-mentioned unfolding area s and the above-mentioned distribution state θ are input into the above-mentioned drying parameter control model to obtain the above-mentioned drying parameter group, which includes the clothing amount type N, the number of cycles p, the above-mentioned inner drum speed V 内 , the above fan speed V 风 and the above-mentioned heating time S. The prediction model predicts the n types corresponding to the current amount of clothes through the calculation of multi-layer neurons according to the four parameters passed in. After the type of clothes is determined, the corresponding drying process is divided into corresponding P cycles, and the specific operating values ​​of the three parameters of the inner drum speed, the wind speed of the fan, and the heating time of the heating mechanism during each drying cycle are determined. An example of the prediction result is shown in Table 1. After taking a photo of the clothes to be dried in the barrel for the first time, the model predicts that the current amount of clothes is large and belongs to the i-th type, and the number of subsequent drying cycles is set to p, and the inner drum speed V in each drying cycle is set to 0. 内 , wind speed V of the fan 风, and the heating time S of the heating mechanism are set to the corresponding preset values. At the same time, in order to further optimize the entire drying process and achieve the purpose of dynamic adjustment, in the prediction results, the clothes in the barrel are photographed and predicted after each cycle, and the parameter value group for the next cycle obtained is compared with the value predicted for the first time before the start of drying, and the median value of the two is selected as the parameter value for the next operation. Therefore, in order to ensure that the washing machine performs drying work in the best state in each cycle, prediction is performed again after each subsequent cycle and the optimal program is calculated for execution.

[0044] Table 1

[0045]

[0046] In order to ensure the improvement of drying quality, in an optional implementation, the training process of the drying parameter control model includes:

[0047] Step S401, obtaining a plurality of drying records with qualified drying quality, wherein the drying records include a historical input parameter group and a corresponding historical drying parameter group, wherein the historical input parameter group includes the historical clothing quality, the corresponding historical forward stacking height value, the corresponding historical unfolding area, and the corresponding historical distribution state parameter;

[0048] Step S402, inputting each of the above historical input parameter groups into a neural network model to obtain a plurality of predicted drying parameter groups;

[0049] Step S403, adjusting the parameters of the neural network model according to the errors between each of the predicted drying parameter groups and the corresponding historical drying parameter groups, until all of the errors are smaller than the corresponding predetermined thresholds, thereby obtaining the drying parameter control model.

[0050] In the above implementation, historical operation data of the washing machine is collected, including the forward stacking height value h of the clothes in the drum, the expansion area s, the mass of clothes g, the distribution state parameter θ of the current clothes in the drum, and the subsequent program execution process corresponding to the above related parameters (including: when the drying process is divided into multiple cycles, the specific operating values ​​of the three parameters of the number of cycles determined by different parameters, the inner drum speed during drying in each cycle, the wind speed of the fan, and the heating time of the heating mechanism). The forward stacking height value h, the expansion area s, the mass of clothes g and the distribution state parameter θ of the current clothes in the drum are regarded as one data point. Then, the collected data is cleaned and preprocessed to remove noise, outliers and redundant information, and finally the data is labeled to clarify the subsequent execution process corresponding to each data point. Select a machine learning model suitable for sequence prediction or classification, select a multi-layer feedforward neural network (BP neural network) model, and use the labeled data to train the model, and adjust the model parameters to optimize the prediction performance.

[0051] In order to obtain training data, in an optional implementation, the above step S401 includes:

[0052] Step S4011, obtaining a plurality of original drying records with qualified drying quality;

[0053] Step S4012, preprocessing the original drying record to obtain the drying record, wherein the preprocessing is used to remove noise, abnormal values ​​and redundant information.

[0054] In the above implementation, the stacking height h, the unfolding area s, the mass g in the drum and the distribution state parameter θ of the clothes in the drum are regarded as a data point. Then, the collected data is cleaned and preprocessed to remove noise, abnormal values ​​and redundant information, and finally the data is labeled to clarify the subsequent execution process corresponding to each data point.

[0055] In order to calculate the input parameters, in an optional implementation, the above step S202 includes:

[0056] Step S2021, performing image segmentation on the clothes to be dried and the washing machine in the clothes to be dried image to obtain an overall contour of the clothes to be dried, wherein the overall contour of the clothes to be dried is an overall contour composed of all the clothes to be dried;

[0057] Step S2022, measuring the forward stacking height value according to the overall profile of the clothes to be dried;

[0058] Step S2023, calculating the unfolded area according to the overall outline of the clothes to be dried;

[0059] Step S2024, dividing the above-mentioned image of the clothes to be dried into a plurality of equal areas;

[0060] Step S2025, calculating the ratio of the area occupied by the overall outline of the clothes to be dried in each of the above regions to the above unfolded area, and obtaining a plurality of the above distribution state parameters.

