Washing machine control method and apparatus, computer device, and storage medium

Abstract

The application provides a washing machine control method and device, computer equipment and a storage medium, the method comprising: obtaining a target laundry image of target laundry to be processed in a washing machine; performing feature extraction on the target laundry image to obtain a target image feature of the target laundry image; determining a target laundry type of the target laundry to be processed according to the target image feature; and processing the target laundry to be processed according to a processing mode corresponding to the target laundry type. The conventional processing mode suitable for ordinary laundry and the professional processing mode suitable for valuable laundry can be simultaneously preset in the washing machine, the target laundry type is determined by using the image recognition mode, and finally the target laundry to be processed is processed by using the processing mode corresponding to the target laundry type. The whole process does not require manual participation and is completely automated, and the processing efficiency of ordinary laundry and valuable laundry is greatly improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of household appliances, in particular to a washing machine control method and device, computer equipment and storage medium. BACKGROUND

[0002] With the improvement of people's living standards, the price of purchased clothes is gradually rising, mainly in the material aspect of clothes, such as leather, fur, down, etc. The current processing mode of the washing machine is fixed, such as fixed as a conventional processing mode suitable for ordinary clothes or a professional processing mode suitable for valuable clothes. When valuable clothes are processed in the washing machine, if the fixed processing mode of the washing machine is the conventional processing mode, it is easy to cause damage to the clothes, and when ordinary clothes are processed in the washing machine, if the fixed processing mode of the washing machine is the professional processing mode, it will increase unnecessary energy consumption (the professional processing mode usually adopts a relatively mild processing strength, so it needs a longer processing time).

[0003] In the prior art, considering the proportion of ordinary clothes and valuable clothes, a washing machine with a fixed processing mode of a conventional processing mode is usually selected, and when valuable clothes need to be processed, a professional service provider can be selected to process them. However, this method seriously reduces the overall processing efficiency of ordinary clothes and valuable clothes. SUMMARY

[0004] In view of the deficiencies in the prior art, the present application provides a washing machine control method and device, computer equipment and storage medium.

[0005] In a first aspect, in one embodiment, the present application provides a washing machine control method, comprising:

[0006] obtaining a target clothes image of a target clothes to be processed in the washing machine;

[0007] performing feature extraction on the target clothes image to obtain a target image feature of the target clothes image;

[0008] determining a target clothes type of the target clothes to be processed according to the target image feature;

[0009] processing the target clothes to be processed according to a processing mode corresponding to the target clothes type.

[0010] In one embodiment, determining the target clothes type of the target clothes to be processed according to the target image feature comprises:

[0011] obtaining a preset image feature database; the image feature database comprises a plurality of sample image features;

[0012] According to the target image feature, feature matching is performed in the image feature database to obtain a matching result;

[0013] If the matching result indicates that the corresponding sample image feature can be matched in the image feature database, the target clothing type of the target clothes to be processed is determined as a professional processing type;

[0014] If the matching result indicates that the corresponding sample image feature cannot be matched in the image feature database, the target clothing type of the target clothes to be processed is determined as a regular processing type.

[0015] In one embodiment, the image features include morphological features, color features, and texture features; according to the target image feature, feature matching is performed in the image feature database to obtain a matching result, including:

[0016] The morphological features, color features, and texture features in the target image feature are respectively compared with the morphological features, color features, and texture features of each sample image feature in the image feature database to obtain a first similarity corresponding to the morphological features, a second similarity corresponding to the color features, and a third similarity corresponding to the texture features in each sample image feature;

[0017] According to the first similarity, the second similarity, and the third similarity of the target image feature and each sample image feature, a target similarity of the target image feature and each sample image feature is obtained;

[0018] If any target similarity is greater than a preset similarity threshold, a matching result indicating that the corresponding sample image feature can be matched in the image feature database is obtained;

[0019] If all target similarities are not greater than the preset similarity threshold, a matching result indicating that the corresponding sample image feature cannot be matched in the image feature database is obtained.

[0020] In one embodiment, according to the first similarity, the second similarity, and the third similarity of the target image feature and each sample image feature, a target similarity of the target image feature and each sample image feature is obtained, including:

[0021] The first weight corresponding to the morphological features, the second weight corresponding to the color features, and the third weight corresponding to the texture features are obtained;

[0022] According to the first weight, the second weight, and the third weight, the first similarity, the second similarity, and the third similarity of the target image feature and each sample image feature are respectively weighted and summed to obtain the target similarity of the target image feature and each sample image feature.

[0023] In an embodiment, before the step of acquiring the target laundry image of the target laundry to be processed in the washing machine, the washing machine control method further comprises:

[0024] acquiring historical laundry images of historical laundry to be processed in the washing machine at each time a professional processing instruction is issued;

[0025] performing feature extraction on the historical laundry images to obtain historical image features of the historical laundry images;

[0026] determining the historical image features as sample image features and adding them to the image feature database.

[0027] In an embodiment, the target laundry to be processed is processed according to the processing mode corresponding to the target laundry type, including:

[0028] in response to the issued processing instruction;

[0029] if the processing instruction is a regular processing instruction but the target laundry type of the target laundry to be processed is a professional processing type, generating target prompt information corresponding to the target laundry to be processed; the prompt information indicates that the processing mode corresponding to the processing instruction is inconsistent with the processing mode corresponding to the determined laundry type;

[0030] displaying the target prompt information;

[0031] in response to the confirmation processing instruction fed back according to the target prompt information, processing the target laundry to be processed according to the processing mode corresponding to the confirmation processing instruction.

