WO2024021661A1 - Steaming control method and device of clothes steamer, and storage medium and electronic device - Google Patents

Abstract

The present application relates to the technical field of smart home, and discloses a steaming control method and device of a clothes steamer, and a storage medium and an electronic device. The steaming control method of the clothes steamer comprises: by means of clothes image data of clothes to be steamed, acquiring a wash care label image of said clothes (201); inputting the wash care label image into a steaming icon recognition model to acquire steaming icon information in the wash care label image (202); acquiring newness and oldness determination results of said clothes according to the clothes image data (203); and according to the steaming icon information and the newness and oldness determination results, determining a steaming mode of steaming each area position of said clothes by the clothes steamer (204). The steaming mode of said clothes can be determined by recognizing the steaming icon information in the wash care label image of said clothes and the newness and oldness of each area position of said clothes, so that the corresponding steaming gears of the clothes steamer are automatically started, thereby realizing accurate steaming of clothes.

Description

Garment ironing machine ironing control method, device, storage medium and electronic device

Cross-references to related applications

This application claims priority to the Chinese patent application with application number 2022109103173 submitted on July 29, 2022, titled "Garment Ironing Machine Ironing Control Method, Device, Storage Medium and Electronic Device", which is fully incorporated by reference. Enter this article.

Technical field

The present application relates to the field of smart home technology, and in particular to a garment ironing machine ironing control method, device, storage medium and electronic device.

Background technique

Existing smart garment ironing machines implemented using sensors cannot provide users with precise ironing control solutions due to the limited sensing range and low accuracy of the sensors.

Therefore, there is an urgent need for a garment ironing machine ironing control method, device, storage medium and electronic device to solve the above problems.

Contents of the invention

This application provides an ironing control method for a garment steamer, including:

Obtain the washing mark image of the clothing to be ironed through the clothing image data of the clothing to be ironed;

The water-washing label image is input into the ironing icon recognition model to obtain the ironing icon information in the water-washing label image, wherein the ironing icon recognition model is based on a sample water-washing label image marked with an ironing icon label. obtained by training;

Obtain the condition determination result of the clothing to be ironed based on the clothing image data;

According to the ironing icon information and the newness level determination result, the ironing mode for the garment ironing machine to iron each area of the clothes to be ironed is determined.

This application also provides an ironing control device for a garment steamer, including:

An image acquisition module, used to obtain the washing mark image of the clothing to be ironed through the clothing image data of the clothing to be ironed;

An ironing icon recognition module, configured to input the water-washing label image into an ironing icon recognition model and obtain the ironing icon information in the water-washing label image, wherein the ironing icon recognition model The model is trained on sample water-washed label images labeled with the ironing icon label;

A clothing condition identification module, configured to obtain a condition determination result of the clothing to be ironed based on the clothing image data;

An ironing mode mapping module is configured to determine an ironing mode for each area of the clothes to be ironed by the garment ironing machine based on the ironing icon information and the condition determination result.

This application also provides a garment steamer, including the above-mentioned garment steamer ironing control device.

The present application also provides a computer-readable storage medium. The computer-readable storage medium includes a stored program. When the program is run, it executes and implements any one of the garment ironing machine ironing control methods described above.

The present application also provides an electronic device, including a memory and a processor. A computer program is stored in the memory, and the processor is configured to implement any one of the above mentioned garment ironing machines by executing the computer program. Control Method.

Description of drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application.

In order to more clearly explain the embodiments of the present application or the technical solutions in the prior art, the following will briefly introduce the drawings needed to describe the embodiments or the prior art. Obviously, for those of ordinary skill in the art, It is said that other drawings can be obtained based on these drawings without exerting creative labor.

Figure 1 is a schematic diagram of the hardware environment of an interaction method for smart devices according to an embodiment of the present application;

Figure 2 is a schematic flow chart of the ironing control method of the garment ironing machine provided by this application;

Figure 3 is a schematic structural diagram of the ironing control device of the garment ironing machine provided by this application;

Figure 4 is a schematic structural diagram of the electronic device provided by the present application;

Figure 5 is a schematic structural diagram of the garment steamer provided by this application. .

Detailed ways

In order to enable those in the technical field to better understand the solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only Examples that are part of this application, not all Embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts should fall within the scope of protection of this application.

It should be noted that the terms "first", "second", etc. in this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It is to be understood that the data so used are interchangeable under appropriate circumstances so that the embodiments of the application described herein can be practiced in sequences other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, e.g., a process, method, system, product, or apparatus that encompasses a series of steps or units and need not be limited to those explicitly listed. Those steps or elements may instead include other steps or elements not expressly listed or inherent to the process, method, product or apparatus.

The garment steamer uses the high-temperature water vapor generated inside to contact the clothes or fabrics in a naturally hanging state, thereby softening the fibers of the clothes or fabrics and completing the ironing of the clothes or fabrics. For clothes made of different fabrics, traditional garment ironing machines require users to manually select different ironing plans for ironing. Since many users do not know the fabrics or the corresponding ironing methods of the fabrics, they can only blindly select the garment ironing gear, or even All clothes are in the highest setting. For clothes with complex craftsmanship, it is even more difficult to find a suitable ironing solution. As a result, an inappropriate ironing solution is chosen, and the ironing effect of the clothes is poor, and the clothes may even be damaged.

Most smart garment ironing machines currently on the market use sensors, such as humidity sensors, temperature sensors and pressure sensors, to sense air humidity, steam temperature and water tank water volume in real time, thereby controlling physical functions such as steam volume or steam temperature to achieve ironing operations. Intelligent control to prevent damage to clothing.

Existing smart garment ironing machines implemented using sensors still cannot provide users with precise ironing control solutions due to the limited sensing range of the sensors and relatively low accuracy.

According to one aspect of the embodiment of the present application, a method for controlling ironing of a garment steamer is provided.

This garment ironing machine ironing control method is widely used in whole-house intelligent digital control application scenarios such as Smart Home, smart home, smart home equipment ecology, and smart residence (Intelligence House) ecology. Optionally, in this embodiment, the above-mentioned garment ironing machine ironing control method can be applied to the hardware environment composed of the terminal device 102 and the server 104 as shown in FIG. 1 . As shown in Figure 1, the server 104 is connected to the terminal device 102 through the network. It can be used to provide services (such as application services, etc.) for the terminal or the client installed on the terminal. The database can be set up on the server or independently from the server. It can be used to provide data storage services for the server 104. It can be configured on the server or independently from the server. Cloud computing and/or edge computing services are used to provide data computing services for the server 104.

