Cleaning device control method and apparatus, cleaning device, and storage medium

Abstract

This invention relates to the field of cleaning equipment technology, and discloses a cleaning equipment control method, device, cleaning equipment, and storage medium. The cleaning equipment includes a bristle assembly, which includes a brush head and multiple bristle tufts disposed on the brush head. The length of the bristle tufts is adjustable. The method includes: in response to the pressure detection value of the brush head of the bristle assembly exceeding a preset threshold, acquiring an initial image of the area to be cleaned; based on the initial image of the area to be cleaned, performing scene recognition to determine a target scene for the area to be cleaned; based on the target scene, determining the bristle tuft length parameter of the bristle assembly; based on the bristle tuft length parameter, adjusting the bristle tuft length of the bristle assembly and driving the brush head to rotate to clean the area to be cleaned; matching the corresponding bristle tuft length parameter according to the identified target scene, and adjusting the bristle tuft length according to the bristle tuft length parameter so that the bristles can better fit or act on the surface to be cleaned; dynamically adjusting the bristle tuft length according to the actual cleaning scene to enhance the cleaning effect and efficiency.

Description

Technical Field

[0001] This invention relates to the field of cleaning tool technology, and more specifically to cleaning equipment control methods, devices, cleaning equipment, and storage media. Background Technology

[0002] With the increasing demand for smart home cleaning, electric cleaning brushes are being used more and more widely. However, the fixed bristle length, single cleaning parameters, and inability to adapt to various cleaning needs in related technologies result in low cleaning efficiency. Summary of the Invention

[0003] This invention provides a cleaning equipment control method, device, cleaning equipment, and storage medium to solve the problem of low cleaning efficiency caused by the fixed length of the cleaning brush bristles, which cannot adapt to the cleaning needs of various scenarios.

[0004] In a first aspect, the present invention provides a method for controlling a cleaning device, the cleaning device including a bristle assembly, the bristle assembly including a brush head and a plurality of bristle bundles disposed on the brush head, the length of the bristle bundles being adjustable, the method comprising: When the pressure detection value of the brush head of the bristle assembly exceeds a preset threshold, an initial image of the area to be cleaned is acquired; Based on the initial image of the area to be cleaned, scene recognition is performed on the area to be cleaned to determine the target scene; Based on the target scenario, determine the bristle tuft length parameters of the bristle component; Based on the bristle length parameter, the bristle length of the brush assembly is adjusted, and the brush head is driven to rotate to clean the area to be cleaned.

[0005] This invention determines whether the brush head is in contact with the area to be cleaned by measuring the pressure applied to the brush head. When the pressure exceeds a preset threshold, the system determines that the area to be cleaned may contain stains or be of a certain type, thus triggering image acquisition. By performing scene recognition on the initial image, the specific scene of the area to be cleaned is determined. Based on the identified target scene, the corresponding bristle length parameter is matched, and the bristle length is adjusted according to this parameter to allow the bristles to better adhere to or act on the cleaning surface, driving the brush head to rotate and perform cleaning. This invention can dynamically adjust the bristle length according to the actual cleaning scene, avoiding situations where the bristles are too long, resulting in insufficient cleaning force, or too short, damaging the surface, or the bristles are not properly matched to the cleaning surface, thus reducing manual intervention and enhancing cleaning effect and efficiency.

[0006] In one optional implementation, based on an initial image of the area to be cleaned, scene recognition is performed on the area to be cleaned to determine the target scene, including: Feature extraction is performed on the initial image of the area to be cleaned to obtain the image features of the area to be cleaned, which include at least the texture features of the area to be cleaned. Based on image features, a pre-defined deep learning model is used to perform scene recognition to obtain the target scene associated with the image features.

[0007] This invention extracts feature information from an initial image of the area to be cleaned to form image features, which at least include the texture features of the area to be cleaned to reflect the type of surface material of the area to be cleaned. The image features are then input into a preset deep learning model, which automatically analyzes the correlation between the image features and different scenes and outputs the target scene associated with the image features. By utilizing texture features, different cleaning surfaces can be effectively distinguished. Combined with the recognition capabilities of the deep learning model, the accuracy and adaptability of scene judgment can be improved, thereby providing a reliable basis for the precise adjustment of hair tuft length in the future.

[0008] In one optional implementation, the bristle tuft length parameter of the bristle assembly is determined based on the target scenario, including: Based on the correspondence between different scenarios and hair tuft length, the target hair tuft length corresponding to the target scenario is determined.

[0009] This invention establishes a pre-defined correspondence between different scenes and hair tuft lengths. Based on the identified target scene, it finds and determines the target hair tuft length that matches the scene. This facilitates the rapid and accurate output of hair tuft length parameters suitable for the current cleaning surface through the mapping between scenes and hair tuft lengths. It also facilitates comprehensive cleaning of the area to be cleaned and improves the adaptability of cleaning equipment to the cleaning area.

[0010] In one optional implementation, adjusting the bristle tuft length of the brush assembly based on the bristle tuft length parameter includes: Adjust the bristle length of the brush assembly to the target bristle length.

[0011] This invention adjusts the actual length of each bristle in the brush assembly to the length value corresponding to the target bristle length by driving an adjustment mechanism based on the determined target bristle length. This effectively cleans the area to be cleaned, ensuring that the pressure and fit of the bristles on the ground are adapted to the target scene, thereby improving the cleaning effect and reducing ineffective cleaning caused by length mismatch.

[0012] In one optional implementation, adjusting the bristle tuft length of the brush assembly based on the bristle tuft length parameter includes: Obtain the current surface curvature in the initial image, and determine the distribution pattern of hair bundles in different regions on the bristle assembly based on the surface curvature, so that the distribution pattern is adapted to the current surface curvature; Adjust the length of the hair tufts in the first region with the longest hair tufts in the distribution pattern to the hair tuft length parameter corresponding to the target hair tuft length. Based on the target hair tuft length, adjust the hair tuft lengths in other regions according to the distribution pattern. The other regions are all regions on the brush assembly other than the first region.