[0032] In an embodiment, after the step of generating the target prompt information corresponding to the target laundry to be processed, the washing machine control method further comprises:

[0033] detecting the number of times the target prompt information is generated;

[0034] if the number of times is greater than a preset number threshold, marking the laundry type corresponding to the target image feature as a regular processing type.

[0035] In a second aspect, in an embodiment, the present application provides a washing machine control device, comprising:

[0036] an image acquisition module configured to acquire a target laundry image of a target laundry to be processed in a washing machine;

[0037] a feature extraction module configured to perform feature extraction on the target laundry image to obtain target image features of the target laundry image;

[0038] a type determination module configured to determine a target laundry type of the target laundry to be processed according to the target image features;

[0039] The laundry processing module is used for processing target laundry according to a processing mode corresponding to a target laundry type.

[0040] In a third aspect, in one embodiment, the present application provides a computer device, comprising a memory and a processor; the memory stores a computer program, and the processor is used to run the computer program in the memory to execute the steps in the washing machine control method in any of the above embodiments.

[0041] In a fourth aspect, in one embodiment, the present application provides a storage medium, which stores a computer program, and the computer program is loaded by a processor to execute the steps in the washing machine control method in any of the above embodiments.

[0042] By the above washing machine control method, device, computer device and storage medium, the conventional processing mode suitable for ordinary laundry and the professional processing mode suitable for valuable laundry can be preset in the washing machine at the same time, and the image recognition mode is adopted to first acquire a target laundry image of target laundry to be processed in the washing machine, and then the corresponding target image feature is obtained through feature extraction. Since the image features of ordinary laundry and valuable laundry are obviously different, the target laundry type, i.e. ordinary laundry or valuable laundry, can be determined according to the target image feature, and finally the processing mode corresponding to the target laundry type, i.e. the conventional processing mode or the professional processing mode, is used to process the target laundry to be processed. The whole process does not need human participation and is completely automated, which greatly improves the processing efficiency of ordinary laundry and valuable laundry. BRIEF DESCRIPTION OF DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0044] Figure 1 The application scenario diagram of the washing machine control method in one embodiment of the present application;

[0045] Figure 2 The flowchart of the washing machine control method in one embodiment of the present application;

[0046] Figure 3 The specific flowchart of the washing machine control method in one embodiment of the present application;

[0047] Figure 4 The specific flowchart of the washing machine control method in another embodiment of the present application;

[0048] Figure 5 Fig. 1 is a schematic diagram of a structure of a washing machine control device according to an embodiment of the present application;

[0049] Figure 6 Fig. 2 is a schematic diagram of an internal structure of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0050] The technical solutions in the embodiments of the present application will be clearly and completely described with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments of the present application, any other embodiments obtained by a person of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0051] In the description of the present application, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the purpose of facilitating the description of the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application. In addition, the terms "first", "second" are only for the purpose of description, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the technical features indicated. Therefore, the features defined as "first", "second" can explicitly or implicitly include one or more of the features. In the description of the present application, the meaning of "a plurality of" is two or more, unless otherwise explicitly and specifically limited. In the present application, the word "exemplary" is used to mean "serving as an example, instance, or illustration". Any embodiment described as "exemplary" in the present application is not necessarily to be construed as preferred or advantageous over other embodiments. The following description is presented to enable any person skilled in the art to make and use the present application. In the following description, details are set forth in order to explain the present application. It will be apparent to a person skilled in the art that the present application can be implemented without using these specific details. In other instances, well-known structures and processes have not been described in detail in order to avoid obscuring the description of the present application. Therefore, the present application is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed in the present application.

[0052] The washing machine control method in this embodiment of the invention is applied to a washing machine control device, which is set on a computer device. The computer device can be a terminal, such as a mobile phone or a tablet computer, or it can be a server or a service cluster composed of multiple servers.

[0053] like Figure 1 As shown, Figure 1 This is a schematic diagram of an application scenario of the washing machine control method according to an embodiment of the present invention. The application scenario of the washing machine control method in this embodiment of the present invention includes a computer device 100 (the computer device 100 integrates a washing machine control device), and a computer-readable storage medium corresponding to the washing machine control method is run in the computer device 100 to execute the steps of the washing machine control method.

[0054] Understandable Figure 1 The computer equipment in the application scenario of the washing machine control method shown, or the devices contained in the computer equipment, do not constitute a limitation on the embodiments of the present invention. That is, the number or type of equipment in the application scenario of the washing machine control method, or the number or type of devices contained in each device, do not affect the overall implementation of the technical solution in the embodiments of the present invention, and can all be considered as equivalent substitutions or derivatives of the technical solutions claimed in the embodiments of the present invention.

[0055] In this embodiment of the invention, the computer device 100 can be an independent device, or a network of devices or a cluster of devices. For example, the computer device 100 described in this embodiment of the invention includes, but is not limited to, a computer, a network host, a single network device, a set of multiple network devices, or a cloud device composed of multiple devices. The cloud device consists of a large number of computers or network devices based on cloud computing.

[0056] Those skilled in the art will understand that Figure 1 The application scenarios shown are merely one example corresponding to the technical solution of this invention and do not constitute a limitation on the application scenarios of the technical solution of this invention. Other application scenarios may include more than one example. Figure 1 The more or fewer computer devices shown, or the network connections of the computer devices, for example Figure 1 Only one computer device is shown in the diagram. It is understood that the scenario of the washing machine control method may also include one or more other computer devices, which are not specifically limited here. The computer device 100 may also include a memory for storing information related to the washing machine control method.

