Self-service cleaning method, device, system, electronic device and storage medium

Abstract

The application provides a self-service cleaning method, device, system, equipment and storage medium. In the augmented reality guidance mode, the electronic device can output first guidance information, which can guide the user to operate the electronic device, so that the electronic device determines the self-service cleaning guidance data corresponding to the device to be cleaned, and then loads the self-service cleaning guidance data into the electronic device. After the user uses the electronic device to real-time shoot the real image of the device to be cleaned, the second guidance information corresponding to the self-service cleaning guidance data can be superimposed on the real image, thereby guiding the user to disassemble and clean the device to be cleaned, so that the user can adopt the corresponding disassembly and cleaning mode for different devices to be cleaned. The application can improve the intuitiveness of the operation and the guidance of the process during self-service cleaning, better meet the needs of the user for efficient, convenient and reliable cleaning of the device to be cleaned, and improve the experience of the user in self-service cleaning of household electrical equipment such as a vertical air conditioner.

Description

Technical Field

[0001] This application relates to the field of self-cleaning technology, and in particular to a self-cleaning method, apparatus, system, electronic device and storage medium. Background Technology

[0002] As people's living standards improve, more and more household appliances are entering people's daily lives, such as household air conditioners, which are becoming increasingly widely used. However, air conditioners accumulate a lot of dust, dirt, and mold during long-term use, which not only affects the cooling and heating effect of the air conditioner, but may also affect indoor air quality and harm human health. Therefore, it is essential to clean air conditioners regularly.

[0003] Currently, there are two main ways to clean residential floor-standing air conditioners: professional cleaning services and simple self-cleaning by the user. While professional cleaning services can achieve good cleaning results to a certain extent, they have several drawbacks. Firstly, the service booking period is long, requiring users to book well in advance, which is extremely inconvenient for users who urgently need their air conditioners cleaned. Secondly, the cleaning fees are high, increasing the financial burden on users. More importantly, the cleaning process lacks transparency; users cannot effectively supervise the cleaning staff's operations or verify the cleaning quality, leaving them in a passive position when receiving the service.

[0004] The challenges faced by users attempting self-cleaning are even more pronounced. Firstly, the internal structure of floor-standing air conditioners is complex, with their outer casing typically secured by hidden clips and screws. Lacking professional structural knowledge, ordinary users are prone to improper handling during disassembly, easily causing broken plastic clips or damage to the outer casing, resulting in unnecessary financial losses. Secondly, the cleaning process lacks intuitive guidance. Users struggle to accurately locate core dirt-laden components such as the evaporator and fan, and lack sufficient understanding of correct cleaning techniques, such as brushing direction and spray angle. This leads to users either only achieving surface cleaning, failing to remove deep-seated dirt and mold, or damaging components due to improper operation.

[0005] While some cleaning tutorial videos and illustrated guides exist on the market to help users perform self-cleaning, these resources are generally general but lack specificity. They cannot provide dynamic feedback based on the user's specific air conditioner model and real-time progress, resulting in poor interactivity and failing to truly meet users' actual needs. Some high-end cleaning equipment integrates endoscope functionality, allowing users to inspect the cleanliness of the air conditioner's interior; however, these devices are expensive and require professional training to operate, making them difficult to popularize among ordinary users.

[0006] In summary, existing technical solutions have significant shortcomings in terms of operational intuitiveness and process guidance, and cannot meet users' needs for efficient, convenient, and reliable cleaning of household vertical air conditioners. Summary of the Invention

[0007] In view of this, in order to solve the technical problem that the existing technology has obvious gaps in terms of the intuitiveness of operation and the guidance of the process, and cannot meet users' needs for efficient, convenient and reliable cleaning of household vertical air conditioners, this application provides a self-cleaning method, device, system, electronic device and storage medium.

[0008] According to a first aspect of the embodiments of this application, a self-cleaning method is provided, the self-cleaning method being applied to electronic devices, the self-cleaning method comprising: In augmented reality guidance mode, first guidance information is output; wherein, the first guidance information is used to guide the user to operate the electronic device to determine the self-service cleaning guidance data corresponding to the device to be cleaned; After determining the self-service cleaning guidance data, load the self-service cleaning guidance data corresponding to the equipment to be cleaned; The second guidance information corresponding to the self-service cleaning guidance data is superimposed on the real image of the device to be cleaned captured in real time by the electronic device; wherein, the second guidance information is used to guide the user to disassemble and clean the device to be cleaned.

[0009] In an optional implementation, the first guidance information includes information for guiding the user to scan a QR code identifier on the equipment to be cleaned, and the self-service cleaning method includes: Based on the scanning result of the QR code identifier of the device to be cleaned, the self-service cleaning guidance data corresponding to the device to be cleaned is determined.

[0010] In an optional implementation, the first guidance information includes information for guiding the user to photograph salient features of the device to be cleaned, and the self-cleaning method includes: If the device to be cleaned does not have the QR code label, or if scanning the QR code label fails, the salient features captured are identified using deep learning-based visual recognition to determine the self-service cleaning guidance data corresponding to the device to be cleaned.

[0011] In an optional implementation, the step of overlaying the second guidance information corresponding to the self-service cleaning guidance data onto the real image of the equipment to be cleaned captured in real time by the electronic device includes: Based on simultaneous localization and mapping (SMR) technology and 3D registration algorithm, the second guidance information is anchored onto the real image of the equipment to be cleaned.

[0012] In one optional implementation, the second guidance information includes step-by-step, interactive disassembly animations and cleaning operation instructions. The second guidance information corresponding to the self-service cleaning guidance data is superimposed on the real image of the device to be cleaned captured in real time by the electronic device, and includes at least one of the following: The hidden connecting parts in the device to be cleaned are identified on the real image of the device to be cleaned captured in real time by the electronic device; For the disassembly steps involving electrical connections in the disassembly animation, output a safety warning message; After the outer casing of the equipment to be cleaned is disassembled, the core components of the equipment to be cleaned are identified.

[0013] In one optional implementation, the self-cleaning method includes: After cleaning the equipment to be cleaned is completed, in quality inspection mode, third guidance information is output; wherein, the third guidance information is used to guide the user to operate the electronic device to take a multispectral image of the evaporator of the equipment to be cleaned; After obtaining the multispectral image, the multispectral image is processed based on an image segmentation model to obtain a visual quality inspection report; wherein, the visual quality inspection report represents the cleaning information of the evaporator.

[0014] In an optional implementation, the image segmentation model is constructed in the following manner: Based on the U-Net architecture, an attention mechanism module and a pyramid pooling module are introduced, and the output channels are set to multiple outputs to construct the image segmentation model.

