Steaming oven bin door control method and device, electronic equipment and storage medium

Abstract

The invention discloses a steaming oven bin door control method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a human body detection result in a preset range corresponding to a steaming oven bin door in response to an opening instruction for the steaming oven bin door, and controlling the steaming oven bin door to be opened when the human body detection result indicates that a human body appears in the preset range corresponding to the steaming oven bin door; the method comprises the steps of collecting a target image group in a preset range, performing human body action prediction analysis based on the target image group to obtain human body action trend information, performing action matching based on the human body action trend information and preset action trend information, determining an action matching result, and controlling the opening and closing state of a bin door of the steaming and baking oven based on the action matching result. According to the technical scheme, the preciseness and intelligence of controlling the opening and closing state of the bin door of the steaming oven are improved, and further, the use safety of a user is improved.

Description

Technical Field

[0001] The present invention relates to the field of control technologies, and more particularly, to a control method, device, electronic device, and storage medium for the door of a steam oven. Background Art

[0002] Steam ovens have now entered thousands of households for use. However, during the use of a steam oven, if people suddenly open the door of the steam oven, there is a risk of scalding, and the situation of people being scalded occurs from time to time. Existing steam ovens only have normal usage functions and do not have alarm and intelligent processing functions. Therefore, this application proposes a new control method for a steam oven. If a human body appears around the steam oven, the steam oven can autonomously determine whether to open or close the door, improving the intelligence of door opening and closing and reducing the usage risk for users. Summary of the Invention

[0003] In view of this, embodiments of the present invention provide a control method, device, electronic device, and storage medium for the door of a steam oven to solve technical problems such as low intelligence and low usage safety in the control of the door of a steam oven during its use.

[0004] One aspect of the present invention provides a control method for the door of a steam oven, the method including the following steps:

[0005] In response to an opening instruction for the door of the steam oven, obtain a human body detection result within a preset range corresponding to the door of the steam oven;

[0006] When the human body detection result indicates that a human body appears within the preset range corresponding to the door of the steam oven, collect a target image group within the preset range;

[0007] Based on the target image group, perform human body motion prediction analysis to obtain human body motion trend information;

[0008] Based on the human body motion trend information and preset motion trend information, perform motion matching to determine a motion matching result;

[0009] Based on the motion matching result, control the opening and closing state of the door of the steam oven.

[0010] Another aspect of the present invention provides a control device for the door of a steam oven, the device including:

[0011] A response module, configured to obtain a human body detection result within a preset range corresponding to the door of the steam oven in response to an opening instruction for the door of the steam oven;

[0012] A collection module, configured to collect a target image group within the preset range when the human body detection result indicates that a human body appears within the preset range corresponding to the steam oven door;

[0013] An analysis module, configured to perform human motion prediction analysis based on the target image group to obtain human motion trend information;

[0014] A matching module, configured to perform motion matching based on the human motion trend information and preset motion trend information to determine a motion matching result;

[0015] A control module, configured to control the opening and closing state of the steam oven door based on the motion matching result.

[0016] Another aspect of the present invention provides an electronic device, including:

[0017] A processor;

[0018] A memory for storing executable instructions of the processor;

[0019] Wherein, the processor is configured to execute the instructions to implement the steam oven door control method described in any one of the above.

[0020] Another aspect of the present invention provides a computer-readable storage medium, when the instructions in the storage medium are executed by a processor of an electronic device, enabling the electronic device to execute the steam oven door control method described in any one of the above.