The above-mentioned network may include but is not limited to at least one of the following: wired network, wireless network. The above-mentioned wired network may include but is not limited to at least one of the following: wide area network, metropolitan area network, and local area network. The above-mentioned wireless network may include at least one of the following: wireless fidelity (Wireless Fidelity, WIFI) and Bluetooth. The terminal device 102 may be, but is not limited to, a PC, a mobile phone, a tablet, a smart air conditioner, a smart hood, a smart refrigerator, a smart oven, a smart stove, a smart washing machine, a smart water heater, a smart washing equipment, a smart dishwasher, or a smart projection device. , smart TV, smart clothes drying rack, smart curtains, smart audio and video, smart sockets, smart audio, smart speakers, smart fresh air equipment, smart kitchen and bathroom equipment, smart bathroom equipment, smart sweeping robot, smart window cleaning robot, smart mopping robot, Smart air purification equipment, smart steamers, smart microwave ovens, smart kitchen appliances, smart purifiers, smart water dispensers, smart door locks, etc.

The ironing control method of the garment steamer provided by this application can integrate the artificial intelligence image recognition function in the mobile application App, and adopts the method of identifying the ironing icon on the washing label of the clothes to accurately match the appropriate ironing mode program for the clothes, and then Sending corresponding ironing instructions to the garment steamer equipment can effectively solve the problem of users being unable to iron accurately when using the garment steamer, and at the same time avoid damaging clothes.

Figure 2 is a schematic flow chart of the method for controlling the ironing of a garment steamer provided by the present application. As shown in Figure 2, the present application provides a method for controlling the ironing of a garment steamer, which includes the following steps.

Step 201: Obtain the washing mark image of the clothing to be ironed through the clothing image data of the clothing to be ironed.

In this application, the clothes to be ironed can be photographed through a camera installed near the steam nozzle of the garment steamer, and the wash mark image of the clothes can be obtained through the photographed image data of the clothes.

Optionally, this application uses the garment steamer as an intelligent network device that achieves higher intelligence standards through the Internet of Things (IoT), and binds it to mobile terminal devices (for example, mobile phones, tablets, etc.) , use the mobile terminal device to select the garment steamer to be used from the bound garment steamers, and then use the camera of the mobile terminal device to wash the clothes to be ironed. mark for image collection. Based on the high-definition camera configured in the existing mobile terminal equipment, a clearer image of the water washing label can be obtained. Moreover, if the existing smart garment steamer is not equipped with a camera, it can communicate with the existing smart garment steamer through a communication module (such as a WiFi module or 5G module). The mobile terminal device communicates and connects to quickly obtain clothing-related images, avoiding the need to re-install a camera device on the garment steamer and increasing equipment costs.

Step 202: Input the water-washing label image into an ironing icon recognition model to obtain the ironing icon information in the water-washing label image, where the ironing icon recognition model is based on samples marked with ironing icon labels. It is obtained by training on water-washed labeled images.

In this application, the ironing icon recognition model can be set up in the mobile terminal device, and the ironing image information of the water-washed label image is recognized through the processor of the mobile terminal device; it can also be set up in the cloud server, and the collected information is collected through the mobile terminal device. The water-washed label image is uploaded to the cloud server for recognition, and the cloud server completes the recognition of the ironing image information and sends the recognition result to the mobile terminal device.

Step 203: Obtain the condition determination result of the clothing to be ironed based on the clothing image data.

In this application, the newness of each area of the clothing in the clothing image data can be identified by using a model trained by a neural network. For example, the back area of the clothing is old, the sleeve area is new, and other recognition results.

Step 204: Determine the ironing mode for the garment ironing machine to iron each area of the clothes to be ironed based on the ironing icon information and the newness determination result.

In this application, the ironing icon recognition model can identify the ironing icon in the washable label image, and the obtained recognition result contains the ironing icon information corresponding to the ironing icon, for example, it can be ironed, and the ironing temperature does not exceed 100 Celsius, ironing temperature does not exceed 150 degrees Celsius, ironing temperature does not exceed 200 degrees Celsius, and information such as no ironing. Corresponding to the recognition results corresponding to different ironing icons, combined with the judgment results of the condition of each area of the clothing, this application is set with a corresponding ironing mode, so that the ironing icon information and the location of each area of the clothing are consistent with the ironing mode. Establish a mapping relationship between each other. After obtaining a certain type of ironing icon information, first determine the current maximum ironing temperature, and then quickly determine the most appropriate ironing mode for each area of the current clothing based on the condition of each area of the clothing. For example, when the ironing icon information is that the ironing temperature does not exceed 100 degrees Celsius, the ironing mode can be a low temperature gear (for example, the ironing temperature is 90 degrees Celsius). to 100 degrees Celsius), and then subdivide the temperature of each area according to the newness of the clothing. For example, if the collar area is older, the ironing temperature can be set to 100 degrees Celsius, while the front part of the top of the clothing is newer. , you can set the ironing temperature to 90 degrees Celsius.

Finally, after the ironing mode of the clothes to be ironed is determined, a corresponding ironing gear switching instruction is generated according to the ironing mode, so that the garment ironing machine can be adjusted to the corresponding gear according to the switching instruction. It should be noted that in this application, for the garment ironing machine that is in a dormant or turned off state, the garment ironing machine can first be awakened through the ironing gear switching command, and then confirm whether the current gear of the garment ironing machine is consistent with the ironing gear. The target ironing gears in the gear switching instructions are consistent. If they are consistent, the ironing operation will be performed directly; if they are inconsistent, the current ironing gear will be adjusted to the target ironing gear first, and then the ironing operation will be performed.

The garment ironing machine ironing control method provided by this application determines the ironing mode of the clothes to be ironed by identifying the ironing icon information in the wash mark image of the clothes to be ironed and the newness of the clothes area location, thereby using the ironing method. The ironing mode automatically turns on the corresponding ironing gear of the garment steamer to achieve precise ironing of clothes.

Based on the above embodiments, the ironing icon recognition model is trained through the following steps:

Obtain the sample washing mark image of the clothing washing mark area;

Generate an ironing icon label based on the ironing information of the ironing icon in the wash label;

Mark the area where the ironing icon is located in the water-washed label image of each sample, mark the corresponding ironing icon label, and construct a training sample set;

Through the training sample set, the convolutional neural network is trained to obtain an ironing icon recognition model.

In this application, the convolutional neural network is trained by constructing a training sample set, and the training is completed after the preset training times are met, and an ironing icon recognition model is obtained. Specifically, the sample washing label image contains washing labels with multiple different meanings. It is necessary to distinguish the ironing icon from other icons (such as dry cleaning icons, washing icons, hand washing icons, etc.). In order for the model to recognize the ironing icon, Mark the iron-on icon area in each sample wash-label image with an iron-on icon label.