[0015] In one optional implementation, the visualized quality inspection report includes at least one of the following: Cleanliness rating, before and after cleaning comparison images, and a heat map of dirt distribution overlaid on the actual image of the evaporator.

[0016] According to a second aspect of the embodiments of this application, a self-service cleaning device is provided, the self-service cleaning device being applied to an electronic device, the self-service cleaning device comprising: The output module is used to output first guidance information in augmented reality guidance mode; wherein, the first guidance information is used to guide the user to operate the electronic device to determine the self-service cleaning guidance data corresponding to the device to be cleaned; The loading module is used to load the self-service cleaning guidance data corresponding to the equipment to be cleaned after determining the self-service cleaning guidance data. The output module is used to overlay second guidance information corresponding to the self-service cleaning guidance data onto the real image of the device to be cleaned captured in real time by the electronic device; wherein, the second guidance information is used to guide the user to disassemble and clean the device to be cleaned.

[0017] In one alternative implementation, The output module is used to output third guidance information after the cleaning of the equipment to be cleaned is completed, if it is determined to enter the quality inspection mode; wherein, the third guidance information is used to guide the user to operate the electronic device to take a multispectral image of the evaporator of the equipment to be cleaned; The output module is further configured to process the multispectral image based on an image segmentation model after obtaining the multispectral image to obtain a visualized quality inspection report; wherein the visualized quality inspection report represents the cleaning information of the evaporator.

[0018] According to a third aspect of the embodiments of this application, a self-service cleaning system is provided, the self-service cleaning system being used to implement the self-service cleaning method as described in any of the first aspects. According to a fourth aspect of the embodiments of this application, an electronic device is provided, the electronic device comprising: processor; Memory used to store the processor's executable instructions; The processor is configured to perform the self-cleaning method as described in any of the first aspects. According to a fifth aspect of the embodiments of this application, a non-transitory computer-readable storage medium is provided, wherein when instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform the self-cleaning method as described in any of the first aspects.

[0019] The technical solutions provided by the embodiments of this application can include the following beneficial effects: This application provides a self-service cleaning solution for equipment to be cleaned (such as household appliances like floor-standing air conditioners). In augmented reality (AR) guidance mode, the electronic device can output first guidance information, which guides the user to operate the electronic device, thereby enabling the electronic device to determine the self-service cleaning guidance data corresponding to the equipment to be cleaned. This self-service cleaning guidance data is then loaded into the electronic device. After the user uses the electronic device to capture a real image of the equipment to be cleaned in real time, second guidance information corresponding to the self-service cleaning guidance data can be superimposed on the real image. That is, the second guidance information corresponding to the self-service cleaning guidance data of the equipment to be cleaned is superimposed on the real image of the equipment to be cleaned, thereby guiding the user to disassemble and clean the equipment, so that the user can adopt corresponding disassembly and cleaning methods for different equipment. This application proposes a "visual perception-driven AR real-time guidance" mechanism. This mechanism transforms the traditional static guidance mode that relies on paper manuals or general videos into an interactive three-dimensional instruction manual dynamically generated based on the specific environment. By converting professional knowledge and operating procedures into intuitive virtual information superimposed on the real image of the equipment to be cleaned, the electronic device achieves the visualization and universal transmission of professional cleaning skills. This application significantly reduces the professional threshold and operational risks associated with cleaning equipment. Ordinary users, without prior knowledge of complex structures, can safely and correctly complete disassembly and cleaning under intuitive step-by-step guidance, effectively avoiding damage to components due to improper operation. This expands high-quality deep cleaning services from relying on professionals to being easily performed by ordinary users. In other words, this application enhances the intuitiveness and guidance of self-cleaning operations, better meeting users' needs for efficient, convenient, and reliable cleaning of equipment, and improving the user experience of self-cleaning household appliances such as standing air conditioners.

[0020] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0021] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] One or more embodiments are illustrated by way of example with reference numerals in the accompanying drawings. These illustrations do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are denoted as similar elements. Unless otherwise stated, the figures in the drawings are not to be limited by scale.

[0024] Figure 1 This is a flowchart illustrating a self-cleaning method according to an exemplary embodiment.

[0025] Figure 2 This is a flowchart illustrating a self-cleaning method according to another exemplary embodiment.

[0026] Figure 3 This is a schematic diagram illustrating a dirt distribution pattern according to an exemplary embodiment.

[0027] Figure 4 This is a block diagram illustrating a self-cleaning device according to an exemplary embodiment.

[0028] Figure 5 This is a block diagram of an electronic device according to an exemplary embodiment. Detailed Implementation

[0029] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0030] The following disclosure provides numerous different embodiments or examples for implementing various aspects of the invention. To simplify the disclosure, specific examples of components and arrangements are described below. These are merely examples and are not intended to limit the scope of the invention. Furthermore, reference numerals and / or letters may be repeated in different examples. Such repetition is for simplification and clarity and does not in itself indicate a relationship between the various embodiments and / or arrangements discussed.

[0031] For ease of description, spatial relative terms may be used in the text to describe the relative position or movement of one element or feature relative to another element or feature, as shown in the figure. These relative terms include, for example, "inside," "outside," "middle," "outer," "below," "below," "above," "front," "back," etc. Such spatial relative terms are intended to include different orientations of the device in use or operation, other than those depicted in the figure. For example, if the device in the figure undergoes a positional flip, orientation change, or change of motion, these directional indications will change accordingly. For instance, an element described as "below other elements or features" or "below other elements or features" will subsequently be oriented "above other elements or features" or "above other elements or features." Therefore, the example term "below" can include both upper and lower orientations. The device may be otherwise oriented (rotated 90 degrees or in other directions), and the spatial relative descriptors used in the text will be interpreted accordingly.

[0032] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of this application. Therefore, the drawings only show the components related to this application and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0033] The embodiments of this application will be described below with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be understood that the preferred embodiments are only for illustrating this application and are not intended to limit the scope of protection of this application.

[0034] To address the significant gaps in the intuitiveness and guidance of existing technologies, which fail to meet users' needs for efficient, convenient, and reliable cleaning of household vertical air conditioners, this application provides a self-cleaning method, apparatus, system, electronic device, and storage medium.