[0013] This invention obtains the surface curvature contained in the image features and determines the distribution pattern of bristle bundles in different areas of the brush assembly based on the curvature. This allows the distribution pattern to adapt to the surface curvature of the area to be cleaned. The bristle bundle length of the first area with the longest bristle bundle in the distribution pattern is adjusted to the bristle bundle length parameter corresponding to the target bristle bundle length. Then, using this length as a reference, the bristle bundle lengths of other areas are adjusted according to the distribution pattern. This allows for differentiated bristle bundle length distributions at different positions on the brush assembly for cleaning surfaces with curved or uneven surfaces. This results in a more uniform fit to the surface contour during rotational cleaning, which helps to match the cleaning bristle bundle length with the curvature of the cleaning surface. This avoids insufficient contact or excessive pressure in some areas due to surface curvature, and improves the cleaning coverage and cleaning consistency of non-planar areas.

[0014] In one alternative implementation, the method further includes: During the process of driving the brush head to rotate and clean the area to be cleaned, the current image of the area to be cleaned is captured. The current image is compared with the target clean image of the target scene to determine the current cleanliness level; When the current cleanliness level is determined to have reached the preset cleanliness level for the target scenario, the area to be cleaned is determined to be cleaned and the length of all bristle tufts in the brush assembly is adjusted to the initial bristle tuft length.

[0015] This invention continuously acquires images of the area to be cleaned during brush head rotation, compares these images with a pre-set target cleaning image for the target scene, calculates the current level of cleanliness, and confirms that the area to be cleaned has been cleaned when the current cleanliness has reached the preset cleanliness requirement for the scene. The length of all bristles on the brush assembly is then restored to their initial length. Real-time evaluation of the cleaning effect is achieved through image comparison, avoiding over-cleaning or incomplete cleaning. Automatically restoring the bristle length after cleaning reduces deformation or wear caused by bristles remaining at non-initial lengths for extended periods, while providing a consistent starting state for the next cleaning task, thus improving the automation level and lifespan of the equipment.

[0016] In one alternative implementation, the method further includes: During the process of driving the brush head to rotate and clean the area to be cleaned, the rate of pressure change of the brush head in the area to be cleaned is obtained; Based on the correspondence between the preset pressure change rate and the preset scene, update the target scene and return the steps of determining the bristle tuft length parameter of the bristle component based on the target scene.

[0017] This invention acquires the pressure change rate of the brush head on the area to be cleaned in real time during the brush head rotation cleaning process. Based on the pre-established correspondence between the pressure change rate and different scenarios, it determines whether the current pressure change rate corresponds to a new scenario. If so, it updates the current target scenario and re-executes the step of determining the bristle length parameters based on the target scenario. This allows for dynamic sensing of changes in the ground material or stain adhesion state during the cleaning process, thereby adjusting the bristle length in a timely manner to adapt to new cleaning conditions. This avoids the problem of poor cleaning effect caused by using the original parameters after the scenario changes, and improves the adaptability of cleaning equipment to complex environments.

[0018] In one alternative embodiment, the cleaning device further includes a drive motor for driving the brush head to rotate, and the method further includes: During the process of driving the brush head to rotate and clean the area to be cleaned, the current cleaning intensity is obtained; Based on the relationship between the current cleaning intensity and the preset cleaning intensity corresponding to the target scene, the speed of the drive motor is adjusted accordingly.

[0019] This invention acquires the current cleaning intensity in real time during the brush head rotation cleaning process, compares the current cleaning intensity with the preset cleaning intensity corresponding to the target scene, and adjusts the speed of the drive motor accordingly based on the relationship between the two. This allows the cleaning intensity to be maintained within the appropriate range required by the target scene. When the cleaning intensity is insufficient, the motor speed is increased to enhance the cleaning ability; when the cleaning intensity is excessive, the motor speed is reduced to avoid damaging the cleaning surface or excessive energy consumption. Thus, while ensuring the cleaning effect, the adaptability and energy efficiency of the cleaning process are improved.

[0020] In a second aspect, the present invention provides a cleaning equipment control device. The cleaning equipment includes a bristle assembly, the bristle assembly including a brush head and a plurality of bristle bundles disposed on the brush head, the length of the bristle bundles being adjustable. The device includes: The acquisition module is used to acquire an initial image of the area to be cleaned in response to the pressure detection value of the brush head of the bristle assembly exceeding a preset threshold. The recognition module is used to identify the target scene of the area to be cleaned based on the initial image of the area to be cleaned. The determination module is used to determine the bristle tuft length parameters of the bristle component based on the target scene; The adjustment module is used to adjust the bristle length of the brush assembly based on the bristle length parameter, and drive the brush head to rotate to clean the area to be cleaned.

[0021] Thirdly, the present invention provides a cleaning device, which includes a bristle assembly, the bristle assembly including a brush head and a plurality of bristle bundles disposed on the brush head, the length of the bristle bundles being adjustable, and the cleaning device further includes a controller, the controller comprising: The memory and the processor are interconnected and communicate with each other. The memory stores computer instructions, and the processor executes the computer instructions to perform the method described in the first aspect or any of its corresponding embodiments.

[0022] In one alternative embodiment, multiple bristle bundles are slidably disposed on the brush head along the length direction of the bristle bundles. The multiple bristle bundles are driven by multiple linear drive mechanisms, which drive the multiple bristle bundles to present multiple distribution patterns on the brush head.

[0023] This invention allows multiple bristle bundles to slide independently or in groups along their length. It can actively adjust the length of the bristle bundles in different areas according to the surface to be cleaned, achieving a higher degree of contact with the surface. Through multiple linear drive mechanisms, the bristle bundles are driven to actively present any desired distribution pattern on the brush head. The force between each bristle bundle is controllable, and the operation of each bristle bundle during the cleaning process is complementary and does not interfere with each other, avoiding the failure of a local individual bristle bundle that causes the entire brush head to stop working, thus improving the working efficiency of the cleaning equipment.

[0024] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to perform the method described in the first aspect or any corresponding embodiment thereof. Attached Figure Description

[0025] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0026] Figure 1 This is a schematic diagram of an application scenario according to an embodiment of the present invention; Figure 2 This is a schematic flowchart of a first method for controlling cleaning equipment according to an embodiment of the present invention; Figure 3 This is a schematic diagram of a second process for a cleaning equipment control method according to an embodiment of the present invention; Figure 4 This is a flowchart of the cleaning equipment operation according to an embodiment of the present invention; Figure 5This is a schematic diagram of a first structure of a brush head assembly of a cleaning device according to an embodiment of the present invention; Figure 6 This is a schematic diagram of a second structure of a brush head assembly for a cleaning device according to an embodiment of the present invention; Figure 7 This is a schematic diagram of a third structure of the brush head assembly of a cleaning device according to an embodiment of the present invention; Figure 8 This is a structural block diagram of a cleaning equipment control device according to an embodiment of the present invention; Figure 9 This is a schematic diagram of the controller structure of the cleaning equipment according to an embodiment of the present invention. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0028] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.

