阅读说明：本技术 洗涤控制方法、装置、洗衣机、及存储介质 (Washing control method and device, washing machine and storage medium ) 是由 李洋 吕佩师 许升 石代兴 于 2020-05-20 设计创作，主要内容包括：本发明实施例公开了一种洗涤控制方法、装置、洗衣机、及存储介质,方法包括：获取待洗衣物的多个图片；根据所述多个图片确定所述待洗衣物的污渍种类；根据所述污渍种类进行洗涤控制。本发明实施例的技术方案能够提高洗涤质量。(The embodiment of the invention discloses a washing control method, a washing control device, a washing machine and a storage medium, wherein the method comprises the following steps: acquiring a plurality of pictures of clothes to be washed; determining the stain type of the clothes to be washed according to the pictures; and performing washing control according to the stain type. The technical scheme of the embodiment of the invention can improve the washing quality.)

1. A washing control method, comprising:

acquiring a plurality of pictures of clothes to be washed;

determining the stain type of the clothes to be washed according to the pictures;

and performing washing control according to the stain type.

2. The method of claim 1, wherein obtaining a plurality of pictures of the laundry comprises:

controlling an illumination module of the washing machine to turn on light;

controlling a power module of the washing machine to rotate a washing barrel so as to turn and shake the clothes to be washed;

controlling a camera module of the washing machine to shoot pictures of clothes to be washed in a washing machine barrel;

the above-mentioned steps of rotating the washing tub and taking pictures are repeatedly performed to obtain a plurality of pictures of the laundry.

3. The method of claim 1, wherein performing wash control based on the stain type comprises:

and adjusting the washing parameters of the current washing program according to the stain type.

4. The method of claim 3, wherein the washing parameters comprise at least one of:

soaking time, water temperature, washing duration, washing barrel rotating speed and rotation-stop ratio.

5. The method according to claim 1, further comprising determining the number of stains on the laundry from the plurality of pictures after obtaining the plurality of pictures of the laundry;

the washing control according to the stain type includes: and performing washing control according to the stain type and the stain quantity.

6. The method according to claim 1, wherein determining the stain type of the laundry from the plurality of pictures comprises:

the pictures are uploaded to a cloud server, so that the cloud server inputs the pictures to a pre-trained stain recognition model respectively, and at least one stain image output by the stain recognition model and the stain type of stains indicated by each stain image are obtained;

and determining the stain type of the clothes to be washed according to the at least one stain image and the stain type of the stain indicated by each stain image.

7. The method according to claim 6, further comprising, after obtaining at least one stain image output by the stain recognition model and the stain category to which the stain indicated by each stain image belongs:

determining the number of stains of the clothes to be washed according to the at least one stain image;

the washing control according to the stain type includes: and performing washing control according to the stain type and the stain quantity.

8. The method according to claim 7, wherein determining the stain amount of the laundry from the at least one stain image comprises:

if the number of the at least one stain image is greater than 1, filtering the at least one stain image according to the D-HASH value of the stain image so as to reserve one stain image for each stain; and determining the number of stains of the clothes to be washed according to the number of the filtered stain images.

9. The method according to claim 6, wherein the stain recognition model is trained by:

acquiring a training sample set, wherein the training sample set comprises a clothes image and marking information, and if the clothes image shows that at least one spot exists on corresponding clothes, the marking information comprises a spot image corresponding to at least one spot displayed in the clothes image and a spot type to which the spot indicated by each spot image belongs;

determining an initialized stain recognition model, wherein the initialized stain recognition model comprises a target layer, and the target layer is used for outputting at least one stain image displayed in the clothes image and the stain type of the stain indicated by each stain image if the clothes image displays that at least one stain exists on the corresponding clothes;

and training to obtain the stain recognition model by using a machine learning method, wherein the clothes images in the training samples in the training sample set are used as the input of the initialized stain recognition model, and the marking information corresponding to the input clothes images is used as the expected output of the initialized stain recognition model.

10. A washing control device, comprising:

the clothes picture acquiring unit is used for acquiring a plurality of pictures of clothes to be washed;

the stain recognition unit is used for determining the stain type of the clothes to be washed according to the pictures;

and the washing control unit is used for carrying out washing control according to the stain type.