[0035] This application provides a self-service cleaning solution for equipment to be cleaned (such as household appliances like floor-standing air conditioners). In augmented reality (AR) guidance mode, the electronic device outputs first guidance information to guide the user in operating the device. This allows the electronic device to determine the corresponding self-service cleaning guidance data for the equipment to be cleaned. The self-service cleaning guidance data is then loaded into the electronic device. After the user uses the electronic device to capture a real image of the equipment to be cleaned in real time, second guidance information corresponding to the self-service cleaning guidance data is superimposed onto the real image. That is, the second guidance information corresponding to the self-service cleaning guidance data for the equipment to be cleaned is superimposed onto the real image, guiding the user in disassembling and cleaning the equipment. This allows the user to adopt appropriate disassembly and cleaning methods for different equipment. This application proposes a "visual perception-driven AR real-time guidance" mechanism. This mechanism transforms the traditional static guidance mode, which relies on paper manuals or general videos, into an interactive, three-dimensional instruction manual dynamically generated based on the specific environment. By converting professional knowledge and operating procedures into intuitive virtual information superimposed on the real image of the equipment to be cleaned, the electronic device achieves the visualization and universal transmission of professional cleaning skills. This application significantly reduces the professional threshold and operational risks associated with cleaning equipment. Ordinary users do not need prior knowledge of complex structures; they can safely and correctly complete disassembly and cleaning with intuitive step-by-step guidance, effectively avoiding damage to components due to improper operation. This expands high-quality deep cleaning services from relying on professionals to being easily completed by ordinary users. In other words, this application enhances the intuitiveness and guidance of self-cleaning operations, better meeting users' needs for efficient, convenient, and reliable cleaning of their equipment, and improving the user experience of self-cleaning household appliances such as standing air conditioners.

[0036] In one exemplary embodiment, reference Figure 1 As shown, a self-cleaning method is provided, which can be applied to electronic devices. This self-cleaning method may include: S110. In augmented reality guidance mode, output first guidance information; wherein, the first guidance information is used to guide the user to operate the electronic device to determine the self-service cleaning guidance data corresponding to the device to be cleaned; S120. After determining the self-service cleaning guidance data, load the self-service cleaning guidance data corresponding to the equipment to be cleaned. S130. Superimpose second guidance information corresponding to the self-service cleaning guidance data onto the real image of the equipment to be cleaned captured in real time by the electronic device; wherein, the second guidance information is used to guide the user to disassemble and clean the equipment to be cleaned.

[0037] In step S110, the first guidance information may include voice information, image information, text information, etc., and there is no limitation thereto.

[0038] The first guidance information may include information for guiding users to scan the QR code of the equipment to be cleaned. After the user understands the first guidance information output by the electronic device, the user can operate the electronic device to scan the QR code of the equipment to be cleaned. The electronic device can then determine the self-service cleaning guidance data corresponding to the equipment to be cleaned by recognizing the QR code, which can both ensure recognition efficiency and improve accuracy.

[0039] It should be noted that the aforementioned QR code can be a unique identifier for the device to be cleaned, representing its model. Once the electronic device obtains the model number of the device, it can determine the corresponding self-service cleaning guidance data. Alternatively, the QR code can be a dedicated QR code within the device itself, used to determine the self-service cleaning guidance data. By recognizing this QR code, the electronic device can directly identify the corresponding self-service cleaning guidance data for that device.

[0040] Some electrical appliances may not have QR code labels; or, although the appliances have QR code labels, the labels may be damaged, causing recognition failure; or, the electronic devices may be unable to accurately recognize the QR code labels for other reasons, resulting in recognition failure. Therefore, the first guidance information in this embodiment may also include information to guide the user to photograph the salient features of the equipment to be cleaned. For example, when the equipment to be cleaned is an air conditioner, salient features may include the air conditioner's air vent grille, brand logo, etc.

[0041] In this embodiment, if the device to be cleaned does not have the QR code label, or if scanning the QR code label fails, the salient features captured can be identified based on deep learning visual recognition to determine the self-service cleaning guidance data corresponding to the device to be cleaned, thereby improving the applicability.

[0042] Take using a mobile phone to perform self-cleaning of an air conditioner as an example. The entire process begins with the user launching the corresponding application on their phone and selecting "AR guidance" mode. At this point, the phone enters augmented reality guidance mode and outputs initial guidance information to intelligently guide the user to point the phone's camera at the air conditioner to be cleaned. To ensure the accuracy of the guidance, the phone guides the user to first scan the unique QR code on the air conditioner to retrieve detailed 3D models and self-cleaning guidance data, such as operating procedures, from the cloud. If there is no QR code or the scan fails, the phone automatically activates a backup solution based on deep learning-based visual recognition. That is, the phone can activate its built-in computer recognition model to capture prominent features such as the air vent grille and brand logo of the air conditioner and match them with the cloud model library in real time to accurately determine the air conditioner model and load the corresponding self-cleaning guidance data.

[0043] In step S120, after the electronic device determines the self-service cleaning guidance data corresponding to the device to be cleaned, the self-service cleaning guidance data can be loaded into the electronic device. That is, the self-service cleaning guidance data can be obtained and downloaded from the cloud so that the self-service cleaning guidance data can be stored in the electronic device.

[0044] In step S130, after the user completes the identification of the device to be cleaned under the guidance of the first guidance information, the user can then use an electronic device to capture a real image of the device to be cleaned in real time, and overlay the second guidance information onto the real image. It should be noted that the second guidance information is generated based on the self-service cleaning guidance data, that is, the second guidance information corresponds to the self-service cleaning guidance data, and is used to guide the user in disassembling and cleaning the device to be cleaned.

[0045] In other words, in this step, the electronic device can act as an "augmented reality lens". Based on Simultaneous Localization and Mapping (SLAM) technology and a precise 3D registration algorithm, the virtual information (i.e. the second guidance information) is stably and accurately anchored on the real real image of the equipment to be cleaned. That is, the second guidance information is stably and accurately superimposed on the real image of the equipment to be cleaned, so as to guide the user to disassemble and clean the equipment.

[0046] In some implementations... The electronic device can be a mobile device, and the device to be cleaned can be an air conditioner. When overlaying virtual information onto a real image, the built-in SLAM capabilities of ARKit (for iOS mobile devices) or ARCore (for Android mobile devices) can be used on the mobile device. These frameworks have integrated functions such as visual inertial odometry (VIO), plane detection, and illumination estimation, which can stably track the device's position and attitude without requiring development from scratch. Open-source libraries such as ORB-SLAM2 and OpenCV + PnP (Perspective-n-Point) can be used to extract key points on the air conditioner's surface (such as logos, grilles, screw holes, etc.), establish 2D-3D correspondences, and calculate camera attitude. The YOLO deep learning model is used to detect the air conditioner type in real time, and the corresponding pre-loaded 3D model (.obj / .gltf format) is called. The PnP (Perspective-n-Point) algorithm is used to align it with the real-time image, thus ensuring that the second guiding information is stably and accurately anchored onto the real-time image of the device to be cleaned.