Based on the above embodiment, the ironing icon label is generated based on the ironing information of the ironing icon in the water washing label, including:

Obtain the ironing information corresponding to the washing label image of each sample, the ironing information including clothing ironing information, low temperature ironing information, medium temperature ironing information, high temperature ironing information and clothing non-ironable information;

The ironing icon label is constructed based on the clothing ironing information, the low-temperature ironing information, the medium-temperature ironing information, the high-temperature ironing information and the clothing non-ironing information.

In this application, for the ironing information corresponding to different ironing icons, ironing icon labels corresponding to different ironing information types are generated, and then according to the type of ironing icon in the sample wash label image, in the ironing icon area Mark the ironing icon label corresponding to the corresponding ironing information type so that the model can identify the ironing information corresponding to different ironing icons.

In this application, the ironing temperature of the clothing represented by the ironable label of the clothing is not specifically limited. The garment steamer can maintain the current gear for ironing operation; the non-ironable label of the clothing indicates that ironing of the clothing is prohibited.

The meaning of the ironing icon label corresponding to the specific ironing temperature range can be set according to actual needs. For example, the low-temperature ironing label indicates that the ironing temperature does not exceed 110 degrees Celsius, the medium-temperature ironing label indicates that the ironing temperature does not exceed 150 degrees Celsius, and the high-temperature ironing label indicates that the ironing temperature does not exceed 150 degrees Celsius. The hot label indicates that the temperature does not exceed 200 degrees Celsius.

According to the ironing temperature requirements of different garment ironing machines, the above three temperature ironing labels can be further subdivided, and corresponding ironing icons can be set at the same time. For example, the low-temperature ironing label also includes the first low-temperature ironing label (such as 60 degrees Celsius). to 80 degrees Celsius), the second low-temperature ironing label (such as 90 degrees Celsius to 100 degrees Celsius) and the third low-temperature ironing label (such as 100 degrees Celsius to 110 degrees Celsius), correspondingly, the first low-temperature ironing label, the second low-temperature ironing label The label and the third low-temperature ironing label also correspond to their respective ironing icons. Based on similar subdivisions, the medium-temperature ironing label and the high-temperature ironing label can also be similarly subdivided to determine the hangers of different gear models. After the ironing machine is put on, the ironing icon recognition model can identify the ironing icons on the clothes based on the ironing gear of the garment ironing machine.

Based on the above embodiments, obtaining the sample wash mark image corresponding to the clothing wash mark area includes:

With the washable label area facing up and placed flat, obtain a tiled image of the washable label area of the clothing;

When the wash mark area is facing up and distorted, obtain a distorted image of the wash mark area of the clothing;

According to the tiled image of the washing label and the distorted image of the washing label, a sample washing label image corresponding to the clothing washing label area is obtained.

In this application, in order to further improve the recognition accuracy of the ironing icon recognition model, when constructing the training sample, in addition to fully presenting the sample image of the wash mark, that is, when the clothes are laid flat and the wash mark area is facing up, Obtain the obtained washing label tile image of the clothing washing label area.

This application also uses sample images where the wash label is distorted or wrinkled. Since the ironing icon recognition is performed on clothes in a naturally hanging state, it is not guaranteed to collect the wash label image, which is different from the wash label image when it is in a flat state. Like the image, the actual water-washed label image has more or less distortions and wrinkles, causing the ironing icon recognition model to be unable to recognize or recognize errors. Therefore, this application uses the water-washed label images in a distorted state as part of the training sample set to train the convolutional neural network, so that the trained model has stronger anti-interference ability and improves the recognition accuracy of the model.

Based on the above embodiment, obtaining the condition determination result of the clothing to be ironed based on the clothing image data includes:

Input the clothing image data into the clothing condition identification model to obtain the condition determination results corresponding to the locations of each area of the clothes to be ironed. The clothing condition identification model is based on the sample clothing image data and performs a neural network on Obtained by training, wherein the positions of each area of clothing in the sample clothing image data are marked with corresponding clothing condition labels.

In this application, different label information is first constructed, that is, clothing condition labels, including old, older, newer, and brand new labels. It should be noted that the clothing condition labels can be set according to actual needs. Furthermore, by marking corresponding labels on the positions of each area of the sample clothing in the sample clothing image data, a training sample set is constructed, and then the neural network is trained through this training sample set. After the preset training times are met, the new and old clothing is obtained. Degree recognition model. Through this clothing condition recognition model, the condition of each area of clothing in the clothing image data can be identified, thereby providing a more accurate condition determination result for subsequent determination of the ironing mode.

Based on the above embodiment, after inputting the water-washing label image into the ironing icon recognition model and obtaining the ironing icon information in the water-washing label image, the method further includes:

Obtain the fabric information of the clothes to be ironed according to the wash mark image;

Determine the ironing time of the clothes to be ironed according to the mapping relationship between the fabric information and the preset ironing time;

Determining the ironing mode for the garment ironing machine to iron the position of each area of the clothes to be ironed based on the ironing icon information and the condition determination result includes:

Obtain multiple target ironing gear information according to the condition determination result corresponding to the position of each area of the clothes to be ironed and the ironing icon information;

Based on the plurality of target ironing gear information and the ironing duration, ironing modes for different areas of the clothes to be ironed are determined.

In this application, when the image of clothes to be ironed is collected through a mobile terminal device, the fabric information of the washing mark of the clothes is also collected. Different clothes materials have different characteristics in the continuous ironing time. In order to prevent Overtime ironing of clothes made of different materials will cause damage to the clothes. This application sets different preset ironing durations based on the fabric information, thereby constructing a mapping relationship between the fabric information and the preset ironing duration. After obtaining the clothing fabric information, based on This mapping relationship determines the ironing time. Furthermore, by combining the ironing icon information and the condition determination results corresponding to each area of the clothing to be ironed, an ironing mode corresponding to each area of the clothing is generated to achieve more precise ironing control, for example, silk fabrics For tops, for silk fabrics, the ironing time in the same position of the clothing does not exceed 10 minutes. The ironing temperature corresponding to the ironing icon information of the clothing is 110 to 120 degrees Celsius. Further, according to the condition of each area of the clothing, degree, and then generate corresponding target ironing gear information for each area position. For example, if the cuff area of a jacket is older, the ironing temperature corresponding to the ironing gear is 120 degrees Celsius; if the front body area of the jacket is newer, the ironing temperature corresponding to the ironing gear is 120 degrees Celsius. Ironing temperature is 110 degrees Celsius.

Based on the above embodiment, after determining the ironing modes for the positions of different areas of the clothes to be ironed based on the multiple target ironing gear information and the ironing duration, the method includes:

Obtain the real-time location of the garment ironing machine that is ironing the clothes to be ironed at the current moment;

According to the real-time area position, a corresponding ironing mode switching instruction is generated for The ironing mode of the garment steamer is switched.