[0021] A steam oven door control method, device, electronic device and storage medium provided by the present invention, in response to an opening instruction for the steam oven door, obtains a human body detection result within the preset range corresponding to the steam oven door, and when the human body detection result indicates that a human body appears within the preset range corresponding to the steam oven door, collects a target image group within the preset range, improving the rigor of collecting the target image group; and then based on the target image group, performs human motion prediction analysis to obtain human motion trend information, and based on the human motion trend information and preset motion trend information, performs motion matching to determine a motion matching result, and then based on the motion matching result, controls the opening and closing state of the steam oven door, improving the rigor and intelligence of controlling the opening and closing state of the steam oven door, and further improving the user's use safety. Description of the Drawings

[0022] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0023] Figure 1 is a schematic structural diagram of a steam oven provided according to an exemplary embodiment;

[0024] Figure 2 is a schematic flowchart of a method for controlling a steam oven door provided according to an exemplary embodiment;

[0025] Figure 3 is a schematic flowchart of a method for performing action prediction analysis based on a target image group to obtain human action trend information provided according to an exemplary embodiment;

[0026] Figure 4 is a schematic flowchart of training a target prediction model provided according to an exemplary embodiment;

[0027] Figure 5 is a schematic structural diagram of a steam oven door control device provided according to an exemplary embodiment. Detailed Embodiments

[0028] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of them. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first", "second", etc. in the specification and drawings of the present invention are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such used data can be interchanged under appropriate circumstances so that the embodiments of the present invention described here can be implemented in an order other than those illustrated or described here. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or server including a series of steps or units does not necessarily need to be limited to those clearly listed steps or units, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0030] Figure 1The following is a schematic structural diagram of a steam oven provided according to an exemplary embodiment. As Figure 1 shown, the steam oven includes components such as a chamber door and an exhaust port. Specifically, the exhaust port is used to discharge the gas generated in the steam oven. Optionally, components with laser sensing functions such as a laser sensor are provided on the chamber door of the steam oven, and the laser beam emitted by the components with laser sensing functions is used for human body sensing. Optionally, a chamber door switch button is also provided on the steam oven to enable the user to trigger the chamber door switch button to control the opening and closing of the chamber door. Optionally, control components such as a controller are provided inside the steam oven to control the opening and closing of the chamber door of the steam oven. Optionally, image acquisition devices such as a camera are also installed on the chamber door of the steam oven to collect human body videos.

[0031] Figure 2 The following is a schematic flowchart of a method for controlling a chamber door of a steam oven provided according to an exemplary embodiment. This specification provides method operation steps such as in the embodiments or flowcharts, but based on routine or non-creative labor, there may be more or fewer operation steps. The step order listed in the embodiments is only one way among the execution orders of numerous steps and does not represent the only execution order. When the actual system or server product executes, it can be executed in the order shown in the embodiments or the drawings or executed in parallel (for example, in an environment of parallel processors or multi-threaded processing). Specifically, as Figure 1 shown, taking the controller in the steam oven as the execution subject, an embodiment of a method for controlling a chamber door of the present application is introduced. The above method may include:

[0032] S201: In response to an opening instruction for the chamber door of the steam oven, obtain a human body detection result within a preset range corresponding to the chamber door of the steam oven.

[0033] In a specific embodiment, the human body detection result is used to indicate whether there is a human body within the preset range corresponding to the chamber door of the steam oven. Specifically, during the use of the steam oven, the user triggers the chamber door switch button on the steam oven to control the opening of the chamber door of the steam oven by issuing an opening instruction. Further, the chamber door switch button transmits the opening instruction to the control components of the steam oven. Correspondingly, the control components start to respond to the opening instruction, activate the components with laser sensing functions to emit laser beams, and detect whether there is a human body within the preset range corresponding to the chamber door of the steam oven to obtain the human body detection result.

[0034] S203: In the case where the human body detection result indicates that a human body appears within the preset range corresponding to the chamber door of the steam oven, collect a target image group within the preset range.

[0035] In a specific embodiment, when the human body detection result indicates that a human body appears within a preset range corresponding to the steam oven door, the image acquisition device on the door is controlled to collect the human body video within the preset range within the preset time. Further, the image acquisition device transmits the collected human body video to the control component, and the control component segments the human body video to obtain a plurality of target image frames, and then the plurality of target image frames are combined to form a target image group.