[0029] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0030] Figure 1 This is a schematic diagram of an optional application scenario of an embodiment of the present invention, such as... Figure 1As shown, the cleaning device includes a controller 101 and a bristle assembly 102. The bristle assembly 102 includes a brush head 1 and multiple bristle bundles 2 disposed on the brush head 1. The length of the bristle bundles 2 is adjustable, and the multiple bristle bundles 2 are slidably disposed on the brush head 1 along the length direction of the bristle bundles 2. The multiple bristle bundles 2 are driven by multiple linear drive mechanisms, which drive the multiple bristle bundles 2 to present multiple distribution patterns on the brush head 1. The cleaning device also includes an image acquisition device 3 disposed on the brush head 1 for acquiring images of the area to be cleaned. It also includes a housing 4, and the housing 4 and the brush head 1 are detachably connected. The controller 101 is used for the cleaning device control method. For details on the overall process of the controller 101 executing the cleaning device control method, please refer to the relevant description of the method embodiment below, which will not be repeated here.

[0031] The multiple distribution patterns of multiple hair bundles 2 on the brush head 1 refer to the various forms that the multiple hair bundles present along the length direction. For example, the length of the hair bundles increases or decreases step by step from the center to the edge of the brush head, presenting a cone shape, that is, a shape with a raised center and a concave edge; it can also present a shape with a concave center and a raised edge, or a horizontal shape with the same hair bundle length from the center to the edge of the brush head.

[0032] The cleaning device provided in this embodiment can be an electric cleaning brush, which is a cleaning tool for home scenarios such as desktops, shoe surfaces, and carpets, or it can be a cleaning device with a brush head assembly, such as an electric toothbrush.

[0033] In related technologies, the brush head control technology of electric cleaning brushes remains at the "mechanical preset" stage, severely limiting cleaning effectiveness and user experience. Brush head lifespan depends on user judgment or a fixed cycle (usually 3 months / use), lacking a real-time wear monitoring mechanism. Ordinary users cannot determine whether the bristles are worn (e.g., cleaning efficiency decreases by 50% when bristle curvature >30%). "Hardware upgrades" for electric cleaning brushes (such as higher frequency sound waves) have reached a bottleneck, and their control logic remains at the "one-way preset" stage, failing to build an intelligent closed loop between perception, decision-making, and execution. This hinders the industry's transformation towards "personalized and sustainable" practices.

[0034] To address the aforementioned issues, a cleaning equipment control method is provided. Through dynamic parameter optimization and adaptive strategies, it achieves the effect of adaptively adjusting the bristle length of traditional electric cleaning brushes, enabling them to adapt to various cleaning scenarios. By identifying and matching the bristle length associated with the scenario, it automatically adjusts the bristle length according to the type of cleaning object to match cleaning needs. This solves the technical problem of low cleaning efficiency or surface damage caused by mismatched bristle lengths, achieving the technical effect of ensuring cleaning effectiveness while avoiding scratches or fiber damage to soft materials. It also solves the inconvenience of users having to frequently replace brush heads or manually adjust them, thus improving operational convenience and user experience.

[0035] According to embodiments of the present invention, an electric cleaning brush system that automatically identifies and intelligently controls changes in bristle length based on the cleaning scenario achieves the goals of multi-purpose brushing and automatic adaptation of cleaning equipment to various scenarios, enabling efficient cleaning of different scenarios. Users do not need to manually replace brush heads or rely on multiple sets of brush heads, avoiding cumbersome operation and improving user experience.

[0036] According to an embodiment of the present invention, a method for controlling a cleaning device is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0037] This embodiment provides a cleaning equipment control method, which can be used in the controller of the aforementioned cleaning equipment. Figure 2 This is a schematic flowchart of a first embodiment of a cleaning equipment control method according to the present invention, such as... Figure 2 As shown, the process includes the following steps: Step S201: In response to the pressure detection value of the brush head of the bristle assembly exceeding a preset threshold, an initial image of the area to be cleaned is acquired.

[0038] Specifically, when the brush head pressure detection value of the bristle assembly exceeds a preset threshold and the acceleration signal of the brush head rotation is within a preset acceleration range, an initial image of the area to be cleaned is acquired.

[0039] It should be noted that the area to be cleaned includes the surface to be cleaned, and the cleaning equipment includes a pressure detection sensor. The pressure detection sensor detects whether the brush head is in contact with the surface to be cleaned in the cleaning area. When the detected pressure value exceeds a preset threshold, it means that the brush head of the bristle assembly is in contact with the surface to be cleaned, and at this time, the initial image of the area to be cleaned is acquired.

[0040] The preset threshold is 0.5N, and the preset acceleration range is based on the stable acceleration of the brush head of the cleaning device when it contacts the cleaning surface.

[0041] The brush head is equipped with an image acquisition device, which acquires an initial image of the area to be cleaned. The initial image refers to the image of the area to be cleaned when the brush head contacts the surface to be cleaned. The area of ​​the area to be cleaned is at least larger than the area of ​​the surface to be cleaned.

[0042] Step S202: Based on the initial image of the area to be cleaned, perform scene recognition on the area to be cleaned to determine the target scene.

[0043] It should be noted that the scene recognition of the area to be cleaned is performed by using the features of the surface to be cleaned in the initial image of the area to be cleaned, thereby determining the target scene.

[0044] The target scenarios include at least hard surfaces such as ceramic tiles and wooden boards, leather shoe uppers, fabric shoelaces, and narrow gaps such as shoe seams and wall corners.

[0045] For example, scene recognition can be determined by pre-storing scene images of multiple scenes and comparing the similarity between the acquired initial image and the scene images.

[0046] Step S203: Determine the bristle tuft length parameters of the brush assembly based on the target scenario.