In this application, the camera installed at the position of the ironing head of the garment ironing machine can be used to collect the position of the clothes area currently being ironed by the garment ironing machine in real time. When the garment ironing machine moves to other areas of the clothes to be ironed, The ironing mode can be switched at any time. Optionally, corresponding ironing mode switching display information can be generated according to the current ironing position of the garment ironing machine, so that the user can use the display terminal set by the garment ironing machine itself through touch control. Select whether to switch ironing mode.

Based on the above embodiments, before obtaining the washing mark image of the clothing to be ironed through the clothing image data of the clothing to be ironed, the method further includes:

Obtain clothing image data of the clothing to be ironed;

If the clothing image data is not saved in the virtual wardrobe, after determining the ironing mode of the clothing to be ironed, an association between the clothing image data and the ironing mode is constructed, and the clothing is The image data, the ironing mode and the association relationship are stored in the database of the virtual wardrobe;

If the clothing image data has been saved in the virtual wardrobe, the ironing mode is obtained from the virtual wardrobe based on the clothing image data;

Wherein, the virtual wardrobe is constructed by using historical clothing image data and an ironing mode corresponding to the historical clothing image data.

In this application, the garment ironing machine is used as an intelligent network device in conjunction with a mobile terminal device, and the image of the clothes to be ironed is collected through the mobile terminal device, that is, the image data of the clothes is obtained, and at the same time, through the corresponding application App, the mobile terminal device A virtual wardrobe is set up in the mobile terminal, and operating instructions for the garment steamer are issued to the garment steamer through the mobile terminal device. It should be noted that in this application, the virtual wardrobe can also be set up on the cloud server, and through the mobile terminal device, image uploading and ironing mode delivery can be implemented between the garment steamer and the cloud server.

Furthermore, when the clothes are photographed through the mobile terminal device, the washing mark of the clothes is also photographed. Further, the clothing image data is uploaded to the virtual wardrobe. When the clothing image data has been saved in the virtual wardrobe, it means that the clothing has an ironing history record, and the ironing icon of the clothing has been identified, and the clothing has been stored in the virtual wardrobe. At this time, there is no need to identify the ironing icon. The ironing mode of the clothing can be directly retrieved from the virtual wardrobe based on the clothing image data, and the corresponding garment ironing machine gear adjustment instructions can be generated.

When the virtual wardrobe does not store the relevant image data of the clothing, the washing label image is input into the ironing icon recognition model, the ironing icon information in the washing label image is obtained, and then the ironing of the clothing is determined based on the ironing icon information. mode; and then save the ironing mode to the virtual wardrobe, so that the next time you iron, according to the image data of the clothes, you can directly click on the corresponding clothes from the virtual wardrobe to achieve one-click ironing. In this application, a mapping relationship between historical clothing images and ironing methods is established through a virtual wardrobe. When there are historical ironing records, the ironing mode can be quickly obtained. The garment ironing machine device receives the And execute the corresponding ironing gear operation instructions.

Based on the above embodiments, if the clothing image data has been saved in the virtual wardrobe, after obtaining the ironing mode from the virtual wardrobe according to the clothing image data, the method Also includes:

Identify the wrinkle parts in the clothing image data to obtain the clothing wrinkle area recognition results;

Generate corresponding ironing area prompt voice information based on the clothing wrinkle area recognition results;

If the steam nozzle of the ironing machine is in the wrinkle area of the clothes, prompt voice will be played according to the prompt voice information of the ironing area.

In this application, the wrinkle parts in the clothing image data collected by the mobile terminal device are identified. Specifically, a preset wrinkle level can be set, and the clothing image data is compared with the sample wrinkle image corresponding to the preset wrinkle level, so as to Determine which areas of clothing image data contain wrinkles. Furthermore, when the user uses the garment ironing machine to iron the wrinkled parts of the clothes, a prompt voice will be generated to remind the user that the ironing needs to be focused here.

The following is a description of the garment ironing control device provided by the present application. The garment ironing control device described below and the garment ironing control method described above may correspond to each other.

Figure 3 is a schematic structural diagram of a garment ironing machine ironing control device provided by this application. As shown in Figure 3, this application provides a garment ironing machine ironing control device, including an image acquisition module 301 and an ironing icon recognition module 302. , clothing condition identification module 303 and ironing mode mapping module 304, wherein the image acquisition module 301 is used to obtain the wash mark image of the clothing to be ironed through the clothing image data of the clothing to be ironed; the ironing icon identification module 302 is used to input the water-washing label image into the ironing icon recognition model and obtain the ironing image in the water-washing label image. label information, wherein the ironing icon recognition model is trained through sample washing label images marked with ironing icon labels; the clothing condition recognition module 303 is used to obtain the to-be-ironed items based on the clothing image data. The condition determination result of the clothes; the ironing mode mapping module 304 is used to determine the ironing mode of each area of the clothes to be ironed by the garment ironing machine according to the ironing icon information and the condition determination result. .

In this application, the image acquisition module 301 may be a camera arranged near the steam nozzle of the garment steamer, taking pictures of the clothes to be ironed and the wash marks of the clothes to be ironed, thereby acquiring the wash mark image of the clothes. Optionally, this application uses the garment steamer as an intelligent network device, binds it to a mobile terminal device (for example, a mobile phone, a tablet computer, etc.), and uses the mobile terminal device to select the garment steamer to be used from the bound garment steamer. The ironing machine uses the camera of the mobile terminal device as the image acquisition module 301 to collect images of the wash labels of the clothes to be ironed. Based on the high-definition camera configured in the existing mobile terminal equipment, a clearer image of the water washing label can be obtained. Moreover, if the existing smart garment steamer is not equipped with a camera, it can communicate with the existing smart garment steamer through a communication module (such as a WiFi module or 5G module). The mobile terminal device communicates and connects to quickly obtain clothing-related images, avoiding the need to re-install a camera device on the garment steamer and increasing equipment costs.

Further, the ironing icon identification module 302 can be set up in the mobile terminal device, and the processor of the mobile terminal device can identify the ironing image information of the water-washing mark image; it can also be set up in the cloud server, and the collected water-washing icon can be processed by the mobile terminal device. The mark image is uploaded to the cloud server for recognition, and the cloud server completes the recognition of the ironing image information and sends the recognition result to the mobile terminal device.

