Drying treatment method and device for accumulated water in steaming oven and electronic equipment

Abstract

The invention relates to a drying treatment method and device for accumulated water in a steaming oven and electronic equipment. The method comprises the steps that a first cavity image in a cavity of the steaming oven is obtained; inputting the first cavity image into a preset ponding recognition network for ponding recognition processing to obtain a ponding recognition result; the preset ponding recognition network is a deep learning network for ponding recognition; and under the condition that the accumulated water identification result indicates that the accumulated water exists in the cavity of the steaming and baking oven, drying the cavity of the steaming and baking oven. By means of the embodiment, whether the drying program is started or not can be more accurately judged, the drying program can be started in time when it is judged that drying is needed, dryness in the cavity of the steaming oven is effectively kept, and timeliness and processing efficiency of accumulated water removal in the cavity of the steaming oven are guaranteed.

Description

Technical Field

[0001] The present disclosure relates to the field of cooking appliances, and particularly to a method, an apparatus, and an electronic device for drying accumulated water in a steam oven. Background Art

[0002] After cooking food, there is often accumulated water at the bottom of the cavity of the existing steam oven. If not cleaned for a long time, it is easy to breed bacteria and affect health. In the prior art, removing the accumulated water in the steam oven often requires manual operation. The way of manually removing the accumulated water in the steam oven will increase the workload and time cost of users, and there is often a phenomenon that the accumulated water stays in the steam oven for a period of time before being discovered and cleaned. As a result, the existing accumulated water removal solutions have problems such as poor timeliness and low processing efficiency of accumulated water removal. Summary of the Invention

[0003] The present disclosure provides a method, an apparatus, and an electronic device for drying accumulated water in a steam oven to at least solve the problems such as poor timeliness and low processing efficiency of removing accumulated water in the steam oven in the related art. The technical solutions of the present disclosure are as follows:

[0004] According to a first aspect of an embodiment of the present disclosure, there is provided a method for drying accumulated water in a steam oven, including:

[0005] Obtaining a first cavity image in the cavity of the steam oven;

[0006] Inputting the first cavity image into a preset accumulated water recognition network for accumulated water recognition processing to obtain an accumulated water recognition result; the preset accumulated water recognition network is a deep learning network for performing accumulated water recognition;

[0007] When the accumulated water recognition result indicates that there is accumulated water in the cavity of the steam oven, performing drying processing on the cavity of the steam oven.

[0008] In an optional embodiment, the method further includes:

[0009] Obtaining the current humidity in the cavity of the steam oven;

[0010] The performing drying processing on the cavity of the steam oven when the accumulated water recognition result indicates that there is accumulated water in the cavity of the steam oven includes:

[0011] When the accumulated water recognition result indicates that there is accumulated water in the cavity of the steam oven and the current humidity is greater than a first preset threshold, performing drying processing on the cavity of the steam oven.

[0012] In an optional embodiment, the performing drying processing on the cavity of the steam oven when the accumulated water recognition result indicates that there is accumulated water in the cavity of the steam oven includes:

[0013] When the water accumulation recognition result indicates that there is water accumulation in the steam oven cavity, a preset drying prompt message is fed back, and the preset drying prompt message is used to indicate that the water accumulation in the steam oven cavity is to be dried;

[0014] When the feedback duration corresponding to the preset drying prompt message is greater than a preset duration and no drying instruction is received, the drying program is automatically started to dry the steam oven cavity.

[0015] In an optional embodiment, the step of automatically starting the drying program to dry the steam oven cavity when the feedback duration corresponding to the preset drying prompt message is greater than the preset duration and no drying instruction is received includes:

[0016] When the feedback duration corresponding to the preset drying prompt message is greater than the preset duration and no drying instruction is received, a second cavity image of the steam oven cavity is obtained;

[0017] The second cavity image is input into a preset food recognition network for food recognition processing to obtain a food recognition result, and the preset food recognition network is a deep learning network for food recognition;

[0018] When the food recognition result indicates that there is no food in the steam oven cavity, the drying program is automatically started to dry the steam oven cavity.

[0019] In an optional embodiment, the step of automatically starting the drying program to dry the steam oven cavity when the food recognition result indicates that there is no food in the steam oven cavity includes:

[0020] When the food recognition result indicates that there is no food in the steam oven cavity and the door of the steam oven is closed, the drying program is automatically started to dry the steam oven cavity.

[0021] In an optional embodiment, the preset food recognition network is trained in the following manner:

[0022] A plurality of second sample images and a preset food label corresponding to each second sample image are obtained. The plurality of second sample images include a plurality of second positive sample images and a plurality of second negative sample images; the plurality of second positive sample images are images containing food; the plurality of second negative sample images are images not containing food;

[0023] Based on the plurality of second sample images and the preset food labels, food recognition training is performed on a second network to be trained to obtain the preset food recognition network.