[0036] S205: Based on the target image group, perform human body motion prediction analysis to obtain human body motion trend information.

[0037] In a specific embodiment, the human body motion trend information can be used to indicate the motion trend of the human body corresponding to the target image group. Optionally, it may include any motion trend such as bending down, leaning forward, raising the hand, lowering the head, etc.; specifically, when the control component acquires the target image group, it performs human body motion prediction analysis on the target image group, and then obtains the human body motion trend information.

[0038] Figure 3 It is a schematic flowchart of a process for performing motion prediction analysis based on a target image group to obtain human body motion trend information according to an exemplary embodiment. In an alternative embodiment, as Figure 3 shown, the above-mentioned performing motion prediction analysis based on the target image group to obtain human body motion trend information includes:

[0039] S301: For each target image frame in the target image group, perform human body key point recognition to determine multiple human body key points in each target image frame;

[0040] S303: Based on the multiple human body key points in each target image frame, perform displacement calculation to determine multiple displacement change groups;

[0041] S305: Input the multiple displacement change groups into the target prediction model to obtain human body motion trend information.

[0042] In a specific embodiment, multiple human key points may be position information indicating multiple human joint points; multiple displacement change groups may be a set of displacement changes of a human body in a target image group within a preset time; specifically, for each target image frame in the target image group, human regions of interest are recognized. Correspondingly, the generated human regions of interest have human joint point information. Further, the human key points in the human regions of interest generated in each image frame are recognized. Correspondingly, multiple human key points in each target image frame are obtained, and at the same time, the position information of the multiple human key points is also obtained. Further, the multiple human key points in each target image frame are subjected to displacement calculation to obtain multiple displacement change groups. Then, the obtained multiple displacement change groups are input into a target prediction model to obtain human action trend information.

[0043] In the above embodiment, by recognizing multiple human key points in each target image frame and using them for displacement calculation to determine multiple displacement change groups, and then inputting the obtained multiple displacement change groups into a target prediction model for human action prediction to obtain human action trend information, the accuracy of human action trend prediction is improved. Further, the accuracy of matching between human action trend information and preset action trend information is improved.

[0044] In an alternative embodiment, the target image group includes multiple target image frames arranged in time sequence; the above-mentioned displacement calculation based on multiple human key points of each target image frame to determine multiple displacement change groups includes:

[0045] Based on the multiple human key points of each current target image frame and the multiple human key points of the reference target image frame corresponding to each current target image frame, displacement calculation is performed to obtain a displacement change group between each current target image frame and the reference target image frame corresponding to each current target image frame.

[0046] In a specific embodiment, each of the current target image frames includes each target image frame among a plurality of target image frames except the first target image frame; the reference target image frame can be the previous frame image of each of the current target image frames; specifically, the multiple target image frames of the target image group are arranged in sequence starting from the first target image frame. Further, at the beginning stage, the first target image frame is used as the reference target image frame, and the second target image frame is used as the current target image frame. Correspondingly, displacement calculations are performed on the multiple human key points in the first target image frame and the multiple human key points in the second target image frame to obtain the displacement change group between the first target image frame and the second target image frame. Further, the second target image frame is updated as the reference target image frame, and the third target image frame is updated as the current target image frame, and displacement calculations are performed again to obtain the displacement change group between the second target image frame and the third target image frame. Further, displacement calculations are performed on the multiple human key points of each current target image frame and the multiple human key points of the reference target image frame corresponding to each current target image frame. Correspondingly, displacement calculations corresponding to the key points are performed on the multiple human key points in each current target image frame and the multiple key points of the reference target image frame corresponding to each current target image frame to obtain the displacement change group between each current target image frame and the reference target image frame corresponding to each current target image frame.

[0047] In the above embodiment, by performing displacement calculations on the multiple human key points in each target image frame and the multiple human key points in the reference target image frame corresponding to each target image frame, the displacement change group between each current target image frame and the reference target image frame corresponding to each current target image frame is determined, which improves the diversity of the determined displacement change group, and by inputting the calculated multiple displacement change groups into the target prediction model, the accuracy of determining the human action trend information is improved.

