Cleaning equipment control method and device and cleaning equipment

Abstract

The invention provides a control method and device of cleaning equipment and the cleaning equipment, and relates to the technical field of cleaning equipment. The cleaning equipment comprises a main machine body, a ground brush assembly, an image recognition device, a water pump assembly and a main draught fan. The floor brush assembly is rotationally connected with the main machine body; the image recognition device is arranged on the floor brush assembly, and the floor brush assembly comprises a rolling brush; the method comprises the steps that in the process that cleaning equipment executes a cleaning task, image information of a to-be-cleaned area is collected based on an image recognition device; under the condition that it is determined that the target particle garbage exists in front of the cleaning equipment based on the image information, the water pump assembly is controlled to be in a closed state, the main fan is controlled to operate based on the first suction force so as to clean the target particle garbage, efficient cleaning of the large particle garbage is achieved, and the cleaning effect is improved; wherein the first suction force is larger than the second suction force, and the second suction force is the suction force in the conventional cleaning mode.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of cleaning equipment, and in particular to a control method and device of a cleaning equipment and the cleaning equipment. BACKGROUND

[0002] With the increasing diversification of household cleaning scenarios, users have higher requirements for the ability of automatic cleaning equipment to handle complex garbage. As an intelligent device integrating suction, mopping and washing, the scrubber assembly of the scrubber, as the core executive mechanism, mainly realizes cleaning of the cleaning surface through the high-speed rotating roller brush combined with the airflow of the main air fan.

[0003] In the related art, the scrubber mainly relies on the close fit of the roller brush and the cleaning surface and the mechanical friction generated by the high-speed rotation to clean the granular garbage. For granular garbage, it is usually thrown by the roller brush and adsorbed by the airflow to be rolled into the sewage tank.

[0004] However, when facing larger or heavier particles such as food, pet dry food, food debris, etc., due to the small gap between the roller brush and the cleaning surface, the large particles are easily pushed rather than effectively sucked, resulting in incomplete cleaning, particle residue and other problems, affecting the cleaning efficiency and user experience. SUMMARY

[0005] The present application provides a control method and device of a cleaning equipment and the cleaning equipment, which pre-judges target granular garbage through image recognition, and links the cleaning equipment to turn off the water function and enhance the suction force, to realize efficient cleaning of large granular garbage and improve the cleaning effect.

[0006] In a first aspect, the present application provides a control method of a cleaning equipment, the cleaning equipment comprising: a main body, a scrubber assembly, an image recognition device, a water pump assembly and a main air fan; the scrubber assembly is rotationally connected with the main body; the image recognition device is arranged on the scrubber assembly, and the scrubber assembly comprises a roller brush; the method comprises:

[0007] During the execution of the cleaning task by the cleaning equipment, the image information of the cleaning area is collected based on the image recognition device;

[0008] In the case that it is determined based on the image information that there is target granular garbage in front of the cleaning equipment, the water pump assembly is controlled to be in an off state, and the main air fan is controlled to operate based on a first suction force to clean the target granular garbage;

[0009] Wherein, the first suction force is greater than the second suction force, and the second suction force is the suction force in the conventional cleaning mode.

[0010] In this way, the application automatically perceives the target granular garbage through image recognition and switches to the "water stop and strong suction" cleaning mode, effectively solving the problem of incomplete cleaning of granular matter and easy residue caused by the pushing and interference of the rolling brush and water flow in the prior art, and significantly improving the cleaning effect and completeness of the target granular garbage. Further, the need for user manual cleaning or repeated cleaning of the device due to residue of granular matter is avoided, making the cleaning process smoother and more efficient, and improving the overall efficiency of the cleaning task and user satisfaction.

[0011] Moreover, since the cleaning device can automatically decide and adjust the cleaning mode according to the actual situation of the front cleaning surface, i.e., whether it is target granular garbage, without manual intervention by the user, the cleaning device can autonomously cope with different cleaning scenarios, and the cleaning process is more intelligent and efficient, achieving intelligent scenario adaptability cleaning, thereby optimizing the user experience.

[0012] In addition, since the application only starts the first suction of high power and closes the water pump when it actually detects the target granular garbage that needs to be processed, rather than maintaining a high suction mode throughout, energy waste caused by high-power operation throughout is avoided, and a balance between effect and energy efficiency is achieved.

[0013] Optionally, the target granular garbage is heavy granular garbage, and the size of the heavy granular garbage is greater than or equal to a first threshold and less than a second threshold; the method further comprises:

[0014] In the case where it is determined based on the image information that there is heavy granular garbage in front of the cleaning device, the rolling brush is controlled to operate based on a first rotational speed; the first rotational speed is less than the second rotational speed, and the second rotational speed is the rotational speed in the normal cleaning mode.

[0015] In this way, during the cleaning of heavy granular garbage, by reducing the rotational speed of the rolling brush, the horizontal component of force generated when it contacts the granular matter is reduced, and by cooperating with the enhanced first suction, the granular matter can be more effectively prevented from being bounced or pushed away by the rolling brush, and the adsorption success rate is improved. Moreover, by introducing fine control of the size of the heavy granular garbage and the rotational speed of the rolling brush, the application can more accurately cope with heavy granular garbage of different sizes and qualities, and the adaptability and robustness of the cleaning device are enhanced. Therefore, through this cleaning mode of water stop, strong suction and speed reduction, an optimized parameter combination for heavy granular garbage is formed, and effective cleaning of the heavy granular garbage is achieved.

[0016] Optionally, the target granular garbage is light granular garbage, and the size of the light granular garbage is greater than or equal to a first threshold and less than a second threshold; the method further comprises:

[0017] In a case where it is determined based on the image information that there is light particle garbage in front of the cleaning device, the control is to control the roller brush to operate at a third rotating speed; the third rotating speed is greater than the second rotating speed, and the second rotating speed is a rotating speed in a normal cleaning mode.

[0018] In this way, in the process of cleaning the light particle garbage, the increase of the rotating speed of the roller brush enhances the physical stirring and throwing of the light particle garbage on the surface to be cleaned, and in combination with the enhanced suction force, the light particle garbage can be quickly and completely sucked away, preventing it from floating or adhering due to its lightness, and improving the cleaning efficiency of the light particle garbage. In addition, the present application can distinguish between heavy particle garbage and light particle garbage and apply different roller brush rotating speed strategies (speed reduction and speed increase), which reflects the self-adaptive adjustment of the present application according to the different physical characteristics of the garbage, and realizes more refined and intelligent cleaning control. The scheme of the present application not only solves the problem of pushing and shoving of heavy particles, but also optimizes the cleaning effect of light particles, and improves the comprehensiveness and adaptability of the overall cleaning ability.

[0019] Optionally, the target particle garbage is deformable garbage, and the size of the deformable garbage is greater than or equal to a first threshold value and less than a second threshold value; the roller brush has a first position and a second position in contact with the surface to be cleaned, and the pressure of the roller brush in contact with the surface to be cleaned at the second position is less than the pressure of the roller brush in contact with the surface to be cleaned at the first position; the method further comprises:

[0020] In a case where it is determined based on the image information that there is deformable garbage in front of the cleaning device, the control is to control the roller brush to be at the first position and operate at a fourth rotating speed; the fourth rotating speed is less than the second rotating speed, and the second rotating speed is a rotating speed in a normal cleaning mode.

[0021] Therefore, by combining the increase of the contact pressure with the surface to be cleaned and the reduction of the rotating speed, the interaction mode of the roller brush and the deformable garbage is optimized, the risk of deformation, splashing or adhesion of the garbage due to high-speed impact is reduced, and the removal rate and cleanliness of the deformable garbage are improved. And by adding the processing mode for deformable garbage, the range of garbage types that the cleaning device can effectively deal with is expanded, and the completion quality of the overall cleaning task and the user experience are improved. In addition, since the present application can adjust the control strategy according to the deformability of the garbage, it not only realizes the targeted processing of multiple types of garbage, but also improves the high adaptability and intelligence level of the cleaning device.

[0022] Optionally, the cleaning device further comprises a steam preparation device, and the steam preparation device sprays steam through a nozzle; the method further comprises:

[0023] In a case where it is determined based on the image information that the deformable garbage is adhered to the surface to be cleaned, the control is to control the steam preparation device to be in an open state to spray steam to the deformable garbage through the nozzle.

[0024] Thus, for the easily deformable garbage adhered to the surface to be cleaned, the application provides a physical and chemical auxiliary means-steam treatment to improve the removal effect of the adhered easily deformable garbage, avoid garbage residues or damage to the surface to be cleaned caused by forced peeling, and effectively solve the problem of difficult removal by relying on simple mechanical friction, thereby significantly improving the thoroughness and reliability of cleaning. Compared with the traditional mechanical scraping or chemical cleaning agent method, steam softening belongs to a physical softening process, without the need for strong scraping or corrosive chemicals, which can significantly reduce the risk of damage to the surface to be cleaned, avoid the impact of chemical residues on the environment and human health, and the high-temperature steam itself has a certain sterilization and disinfection effect, which helps to improve the hygiene of the cleaning area. Moreover, steam acts quickly and can soften the garbage in a short time, thereby shortening the processing time and improving the execution efficiency of the overall cleaning task. In addition, the image recognition technology is used to determine the garbage adhesion state in real time, and the steam spraying is automatically triggered, realizing intelligent response to complex cleaning scenes, reducing the need for manual intervention, and improving the autonomy and environmental adaptability of the cleaning device.