[0057] In addition, the computer device 100 in the application scenario of the washing machine control method in the embodiment of the present application can be provided with a display device, or the computer device 100 is not provided with a display device and is in communication connection with an external display device 200, and the display device 200 is used to output the result of the execution of the washing machine control method in the computer device. The computer device 100 can access a background database 300 (the background database 300 can be a local memory of the computer device 100, and the background database 300 can also be set in the cloud), and the background database 300 stores information related to the washing machine control method.

[0058] It should be noted that, Figure 1 The application scenario of the washing machine control method shown is only an example, and the application scenario of the washing machine control method described in the embodiment of the present application is used to more clearly illustrate the technical scheme of the embodiment of the present application, and does not constitute a limitation on the technical scheme provided by the embodiment of the present application.

[0059] Based on the above-mentioned application scenario of the washing machine control method, an embodiment of the washing machine control method is provided.

[0060] In a first aspect, as Figure 2 As shown in an embodiment, the present application provides a washing machine control method, comprising:

[0061] Step 201, obtaining a target clothes image of a target clothes to be processed in a washing machine;

[0062] The target clothes image of the target clothes to be processed in the washing machine can be obtained by a camera device installed at the inlet of the washing machine, and the camera device can be a miniature industrial camera CCD;

[0063] Wherein, in order to reduce the energy consumption of the camera, a corresponding wake-up condition can be set for the camera, and only when the wake-up condition is met, the camera will work normally, and when the wake-up condition is not met, the camera is in standby state or shutdown state; The wake-up condition can be a user's trigger instruction, such as before the user can put clothes into the barrel, the user can first input the corresponding trigger instruction to inform the washing machine that clothes will be put in later, and the washing machine receives the trigger instruction and immediately converts the working state of the camera from standby state or shutdown state to normal state, so that the camera can reliably obtain the target clothes image of each target clothes put in by the user; For example, for the washing machine provided with a machine door, the machine door can only be opened after power-on, so that the user can put in clothes, in this case, the wake-up condition can be set based on the power-on operation, such as counting the time after the power-on operation, when the time from the power-on operation is counted to be more than the preset time interval, it is determined that the wake-up condition is met, and if the power is not turned on after the power is turned on, the preset time interval is not exceeded, it is determined that the wake-up condition is not met. The preset time interval mainly takes into account that the user will not put in clothes at the same time after the power-on of the washing machine, but there is a certain lag time, and the preset time interval is set based on the "lag time", such as setting the preset time interval to be slightly less than the lag time. The lag time can be obtained through big data experience statistics, so as to sufficiently reduce the energy consumption of the camera; In other embodiments, any other form of wake-up condition can also be used, as long as it can reduce the energy consumption of the camera, which will not be described here.

[0064] Step 202, feature extraction is performed on the target clothes image to obtain target image features of the target clothes image;

[0065] Wherein, the feature extraction of the target clothes image can adopt a traditional feature extraction algorithm, or a machine learning algorithm; Specifically, if a machine learning algorithm is used, a trained feature extraction model is first obtained, and the target clothes image is input into the feature extraction model for feature extraction to obtain target image features of the target clothes image; The machine model is used for feature extraction, which can identify some details that cannot be identified by traditional algorithms through machine learning, thereby improving the accuracy and efficiency of feature extraction;

[0066] Wherein, before the step of obtaining the trained feature extraction model, the above washing machine control method further comprises:

[0067] Obtain a first training sample set; The first training sample set includes a plurality of training clothes images and labeled image features corresponding to the training clothes images;

[0068] The training clothes images in the first training sample set are input into the initial feature extraction model for feature extraction to obtain predicted image features of the training clothes images;

[0069] Based on the first loss function, a first loss is obtained according to the predicted image feature and the labeled image feature;

[0070] If the first loss does not satisfy the first preset convergence condition, the weight parameters of the initial feature extraction model are adjusted according to the first loss, the next first training sample set is obtained, and until the obtained first loss satisfies the first preset convergence condition, a trained feature extraction model is obtained;

[0071] In step 203, the target image feature is used to determine the target clothing type of the target laundry to be processed.

[0072] In this step, a machine learning algorithm can also be used to classify the target image feature to determine the target clothing type of the target laundry to be processed. Specifically, a trained clothing classification model is obtained, which has learned the image features of different types of clothes. The target image feature is input into the clothing classification model for clothing classification to obtain the target clothing type of the target laundry to be processed. Using a machine model to classify clothes can identify details that traditional algorithms cannot identify during the classification process, thereby improving the accuracy and efficiency of clothing classification.

[0073] Before the step of obtaining the trained clothing classification model, the above washing machine control method further comprises:

[0074] A second training sample set is obtained. The second training sample set includes a plurality of training image features and labeled clothing types corresponding to the training image features.

[0075] The training image features in the second training sample set are input into the initial clothing classification model for clothing classification to obtain predicted clothing types.

[0076] Based on the second loss function, a second loss is obtained according to the predicted clothing type and the labeled clothing type.

[0077] If the second loss does not satisfy the second preset convergence condition, the weight parameters of the initial clothing classification model are adjusted according to the second loss, the next second training sample set is obtained, and until the obtained second loss satisfies the second preset convergence condition, a trained clothing classification model is obtained.

[0078] The training image features in the second training sample set can be obtained by using the trained feature extraction model to extract features from the training clothing images.

[0079] In step 204, the target laundry to be processed is processed according to the processing mode corresponding to the target clothing type.

[0080] If the determined target clothes type is a professional processing type, it indicates that the target clothes to be processed is valuable clothes, and the corresponding processing mode can be determined as a professional processing mode, so that the target clothes to be processed is processed by using the professional processing mode. Similarly, if the determined target clothes type is a conventional processing type, it indicates that the target clothes to be processed is ordinary clothes, and the corresponding processing mode can be determined as a conventional processing mode, so that the target clothes to be processed is processed by using the conventional processing mode.