[0047] The second guidance information may include step-by-step, interactive disassembly animations and cleaning operation instructions. The second guidance information, corresponding to the self-service cleaning guidance data, is overlaid onto a real image of the equipment to be cleaned captured in real time by the electronic device. This information may include at least one of the following: The hidden connecting parts in the equipment to be cleaned are identified on the real image of the equipment to be cleaned captured in real time by the electronic device; For the disassembly steps involving electrical connections in the disassembly animation, output a safety warning message; After disassembling the outer casing of the equipment to be cleaned, identify the core components inside the equipment that need to be cleaned.

[0048] It should be noted that concealed connecting components may include, for example, clips and screws for connecting the two parts. Electrical connection locations may include, for example, power supplies or cables for making electrical connections. Safety warning information may include text, voice, or images, etc., and is not limited thereto. When the equipment to be cleaned is an air conditioner, its core components may include, for example, an evaporator and a fan.

[0049] In some implementations... The device to be cleaned can be an air conditioner, and the electronic device can be a mobile phone. After the mobile phone successfully identifies the air conditioner, the user's mobile phone screen transforms into an "augmented reality perspective." Using simultaneous localization and mapping (SLAM) technology and precise 3D registration algorithms, hidden connecting parts within the device to be cleaned are identified on a real-time image captured by the electronic device. For example, hidden clips and screws that are difficult to detect in reality can be clearly marked with bright, illuminated circles and arrows, accompanied by concise text prompts.

[0050] In some implementations... The device to be cleaned can be an air conditioner, and the electronic device can be a mobile phone. After the mobile phone successfully identifies the air conditioner, the user's mobile phone screen transforms into an "augmented reality perspective." Utilizing simultaneous localization and mapping (SLAM) technology and precise 3D registration algorithms, safety warnings are output for disassembly steps involving electrical connections in the disassembly animation. For example, for critical steps involving power or cable connections, the system proactively displays a prominent safety warning icon accompanied by voice prompts, greatly enhancing operational safety.

[0051] In some implementations... The device to be cleaned can be an air conditioner, or an electronic device can be a mobile phone. After the mobile phone successfully identifies the air conditioner, the user's phone screen transforms into an "augmented reality perspective." Utilizing simultaneous localization and mapping (SLAM) technology and precise 3D registration algorithms, the core components to be cleaned are identified after the outer casing of the device is disassembled. For example, once the air conditioner's casing is successfully disassembled, the built-in computer vision model can identify core components such as the evaporator and fan impeller, outlining and labeling them with semi-transparent contour lines of different colors. This visually presents the cleaning focus to the user, ensuring thorough and complete deep cleaning.

[0052] In some implementations... The device to be cleaned can be an air conditioner, and electronic devices can be mobile phones. After the phone successfully identifies the air conditioner, the user's phone screen transforms into an "augmented reality lens." Utilizing simultaneous localization and mapping (SLAM) technology and precise 3D registration algorithms, secondary guidance information is stably and accurately anchored onto the real image of the air conditioner as virtual information. For example, hidden clips and screws that are difficult to detect in reality are clearly marked with bright, illuminated circles and arrows, accompanied by concise text prompts. Users simply follow the on-screen instructions and click "Next" to view step-by-step 3D animation demonstrations; for instance, a virtual hand model visually demonstrates how to apply force correctly to safely pry open the panel. For critical steps involving power or cable connections, the system proactively displays prominent safety warning icons along with voice prompts, greatly enhancing operational safety. Once the air conditioner's casing is successfully disassembled, the built-in computer vision model identifies core components such as the evaporator and fan, outlining and marking them with semi-transparent contour lines of different colors, thus visually presenting the cleaning focus to the user and ensuring thorough deep cleaning.

[0053] It should be noted that, in the above embodiments, all information displayed on the mobile phone's screen other than the actual image of the air conditioner belongs to the second guidance information. In addition to the information mentioned above, the second guidance information can also be set to include other relevant information for guiding disassembly and cleaning, as needed; there is no limitation on this.

[0054] In this embodiment, an electronic device (such as a mobile phone) captures a real-time image stream of the device to be cleaned (e.g., an air conditioner) using its camera. A deep learning-based computer vision model is then used to dynamically identify and lock hidden clips, screws, and internal core components (such as the evaporator and fan wheel) on the air conditioner's casing. The electronic device performs AR registration and fusion with a pre-set 3D model of the air conditioner model, overlaying a step-by-step, interactive disassembly animation and cleaning operation instructions (i.e., second guidance information) onto the real-time video feed. This embodiment's "visual perception-driven AR real-time guidance" transforms the traditional static guidance mode, which relies on paper manuals or generic videos, into an interactive, three-dimensional instruction manual dynamically generated based on the specific environment. By transforming professional knowledge and operating procedures into intuitive virtual information overlaid on the real image of the device to be cleaned, the electronic device achieves the visualization and universal transmission of professional cleaning skills. This application significantly reduces the professional threshold and operational risks associated with cleaning the device. Ordinary users do not need to learn complex structural knowledge beforehand; they can safely and correctly complete disassembly and cleaning under intuitive step-by-step guidance, effectively avoiding component damage caused by improper operation. This expands high-quality deep cleaning services from relying on professionals to being easily completed by ordinary users. In other words, this embodiment can improve the intuitiveness of operation and the guidance of the process when cleaning self-service equipment, better meet the user's needs for efficient, convenient and reliable cleaning of the equipment to be cleaned, and improve the user's experience of cleaning household appliances such as standing air conditioners by themselves.

[0055] In one exemplary embodiment, reference is made to the figure. Figure 2 As shown, a self-cleaning method is provided, which can be applied to electronic devices. This self-cleaning method may include: S210. In augmented reality guidance mode, output first guidance information; wherein, the first guidance information is used to guide the user to operate the electronic device to determine the self-service cleaning guidance data corresponding to the device to be cleaned; S220. After determining the self-service cleaning guidance data, load the self-service cleaning guidance data corresponding to the equipment to be cleaned. S230. Superimpose second guidance information corresponding to the self-service cleaning guidance data onto the real image of the equipment to be cleaned captured in real time by the electronic device; wherein, the second guidance information is used to guide the user in disassembling and cleaning the equipment to be cleaned. S240. After cleaning the equipment to be cleaned is completed, if it is determined to enter the quality inspection mode, the third guidance information is output; wherein, the third guidance information is used to guide the user to operate the electronic device to take a multispectral image of the evaporator of the equipment to be cleaned. S250. After obtaining the multispectral image, the multispectral image is processed based on the image segmentation model to obtain a visualized quality inspection report; wherein, the visualized quality inspection report represents the cleaning information of the evaporator.