[0061] In the above embodiment, the first camera is installed in a suitable area directly in front of the washing machine to shoot the front of the inner drum of the washing machine. Based on the semantic segmentation technology of computer vision, a large number of images are marked and the marked images are made into a data set; the data set is trained in the MobileU-net model of the convolutional neural network (CNN). The model obtained through training can accurately recognize the real-time captured images and realize the accurate segmentation of the independent areas between the clothes and the washing machine. Therefore, after the pre-processing stage of dehydration is completed, the first camera is used to shoot the front image in the drum, the acquired image is sent to the remote server, and the clothes are segmented from the drum wall by the segmentation algorithm, and finally the positive stacking height value h of the clothes at the current stage is measured. The second camera is installed in the upper area directly in front of the washing machine. After the program execution of the pre-processing stage is completed, the inner drum of the washing machine is taken obliquely downward, and the expansion area s of the clothes in the inner drum of the washing machine in the inner barrel wall is identified through image segmentation. It is worth noting that when the clothes in the drum have the same stacking height h and unfolding area s, the state of the clothes in the inner drum cannot be uniquely determined, and different distribution states of clothes will also have different effects on the subsequent drying control process; therefore, in addition to the stacking height and unfolding area, another variable needs to be introduced to describe the current distribution state of the clothes in the inner drum, so the clothing distribution state parameter θ is introduced in this patent. In addition to obtaining the area parameter through the second camera, the distribution state parameter θ of the clothes in the drum needs to be calculated using semantic segmentation technology. When calculating the distribution state parameter, such as Figure 4 As shown, the shaded part representing the clothes is divided into four parts by drawing two cross-cutting lines with the center of the entire picture as the midpoint. The clothes are calculated by calculating the number of pixels in the four parts and the percentage of clothing pixels in all pixels in the entire quadrant to obtain a set of data within 100 (such as (20, 25, 10, 5) according to the four quadrants). Finally, the values ​​of the four quadrants are input into the prediction network according to (θ1, θ2, θ3, θ4).

[0062] In order to calculate the input parameters, in an optional implementation manner, before the washing machine enters the drying stage, the method further includes:

[0063] Step S501: deploy the drying parameter control model on a remote server, so that the remote server performs drying control on all washing machines of the same type.

[0064] In the above implementation, the trained prediction model (drying parameter control model) is deployed on the remote server, and the remote server can perform drying control on all the above washing machines of the same type. After the pre-processing stage is completed, the clothes in the drum are photographed by the two cameras in front, and the photos in the drum are transmitted to the remote server after obtaining the photos. Relying on the high performance of the remote server, the photos can be quickly processed. After receiving the photos, the remote server inputs them into the semantic segmentation model, and the stacking height h, expansion area s and distribution state parameter θ of the clothes in the current photo in the drum of the washing machine are obtained through the segmentation processing of the model. The total mass g of the clothes in the drum is calculated locally by the weighing module in the washing machine body. So far, the four parameters of stacking height h, expansion area s, distribution state parameter θ, and total mass g of the clothes in the drum are obtained, and the four parameters are set as a parameter group, and then the total mass g of the clothes in the drum is also sent to the remote server for subsequent processing. After receiving the parameter g, the remote server inputs the other three parameters obtained by itself into the prediction model. The prediction model predicts the n types corresponding to the current amount of clothing based on the four parameters passed in through the calculation of multiple layers of neurons. After determining the type of clothing amount, the corresponding drying process is divided into P corresponding cycles, and the specific operating values ​​of the three parameters of the inner drum speed, the fan speed, and the heating time of the heating mechanism during each drying cycle are determined.

[0065] In order to ensure that the clothes to be dried are loose, in an optional implementation manner, before the washing machine enters the drying stage, the method further includes:

[0066] Step S601, controlling the washing machine to execute a shaking program, wherein the shaking program is a program for controlling the washing machine to shake so as to loosen the clothes to be dried.

[0067] In the above implementation, after the dehydration stage is completed and before the drying stage begins, since the clothes have been dehydrated at a relatively high speed, they are in a state of being close to the drum wall, which is not conducive to the subsequent drying process. In order to ensure that the clothes to be dried are as loose as possible, it is necessary to perform a shaking procedure before drying. At the same time, in order to ensure the accuracy of subsequent prediction results, a relatively unified reference standard needs to be established before the drying starts to reduce the influence of other irrelevant or redundant features, so a pre-processing process needs to be introduced. For example, the washing machine is rotated forward and reverse at a relatively low specific speed for a certain period of time so that the clothes in the drum are uniformly processed to facilitate the prediction of subsequent processing processes for different amounts of clothes.

[0068] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0069] The embodiment of the present application also provides a drying control device for a washing machine. It should be noted that the drying control device for the washing machine in the embodiment of the present application can be used to execute the drying control method for the washing machine provided in the embodiment of the present application. The device is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0070] The following is an introduction to the drying control device of the washing machine provided in the embodiment of the present application.