[0048] In an alternative embodiment, the displacement change group includes multiple position differences; the above-mentioned displacement calculations based on the multiple human key points of each current target image frame and the multiple human key points of the reference target image frame corresponding to each current target image frame to obtain the displacement change group between each current target image frame and the reference target image frame corresponding to each current target image frame include:

[0049] Perform position difference calculations on the multiple human key points of each current target image frame and the multiple human key points of the reference target image frame corresponding to each current target image frame to determine the multiple position differences.

[0050] In a specific embodiment, the control component obtains multiple human key points in each target image frame, that is, the position information of each human key point is also obtained. Displacement calculation is performed based on the position information corresponding to the multiple key points in each target image frame. Specifically, the multiple human key points in each current target image frame and the multiple human key points in the reference target image frame corresponding to each current target image frame are subjected to a subtraction operation, that is, a position difference calculation, to determine multiple position differences.

[0051] Further, the displacement change group containing multiple position differences is input into the target prediction model to predict the human motion trend information.

[0052] In the above embodiment, by determining the multiple position differences in the multiple displacement change groups based on the position information of the multiple human key points in each current target image frame and the position information of the multiple human key points in the reference target image frame corresponding to each current target image frame, the accuracy of determining the human motion trend information is improved.

[0053] S207: Based on the human motion trend information and the preset motion trend information, perform motion matching to determine the motion matching result.

[0054] In a specific embodiment, the motion matching result is used to indicate whether the human motion trend information and the preset motion trend information match; the preset motion trend information can be the motion information of the human body at risk when the oven door is opened. Optionally, the preset motion trends can include motion trends such as bending down, leaning forward, raising the hand, etc.; the obtained human motion trend information and the preset motion information are subjected to motion matching to determine the motion matching result; optionally, in the case where any motion trend included in the human motion trend information matches the preset motion trend information, it is regarded as the human motion trend information and the preset motion trend information matching, that is, the motion matching result indicates that the human motion trend information and the preset motion trend information match; optionally, in the case where any motion trend included in the human motion trend information does not match the preset motion trend information, it is that the human motion trend and the preset motion trend do not match, that is, the motion matching result indicates that the human motion trend information and the preset motion trend information do not match.

[0055] S209: Based on the motion matching result, control the opening and closing state of the oven door.

[0056] In a specific embodiment, based on the determined motion matching result, control the opening and closing state of the oven door, that is, determine whether the oven door can be opened, and then control the opening and closing state of the oven door.

[0057] In an alternative embodiment, the above controlling the opening and closing state of the door based on the motion matching result includes:

[0058] When the action matching result indicates that the human body action trend information matches the preset action trend information, control the opening and closing state of the chamber door to the closed state.

[0059] In a specific embodiment, when the action matching result indicates that the human body action trend information matches the preset action trend information, the control component will control the opening and closing state of the chamber door to the closed state, that is, keep the chamber door closed, and at the same time, a warning message will be sent to the human body to warn the user to stay away from the steam oven.

[0060] In an alternative embodiment, the above control of the opening and closing state of the chamber door based on the action matching result further includes:

[0061] When the action matching result indicates that the human body action trend information does not match the preset action trend information, control the opening and closing state of the chamber door to the open state and open the chamber door to a preset angle.

[0062] In a specific embodiment, the preset angle can be the standard angle at which the chamber door opens; when the action matching result indicates that the human body action trend information does not match the preset action trend information, the control component will control the opening and closing state of the chamber door to the open state, that is, the control component controls the chamber door to open and opens the chamber door to a preset angle.

[0063] In the above embodiments, the opening and closing state of the chamber door is controlled through the action matching result of the human body action trend information and the preset action trend information, which improves the intelligence of controlling the chamber door and further ensures the use safety of the user.