11. A washing machine, characterized by comprising:

a processor; and

a memory to store executable instructions that, when executed by the one or more processors, cause the laundry machine to perform the method of any one of claims 1-9.

12. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the method according to any one of claims 1-9.

Technical Field

The embodiment of the invention relates to the technical field of intelligent washing machines, in particular to a washing control method and device, a washing machine and a storage medium.

Background

With the continuous improvement of living standard, washing machines have entered into thousands of households. Washing machines have become a necessity in home life. With the development of the washing technology, the range of the washing machine capable of washing clothes is expanded, and various stains can be thoroughly cleaned.

At present, although some intelligent washing machines can recognize information such as material and color of clothes to be washed and perform fine washing according to the information such as the material and the color of the clothes to be washed, the problems that stains are not cleaned and the like still exist.

Disclosure of Invention

In view of the above, embodiments of the present invention provide a washing control method, a washing control apparatus, a washing machine, and a storage medium to improve washing quality.

Additional features and advantages of embodiments of the invention will be set forth in the detailed description which follows, or in part will be obvious from the description, or may be learned by practice of embodiments of the invention.

In a first aspect of the present disclosure, an embodiment of the present invention provides a washing control method, including:

acquiring a plurality of pictures of clothes to be washed;

determining the stain type of the clothes to be washed according to the pictures;

and performing washing control according to the stain type.

In one embodiment, the obtaining of the plurality of pictures of the laundry includes: controlling an illumination module of the washing machine to turn on light; controlling a power module of the washing machine to rotate a washing barrel so as to turn and shake the clothes to be washed; controlling a camera module of the washing machine to shoot pictures of clothes to be washed in a washing machine barrel; the above-mentioned steps of rotating the washing tub and taking pictures are repeatedly performed to obtain a plurality of pictures of the laundry.

In one embodiment, the performing the washing control according to the stain type includes: and adjusting the washing parameters of the current washing program according to the stain type.

In one embodiment, the washing parameters include at least one of the following parameters: soaking time, water temperature, washing duration, washing barrel rotating speed and rotation-stop ratio.

In one embodiment, after obtaining a plurality of pictures of the clothes to be washed, determining the number of stains in the clothes to be washed according to the pictures; the washing control according to the stain type includes: and performing washing control according to the stain type and the stain quantity.

In an embodiment, the determining the stain type of the laundry according to the plurality of pictures includes: the pictures are uploaded to a cloud server, so that the cloud server inputs the pictures to a pre-trained stain recognition model respectively, and at least one stain image output by the stain recognition model and the stain type of stains indicated by each stain image are obtained; and determining the stain type of the clothes to be washed according to the at least one stain image and the stain type of the stain indicated by each stain image.

In an embodiment, after obtaining at least one stain image output by the stain recognition model and the stain type of the stain indicated by each stain image, the method further includes: determining the number of stains of the clothes to be washed according to the at least one stain image; the washing control according to the stain type includes: and performing washing control according to the stain type and the stain quantity.

In one embodiment, the determining the stain amount of the laundry according to the at least one stain image comprises: if the number of the at least one stain image is greater than 1, filtering the at least one stain image according to the D-HASH value of the stain image so as to reserve one stain image for each stain; and determining the number of stains of the clothes to be washed according to the number of the filtered stain images.

In one embodiment, the stain recognition model is trained by the following steps:

acquiring a training sample set, wherein the training sample set comprises a clothes image and marking information, and if the clothes image shows that at least one spot exists on corresponding clothes, the marking information comprises a spot image corresponding to at least one spot displayed in the clothes image and a spot type to which the spot indicated by each spot image belongs;

determining an initialized stain recognition model, wherein the initialized stain recognition model comprises a target layer, and the target layer is used for outputting at least one stain image displayed in the clothes image and the stain type of the stain indicated by each stain image if the clothes image displays that at least one stain exists on the corresponding clothes;

and training to obtain the stain recognition model by using a machine learning method, wherein the clothes images in the training samples in the training sample set are used as the input of the initialized stain recognition model, and the marking information corresponding to the input clothes images is used as the expected output of the initialized stain recognition model.