[0024] In an alternative embodiment, the preset water accumulation recognition network is trained in the following manner:

[0025] Obtain a plurality of first sample images and a preset water accumulation label corresponding to each first sample image. The plurality of first sample images include a plurality of first positive sample images and a plurality of first negative sample images; the plurality of first positive sample images are images containing water accumulation; the plurality of first negative sample images are images not containing water accumulation;

[0026] Based on the plurality of first sample images and the preset water accumulation label, perform water accumulation recognition training on a first network to be trained to obtain the preset water accumulation recognition network.

[0027] In an alternative embodiment, the method further includes:

[0028] Obtain working state indication information corresponding to the steam oven;

[0029] The obtaining of the first cavity image in the steam oven cavity includes:

[0030] When the working state indication information indicates that the steam oven is in a non-working state, obtain the first cavity image in the steam oven cavity.

[0031] According to a second aspect of the embodiments of the present disclosure, there is provided a water accumulation drying processing device in a steam oven, including:

[0032] A first cavity image acquisition module, configured to acquire a first cavity image in the steam oven cavity;

[0033] A water accumulation recognition processing module, configured to input the first cavity image into a preset water accumulation recognition network for water accumulation recognition processing to obtain a water accumulation recognition result; the preset water accumulation recognition network is a deep learning network for water accumulation recognition;

[0034] A drying processing module, configured to perform drying processing on the steam oven cavity when the water accumulation recognition result indicates that there is water accumulation in the steam oven cavity.

[0035] In an alternative embodiment, the device further includes:

[0036] A humidity acquisition module, configured to acquire the current humidity in the steam oven cavity;

[0037] The drying processing module includes:

[0038] A first drying processing unit, configured to perform drying processing on the steam oven cavity when the water accumulation recognition result indicates that there is water accumulation in the steam oven cavity and the current humidity is greater than a first preset threshold.

[0039] In an optional embodiment, the drying processing module includes:

[0040] A preset drying prompt information feedback unit, configured to feedback preset drying prompt information when the water accumulation recognition result indicates that there is water accumulation in the steam oven cavity, and the preset drying prompt information is used to indicate that the water accumulation in the steam oven cavity is to be dried;

[0041] A second drying processing unit, configured to automatically start a drying program to dry the steam oven cavity when the feedback duration corresponding to the preset drying prompt information is greater than a preset duration and no drying instruction is received.

[0042] In an optional embodiment, the second drying processing unit includes:

[0043] A second cavity image acquisition sub-unit, configured to acquire a second cavity image in the steam oven cavity when the feedback duration corresponding to the preset drying prompt information is greater than the preset duration and no drying instruction is received;

[0044] A food recognition result acquisition sub-unit, configured to input the second cavity image into a preset food recognition network for food recognition processing to obtain a food recognition result, and the preset food recognition network is a deep learning network for food recognition;

[0045] A drying processing sub-unit, configured to automatically start a drying program to dry the steam oven cavity when the food recognition result indicates that there is no food in the steam oven cavity.

[0046] In an optional embodiment, the drying processing sub-unit includes:

[0047] An automatic drying sub-unit, configured to automatically start a drying program to dry the steam oven cavity when the food recognition result indicates that there is no food in the steam oven cavity and the door of the steam oven is closed.

[0048] In an optional embodiment, the preset food recognition network is trained by using the following modules:

[0049] A first training data acquisition module, configured to acquire a plurality of second sample images and a preset food label corresponding to each second sample image, and the plurality of second sample images include a plurality of second positive sample images and a plurality of second negative sample images; the plurality of second positive sample images are images containing food; the plurality of second negative sample images are images not containing food;

[0050] A first network training module, configured to perform food recognition training on a second network to be trained based on the multiple second sample images and the preset food labels, so as to obtain the preset food recognition network.

[0051] In an optional embodiment, the preset ponding recognition network is trained by using the following modules:

[0052] A second training data acquisition module, configured to acquire a plurality of first sample images and a preset ponding label corresponding to each first sample image, where the plurality of first sample images include a plurality of first positive sample images and a plurality of first negative sample images; the plurality of first positive sample images are images containing ponding; the plurality of first negative sample images are images not containing ponding;

[0053] A second network training module, configured to perform ponding recognition training on a first network to be trained based on the plurality of first sample images and the preset ponding label, so as to obtain the preset ponding recognition network.

[0054] In an optional embodiment, the apparatus further includes:

[0055] A working state indication information acquisition module, configured to acquire the working state indication information corresponding to the steam oven;

[0056] The first cavity image acquisition module includes:

[0057] A first cavity image acquisition unit, configured to acquire a first cavity image in the cavity of the steam oven when the working state indication information indicates that the steam oven is in a non-working state.

[0058] According to a third aspect of the embodiments of the present disclosure, there is provided an electronic device, including: a processor; and a memory for storing executable instructions of the processor; wherein, the processor is configured to execute the instructions to implement the method according to any one of the first aspects above.