[0071] Figure 5 is a structural block diagram of a drying control device for a washing machine according to an embodiment of the present application. Figure 5 As shown, the device comprises:

[0072] The acquisition unit 10 is used to perform an acquisition step, in which, when the washing machine is in a drying stage, an image of the clothes to be dried and a mass of the clothes to be dried are acquired, wherein the image of the clothes to be dried includes all images of the clothes to be dried, and the mass of the clothes is the sum of the masses of all the clothes to be dried;

[0073] The recognition unit 20 is used to perform the recognition step, perform image recognition on the image of the clothes to be dried, and obtain a positive stacking height value, an expanded area, and a distribution state parameter of the clothes to be dried, wherein the positive stacking height value is the height of the clothes to be dried as a whole in the vertical direction, the expanded area is the area occupied by the overall outline of the clothes to be dried, and the distribution state parameter is the distribution ratio of the clothes to be dried in multiple equally divided areas on the image of the clothes to be dried;

[0074] The first analysis unit 30 is used to input the above-mentioned clothing mass, the above-mentioned forward stacking height value, the above-mentioned unfolding area and the above-mentioned distribution state into a drying parameter control model to obtain a drying parameter group, wherein the above-mentioned drying parameter group includes an inner drum speed, a fan speed and a heating time, and the above-mentioned drying parameter control model is obtained by training with multiple groups of training data, and each group of the above-mentioned training data includes a historical clothing mass, a corresponding historical forward stacking height value, a corresponding historical unfolding area, a corresponding historical distribution state parameter and a corresponding historical drying parameter group;

[0075] The first control unit 40 is used to control the washing machine to dry according to the drying parameter group.

[0076] In the drying control device of the above-mentioned washing machine, by acquiring the image of the clothes to be dried and the clothes mass of the clothes to be dried, image recognition is performed on the image of the clothes to be dried, and the forward stacking height value, unfolding area and distribution state parameters of the above-mentioned clothes to be dried are obtained. The clothes mass, forward stacking height value, unfolding area and distribution state are input into the input parameters of the drying parameter control model, and a drying parameter group is obtained by analysis, including the inner drum speed, the fan speed and the heating time. The above-mentioned washing machine can be controlled to dry according to the drying parameter group. Compared with the prior art that uses a single parameter of clothes mass to analyze the drying parameters, the present application uses clothes mass, forward stacking height value, unfolding area and distribution state to analyze the drying parameter group suitable for the clothes to be dried from multiple dimensions, so as to facilitate the training of a drying parameter control model that accurately predicts the drying parameters, thereby greatly improving the drying quality of the washing machine and solving the problem of poor drying quality of the washing machine in the prior art.

[0077] In order to further improve the drying quality, in an optional implementation manner, the above device further includes:

[0078] a second analysis unit for executing an analysis step, wherein after performing image recognition on the image of the clothes to be dried and obtaining the forward stacking height value, the unfolding area and the distribution state parameters of the clothes to be dried, the clothes mass, the forward stacking height value, the unfolding area and the distribution state are input into the drying parameter control model to obtain the drying parameter group, wherein the drying parameter group includes the type of clothes quantity, the number of cycles, the inner drum speed, the fan speed and the heating time, the type of clothes quantity is one of a plurality of types of clothes quantity from low to high, the number of cycles is the number of cycles expected to be experienced in the drying process, and the drying parameter control model is obtained by training with a plurality of sets of the training data, wherein each set of the training data includes a historical clothes mass, a corresponding historical forward stacking height value, a corresponding historical unfolding area, a corresponding historical distribution state parameter and a corresponding historical drying parameter group;

[0079] A second control unit is used to execute a drying step, and control the washing machine to dry for one cycle according to the inner drum speed, the fan speed and the single-cycle heating time, wherein the single-cycle heating time is the ratio of the heating time to the number of cycles;

[0080] A repeating unit is used to sequentially repeat the acquisition step, the identification step, the analysis step and the drying step at least once, and in each repeated drying step, update the value of the drying parameter group of the current cycle to the average value of the drying parameter group of the current cycle and the value of the drying parameter group of the previous cycle, until the current number of cycles is 1 or the number of cycles reaches the maximum number of cycles.

