Control method of cleaning apparatus and cleaning apparatus

Abstract

The application discloses a control method of a cleaning device and the cleaning device, and relates to the field of intelligent cleaning. The method comprises the following steps: determining material information of a target object in a cleaning area, wherein the material information is used for representing the material of the target object; further, determining initial cleaning parameters corresponding to the cleaning area based on the material information and an initial model, wherein the initial model is a model determined based on known training data, and the initial model is used for obtaining the initial cleaning parameters of the cleaning device based on the initial data; and further, cleaning the cleaning area based on the initial cleaning parameters. Through the determination of the material information, the material information is input into the initial model to obtain corresponding cleaning parameters, and the cleaning area is further cleaned based on the cleaning parameters, so that the cleaning of different materials and different degrees of dirt is realized, and the cleaning effect of the cleaning device is improved.

Description

Technical Field

[0001] This application relates to the field of intelligent cleaning, and more particularly to a control method for a cleaning device and a cleaning device. Background Technology

[0002] With the development of artificial intelligence and the increasing number of AI devices entering people's lives, cleaning equipment, as a major AI device in daily life, can automatically complete cleaning tasks.

[0003] In related technologies, in a scene to be cleaned, cleaning equipment usually cleans the entire scene in a single operating mode corresponding to a preset cleaning mode; however, the floors in the scene are often quite complex. For example, in a home scene, the flooring in different areas is different, which leads to poor cleaning effect of the cleaning equipment in some areas. Summary of the Invention

[0004] This application provides a control method and cleaning equipment for a cleaning device, which can solve the technical problem of poor cleaning effect of the cleaning device on certain areas of the entire scene.

[0005] In a first aspect, a control method for a cleaning device is provided, comprising: determining the material information of a target object in a cleaning area, wherein the material information is used to characterize the material of the target object; determining initial cleaning parameters corresponding to the cleaning area based on the material information and an initial model, wherein the initial model is a model determined based on known training data; and cleaning the cleaning area based on the initial cleaning parameters.

[0006] It should be understood that the initial model is a model determined based on known training data; the cleaning parameters corresponding to the cleaning area are determined based on the already trained initial model, such as the initial cleaning parameters, which not only provides more accurate cleaning parameters but also improves data processing speed.

[0007] The control method of the cleaning equipment determines the material information and inputs it into the initial model to obtain the corresponding cleaning parameters. Based on these cleaning parameters, the cleaning area is cleaned to achieve cleaning of different materials and different levels of dirt, thereby improving the cleaning effect of the cleaning equipment.

[0008] In one possible implementation, after cleaning the cleaning area based on initial cleaning parameters, a first degree of cleanliness of the cleaning area is determined; the initial model is adjusted based on the first degree of cleanliness to determine a target model; target cleaning parameters are determined based on the target model, and the cleaning area is cleaned based on the target cleaning parameters.

[0009] In this case, in one possible implementation, the method further includes: if the first degree of cleanliness does not reach the preset degree of cleanliness, adjusting the initial cleaning parameters; and determining the second degree of cleanliness corresponding to the clean area based on the cleaning of the clean area using the adjusted initial cleaning parameters; and when the second degree of cleanliness reaches the preset degree of cleanliness, adjusting the initial model based on the corresponding material information and the adjusted initial cleaning parameters, and determining the target model.

[0010] By analyzing the cleaning levels in actual use, such as the relationship between the first cleaning level and the preset cleaning level, the initial model is adjusted to make the adjusted target model more suitable for the user's application scenario, thereby further improving the cleaning effect.

[0011] In one possible implementation, determining the material information of the target object in the cleaning area includes:

[0012] Obtain initial data corresponding to the cleaning area, including at least material identification data, which is data collected on the material of the target object; determine the material information of the cleaning area based on the material identification data; or,

[0013] Obtain initial data corresponding to the cleaning area, including at least material identification data and resistance data; determine the material information of the cleaning area based on the material identification data and resistance data.

[0014] Different methods for determining material information have varying degrees of accuracy and processing speed. The appropriate material information determination process can be determined based on the specific application.

[0015] In this case, in one possible implementation, the initial cleaning parameters corresponding to the cleaning area can be determined based on the material information, initial data, and initial model. The initial data may also include information about the degree of dirt on the target object within the cleaning area.

[0016] In one possible implementation, the initial data includes ultrasonic data, imaging data, rotational speed data, and current data, comprising: acquiring ultrasonic data, imaging data, rotational speed data, and current data, wherein the imaging data includes at least an image or video corresponding to the cleaned area; determining material identification data based on the ultrasonic data and imaging data; and determining resistance data based on the rotational speed data and current data.

[0017] In one possible implementation, the initial data also includes location data, and the method further includes: constructing a spatial map of the space to be cleaned corresponding to the cleaning area based on the location data, wherein the space to be cleaned includes the cleaning area; after identifying the material information of the target object in the cleaning area, determining the association between the material information and the target object and the spatial map; and updating the spatial map based on the association, so that the cleaning equipment cleans based on the updated spatial map.

[0018] By creating a spatial map of the target object with material information, the efficiency of subsequent cleaning processes of cleaning equipment can be improved, thus enhancing the user experience.

[0019] In a second aspect, a control device for a cleaning equipment is provided, including a unit for performing the control method of any of the cleaning equipment in the first aspect.

[0020] Thirdly, a cleaning device is provided, including a sensor module, a cleaning module, a model module, and a control module;

[0021] The sensor module is used to collect initial data corresponding to the cleaning area, which is the area corresponding to the location of the cleaning equipment.

[0022] The control module is used to perform the following: determine the material information of the target object in the cleaning area. The material information is determined through initial data and is used to characterize the material of the target object; send the material information to the model module; receive the initial cleaning parameters fed back by the model module and send the initial cleaning parameters to the cleaning module.