[0047] It should be noted that, based on the characteristics of the surface to be cleaned in each scenario, a bristle tuft length adapted to the surface to be cleaned in that scenario is configured accordingly. After the target scenario is determined through scenario recognition, the bristle tuft length parameter of the brush component can be determined based on the matching relationship between the target scenario and the corresponding bristle tuft length.

[0048] Step S204: Based on the bristle length parameter, adjust the bristle length of the brush assembly and drive the brush head to rotate to clean the area to be cleaned.

[0049] It should be noted that the brush head has multiple bristle tufts, and the length of each bristle tuft is adjusted according to the characteristics of the target scene. In different target scenes, the length of each bristle tuft can be the same or different. For example, when the target scene is a cup, the length of each bristle tuft is different, and the length of the bristle tuft is adapted to the shape of the surface of the cup to be cleaned.

[0050] The cleaning equipment control method provided in this embodiment determines whether the brush head is in contact with the area to be cleaned by the pressure it receives. When the pressure on the brush head exceeds a preset threshold, the system determines that there may be stains or a specific type of area to be cleaned in the current area, thereby triggering image acquisition. By performing scene recognition on the initial image, the specific scene of the area to be cleaned is determined. The corresponding bristle length parameter is matched according to the identified target scene, and the bristle length is adjusted according to the bristle length parameter so that the bristles can better fit or act on the cleaning surface, and drive the brush head to rotate to perform cleaning. The bristle length can be dynamically adjusted according to the actual cleaning scene, avoiding insufficient cleaning force due to excessively long bristles, damage to the surface due to excessively short bristles, or incomplete cleaning due to mismatch between bristle length and the cleaning surface. This reduces manual intervention and enhances cleaning effect and efficiency.

[0051] This embodiment provides a cleaning equipment control method, which can be used in the controller of the aforementioned cleaning equipment. Figure 3 This is a schematic diagram of a second process for a cleaning equipment control method according to an embodiment of the present invention, as shown below. Figure 3 As shown, the process includes the following steps: Step S301: In response to the pressure detection value of the brush head of the bristle assembly exceeding a preset threshold, an initial image of the area to be cleaned is acquired. For details, please refer to [link to relevant documentation]. Figure 2 Step S201 of the illustrated embodiment will not be described again here.

[0052] Step S302: Based on the initial image of the area to be cleaned, perform scene recognition on the area to be cleaned to determine the target scene.

[0053] Specifically, step S302 includes: Step S3021: Extract features from the initial image of the area to be cleaned to obtain image features of the area to be cleaned. The image features include at least the texture features of the area to be cleaned.

[0054] It should be noted that the initial image of the area to be cleaned is filtered, denoised, and normalized to obtain a preprocessed image, and the image features are extracted from the preprocessed image.

[0055] Step S3022: Based on image features, use a preset deep learning model to perform scene recognition to obtain the target scene associated with the image features.

[0056] It should be noted that image features are input into a pre-defined deep learning model for scene recognition. This model, trained on a large number of samples, can accurately identify multiple scenes. For example, it can accurately identify hard tabletops (such as tiles or wooden boards), leather shoe uppers, fabric shoelaces, and narrow gaps (such as shoe seams or wall corners), thus identifying the target scene associated with the image features. For instance, if the texture features in the image match the texture features of the tabletop, then the identified target scene is the tabletop.

[0057] The cleaning equipment control method provided in this embodiment extracts feature information from the initial image of the area to be cleaned to form image features, which at least include the texture features of the area to be cleaned to reflect the type of cleaning surface material of the area. The image features are input into a preset deep learning model, which automatically analyzes the correlation between the image features and different scenes and outputs the target scene associated with the image features. The texture features can effectively distinguish different cleaning surfaces. Combined with the recognition ability of the deep learning model, the accuracy and adaptability of scene judgment can be improved, thereby providing a reliable basis for the precise adjustment of the hair tuft length in the future.

[0058] Step S303: Determine the bristle tuft length parameters of the brush component based on the target scenario.

[0059] Specifically, step S303 includes: Step S3031: Based on the correspondence between different scenarios and hair tuft length, determine the target hair tuft length corresponding to the target scenario.

[0060] It should be noted that after identifying the target scene, the target hair bundle length corresponding to the target scene is obtained by looking up a table.

[0061] For example, the correspondence between the target scene and the target hair tuft length is shown in Table 1.

[0062] Table 1. Correspondence between Scene and Hair Bundle Length

[0063] The cleaning equipment control method provided in this embodiment, through the pre-established correspondence between different scenes and hair tuft lengths, finds and determines the target hair tuft length that matches the identified target scene. This facilitates the rapid and accurate output of hair tuft length parameters suitable for the current cleaning surface through the mapping between scenes and hair tuft lengths, which is beneficial for comprehensive cleaning of the area to be cleaned and improves the adaptability of the cleaning equipment to the cleaning area.

[0064] Step S304: Based on the bristle length parameter, adjust the bristle length of the brush assembly and drive the brush head to rotate to clean the area to be cleaned.

[0065] Specifically, adjust the bristle length of the brush assembly to the target bristle length.

[0066] It's important to note that the target bristle length is the length of the bristles that adapts to the surface to be cleaned. For example, when the surface is uneven, the lengths of the bristles may not be equal. Adjustments are made based on the curvature differences across the surface to ensure each bristle maintains effective contact with its corresponding location during brush head rotation. On uneven surfaces, the ability to adapt the bristle lengths allows for effective contact between the bristles and the surface, resulting in efficient cleaning.

[0067] The cleaning equipment control method provided in this embodiment drives the adjustment mechanism to adjust the actual length of each bristle in the brush assembly to the length value corresponding to the target bristle length according to the determined target bristle length, thereby effectively cleaning the area to be cleaned, ensuring that the pressure and fit of the bristles on the ground are adapted to the target scene, thereby improving the cleaning effect and reducing ineffective cleaning caused by length mismatch.

[0068] Specifically, step S304 includes: Step S3041: Obtain the current surface curvature in the initial image, and determine the distribution pattern of hair bundles in different regions on the brush assembly based on the surface curvature so that the distribution pattern is adapted to the current surface curvature.

[0069] The current surface curvature of the surface to be cleaned is obtained from the initial image.