[0064] Figure 4 It is a schematic flowchart of training a target prediction model provided according to an exemplary embodiment. In an alternative embodiment, as Figure 4 shown, the above target prediction model is trained in the following manner:

[0065] S401: Obtain the sample displacement change group corresponding to the sample image group and the target action trend information corresponding to the sample displacement change group;

[0066] S403: Input the sample displacement change group into the model to be trained for human body action prediction to obtain the sample action trend information;

[0067] S405: Determine the prediction loss information based on the sample action trend information and the target action trend information;

[0068] S407: Train the model to be trained based on the prediction loss information to obtain the target prediction model.

[0069] In a specific embodiment, the sample image group may be an image set containing multiple sample image frames. Optionally, the multiple sample image frames are segmented from a sample human body video; the prediction loss information may include, but is not limited to, a cross-entropy loss function, a logistic loss function, an exponential loss function, etc.; specifically, in the case of training the target prediction model, first obtain the sample image group. Further, for each sample image frame in the sample image group, perform human key point recognition to determine multiple human key points in each sample image frame. Then, based on the multiple human key points in each sample image frame, perform displacement calculation to determine the sample displacement change group corresponding to the sample image group. Further, perform manual annotation on the sample image group to determine the target action trend information corresponding to the sample image group. Further, input the sample displacement change group corresponding to the sample image group into a preset detection model to obtain the sample action trend information. Correspondingly, based on the determined target action trend information and the sample action trend information, determine the loss information to obtain the prediction loss information. Further, based on the prediction loss information, train the model to be trained to obtain the target prediction model. Specifically, update the network parameters of the model to be trained based on the prediction loss information; based on the updated model to be trained, repeat the training iteration operation from step S503 to updating the network parameters of the model to be trained based on the prediction loss information until the training convergence condition is reached; use the model to be trained obtained when the training convergence condition is reached as the target prediction model.

[0070] In the above embodiment, by inputting the sample displacement change group corresponding to the sample image group into the model to be trained to obtain the sample action trend information, and then determining the preset loss information through the sample action trend information and the target action trend information corresponding to the sample displacement change group. Further, based on the prediction loss information, perform iteration to update the model to be trained, and then determine the target prediction model and put the determined target prediction model into use, which improves the rigor and accuracy of determining the human action trend information.

[0071] A method for controlling the door of a steam oven provided by the present invention pre-obtains a sample image group, and obtains a corresponding sample displacement change group of the sample image group and target action trend information corresponding to the sample displacement change group. The sample displacement change group is input into a model to be trained for human action prediction to obtain sample action trend information. Then, based on the sample action trend information and the target action trend information, prediction loss information is determined. Further, based on the determined prediction loss information, the model to be trained is trained to obtain a target prediction model, and the target prediction model is put into use. Further, when a user issues an opening instruction, the controller of the steam oven responds to the opening instruction, controls a laser induction functional component on the door to emit a laser beam for human detection, and obtains a human detection result. Then, when the human detection result indicates that there is a human body within a preset range corresponding to the steam oven door, an image acquisition device is used to collect a target image group within the preset range. Further, based on the collected target image group, human action prediction analysis is performed to determine human action trend information. Specifically, each target image frame in the target image group is subjected to human key point recognition, and correspondingly, multiple human key points in each target image frame are obtained. Further, displacement calculation is performed based on the multiple human key points in each target image frame to determine a displacement change group. Specifically, based on the multiple human key points in each target image frame and the multiple human key points in a reference target image frame corresponding to each target image frame, position difference calculation is performed to determine the position difference of each displacement change group. Further, the multiple displacement change groups are input into the aforementioned determined target prediction model for human action prediction to obtain human action trend information. Further, the human action trend information is matched with preset action trend information to obtain an action matching result. When the action matching result indicates that the human action trend information matches the preset action trend information, the opening and closing state of the door is controlled to be the open state, and the door is opened to a preset angle. When the action matching result indicates that the human action trend information does not match the preset action trend information, the opening and closing state of the door is controlled to be the closed state, and the door is kept closed. Through the technical solution of the present application, the opening and closing of the door can be controlled automatically, improving the intelligence of door control. Further, the use safety of the user is improved.