In this application, the ironing icon identification module 302 can identify the ironing icon in the washable label image, and the obtained recognition result includes the ironing icon information corresponding to the ironing icon, for example, ironing is possible, and the ironing temperature does not exceed 100 degrees Celsius, ironing temperature does not exceed 150 degrees Celsius, ironing temperature does not exceed 200 degrees Celsius, and cannot be ironed. Corresponding to the recognition results corresponding to different ironing icons, combined with the clothing condition identification module 303's judgment results of the condition of each area of the clothing, this application is set with a corresponding ironing mode. When the ironing mode mapping module 304 obtains a certain After a kind of ironing icon information, first determine the current maximum temperature of ironing, and then quickly determine the most suitable ironing mode for each area of the current clothing based on the condition of each area of the clothing. For example, the ironing icon information is Ironing When the temperature does not exceed 100 degrees Celsius, the ironing mode can be the low temperature setting (for example, the ironing temperature is between 90 degrees Celsius and 100 degrees Celsius). time), and then subdivide the temperature of each area according to the newness of the clothing. For example, if the collar area is older, the ironing temperature can be set to 100 degrees Celsius, while the front part of the top of the clothing is newer, and the ironing temperature can be set to 100 degrees Celsius. The temperature is set to 90 degrees Celsius.

Finally, after the ironing mode of the clothes to be ironed is determined, a corresponding ironing gear switching instruction is generated according to the ironing mode, and the ironing gear of the garment ironing machine is adjusted according to the switching instruction. It should be noted that in this application, for the garment ironing machine that is in a dormant or closed state, the garment ironing machine can be awakened through the ironing gear switching command, and then it is confirmed whether the current gear of the garment ironing machine is consistent with the ironing gear. The target ironing gears in the position switching instructions are consistent. If they are consistent, the ironing operation will be performed directly; if they are inconsistent, the current ironing gear will be adjusted to the target ironing gear first, and then the ironing operation will be performed.

The garment ironing machine ironing control device provided by this application determines the ironing mode of the clothing to be ironed by identifying the ironing icon information in the wash mark image of the clothing to be ironed and the newness of the location of the clothing area. The ironing mode automatically turns on the corresponding ironing gear of the garment steamer to achieve precise ironing of clothes.

On the basis of the above embodiments, the device further includes a sample image acquisition module, a sample label generation module, a training set construction module and a training module, wherein the sample image acquisition module is used to acquire the sample wash label image of the clothing wash label area; The sample label generation module is used to generate ironing icon labels based on the ironing information of the ironing icon in the water-washing label; the training set construction module is used to mark the area where the ironing icon is located in each sample water-washing label image to mark the corresponding ironing The icon label is constructed to obtain a training sample set; the training module is used to train the convolutional neural network through the training sample set to obtain an ironing icon recognition model.

In this application, the sample water-washing label image contains a variety of water-washing labels with different meanings. First, the sample image acquisition module collects sample water-washing label images with different meanings; then, the sample label generation module combines the ironing icon and other icons ( (such as dry cleaning icons, washing icons and hand washing icons, etc.) to generate labels corresponding to different ironing icons. In this application, the sample label generation module is specifically used to: obtain the ironing information corresponding to each sample washing image, The ironing information includes clothing ironing information, low temperature ironing information, medium temperature ironing information, high temperature ironing information and clothing non-ironable information; according to the clothing ironing information, the low temperature ironing information, the The medium-temperature ironing information, the high-temperature ironing information and the clothing non-ironable information are used to construct the ironing icon label.

In this application, the sample label generation module generates ironing icon labels corresponding to different ironing information types for the ironing information corresponding to different ironing icons, and then based on the type of the ironing icon in the sample wash label image, in The ironing icon area is marked with an ironing icon label corresponding to the corresponding ironing information type, so that the model can identify the ironing information corresponding to different ironing icons.

In this application, the ironing temperature of the clothing represented by the ironable label of the clothing is not specifically limited. The garment steamer can maintain the current gear for ironing operation; the non-ironable label of the clothing indicates that ironing of the clothing is prohibited.

The meaning of the ironing icon label corresponding to the specific ironing temperature range can be set according to actual needs. For example, the low-temperature ironing label indicates that the ironing temperature does not exceed 110 degrees Celsius, the medium-temperature ironing label indicates that the ironing temperature does not exceed 150 degrees Celsius, and the high-temperature ironing label indicates that the ironing temperature does not exceed 150 degrees Celsius. The hot label indicates that the temperature does not exceed 200 degrees Celsius. According to the ironing temperature requirements of different garment ironing machines, the above three temperature ironing labels can be further subdivided, and corresponding ironing icons can be set at the same time. For example, the low-temperature ironing label also includes the first low-temperature ironing label (such as 60 degrees Celsius). to 80 degrees Celsius), the second low-temperature ironing label (such as 90 degrees Celsius to 100 degrees Celsius) and the third low-temperature ironing label (such as 100 degrees Celsius to 110 degrees Celsius), correspondingly, the first low-temperature ironing label, the second low-temperature ironing label The label and the third low-temperature ironing label also correspond to their respective ironing icons. Based on similar subdivisions, the medium-temperature ironing label and the high-temperature ironing label can also be similarly subdivided to determine the hangers of different gear models. After the ironing machine is put on, the ironing icon recognition model can identify the ironing icons on the clothes based on the ironing gear of the garment ironing machine.

Further, in order to enable the model to recognize the ironing icon, the training set construction module marks the ironing icon area in each sample water-labeled image with an ironing icon label, thereby completing the construction of the training set. Finally, through the training module, the convolutional neural network is trained using the training sample set. The training is completed after the preset training times are met, and the ironing icon recognition model is obtained.

On the basis of the above embodiments, the sample image acquisition module includes: a first sample image acquisition unit, a second sample image acquisition unit and a processing unit, wherein the first sample image acquisition unit is used to collect images on the front of the water wash mark area. When the wash label area is facing up and placed flat, a tiled image of the wash label area of the clothing is obtained; the second sample image acquisition unit is used to obtain a tiled image of the wash label area of the clothing when the wash label area is facing up and distorted. A water-washing label distorted image; the processing unit is configured to obtain a sample water-washing label image corresponding to the clothing washing label area based on the water-washing label tiled image and the water-washing label distorted image.

In this application, in order to further improve the recognition accuracy of the ironing icon recognition model, when constructing the training sample, in addition to fully presenting the sample image of the wash mark, that is, when the clothes are laid flat and the wash mark area is facing up, A tiled image of the washing mark of the clothing washing mark area is obtained through the first sample image acquisition unit. The second sample image acquisition unit is also used to obtain sample images when there are distortions or wrinkles of the water-wash label. Since the ironing icon recognition of the clothes is in a natural hanging state, it is not guaranteed to collect the water-wash label image, unlike when the clothes are in a tiled state. Like the water-washing label image in the state, the actual water-washing label image has more or less distortions and wrinkles, causing the ironing icon recognition model to be unable to recognize or recognize errors. Therefore, this application uses the water-washed label images in a distorted state as part of the training sample set to train the convolutional neural network, so that the trained model has stronger anti-interference ability and improves the recognition accuracy of the model.