[0070] It should be noted that the distribution pattern refers to the distribution pattern of hair tuft length, that is, the lengths of hair tufts in different regions are not the same.

[0071] For example, in some optional embodiments of this embodiment, when the bristle tufts of the brush assembly are tilted at an adjustable angle, the distribution pattern includes at least the distribution pattern of bristle tuft length and the distribution pattern of bristle tufts at different tilt angles. By using different tilt angles, the effective contact between the bristle tufts of the brush assembly and the surface to be cleaned can be achieved when cleaning various complex scenarios.

[0072] It should be noted that the surface curvature of the area to be cleaned is identified by a pre-set deep learning model. Then, based on this curvature, different distribution patterns of the bristle tufts in different areas of the brush assembly are planned. These distribution patterns include at least the length distribution pattern. Taking a cup as an example, a cup has a cylindrical body, an arc-shaped bottom, and rounded corners at the rim. Its surface is curved, resulting in varying degrees of surface curvature. Areas with greater surface curvature correspond to bristle tuft lengths that are shorter than areas with less surface curvature.

[0073] For example, in some optional implementations, the height difference between different areas in the area to be cleaned is obtained, and the distribution pattern of the bristle tufts in different areas of the bristle assembly is determined based on the height difference between the different areas, so that the distribution pattern is adapted to the current surface curvature. For example, the bristle tuft length corresponding to the area of ​​the surface to be cleaned with a larger height relative to the brush head is smaller than the bristle tuft length corresponding to the area of ​​the surface to be cleaned with a smaller height relative to the brush head.

[0074] Step S3042: Adjust the hair tuft length of the first region with the longest hair tuft length in the distribution pattern to the hair tuft length parameter corresponding to the target hair tuft length, and adjust the hair tuft length of other regions based on the distribution pattern with the target hair tuft length as the reference. Other regions are all regions on the brush assembly other than the first region.

[0075] It should be noted that the distribution pattern refers to the spatial distribution pattern of the bristle length in different areas of the bristle assembly, such as the length gradually increasing or decreasing from the center to the edge, or the length distribution set according to the curvature.

[0076] The determination of the hair tuft length in other areas based on the target hair tuft length can be achieved by proportionally determining the length of other areas relative to the target hair tuft length according to their distribution pattern. For example, the target hair tuft length can be multiplied by a proportional coefficient to ensure that the hair tuft length in each area effectively contacts the surface to be cleaned.

[0077] For example, the bristle length adjustment range is 3mm (very short) to 18mm (longest), supporting continuous adjustment or three-level switching (short: 5mm, medium: 10mm, long: 18mm). To ensure adjustment accuracy, a high-precision encoder is installed at the end of the lead screw of the cleaning device to provide real-time feedback on the current bristle length, with an error controlled within ±0.5mm. Simultaneously, mechanical limit switches are installed at both ends of the brush head guide rail of the bristle assembly to prevent excessive extension and retraction from causing structural damage.

[0078] Taking a cup as an example, when cleaning the inside of the cup, the bristle length is 18cm in the middle circle with a radius of 1cm, 10cm in the annular area with a radius of 1cm to 3cm, and 5cm in the annular area with a radius of 3cm to 5cm. With this distribution, the bristles in the middle area are finer and can penetrate deep into the slender inside of the cup to clean the inside.

[0079] The cleaning equipment control method provided in this embodiment obtains the surface curvature contained in the image features and determines the distribution pattern of the bristle bundles in different areas of the bristle assembly based on the curvature. This allows the distribution pattern to adapt to the surface curvature of the area to be cleaned. The bristle bundle length of the first area with the longest bristle bundle in the distribution pattern is adjusted to the target bristle bundle length. Then, using this length as a reference, the bristle bundle lengths of other areas are adjusted accordingly according to the distribution pattern. This method can make the bristle bundles at different positions on the bristle assembly present a differentiated length distribution for cleaning surfaces with curved or uneven surfaces. This allows for a more uniform fit to the surface contour during rotational cleaning, which helps to match the length of the cleaning bristles with the curvature of the cleaning surface of the area to be cleaned. This avoids insufficient contact or excessive pressure in some areas due to surface curvature, and improves the cleaning coverage and cleaning consistency of non-planar areas.

[0080] Step S305: During the process of driving the brush head to rotate and clean the area to be cleaned, the current image of the area to be cleaned is acquired.

[0081] It should be noted that the brush assembly rotates under the drive of a motor, removing stains through friction. The area to be cleaned is the cleaning range of the object surface currently being cleaned. The current image is a real-time image acquired by an image acquisition device used to determine the degree of cleanliness.

[0082] Step S306: Compare the current image with the target clean image of the target scene to determine the current cleanliness.

[0083] The target cleaning image is an image of the area to be cleaned in a clean state.

[0084] The comparison between the current image and the target clean image of the target scene can be performed using image algorithms such as pixel difference comparison, texture similarity comparison, and stain area detection. The current cleanliness is determined based on the pixel difference comparison results, texture similarity comparison results, and / or stain area detection results. In some optional implementations of this embodiment, the ratio of the difference in pixel values ​​between the current image and the target clean image of the target scene to the total pixel values ​​can be calculated first, and then the current cleanliness is obtained by subtracting this ratio from the cleanliness coefficient. When performing texture similarity comparison, the similarity between the current image and the target clean image is positively correlated with the cleanliness of the current image, that is, the higher the similarity, the higher the cleanliness. In stain area detection, the stain area in the current image is segmented using an image segmentation algorithm, and the ratio of the stain area to the total image area is calculated. The ratio of the stain area to the total image area is negatively correlated with the cleanliness, that is, the smaller the ratio, the higher the cleanliness.

[0085] Step S307: When it is determined that the current cleanliness has reached the preset cleanliness of the target scene, it is determined that the area to be cleaned has been cleaned and the length of all bristles of the brush assembly is adjusted to the initial bristle length.

[0086] It should be noted that the preset cleanliness level is a cleanliness indicator; for example, a cleanliness level of 95% to 100% means cleaning is complete. The initial bristle length is the shortest possible, with all bristles being the same length, which helps protect the bristles. In the next area to be cleaned, the surface shape is different, requiring the bristle length to be readjusted according to the curvature; therefore, the bristle length needs to be adjusted back to the initial bristle length.