[0081] In other embodiments, in addition to the clothes type, the number of clothes can also be considered at the same time. For example, if the number of clothes put in by the user is determined to be multiple, if at least one of the target clothes types of the clothes is a professional processing type, the clothes are processed by using a professional processing mode, and if the target clothes types of all the clothes are conventional processing types, the clothes are processed by using a conventional processing mode. In addition, the number of clothes of the clothes with a professional processing type can also be used to determine the level of the professional processing mode. For example, if the number of clothes of the clothes with a professional processing type is greater than zero and less than a first preset number threshold, the clothes are processed by using a first level of professional processing mode, if the number of clothes of the clothes with a professional processing type is not less than the first preset number threshold and less than a second preset number threshold, the clothes are processed by using a second level of professional processing mode, and if the number of clothes of the clothes with a professional processing type is not less than a third preset number threshold, the clothes are processed by using a third level of professional processing mode.

[0082] The processing mode includes a washing mode, and if the washing machine also has a drying function, the processing mode also includes a drying mode.

[0083] By using the above washing machine control method, the conventional processing mode suitable for ordinary clothes and the professional processing mode suitable for valuable clothes can be simultaneously preset in the washing machine. The target clothes image of the target clothes to be processed in the washing machine is obtained by using image recognition, and the corresponding target image features are obtained by feature extraction. Since the image features of ordinary clothes and valuable clothes are obviously different, the target clothes type, i.e., ordinary clothes or valuable clothes, can be determined according to the target image features. Finally, the target clothes to be processed is processed by using the processing mode corresponding to the target clothes type, i.e., the conventional processing mode or the professional processing mode. The whole process does not require human intervention and is completely automated, which greatly improves the processing efficiency of ordinary clothes and valuable clothes.

[0084] In one embodiment, the target clothes type of the target clothes to be processed is determined according to the target image features, including:

[0085] obtaining a preset image feature database;

[0086] The image feature database includes a plurality of sample image features.

[0087] As mentioned in the above embodiments, a machine learning algorithm can be used to classify clothes according to target image features to determine the target clothes type of the target clothes to be processed. However, the training phase of the clothes classification model requires a lot of cost, and considering that each user has a limited number of clothes types, they usually do not have clothes of all clothes types. Therefore, in this embodiment, in order to reduce costs, a corresponding image feature database can be pre-constructed to include sample image features corresponding to professional processing type clothes, so that subsequent clothes classification of the target clothes to be processed can be directly performed through feature matching.

[0088] The image feature database can be constructed by user selection. For example, the user can access an upper database that contains image features of all clothes types, and select corresponding image features according to their own clothes type ownership (such as which valuable clothes they have), and then construct an image feature database that is exclusive to the user based on the selected image features.

[0089] According to the target image feature, perform feature matching in the image feature database to obtain a matching result.

[0090] When performing feature matching in the image feature database, the target image feature is compared with each sample image feature in the image feature database to determine whether there is a sample image feature with a similarity exceeding a similarity threshold. If there is, a matching result is obtained that indicates that the corresponding sample image feature can be matched in the image feature database. If there is not, a matching result is obtained that indicates that the corresponding sample image feature cannot be matched in the image feature database.

[0091] If the matching result indicates that the corresponding sample image feature can be matched in the image feature database, the target clothes type of the target clothes to be processed is determined to be a professional processing type.

[0092] Since all sample image features determined during the construction of the image feature database correspond to valuable clothes, the corresponding clothes type is also a professional processing type. Therefore, when a matching result that can be matched is obtained, the target clothes type of the target clothes to be processed can be directly determined to be a professional processing type.

[0093] If the matching result indicates that the corresponding sample image feature cannot be matched in the image feature database, the target clothes type of the target clothes to be processed is determined to be a regular processing type.

[0094] If a matching result that cannot be matched is obtained, it indicates that the target laundry to be processed does not belong to the valuable laundry defined in the image feature database, and thus the target laundry type of the target laundry to be processed is determined as a regular processing type.

[0095] The target laundry to be processed is classified by feature matching, and under the condition that each user has fewer valuable laundry types, the accuracy of the laundry classification can be ensured, and the cost generated by training the model can be reduced.

[0096] In an embodiment, the image features include morphological features, color features, and texture features; according to the target image features, feature matching is performed in the image feature database to obtain a matching result, including:

[0097] The morphological features, color features, and texture features in the target image features are respectively compared with the morphological features, color features, and texture features of each sample image feature in the image feature database to obtain a first similarity corresponding to the morphological features, a second similarity corresponding to the color features, and a third similarity corresponding to the texture features in each sample image feature;

[0098] The morphological features, color features, and texture features of the laundry image are considered respectively to ensure the richness of the data and improve the matching effect;

[0099] According to the first similarity, the second similarity, and the third similarity of the target image features and each sample image feature, a target similarity of the target image features and each sample image feature is obtained;

[0100] The first similarity, the second similarity, and the third similarity can be directly summed to obtain the target similarity, and the target similarity considers the morphological features, color features, and texture features of the image;

[0101] If any target similarity is greater than a preset similarity threshold, a matching result representing that the corresponding sample image feature can be matched in the image feature database is obtained;

[0102] If all target similarities are not greater than the preset similarity threshold, a matching result representing that the corresponding sample image feature cannot be matched in the image feature database is obtained;

[0103] Since the sample image features in the image feature database correspond to professional processing types, as long as one target similarity is greater than the preset similarity threshold, it indicates that the target image features correspond to a professional processing type.