In a second aspect of the present disclosure, an embodiment of the present invention further provides a washing control apparatus, including:

the clothes picture acquiring unit is used for acquiring a plurality of pictures of clothes to be washed;

the stain recognition unit is used for determining the stain type of the clothes to be washed according to the pictures;

and the washing control unit is used for carrying out washing control according to the stain type.

In one embodiment, the clothing image capturing unit is configured to: controlling an illumination module of the washing machine to turn on light; controlling a power module of the washing machine to rotate a washing barrel so as to turn and shake the clothes to be washed; controlling a camera module of the washing machine to shoot pictures of clothes to be washed in a washing machine barrel; the above-mentioned steps of rotating the washing tub and taking pictures are repeatedly performed to obtain a plurality of pictures of the laundry.

In one embodiment, the washing control unit is configured to: and adjusting the washing parameters of the current washing program according to the stain type.

In one embodiment, the washing parameters in the washing control unit include at least one of the following parameters: soaking time, water temperature, washing duration, washing barrel rotating speed and rotation-stop ratio.

In an embodiment, the stain recognition unit is further configured to, after obtaining a plurality of pictures of the laundry, determine the number of stains on the laundry according to the plurality of pictures; the washing control unit is used for: and performing washing control according to the stain type and the stain quantity.

In one embodiment, the stain recognition unit is configured to: the pictures are uploaded to a cloud server, so that the cloud server inputs the pictures to a pre-trained stain recognition model respectively, and at least one stain image output by the stain recognition model and the stain type of stains indicated by each stain image are obtained; and determining the stain type of the clothes to be washed according to the at least one stain image and the stain type of the stain indicated by each stain image.

In an embodiment, the stain recognition unit is further configured to, after obtaining at least one stain image output by the stain recognition model and the stain type to which the stain indicated by each stain image belongs: determining the number of stains of the clothes to be washed according to the at least one stain image; the washing control unit is used for: and performing washing control according to the stain type and the stain quantity.

In an embodiment, the determining the number of stains in the laundry according to the at least one stain image by the stain recognition unit includes: if the number of the at least one stain image is greater than 1, filtering the at least one stain image according to the D-HASH value of the stain image so as to reserve one stain image for each stain; and determining the number of stains of the clothes to be washed according to the number of the filtered stain images.

In one embodiment, the stain recognition model is trained by the following modules:

the system comprises a sample acquisition module, a data acquisition module and a data processing module, wherein the sample acquisition module is used for acquiring a training sample set, the training sample comprises a clothes image and marking information, if the clothes image displays that at least one stain exists on corresponding clothes, and the marking information comprises a stain image corresponding to at least one stain displayed in the clothes image and a stain type to which stains indicated by each stain image belong;

the model determining module is used for determining an initialized stain recognition model, wherein the initialized stain recognition model comprises a target layer, and the target layer is used for outputting at least one stain image displayed in the clothes image and the stain type of the stain indicated by each stain image if the clothes image displays at least one stain on the corresponding clothes;

and the model training module is used for training the clothes images in the training samples in the training sample set as the input of the initialized stain recognition model by using a machine learning device, and the marking information corresponding to the input clothes images as the expected output of the initialized stain recognition model to obtain the stain recognition model.

In a third aspect of the present disclosure, a washing machine is provided. The washing machine includes: a processor; and a memory for storing executable instructions that, when executed by the processor, cause the laundry machine to perform the method of the first aspect.

In a fourth aspect of the disclosure, a computer-readable storage medium is provided, on which a computer program is stored, which computer program, when being executed by a processor, carries out the method in the first aspect.

The technical scheme provided by the embodiment of the invention has the beneficial technical effects that:

according to the embodiment of the invention, the plurality of pictures of the clothes to be washed are obtained, the stain type of the clothes to be washed is determined according to the pictures, and the washing control is carried out according to the stain type, so that the washing machine can wash the clothes more pertinently and finely, and the washing quality can be improved.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments of the present invention will be briefly described below, and it is obvious that the drawings in the following description are only a part of the embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the contents of the embodiments of the present invention and the drawings without creative efforts.