[0087] The cleaning equipment control method provided in this embodiment continuously acquires the current image of the area to be cleaned during the rotation of the brush head, compares the current image with a pre-set target cleaning image for the target scene, calculates the current cleaning level, and confirms that the area to be cleaned has been cleaned when it is determined that the current cleaning level has reached the preset cleaning level requirement corresponding to the scene. The length of all bristles on the brush assembly is restored to the initial bristle length. Real-time evaluation of the cleaning effect is achieved through image comparison to avoid over-cleaning or incomplete cleaning. Automatically restoring the bristle length after cleaning can reduce deformation or wear caused by the bristles being at a non-initial length for a long time, and at the same time provide a uniform starting state for the next cleaning task, improving the automation level and service life of the equipment.

[0088] Step S308: During the process of driving the brush head to rotate and clean the area to be cleaned, the pressure change rate of the brush head in the area to be cleaned is obtained.

[0089] For example, pressure can identify whether the brush head bristles are in contact with the surface to be cleaned. For instance, pressure can identify whether the bristles of the brush head are in contact with the surface to be cleaned at their initial bristle length. The rate of pressure change can reflect the scenario in which the user is using the brush, such as a change of 5N to 10N for hard materials and a change of 1N to 2N for leather shoe uppers. Furthermore, increasing the force during use can reduce the rotation speed, thereby increasing the torque and achieving a more effective cleaning effect.

[0090] Step S309: Based on the correspondence between the preset pressure change rate and the preset scene, update the target scene and return to the step of determining the bristle tuft length parameter of the bristle component based on the target scene.

[0091] It should be noted that the surface shape of the object may change during the cleaning process, such as from the body of the cup to the bottom. The pressure change rate can identify geometric abrupt changes, thereby providing a basis for adjusting the bristle length, enabling the bristle length to be adapted to the surface to be cleaned, and to adjust the bristle length in real time based on the real-time changes of the surface to be cleaned.

[0092] The cleaning equipment control method provided in this embodiment acquires the pressure change rate of the brush head in the area to be cleaned in real time during the brush head rotation cleaning process. Based on the pre-established correspondence between the pressure change rate and different scenarios, it determines whether the current pressure change rate corresponds to a new scenario. If so, it updates the current target scenario and re-executes the step of determining the bristle length parameter based on the target scenario. This allows for dynamic perception of changes in the ground material or stain adhesion state during the cleaning process, thereby adjusting the bristle length in a timely manner to adapt to new cleaning conditions. This avoids the problem of poor cleaning effect caused by using the original parameters after the scenario changes, and improves the adaptability of the cleaning equipment to complex environments.

[0093] The cleaning device also includes a drive motor for driving the brush head to rotate, and the method further includes: Step b1: During the process of driving the brush head to rotate and clean the area to be cleaned, obtain the current cleaning intensity.

[0094] It should be noted that the cleaning force can be the motor speed of the cleaning device, and in some alternative implementations, the cleaning force can be the force applied by the brush head to the surface to be cleaned, such as pressure.

[0095] Step b2: Based on the relationship between the current cleaning intensity and the preset cleaning intensity corresponding to the target scene, adjust the speed of the drive motor accordingly.

[0096] Different preset cleaning intensities are set for different target scenarios. Based on the preset cleaning intensities corresponding to the current target scenario, the relationship between the current cleaning intensity and the preset cleaning intensity is obtained in real time. When the current cleaning intensity is greater than the preset cleaning intensity, the drive motor speed is reduced; when the current cleaning intensity is less than the preset cleaning intensity, the drive motor speed is increased.

[0097] The preset cleaning intensity can be determined by using a pre-set deep learning algorithm to identify the current level of cleanliness when acquiring the initial image of the area to be cleaned, and then matching a cleaning intensity parameter based on that level. This cleaning intensity parameter drives the brush head to rotate and clean the area. As the cleaning intensity increases during use, the rotation speed can be reduced, thereby increasing the torque and achieving a more effective cleaning.

[0098] The cleaning equipment control method provided in this embodiment acquires the current cleaning intensity in real time during the cleaning process of driving the brush head to rotate, compares the current cleaning intensity with the preset cleaning intensity corresponding to the target scene, and adjusts the speed of the drive motor accordingly based on the relationship between the two. This allows the cleaning intensity to be maintained within the appropriate range required by the target scene. When the cleaning intensity is insufficient, the motor speed is increased to enhance the cleaning ability; when the cleaning intensity is too high, the motor speed is reduced to avoid damaging the cleaning surface or excessive energy consumption. This improves the adaptability and energy efficiency of the cleaning process while ensuring the cleaning effect.

[0099] Combination Figures 4 to 7 This describes one optional application embodiment of the present invention.

[0100] For example, Figure 4 This is a flowchart of the cleaning equipment workflow. Figure 5 A schematic diagram of the first structure of the brush head assembly for a cleaning device; Figure 6 A schematic diagram of a second structure for the brush head assembly of a cleaning device; Figure 7 This is a schematic diagram of a third structure for the brush head assembly of a cleaning device; the diagram includes a brush head 1, bristle bundles 2, an image acquisition device 3, and a housing 4; wherein... Figure 5 This illustration shows a first example of how the bristles of the cleaning device provided in this embodiment of the invention are adapted to the surface to be cleaned in a target scene. Figure 6 This illustration shows a second example of how the bristle tufts of the cleaning device provided in this embodiment of the invention are adapted to the surface to be cleaned in a target scene. In this embodiment, the bristle assembly is detachably mounted on the housing. Figure 7 An example of a detachable installation of the bristle assembly and housing is shown in an embodiment of the present invention.

[0101] In some optional embodiments of the present invention, the cleaning device control method can be applied to cleaning devices with brush heads of various shapes. For example, the brush head shown in the figure is circular, which is beneficial for cleaning corners and crevices and provides efficient rotational cleaning force, can better fit the surface to be cleaned, and is convenient for reaching into narrow spaces.

[0102] In this embodiment, the control method for the cleaning equipment includes a brush head body, a control unit, sensors, a bristle extension drive mechanism, and a power module. The brush head body is equipped with a retractable bristle assembly, and the control unit is integrated inside the brush handle to execute intelligent control algorithms. This system achieves adaptive cleaning for different objects by sensing the cleaning scene, identifying the surface type, and automatically adjusting the bristle length.