[0056] Steps S210 to S230 can refer to steps S110 to S130 in other embodiments, and will not be described in detail here.

[0057] In step S240, the electronic device is also configured with a quality inspection mode, which can be used to inspect the dirt status of the equipment to be cleaned, that is, it can be used to inspect the cleaning effect of the equipment to be cleaned after cleaning.

[0058] The quality inspection mode can be entered automatically after cleaning is completed, or it can be entered after the user selects it; there is no limitation on which mode is entered.

[0059] For example, after the user completes the cleaning of the equipment under the guidance of the second guidance message, the electronic device may display a prompt indicating whether to enter the quality inspection mode. The user can then choose whether to enter the quality inspection mode. If the user chooses to enter the quality inspection mode, the electronic device will enter the quality inspection mode and output the third guidance message to guide the user in operating the electronic device for quality inspection.

[0060] For example, after the user completes the cleaning of the equipment under the guidance of the second guidance information, the electronic device can directly and seamlessly enter the quality inspection mode and output the third guidance information to guide the user to operate the electronic device for quality inspection.

[0061] The third guidance information can be used to guide the user in operating the electronic device to capture multispectral images of the evaporator of the equipment to be cleaned. For example, the third guidance information may include the optimal shooting distance and angle of the electronic device's camera. For instance, in quality inspection mode, the electronic device can output clear graphic and voice guidance to ensure that the user can operate the camera to automatically capture a series of high-definition multispectral images of the evaporator after cleaning at the optimal shooting distance and angle.

[0062] It's important to note that the evaporator is the core of air conditioner contamination. Its densely packed fins are prone to mold and bacteria growth, and the narrow gaps between the fins make cleaning extremely difficult. Its cleanliness directly determines the hygiene of the exhaust air and heat exchange efficiency. Users only need to focus on the evaporator for image capture, making the operation simpler and requiring less processing power from the phone, thus adapting to more mid-to-low-end devices. The core of this embodiment is to address the issues of "complex operation and subjective effect evaluation." By focusing solely on evaporator quality control, it not only echoes the AR-guided highlighting of the evaporator but also provides users with crucial evidence of "effective cleaning." Furthermore, cleaning the evaporator requires first removing the filter; large dust particles are visually identifiable and will be cleaned naturally by the user. Spraying the evaporator simultaneously washes the impeller and drain pan, removing most of the floating dust. If the evaporator meets the standards, it indirectly indicates that the cleanliness of other components meets basic requirements. Based on this, this embodiment selects to collect multispectral images of the evaporator.

[0063] In step S250, after the electronic device acquires the multispectral image, it can process the multispectral image based on the image segmentation model to obtain a visualized quality inspection report.

[0064] It should be noted that the image segmentation mode can be built into electronic devices or deployed on cloud servers, and there is no limitation on this.

[0065] When an electronic device has a built-in image segmentation model, it can process the multispectral image after obtaining it, thereby generating a visual quality inspection report.

[0066] When the image segmentation model is deployed on a cloud server, after the electronic device obtains a multispectral image, it can transmit the image to the cloud server. The image segmentation model on the cloud server processes the multispectral image, and after the cloud server determines the visual quality inspection report, it transmits the report to the electronic device, thus enabling the electronic device to obtain the visual quality inspection report.

[0067] The image segmentation model can be based on the U-Net architecture, which can distinguish metal fins, water stains, dust, and mold like the human eye, and accurately calculate objective quantitative indicators such as "clean area ratio" and "specific stain residue rate". The model can also incorporate an attention mechanism module and a pyramid pooling module (to enable multi-scale input), and set the output channels to multiple outputs to construct the original image segmentation model. This model is then trained to obtain the final desired image segmentation model.

[0068] The following is an introduction to image segmentation models: I. Model Architecture Based on the U-Net architecture, which performs excellently in medical image segmentation and is suitable for small-sample, high-precision segmentation tasks, the following improvements were made to address the image characteristics of air conditioner evaporators (metallic reflection, complex texture, and diverse stain morphologies): Introduce attention mechanism modules (such as SE-Block or CBAM) to enhance attention to stained areas; Multi-scale input (pyramid pooling module) is used to improve the ability to identify stains of different sizes; The output channels are divided into four categories: background, dust, water stains, and mold.

[0069] II. Main Modules and Hierarchy of the Model 1. Encoder (downsampling path) Input layer: RGB image (224×224); Convolutional blocks: Each block contains: 2×convolutional layer (3×3 convolution, ReLU activation); Batch normalization (BatchNorm); Max pooling (2×2, step size 2); Layer depth: 4 levels, with the number of channels doubling at each level (64→128→256→512). 2. Attention module (inserted between the encoder and decoder) SE-Block: Weights each channel to enhance important features.

[0070] Position: Added before the skip connection.

[0071] 3. Decoder (upsampling path) Upsampling blocks, each block containing: Transposed convolution (2×2, stride 2); Perform skip connections (concat) between the feature maps of the corresponding layers of the encoder; 2×convolutional layers (3×3, ReLU + BatchNorm); Output layer: 1×1 convolution + Softmax activation, outputting a 4-channel probability map; 4. Skip Connections By directly connecting the encoder's feature map to the corresponding layer of the decoder, detailed information is preserved and edge segmentation accuracy is improved.

[0072] III. Data Preparation 1. Training set construction: We have collected a large number of images of air conditioner evaporators, covering different brands, models, and types of stains.

[0073] The items are manually labeled into four categories: background, dust, water stains, and mold.

[0074] Data augmentation: rotation, scaling, brightness adjustment, noise addition, and simulated metallic reflection.

[0075] It should be noted that in real-world shooting scenarios, cameras may have issues such as pixel noise (especially in low-light environments), image compression distortion, and slight blurring due to camera shake. These all contribute to "noise interference." Adding noise in data augmentation is equivalent to allowing the model to "adapt" to the imperfections of real images in advance. This trains the model to ignore irrelevant interference and focus on core stain features (such as the texture of mold spots or the grayscale differences in dust), preventing noise from being misidentified as stains or stains from being masked by noise.