[0104] In one embodiment, the target similarity between the target image feature and each sample image feature is obtained according to the first similarity, the second similarity and the third similarity between the target image feature and each sample image feature, comprising:

[0105] The first weight corresponding to the shape feature, the second weight corresponding to the color feature and the third weight corresponding to the texture feature are obtained.

[0106] The first weight, the second weight and the third weight are preset according to the importance of the shape feature, the color feature and the texture feature.

[0107] The first similarity, the second similarity and the third similarity between the target image feature and each sample image feature are weighted and summed according to the first weight, the second weight and the third weight, to obtain the target similarity between the target image feature and each sample image feature.

[0108] The weighted sum according to the weight corresponding to each feature fully considers the importance of different features, and improves the accuracy of the obtained target similarity.

[0109] In one embodiment, before the step of obtaining the target laundry image of the target laundry in the washing machine, the above washing machine control method further comprises:

[0110] The historical laundry image of the historical laundry in the washing machine is obtained each time the professional treatment instruction is issued.

[0111] The historical image feature of the historical laundry image is obtained by feature extraction.

[0112] The historical image feature is determined as a sample image feature and added to the image feature database.

[0113] As mentioned in the above embodiments, the sample image feature in the image feature database can be obtained by selecting from the upper database by the user, and the image feature in the upper database is usually obtained based on big data, which may have certain differences with the image feature of the laundry owned by the user, thereby affecting the accuracy of subsequent feature matching. Therefore, in the present embodiment, the sample image feature can be directly obtained by processing the laundry owned by the user. Specifically, the user can select a professional treatment mode for the historical laundry in the historical stage, i.e. input a professional treatment instruction, indicating that the user thinks that the historical laundry is a valuable laundry, and the corresponding laundry type is a professional treatment type, so that the historical laundry can be directly subjected to image acquisition and feature extraction, and the obtained historical image feature is determined as a sample image feature and added to the image feature database.

[0114] The professional processing instruction input by the user is used to determine the corresponding image feature as a sample image feature in the image feature database, which matches the actual clothing possession of the user and improves the accuracy of subsequent feature matching.

[0115] In one embodiment, the target clothes to be processed are processed according to a processing mode corresponding to the target clothes type, including:

[0116] in response to the processing instruction issued;

[0117] In this embodiment, the user is also allowed to select the processing mode by himself / herself in order to improve the user care. Specifically, if the user selects the professional processing mode, the professional processing instruction is input, and if the user selects the conventional processing mode, the conventional processing instruction is input.

[0118] If the processing instruction is the conventional processing instruction, but the target clothes to be processed are of the professional processing type, the target prompt information corresponding to the target clothes to be processed is generated.

[0119] The prompt information indicates that the processing mode corresponding to the processing instruction is inconsistent with the processing mode corresponding to the clothes type determined.

[0120] When the user intervenes, the input processing instruction is the conventional processing instruction, but the target clothes type determined is the professional processing type, which indicates that the processing mode selected by the user this time is inconsistent with the processing mode selected in the previous historical stage, which may be due to the error of the user this time. Therefore, the corresponding target prompt information can be generated.

[0121] It should be noted that when the user intervenes, the input processing instruction is the professional processing instruction, but the target clothes type determined is the conventional processing type, which indicates that the user considers that the clothes this time are valuable clothes and hopes to determine the clothes type of the clothes this time as the professional processing type. The specific details can be referred to the historical stage in the above embodiment, which will not be repeated here.

[0122] The target prompt information is displayed.

[0123] The target prompt information can be sent to the display panel of the washing machine to be displayed to the user.

[0124] In response to the confirmation processing instruction fed back according to the target prompt information, the target clothes to be processed are processed according to the processing mode corresponding to the confirmation processing instruction.

[0125] If the user thinks that he or she has not made a wrong selection, the user can further input a normal processing instruction as a confirmation processing instruction, so that the washing machine adopts a normal processing mode for processing. If the user thinks that he or she has made a wrong selection, the user can further input a professional processing instruction as a confirmation processing instruction, so that the washing machine adopts a professional processing mode for processing.

[0126] If the user does not make any response within a certain time, it is determined that the user feeds back a normal processing instruction as a confirmation processing instruction.

[0127] In the scenario of user manual intervention, the inconsistent processing mode is pre-warned and prompted, and the processing risk of clothes is fully avoided.

[0128] In one embodiment, after the step of generating the target prompt information corresponding to the target clothes to be processed, the washing machine control method further comprises:

[0129] Detecting the generation frequency of the target prompt information;

[0130] If the generation frequency is greater than a preset frequency threshold, the clothes type corresponding to the target image feature is marked as a normal processing type;

[0131] When the generation frequency is greater than the preset frequency threshold, it is indicated that the user has not simply made a wrong selection, but expects to adjust the clothes type of the clothes (for example, the clothes have become old or damaged, and do not need to be processed professionally). Specifically, it is expected to adjust the clothes type from a professional processing type to a normal processing type. For the washing machine, the clothes type is determined by constructing an image feature database. Therefore, in this case, the sample image feature matching the target image feature in the image feature database can be directly deleted, so that when the same target image feature is obtained subsequently, the corresponding sample image feature cannot be matched, that is, the clothes type corresponding to the target image feature can only be determined as a normal processing type, so as to realize the marking of the normal processing type.