Based on the above embodiments, the clothing condition identification module is specifically used to:

Input the clothing image data into the clothing condition identification model to obtain the condition determination results corresponding to the locations of each area of the clothes to be ironed. The clothing condition identification model is based on the sample clothing image data and performs a neural network on Obtained by training, wherein the positions of each area of clothing in the sample clothing image data are marked with corresponding clothing condition labels.

Based on the above embodiment, the device further includes a fabric information collection module and an ironing duration determination module, wherein the fabric information collection module is used to obtain fabric information of the clothes to be ironed based on the wash mark image; The ironing duration determination module is used to determine the ironing duration of the clothes to be ironed based on the mapping relationship between the fabric information and the preset ironing duration;

The ironing mode mapping module is specifically used for:

Obtain multiple target ironing gear information according to the condition determination result corresponding to the position of each area of the clothes to be ironed and the ironing icon information;

Based on the plurality of target ironing gear information and the ironing duration, ironing modes for different areas of the clothes to be ironed are determined.

In this application, when collecting images of clothes to be ironed, the mobile terminal device simultaneously collects fabric information at the washing mark of the clothes through the fabric information collection module. In view of the different characteristics of the continuous ironing time of different clothing materials, in order to prevent overtime ironing of clothing of different materials, resulting in damage to the clothing, the ironing time determination module sets different settings based on the fabric information. The same preset ironing time is used to construct a mapping relationship between the fabric information and the preset ironing time. After obtaining the clothing fabric information, the available ironing time is determined based on the mapping relationship. Further, the ironing icon information and the preset ironing time are determined. The judgment results of the condition of each area of the clothes to be ironed are used to generate the ironing mode corresponding to each area of the clothes to achieve more precise ironing control. For example, for a top made of silk fabric, the ironing temperature is 110 to 120 degrees Celsius. For silk fabrics, the ironing time in the same position of the clothing is no more than 10 minutes. The ironing temperature corresponding to the ironing icon information of the clothing is 110 to 120 degrees Celsius. Further, according to the location of each area of the clothing The degree of newness, and then generate corresponding target ironing gear information for each area. For example, if the cuff area of a jacket is older, the ironing temperature corresponding to the ironing gear is 120 degrees Celsius; if the front body area of the jacket is newer, the ironing gear corresponding to The ironing temperature is 110 degrees Celsius.

On the basis of the above embodiment, the device further includes an automatic switching module for ironing mode, which is used to obtain the real-time area position of the clothes to be ironed by the garment ironing machine at the current moment, and generate a The corresponding ironing mode switching instruction is used to switch the ironing mode of the garment ironing machine.

On the basis of the above embodiment, the device further includes a clothing image acquisition module and a virtual wardrobe module, wherein the clothing image acquisition module is used to obtain the clothing image data of the clothes to be ironed; the virtual wardrobe module is used if the virtual wardrobe The clothing image data is not saved in, then after determining the ironing mode of the clothing to be ironed, construct an association between the clothing image data and the ironing mode, and combine the clothing image data, The ironing mode and the association relationship are stored in the database of the virtual wardrobe; if the clothing image data has been saved in the virtual wardrobe, the clothing image data is obtained from the virtual wardrobe based on the clothing image data. The ironing mode; wherein, the virtual wardrobe is constructed by historical clothing image data and the ironing mode corresponding to the historical clothing image data.

In this application, the garment ironing machine is used as an intelligent network device in conjunction with a mobile terminal device, and the camera of the mobile terminal device is also used as a clothing image acquisition module to collect images of clothing to be ironed, that is, to obtain clothing image data, and at the same time, through the corresponding The application App sets up a virtual wardrobe in the mobile terminal device and sends operating instructions to the garment steamer through the virtual wardrobe module. It should be noted that in this application, the virtual wardrobe module can also be set up on the cloud server, and through the mobile terminal device, image uploading and ironing mode delivery can be implemented between the garment steamer and the cloud server.

Further, when the clothes are photographed through the mobile terminal device, the washing mark of the clothes is also photographed. Further, the clothing image data is uploaded to the virtual wardrobe module. When the clothing image data has been saved in the virtual wardrobe module, it means that the clothing has an ironing history record, and the ironing icon of the clothing has been identified. The virtual wardrobe module has Store the ironing mode of the clothing. At this time, there is no need to identify the ironing icon. The ironing mode of the clothing can be directly retrieved from the virtual wardrobe module based on the clothing image data, and the corresponding garment ironing machine gear adjustment instruction can be generated. .

When the virtual wardrobe module does not store the relevant image data of the clothing, the washing label image is input into the ironing icon recognition model, the ironing icon information in the washing label image is obtained, and then the ironing method of the clothing is determined based on the ironing icon information. Ironing mode; and then save the ironing mode to the virtual wardrobe module, so that the next time you iron, according to the image data of the clothes, you can directly click on the corresponding clothes from the virtual wardrobe module to achieve one-click ironing. In this application, the mapping relationship between historical clothing images and ironing methods is established through the virtual wardrobe module. When there are historical ironing records, the ironing mode can be quickly obtained. Among them, the garment ironing machine device uses a wireless network, Receive and execute the corresponding ironing gear operation instructions.

On the basis of the above embodiments, the device further includes a wrinkle area recognition module and a wrinkle area voice prompt module, wherein the wrinkle area recognition module is used to identify wrinkle parts in the clothing image data to obtain clothing wrinkle area identification. Result; The wrinkle area voice prompt module is used to generate corresponding ironing area prompt voice information based on the clothing wrinkle area recognition result; if the steam nozzle of the ironing machine is in the clothing wrinkle area, according to the ironing area prompt voice information The hot area prompt voice message plays the prompt voice.

In this application, the wrinkle area recognition module identifies the wrinkle parts in the clothing image data collected by the mobile terminal device. Specifically, a preset wrinkle level can be set, and the sample wrinkle image corresponding to the clothing image data and the preset wrinkle level can be set. Make comparisons to determine which areas in the clothing image data have wrinkles. Furthermore, when the user uses the garment ironing machine to iron the wrinkled parts of the clothes, the wrinkle area voice prompt module will generate a prompt voice to remind the user that focused ironing is required here.