[0025] Optionally, the method further comprises:

[0026] generating first prompt information when it is determined based on the image information that the front of the cleaning device exists particle garbage with a size greater than or equal to a second threshold value.

[0027] Therefore, when it is determined based on image information analysis that the particle garbage existing in front of the cleaning device has a size greater than or equal to a preset second threshold value, first prompt information can be generated and output. Through active prompting, the user is timely informed of the current situation that the device cannot automatically handle, guiding the user to manually intervene (such as manually picking up), so that the user has a reasonable expectation of the working state and cleaning result of the cleaning device, avoiding misunderstanding caused by the device missing large garbage. Moreover, it can also avoid the cleaning device forcibly cleaning the oversized garbage that may block the suction port, entangle the roller brush, or damage the mechanism, preventing device failure, performance degradation, or cleaning failure. In addition, once the cleaning device is stuck by large particle garbage, the cleaning task will be interrupted and manual rescue is needed. Through early warning, the user has the opportunity to remove the obstacle before the device is trapped, ensuring that the cleaning task can be smoothly completed, thereby improving the reliability and user experience of the cleaning device.

[0028] Optionally, the cleaning device further comprises a display device, and the method further comprises:

[0029] acquiring state information of the cleaning device during execution of the cleaning task by the cleaning device;

[0030] determining a current working state of the cleaning device according to the state information, and visually displaying the current working state on the display device and / or generating second prompt information corresponding to the current working state.

[0031] In this way, by converting the cleaning device operating state into intuitive visualized information such as icons, progress, animations, etc. for display, the user can clearly perceive the working progress and real-time status of the cleaning device, enhancing the user's confirmation and control of the working effect of the cleaning device. Moreover, according to the state information, corresponding prompt information is generated, which can actively guide the user to intervene or maintain as necessary, improving cleaning efficiency and preventing damage to the device due to neglecting problems. In addition, such transparent and timely state feedback can also enable the user to understand the behavior of the device, such as why it automatically slows down or why the water pump assembly suddenly shuts down, reducing doubts or unease caused by switching the automatic operation mode of the device, thereby establishing the user's understanding and trust in the intelligent function and improving the smoothness and satisfaction of the overall user experience.

[0032] Optionally, the determination that the target particulate garbage exists in front of the cleaning device based on the image information comprises:

[0033] The image information is preprocessed to obtain a target image;

[0034] Target features in the target image are extracted, and the target features are compared with a preset feature library to determine that the target particulate garbage exists in front of the cleaning device;

[0035] The target features at least include a size greater than or equal to a first threshold value and less than a second threshold value.

[0036] In this way, by preprocessing, the image quality can be improved, and by target feature extraction and comparison with the feature library, the recognition algorithm is more targeted, so that the target particulate garbage can be effectively distinguished from the complex background, reducing the probability of misjudgment and omission. Moreover, through the explicit feature extraction and comparison process, the algorithm structure can be optimized, unnecessary calculation amount can be reduced, so that the image recognition chip can realize fast and real-time image recognition, improve the algorithm processing efficiency and real-time performance, and meet the demand for instant decision-making of the cleaning device during travel.

[0037] Optionally, the method further comprises:

[0038] The texture features of the target particulate garbage are determined based on the target features;

[0039] The garbage type of the target particulate garbage is determined based on the texture features, and the garbage type includes heavy particulate garbage, light particulate garbage, and easily deformable garbage.

[0040] In this way, by analyzing the texture features to infer the garbage type of the garbage, the cleaning device can surpass simple size recognition and achieve accurate judgment of the garbage, thereby realizing intelligent classification of the target granular garbage. Accurate garbage type classification is a prerequisite for adopting different control strategies for different types of garbage (heavy granular garbage, light granular garbage, and easily deformable garbage). By accurately identifying the garbage classification, the cleaning device can dynamically adjust cleaning parameters such as suction force, roller brush speed, or whether to start the steam device, etc. for garbage with different physical characteristics, thereby ensuring cleaning effectiveness while optimizing energy consumption and improving overall cleaning efficiency.

[0041] Optionally, the method further comprises:

[0042] After cleaning the target granular garbage, if it is detected again that there is residual granular garbage at the target position, the main air blower is controlled to clean the residual granular garbage based on the first suction force.

[0043] The target position is the area occupied by the target granular garbage before being cleaned.

[0044] In this way, through immediate review and secondary cleaning after cleaning, the situation that single cleaning may not be complete can be effectively addressed, the residual rate of granular garbage is significantly reduced, and the overall completion quality of the cleaning task is improved. Since the above steps introduce a result-based feedback mechanism, the cleaning process is no longer a one-time open-loop execution, but has a closed-loop control capability of "execution-verification-adjustment", which embodies the adaptability and robustness of the cleaning device, realizes closed-loop control and self-optimization of the cleaning process, reduces the need for subsequent inspection or rework by the user, and enhances the user's trust and satisfaction with the cleaning ability of the cleaning device.

[0045] In a second aspect, the application provides a control device of a cleaning device, the cleaning device comprising: a main body, a floor brush assembly, an image recognition device, a water pump assembly, and a main air blower; the floor brush assembly is rotationally connected to the main body; the image recognition device is arranged on the floor brush assembly, and the floor brush assembly comprises a roller brush; the control device comprises:

[0046] The acquisition module is configured to acquire image information of a to-be-cleaned area based on the image recognition device during execution of a cleaning task by the cleaning device.

[0047] The control module is configured to, in a case where it is determined based on the image information that there is target granular garbage in front of the cleaning device, control the water pump assembly to be in an off state, and control the main air blower to operate based on a first suction force to clean the target granular garbage.

[0048] The first suction force is greater than the second suction force, and the second suction force is a suction force in a regular cleaning mode.

[0049] In a third aspect, the present application provides a cleaning device, comprising: a main body, a floor brush assembly, an image recognition device, a water pump assembly, and a main air blower; the floor brush assembly is rotationally connected to the main body; the image recognition device is arranged on the floor brush assembly, and the floor brush assembly comprises a rolling brush;

[0050] The cleaning device is used to perform the method of any one of the first aspect.

[0051] It should be noted that the second aspect to the third aspect of the present application correspond to the technical solution of the first aspect of the present application, and the beneficial effects obtained by each aspect and the corresponding feasible implementation manner are similar, which will not be repeated here.

[0052] The control method and device of the cleaning device and the cleaning device provided by the present application can realize real-time collection of image information of a to-be-cleaned area during the execution of a cleaning task by arranging an image recognition device on the floor brush assembly, so as to identify whether there is target particulate garbage, such as a particulate matter with a larger size or a heavier mass, in front. Further, when the image information analysis determines that there is target particulate garbage, the cleaning device immediately adjusts the operating parameters, including controlling the water pump assembly to be closed, stopping the water spraying or wet mopping function, ensuring that the cleaning process is performed in a dry state, avoiding the adhesion of water flow to the particulate matter; controlling the main air blower to be switched to a higher first suction force, so that the large particulate matter is more easily sucked directly instead of being pushed by the rolling brush, thereby improving the cleaning efficiency of the target particulate garbage. In this way, by controlling the water outlet function to be closed and cooperating with the high-suction air blower, the floor brush assembly is in a "strong suction dry suction" state when passing through the area of the target particulate garbage. The high suction force can more effectively overcome the inertia and gravity of the particulate matter and suck it into the sewage tank, solving the problem that the particulate matter is pushed by the rolling brush and remains on the to-be-cleaned surface. BRIEF DESCRIPTION OF DRAWINGS

[0053] The accompanying drawings, which are incorporated into and form a part of the specification, illustrate an embodiment consistent with the present application and, together with the specification, serve to explain the principles of the application.

[0054] Figure 1 A partial structure schematic diagram of a cleaning device provided by an embodiment of the present application;

[0055] Figure 2 A structure schematic diagram of an image recognition device provided by an embodiment of the present application;

[0056] Figure 3 A position setting schematic diagram of an image recognition device provided by an embodiment of the present application;

[0057] Figure 4 An application scenario schematic diagram provided by an embodiment of the present application;

[0058] Figure 5 A flowchart of a control method of a cleaning device provided in an embodiment of the present application is shown in the figure.

[0059] Figure 6 A structural diagram of a control device of a cleaning device provided in an embodiment of the present application is shown in the figure.

[0060] Figure 7 A structural diagram of an electronic device provided in an embodiment of the present application is shown in the figure.

[0061] The specific embodiments of the present application have been shown in the above-described figures, and will be described in more detail hereinafter. These figures and the written description are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0062] The exemplary embodiments will be described in detail herein with reference to the attached drawings. The same reference numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments are not meant to represent all implementations consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present application as detailed in the appended claims.