[0132] In order to make the technical solutions of the present application clearer, the above embodiments are combined and described by taking washing as an example; for example, Figure 3As shown, in one embodiment, the present invention provides a washing machine control method, including: starting the execution of steps based on the power-on operation of the washing machine; after starting, activating the camera, opening the door, and starting the washing machine simultaneously; if the user puts clothes in at this time, the camera can capture the corresponding clothing image, and then extract features from the clothing image to obtain the corresponding feature parameters; if the clothing loading is not finished, the above steps are continued until the clothing loading is finished; after the loading is finished, receiving a processing instruction issued by the user; if the user clicks "professional wash", a professional processing instruction is received from the user, otherwise a regular processing instruction is received from the user; if it is a regular processing instruction, a normal washing program is matched, i.e., a regular processing mode; if it is a professional processing instruction, clothing information is stored, i.e., the corresponding image features are determined as sample image features and added to the image feature database, and a professional washing program is matched, i.e., a professional processing mode; finally, washing is performed according to the matched washing program.

[0133] To make the technical solution of this application clearer, the above embodiments will now be described in combination, taking washing as an example; for example Figure 4 As shown, in one embodiment, the present invention provides a washing machine control method, which is consistent with... Figure 3 The difference in the illustrated embodiment is that this embodiment allows for manual intervention by the user. After determining the type of clothing, the user can select a non-professional washing mode, i.e., input a regular processing command. At this time, if there are valuable clothes, i.e., the determined type of clothing is a professional processing type, a pop-up prompt will appear. If the user chooses to process the clothes, the clothes can be removed, or the professional processing command can be re-entered. If the user chooses not to process the clothes, or still inputs a regular processing command, the regular processing mode will be used for processing.

[0134] Secondly, such as Figure 5 As shown, in one embodiment, the present invention provides a washing machine control device, comprising:

[0135] Image acquisition module 301 is used to acquire the image of the target clothing to be processed in the washing machine;

[0136] Feature extraction module 302 is used to extract features from the target clothing image to obtain the target image features of the target clothing image;

[0137] The type determination module 303 is used to determine the target clothing type of the target clothing to be processed based on the characteristics of the target image;

[0138] The clothing processing module 304 is used to process the target clothing according to the processing mode corresponding to the target clothing type.

[0139] Through the washing machine control device, the conventional processing mode suitable for common clothes and the professional processing mode suitable for valuable clothes can be preset in the washing machine at the same time, and an image recognition manner is adopted to first acquire a target clothes image of target clothes to be processed in the washing machine, and then target image features are obtained through feature extraction. Since the image features of common clothes and valuable clothes are obviously different, the target clothes type, i.e., common clothes or valuable clothes, can be determined according to the target image features, and finally the target clothes to be processed is processed by using the processing mode corresponding to the target clothes type, i.e., the conventional processing mode or the professional processing mode. The whole process does not need manual participation and is completely automated, greatly improving the processing efficiency of common clothes and valuable clothes.

[0140] In one embodiment, the type determination module is specifically configured to acquire a preset image feature database; the image feature database includes a plurality of sample image features; feature matching is performed in the image feature database according to the target image features to obtain a matching result; if the matching result indicates that a corresponding sample image feature can be matched in the image feature database, the target clothes type of the target clothes to be processed is determined as a professional processing type; if the matching result indicates that a corresponding sample image feature cannot be matched in the image feature database, the target clothes type of the target clothes to be processed is determined as a conventional processing type.

[0141] In one embodiment, the image features include morphological features, color features, and texture features; the type determination module is specifically configured to compare the morphological features, color features, and texture features in the target image features with the morphological features, color features, and texture features of each sample image feature in the image feature database for similarity, to obtain a first similarity corresponding to the morphological features, a second similarity corresponding to the color features, and a third similarity corresponding to the texture features in each sample image feature; according to the first similarity, the second similarity, and the third similarity of the target image features and each sample image feature, a target similarity of the target image features and each sample image feature is obtained; if any target similarity is greater than a preset similarity threshold, a matching result indicating that a corresponding sample image feature can be matched in the image feature database is obtained; if all target similarities are not greater than the preset similarity threshold, a matching result indicating that a corresponding sample image feature cannot be matched in the image feature database is obtained.

[0142] In one embodiment, the type determination module is specifically configured to acquire a first weight corresponding to the morphological features, a second weight corresponding to the color features, and a third weight corresponding to the texture features; and according to the first weight, the second weight, and the third weight, the first similarity, the second similarity, and the third similarity of the target image features and each sample image feature are weighted and summed respectively to obtain the target similarity of the target image features and each sample image feature.

[0143] In one embodiment, the laundry machine control device further comprises:

[0144] The sample construction module is configured to, before the step of acquiring the target laundry image of the target laundry in the laundry machine, acquire a historical laundry image of a historical laundry in the laundry machine each time a professional treatment instruction is issued; perform feature extraction on the historical laundry image to obtain a historical image feature of the historical laundry image; and determine the historical image feature as a sample image feature and add the sample image feature to the image feature database.

[0145] In one embodiment, the laundry treatment module is specifically configured to, in response to the issued treatment instruction, generate target prompt information corresponding to the target laundry if the treatment instruction is a regular treatment instruction but the target laundry type of the target laundry is a professional treatment type; the prompt information indicates that the treatment mode corresponding to the treatment instruction is inconsistent with the treatment mode corresponding to the determined laundry type; display the target prompt information; and in response to a confirmation treatment instruction fed back according to the target prompt information, perform treatment on the target laundry according to the treatment mode corresponding to the confirmation treatment instruction.

[0146] In one embodiment, the laundry machine control device further comprises:

[0147] The feature deletion module is configured to, after the step of generating the target prompt information corresponding to the target laundry, detect a generation number of the target prompt information; and if the generation number is greater than a preset number threshold, mark the laundry type corresponding to the target image feature as a regular treatment type.