Figure 5 is a schematic structural diagram of the garment steamer provided by this application. As shown in Figure 5, this application also provides a garment steamer, including the garment steamer ironing control device described in the above embodiments, an inner core (steam heater), a body shell, a water tank, a steam nozzle, steam duct and retractable stand. The garment ironing machine uses the garment ironing machine ironing control device to identify the ironing icon information in the wash mark image of the clothes to be ironed and the newness of the clothing area location, and then uses the mapping relationship stored in the cloud server or mobile terminal device to Determine the ironing mode of the clothes to be ironed, and automatically turn on the corresponding ironing gear of the garment ironing machine through this ironing mode, achieving precise ironing of the clothes.

Figure 4 is a schematic structural diagram of an electronic device provided by this application. As shown in Figure 4, the electronic device may include: a processor (processor) 410, a communications interface (Communications Interface) 420, a memory (memory) 430 and a communication bus 440. Among them, the processor 410, the communication interface 420, and the memory 430 complete communication with each other through the communication bus 440. The processor 410 can call the logic instructions in the memory 430 to execute the garment ironing machine ironing control method. The method includes: obtaining the wash mark image of the clothing to be ironed through the clothing image data of the clothing to be ironed; The water-washing label image is input into the ironing icon recognition model to obtain the ironing icon information in the water-washing label image, wherein the ironing icon recognition model is trained by sample water-washing label images marked with ironing icon labels. According to the clothing image data, the condition determination result of the clothes to be ironed is obtained; according to the ironing icon information and the condition determination result, it is determined that the garment ironing machine irons the clothes to be ironed every time Ironing mode for one zone position.

In addition, the above-mentioned logical instructions in the memory 430 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the existing technology or the part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including Several instructions are used to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program code. .

On the other hand, this application also provides a computer program product. The computer program product includes a computer program. The computer program can be stored on a computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the above-mentioned steps. The hooks provided by each method An ironing control method for an ironing machine, which method includes: obtaining the washing mark image of the clothing to be ironed through the clothing image data of the clothing to be ironed; inputting the washing mark image into the ironing icon recognition model to obtain the washing mark image The ironing icon information in the above-mentioned washing label image, wherein the ironing icon recognition model is obtained by training the sample washing label image marked with the ironing icon label; according to the clothing image data, the to-be-ironed The condition determination result of the clothes; according to the ironing icon information and the condition determination result, determine the ironing mode for the garment ironing machine to iron each area of the clothes to be ironed.

In another aspect, the present application also provides a computer-readable storage medium, which includes a stored program, wherein when the program is run, the garment ironing control method provided by each of the above methods is executed. , the method includes: obtaining the wash mark image of the clothes to be ironed through the clothing image data of the clothes to be ironed; inputting the wash mark image into the ironing icon recognition model, and obtaining the wash mark image in the wash mark image. Ironing icon information, wherein the ironing icon recognition model is trained through sample wash label images marked with ironing icon labels; according to the clothing image data, the newness determination result of the clothing to be ironed is obtained ; According to the ironing icon information and the newness determination result, determine the ironing mode of the garment ironing machine for ironing each area of the clothes to be ironed.

The device embodiments described above are only illustrative. The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they may be located in One location, or it can be distributed across multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Persons of ordinary skill in the art can understand and implement the method without any creative effort.

Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the part of the above technical solution that essentially contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., including a number of instructions to cause a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in various embodiments or certain parts of the embodiments.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present application, rather than Limitation thereof; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalents to some of the technical features. Replacements; however, these modifications or substitutions do not deviate from the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of this application.

Claims (21)

1. An ironing control method for a garment steamer, including:

   Obtain the washing mark image of the clothing to be ironed through the clothing image data of the clothing to be ironed;

   The water-washing label image is input into the ironing icon recognition model to obtain the ironing icon information in the water-washing label image, wherein the ironing icon recognition model is based on a sample water-washing label image marked with an ironing icon label. obtained by training;

   Obtain the condition determination result of the clothing to be ironed based on the clothing image data;

   According to the ironing icon information and the newness level determination result, the ironing mode for the garment ironing machine to iron each area of the clothes to be ironed is determined.
2. The ironing control method of a garment ironing machine according to claim 1, wherein the ironing icon recognition model is trained through the following steps:

   Obtain the sample washing label image corresponding to the clothing washing label area;

   Generate an ironing icon label based on the ironing information of the ironing icon in the wash label;

   Mark the area where the ironing icon is located in the water-washed label image of each sample, mark the corresponding ironing icon label, and construct a training sample set;

   Through the training sample set, the convolutional neural network is trained to obtain an ironing icon recognition model.
3. The ironing control method of a garment ironing machine according to claim 2, wherein said obtaining the sample wash mark image corresponding to the clothing wash mark area includes:

   With the washable label area facing up and placed flat, obtain a tiled image of the washable label area of the clothing;

   When the wash mark area is facing up and distorted, obtain a distorted image of the wash mark area of the clothing;

   According to the tiled image of the washing label and the distorted image of the washing label, a sample washing label image corresponding to the clothing washing label area is obtained.
4. The ironing control method of a garment ironing machine according to claim 2, wherein the generating an ironing icon label based on the ironing information of the ironing icon in the water washing label includes:

   Obtain the ironing information corresponding to the washing label image of each sample, the ironing information includes clothing Ironing information, low temperature ironing information, medium temperature ironing information, high temperature ironing information and clothing cannot be ironed information;

   The ironing icon label is constructed based on the clothing ironing information, the low-temperature ironing information, the medium-temperature ironing information, the high-temperature ironing information and the clothing non-ironing information.
5. The ironing control method of a garment ironing machine according to claim 1, wherein said obtaining the condition determination result of the clothing to be ironed based on the clothing image data includes:

   Input the clothing image data into the clothing condition identification model to obtain the condition determination results corresponding to the locations of each area of the clothes to be ironed. The clothing condition identification model is based on the sample clothing image data and performs a neural network on Obtained by training, wherein the positions of each area of clothing in the sample clothing image data are marked with corresponding clothing condition labels.
6. The ironing control method of a garment ironing machine according to claim 1, wherein after the water-washing mark image is input into the ironing icon recognition model and the ironing icon information in the water-washing mark image is obtained, the The above methods also include:

   Obtain the fabric information of the clothes to be ironed according to the wash mark image;

   Determine the ironing time of the clothes to be ironed according to the mapping relationship between the fabric information and the preset ironing time;

   Determining the ironing mode for the garment ironing machine to iron the position of each area of the clothes to be ironed based on the ironing icon information and the condition determination result includes:

   Obtain multiple target ironing gear information according to the condition determination result corresponding to the position of each area of the clothes to be ironed and the ironing icon information;