[0063] In order to clearly describe the technical solutions of the embodiments of the present application, in the embodiments of the present application, the terms "first", "second", etc. are used to distinguish the same or similar items or elements with basically the same function and role. For example, the first rotation speed and the second rotation speed are merely used to distinguish different rotation speeds, and do not limit the sequence. Those skilled in the art can understand that the terms "first", "second", etc. do not limit the number and execution sequence, and the terms "first", "second", etc. also do not necessarily mean different.

[0064] It should be noted that in the present application, the words "exemplary" or "for example" are used to mean serving as an example, instance, or illustration. Any embodiment or design presented as "exemplary" or "for example" in the present application should not be interpreted as being more preferred or advantageous than other embodiments or designs. Rather, the use of the words "exemplary" or "for example" is intended to present concepts in a particular manner. The present application is not limited to the embodiments or designs presented as "exemplary" or "for example".

[0065] In the present application, "at least one" means one or more, and "multiple" means two or more. The association relationship of the associated objects is described by "and / or", which means that there can be three kinds of relationships, for example, A and / or B, which can represent the following three cases: A exists alone, A and B exist together, and B exists alone, where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the front and rear associated objects. "At least one" or similar expressions refer to any combination of these items, including single or multiple items in any combination. For example, at least one of a, b, or c can represent a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, and c can be single or multiple.

[0066] In the related art, the scrubber mainly relies on the close contact between the roller brush and the surface to be cleaned and the mechanical friction generated by high-speed rotation to generate mechanical friction. For granular garbage, it is usually thrown by the roller brush and adsorbed by airflow to be rolled into the sewage tank.

[0067] However, when facing larger size or heavier particles such as food, pet dry food, food debris, etc., due to the small gap between the roller brush and the cleaning surface, the large particles are easily pushed rather than effectively sucked, resulting in incomplete cleaning, particle residue, and other problems, affecting the cleaning efficiency and user experience.

[0068] To solve the above problems, the present application provides a control method of a cleaning device, which sets an image recognition device on the floor brush assembly. During the execution of the cleaning task by the cleaning device, the image information of the area to be cleaned is collected in real time to identify whether there is target granular garbage such as larger size or heavier particles in front. Further, when the image information analysis determines that there is target granular garbage, the cleaning device immediately adjusts the operating parameters, including controlling the water pump assembly to be closed, stopping the water spraying or wet mopping function, to ensure that the cleaning process is carried out in a dry state to avoid the adhesion of water flow to the particles; controlling the main air blower to switch to a higher first suction force, so that the large particles are more easily sucked directly rather than being pushed by the roller brush, thereby improving the cleaning efficiency of the target granular garbage. In this way, by controlling the water outlet function to be closed and cooperating with the high-suction air blower, the floor brush assembly is in a "strong suction dry suction" state when passing through the area of the target granular garbage. The high suction force can more effectively overcome the inertia and gravity of the particles and suck them into the sewage tank, solving the problem of particles being pushed by the roller brush and remaining on the surface to be cleaned.

[0069] It should be noted that the control method of the cleaning device provided by the present application is applied to a cleaning device, for example, Figure 1 A partial structure schematic diagram of a cleaning device provided by an embodiment of the present application is shown in Figure 1As shown, the cleaning device 100 comprises: a main body 101, a ground brush assembly 102, an image recognition device 103, a water pump assembly 104, and a main air blower 105; the ground brush assembly 102 is rotationally connected with the main body 101; the image recognition device 103 is arranged on the ground brush assembly 102, and the ground brush assembly 102 comprises a rolling brush 11.

[0070] Optionally, Figure 2 A structural schematic diagram of an image recognition device provided by an embodiment of the present application is shown in FIG. 2. Figure 2 As shown, the image recognition device 103 comprises a camera 12 and a gimbal assembly 13. The camera 12 can be a waterproof camera, which is used to capture garbage on a to-be-cleaned surface in a front area of the cleaning device 100 at a close distance, for example, Figure 3 A position setting schematic diagram of an image recognition device provided by an embodiment of the present application is shown in FIG. 3. Figure 3 As shown, the camera 12 is arranged on the ground brush assembly 102 through the gimbal assembly 13, and is 5-10 cm away from the to-be-cleaned surface. The gimbal assembly 13 can realize a range of activities of 160 degrees of horizontal rotation, 120 degrees of pitching, and 60 degrees of rolling, so as to drive the camera 12 to rotate.

[0071] Illustratively, the lens axis of the camera 12 is at an angle of 30° with the to-be-cleaned surface, so that the camera 12 can accurately cover the to-be-cleaned area 5-10 cm in front of the rolling brush 11.

[0072] Optionally, the camera 12 has a resolution of 1080P, a frame rate of 30 fps, a focal length of 2.8 mm, and a viewing angle of 80°, and has a fog-proof protective cover. Further, a light supplement assembly is used to supplement light in a dark environment, so as to ensure that the collected picture is clear, and thus the target features of the garbage, such as the texture of the particles and the circular profile of the particles, can be clearly determined, so as to avoid the loss of the target features due to the blurred picture quality. The light supplement assembly can be a white light emitting diode (Light Emitting Diode, LED), and the specific type of the light supplement assembly is not limited in the embodiment of the present application.

[0073] Illustratively, after the user starts the cleaning mode of the cleaning device 100, the camera 12 enters a working state, and is ready to collect image information at a resolution of 1080P and a frame rate of 30 fps, so that the camera 12 can collect 30 frames of RGB color images per second, so as to capture the garbage that is about to enter the rolling brush 11 in advance, and avoid the situation that the garbage is identified after entering the cleaning area, which leads to untimely cleaning. Optionally, the cleaning device 100 can also record the target features of the garbage, such as the color (such as the color of the particles), the shape (such as the circular shape of the particles), and the texture (such as the irregular crack texture).

[0074] Optionally, the camera 12 can also integrate an image recognition chip, which carries a lightweight Artificial Intelligence (AI) classification model, for real-time processing of image information collected by the camera 12, color, shape, texture, and other feature algorithm processing, and completing the rapid classification of garbage types.

[0075] For example, the image recognition chip can perform noise reduction, effective area cropping, and other processing on the image information, and then extract target features of the garbage, such as irregular crack texture features, circular contour features, and convex surface features on the surface of ceramic fragments, and compare the features with the features in the pre-stored feature library through the lightweight AI model, and determine the type of garbage by whether the matching degree is greater than a preset matching degree threshold. For example, the type of garbage can be hair, particles, liquid, etc. The size of the preset matching degree threshold is not limited in the embodiments of the present application. For example, the preset matching degree threshold is 85%.

[0076] Optionally, the cleaning device 100 further comprises a display device (not shown in the figure), and the image recognition chip can also send the result of identifying the type of garbage to the host of the cleaning device 100. On the one hand, the type of garbage is displayed on the display device, for example, taking the display device as a display screen, the controller of the host immediately displays the type of garbage on the display screen of the host in real time after receiving the "garbage type signal", such as displaying information such as "detecting particles" and "detecting liquid stains" on the screen, so that the user can intuitively grasp the garbage situation of the cleaning area.

[0077] On the other hand, the image recognition chip can also be linked to the cleaning strategy, such as increasing the suction force after identifying particles, to realize the precise adaptation of "recognition-cleaning strategy".

[0078] It should be noted that the embodiments of the present application do not limit the specific component type corresponding to the display device, which can be a component capable of presenting information in a visual form, for example, the display device can also be an LED, a digital tube, a character liquid crystal screen, etc.

[0079] Optionally, the roller brush 11 has a first position and a second position in contact with the surface to be cleaned. The pressure of the roller brush 11 in contact with the surface to be cleaned at the second position is less than the pressure of the roller brush 11 in contact with the surface to be cleaned at the first position.

[0080] In the embodiments of the present application, the first position can refer to the working position of the roller brush 11 adjusted to a relatively large contact pressure with the surface to be cleaned. At the first position, the roller brush 11 has a high normal pressure on the surface to be cleaned, thereby providing stronger physical friction, rolling or grabbing action.

[0081] The second position may refer to a working position where the rotary brush 11 is adjusted to have a relatively small contact pressure with the surface to be cleaned. At the second position, the normal pressure of the rotary brush 11 on the surface to be cleaned is low, so the physical action on the surface to be cleaned is gentler.

[0082] It can be understood that by controlling the switching of the rotary brush 11 between the first position and the second position, the rotary brush 11 can adapt to the cleaning requirements of garbage with different physical properties. For example, the first position is adopted for easily deformable garbage to enhance the rolling and winding effect, and in the conventional cleaning mode, the second position is adopted for cleaning tasks.

[0083] Optionally, the cleaning device 100 further includes a steam preparation device (not shown in the figure), and the steam preparation device sprays steam through a nozzle; for example, the steam preparation device is a boiler.

[0084] Optionally, the nozzle is arranged below the floor brush assembly 102, and the squeegee assembly is arranged in front of the rotary brush 11 for scraping and washing the surface to be cleaned.

[0085] Exemplarily, Figure 4 is a schematic diagram of an application scenario provided by an embodiment of the present application. As Figure 4 shown, taking a home scenario as an example, the cleaning device 100 can be a floor washer. This application scenario includes a floor washer and particulate garbage 200. For example, the particulate garbage 200 can be stones, soybeans, coins, etc.