[0059] According to a fourth aspect of the embodiments of the present disclosure, there is provided a computer-readable storage medium, when instructions in the storage medium are executed by a processor of an electronic device, enabling the electronic device to execute the method according to any one of the first aspects of the embodiments of the present disclosure.

[0060] According to a fifth aspect of the embodiments of the present disclosure, there is provided a computer program product including instructions, when the computer program product runs on a computer, enabling the computer to execute the method according to any one of the first aspects of the embodiments of the present disclosure.

[0061] The technical solutions provided by the embodiments of the present disclosure at least bring the following beneficial effects:

[0062] During the process of drying accumulated water in a steam oven, a deep learning network is used to identify the accumulated water to ensure the accuracy of the identification. When the identification result indicates that there is accumulated water in the steam oven cavity, the steam oven cavity is dried, which can timely remove the accumulated water, dry the cavity of the steam oven, avoid the growth of bacteria in the cavity due to the long-term residue of the accumulated water, keep the cavity dry and clean at all times, and ensure the timeliness and processing efficiency of the removal of the accumulated water.

[0063] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and do not limit the present disclosure. Brief Description of the Drawings

[0064] The drawings herein are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with the present disclosure, and are used together with the specification to explain the principles of the present disclosure, and do not constitute an improper limitation of the present disclosure.

[0065] Figure 1 is a flowchart of a method for drying accumulated water in a steam oven shown according to an exemplary embodiment;

[0066] Figure 2 is a schematic flow diagram of training an accumulated water identification network shown according to an exemplary embodiment;

[0067] Figure 3 is a schematic flow diagram of a drying process shown according to an exemplary embodiment;

[0068] Figure 4 is a schematic flow diagram of another drying process shown according to an exemplary embodiment;

[0069] Figure 5 is a schematic flow diagram of training a food identification network shown according to an exemplary embodiment;

[0070] Figure 6 is a schematic flow diagram of another method for drying accumulated water in a steam oven shown according to an exemplary embodiment;

[0071] Figure 7 is a block diagram of a device for drying accumulated water in an oven shown according to an exemplary embodiment;

[0072] Figure 8 is a block diagram of an electronic device for drying accumulated water in an oven shown according to an exemplary embodiment. Detailed Description of the Embodiments

[0073] In order to enable those of ordinary skill in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the drawings.

[0074] It should be noted that the terms "first", "second", etc. in the description, claims and the above drawings of the present disclosure are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present disclosure described here can be implemented in an order other than those illustrated or described here. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0075] A method for drying accumulated water in a steam oven provided by the present application can be applied to an electronic device, which includes a memory, a processor, a bus, and a communication interface. Memory: The memory is used to store the software system required by the device, a preset accumulated water recognition network, and a preset food recognition network. Among them, the preset accumulated water recognition network is a deep learning network for recognizing accumulated water. The input of the preset accumulated water recognition network is the first cavity image obtained by the camera in the cavity, and the output is the accumulated water recognition result; the preset food recognition network is a deep learning network for recognizing food. The input of the preset food recognition network is the second cavity image obtained by the camera in the cavity, and the output is the food recognition result. The software system is used to control various application programs of the software. Processor: An integrated circuit chip with the ability to process signals. Bus: Includes an address bus, a data bus, a control bus, etc. Software system: Used to control various application programs of the software.

[0076] Please refer to Figure 1 , Figure 1 is a flowchart of a method for drying accumulated water in a steam oven shown according to an exemplary embodiment. Specifically, the method may include the following steps:

[0077] Step S101, obtain the first cavity image in the steam oven cavity.

[0078] In a specific embodiment, the above first cavity image may be an image in the steam oven cavity; specifically, the steam oven cavity may be internally provided with a camera, and correspondingly, the above first cavity image may be collected through the internally provided camera.

[0079] In an alternative embodiment, the above method may further include:

[0080] Obtain the working state indication information corresponding to the steam oven;

[0081] Correspondingly, the above obtaining the first cavity image in the steam oven cavity may include:

[0082] When the working status indication information indicates that the steam oven is in a non - working state, obtain the first cavity image inside the steam oven cavity.

[0083] In a specific embodiment, the above - mentioned working status indication information can be used to indicate whether the steam oven is in a working state. Specifically, in order to avoid affecting the normal operation of the steam oven, water treatment can be performed when the working status indication information indicates that the steam oven is in a non - working state. Correspondingly, the first cavity image inside the steam oven cavity can be obtained to enter the automatic water removal process.

[0084] In the above - mentioned embodiment, the automatic water removal function is judged in combination with the working status of the steam oven. The automatic water removal function can only be turned on when the steam oven is in a non - working state, ensuring that the activation of the automatic water removal function will not affect the normal operation of the steam oven, thus ensuring the safety of the steam oven during the working state.

[0085] Step S103: Input the first cavity image into a preset water accumulation recognition network for water accumulation recognition processing to obtain a water accumulation recognition result.