[0076] 2. Dataset partitioning: Training set : validation set : test set = 70% : 15% : 15% IV. Loss Function Using the combination of Dice Loss and Focal Loss: Dice Loss: Addressing category imbalance (clean areas are much larger than stained areas). Focal Loss: Increase attention to difficult-to-classify samples (such as small mold spots).

[0077] V. Optimizer and Hyperparameters Optimizer: AdamW (weight decay to prevent overfitting); Learning rate: Initially 1e-4, using cosine annealing strategy. Batch size: 8 or 16 (adjustable based on video memory); Training cycles: 100~150 epochs; Early stopping mechanism: If the validation set loss does not decrease for 5 consecutive rounds, the process will stop.

[0078] VI. Evaluation Indicators mIoU (mean crossover ratio), category-level accuracy, Dice coefficient, and stain detection recall.

[0079] VII. Model Output and Quality Inspection Report Generation Process 1. Model output: 4-channel probability map (probability of each pixel belonging to each category); 2. Post-processing: Use connected component analysis to remove small-area noise.

[0080] Calculate the pixel area percentage for each type of stain.

[0081] 3. Indicator Calculation: Clean area percentage = number of background pixels / total number of pixels; Specific stain residue rate = Number of pixels of a specific stain type / Total number of pixels; 4. Report generation: Generate a heat map (i.e., a dirt distribution map, where red / yellow / green correspond to the degree of dirt, for reference). Figure 3 ); The evidence is uploaded by combining the timestamp, device ID, and image hash value.

[0082] It should be noted that, in addition to the methods described above, other methods can also be used to construct image segmentation models, and there are no restrictions on which method is used.

[0083] In addition, this step includes a visual quality inspection report comprising at least one of the following: a cleanliness score, a before-and-after cleaning comparison image, and a heat map of dirt distribution overlaid on a photograph of the evaporator. The cleanliness score allows users to intuitively understand the current cleanliness level of the evaporator. The before-and-after cleaning comparison image allows users to intuitively understand the effectiveness of the cleaning. The dirt distribution heat map allows users to intuitively understand the current dirt distribution on the evaporator.

[0084] In the dirt distribution map, heavily soiled areas are marked in red, lightly soiled areas in yellow, and clean areas in green, making the cleaning effect immediately clear. The visualized quality inspection report can also include specific improvement suggestions and supports local saving and encrypted sharing. All key data in the visualized quality inspection report, such as image hash values ​​and timestamps, can be uploaded to the blockchain for evidence storage, ensuring its immutability and providing authoritative evidence for resolving potential service disputes.

[0085] The following is a sample intelligent quality inspection report for air conditioner cleanliness: Detection time: Year X Month X Day X:X:X (e.g., December 13, 2025, 14:30:25); Air conditioner model: Brand X, Model X, floor-standing air conditioner; Device serial number: X; User ID: X; Inspection location: Main air conditioner in the living room - evaporator assembly; I. Overall Cleanliness Score: Overall cleanliness score: 86.5 / 100; Rating: Good; Scoring Components: Surface cleanliness: 92 / 100; Deep stain removal rate: 81 / 100; Mold treatment effectiveness: 85 / 100; Component integrity: 100 / 100 (no damage); II. Quantitative Analysis Indicators:

[0086] III. Visual Analysis Chart: For a detailed dirt distribution diagram, please see... Figure 3 ; Heatmap Interpretation: Red area: mainly concentrated in the dense finned area in the lower right corner of the evaporator; Yellow area: distributed at the edge and on the air inlet side; Green area: The central and upper left areas are thoroughly cleaned; IV. Stain Classification Details: 1. Dust distribution analysis: Main types: fine particulate dust (PM2.5), fibrous flocculent matter; Concentration areas: the windward side of the fins and the edge of the drainage channel; Thickness assessment: average 0.2mm, maximum 0.5mm (bottom right corner); 2. Analysis of residual water stains: Speculated composition: Hard water scale (calcium and magnesium deposits); Location: Bottom of fins, condensate pipe interface; Recommendation: A mild acidic cleaner can be used for further treatment; 3. Analysis of residual mold: Severity: Mild mold colony; Location: Shady areas on the leeward side of the fins (3 locations); Microbial risk: Suspected Aspergillus niger characteristics detected (retest recommended); V. Cleanliness Quality Level Determination:

[0087] Detailed rating of this machine: Surface cleaning: B+; Deep cleaning: B-; Antibacterial treatment: B; Overall rating: Grade B (Good); VI. Specific Improvement Suggestions 1. Re-washing of key areas and special treatment for mold: For red-contaminated areas, use a soft-bristled brush and a specialized air conditioner cleaner for localized treatment; Spray the mold-removing agent on the moldy area, let it sit for 15 minutes, and then rinse with clean water.

[0088] 2. Maintenance Recommendations: Next cleaning time: It is recommended to clean again before [month / year] (e.g., June 2026); Routine maintenance: Clean the filter once a month; Use air conditioner disinfectant spray once per quarter; Environmental improvement: Maintain indoor humidity at 50%-60%; Increase the drying time of the air supply before and after using the air conditioner.

[0089] It should be noted that visual quality inspection reports can take other forms besides those mentioned above, and there are no restrictions on the specific forms.

[0090] In this embodiment, after the equipment to be cleaned is completed, high-definition images of the core components (focusing on the evaporator) are acquired using the same electronic device. A dedicated image analysis algorithm (combining image segmentation and feature comparison technology) is used to quantitatively compare the acquired image with "standard cleaning" samples in the system database, automatically calculating key indicators such as "cleaning area percentage" and "specific stain (such as mold) residue rate," and generating a comprehensive, visual quality inspection report with an objective "cleanliness score." This embodiment creates a "computer vision-based quantitative assessment model for air conditioning cleaning" (i.e., an image segmentation model), inventing a new paradigm for service quality verification "from subjective judgment to objective measurement." This model transforms the traditional vague evaluation based on "feeling and visual inspection" into a data-driven, traceable, and reproducible precise assessment, providing an indisputable standardized measurement scale for service quality. In other words, this embodiment establishes a transparent and credible cleaning service quality inspection standard. Both users and service providers can confirm the cleaning effect based on the same data report, fundamentally solving the trust crisis and service disputes caused by inconsistent standards. At the same time, the report can be stored as an electronic archive, making it easy to track the health status and historical service records of the air conditioner.

[0091] This embodiment achieves system self-evolution by constructing a complete data closed loop from intelligent recognition and dynamic AR guidance to quantitative quality inspection. When the visualized quality inspection report indicates that rework and re-cleaning are required, the user can restart the self-service cleaning process to ensure the final cleaning effect.