[0086] The user starts the floor washer in the living room and selects the conventional cleaning mode to perform a cleaning task on the surface to be cleaned in the living room. At this time, the water pump assembly is in an on state to spray an appropriate amount of clean water or cleaning liquid onto the rotary brush or the surface to be cleaned; the main blower operates at a second suction force to perform wet wiping cleaning on the surface to be cleaned.

[0087] During the progress of the floor washer, the image recognition device arranged on the floor brush assembly continuously collects image information of the surface to be cleaned ahead. When the floor washer approaches or there is particulate garbage 200 on the surface to be cleaned ahead, the image recognition device can capture the image information containing the particulate garbage 200.

[0088] Furthermore, the floor washer processes and analyzes the image information, and determines that there is particulate garbage 200 ahead based on image features (such as specific size and shape). After confirming that there is particulate garbage 200 ahead, the floor washer immediately performs the following linkage control:

[0089] The water pump assembly is turned off, that is, the water spraying is stopped, which is to prevent the water flow from dispersing the particulate garbage 200 or making it adhere to the surface to be cleaned.

[0090] Increase the suction power of the main blower, that is, increase the suction power of the main blower from the second suction power to the first suction power. This process aims to generate a stronger airflow to overcome the gravity and inertia of the particulate waste 200 and effectively suck it into the sewage tank.

[0091] Optionally, after confirming the absence of particulate debris 200 based on image information collected by the image recognition device, or after a preset time or a certain distance, the floor scrubber can automatically return to its normal cleaning mode. This involves restarting the water pump assembly to resume wet mopping and adjusting the main fan suction to the second suction level. This allows the floor scrubber to continue cleaning other areas of the living room in normal mode while continuously detecting images to prepare for the next occurrence of particulate debris 200.

[0092] It should be noted that this application can also be applied to shopping malls, schools, and offices. The embodiments of this application do not limit the specific application scenarios; the above are merely illustrative examples.

[0093] It should be noted that the cleaning device 100 can be a floor scrubber or any smart handheld mobile device with cleaning function. This application embodiment does not specifically limit the type of cleaning device 100.

[0094] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0095] For example, Figure 5 This is a flowchart illustrating a control method for a cleaning device provided in an embodiment of this application. The control method for the cleaning device is applied to... Figures 1-3 The cleaning equipment shown, such as Figure 5 As shown, the control method for this cleaning equipment includes the following steps:

[0096] S501. During the cleaning process, the cleaning equipment collects image information of the area to be cleaned based on the image recognition device.

[0097] In this embodiment of the application, image information may refer to visual information collected by the image recognition device on the floor brush assembly of the cleaning equipment, which reflects the condition of the surface to be cleaned in the area to be cleaned. It may include information such as the texture, shape, color, and spatial distribution of the garbage. This embodiment of the application does not limit the specific content corresponding to the image information.

[0098] For example, during the process of the cleaning device performing a cleaning task according to a preset path or user instructions, the image recognition device integrated on the brush assembly continuously or periodically collects real-time image information of the area to be cleaned in front of the device, for example, a camera or a visual sensor collects image information of the area to be cleaned in front of the device at a resolution of 1080P and a frame rate of 30fps after entering the working state, so as to identify the garbage about to enter the roller brush in real time.

[0099] S502, in a case where it is determined based on the image information that there is target particulate garbage in front of the cleaning device, controlling the water pump assembly to be in an off state, and controlling the main air blower to operate based on a first suction force to clean the target particulate garbage.

[0100] The first suction force is greater than the second suction force, and the second suction force is a suction force in a conventional cleaning mode.

[0101] In the embodiments of the present application, the target particulate garbage can refer to solid particulate garbage that is relatively large in size and is difficult to be effectively sucked into the sewage tank due to the pushing of the roller brush in the conventional cleaning mode. For example, the target particulate garbage can include heavy particulate garbage, light particulate garbage, and easily deformable garbage.

[0102] The heavy particulate garbage can refer to solid particulate garbage that is relatively heavy in mass and falls within a specific range, i.e., between a first threshold and a second threshold. For example, the heavy particulate garbage can be stones, coins, ceramic fragments, pet dry food, etc.

[0103] The light particulate garbage can refer to solid particulate garbage that is relatively light in mass and falls within a specific range, i.e., between a first threshold and a second threshold. For example, the light particulate garbage can be plastic foam, potato chip fragments, etc.

[0104] The easily deformable garbage can refer to garbage that is easily deformed, broken, or adhered when subjected to mechanical forces such as roller brush impact or crushing, and falls within a specific range, i.e., between a first threshold and a second threshold. For example, the easily deformable garbage can be rice balls, gummy candies, etc.

[0105] The size includes the limitation of volume and diameter, for example, when the maximum diameter of the garbage is detected to be greater than 5mm and less than 20mm, and the volume is greater than 125mm³ and less than 300mm³, it is preliminarily determined to be target particulate garbage, and the recognition error is controlled within ±0.5mm.

[0106] It should be noted that the first threshold and the second threshold are quantitative standards for defining the size range of the target granular garbage by image information. The first threshold is the lower limit of the size of the particle to determine whether it is a large particle, and the second threshold is the upper limit of the size of the particle to determine whether it is too large to exceed the processing capacity of the device. The particle size between the first threshold and the second threshold is identified as the target granular garbage.

[0107] It should also be noted that the specific garbage types corresponding to the heavy granular garbage, the light granular garbage and the easily deformed garbage, and the specific values corresponding to the first threshold and the second threshold are not limited by the embodiments of the present application, and the above are only illustrative.

[0108] The first suction force can refer to a specific suction level of the main fan controlled to be activated when the target granular garbage is identified, which is higher than the regular cleaning mode. The first suction force is an enhanced suction force set to achieve effective suction of the target granular garbage. For example, the first suction force can be 15000-25000 Pa, and the embodiments of the present application do not limit the suction force corresponding to the first suction force.

[0109] Optionally, different target granular garbage can correspond to different first suction force, for example, the first suction force corresponding to the light granular garbage is 15000-18000 Pa, and the first suction force corresponding to the heavy granular garbage is 20000-25000 Pa.

[0110] The second suction force can refer to the suction level of the cleaning device by default when no target granular garbage is identified or when ordinary cleaning is performed, i.e. the suction force in the regular cleaning mode. The second suction force can be set according to the balance of cleaning effect, energy consumption, noise and other factors, and the embodiments of the present application do not limit the suction force corresponding to the second suction force.

[0111] The regular cleaning mode can refer to the standard working mode of the cleaning device. In the regular cleaning mode, the water pump assembly, the main fan suction force, the rolling brush rotating speed and other parameters are operated according to the preset default values, such as the second suction force and the second rotating speed, which are suitable for cleaning most ordinary dust, debris, dirt and the like.

[0112] For example, when the image information collected is identified by the image processing algorithm to exist the target granular garbage in front of the cleaning device, the cleaning device performs the preset control action, including: controlling the water pump assembly to be turned off, stopping the water spraying or wet mopping function, avoiding the water flow to make the particles adhere or increase the moving resistance, and controlling the suction force of the main fan to be raised to the preset first suction force to run, which improves the ability to adsorb large size particles. This series of controls aims to make the cleaning device clean the target granular garbage in the state of "no water and strong suction". The cleaning effect of stubborn granular garbage is significantly improved.

[0113] It should be noted that when any target particle garbage is detected, the cleaning device immediately closes the water function (delay <0.2 seconds), which can prevent the target particle garbage from sticking together (such as flour dough into paste) or the sewage tank from being blocked (such as wet garbage mixed with liquid into a lump), and after the target particle garbage is cleaned, it can be decided whether to restore the water wet mop according to the residual stains on the surface to be cleaned (such as whether there are food residue stains).

[0114] In this way, the application automatically senses the target particle garbage through image recognition and switches to the "water stop strong suction" cleaning mode, effectively solving the problem of incomplete cleaning of particle matter and easy residue caused by the pushing of the roller brush and the disturbance of the water flow in the prior art, and significantly improving the cleaning effect and completeness of the target particle garbage. Further, the situation of manual cleaning or repeated cleaning of the device due to particle residue is avoided, making the cleaning process more smooth and efficient, and improving the overall efficiency of the cleaning task and user satisfaction.

[0115] Moreover, since the cleaning device can automatically decide and adjust the cleaning mode according to the actual situation of the front surface to be cleaned, i.e., whether it is target particle garbage, without manual intervention, the cleaning device can independently cope with different cleaning scenes, and the cleaning process is more intelligent and efficient, realizing intelligent scene adaptability cleaning, thereby optimizing the user experience.

[0116] In addition, since the application only starts the first suction of high power and closes the water pump when it actually detects the target particle garbage that needs to be processed, rather than maintaining the high suction mode all the time, energy waste caused by high power operation all the time is avoided, and the balance between effect and energy efficiency is realized.

[0117] Optionally, the target particle garbage is heavy particle garbage, and the size of the heavy particle garbage is greater than or equal to a first threshold and less than a second threshold; the method further comprises:

[0118] In the case that it is determined based on the image information that there is heavy particle garbage in front of the cleaning device, the roller brush is controlled to operate based on a first rotating speed; the first rotating speed is less than a second rotating speed, and the second rotating speed is a rotating speed in a regular cleaning mode.