[0081] In the above implementation mode, if Figure 3 As shown, the above-mentioned clothing mass g, the above-mentioned forward stacking height value h, the above-mentioned unfolding area s and the above-mentioned distribution state θ are input into the above-mentioned drying parameter control model to obtain the above-mentioned drying parameter group, which includes the clothing amount type N, the number of cycles p, the above-mentioned inner drum speed V 内 , the above fan speed V 风 and the above-mentioned heating time S. The prediction model predicts the n types corresponding to the current amount of clothes through the calculation of multi-layer neurons according to the four parameters passed in. After the type of clothes is determined, the corresponding drying process is divided into corresponding P cycles, and the specific operating values ​​of the three parameters of the inner drum speed, the wind speed of the fan, and the heating time of the heating mechanism during each drying cycle are determined. An example of the prediction result is shown in Table 1. After taking a photo of the clothes to be dried in the barrel for the first time, the model predicts that the current amount of clothes is large and belongs to the i-th type, and the number of subsequent drying cycles is set to p, and the inner drum speed V in each drying cycle is set to 0. 内 , wind speed V of the fan 风 , and the heating time S of the heating mechanism are set to the corresponding preset values. At the same time, in order to further optimize the entire drying process and achieve the purpose of dynamic adjustment, in the prediction results, the clothes in the barrel are photographed and predicted after each cycle, and the parameter value group for the next cycle obtained is compared with the value predicted for the first time before the start of drying, and the median value of the two is selected as the parameter value for the next operation. Therefore, in order to ensure that the washing machine performs drying work in the best state in each cycle, prediction is performed again after each subsequent cycle and the optimal program is calculated for execution.

[0082] In order to ensure the improvement of drying quality, in an optional implementation, the device includes a training unit, and the training unit includes:

[0083] an acquisition module, for acquiring a plurality of drying records with qualified drying quality, wherein the drying records include a historical input parameter group and a corresponding historical drying parameter group, wherein the historical input parameter group includes the historical clothing quality, the corresponding historical forward stacking height value, the corresponding historical unfolding area, and the corresponding historical distribution state parameter;

[0084] A training module, used for inputting each of the above historical input parameter groups into a neural network model to obtain a plurality of predicted drying parameter groups;

[0085] The adjustment module is used to adjust the parameters of the neural network model according to the errors between each of the predicted drying parameter groups and the corresponding historical drying parameter groups, until all of the errors are less than the corresponding predetermined thresholds, thereby obtaining the drying parameter control model.

[0086] In the above implementation, historical operation data of the washing machine is collected, including the forward stacking height value h of the clothes in the drum, the expansion area s, the mass of clothes g, the distribution state parameter θ of the current clothes in the drum, and the subsequent program execution process corresponding to the above related parameters (including: when the drying process is divided into multiple cycles, the specific operating values ​​of the three parameters of the number of cycles determined by different parameters, the inner drum speed during drying in each cycle, the wind speed of the fan, and the heating time of the heating mechanism). The forward stacking height value h, the expansion area s, the mass of clothes g and the distribution state parameter θ of the current clothes in the drum are regarded as one data point. Then, the collected data is cleaned and preprocessed to remove noise, outliers and redundant information, and finally the data is labeled to clarify the subsequent execution process corresponding to each data point. Select a machine learning model suitable for sequence prediction or classification, select a multi-layer feedforward neural network (BP neural network) model, and use the labeled data to train the model, and adjust the model parameters to optimize the prediction performance.

[0087] In order to obtain training data, in an optional implementation, the acquisition module includes:

[0088] An acquisition submodule is used to acquire a plurality of original drying records with qualified drying quality;

[0089] The processing submodule is used to pre-process the original drying record to obtain the drying record, and the pre-processing is used to remove noise, abnormal values ​​and redundant information.

[0090] In the above implementation, the stacking height h, the unfolding area s, the mass g in the drum and the distribution state parameter θ of the clothes in the drum are regarded as a data point. Then, the collected data is cleaned and preprocessed to remove noise, abnormal values ​​and redundant information, and finally the data is labeled to clarify the subsequent execution process corresponding to each data point.

[0091] In order to calculate the input parameters, in an optional implementation, the identification unit includes:

[0092] a segmentation module, configured to perform image segmentation on the clothes to be dried and the washing machine in the clothes to be dried image to obtain an overall contour of the clothes to be dried, wherein the overall contour of the clothes to be dried is an overall contour composed of all the clothes to be dried;

[0093] A measuring module, used for measuring the forward stacking height value according to the overall profile of the clothes to be dried;

[0094] A first calculation module, used for calculating the above-mentioned unfolding area according to the overall outline of the above-mentioned clothes to be dried;

[0095] A division module, used for dividing the above-mentioned image of the clothes to be dried into a plurality of equal areas;

[0096] The second calculation module is used to calculate the ratio of the area occupied by the overall outline of the above-mentioned clothes to be dried in each of the above-mentioned regions to the above-mentioned unfolded area, so as to obtain a plurality of the above-mentioned distribution state parameters.