[0086] In a specific embodiment, the above - mentioned preset water accumulation recognition network is a deep - learning network for water accumulation recognition. In an alternative embodiment, the above - mentioned preset water accumulation recognition network can be trained based on multiple first - sample images and preset water accumulation labels. In a specific embodiment, as Figure 2 shown, the steps of training the water accumulation recognition network may include:

[0087] Step S201: Obtain multiple first - sample images and the preset water accumulation label corresponding to each first - sample image.

[0088] In some embodiments, the above - mentioned first - sample images include multiple first - positive - sample images and multiple first - negative - sample images. In some embodiments, the multiple first - positive - sample images are images containing water accumulation, and the multiple first - negative - sample images are images not containing water accumulation.

[0089] In a specific embodiment, the preset water accumulation label can be used to indicate whether there is water accumulation in the corresponding image. Optionally, the preset water accumulation label can be the probability of indicating that the corresponding image contains water accumulation; correspondingly, the preset water accumulation label corresponding to the first - positive - sample image can be 1; the preset water accumulation label corresponding to the first - negative - sample image can be 0.

[0090] Step S203: Based on the multiple first - sample images and the preset water accumulation labels, perform water accumulation recognition training on the first network to be trained to obtain a preset water accumulation recognition network.

[0091] In a specific embodiment, the above-mentioned training of the first network to be trained for waterlogging recognition based on multiple first sample images and a preset waterlogging label to obtain a preset waterlogging recognition network may include: determining a current first sample image from the multiple first sample images, inputting the current first sample image into the first network to be trained for waterlogging recognition training to obtain a predicted waterlogging recognition result; determining a waterlogging recognition result loss according to the predicted waterlogging recognition result and the preset waterlogging label; and training the first network to be trained based on the waterlogging recognition result loss to obtain a preset waterlogging recognition network.

[0092] In a specific embodiment, the current first sample image may be the training data (part of the first sample images) of the current first training cycle. Specifically, the current first sample image may be determined randomly from the multiple first sample images, or a part of the first sample images that have not participated in model training may be randomly selected from the multiple first sample images as the current first sample image; the predicted waterlogging recognition result corresponding to any first sample image may be used to indicate whether there is waterlogging in the first sample image. Specifically, the predicted waterlogging recognition result corresponding to any first sample image may be used to indicate the probability of waterlogging in the first sample image.

[0093] In a specific embodiment, determining the waterlogging recognition result loss according to the predicted waterlogging recognition result and the preset waterlogging label may include combining a first preset loss function to determine the waterlogging recognition result loss between the predicted waterlogging recognition result and the preset waterlogging label; specifically, the waterlogging recognition result loss may characterize the waterlogging recognition performance of the current first network to be trained. Specifically, the first preset loss function may be set in combination with actual applications.

[0094] In a specific embodiment, training the first network to be trained based on the waterlogging recognition result loss to obtain a preset waterlogging recognition network may include: combining the gradient descent method and the waterlogging recognition result loss to update the model parameters of the first network to be trained, and based on the updated first network to be trained, repeating the above-mentioned loop iteration operation from determining the current first sample image from the multiple first sample images to updating the model parameters of the first network to be trained until a first preset convergence condition is met, and the first network to be trained corresponding to when the first preset convergence condition is met is the preset waterlogging recognition network.

[0095] In a specific embodiment, the first preset convergence condition may be set in combination with actual applications. For example, the first execution number of the loop iteration operation reaches a first preset number, the waterlogging recognition result is less than a first specified threshold, etc. Specifically, it may be set in combination with the training speed and model accuracy requirements.

[0096] In a specific example, the network structure of the first network to be trained can be set according to the actual application. Optionally, the first network to be trained can be a deep learning network such as a convolutional neural network.

[0097] Step S105: When the water accumulation recognition result indicates that there is water accumulation in the steam oven cavity, perform a drying process on the steam oven cavity.

[0098] In a specific embodiment, the above water accumulation recognition result can be used to indicate whether there is water accumulation in the steam oven cavity. Specifically, the water accumulation recognition result can be the probability of water accumulation in the first cavity image. Optionally, when the probability of water accumulation in the first cavity image is greater than a second preset threshold, a water accumulation recognition result indicating that there is water accumulation in the steam oven cavity can be obtained; conversely, when the probability of water accumulation in the first cavity image is less than or equal to the second preset threshold, a water accumulation recognition result indicating that there is no water accumulation in the steam oven cavity can be obtained. In a specific embodiment, the second preset threshold can be a probability threshold.

[0099] In an alternative embodiment, as Figure 3 shown, the above method further includes:

[0100] Step S301: Obtain the current humidity in the steam oven cavity.

[0101] In a specific embodiment, the above current humidity can be the current humidity in the steam oven cavity. Specifically, the steam oven cavity can be internally provided with a humidity sensor. Correspondingly, the current humidity can be collected through the internally provided humidity sensor.