[0119] In the embodiment of the application, the first rotating speed can refer to a specific rotating speed of the roller brush that is controlled to be started when heavy particle garbage is identified, which is lower than the regular cleaning mode. The first rotating speed is used to reduce the pushing of the particle matter and reduce the abrasion caused by the friction between the roller brush and the hard object. For example, the first rotating speed can be 300 rpm, and the embodiment of the application does not limit the size of the rotating speed corresponding to the first rotating speed.

[0120] The second rotation speed can refer to a standard or default rotation speed of the rolling brush when the cleaning device is running in a normal cleaning mode. For example, the second rotation speed can be 400 rpm, and the embodiments of the present application do not specifically limit the rotation speed corresponding to the second rotation speed.

[0121] For example, when it is identified based on the image information that there is heavy particle garbage in front, in addition to controlling to turn off the water outlet function and enhance the suction force, the rotation speed of the rolling brush can also be actively reduced to a first rotation speed lower than that in the normal cleaning mode, so that when the cleaning device passes through the area where the heavy particle garbage is located, the forward pushing force of the particle garbage generated by the rolling brush is reduced, and the abrasion generated by the friction between the rolling brush and the hard object is reduced, so that the particle garbage is more easily sucked away by the enhanced airflow.

[0122] In this way, during the cleaning of the heavy particle garbage, by reducing the rotation speed of the rolling brush, the horizontal component force generated when the rolling brush contacts the particle garbage is reduced, and then by cooperating with the enhanced first suction force, the particle garbage can be more effectively prevented from being bounced or pushed away by the rolling brush, and the adsorption success rate is improved. Moreover, by introducing the fine control of the size of the heavy particle garbage and the rotation speed of the rolling brush, the present application can more accurately cope with heavy particle garbage of different sizes and qualities, and the adaptability and robustness of the cleaning device are enhanced. Therefore, by using the cleaning mode of water stop, strong suction and speed reduction, an optimized parameter combination for heavy particle garbage is formed, and the heavy particle garbage is effectively cleaned.

[0123] Optionally, the target particle garbage is light particle garbage, and the size of the light particle garbage is greater than or equal to a first threshold value and less than a second threshold value; the method further comprises:

[0124] In a case where it is determined based on the image information that there is light particle garbage in front of the cleaning device, the rolling brush is controlled to run based on a third rotation speed; the third rotation speed is greater than the second rotation speed, and the second rotation speed is a rotation speed in a normal cleaning mode.

[0125] In the embodiments of the present application, the third rotation speed can refer to a specific rotation speed higher than that in the normal cleaning mode, which is used for enhancing the adsorption of light particle garbage. In this way, by using strong airflow adsorption and fast rolling brush conveying, the garbage floating can be avoided. For example, the third rotation speed can be 500 rpm, and the embodiments of the present application do not specifically limit the rotation speed corresponding to the third rotation speed.

[0126] For example, when it is identified based on the image information that there is light particle garbage in front, in addition to controlling to turn off the water outlet function and enhance the suction force, the rotation speed of the rolling brush can also be actively increased to a third rotation speed higher than that in the normal cleaning mode, so that the light particle garbage can be more effectively sucked into the dirt suction channel by using the stronger throwing force generated by the rolling brush and the airflow.

[0127] In this way, in the process of cleaning light particle garbage, the increase of the rotation speed of the rolling brush enhances the physical stirring and throwing action of the rolling brush on the light particles on the surface to be cleaned, and in combination with the enhanced suction force, the light particles can be quickly and completely sucked away, preventing them from floating or adhering due to their light weight, and improving the cleaning efficiency of the light particle garbage. In addition, the present application can distinguish between heavy particle garbage and light particle garbage and apply different rolling brush rotation speed strategies (speed reduction and speed increase), which reflects the self-adaptive adjustment of the present application according to the different physical characteristics of the garbage, and realizes more refined and intelligent cleaning control. The scheme of the present application not only solves the problem of pushing and shoving heavy particles, but also optimizes the cleaning effect of light particles, and improves the comprehensiveness and adaptability of the overall cleaning ability.

[0128] Optionally, the target particle garbage is deformable garbage, and the size of the deformable garbage is greater than or equal to a first threshold and less than a second threshold; the rolling brush has a first position and a second position in contact with the surface to be cleaned, and the pressure of the rolling brush in contact with the surface to be cleaned at the second position is less than the pressure of the rolling brush in contact with the surface to be cleaned at the first position; the method further comprises:

[0129] In a case where it is determined based on the image information that there is deformable garbage in front of the cleaning device, the rolling brush is controlled to be at the first position and operates based on a fourth rotation speed; the fourth rotation speed is less than the second rotation speed, and the second rotation speed is a rotation speed in a normal cleaning mode.

[0130] In the present application, the fourth rotation speed can refer to a specific rotation speed of the rolling brush that is controlled to be activated when the deformable garbage is identified, which is lower than the normal cleaning mode. The fourth rotation speed is used to reduce the impact force on the deformable garbage. For example, the fourth rotation speed can be 200 rpm, and the present application does not limit the size of the fourth rotation speed.

[0131] Optionally, the fourth rotation speed can be the same as or different from the first rotation speed.

[0132] For example, when it is identified based on the image information that there is deformable garbage in front, in addition to controlling the water outlet function to be closed and the suction force to be enhanced, two cooperative control actions can be added: controlling the rolling brush to adjust to the first position with a larger contact pressure with the surface to be cleaned; and controlling the rolling brush to operate at a fourth rotation speed lower than the normal rotation speed. In this way, by increasing the contact pressure and reducing the rotation speed, the rolling brush applies a more stable and softer rolling and winding action to the deformable garbage, so that it is dispersed into small particles and then sucked in by the high suction force, avoiding blockage of the suction port by large pieces of garbage, and avoiding the garbage being flattened, flying or adhering due to high speed rotation.

[0133] Therefore, by increasing the contact pressure with the surface to be cleaned and reducing the rotation speed in combination, the interaction mode of the rolling brush with the easily deformed garbage is optimized, the risk of garbage deformation, splashing or adhesion due to high-speed impact is reduced, and the removal rate and cleanliness of the easily deformed garbage are improved. And by adding a processing mode for easily deformed garbage, the range of garbage types that the cleaning device can effectively deal with is expanded, and the completion quality of the overall cleaning task and the user experience are improved. In addition, since the present application can differentially adjust the control strategy according to the deformability of the garbage, not only the targeted processing of multiple types of garbage is realized, but also the high adaptability and intelligent level of the cleaning device are improved.

[0134] Optionally, the method further comprises:

[0135] In a case where it is determined based on the image information that the easily deformed garbage is adhered to the surface to be cleaned, the steam preparation device is controlled to be in an open state to spray steam to the easily deformed garbage through the nozzle.

[0136] It should be noted that the easily deformed garbage has formed a strong adhesion or combination with the surface to be cleaned due to its physical and chemical properties (such as viscosity, solidification after drying, etc.) and possible time factors, making it difficult to be directly removed by conventional rolling brush friction and air flow adsorption. The cleaning device can soften the easily deformed garbage by spraying steam from the steam preparation device and then clean it to ensure that the garbage is effectively cleaned.

[0137] For example, when the image information not only identifies that there is easily deformed garbage in front, but also further judges that the easily deformed garbage has adhered to the surface to be cleaned, in addition to controlling the water outlet function to be closed, the suction force to be enhanced, and the rolling brush to be reduced in pressure and speed, a control action of opening the steam preparation device can be added, that is, steam is sprayed to the area where the adhered easily deformed garbage is located through the nozzle. By using the heat and humidity of the steam to soften, dissolve or loosen the adhesion between the garbage and the surface to be cleaned, the adhesion state is destroyed, so that it can be effectively removed by the rolling brush and the suction force.

[0138] In this way, for the easily deformed garbage adhered to the surface to be cleaned, the application provides a physical and chemical auxiliary means-steam treatment, improves the removal effect of the adhering and easily deformed garbage, avoids garbage residues or damage to the surface to be cleaned caused by forced peeling, thereby effectively solving the problem that it is difficult to remove by relying on pure mechanical friction, and significantly improving the thoroughness and reliability of cleaning. Compared with the traditional mechanical scraping or chemical cleaning agent method, steam softening belongs to a physical softening process, without the need for strong scraping or corrosive chemicals, which can significantly reduce the risk of damage to the surface to be cleaned, avoid the influence of chemical residues on the environment and human health, and the high-temperature steam itself has a certain sterilization and disinfection effect, which helps to improve the sanitary condition of the cleaning area. Moreover, steam acts quickly and can soften the garbage in a short time, thereby shortening the processing time and improving the execution efficiency of the overall cleaning task. In addition, the image recognition technology is used to determine the garbage adhesion state in real time, and the steam spraying is automatically triggered, realizing intelligent response to complex cleaning scenes, reducing the need for manual intervention, and improving the autonomy and environmental adaptability of the cleaning equipment.

[0139] Optionally, the method further comprises:

[0140] generating first prompt information in a case where it is determined based on the image information that the front of the cleaning equipment exists particle garbage with a size greater than or equal to the second threshold.