Fig. 1 is a schematic flow chart of a washing control method according to an embodiment of the present invention;

FIG. 2 is a schematic flow chart of another washing control method provided according to an embodiment of the present invention;

fig. 3 is a schematic structural diagram of a washing control device according to an embodiment of the present invention;

fig. 4 is a schematic structural diagram of another washing control device provided in accordance with an embodiment of the present invention;

FIG. 5 is a schematic structural diagram of a training device for a stain recognition model according to an embodiment of the present disclosure;

fig. 6 shows a schematic structural view of a washing machine suitable for implementing an embodiment of the present invention.

Detailed Description

In order to make the technical problems solved, the technical solutions adopted and the technical effects achieved by the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be described in further detail below with reference to the accompanying drawings, and it is obvious that the described embodiments are only some embodiments, but not all embodiments, of the embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, belong to the scope of protection of the embodiments of the present invention.

It should be noted that the terms "system" and "network" are often used interchangeably herein in embodiments of the present invention. Reference to "and/or" in embodiments of the invention is intended to include any and all combinations of one or more of the associated listed items. The terms "first", "second", and the like in the description and claims of the present disclosure and in the drawings are used for distinguishing between different objects and not for limiting a particular order.

It should be further noted that, in the embodiments of the present invention, each of the following embodiments may be executed alone, or may be executed in combination with each other, and the embodiments of the present invention are not limited in this respect.

The names of messages or information exchanged between devices in the embodiments of the present disclosure are for illustrative purposes only, and are not intended to limit the scope of the messages or information.

The technical solutions of the embodiments of the present invention are further described by the following detailed description with reference to the accompanying drawings.

Fig. 1 is a schematic flow chart of a washing control method according to an embodiment of the present invention, which is applicable to a washing machine performing washing control, and the method can be executed by a washing control device configured in the washing machine, as shown in fig. 1, the washing control method according to the embodiment includes:

in step S110, a plurality of pictures of the laundry are acquired.

For example, the lighting module of the washing machine can be controlled to turn on the light, the power module of the washing machine is controlled to rotate the washing tub to turn over and shake away the laundry, the camera module of the washing machine is controlled to shoot the pictures of the laundry in the washing tub, and the steps of rotating the washing tub and shooting the pictures are repeatedly executed to obtain a plurality of pictures of the laundry.

In step S120, a stain type of the laundry is determined according to the plurality of pictures.

Common laundry stains include various types, such as greasy stains, proteinaceous stains, tannin-based stains, and aqueous pigment-based stains.

It is known that various kinds of stains, such as greasy stains formed on clothes from vegetable oils, animal oils, mineral oils, etc., have different morphologies and/or colors, and since the greasy stains penetrate along the fabric fibers, the stains generally have no distinct boundaries and often have a crisscross shape. Milk or yogurt is milky white, uniform in appearance, red to yellowish brown in the color of animal meat juice, and yellow to brown in the color of urine. There are also various fruit juices, tea, and fruit juices from vegetable juices, etc., generally ranging from brown to dark brown, which occur over a longer period of time and are darker in color. The stains are clear in outline and darker in color at the edges of the stains. There are also aqueous pigment stains on clothes formed by various inks and dyes, such as pure blue ink, blue-black ink, red ink, carbon black ink, etc., and since various inks have relatively strong permeability to clothes, but have less wettability than grease, the boundaries of stains on clothes are still more distinct.

Therefore, the stain type of the clothes to be washed can be determined according to the picture characteristics of the clothes to be washed, and the specific method for determining the stain type can adopt various modes, for example, the stain type can be identified according to the shape and the color of a color block in an image, which patterns are stains and which patterns are clothes, the stain image can be obtained by screenshot of the stain block identified from the clothes picture, and the stain type can be determined according to the characteristic information of the stain image.

Specifically, a stain image can be obtained by capturing images of stain blocks recognized from a clothes picture, and then the stain type can be determined according to the characteristic information of the stain image, specifically, the stain type can be determined by adopting various methods, for example, the stain type can be determined by adopting an image processing algorithm, and the stain type can also be recognized by adopting a stain recognition model.