[0102] Correspondingly, when the water accumulation recognition result indicates that there is water accumulation in the steam oven cavity, performing a drying process on the steam oven cavity can include:

[0103] Step S303: When the water accumulation recognition result indicates that there is water accumulation in the steam oven cavity and the current humidity is greater than a first preset threshold, perform a drying process on the steam oven cavity.

[0104] In a specific embodiment, the first preset threshold can be a preset humidity that needs to be dried. In a specific embodiment, the first preset threshold can be set in advance. Optionally, when the current humidity is greater than the first preset threshold, it can be determined that there is water accumulation in the steam oven cavity; conversely, when the current humidity is less than or equal to the first preset threshold, it can be determined that there is no water accumulation in the steam oven cavity. In a specific embodiment, the first preset threshold can be a humidity threshold.

[0105] In the above embodiments, the humidity sensor is combined to obtain the humidity in the steam oven cavity. When the water accumulation recognition result indicates that there is water accumulation in the steam oven cavity and the current humidity is greater than the first preset threshold, the steam oven cavity is dried, which further ensures the accuracy of the water accumulation recognition result and then effectively dries the steam oven.

[0106] In a specific embodiment, as Figure 4 shown, when the water accumulation recognition result indicates that there is water accumulation in the steam oven cavity, the drying process of the steam oven cavity may include:

[0107] Step S107: When the water accumulation recognition result indicates that there is water accumulation in the steam oven cavity, feedback the preset drying prompt information.

[0108] In a specific embodiment, the above preset drying prompt information may be a prompt information for water accumulation removal in the steam oven cavity. Specifically, the user can set the prompt method of the preset drying prompt information. In an alternative embodiment, the prompt method may include the steam oven reminding the user that the steam oven cavity needs to remove water accumulation in a sound prompt manner. In an alternative embodiment, the prompt method may include reminding the user that the steam oven cavity needs to remove water accumulation in a manner of displaying information on the steam oven screen.

[0109] Step S109: When the feedback duration corresponding to the preset drying prompt information is greater than the preset duration and no drying instruction is received, automatically start the drying program to dry the steam oven cavity.

[0110] In a specific embodiment, the feedback duration corresponding to the above preset drying prompt information may be the duration between the feedback start time and the current time of the preset drying prompt information. In a specific embodiment, the above preset duration may be the reminder duration of the preset drying prompt information. In a specific embodiment, the above drying instruction may be an instruction for the user to trigger the start of the drying program. Specifically, the user can trigger the drying instruction by pressing the button corresponding to the water accumulation removal function on the steam oven screen, etc.

[0111] In the above embodiments, when the water accumulation recognition result indicates that there is water accumulation in the steam oven cavity, the preset drying prompt information is fed back to the user, which can timely notify the user that the steam oven cavity needs to remove water accumulation at this time. When the user does not remove the water accumulation, the steam oven automatically starts the drying program, reducing the residence time of the water accumulation in the cavity and reducing the growth of bacteria, thus ensuring the timeliness and processing efficiency of water accumulation removal and ensuring the cleanliness of the steam oven cavity.

[0112] In an optional embodiment, when the feedback duration corresponding to the preset drying prompt message is greater than the preset duration and no drying instruction is received, automatically starting a drying program to perform a drying process on the steam oven cavity includes:

[0113] When the feedback duration corresponding to the preset drying prompt message is greater than the preset duration and no drying instruction is received, obtain a second cavity image inside the steam oven cavity;

[0114] Input the second cavity image into a preset food recognition network for food recognition processing to obtain a food recognition result;

[0115] When the food recognition result indicates that there is no food in the steam oven cavity, automatically start a drying program to perform a drying process on the steam oven cavity.

[0116] In a specific embodiment, the above second cavity image can be an image inside the steam oven cavity; specifically, the steam oven cavity can be internally provided with a camera. Correspondingly, when the feedback duration corresponding to the preset drying prompt message is greater than the preset duration and no drying instruction is received, the above second cavity image can be collected through the internally provided camera.

[0117] In a specific embodiment, the above preset food recognition network is a deep learning network for food recognition. In an optional embodiment, the above food recognition network can be trained based on multiple second sample images and preset food labels. In a specific embodiment, as Figure 5 shown, the steps of training the food recognition network may include:

[0118] Step S501, obtain multiple second sample images and the preset food label corresponding to each second sample image.

[0119] In some embodiments, the above second sample images may include multiple second positive sample images and multiple second negative sample images for training the to-be-trained food recognition network. Correspondingly, the multiple second positive sample images are multiple images of the steam oven cavity containing food, and the multiple second negative sample images are multiple images of the steam oven cavity not containing food. Specifically, the steam oven cavity can be internally provided with a camera. Correspondingly, the second positive sample images and the second negative sample images can be collected through the internally provided camera.

[0120] Step S503, based on the multiple second sample images and the preset food labels, perform food recognition training on the second to-be-trained network to obtain a preset food recognition network.