[0141] In the embodiment of the application, the first prompt information can refer to specific notification information generated by the cleaning equipment when detecting particle garbage with a size greater than or equal to the second threshold and intended to convey to the user. The form is not limited to text prompts, graphical prompts, sound prompts, light prompts, voice prompts, etc., and the embodiment of the application does not limit the form of the first prompt information.

[0142] Optionally, the first prompt information can be displayed through the display device of the cleaning equipment, or can be reminded through voice to inform the user that the garbage volume is too large and exceeds the cleaning capacity to avoid equipment damage. For example, the voice reminder can be as follows: "metallic large particles are detected, the cleaning mode is adjusted", "super large particle garbage is found, please clean manually", etc.

[0143] It should be noted that the embodiment of the application does not limit the form and content of the first prompt information, and the above is only an example.

[0144] Therefore, when it is determined based on the image information analysis that the size of the particle garbage existing in front of the cleaning device is greater than or equal to the preset second threshold, the first prompt information can be generated and output. Through active prompting, the user is timely informed of the current encountered condition that cannot be automatically processed by the device, guiding the user to manually intervene (such as manual pickup), so that the user has a reasonable expectation of the working state and cleaning result of the cleaning device, avoiding misunderstanding caused by the device missing large garbage. Moreover, it can also avoid the cleaning device forcibly cleaning the oversized garbage that may block the suction port, wrap the roller brush or damage the mechanism, preventing device failure, performance degradation or cleaning failure. In addition, once the cleaning device is stuck by large particle garbage, the cleaning task will be interrupted and manual rescue is needed. Through early warning, the user has the opportunity to remove the obstacle before the device is trapped, ensuring that the cleaning task can be smoothly completed, improving the reliability and user experience of the cleaning device.

[0145] Optionally, the method further comprises:

[0146] In the process of the cleaning device performing the cleaning task, state information of the cleaning device is acquired;

[0147] A current working state of the cleaning device is determined according to the state information, and the current working state is visually displayed on the display device and / or the second prompt information corresponding to the current working state is generated.

[0148] In the embodiments of the present application, the state information can refer to data or logical signals that can reflect the condition of a specific aspect of the device generated or recorded by various sensors, controllers and functional modules inside the cleaning device during operation. For example, the state information can include image recognition results, roller brush motor current values, water tank liquid level sensor signals, fan rotation speed, fault codes, etc.

[0149] The current working state can refer to a general description of the current running situation of the device obtained based on the acquired state information after logical judgment. For example, the current working state can include the currently executed cleaning mode, abnormal warning, completion prompt, initial identification result, process state feedback, etc.

[0150] The second prompt information can refer to the message content generated to convey the current working state or operation suggestions, maintenance requirements, abnormal alarms related thereto to the user. Its form can refer to the description of the first prompt information, which will not be repeated here, only the forms of the two are different.

[0151] For example, the second prompt information can be displayed through the display device of the cleaning device, such as displaying a corresponding screen animation through a display screen, displaying a garbage type icon, a current suction force, a rotating speed parameter, and the like, and changing a color through an indicator light and a breathing light, so that the user can more intuitively understand the working state of the cleaning device. The embodiments of the present application do not limit the specific display content corresponding to the screen animation.

[0152] For example, in the process of executing a cleaning task by the cleaning device, the cleaning device continuously or periodically acquires various state information reflecting the running state of the device, and further, analyzes the state information according to a preset algorithm or mapping relationship, so as to determine the current working state of the cleaning device. For example, the current working state is "in regular cleaning", "in target particle garbage cleaning", "water shortage in the water tank", and the like.

[0153] After determining the current working state, the user can be fed back in two main ways. One is to visually display the current working state in the form of an icon, text, a progress bar, a color, and the like on the display device of the device. The other way is to generate second prompt information matched with the current working state, which can be conveyed to the user through voice, a bee sound, an application (APP) message push of a terminal device, and the like.

[0154] In this way, by converting the running state of the cleaning device into intuitive visual information such as an icon, a progress, an animation, and the like for display, the user can clearly perceive the working progress and real-time state of the cleaning device, and enhance the confirmation and control of the working effect of the cleaning device. Moreover, according to the state information, the corresponding prompt information is generated, which can actively guide the user to intervene or maintain as necessary, improve the cleaning efficiency, and prevent the damage of the device due to neglecting the problem. In addition, such transparent and timely state feedback can enable the user to understand the behavior of the device, such as why the device automatically slows down and why the water pump assembly suddenly shuts down, reduce doubts or anxiety caused by switching the automatic running mode of the device, thereby establishing the understanding and trust of the user for the intelligent function, and improving the smoothness and satisfaction of the overall use experience.

[0155] Optionally, determining that the target particle garbage exists in front of the cleaning device based on the image information comprises:

[0156] Preprocessing the image information to obtain a target image;

[0157] Extracting a target feature in the target image, and comparing the target feature with a preset feature library to determine that the target particle garbage exists in front of the cleaning device.

[0158] The target feature at least includes a size greater than or equal to a first threshold value and less than a second threshold value.

[0159] In the embodiments of the present application, preprocessing can refer to a series of standardization and optimization operations performed on the original image data before image feature extraction and analysis. The purpose is to eliminate or weaken noise, uneven illumination and other interference, enhance the region of interest, and provide higher quality and more consistent input images for subsequent processing. Preprocessing can include algorithms such as grayscale, filtering, denoising, contrast enhancement, binarization, cropping, etc. The specific algorithms corresponding to preprocessing are not limited in the embodiments of the present application.

[0160] For example, the image recognition chip integrated in the cleaning device can perform optimization processing on the collected image. For example, through a denoising algorithm, the image noise caused by sewage reflection and dust obstruction is filtered, and through a region of interest (ROI) cropping technique, only the garbage area of the cleaning surface is retained, and the brush shell, roller brush and other irrelevant areas are excluded, reducing the chip computing load and improving the processing efficiency.

[0161] After obtaining the optimized target image, the target features in the target image can be extracted through image analysis algorithms such as edge detection, texture analysis, color segmentation or feature extraction based on deep learning, and the extracted target features are compared and matched with the feature templates of the target granular garbage in the preset feature library. If the matching degree reaches the set threshold, it is determined that there is target granular garbage in front of the cleaning device.

[0162] The preset feature library can refer to a database or model set that is pre-established and stored in the cleaning device. The preset feature library contains standard feature data of the target granular garbage, which serves as a reference benchmark for real-time identification and comparison. For example, the standard feature data includes features corresponding to different types and forms of particulate matter.

[0163] For example, for soybeans with a diameter of 8 mm, the corresponding features can be circular contour features and convex surface features; for irregular nut shells, the corresponding features can be multi-angled features and asymmetric morphological features, which are clearly distinguished from small particle dust (diameter < 2 mm).

[0164] Optionally, the RGB (Red, Green, Blue) vision sensor of the camera can also be used to collect the two-dimensional profile of the garbage, and the three-dimensional point cloud model can be generated by combining the structured light sensor to calculate the length, width, height and volume of the garbage, and further determine whether there is target granular garbage.

[0165] Optionally, the image information is input into a pre-trained machine learning model to identify the garbage category in the image information, and further confirm whether there is target granular garbage.

[0166] The machine learning model can be a convolutional neural network model, a classification module, a YOLO model, etc. The specific algorithm model corresponding to the machine learning model is not limited in the embodiments of the present application.

[0167] In this way, through preprocessing, the image quality can be improved, and through target feature extraction and comparison with the feature library, the recognition algorithm is more targeted, so that the target granular garbage can be effectively distinguished from the complex background, and the probability of misjudgment and missed judgment is reduced. Moreover, through the explicit feature extraction and comparison process, the algorithm structure can be optimized, and unnecessary calculation amount can be reduced, so that the image recognition chip can realize fast and real-time image recognition, improve the algorithm processing efficiency and real-time performance, and meet the needs of instant decision-making of the cleaning device during travel.

[0168] Optionally, the method further comprises:

[0169] determining a texture feature of the target granular garbage based on the target feature;

[0170] determining a garbage type of the target granular garbage based on the texture feature, the garbage type including heavy granular garbage, light granular garbage, and easily deformable garbage.

[0171] In the embodiments of the present application, the texture feature can refer to a quantitative feature extracted from the image of the target granular garbage, which is used to describe the regularity, roughness, directionality, contrast, and other spatial distribution characteristics of the surface or internal structure of the target granular garbage. For example, a dense and smooth texture can be associated with heavy rigid particles, a loose and porous texture can be associated with light particles, and a viscous and filamentous texture can be associated with easily deformable garbage.

[0172] For example, the surface of ceramic fragments has an "irregular crack texture", the surface of pet food has a "regular embossed texture", and the surface of stones has a "coarse granular feel". These texture features are significantly different from the material of the surface to be cleaned (such as the smooth surface of ceramic tiles and the wood grain of wooden floors), so the garbage classification of the target granular garbage can be realized through texture feature recognition, and the material recognition accuracy can be improved.