[0097] In the above embodiment, the first camera is installed in a suitable area directly in front of the washing machine to shoot the front of the inner drum of the washing machine. Based on the semantic segmentation technology of computer vision, a large number of images are marked and the marked images are made into a data set; the data set is trained in the MobileU-net model of the convolutional neural network (CNN). The model obtained through training can accurately recognize the real-time captured images and realize the accurate segmentation of the independent areas between the clothes and the washing machine. Therefore, after the pre-processing stage of dehydration is completed, the first camera is used to shoot the front image in the drum, the acquired image is sent to the remote server, and the clothes are segmented from the drum wall by the segmentation algorithm, and finally the positive stacking height value h of the clothes at the current stage is measured. The second camera is installed in the upper area directly in front of the washing machine. After the program execution of the pre-processing stage is completed, the inner drum of the washing machine is taken obliquely downward, and the expansion area s of the clothes in the inner drum of the washing machine in the inner barrel wall is identified through image segmentation. It is worth noting that when the clothes in the drum have the same stacking height h and unfolding area s, the state of the clothes in the inner drum cannot be uniquely determined, and different distribution states of clothes will also have different effects on the subsequent drying control process; therefore, in addition to the stacking height and unfolding area, another variable needs to be introduced to describe the current distribution state of the clothes in the inner drum, so the clothing distribution state parameter θ is introduced in this patent. In addition to obtaining the area parameter through the second camera, the distribution state parameter θ of the clothes in the drum needs to be calculated using semantic segmentation technology. When calculating the distribution state parameter, such as Figure 4 As shown, the shaded part representing the clothes is divided into four parts by drawing two cross-cutting lines with the center of the entire picture as the midpoint. The clothes are calculated by calculating the number of pixels in the four parts and the percentage of clothing pixels in all pixels in the entire quadrant to obtain a set of data within 100 (such as (20, 25, 10, 5) according to the four quadrants). Finally, the values ​​of the four quadrants are input into the prediction network according to (θ1, θ2, θ3, θ4).

[0098] In order to calculate the input parameters, in an optional implementation manner, the above-mentioned device further includes:

[0099] The deployment unit is used to deploy the drying parameter control model on a remote server before the washing machine enters the drying stage, so that the remote server performs drying control on all the washing machines of the same type.

[0100] In the above implementation, the trained prediction model (drying parameter control model) is deployed on the remote server, and the remote server can perform drying control on all the above washing machines of the same type. After the pre-processing stage is completed, the clothes in the drum are photographed by the two cameras in front, and the photos in the drum are transmitted to the remote server after obtaining the photos. Relying on the high performance of the remote server, the photos can be quickly processed. After receiving the photos, the remote server inputs them into the semantic segmentation model, and the stacking height h, expansion area s and distribution state parameter θ of the clothes in the current photo in the drum of the washing machine are obtained through the segmentation processing of the model. The total mass g of the clothes in the drum is calculated locally by the weighing module in the washing machine body. So far, the four parameters of stacking height h, expansion area s, distribution state parameter θ, and total mass g of the clothes in the drum are obtained, and the four parameters are set as a parameter group, and then the total mass g of the clothes in the drum is also sent to the remote server for subsequent processing. After receiving the parameter g, the remote server inputs the other three parameters obtained by itself into the prediction model. The prediction model predicts the n types corresponding to the current amount of clothing based on the four parameters passed in through the calculation of multiple layers of neurons. After determining the type of clothing amount, the corresponding drying process is divided into P corresponding cycles, and the specific operating values ​​of the three parameters of the inner drum speed, the fan speed, and the heating time of the heating mechanism during each drying cycle are determined.

[0101] In order to ensure that the clothes to be dried are loose, in an optional embodiment, the device further includes:

[0102] The third control unit is used to control the washing machine to execute a shaking program before the washing machine enters a drying stage. The shaking program is a program for controlling the washing machine to shake so that the clothes to be dried are loosened.

[0103] In the above implementation, after the dehydration stage is completed and before the drying stage begins, since the clothes have been dehydrated at a relatively high speed, they are in a state of being close to the drum wall, which is not conducive to the subsequent drying process. In order to ensure that the clothes to be dried are as loose as possible, it is necessary to perform a shaking procedure before drying. At the same time, in order to ensure the accuracy of subsequent prediction results, a relatively unified reference standard needs to be established before the drying starts to reduce the influence of other irrelevant or redundant features, so a pre-processing process needs to be introduced. For example, the washing machine is rotated forward and reverse at a relatively low specific speed for a certain period of time so that the clothes in the drum are uniformly processed to facilitate the prediction of subsequent processing processes for different amounts of clothes.

[0104] The drying control device of the washing machine includes a processor and a memory. The acquisition unit, the identification unit, the first analysis unit and the first control unit are stored in the memory as program units, and the processor executes the program units stored in the memory to implement corresponding functions. The modules are all located in the same processor; or, the modules are located in different processors in any combination.

[0105] The processor includes a kernel, and the kernel retrieves the corresponding program unit from the memory. One or more kernels can be provided, and the problem of poor drying quality of the washing machine in the prior art can be solved by adjusting the kernel parameters.

[0106] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0107] An embodiment of the present invention provides a computer-readable storage medium, wherein 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 drying control method of the washing machine.