[0103] The bristle assembly consists of multiple bristle bundles, each mounted on a sliding bristle guide rail. The guide rail is connected to the drive shaft via a miniature lead screw and nut mechanism, driven by a miniature stepper motor. The motor receives commands from the control unit, driving the lead screw to rotate, achieving linear extension and retraction of the bristle bundles. The bristle length (bristle bundle length) adjustment range is 3mm (extremely short) to 18mm (longest), supporting continuous adjustment or three-level switching (short: 5mm, medium: 10mm, long: 18mm). To ensure adjustment accuracy, a high-precision encoder is installed at the end of the lead screw, providing real-time feedback on the current bristle length (bristle bundle length), with an error controlled within ±0.5mm. Simultaneously, mechanical limit switches are installed at both ends of the guide rail to prevent structural damage from excessive extension and retraction.

[0104] During the cleaning process, the system first uses a pressure sensor to detect whether the brush head is in contact with a surface, such as the surface to be cleaned in the area to be cleaned. When the contact pressure exceeds 0.5N and the acceleration signal is stable, the system initiates a multimodal perception process: the optical recognition module (miniature camera) captures the texture of the surface to be cleaned, acquiring image information; the pressure sensor continuously monitors the rate of change of contact force. All raw data is filtered, denoised, and normalized before being input into a lightweight deep learning model for scene recognition. This model has been trained with a large number of samples and can accurately identify four typical scenes: hard tabletops (such as tiles and wooden boards), leather shoe uppers, fabric shoelaces, and narrow gaps (such as shoe seams and corners). After the recognition result is output, the control unit looks up the corresponding bristle length instruction. For example, when it is recognized as "leather shoe upper," the system controls the motor to reverse, retracting the bristles from 18mm to 5mm; when it is recognized as "hard tabletop," the motor rotates forward, extending the bristles to 18mm. After cleaning, the bristles automatically retract to the standby length.

[0105] The electric cleaning brush system combines structure and control logic to automatically identify and intelligently control the changes in bristle length according to the cleaning scenario, so as to achieve the goal of "one brush for multiple uses, automatic adaptation, and efficient cleaning". Users do not need to manually change brush heads or rely on multiple sets of brush heads, avoiding cumbersome operation and improving user experience.

[0106] An electric cleaning brush system that can automatically identify and intelligently control the changes in bristle length according to the cleaning scenario achieves the goal of "one brush for multiple uses, automatic adaptation, and efficient cleaning". Users do not need to manually change brush heads or rely on multiple sets of brush heads, avoiding cumbersome operation and improving user experience.

[0107] This embodiment also provides a cleaning equipment control device for implementing the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0108] This embodiment provides a cleaning equipment control device. The cleaning equipment includes a bristle assembly, which includes a brush head and multiple bristle bundles disposed on the brush head. The length of the bristle bundles is adjustable. Figure 8 As shown, the device includes: The acquisition module 801 is used to acquire an initial image of the area to be cleaned in response to the pressure detection value of the brush head of the bristle assembly exceeding a preset threshold. The recognition module 802 is used to perform scene recognition on the area to be cleaned based on an initial image of the area to be cleaned to determine the target scene. The determination module 803 is used to determine the bristle tuft length parameters of the bristle component based on the target scene; The adjustment module 804 is used to adjust the bristle length of the brush assembly based on the bristle length parameter and drive the brush head to rotate to clean the area to be cleaned.

[0109] In some alternative implementations, the identification module 802 includes: The feature extraction unit is used to extract features from the initial image of the area to be cleaned, and obtain the image features of the area to be cleaned. The image features include at least the texture features of the area to be cleaned.

[0110] The recognition unit is used to identify the target scene associated with the image features by using a preset deep learning model based on image features.

[0111] In some alternative implementations, the determining module 803 includes: The determining unit is used to determine the target hair tuft length corresponding to the target scene based on the correspondence between different scenes and hair tuft lengths.

[0112] In some alternative implementations, the adjustment module 804 includes: The first adjustment unit is used to acquire the current surface curvature in the initial image and determine the distribution pattern of hair bundles in different regions on the bristle assembly based on the surface curvature, so that the distribution pattern is adapted to the current surface curvature.

[0113] The second adjustment unit is used to adjust the hair tuft length of the first region with the longest hair tuft length in the distribution pattern to the hair tuft length parameter corresponding to the target hair tuft length, and to adjust the hair tuft length of other regions based on the distribution pattern with the target hair tuft length as a reference. The other regions are all regions on the brush assembly other than the first region.

[0114] In some alternative embodiments, the device further includes: The current image acquisition module is used to acquire the current image of the area to be cleaned during the process of driving the brush head to rotate and clean the area.

[0115] The cleanliness determination module is used to compare the current image with the target clean image of the target scene to determine the current cleanliness.

[0116] The module for adjusting the initial bristle length is used to determine that the cleaning of the area to be cleaned is complete when the current cleanliness reaches the preset cleanliness of the target scene, and to adjust the length of all bristles of the brush assembly to the initial bristle length.

[0117] The detection module is used to obtain the pressure change rate of the brush head in the area to be cleaned during the process of driving the brush head to rotate and clean the area.

[0118] The update module is used to update the target scene based on the correspondence between the preset pressure change rate and the preset scene, and return the steps of determining the bristle tuft length parameters of the bristle component based on the target scene.

[0119] The acquisition module is used to acquire the current cleaning intensity during the process of driving the brush head to rotate and clean the area to be cleaned.

[0120] The speed adjustment module is used to adjust the speed of the drive motor according to the relationship between the current cleaning intensity and the preset cleaning intensity corresponding to the target scene.

[0121] The cleaning equipment control device provided in this embodiment of the invention can execute the cleaning equipment control method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects for executing the method. Further functional descriptions of the various modules and units described above are the same as in the corresponding embodiments described above, and will not be repeated here.

[0122] Figure 9This is a schematic diagram of the controller structure of a cleaning device provided in an embodiment of the present invention.