Since the washing machine has limited storage and operation functions, the recognition using the stain recognition model may be performed by the server. For example, the plurality of pictures can be uploaded to a cloud server, so that the cloud server inputs the plurality of pictures to a pre-trained stain recognition model respectively to obtain at least one stain image output by the stain recognition model and a stain type to which stains are indicated by each stain image; and determining the stain type of the clothes to be washed according to the at least one stain image and the stain type of the stain indicated by each stain image.

In some embodiments, the stain recognition model may be trained by using a plurality of methods, and fig. 3 is a schematic structural diagram of a washing control device according to an embodiment of the present invention, as shown in fig. 3, the stain recognition model may be trained by the following steps:

in step S310, a training sample set is obtained, where the training sample includes a clothing image and annotation information, and if the clothing image shows that there is at least one spot on the corresponding clothing, the annotation information includes a spot image corresponding to at least one spot displayed in the clothing image and a spot type to which the spot indicated by each spot image belongs.

In step S320, an initialized stain recognition model is determined, where the initialized stain recognition model includes a target layer, and the target layer is configured to output at least one stain image displayed in the clothing image and a stain type to which stains indicated by each stain image belong, if the clothing image shows that there is at least one stain on corresponding clothing.

The initialized stain recognition model can be of various types, for example, a convolutional neural network model can be adopted.

In step S330, the stain recognition model is obtained by training using a machine learning method, with the clothes images in the training samples in the training sample set as the input of the initialized stain recognition model, and the labeling information corresponding to the input clothes images as the expected output of the initialized stain recognition model.

Further, after the plurality of pictures of the laundry are obtained in step S110, the number of stains on the laundry is determined according to the plurality of pictures. For example, the stain amount can be determined according to a plurality of pictures taken after the clothes to be washed are overturned for a plurality of times. Specifically, the method for determining the number of stains may be implemented in various ways, for example, after the stain images are respectively extracted from the photos taken multiple times, some stains are inevitably taken from multiple clothes pictures, so it is not easy to simply use the number of stain images identified from all the pictures as the number of stains on the clothes to be washed in the washing tub, and the number of stains on the clothes to be washed in the washing tub should be less than the sum of all the extracted stain images. Therefore, the extracted stain images need to be subjected to duplication removal processing, so that only one stain image is reserved for each stain, and the number of the stain images obtained after duplication removal is the number of the stains of the clothes to be washed.

Specifically, the method for performing the deduplication processing on the stain image may include multiple methods, which is not limited in this embodiment. Since the D-HASH values of the images from different angles should have similarity for the same stain, if the number of the at least one stain image is greater than 1, the at least one stain image may be filtered according to the D-HASH value of the stain image (e.g., only one stain image is retained if the D-HASH values of a plurality of stain images are similar) to retain one stain image for each stain. And the number of the filtered stain images is the number of the stains of the clothes to be washed.

In step S130, washing control is performed according to the stain type.

Different types of stains have different cleaning modes, if a washing machine is adopted for washing, different washing programs can be selected according to the types and the number of the stains, and washing parameters of the current washing program can be adjusted according to the types and the number of the stains, such as one or more parameters of soaking time, water temperature, washing time, washing barrel rotating speed, rotating-stopping ratio and the like.

For example, greasy stains, solvents or high water temperatures can be used for washing. In another example, the protein stain does not need to use a solvent, the water temperature is not too high, and otherwise, the stain is firmer. For another example, tannin pigments are afraid of high temperature or alkaline materials, and the water temperature or alkaline detergent concentration is increased during washing.

In some embodiments, if the number of stains in the laundry is determined according to the plurality of pictures in step S120, the step may further perform washing control according to the stain type and the stain number, specifically, the washing parameters of the current washing program may be adjusted according to the stain type and the stain number, for example, the soaking time, the water temperature, the washing duration, the rotation speed of the washing tub, the rotation-stop ratio, and the like of the current washing program may be adjusted according to the stain type and the stain number.

According to the embodiment, the plurality of pictures of the clothes to be washed are obtained, the stain type of the clothes to be washed is determined according to the pictures, and the washing control is performed according to the stain type, so that the washing machine can wash the clothes more specifically and finely, and the washing quality can be improved.