[0092] In addition, in this embodiment, with user authorization, the collected desensitized cleaning data can be continuously used to train and optimize the computer vision model and image segmentation model in this embodiment, enabling them to identify more models of devices to be cleaned and more complex stain types, thereby making the entire self-service cleaning increasingly intelligent, and ultimately transforming the traditional, experience-dependent cleaning labor into a standardized, visualized, and reliable modern home service.

[0093] In one exemplary embodiment, reference Figure 1 and Figure 2 As shown, a self-service cleaning system is provided, which can be used to implement the self-service cleaning method described above.

[0094] This embodiment provides an application integrated into an electronic device (such as a smartphone) as its core, making full use of its powerful computing capabilities, high-definition camera, touch screen and network connectivity to provide users with a complete and smooth air conditioner cleaning experience from preparation, operation to acceptance, which can greatly improve the self-cleaning experience.

[0095] In one exemplary embodiment, reference Figure 4As shown, a self-cleaning device is provided, which can be applied to electronic devices. This device is used to implement the self-cleaning method described above. For example, the device may include: Output module 10 is used to output first guidance information in augmented reality guidance mode; wherein, the first guidance information is used to guide the user to operate the electronic device to determine the self-service cleaning guidance data corresponding to the device to be cleaned; The loading module 20 is used to load the self-service cleaning guidance data corresponding to the equipment to be cleaned after determining the self-service cleaning guidance data; The output module 10 is used to overlay the second guidance information corresponding to the self-service cleaning guidance data onto the real image of the device to be cleaned captured in real time by the electronic device; wherein the second guidance information is used to guide the user to disassemble and clean the device to be cleaned.

[0096] In one exemplary embodiment, reference Figure 4 As shown, a self-service cleaning device is provided, which can be applied to electronic devices. In this device, first guidance information includes information for guiding the user to scan a QR code identifier on the device to be cleaned. The device may include: The determining module 30 is used to determine the self-service cleaning guidance data corresponding to the device to be cleaned based on the scanning result of the QR code identifier of the device to be cleaned.

[0097] In one exemplary embodiment, reference Figure 4 As shown, a self-service cleaning device is provided, which can be applied to electronic devices. In this device, first guidance information includes information for guiding the user to photograph salient features of the device to be cleaned. The device may include: The determination module 30 is used to identify the salient features captured based on deep learning visual recognition when the device to be cleaned does not have the QR code identifier, or when scanning the QR code identifier fails, so as to determine the self-service cleaning guidance data corresponding to the device to be cleaned.

[0098] In one exemplary embodiment, reference Figure 4 As shown, a self-service cleaning device is provided, which can be applied to electronic devices. In this device, the output module 10 can be used for: Based on simultaneous localization and mapping (SMR) technology and 3D registration algorithm, the second guidance information is anchored onto the real image of the equipment to be cleaned.

[0099] In one exemplary embodiment, reference Figure 4 As shown, a self-cleaning device is provided, applicable to electronic devices. In this device, the second guidance information includes step-by-step, interactive disassembly animations and cleaning operation instructions, and the output module 10 can be used to perform at least one of the following methods: The hidden connecting parts in the device to be cleaned are identified on the real image of the device to be cleaned captured in real time by the electronic device; For the disassembly steps involving electrical connections in the disassembly animation, output a safety warning message; After the outer casing of the equipment to be cleaned is disassembled, the core components of the equipment to be cleaned are identified.

[0100] In one exemplary embodiment, reference Figure 4 As shown, a self-service cleaning device is provided, which can be applied to electronic devices. In this device, the output module 10 can be used for: After cleaning the equipment to be cleaned is completed, in quality inspection mode, third guidance information is output; wherein, the third guidance information is used to guide the user to operate the electronic device to take a multispectral image of the evaporator of the equipment to be cleaned; After obtaining the multispectral image, the multispectral image is processed based on an image segmentation model to obtain a visual quality inspection report; wherein, the visual quality inspection report represents the cleaning information of the evaporator.

[0101] In one exemplary embodiment, an electronic device is provided. The electronic device may be a mobile terminal (e.g., a mobile phone, smartwatch, etc.), or a tablet computer, laptop computer, etc., and is not limited thereto.

[0102] Among them, reference Figure 5 As shown, electronic device 100 includes at least one processor 101, memory 102, at least one network interface 104, and user interface 103. The various components in electronic device 100 are coupled together via bus system 105. It is understood that bus system 105 is used to implement communication between these components. In addition to a data bus, bus system 105 also includes a power bus, a control bus, and a status signal bus. However, for clarity, all buses are labeled as bus system 105 in the figure.

[0103] The user interface 103 may include a display, keyboard, or clickable electronic device (e.g., mouse, trackball), touchpad, sensor, or touchscreen. For example, in a myoelectric bracelet, the sensor or other detection unit used to detect the user's finger information can serve as the user interface 103.

[0104] It is understood that the memory 102 in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous DRAM (SDRAM), Double Data Rate Synchronous DRAM (DDRSDRAM), Enhanced Synchronous DRAM (ESDRAM), Synchlink DRAM (SLDRAM), and Direct Rambus RAM (DRRAM). The memory 102 described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0105] In some implementations, memory 102 stores elements, executable units or data structures, or subsets thereof, or extended sets thereof: operating system 1021 and application program 1022.

[0106] The operating system 1021 includes various system programs, such as the framework layer, core library layer, and driver layer, used to implement various basic business functions and handle hardware-based tasks. The application program 1022 includes various applications, such as a media player and a browser, used to implement various application functions. Programs implementing the methods of this application embodiment can be included in the application program 1022.

[0107] In this embodiment of the application, the processor 101 executes the method steps provided in each method embodiment by calling the program or instructions stored in the memory 102, specifically the program or instructions stored in the application program 1022.

[0108] The methods disclosed in the embodiments of this application can be applied to or implemented by the processor 101. The processor 101 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware or by instructions in the form of software in the processor 101. The processor 101 may be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software units in the decoding processor. The software units may be located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory 102. Processor 101 reads the information in memory 102 and, in conjunction with its hardware, completes the steps of the above method.

[0109] It is understood that the embodiments described herein can be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof. For hardware implementation, the processing unit can be implemented in one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing electronic devices (DSP devices, DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers, microprocessors, other electronic units for performing the functions of this application, or combinations thereof.

[0110] For software implementation, the techniques described herein can be implemented through units that perform the functions described herein. The software code can be stored in memory and executed by a processor. The memory can be implemented within the processor or external to the processor.