[0173] Optionally, based on the texture feature of the target granular garbage, the specific garbage type to which the target granular garbage belongs is determined through algorithm analysis or comparison with a preset texture model library, i.e., the target granular garbage is classified into one of heavy granular garbage, light granular garbage, and easily deformable garbage.

[0174] In this way, by analyzing the texture features to infer the garbage type of the garbage, the cleaning device can surpass simple size recognition and achieve accurate judgment of the garbage, thereby realizing intelligent classification of the target granular garbage. Accurate garbage type classification is a prerequisite for adopting different control strategies for different types of garbage (heavy granular garbage, light granular garbage, and easily deformable garbage). By accurately identifying the garbage classification, the cleaning device can dynamically adjust cleaning parameters such as suction force, roller brush speed, or whether to start the steam device, etc. for garbage with different physical characteristics, thereby ensuring cleaning effectiveness while optimizing energy consumption and improving overall cleaning efficiency.

[0175] Optionally, the method further comprises:

[0176] After the target granular garbage is cleaned, if it is detected again that there is residual granular garbage at the target position, the main air blower is controlled to clean the residual granular garbage based on the first suction force.

[0177] The target position is the area occupied by the target granular garbage before being cleaned.

[0178] In the embodiments of the present application, the residual granular garbage can refer to the granular garbage that still exists at the target position (i.e., the area where the original garbage was located) and is detected again by the image recognition device after the cleaning device performs a targeted cleaning operation on the identified target granular garbage. The residual granular garbage can be a part of the original target granular garbage that was not completely removed, or it can be a fragment that fell off or dispersed from the original target granular garbage during the cleaning process. The present application does not limit the cause of the residual granular garbage.

[0179] For example, after completing a cleaning operation for the target granular garbage, the target position is continuously photographed at 10 frames per second based on the camera, and it is analyzed whether there is residual granular garbage in the photographed image. If residual granular garbage is detected, the cleaning mode of "point re-suction" is automatically started, i.e., the suction port position is adjusted to align with the target position, and the residual granular garbage is cleaned again at the first suction force until the re-inspection is passed without residual garbage.

[0180] Optionally, whether to start the cleaning mode of "point re-suction" can be determined by detecting the area of the residual granular garbage and the re-inspection pass rate, for example, if the area of the residual granular garbage is greater than 2 mm² or the re-inspection pass rate is less than 99%, the cleaning mode of "point re-suction" is started. The re-inspection pass rate can be determined by detecting the size of the residual granular garbage, the degree of dirt, or the number of residual granular garbage, and the present application does not limit it specifically.

[0181] In this way, immediate review and secondary cleaning after initial cleaning effectively address situations where a single cleaning might not be thorough, significantly reducing the residual rate of particulate waste and improving the overall quality of the cleaning task. Because the above steps introduce a result-based feedback mechanism, the cleaning process is no longer a one-time open-loop execution, but rather possesses a closed-loop control capability of "execution-verification-adjustment." This demonstrates the adaptability and robustness of the cleaning equipment, achieving closed-loop control and self-optimization of the cleaning process. It reduces the need for subsequent user inspections or rework, enhancing user trust and satisfaction with the cleaning equipment's capabilities.

[0182] In the foregoing embodiments, the control method for the cleaning equipment provided in this application has been described. To achieve the functions of the methods provided in the embodiments of this application, the cleaning equipment, as the executing entity, may include hardware structures and / or software modules, implementing the above functions in the form of hardware structures, software modules, or a combination of hardware structures and software modules. Whether a particular function is executed in the form of hardware structures, software modules, or a combination of hardware structures and software modules depends on the specific application and design constraints of the technical solution.

[0183] For example, Figure 6 This is a schematic diagram of the structure of a control device for a cleaning equipment provided in an embodiment of this application, as shown below. Figure 6 As shown, the control device 600 of the cleaning equipment is applied to the cleaning equipment, which includes: a main body, a floor brush assembly, an image recognition device, a water pump assembly, and a main fan; the floor brush assembly is rotatably connected to the main body; the image recognition device is mounted on the floor brush assembly, which includes a roller brush; the control device 600 of the cleaning equipment includes:

[0184] The acquisition module 601 is used to acquire image information of the area to be cleaned based on an image recognition device during the cleaning process of the cleaning equipment performing the cleaning task.

[0185] The control module 602 is used to control the water pump assembly to be shut off and to control the main fan to operate based on a first suction force to clean the target particulate debris when it is determined based on image information that there is target particulate debris in front of the cleaning equipment.

[0186] The first suction power is greater than the second suction power, which is the suction power in the normal cleaning mode.

[0187] Optionally, the target particulate waste is heavy particulate waste, and the size of the heavy particulate waste is greater than or equal to a first threshold and less than a second threshold; the control device 600 of the cleaning equipment further includes a first control module, which is used for:

[0188] In a case where it is determined based on the image information that heavy particulate garbage exists in front of the cleaning device, the control device controls the roller brush to operate based on a first rotating speed; the first rotating speed is less than a second rotating speed, and the second rotating speed is a rotating speed in a normal cleaning mode.

[0189] Optionally, the target particulate garbage is light particulate garbage, and the light particulate garbage has a size greater than or equal to a first threshold value and less than a second threshold value; the control device 600 of the cleaning device further comprises a second control module, which is configured to:

[0190] In a case where it is determined based on the image information that light particulate garbage exists in front of the cleaning device, the control device controls the roller brush to operate based on a third rotating speed; the third rotating speed is greater than the second rotating speed, and the second rotating speed is a rotating speed in a normal cleaning mode.

[0191] Optionally, the target particulate garbage is deformable garbage, and the deformable garbage has a size greater than or equal to the first threshold value and less than the second threshold value; the roller brush has a first position and a second position in contact with the surface to be cleaned, and the pressure of the roller brush in contact with the surface to be cleaned at the second position is less than the pressure of the roller brush in contact with the surface to be cleaned at the first position; the control device 600 of the cleaning device further comprises a third control module, which is configured to:

[0192] In a case where it is determined based on the image information that deformable garbage exists in front of the cleaning device, the control device controls the roller brush to be at the first position and operate based on a fourth rotating speed; the fourth rotating speed is less than the second rotating speed, and the second rotating speed is a rotating speed in a normal cleaning mode.

[0193] Optionally, the cleaning device further comprises a steam preparation device, and the steam preparation device sprays steam through a nozzle; the control device 600 of the cleaning device further comprises a fourth control module, which is configured to:

[0194] In a case where it is determined based on the image information that the deformable garbage is adhered to the surface to be cleaned, the control device controls the steam preparation device to be in an open state to spray steam to the deformable garbage through the nozzle.

[0195] Optionally, the control device 600 of the cleaning device further comprises a generation module, which is configured to:

[0196] In a case where it is determined based on the image information that the cleaning device is in front of the cleaning device, the control device controls the roller brush to operate based on a first rotating speed; the first rotating speed is less than a second rotating speed, and the second rotating speed is a rotating speed in a normal cleaning mode.

[0197] Optionally, the cleaning device further comprises a display device, and the control device 600 of the cleaning device further comprises a display module, which is configured to:

[0198] In a process of performing a cleaning task by the cleaning device, the control device acquires state information of the cleaning device;

[0199] The current working state of the cleaning device is determined according to the state information, and the current working state is visually displayed on the display device and / or second prompt information corresponding to the current working state is generated.

[0200] Optionally, the control module 602 comprises a determination unit, configured to:

[0201] The image information is preprocessed to obtain a target image.

[0202] Target features in the target image are extracted, and the target features are compared with a preset feature library to determine that the target particulate garbage exists in front of the cleaning device.

[0203] Optionally, the target features at least include a size greater than or equal to a first threshold and less than a second threshold.

[0204] Optionally, the control device 600 of the cleaning device further comprises a seventh control module, configured to:

[0205] The texture features of the target particulate garbage are determined based on the target features.

[0206] The garbage type of the target particulate garbage is determined based on the texture features, and the garbage type includes heavy particulate garbage, light particulate garbage and easily deformable garbage.

[0207] Optionally, the control device 600 of the cleaning device further comprises an eighth control module, configured to:

[0208] After the target particulate garbage is cleaned, if the residual particulate garbage is detected again at the target position, the main air fan is controlled to clean the residual particulate garbage based on the first suction force.

[0209] Optionally, the target position is a region occupied by the target particulate garbage before being cleaned.

[0210] It should be noted that the specific implementation principles and effects of the control device 600 of the cleaning device described above can be referred to the related descriptions and effects of the above-mentioned embodiments, which will not be described in detail here.

[0211] The embodiments of the present application also provide an electronic device, Figure 7 A structural schematic diagram of an electronic device provided by the embodiments of the present application is shown in Figure 7 The electronic device can include a processor 701 and a memory 702 in communication with the processor 701; the memory 702 stores a computer program; the processor 701 executes the computer program stored in the memory 702, so that the processor 701 executes the method described in any of the above embodiments.

[0212] The memory 702 and the processor 701 can be connected through the bus 703.

[0213] The embodiment of the present application further provides a computer readable storage medium, which stores computer execution instructions. The computer execution instructions are executed by a processor to implement the method described in any of the foregoing embodiments of the present application.