Fig. 2 is a schematic flow chart of another washing control method provided by the embodiment of the present invention, which is based on the foregoing embodiment and is optimized. As shown in fig. 2, the washing control method according to the present embodiment includes:

in step S210, the lighting module of the washing machine is controlled to turn on the light.

In step S220, the power module of the washing machine is controlled to rotate the washing tub to turn over and disperse the laundry. The steps can acquire a plurality of pictures of a plurality of angles of the clothes to be washed in the washing bucket, can more comprehensively identify the stains of the clothes, and can increase the accuracy of stain identification, thereby further improving the refining degree of washing.

In step S230, the camera module of the washing machine is controlled to take a picture of the laundry in the tub of the washing machine.

In step S240, it is determined whether re-photographing is required, if so, the process returns to step S220, otherwise, step S250 is executed.

In step S250, the plurality of pictures are uploaded to a cloud server, so that the cloud server inputs the plurality of pictures to a pre-trained stain recognition model respectively, and at least one stain image output by the stain recognition model and a stain type to which stains indicated by each stain image belong are obtained.

The stain recognition model can be obtained by training through the steps shown in fig. 3, which are described in the embodiment corresponding to fig. 1, and this embodiment is not described in detail here.

In step S260, the stain type and the stain amount of the laundry are determined according to the at least one stain image and the stain type to which the stain indicated by each stain image belongs.

In step S270, washing control is performed according to the stain type and the stain amount.

According to the technical scheme, after the clothes to be washed are shot for multiple times to obtain multiple pictures, the pictures are uploaded to the cloud server to be subjected to model analysis, so that the stain type and the stain quantity of the clothes to be washed in the washing machine barrel are determined, washing control is performed on stains, the washing machine can wash the clothes more specifically and finely, and the washing quality can be improved.

As an implementation of the methods shown in the above figures, the present application provides an embodiment of a washing control device, and fig. 4 shows a schematic structural diagram of a washing control device provided in this embodiment, where the embodiment of the device corresponds to the embodiment of the method shown in fig. 1 to 3, and the device can be applied to various washing machines. As shown in fig. 4, the washing control device according to the present embodiment includes a clothing image capturing unit 410, a stain recognition unit 420, and a washing control unit 430.

The laundry picture acquiring unit 410 is configured to acquire a plurality of pictures of laundry.

The stain recognition unit 420 is configured to determine a stain type of the laundry according to the plurality of pictures.

The washing control unit 430 is configured to perform washing control according to the stain type.

In some embodiments, the laundry picture acquiring unit 410 is configured to control an illumination module of the washing machine to turn on light; controlling a power module of the washing machine to rotate a washing barrel so as to turn and shake the clothes to be washed; controlling a camera module of the washing machine to shoot pictures of clothes to be washed in a washing machine barrel; the above-mentioned steps of rotating the washing tub and taking pictures are repeatedly performed to obtain a plurality of pictures of the laundry.

In some embodiments, the washing control unit 430 is configured to adjust the washing parameters of the current washing program according to the stain category.

In some embodiments, the washing parameters in the washing control unit 430 include at least one of the following parameters: soaking time, water temperature, washing duration, washing barrel rotating speed and rotation-stop ratio.

In some embodiments, the stain recognition unit 420 is configured to further determine the stain amount of the laundry according to a plurality of pictures of the laundry after the pictures are acquired. The washing control unit 430 is configured to also perform washing control according to the stain type and the stain amount.

In some embodiments, the stain recognition unit 420 is further configured to upload the multiple pictures to a cloud server, so that the cloud server inputs the multiple pictures to a pre-trained stain recognition model respectively, and obtains at least one stain image output by the stain recognition model and a stain type to which stains indicated by each stain image belong; and determining the stain type of the clothes to be washed according to the at least one stain image and the stain type of the stain indicated by each stain image.

Further, the stain recognition unit 420 is configured to, after obtaining at least one stain image output by the stain recognition model and the stain type to which the stain indicated by each stain image belongs, determine the stain amount of the laundry according to the at least one stain image. The washing control unit 430 is configured to also perform washing control according to the stain type and the stain amount.