[0108] Specifically, the drying control method of the washing machine includes:

[0109] Step S201, an acquisition step, in which, when the washing machine is in a drying stage, an image of the clothes to be dried and the mass of the clothes to be dried are acquired, wherein the image of the clothes to be dried includes all images of the clothes to be dried, and the mass of the clothes is the sum of the masses of all the clothes to be dried;

[0110] Step S202, a recognition step, performing image recognition on the image of the clothes to be dried to obtain a positive stacking height value, an expanded area and a distribution state parameter of the clothes to be dried, wherein the positive stacking height value is a height of the clothes to be dried as a whole in a vertical direction, the expanded area is an area occupied by the overall outline of the clothes to be dried, and the distribution state parameter is a distribution ratio of the clothes to be dried in a plurality of equally divided areas on the image of the clothes to be dried;

[0111] Step S203, inputting the above-mentioned clothing mass, the above-mentioned forward stacking height value, the above-mentioned unfolding area and the above-mentioned distribution state into a drying parameter control model to obtain a drying parameter group, wherein the above-mentioned drying parameter group includes an inner drum speed, a fan speed and a heating time, and the above-mentioned drying parameter control model is obtained by training with multiple groups of training data, and each group of the above-mentioned training data includes a historical clothing mass, a corresponding historical forward stacking height value, a corresponding historical unfolding area, a corresponding historical distribution state parameter and a corresponding historical drying parameter group;

[0112] Step S204, controlling the washing machine to dry according to the drying parameter group.

[0113] An embodiment of the present invention provides a processor, and the processor is used to run a program, wherein the drying control method of the washing machine is executed when the program is run.

[0114] Specifically, the drying control method of the washing machine includes:

[0115] Step S201, an acquisition step, in which, when the washing machine is in a drying stage, an image of the clothes to be dried and the mass of the clothes to be dried are acquired, wherein the image of the clothes to be dried includes all images of the clothes to be dried, and the mass of the clothes is the sum of the masses of all the clothes to be dried;

[0116] Step S202, a recognition step, performing image recognition on the image of the clothes to be dried to obtain a positive stacking height value, an expanded area and a distribution state parameter of the clothes to be dried, wherein the positive stacking height value is a height of the clothes to be dried as a whole in a vertical direction, the expanded area is an area occupied by the overall outline of the clothes to be dried, and the distribution state parameter is a distribution ratio of the clothes to be dried in a plurality of equally divided areas on the image of the clothes to be dried;

[0117] Step S203, inputting the above-mentioned clothing mass, the above-mentioned forward stacking height value, the above-mentioned unfolding area and the above-mentioned distribution state into a drying parameter control model to obtain a drying parameter group, wherein the above-mentioned drying parameter group includes an inner drum speed, a fan speed and a heating time, and the above-mentioned drying parameter control model is obtained by training with multiple groups of training data, and each group of the above-mentioned training data includes a historical clothing mass, a corresponding historical forward stacking height value, a corresponding historical unfolding area, a corresponding historical distribution state parameter and a corresponding historical drying parameter group;

[0118] Step S204, controlling the washing machine to dry according to the drying parameter group.

[0119] An embodiment of the present invention provides a drying management system, including a plurality of washing machines of the same type, a remote server, a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, at least the following steps are implemented:

[0120] Step S201, an acquisition step, in which, when the washing machine is in a drying stage, an image of the clothes to be dried and the mass of the clothes to be dried are acquired, wherein the image of the clothes to be dried includes all images of the clothes to be dried, and the mass of the clothes is the sum of the masses of all the clothes to be dried;

[0121] Step S202, a recognition step, performing image recognition on the image of the clothes to be dried to obtain a positive stacking height value, an expanded area and a distribution state parameter of the clothes to be dried, wherein the positive stacking height value is a height of the clothes to be dried as a whole in a vertical direction, the expanded area is an area occupied by the overall outline of the clothes to be dried, and the distribution state parameter is a distribution ratio of the clothes to be dried in a plurality of equally divided areas on the image of the clothes to be dried;

[0122] Step S203, inputting the above-mentioned clothing mass, the above-mentioned forward stacking height value, the above-mentioned unfolding area and the above-mentioned distribution state into a drying parameter control model to obtain a drying parameter group, wherein the above-mentioned drying parameter group includes an inner drum speed, a fan speed and a heating time, and the above-mentioned drying parameter control model is obtained by training with multiple groups of training data, and each group of the above-mentioned training data includes a historical clothing mass, a corresponding historical forward stacking height value, a corresponding historical unfolding area, a corresponding historical distribution state parameter and a corresponding historical drying parameter group;

[0123] Step S204, controlling the washing machine to dry according to the drying parameter group.