[0121] In a specific embodiment, the preset food label can be used to indicate whether there is food in the corresponding image. Optionally, the preset food label can be the probability indicating that the corresponding image contains food. Correspondingly, the preset food label corresponding to the second positive sample image can be 1; the preset food label corresponding to the second negative sample image can be 0.

[0122] In a specific embodiment, the above-mentioned food recognition training of the second network to be trained based on multiple second sample images and preset food labels to obtain a preset food recognition network may include: determining the current second sample image from the multiple second sample images, inputting the current second sample image into the second network to be trained for food recognition training to obtain a predicted food recognition result; determining the food recognition result loss according to the predicted food recognition result and the preset food label; and training the second network to be trained based on the food recognition result loss to obtain a preset food recognition network.

[0123] In a specific embodiment, the current second sample image can be the training data (part of the second sample images) of the current second training cycle. Specifically, the current second sample image can be randomly determined from the multiple second sample images, or a part of the second sample images that have not participated in model training can be randomly selected from the multiple second sample images as the current second sample image. The predicted food recognition result corresponding to any second sample image can be used to indicate whether there is food in the second sample image. Specifically, the predicted food recognition result corresponding to any second sample image can be used to indicate the probability that the second sample image contains food.

[0124] In a specific embodiment, determining the food recognition result loss according to the predicted food recognition result and the preset food label may include combining a second preset loss function to determine the food recognition result loss between the predicted food recognition result and the preset food label. Specifically, the food recognition result loss can represent the food recognition performance of the current second network to be trained. Specifically, the second preset loss function can be set in combination with actual applications.

[0125] In a specific embodiment, training the second network to be trained based on the food recognition result loss to obtain a preset food recognition network may include: combining the gradient descent method and the food recognition result loss to update the model parameters of the second network to be trained, and based on the updated second network to be trained, repeating the above loop iteration operations from determining the current second sample image from the multiple second sample images to updating the model parameters of the second network to be trained until the second preset convergence condition is met, and the second network to be trained corresponding to when the second preset convergence condition is met is the preset food recognition network.

[0126] In a specific embodiment, the satisfaction of the second preset convergence condition can be set in combination with the actual application. For example, the second execution count of the loop iteration operation reaches the second preset count, the food recognition result is less than the second specified threshold, etc. Specifically, it can be set in combination with the training speed and model accuracy requirements.

[0127] In a specific example, the network structure of the second network to be trained can be set in combination with the actual application. Optionally, the second training network can be a deep learning network such as a convolutional neural network.

[0128] In the above embodiment, by determining whether there is food in the steam oven cavity to determine whether to start the automatic drying program, the automatic drying program is started only when there is no food in the steam oven cavity, which can effectively ensure the taste and integrity of the food and guarantee the user's experience of using the steam oven and dining experience.

[0129] In a specific embodiment, in the case where the food recognition result indicates that there is no food in the steam oven cavity, automatically starting the drying program to perform a drying process on the steam oven cavity includes:

[0130] When the food recognition result indicates that there is no food in the steam oven cavity and the door of the steam oven is closed, automatically start the drying program to perform a drying process on the steam oven cavity.

[0131] In the above embodiment, when it is determined that the door of the steam oven is closed, starting the automatic drying program can effectively ensure the tightness and safety of water accumulation removal.

[0132] In an alternative embodiment, when jointly determining whether there is water accumulation in the steam oven cavity in combination with the current humidity of the steam oven and the water accumulation recognition result, as Figure 6 shown, Figure 6 FIG. is a schematic flowchart of another method for drying water accumulation in a steam oven shown according to an exemplary embodiment. Specifically, it may include the following steps:

[0133] In step S601, obtain a first cavity image of the steam oven cavity;

[0134] In step S603, input the first cavity image into a preset water accumulation recognition network for water accumulation recognition processing to obtain a water accumulation recognition result; the preset water accumulation recognition network is a deep learning network for performing water accumulation recognition.

[0135] In step S605, obtain the current humidity in the steam oven cavity;

[0136] In step S607, when the water accumulation recognition result indicates that there is water accumulation in the steam oven cavity and the current humidity is greater than the first preset threshold, a preset drying prompt message is fed back, and the preset drying prompt message is used to indicate that the water accumulation in the steam oven cavity is to be dried;

[0137] In step S609, when the feedback duration corresponding to the preset drying prompt message is greater than the preset duration and no drying instruction is received, the second cavity image in the steam oven cavity is acquired;

[0138] In step S611, the second cavity image is input into a preset food recognition network for food recognition processing to obtain a food recognition result. The preset food recognition network is a deep learning network for food recognition;

[0139] In step S613, when the food recognition result indicates that there is no food in the steam oven cavity and the door of the steam oven is closed, the drying program is automatically started to dry the steam oven cavity.