[0148] In a third aspect, in one embodiment, the present application provides a computer device, as shown in Figure 6 The computer device is shown in the structure of the computer device involved in the present application, specifically:

[0149] The computer device can include a processor 401 with one or more processing cores, a memory 402 with one or more computer readable storage media, a power supply 403, and an input unit 404, etc. Those skilled in the art can understand that the computer device can include more or less components than those shown in the figure, or combine some components, or different component arrangements. Among them: Figure 6 The structure of the computer device shown in the figure does not constitute a limitation on the computer device, and can include more or less components than those shown in the figure, or combine some components, or different component arrangements. Among them:

[0150] The processor 401 is the control center of the computer device, connects the various parts of the computer device through various interfaces and lines, and performs various functions and processes data of the computer device by running or executing software programs and / or modules stored in the memory 402 and calling data stored in the memory 402, thereby monitoring the computer device as a whole. Optionally, the processor 401 can include one or more processing cores; preferably, the processor 401 can integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and computer programs, and the modem processor mainly processes wireless communication. It can be understood that the above-mentioned modem processor can also not be integrated into the processor 401.

[0151] The memory 402 can be used to store software programs and modules, and the processor 401 executes various functions and data processing by running the software programs and modules stored in the memory 402. The memory 402 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one computer program required by a function (such as a sound playing function, an image playing function, etc.), and the like; the data storage area can store data created according to the use of the server, etc. In addition, the memory 402 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other volatile solid-state memory device. Accordingly, the memory 402 can also include a memory controller to provide access for the processor 401 to the memory 402.

[0152] The computer device further includes a power supply 403 for powering various components, and preferably the power supply 403 can be logically connected to the processor 401 through a power management system, so as to realize functions such as management of charging, discharging, and power consumption management through the power management system. The power supply 403 can also include one or more than one direct current or alternating current power supply, a recharging system, a power failure detection circuit, a power converter or inverter, a power state indicator, and any other components.

[0153] The computer device can also include an input unit 404, which can be used to receive input digital or character information, and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0154] Although not shown, the computer device can also include a display unit, etc., which will not be described here. Specifically, in the present embodiment, the processor 401 in the computer device will load one or more executable files corresponding to the processes of one or more computer programs into the memory 402 according to the following instructions, and run the computer programs stored in the memory 402 by the processor 401 to perform the following steps:

[0155] obtaining a target laundry image of a target laundry to be processed in the washing machine;

[0156] performing feature extraction on the target laundry image to obtain a target image feature of the target laundry image;

[0157] determining a target laundry type of the target laundry to be processed according to the target image feature;

[0158] processing the target laundry to be processed according to a processing mode corresponding to the target laundry type.

[0159] Through the above computer device, the conventional processing mode suitable for ordinary laundry and the professional processing mode suitable for valuable laundry can be simultaneously preset in the washing machine, and the image recognition mode is adopted to first obtain the target laundry image of the target laundry to be processed in the washing machine, and then the corresponding target image feature is obtained through feature extraction. Since the image features of ordinary laundry and valuable laundry are obviously different, the target laundry type, i.e., ordinary laundry or valuable laundry, can be determined according to the target image feature, and finally the processing mode corresponding to the target laundry type, i.e., the conventional processing mode or the professional processing mode, is used to process the target laundry to be processed. The whole process does not need manual participation and completely realizes automation, greatly improving the processing efficiency of ordinary laundry and valuable laundry.

[0160] Those skilled in the art can understand that all or part of the steps in any one of the methods of the above embodiments can be completed by a computer program or by a computer program controlling related hardware. The computer program can be stored in a computer readable storage medium and loaded and executed by a processor.

[0161] In a fourth aspect, in one embodiment, the present application provides a storage medium having stored therein a plurality of computer programs, which can be loaded by a processor to perform the following steps:

[0162] obtaining a target laundry image of a target laundry to be processed in the washing machine;

[0163] performing feature extraction on the target laundry image to obtain a target image feature of the target laundry image;

[0164] determining a target laundry type of the target laundry to be processed according to the target image feature;

[0165] processing the target laundry to be processed according to a processing mode corresponding to the target laundry type.

[0166] Through the storage medium, the conventional processing mode suitable for common clothes and the professional processing mode suitable for valuable clothes can be preset in the washing machine at the same time, and an image recognition manner is adopted to first acquire a target clothes image of target clothes to be processed in the washing machine, and then target image features corresponding to the target clothes image are obtained through feature extraction. Since the image features of the common clothes and the valuable clothes are obviously different, the type of the target clothes, i.e., the common clothes or the valuable clothes, can be determined according to the target image features, and finally the target clothes to be processed is processed by using the processing mode corresponding to the type of the target clothes, i.e., the conventional processing mode or the professional processing mode. The whole process does not need manual participation and is completely automated, and the processing efficiency of the common clothes and the valuable clothes is greatly improved.

[0167] It is understood by those of ordinary skill in the art that any reference to memory, storage, databases, or other media in the embodiments provided by the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink), DRAM (SLDRAM), memory bus (Rambus), direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0168] Due to the computer program stored in the storage medium, the steps in the washing machine control method in any of the embodiments provided by the present application can be executed, and thus the beneficial effects that can be achieved by the washing machine control method in any of the embodiments provided by the present application can be achieved. Details are described above and will not be repeated here.

[0169] The specific implementation of each operation can be seen from the above embodiments and will not be repeated here.