[0124] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program for initializing at least the following method steps:

[0125] Step S201, an acquisition step, in which, when the washing machine is in a drying stage, an image of the clothes to be dried and the mass of the clothes to be dried are acquired, wherein the image of the clothes to be dried includes all images of the clothes to be dried, and the mass of the clothes is the sum of the masses of all the clothes to be dried;

[0126] Step S202, a recognition step, performing image recognition on the image of the clothes to be dried to obtain a positive stacking height value, an expanded area and a distribution state parameter of the clothes to be dried, wherein the positive stacking height value is a height of the clothes to be dried as a whole in a vertical direction, the expanded area is an area occupied by the overall outline of the clothes to be dried, and the distribution state parameter is a distribution ratio of the clothes to be dried in a plurality of equally divided areas on the image of the clothes to be dried;

[0127] Step S203, inputting the above-mentioned clothing mass, the above-mentioned forward stacking height value, the above-mentioned unfolding area and the above-mentioned distribution state into a drying parameter control model to obtain a drying parameter group, wherein the above-mentioned drying parameter group includes an inner drum speed, a fan speed and a heating time, and the above-mentioned drying parameter control model is obtained by training with multiple groups of training data, and each group of the above-mentioned training data includes a historical clothing mass, a corresponding historical forward stacking height value, a corresponding historical unfolding area, a corresponding historical distribution state parameter and a corresponding historical drying parameter group;

[0128] Step S204, controlling the washing machine to dry according to the drying parameter group.

[0129] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0130] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may 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 may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0131] 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 generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. 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.

[0132] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate 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 A function specified in one or more boxes.

[0133] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0134] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0135] 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.

[0136] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. 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 disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape 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 temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0137] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0138] From the above description, it can be seen that the above embodiments of the present application achieve the following technical effects:

[0139] 1) In the drying control method of the washing machine of the present application, by acquiring the image of the clothes to be dried and the clothes mass of the clothes to be dried, image recognition is performed on the image of the clothes to be dried, and the forward stacking height value, the unfolding area and the distribution state parameters of the above-mentioned clothes to be dried are obtained. The clothes mass, the forward stacking height value, the unfolding area and the distribution state are input into the input parameters of the drying parameter control model, and the drying parameter group is obtained by analysis, including the inner drum speed, the fan speed and the heating time. The above-mentioned washing machine can be controlled to dry according to the drying parameter group. Compared with the prior art that uses a single parameter of clothes mass to analyze the drying parameters, the present application uses clothes mass, the forward stacking height value, the unfolding area and the distribution state to analyze the drying parameter group suitable for the clothes to be dried from multiple dimensions, so as to facilitate the training of a drying parameter control model that accurately predicts the drying parameters, thereby greatly improving the drying quality of the washing machine and solving the problem of poor drying quality of the washing machine in the prior art.

[0140] 2) In the drying control device of the washing machine of the present application, by acquiring the image of the clothes to be dried and the clothes mass of the clothes to be dried, image recognition is performed on the image of the clothes to be dried, and the forward stacking height value, unfolding area and distribution state parameters of the above-mentioned clothes to be dried are obtained. The clothes mass, forward stacking height value, unfolding area and distribution state are input into the input parameters of the drying parameter control model, and a drying parameter group is obtained by analysis, including the inner drum speed, the fan speed and the heating time. The above-mentioned washing machine can be controlled to dry according to the drying parameter group. Compared with the prior art that uses a single parameter of clothes mass to analyze the drying parameters, the present application uses clothes mass, forward stacking height value, unfolding area and distribution state to analyze the drying parameter group suitable for the clothes to be dried from multiple dimensions, so as to facilitate the training of a drying parameter control model that accurately predicts the drying parameters, thereby greatly improving the drying quality of the washing machine and solving the problem of poor drying quality of the washing machine in the prior art.

[0141] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A drying control method for a washing machine, characterized in that: include: an acquisition step, when the washing machine is in a drying stage, acquiring an image of the clothes to be dried and a mass of the clothes to be dried, wherein the image of the clothes to be dried includes images of all the clothes to be dried, and the mass of the clothes is the sum of the masses of all the clothes to be dried; an identification step of performing image recognition on the image of the clothes to be dried to obtain a forward stacking height value, an expanded area, and a distribution state parameter of the clothes to be dried, wherein the forward stacking height value is a height of the clothes to be dried as a whole in a vertical direction, the expanded area is an area occupied by the overall outline of the clothes to be dried, and the distribution state parameter is a distribution ratio of the clothes to be dried in a plurality of equally divided areas on the image of the clothes to be dried; The clothing mass, the forward stacking height value, the unfolded area and the distribution state are input into a drying parameter control model to obtain a drying parameter group, wherein the drying parameter group includes an inner drum speed, a fan speed and a heating time, and the drying parameter control model is obtained by training with multiple sets of training data, each set of the training data includes a historical clothing mass, a corresponding historical forward stacking height value, a corresponding historical unfolded area, a corresponding historical distribution state parameter and a corresponding historical drying parameter group; The washing machine is controlled to perform drying according to the drying parameter group.