Further, the stain recognition unit 420 is configured to filter the at least one stain image according to the D-HASH value of the stain image if the number of the at least one stain image is greater than 1, so as to retain one stain image for each stain; and determining the number of stains of the clothes to be washed according to the number of the filtered stain images.

The washing control device provided by the embodiment can execute the washing control method provided by the embodiment of the method disclosed by the invention, and has corresponding functional modules and beneficial effects of the execution method.

Fig. 5 is a schematic structural diagram of a training apparatus for a stain recognition model, and as shown in fig. 5, the training apparatus for a stain recognition model according to this embodiment includes a sample obtaining module 510, a model determining module 520, and a model training module 530.

The sample acquiring module 510 is configured to acquire a training sample set, where a training sample includes a clothing image and annotation information, and if the clothing image shows that there is at least one spot on corresponding clothing, the annotation information includes a spot image corresponding to at least one spot displayed in the clothing image and a spot type to which the spot indicated by each spot image belongs;

the model determining module 520 is configured to determine an initialized stain recognition model, wherein the initialized stain recognition model includes a target layer, and the target layer is configured to output at least one stain image displayed in the clothing image and a stain type to which stains indicated by each stain image belong, if the clothing image shows that there is at least one stain on corresponding clothing;

the model training module 530 is configured to train the stain recognition model by using the machine learning apparatus, using the clothes images in the training samples in the training sample set as the input of the initialized stain recognition model, and using the labeling information corresponding to the input clothes images as the expected output of the initialized stain recognition model.

The washing control device provided by the embodiment can execute the washing control method provided by the embodiment of the method disclosed by the invention, and has corresponding functional modules and beneficial effects of the execution method.

The training device for the stain recognition model provided by the embodiment can execute the training method for the stain recognition model provided by the method embodiment of the disclosure, and has the corresponding functional modules and beneficial effects of the execution method.

Referring now to FIG. 6, a schematic diagram of a washing machine 600 suitable for implementing embodiments of the present invention is shown. The washing machine shown in fig. 6 is only an example, and should not bring any limitation to the function and use range of the embodiment of the present invention.

As shown in fig. 6, the washing machine 600 may include a processing device (e.g., a central processing unit, a graphic processor, etc.) 601, which may perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)602 or a program loaded from a storage device 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the washing machine 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.

Generally, the following devices may be connected to the I/O interface 605: input devices 606 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 607 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 608 including, for example, tape, hard disk, etc.; and a communication device 609. The communication means 609 may allow the washing machine 600 to perform wireless or wired communication with other devices to exchange data. While FIG. 6 illustrates a washing machine 600 having various devices, it is to be understood that not all of the illustrated devices are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided.

In particular, according to an embodiment of the present invention, the processes described above with reference to the flowcharts may be implemented as a computer software program. For example, embodiments of the invention include a computer program product comprising a computer program embodied on a computer-readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication means 609, or may be installed from the storage means 608, or may be installed from the ROM 602. The computer program, when executed by the processing means 601, performs the above-described functions defined in the method of an embodiment of the invention.

It should be noted that the computer readable medium mentioned above can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In embodiments of the invention, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In yet another embodiment of the invention, a computer readable signal medium may comprise a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.

The computer readable medium may be included in the washing machine; or may be separate and not assembled into the washing machine.

The computer readable medium carries one or more programs which, when executed by the washing machine, cause the washing machine to: acquiring a plurality of pictures of clothes to be washed; determining the stain type of the clothes to be washed according to the pictures; and performing washing control according to the stain type.

Computer program code for carrying out operations for embodiments of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units described in the embodiments of the present invention may be implemented by software or hardware. Where the name of a unit does not in some cases constitute a limitation of the unit itself, for example, the first retrieving unit may also be described as a "unit for retrieving at least two internet protocol addresses".

The foregoing description is only a preferred embodiment of the invention and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the disclosure in the embodiments of the present invention is not limited to the specific combinations of the above-described features, but also encompasses other embodiments in which any combination of the above-described features or their equivalents is possible without departing from the spirit of the disclosure. For example, the above features and (but not limited to) the features with similar functions disclosed in the embodiments of the present invention are mutually replaced to form the technical solution.