[0072] Figure 5 FIG. is a schematic structural diagram of a steam oven door control device according to an exemplary embodiment. The following introduces an embodiment of a steam oven door control device of the present application. Specifically, as Figure 5 shown, the device includes:

[0073] A response module 501, configured to obtain a human detection result within a preset range corresponding to the steam oven door in response to an opening instruction for the steam oven door;

[0074] The acquisition module 503 is configured to acquire a target image group within the preset range when the human body detection result indicates that a human body appears within the preset range corresponding to the steam oven door;

[0075] The analysis module 505 is configured to perform human motion prediction analysis based on the target image group to obtain human motion trend information;

[0076] The matching module 507 is configured to perform motion matching based on the human motion trend information and preset motion trend information to determine a motion matching result;

[0077] The control module 509 is configured to control the opening and closing state of the steam oven door based on the motion matching result.

[0078] In an alternative embodiment, the above analysis module 505 includes:

[0079] The recognition unit is configured to perform human key point recognition on each target image frame in the target image group to determine multiple human key points in each target image frame;

[0080] The displacement calculation unit is configured to perform displacement calculation based on the multiple human key points in each target image frame to determine multiple displacement change groups;

[0081] The prediction unit is configured to input the multiple displacement change groups into a target prediction model to obtain the human motion trend information.

[0082] In an alternative embodiment, the above displacement calculation unit includes a key point calculation sub-unit for:

[0083] Performing displacement calculation based on the multiple human key points of each current target image frame and the multiple human key points of the reference target image frame corresponding to each current target image frame to obtain a displacement change group between each current target image frame and the reference target image frame corresponding to each current target image frame; each current target image frame includes each target image frame except the first target image frame among the multiple target image frames; the reference target image frame may be the previous frame image of each current target image frame.

[0084] In an alternative embodiment, the key point calculation sub-unit includes:

[0085] Performing position difference calculation on the multiple human key points of each current target image frame and the multiple human key points of the reference target image frame corresponding to each current target image frame to determine the multiple position differences.

[0086] In an alternative embodiment, the above control module 509 includes a closing unit for:

[0087] When the action matching result indicates that the human body action trend information matches the preset action trend information, control the opening and closing state of the bin door to the closed state.

[0088] In an alternative embodiment, the control module 509 further includes an opening unit for:

[0089] When the action matching result indicates that the human body action trend information does not match the preset action trend information, control the opening and closing state of the bin door to the open state and open the bin door to a preset angle.

[0090] In an exemplary embodiment, there is also provided an electronic device, including: a processor; a memory for storing executable instructions of the processor; wherein, the processor is configured to execute the instructions to implement the steam oven bin door control method as in the embodiments of the present disclosure.

[0091] In an exemplary embodiment, there is also provided a computer-readable storage medium, when the instructions in the storage medium are executed by the processor of the electronic device, enabling the electronic device to execute the steam oven bin door control method in the embodiments of the present disclosure.

[0092] In an exemplary embodiment, there is also provided a computer program product or a computer program, the computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, enabling the computer device to execute the steam oven bin door control method provided in the above various alternative implementation manners.

[0093] It can be understood that in the specific implementation manner of the present invention, user-related data is involved. When the above embodiments of the present invention are applied to specific products or technologies, user permission or consent needs to be obtained, and the collection, use, and processing of relevant data need to comply with the relevant laws, regulations, and standards of relevant countries and regions.

[0094] 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 can 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 embodiments provided by the present invention can include non-volatile and / or volatile memories. 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. 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 DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0095] After considering the specification and practicing the invention disclosed herein, those skilled in the art will readily conceive of other embodiments of the present disclosure. The present invention 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 knowledge or conventional technical means in the technical field not disclosed in the present disclosure. The specification and embodiments are only to be considered as exemplary, and the true scope and spirit of the present disclosure are pointed out by the following claims.