[0140] Figure 7 It is a block diagram of a water accumulation drying processing device in a steam oven shown according to an exemplary embodiment. Refer to Figure 7 and the device includes:

[0141] The first cavity image acquisition module 710 is configured to acquire the first cavity image in the steam oven cavity;

[0142] The water accumulation recognition processing module 720 is configured to input the first cavity image into a preset water accumulation recognition network for water accumulation recognition processing to obtain a water accumulation recognition result; the preset water accumulation recognition network is a deep learning network for water accumulation recognition;

[0143] The drying processing module 730 is configured to dry the steam oven cavity when the water accumulation recognition result indicates that there is water accumulation in the steam oven cavity.

[0144] In an optional embodiment, the above device further includes:

[0145] The humidity acquisition module is configured to acquire the current humidity in the steam oven cavity;

[0146] The above drying processing module 730 includes:

[0147] The first drying processing unit is configured to dry the steam oven cavity when the water accumulation recognition result indicates that there is water accumulation in the steam oven cavity and the current humidity is greater than the first preset threshold.

[0148] In an optional embodiment, the above drying processing module 730 includes:

[0149] A preset drying prompt information feedback unit, configured to feedback preset drying prompt information when the water accumulation recognition result indicates that there is water accumulation in the steam oven cavity, and the preset drying prompt information is used to indicate that the water accumulation in the steam oven cavity is to be dried;

[0150] A second drying processing unit, configured to automatically start a drying program to dry the steam oven cavity when the feedback duration corresponding to the preset drying prompt information is greater than a preset duration and no drying instruction is received.

[0151] In an optional embodiment, the above-mentioned second drying processing unit includes:

[0152] A second cavity image acquisition sub-unit, configured to acquire a second cavity image in the steam oven cavity when the feedback duration corresponding to the preset drying prompt information is greater than a preset duration and no drying instruction is received;

[0153] A food recognition result acquisition sub-unit, configured to input the second cavity image into a preset food recognition network for food recognition processing to obtain a food recognition result, and the preset food recognition network is a deep learning network for food recognition;

[0154] A drying processing sub-unit, configured to automatically start a drying program to dry the steam oven cavity when the food recognition result indicates that there is no food in the steam oven cavity.

[0155] In an optional embodiment, the above-mentioned drying processing sub-unit includes:

[0156] An automatic drying sub-unit, configured to automatically start a drying program to dry the steam oven cavity when the food recognition result indicates that there is no food in the steam oven cavity and the door of the steam oven is closed.

[0157] In an optional embodiment, the above-mentioned preset food recognition network is trained by using the following modules:

[0158] A first training data acquisition module, configured to acquire a plurality of second sample images and a preset food label corresponding to each second sample image, and the plurality of second sample images include a plurality of second positive sample images and a plurality of second negative sample images; the plurality of second positive sample images are images containing food; the plurality of second negative sample images are images not containing food;

[0159] A first network training module, configured to perform food recognition training on a second network to be trained based on the plurality of second sample images and the preset food label to obtain a preset food recognition network.

[0160] In an optional embodiment, the above-mentioned preset water accumulation recognition network is trained by using the following modules:

[0161] A second training data acquisition module, configured to acquire a plurality of first sample images and preset water accumulation labels corresponding to each of the first sample images, where the plurality of first sample images include a plurality of first positive sample images and a plurality of first negative sample images; the plurality of first positive sample images are images containing water accumulation; the plurality of first negative sample images are images not containing water accumulation.

[0162] A second network training module, configured to perform water accumulation recognition training on a first network to be trained based on the plurality of first sample images and the preset water accumulation labels, so as to obtain a preset water accumulation recognition network.

[0163] In an optional embodiment, the above device further includes:

[0164] A working state indication information acquisition module, configured to acquire working state indication information corresponding to the steam oven.

[0165] The above first cavity image acquisition module 710 includes:

[0166] A first cavity image acquisition unit, configured to acquire a first cavity image inside the steam oven when the working state indication information indicates that the steam oven is in a non-working state.

[0167] Regarding the device in the above embodiment, the specific manners in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated herein.

[0168] Figure 8 It is a block diagram of an electronic device for a method of drying water accumulation in a steam oven according to an exemplary embodiment. The electronic device may be a terminal, and its internal structure diagram may be as Figure 8 shown. The electronic device includes a processor, a memory, a network interface, a display screen, and an input device connected through a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a method of drying water accumulation in a steam oven. The display screen of the electronic device may be a liquid crystal display screen or an electronic ink display screen. The input device of the electronic device may be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the outer shell of the electronic device, or an external keyboard, touchpad, or mouse, etc.

[0169] Those skilled in the art can understand, Figure 8The structure shown is only a block diagram of some of the structures related to the present disclosure, and does not constitute a limitation on the electronic device to which the present disclosure is applied. The specific electronic device may include more or fewer components than those shown in the figure, or combine some components, or have a different component arrangement.

[0170] In an exemplary embodiment, an electronic device is further provided, including: a processor; a memory for storing instructions executable by the processor; wherein, the processor is configured to execute the instructions to implement the method for drying accumulated water in a steam oven as in the embodiments of the present disclosure.