   Based on the plurality of target ironing gear information and the ironing duration, ironing modes for different areas of the clothes to be ironed are determined.
7. The ironing control method of a garment ironing machine according to claim 6, wherein in the step of determining the ironing position of different areas of the clothes to be ironed based on the plurality of target ironing gear information and the ironing duration, After ironing mode, the method includes:

   Obtain the real-time location of the garment ironing machine that is ironing the clothes to be ironed at the current moment;

   According to the real-time area position, a corresponding ironing mode switching instruction is generated for switching the ironing mode of the garment ironing machine.
8. The ironing control method of a garment ironing machine according to claim 1, wherein before obtaining the washing mark image of the clothing to be ironed through the clothing image data of the clothing to be ironed, the method further includes:

   Obtain clothing image data of the clothing to be ironed;

   If the clothing image data is not saved in the virtual wardrobe, after determining the ironing mode of the clothing to be ironed, an association between the clothing image data and the ironing mode is constructed, and the clothing is The image data, the ironing mode and the association relationship are stored in the database of the virtual wardrobe;

   If the clothing image data has been saved in the virtual wardrobe, the ironing mode is obtained from the virtual wardrobe based on the clothing image data;

   Wherein, the virtual wardrobe is constructed by using historical clothing image data and an ironing mode corresponding to the historical clothing image data.
9. The ironing control method of a garment ironing machine according to claim 8, wherein if the clothing image data has been saved in the virtual wardrobe, the clothing image data is obtained from the virtual wardrobe according to the clothing image data. After the ironing mode is set, the method further includes:

   Identify wrinkle parts in the clothing image data to obtain clothing wrinkle area recognition results;

   Generate corresponding ironing area prompt voice information based on the clothing wrinkle area recognition results;

   If the steam nozzle of the ironing machine is in the wrinkle area of the clothes, prompt voice will be played according to the prompt voice information of the ironing area.
10. An ironing control device for a garment steamer, including:

    The image acquisition module is configured to obtain the washing mark image of the clothing to be ironed through the clothing image data of the clothing to be ironed;

    The ironing icon recognition module is configured to input the water-washing label image into an ironing icon recognition model and obtain the ironing icon information in the water-washing label image, wherein the ironing icon recognition model is constructed by marking the ironing icon. The sample water-washed label image of the hot icon label is obtained by training;

    The clothing condition identification module is configured to obtain the condition determination result of the clothes to be ironed based on the clothing image data;

    An ironing mode mapping module, configured to operate according to the ironing icon information and the degree of newness The determination result determines the ironing mode for the garment ironing machine to iron each area of the clothes to be ironed.
11. The ironing control device for a garment ironing machine according to claim 10, wherein the ironing icon recognition model is trained through the following steps:

    Obtain the sample washing label image corresponding to the clothing washing label area;

    Generate an ironing icon label based on the ironing information of the ironing icon in the wash label;

    Mark the area where the ironing icon is located in the water-washed label image of each sample, mark the corresponding ironing icon label, and construct a training sample set;

    Through the training sample set, the convolutional neural network is trained to obtain an ironing icon recognition model.
12. The ironing control device of a garment steamer according to claim 11, wherein said obtaining the sample wash mark image corresponding to the laundry wash mark area includes:

    With the washable label area facing up and placed flat, obtain a tiled image of the washable label area of the clothing;

    When the wash mark area is facing up and distorted, obtain a distorted image of the wash mark area of the clothing;

    According to the tiled image of the washing label and the distorted image of the washing label, a sample washing label image corresponding to the clothing washing label area is obtained.
13. The ironing control device of a garment ironing machine according to claim 11, wherein said generating an ironing icon label based on the ironing information of the ironing icon in the water washing label includes:

    Obtain the ironing information corresponding to the washing label image of each sample, the ironing information including clothing ironing information, low temperature ironing information, medium temperature ironing information, high temperature ironing information and clothing non-ironable information;

    The ironing icon label is constructed based on the clothing ironing information, the low-temperature ironing information, the medium-temperature ironing information, the high-temperature ironing information and the clothing non-ironing information.
14. The ironing control device for a garment ironing machine according to claim 10, wherein the clothing condition identification module is specifically configured to:

    Input the clothing image data into the clothing condition identification model to obtain the condition determination results corresponding to the locations of each area of the clothes to be ironed. The clothing condition identification model is based on the sample clothing image data and performs a neural network on obtained by training, among which, all Each area of the clothing in the sample clothing image data is marked with a corresponding clothing condition label.
15. The ironing control device for a garment ironing machine according to claim 10, wherein the ironing icon identification module is further configured to:

    Obtain the fabric information of the clothes to be ironed according to the wash mark image;

    Determine the ironing time of the clothes to be ironed according to the mapping relationship between the fabric information and the preset ironing time;

    Determining the ironing mode for the garment ironing machine to iron the position of each area of the clothes to be ironed based on the ironing icon information and the condition determination result includes:

    Obtain multiple target ironing gear information according to the condition determination result corresponding to the position of each area of the clothes to be ironed and the ironing icon information;

    Based on the plurality of target ironing gear information and the ironing duration, ironing modes for different areas of the clothes to be ironed are determined.
16. The ironing control device for a garment ironing machine according to claim 15, wherein the ironing icon recognition module is further configured to:

    Obtain the real-time location of the garment ironing machine that is ironing the clothes to be ironed at the current moment;

    According to the real-time area position, a corresponding ironing mode switching instruction is generated for switching the ironing mode of the garment ironing machine.
17. The ironing control device for a garment steamer according to claim 10, wherein the image acquisition module is further configured to:

    Obtain clothing image data of the clothing to be ironed;

    If the clothing image data is not saved in the virtual wardrobe, after determining the ironing mode of the clothing to be ironed, an association between the clothing image data and the ironing mode is constructed, and the clothing is The image data, the ironing mode and the association relationship are stored in the database of the virtual wardrobe;

    If the clothing image data has been saved in the virtual wardrobe, the ironing mode is obtained from the virtual wardrobe based on the clothing image data;

    Wherein, the virtual wardrobe is constructed by using historical clothing image data and an ironing mode corresponding to the historical clothing image data.
18. The ironing control device of a garment steamer according to claim 17, wherein the image The acquisition module is also set to:

    Identify the wrinkle parts in the clothing image data to obtain the clothing wrinkle area recognition results;

    Generate corresponding ironing area prompt voice information based on the clothing wrinkle area recognition results;

    If the steam nozzle of the ironing machine is in the wrinkle area of the clothes, prompt voice will be played according to the prompt voice information of the ironing area.
19. A garment steamer, including the garment steamer ironing control device according to any one of claims 10-18.
20. A computer-readable storage medium includes a stored program, wherein the method of any one of claims 1 to 9 is executed when the program is run.
21. An electronic device includes a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 9 through the computer program.