[0123] The following is a detailed reference. Figure 9 The diagram illustrates a structural schematic suitable for implementing a controller in an embodiment of the present invention. The controller may include a processor (e.g., a central processing unit, graphics processing unit, etc.) 901, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 902 or a program loaded from memory 908 into random access memory (RAM) 903. The RAM 903 also stores various programs and data required for controller operation. The processor 901, ROM 902, and RAM 903 are interconnected via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0124] Typically, the following devices can be connected to I / O interface 905: input devices 906 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 907 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 908 including, for example, magnetic tapes, hard disks, etc.; and communication devices 909. Communication device 909 allows the controller to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 9 A controller with various devices is shown, but it should be understood that it is not required to implement or have all of the devices shown, and may alternatively implement or have more or fewer devices.

[0125] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 909, or installed from a memory 908, or installed from a ROM 902. When the computer program is executed by the processor 901, it performs the functions defined in the cleaning equipment control method of the embodiments of the present invention.

[0126] Figure 9 The controller shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0127] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the cleaning equipment control method shown in the above embodiments is implemented.

[0128] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0129] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for controlling cleaning equipment, characterized in that, The cleaning device includes a bristle assembly, the bristle assembly including a brush head and a plurality of bristle tufts disposed on the brush head, the length of the bristle tufts being adjustable, and the method including: When the pressure detection value of the brush head of the bristle assembly exceeds a preset threshold, an initial image of the area to be cleaned is acquired; Based on the initial image of the area to be cleaned, scene recognition is performed on the area to be cleaned to determine the target scene; Based on the target scenario, determine the bristle tuft length parameter of the bristle assembly; Based on the bristle length parameter, the bristle length of the brush assembly is adjusted, and the brush head is driven to rotate to clean the area to be cleaned; Adjusting the bristle length of the brush assembly based on the bristle length parameter includes: The current surface curvature in the initial image is obtained, and the distribution pattern of hair bundles in different regions on the bristle assembly is determined based on the surface curvature so that the distribution pattern is adapted to the current surface curvature. The hair tuft length of the first region with the longest hair tuft length in the distribution pattern is adjusted to the hair tuft length parameter corresponding to the target hair tuft length. Based on the target hair tuft length, the hair tuft length of other regions is adjusted according to the distribution pattern. The other regions are all regions on the brush assembly other than the first region. The cleaning device has multiple bristle bundles that are slidably disposed on the brush head along the length direction of the bristle bundles. The multiple bristle bundles are driven by multiple linear drive mechanisms, and the multiple linear drive mechanisms drive the multiple bristle bundles to present multiple distribution patterns on the brush head. The target tuft length is the length of each tuft that is adapted to the surface to be cleaned in the target scene.

2. The method according to claim 1, characterized in that, The step of determining the target scene by scene recognition of the area to be cleaned based on the initial image of the area to be cleaned includes: Feature extraction is performed on the initial image of the area to be cleaned to obtain image features of the area to be cleaned, wherein the image features include at least the texture features of the area to be cleaned; Based on the image features, a target scene associated with the image features is obtained by using a preset deep learning model for scene recognition.

3. The method according to claim 1, characterized in that, The step of determining the bristle tuft length parameter of the bristle component based on the target scenario includes: Based on the correspondence between different scenarios and hair tuft length, the target hair tuft length corresponding to the target scenario is determined.

4. The method according to claim 1, characterized in that, The method further includes: During the process of driving the brush head to rotate and clean the area to be cleaned, the current image of the area to be cleaned is acquired; The current image is compared with the target clean image of the target scene to determine the current cleanliness level; When it is determined that the current cleanliness level has reached the preset cleanliness level of the target scene, it is determined that the area to be cleaned has been cleaned, and the length of all bristles of the brush assembly is adjusted to the initial bristle length.

5. The method according to claim 1, characterized in that, The method further includes: During the process of driving the brush head to rotate and clean the area to be cleaned, the pressure change rate of the brush head in the area to be cleaned is obtained; Based on the correspondence between the preset pressure change rate and the preset scenario, the target scenario is updated, and the step of determining the bristle tuft length parameter of the bristle component based on the target scenario is returned.

6. The method according to claim 1, characterized in that, The cleaning device further includes a drive motor for driving the brush head to rotate, and the method further includes: During the process of driving the brush head to rotate and clean the area to be cleaned, the current cleaning intensity is obtained; Based on the relationship between the current cleaning intensity and the preset cleaning intensity corresponding to the target scene, the rotation speed of the drive motor is adjusted accordingly.

7. A cleaning equipment control device, characterized in that, The cleaning device includes a bristle assembly, the bristle assembly including a brush head and a plurality of bristle tufts disposed on the brush head, the length of the bristle tufts being adjustable; the device includes: The acquisition module is used to acquire an initial image of the area to be cleaned in response to the pressure detection value of the brush head of the bristle assembly exceeding a preset threshold. The recognition module is used to perform scene recognition on the area to be cleaned based on an initial image of the area to be cleaned to determine the target scene; The determining module is used to determine the bristle tuft length parameter of the bristle component based on the target scene; An adjustment module is used to adjust the bristle length of the brush assembly based on the bristle length parameter, and drive the brush head to rotate to clean the area to be cleaned; The adjustment module specifically includes: The current surface curvature in the initial image is obtained, and the distribution pattern of hair bundles in different regions on the bristle assembly is determined based on the surface curvature so that the distribution pattern is adapted to the current surface curvature. The hair tuft length of the first region with the longest hair tuft length in the distribution pattern is adjusted to the hair tuft length parameter corresponding to the target hair tuft length. Based on the target hair tuft length, the hair tuft length of other regions is adjusted according to the distribution pattern. The other regions are all regions on the brush assembly other than the first region. The cleaning device has multiple bristle bundles that are slidably disposed on the brush head along the length direction of the bristle bundles. The multiple bristle bundles are driven by multiple linear drive mechanisms, and the multiple linear drive mechanisms drive the multiple bristle bundles to present multiple distribution patterns on the brush head. The target tuft length is the length of each tuft that is adapted to the surface to be cleaned in the target scene.

8. A cleaning device, characterized in that, The cleaning device includes a bristle assembly, the bristle assembly including a brush head and a plurality of bristle tufts disposed on the brush head, the length of the bristle tufts being adjustable; the cleaning device also includes a controller, the controller comprising: A memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, the processor executing the computer instructions to perform the method of any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a computer to perform the method of any one of claims 1 to 6.

Images