[0170] In the above embodiments, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be seen from the detailed description of other embodiments above, and will not be repeated here.

[0171] The laundry machine control method, device, computer equipment and storage medium provided by the present application are described in detail above, the principle and implementation mode of the present application are described by applying specific examples in this paper, and the above example is only used to help understand the method and core idea of the present application; meanwhile, for those skilled in the art, according to the idea of the present application, the specific implementation mode and application range will be changed, and the above description should not be understood as the limitation of the present application.

[0172] The technical features of the above examples can be combined arbitrarily, and in order to make the description simple, all possible combinations of the technical features in the above examples are not described, however, as long as the combination of the technical features does not exist contradictory, it should be considered that it is within the scope of the present application.

Claims

1. A washing machine control method, characterized in that, Applied to washing machines, including: Obtain the image of the target garment in the washing machine; Feature extraction is performed on the target clothing image to obtain the target image features of the target clothing image; Based on the features of the target image, determine the target clothing type of the target clothing to be processed; The target clothing to be processed is processed according to the processing mode corresponding to the target clothing type; The step of processing the target clothing according to the processing mode corresponding to the target clothing type includes: Responding to the issued processing instructions; If the processing instruction is a regular processing instruction, but the target garment type is a professional processing type, then a target prompt message corresponding to the target garment is generated; the prompt message indicates that the processing mode corresponding to the processing instruction is inconsistent with the processing mode corresponding to the determined garment type. Display the target prompt information; In response to the confirmation processing instruction fed back based on the target prompt information, the target clothing to be processed is processed according to the processing mode corresponding to the confirmation processing instruction; After the step of generating the target prompt information corresponding to the target clothing to be processed, the method further includes: Detect the number of times the target prompt information is generated; If the number of generation times exceeds a preset threshold, the clothing type corresponding to the target image feature is marked as a regular processing type.

2. The washing machine control method according to claim 1, characterized in that, The step of determining the target clothing type of the target clothing to be processed based on the target image features includes: Obtain a preset image feature database; the image feature database includes multiple sample image features; Based on the target image features, feature matching is performed in the image feature database to obtain the matching result; If the matching result characterization can match the corresponding sample image features in the image feature database, then the target clothing type of the target clothing to be processed is determined as the professional processing type; If the matching result indicates that the corresponding sample image feature cannot be matched in the image feature database, then the target clothing type of the target clothing to be processed is determined to be the regular processing type.

3. The washing machine control method according to claim 2, characterized in that, Image features include morphological features, color features, and texture features; the step of performing feature matching in the image feature database based on the target image features to obtain matching results includes: The morphological features, color features, and texture features in the target image features are compared with the morphological features, color features, and texture features of each sample image feature in the image feature database to obtain the first similarity corresponding to the morphological features, the second similarity corresponding to the color features, and the third similarity corresponding to the texture features in each sample image feature. The target similarity between the target image features and each sample image features is obtained based on the first similarity, second similarity, and third similarity between the target image features and each sample image features. If the similarity of any of the targets is greater than a preset similarity threshold, a matching result is obtained that represents the sample image features that can be matched in the image feature database; If the similarity of all targets is not greater than the preset similarity threshold, then a matching result is obtained that indicates that the corresponding sample image features cannot be matched in the image feature database.

4. The washing machine control method according to claim 3, characterized in that, The step of obtaining the target similarity between the target image features and each sample image features based on the first similarity, second similarity, and third similarity between the target image features and each sample image features includes: Obtain the first weight corresponding to the morphological feature, the second weight corresponding to the color feature, and the third weight corresponding to the texture feature; Based on the first weight, the second weight, and the third weight, the first similarity, the second similarity, and the third similarity between the target image feature and each sample image feature are weighted and summed to obtain the target similarity between the target image feature and each sample image feature.

5. The washing machine control method according to claim 2, characterized in that, Before the step of acquiring the target garment image in the washing machine, the method further includes: Acquire historical images of clothes to be processed in the washing machine each time a professional processing instruction is issued; Feature extraction is performed on the historical clothing image to obtain the historical image features of the historical clothing image; The historical image features are identified as sample image features and added to the image feature database.

6. A washing machine control device, characterized in that, include: The image acquisition module is used to acquire images of the target garments to be processed in the washing machine. The feature extraction module is used to extract features from the target clothing image to obtain the target image features of the target clothing image; The type determination module is used to determine the target clothing type of the target clothing to be processed based on the features of the target image; The clothing processing module is used to process the target clothing according to the processing mode corresponding to the target clothing type. The step of processing the target clothing according to the processing mode corresponding to the target clothing type includes: Responding to the issued processing instructions; If the processing instruction is a regular processing instruction, but the target garment type is a professional processing type, then a target prompt message corresponding to the target garment is generated; the prompt message indicates that the processing mode corresponding to the processing instruction is inconsistent with the processing mode corresponding to the determined garment type. Display the target prompt information; In response to the confirmation processing instruction fed back based on the target prompt information, the target clothing to be processed is processed according to the processing mode corresponding to the confirmation processing instruction; After the step of generating the target prompt information corresponding to the target clothing to be processed, the method further includes: Detect the number of times the target prompt information is generated; If the number of generation times exceeds a preset threshold, the clothing type corresponding to the target image feature is marked as a regular processing type.

7. A computer device, characterized in that, It includes a memory and a processor; the memory stores a computer program, and the processor is used to run the computer program in the memory to perform the steps in the washing machine control method according to any one of claims 1 to 5.

8. A storage medium, characterized in that, The storage medium stores a computer program, which is loaded by a processor to execute the steps of the washing machine control method according to any one of claims 1 to 5.

Images