[0111] The electronic device provided in this embodiment can execute all the steps of the methods described in the above embodiments, thereby achieving the technical effects of the above methods. For details, please refer to the relevant description of the above data processing method. For the sake of brevity, it will not be elaborated here.

[0112] This application also provides a storage medium (computer-readable storage medium). This storage medium stores one or more programs. The storage medium may include volatile memory, such as random access memory; it may also include non-volatile memory, such as read-only memory, flash memory, hard disk, or solid-state drive; and it may also include combinations of the above types of memory.

[0113] When one or more programs in the storage medium can be executed by one or more processors to achieve the above-described method of execution on the electronic device side.

[0114] The processor is used to execute a program stored in memory to implement the steps of the following methods performed on the electronic device side.

[0115] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0116] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented in hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0117] It should be noted that the terms "one implementation," "embodiment," "exemplary embodiment," and "some embodiments" used in the specification indicate that the described embodiment may include a specific feature, structure, or characteristic, but not every embodiment necessarily includes that specific feature, structure, or characteristic. Furthermore, such phrases do not necessarily refer to the same embodiment. Moreover, when a specific feature, structure, or characteristic is described in connection with an embodiment, implementing such a feature, structure, or characteristic in conjunction with other embodiments, whether explicitly described or not, is within the knowledge scope of those skilled in the art.

[0118] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or air conditioning apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or air conditioning apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or air conditioning apparatus that includes said element.

[0119] The above embodiments are merely preferred embodiments provided to fully illustrate this application, and the scope of protection of this application is not limited thereto. Equivalent substitutions or modifications made by those skilled in the art based on this application are all within the scope of protection of this application.

Claims

1. A self-cleaning method, characterized in that, The self-cleaning method is applied to electronic devices, and the self-cleaning method includes: In augmented reality guidance mode, first guidance information is output; wherein, the first guidance information is used to guide the user to operate the electronic device to determine the self-service cleaning guidance data corresponding to the device to be cleaned; After determining the self-service cleaning guidance data, load the self-service cleaning guidance data corresponding to the equipment to be cleaned; The second guidance information corresponding to the self-service cleaning guidance data is superimposed on the real image of the device to be cleaned captured in real time by the electronic device; wherein, the second guidance information is used to guide the user to disassemble and clean the device to be cleaned.

2. The self-cleaning method according to claim 1, characterized in that, The first guidance information includes information for guiding the user to scan the QR code identifier of the equipment to be cleaned, and the self-service cleaning method includes: Based on the scanning result of the QR code identifier of the device to be cleaned, the self-service cleaning guidance data corresponding to the device to be cleaned is determined.

3. The self-cleaning method according to claim 2, characterized in that, The first guidance information includes information for guiding the user to photograph the salient features of the equipment to be cleaned, and the self-cleaning method includes: If the device to be cleaned does not have the QR code label, or if scanning the QR code label fails, the salient features captured are identified using deep learning-based visual recognition to determine the self-service cleaning guidance data corresponding to the device to be cleaned.

4. The self-cleaning method according to claim 1, characterized in that, The second guidance information corresponding to the self-service cleaning guidance data is superimposed onto the real image of the device to be cleaned captured in real time by the electronic device, including: Based on synchronous positioning and mapping technology and 3D registration algorithm, the second guidance information is overlaid on the real image of the equipment to be cleaned.

5. The self-cleaning method according to claim 1, characterized in that, The second guidance information includes step-by-step, interactive disassembly animations and cleaning operation instructions. The second guidance information, corresponding to the self-service cleaning guidance data, is superimposed onto the real image of the device to be cleaned captured in real time by the electronic device. It includes at least one of the following: The hidden connecting parts in the device to be cleaned are identified on the real image of the device to be cleaned captured in real time by the electronic device; For the disassembly steps involving electrical connections in the disassembly animation, output a safety warning message; After the outer casing of the equipment to be cleaned is disassembled, the core components of the equipment to be cleaned are identified.

6. The self-cleaning method according to any one of claims 1-5, characterized in that, The self-cleaning method includes: After cleaning the equipment to be cleaned is completed, in quality inspection mode, third guidance information is output; wherein, the third guidance information is used to guide the user to operate the electronic device to take a multispectral image of the evaporator of the equipment to be cleaned; After obtaining the multispectral image, the multispectral image is processed based on an image segmentation model to obtain a visual quality inspection report; wherein, the visual quality inspection report represents the cleaning information of the evaporator.

7. The self-cleaning method according to claim 6, characterized in that, The image segmentation model is constructed in the following way: Based on the U-Net architecture, an attention mechanism module and a pyramid pooling module are introduced, and the output channels are set to multiple outputs to construct the image segmentation model.

8. The self-cleaning method according to claim 6, characterized in that, The visualized quality inspection report includes at least one of the following: Cleanliness rating, before and after cleaning comparison images, and a heat map of dirt distribution overlaid on the actual image of the evaporator.

9. A self-service cleaning device, characterized in that, The self-service cleaning device is applied to electronic equipment, and the self-service cleaning device includes: The output module is used to output first guidance information in augmented reality guidance mode; wherein, the first guidance information is used to guide the user to operate the electronic device to determine the self-service cleaning guidance data corresponding to the device to be cleaned; The loading module is used to load the self-service cleaning guidance data corresponding to the equipment to be cleaned after determining the self-service cleaning guidance data. The output module is used to overlay second guidance information corresponding to the self-service cleaning guidance data onto the real image of the device to be cleaned captured in real time by the electronic device; wherein, the second guidance information is used to guide the user to disassemble and clean the device to be cleaned.

10. The self-service cleaning device according to claim 9, characterized in that, The output module is used to output third guidance information after the cleaning of the equipment to be cleaned is completed, if it is determined to enter the quality inspection mode; wherein, the third guidance information is used to guide the user to operate the electronic device to take a multispectral image of the evaporator of the equipment to be cleaned; The output module is further configured to process the multispectral image based on an image segmentation model after obtaining the multispectral image to obtain a visualized quality inspection report; wherein the visualized quality inspection report represents the cleaning information of the evaporator.

11. A self-service cleaning system, characterized in that, The self-cleaning system is used to implement the self-cleaning method as described in any one of claims 1-8.

12. An electronic device, characterized in that, The electronic device includes: processor; Memory used to store the processor's executable instructions; The processor is configured to perform the self-cleaning method as described in any one of claims 1-8.

13. A non-transitory 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 able to perform the self-cleaning method as described in any one of claims 1-8.

Images