[0171] In an exemplary embodiment, a computer-readable storage medium is further provided. When the instructions in the storage medium are executed by the processor of the electronic device, the electronic device can execute the method for drying accumulated water in a steam oven in the embodiments of the present disclosure.

[0172] In an exemplary embodiment, a computer program product containing instructions is further provided. When it runs on a computer, the computer is caused to execute the method for drying accumulated water in a steam oven in the embodiments of the present disclosure.

[0173] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it may include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided in the present application may include non-volatile and / or volatile memories. Non-volatile memories may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many 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.

[0174] Other embodiments of the present disclosure will be readily apparent to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include known common general knowledge or conventional technical means in the technical field not disclosed herein. The specification and examples are only to be considered as exemplary, and the true scope and spirit of the present disclosure are pointed out by the following claims.

[0175] It should be understood that the present disclosure is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present disclosure is only limited by the appended claims.

Claims

1. A method for drying accumulated water in a steam oven, characterized in that: include: Acquire a first cavity image in the oven cavity; Inputting the first cavity image into a preset water accumulation recognition network for water accumulation recognition processing to obtain a water accumulation recognition result; The preset water accumulation recognition network is a deep learning network used for water accumulation recognition; When the water accumulation identification result indicates that water is accumulated in the oven cavity, the oven cavity is dried.

2. The method according to claim 1, characterized in that: The method further comprises: Acquiring the current humidity in the oven cavity; When the water accumulation identification result indicates that water is accumulated in the oven cavity, drying the oven cavity includes: When the water accumulation identification result indicates that water is accumulated in the oven cavity and the current humidity is greater than a first preset threshold, the oven cavity is dried.

3. The method according to claim 1, characterized in that: When the water accumulation identification result indicates that water is accumulated in the oven cavity, drying the oven cavity includes: When the water accumulation identification result indicates that water is accumulated in the oven cavity, feeding back preset drying prompt information, wherein the preset drying prompt information is used to instruct to dry the water in the oven cavity; When the feedback time corresponding to the preset drying prompt information is greater than the preset time and no drying instruction is received, the drying program is automatically started to dry the oven cavity.

4. The method according to claim 3, characterized in that: When the feedback time corresponding to the preset drying prompt information is longer than the preset time and no drying instruction is received, automatically starting the drying program to dry the oven cavity includes: When the feedback time corresponding to the preset drying prompt information is greater than the preset time and no drying instruction is received, acquiring a second cavity image in the cavity of the steam oven; Inputting the second cavity image into a preset food recognition network for food recognition processing to obtain a food recognition result, wherein the preset food recognition network is a deep learning network for food recognition; When the food recognition result indicates that there is no food in the oven cavity, a drying program is automatically started to dry the oven cavity.

5. The method according to claim 4, characterized in that: When the food recognition result indicates that there is no food in the oven cavity, automatically starting a drying process to dry the oven cavity includes: When the food recognition result indicates that there is no food in the oven cavity and the door of the oven is closed, a drying program is automatically started to dry the oven cavity.

6. The method of claim 4, characterized in that The preset food recognition network is trained in the following manner: Acquire a plurality of second sample images and a preset food label corresponding to each second sample image, wherein the plurality of second sample images include a plurality of second positive sample images and a plurality of second negative sample images; the plurality of second positive sample images are images containing food; The plurality of second negative sample images are images that do not contain food; Based on the multiple second sample images and the preset food labels, food recognition training is performed on the second network to be trained to obtain the preset food recognition network.

7. The method according to any one of claims 1 to 6, characterized in that: The preset water accumulation recognition network is trained in the following way: Acquire a plurality of first sample images and a preset water accumulation label corresponding to each first sample image, wherein the plurality of first sample images include a plurality of first positive sample images and a plurality of first negative sample images; the plurality of first positive sample images are images containing water accumulation; and the plurality of first negative sample images are images not containing water accumulation; Based on the multiple first sample images and the preset water accumulation labels, water accumulation recognition training is performed on the first network to be trained to obtain the preset water accumulation recognition network.

8. The method according to any one of claims 1 to 6, characterized in that: The method further comprises: Obtaining working status indication information corresponding to the steam oven; The acquiring of a first cavity image in the oven cavity comprises: When the working state indication information indicates that the steam oven is in a non-working state, a first cavity image in the cavity of the steam oven is acquired.

9. A device for drying accumulated water in a steam oven, characterized in that: include: A first cavity image acquisition module, used to acquire a first cavity image in the cavity of the steam oven; a water accumulation recognition processing module, used for inputting the first cavity image into a preset water accumulation recognition network for water accumulation recognition processing to obtain a water accumulation recognition result; the preset water accumulation recognition network is a deep learning network for water accumulation recognition; The drying processing module is used to dry the cavity of the steam oven when the water accumulation identification result indicates that there is water accumulation in the cavity of the steam oven.

10. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the method for drying accumulated water in a steam oven as described in any one of claims 1 to 8.

Images