[0096] 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 controlling the door of a steam oven, characterized in that, The method includes: In response to an opening instruction for the steam oven door, obtaining a human detection result within a preset range corresponding to the steam oven door; When the human detection result indicates that a human appears within the preset range corresponding to the steam oven door, collecting a target image group within the preset range; Based on the target image group, performing human motion prediction analysis to obtain human motion trend information; Based on the human motion trend information and preset motion trend information, performing motion matching to determine a motion matching result; Based on the motion matching result, controlling the opening and closing state of the steam oven door.

2. The method according to claim 1, characterized in that The performing motion prediction analysis based on the target image group to obtain human motion trend information includes: For each target image frame in the target image group, performing human key point recognition to determine multiple human key points in each target image frame; Based on the multiple human key points in each target image frame, performing displacement calculation to determine multiple displacement change groups; Inputting the multiple displacement change groups into a target prediction model to obtain the human motion trend information.

3. The method according to claim 2, wherein The target image group includes multiple target image frames arranged in time sequence; The performing displacement calculation based on the multiple human key points in each target image frame to determine multiple displacement change groups includes: Based on the multiple human key points in each current target image frame and the multiple human key points in the reference target image frame corresponding to each current target image frame, performing displacement calculation to obtain a displacement change group between each current target image frame and the reference target image frame corresponding to each current target image frame; each current target image frame includes each target image frame except the first target image frame among the multiple target image frames; the reference target image frame can be the previous frame image of each current target image frame.

4. The method according to claim 3, wherein The displacement change group includes multiple position differences; the performing displacement calculation based on the multiple human key points in each current target image frame and the multiple human key points in the reference target image frame corresponding to each current target image frame to obtain a displacement change group between each current target image frame and the reference target image frame corresponding to each current target image frame includes: Performing position difference calculation on the multiple human key points in each current target image frame and the multiple human key points in the reference target image frame corresponding to each current target image frame to determine the multiple position differences.

5. The method according to claim 1, characterized in that, The controlling the opening and closing state of the door based on the motion matching result includes: When the motion matching result indicates that the human motion trend information and the preset motion trend information match, controlling the opening and closing state of the door to be a closed state.

6. The method according to claim 5, wherein The controlling the opening and closing state of the door based on the motion matching result further includes: When the motion matching result indicates that the human motion trend information and the preset motion trend information do not match, controlling the opening and closing state of the door to be an open state and opening the door to a preset angle.

7. The method according to claim 2, wherein The target prediction model is trained in the following manner: Obtain the sample displacement change group corresponding to the sample image group and the target action trend information corresponding to the sample displacement change group; Input the sample displacement change group into the model to be trained for human action prediction to obtain sample action trend information; Determine the prediction loss information based on the sample action trend information and the target action trend information; Train the model to be trained based on the prediction loss information to obtain the target prediction model.

8. A control device for the door of a steam oven, characterized in that, The device includes: A response module, configured to obtain a human detection result within a preset range corresponding to the steam oven door in response to an opening instruction for the steam oven door; An acquisition module, configured to acquire a target image group within the preset range when the human detection result indicates that a human appears within the preset range corresponding to the steam oven door; An analysis module, configured to perform human action prediction analysis based on the target image group to obtain human action trend information; A matching module, configured to perform action matching based on the human action trend information and preset action trend information to determine an action matching result; A control module, configured to control the opening and closing state of the steam oven door based on the action matching result.

9. An electronic device, characterized in that, Includes: A processor; A memory for storing executable instructions of the processor; Wherein, the processor is configured to execute the instructions to implement the steam oven door control method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, When the instructions in the storage medium are executed by the processor of the electronic device, the electronic device is enabled to execute the steam oven door control method according to any one of claims 1 to 7.

Images