2. The method according to claim 1, characterized in that After performing image recognition on the image of the clothes to be dried to obtain the forward stacking height value, the unfolding area and the distribution state parameters of the clothes to be dried, the method further includes: an analysis step, inputting the clothing mass, the forward stacking height value, the unfolding area and the distribution state into the drying parameter control model to obtain the drying parameter group, wherein the drying parameter group includes a clothing amount type, a cycle number, the inner drum speed, the fan speed and the heating time, wherein the clothing amount type is one of a plurality of types of clothing amounts from low to high, the cycle number is the number of cycles expected to be experienced in the drying process, and the drying parameter control model is obtained by training with a plurality of sets of the training data, wherein each set of the training data includes a historical clothing mass, a corresponding historical forward stacking height value, a corresponding historical unfolding area, a corresponding historical distribution state parameter and a corresponding historical drying parameter group; a drying step, controlling the washing machine to dry for one cycle according to the inner drum speed, the fan speed and a single-cycle heating time, wherein the single-cycle heating time is a ratio of the heating time to the number of cycles; Repeat the acquisition step, the identification step, the analysis step and the drying step in sequence at least once, and in each repeated drying step, update the value of the drying parameter group of the current cycle to the average value of the drying parameter group of the current cycle and the value of the drying parameter group of the previous cycle, until the current cycle number is 1 or the cycle number reaches the maximum cycle number.

3. The method according to claim 2, characterized in that The training process of the drying parameter control model includes: Acquire a plurality of drying records with qualified drying quality, wherein the drying records include a historical input parameter group and a corresponding historical drying parameter group, wherein the historical input parameter group includes the historical clothing quality, the corresponding historical forward stacking height value, the corresponding historical unfolding area, and the corresponding historical distribution state parameter; Inputting each of the historical input parameter groups into a neural network model to obtain a plurality of predicted drying parameter groups; The parameters of the neural network model are adjusted according to the errors between each predicted drying parameter group and the corresponding historical drying parameter group until all the errors are smaller than the corresponding predetermined thresholds, thereby obtaining the drying parameter control model.

4. The method according to claim 3, characterized in that Obtain multiple drying records with qualified drying quality, including: Obtain multiple original drying records with qualified drying quality; The original drying record is preprocessed to obtain the drying record, wherein the preprocessing is used to remove noise, abnormal values ​​and redundant information.

5. The method according to claim 1, characterized in that performing image recognition on the image of the clothes to be dried, Obtaining the forward stacking height value, the unfolded area and the distribution state parameters of the clothes to be dried, including: Performing image segmentation on the clothes to be dried and the washing machine in the clothes to be dried image to obtain an overall outline of the clothes to be dried, wherein the overall outline of the clothes to be dried is an overall outline composed of all the clothes to be dried; Measuring the forward stacking height value according to the overall contour of the clothes to be dried; Calculating the unfolded area according to the overall outline of the clothes to be dried; Dividing the image of the clothes to be dried into a plurality of equal areas; The ratio of the area occupied by the overall outline of the clothes to be dried in each of the regions to the unfolded area is calculated to obtain a plurality of distribution state parameters.

6. The method according to any one of claims 1 to 5, characterized in that Before the washing machine enters the drying stage, the method further comprises: The drying parameter control model is deployed on a remote server, so that the remote server performs drying control on all washing machines of the same type.

7. The method according to any one of claims 1 to 5, characterized in that Before the washing machine enters the drying stage, the method further comprises: The washing machine is controlled to execute a shaking program, wherein the shaking program is a program for controlling the washing machine to shake so that the clothes to be dried are loosened.

8. A drying control device for a washing machine, characterized in that: include: an acquisition unit, configured to execute an acquisition step, and when the washing machine is in a drying stage, acquire an image of the laundry to be dried and a mass of the laundry to be dried, wherein the image of the laundry to be dried includes images of all the laundry to be dried, and the mass of the laundry is the sum of the masses of all the laundry to be dried; a recognition unit, configured to execute a recognition step, perform image recognition on the image of the clothes to be dried, and obtain a forward stacking height value, an expanded area, and a distribution state parameter of the clothes to be dried, wherein the forward stacking height value is a height of the clothes to be dried as a whole in a vertical direction, the expanded area is an area occupied by the overall outline of the clothes to be dried, and the distribution state parameter is a distribution ratio of the clothes to be dried in a plurality of equally divided areas on the image of the clothes to be dried; a first analysis unit, for inputting the clothing mass, the forward stacking height value, the unfolding area and the distribution state into a drying parameter control model to obtain a drying parameter group, wherein the drying parameter group includes an inner drum speed, a fan speed and a heating time, and the drying parameter control model is obtained by training with multiple sets of training data, each set of the training data includes a historical clothing mass, a corresponding historical forward stacking height value, a corresponding historical unfolding area, a corresponding historical distribution state parameter and a corresponding historical drying parameter group; The first control unit is used to control the washing machine to dry according to the drying parameter group.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

10. A drying management system, characterized in that: include: A plurality of washing machines of the same type, a remote server, 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 methods for executing any one of claims 1 to 7.

Images