[0214] The embodiment of the present application further provides a chip running instructions, which is used to execute the method described in any of the foregoing embodiments and executed by an electronic device.

[0215] The embodiment of the present application further provides a computer program product, which comprises a computer program. The computer program is executed by a processor to implement the method described in any of the foregoing embodiments and executed by an electronic device.

[0216] In several embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented by other manners. For example, the apparatus embodiment described above is only schematic, for example, the division of the module is only a logical function division, and actual implementation can have another division manner, for example, a plurality of modules or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed each other can be indirect coupling or communication connection through some interfaces, apparatuses or modules, which can be electrical, mechanical or other forms.

[0217] The module described as a separate component can be or can not be physically separated, and the component displayed as a module can be or can not be a physical unit, that is, can be located in one place, or can be distributed to a plurality of network units. Part or all of the modules can be selected according to actual needs to implement the embodiment scheme.

[0218] In addition, each function module in each embodiment of the present application can be integrated in one processing unit, or each module can be physically present alone, or two or more modules can be integrated in one unit. The unit composed of the above modules can be realized in the form of hardware, or in the form of hardware plus software function unit.

[0219] The integrated module realized in the form of software function module can be stored in a computer readable storage medium. The software function module stored in a storage medium comprises a plurality of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute part of the steps of the method described in each embodiment of the present application.

[0220] It should be understood that the above-mentioned processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in combination with the application can be directly embodied as hardware processor execution, or executed by a combination of hardware and software modules in the processor.

[0221] The memory can include a high-speed random access memory (RAM), and can also include a non-volatile memory (NVM), such as at least one disk memory, and can also be a U disk, a mobile hard disk, a read-only memory, a magnetic disk or an optical disk, etc.

[0222] The bus can be an industry standard architecture (ISA) bus, a peripheral component interconnect (PCI) bus, or an extended industry standard architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, the bus in the drawings of the present application does not limit only one bus or one type of bus.

[0223] The aforementioned storage medium can be realized by any type of volatile or nonvolatile storage devices or a combination thereof, such as a Static Random-Access Memory (SRAM), an Electrically Erasable Programmable Read Only Memory (EEPROM), an Erasable Programmable Read-Only Memory (EPROM), a Programmable Read-Only Memory (PROM), a Read-Only Memory (ROM), a magnetic storage, a flash memory, a magnetic disk, or an optical disk. The storage medium can be any available medium that can be accessed by a general or special purpose computer.

[0224] An exemplary storage medium is coupled to the processor such that the processor can read information from, and write information to, the storage medium. Of course, the storage medium can be a part of the processor. Consistent with the teachings provided herein, the processor and the storage medium can be located in an ASIC. Alternatively, the processor and the storage medium can be located in a circuit.

[0225] It is noted that, for the aforementioned method embodiments, the sequences of the actions are described for simple description, but those skilled in the art should know that the present application is not limited to the described action sequences, because according to the present application, some steps can be performed in other sequences or simultaneously. In addition, those skilled in the art should know that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present application.

[0226] It is further noted that, although the steps in the flowcharts are shown in a sequence following the arrows, the steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in the present document, the execution of the steps is not necessarily limited to the order indicated by the arrows, and the steps can be executed in other orders. Moreover, at least some of the steps in the flowcharts can include multiple sub-steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times. The execution of the sub-steps or stages is not necessarily sequential, but can be performed in rotation or alternation with other steps or sub-steps or stages of other steps.

[0227] In the above embodiments, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the relevant description of other embodiments. Each technical feature of the above embodiments can be combined arbitrarily, and in order to make the description concise, each technical feature in the above embodiments is not described in all possible combinations, however, as long as the combination of these technical features does not exist contradictory, it should be considered as the scope disclosed in the specification.

[0228] Other embodiments of this application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. It is intended that the specification and examples be considered as exemplary only, with the true scope and spirit of the application being indicated by the following claims.

[0229] The above is only a specific implementation of the embodiments of the present application, but the protection scope of the embodiments of the present application is not limited to this, any change or replacement within the technical scope disclosed by the embodiments of the present application should be covered in the protection scope of the embodiments of the present application. Therefore, the protection scope of the embodiments of the present application should be subject to the protection scope of the claims.

Claims

1. A control method for cleaning equipment, characterized in that, The cleaning equipment includes: a main body, a floor brush assembly, an image recognition device, a water pump assembly, and a main fan; the floor brush assembly is rotatably connected to the main body; the image recognition device is disposed on the floor brush assembly, and the floor brush assembly includes a roller brush; the method includes: During the cleaning process, the image recognition device collects image information of the area to be cleaned. If, based on the image information, it is determined that there is target particulate debris in front of the cleaning equipment, the water pump assembly is controlled to be turned off, and the main fan is controlled to operate based on a first suction force to clean the target particulate debris; Wherein, the first suction power is greater than the second suction power, and the second suction power is the suction power in the normal cleaning mode.

2. The method according to claim 1, characterized in that, The target particulate waste is heavy particulate waste, and the size of the heavy particulate waste is greater than or equal to a first threshold and less than a second threshold; the method further includes: If, based on the image information, it is determined that there is heavy particulate waste in front of the cleaning device, the roller brush is controlled to operate at a first rotation speed; the first rotation speed is less than the second rotation speed, and the second rotation speed is the rotation speed in the normal cleaning mode.

3. The method according to claim 1, characterized in that, The target particulate waste is lightweight particulate waste, and the size of the lightweight particulate waste is greater than or equal to a first threshold and less than a second threshold; the method further includes: If it is determined based on the image information that there is light particulate waste in front of the cleaning device, the roller brush is controlled to operate at a third rotation speed; the third rotation speed is greater than the second rotation speed, which is the rotation speed in the normal cleaning mode.

4. The method according to claim 1, characterized in that, The target particulate waste is easily deformable waste, and the size of the easily deformable waste is greater than or equal to a first threshold and less than a second threshold; the roller brush has a first position and a second position that contact the surface to be cleaned, and the pressure of the roller brush contacting the surface to be cleaned when it is in the second position is less than the pressure of the roller brush contacting the surface to be cleaned when it is in the first position; The method further includes: If it is determined based on the image information that there is deformable debris in front of the cleaning device, the roller brush is controlled to be in the first position and run at a fourth rotation speed; the fourth rotation speed is less than the second rotation speed, and the second rotation speed is the rotation speed in the normal cleaning mode.

5. The method according to claim 4, characterized in that, The cleaning equipment further includes a steam generating device, which sprays steam through a nozzle; the method further includes: If, based on the image information, it is determined that the easily deformable waste is adhered to the surface to be cleaned, the steam generating device is turned on to spray steam onto the easily deformable waste through the nozzle.

6. The method according to claim 1, characterized in that, The method further includes: If, based on the image information, it is determined that there are particulate debris with a size greater than or equal to a second threshold in front of the cleaning equipment, a first prompt message is generated.

7. The method according to any one of claims 1-6, characterized in that, The cleaning equipment further includes a display device, and the method further includes: During the cleaning process, the status information of the cleaning equipment is acquired. The current working status of the cleaning equipment is determined based on the status information, and the current working status is displayed visually on the display device and / or a second prompt message corresponding to the current working status is generated.

8. The method according to claim 1, characterized in that, The step of determining that there is target particulate waste in front of the cleaning equipment based on the image information includes: The image information is preprocessed to obtain the target image; Extract target features from the target image and compare the target features with a preset feature library to determine that there is target particulate waste in front of the cleaning equipment; The target feature includes at least a size greater than or equal to a first threshold and less than a second threshold.

9. The method according to claim 8, characterized in that, The method further includes: The texture features of the target particulate waste are determined based on the target features; The waste type of the target particulate waste is determined based on the texture features. The waste type includes: heavy particulate waste, light particulate waste, and easily deformable waste.

10. The method according to claim 1, characterized in that, The method further includes: After cleaning the target particulate waste, if residual particulate waste is detected again at the target location, the main fan is controlled to clean the residual particulate waste based on the first suction force. The target location is the area occupied by the target particulate waste before it was cleaned up.

11. A control device for a cleaning equipment, characterized in that, The cleaning equipment includes: a main body, a floor brush assembly, an image recognition device, a water pump assembly, and a main fan; the floor brush assembly is rotatably connected to the main body; the image recognition device is mounted on the floor brush assembly, and the floor brush assembly includes a roller brush; the control device includes: The acquisition module is used to acquire image information of the area to be cleaned based on the image recognition device during the cleaning process of the cleaning equipment; The control module is used to control the water pump assembly to be turned off and to control the main fan to operate based on a first suction force when it is determined based on the image information that there is target particulate debris in front of the cleaning equipment, so as to clean the target particulate debris. Wherein, the first suction power is greater than the second suction power, and the second suction power is the suction power in the normal cleaning mode.

12. A cleaning device, characterized in that, The cleaning equipment includes: a main body, a floor brush assembly, an image recognition device, a water pump assembly, and a main fan; the floor brush assembly is rotatably connected to the main body; the image recognition device is mounted on the floor brush assembly, and the floor brush assembly includes a roller brush; The cleaning equipment is used to perform the method as described in any one of claims 1-10.

Images