[0023] The cleaning module is used to clean the cleaning area based on the initial cleaning parameters;

[0024] The model module is used to determine the initial cleaning parameters corresponding to the cleaning area based on material information and an initial model. The initial model is a model determined based on known training data.

[0025] In one possible implementation, the control module is also used to perform: determining the first cleanliness level of the cleaning area; if the first cleanliness level does not reach the preset cleanliness level, adjusting the initial cleaning parameters, and sending the material information and the adjusted initial cleaning parameters to the model module; receiving the target cleaning parameters fed back by the model module, and sending the target cleaning parameters to the cleaning module;

[0026] The cleaning module is used to clean the cleaning area based on the target cleaning parameters;

[0027] The model module is also used to determine the target model based on adjusting the initial model, and to determine the target cleaning parameters based on the target model.

[0028] In one possible implementation, the sensor module includes an ultrasonic sensor, a speed sensor, and a current sensor; the ultrasonic sensor is used to acquire ultrasonic data of the target object in the cleaning area, and the material identification data is determined at least by the ultrasonic data, which is part of the initial data; the speed sensor is used to detect the speed data of the motor in the cleaning equipment; the current sensor is used to detect the current data of the motor; the resistance data is determined by the speed data and the current data, which is part of the initial data.

[0029] In one possible implementation, the sensor module further includes a camera; the camera is used to acquire shooting data, which includes at least an image or video corresponding to the cleaned area; the material identification data is determined by the ultrasonic data and the shooting data.

[0030] In one possible implementation, the sensor module also includes a radar sensor and a gyroscope;

[0031] Radar sensors are used to detect the positional characteristics of objects around the cleaning equipment, including the object's velocity, distance, and orientation; gyroscopes detect the dynamic characteristics of objects around the cleaning equipment, including the object's angular velocity and angular changes; based on the positional and dynamic characteristics, positioning data is determined.

[0032] The control module is also used to perform the following: based on the positioning data, construct a spatial map of the space to be cleaned corresponding to the cleaning area, the space to be cleaned including the cleaning area.

[0033] In one possible implementation, the control module is also used to perform: determining the association between the material information and the target object and the spatial map; and updating the spatial map based on the association so that the cleaning equipment can perform cleaning based on the updated spatial map.

[0034] Fourthly, a computer-readable storage medium is provided, the computer-readable storage medium storing computer program code, which, when executed, performs the control method of any of the cleaning devices in the first aspect.

[0035] Fifthly, a computer program product is provided, the computer program product comprising: computer program code, which, when executed, performs the control method of any of the cleaning devices in the first aspect.

[0036] It is understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant descriptions in the first aspect mentioned above, and will not be repeated here. Attached Figure Description

[0037] Figure 1 This is a flowchart of the control method for the cleaning equipment provided in the embodiments of this application;

[0038] Figure 2 This is a flowchart of the control method for the cleaning equipment provided in the embodiments of this application;

[0039] Figure 3 This is a flowchart of the control method for the cleaning equipment provided in the embodiments of this application;

[0040] Figure 4 This is a flowchart of adjusting the initial model in the control method of the cleaning equipment provided in this application embodiment;

[0041] Figure 5 This is a schematic diagram of the control device for the cleaning equipment provided in the embodiments of this application;

[0042] Figure 6 This is a schematic diagram of the structure of the cleaning equipment provided in the embodiments of this application;

[0043] Figure 7 This is a structural diagram of the cleaning equipment provided in the embodiments of this application. Detailed Implementation

[0044] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0045] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0046] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0047] With the development of artificial intelligence and the increasing number of AI devices entering people's lives, cleaning equipment, as a major AI device in daily life, can automatically complete cleaning tasks.

[0048] In a scenario to be cleaned, the cleaning equipment typically cleans the entire scenario using a single operating mode corresponding to a preset cleaning mode; for example, the cleaning equipment cleans the entire scenario using the suction power of the fan at a fixed level, the speed of the roller brush, and the speed of movement.

[0049] However, the floors in real-world application scenarios are often quite complex. For example, in a home setting, different areas may have different types of flooring, such as wood flooring, tiles, or carpets and rugs. If a single operating mode is used to clean all the different floors in the entire scenario, the cleaning equipment may not be effective in cleaning certain areas.

[0050] To address the aforementioned problems, this application proposes a control method and a cleaning device for a cleaning equipment. The control method includes: determining the material information of a target object in a cleaning area, where the material information characterizes the material of the target object; further, determining initial cleaning parameters corresponding to the cleaning area based on the material information and an initial model, wherein the initial model is a model determined based on known training data, and this initial model is used to obtain the initial cleaning parameters of the cleaning equipment based on the aforementioned initial data; and further, cleaning the cleaning area based on the initial cleaning parameters. By determining the material information and inputting it into the initial model to obtain the corresponding cleaning parameters, and further cleaning the cleaning area based on these cleaning parameters, the cleaning equipment can effectively clean different materials and levels of dirt, thereby improving its cleaning efficiency.

[0051] The following is combined Figures 1 to 4 The control method for the cleaning equipment provided in the embodiments of this application will be described in detail.

[0052] Figure 1 This is a flowchart of a control method for a cleaning device provided in an embodiment of this application. Figure 1 As shown, the control method includes the following steps:

[0053] S110. Determine the material information of the target object in the cleaning area.

[0054] Material information is used to characterize the material of the target object. This target object can refer to materials laid on the ground, such as flooring, carpets, and mats.

[0055] S120. Based on material information and the initial model, determine the initial cleaning parameters corresponding to the cleaning area.

[0056] The initial model is a model determined based on known training data. For example, the initial model can be a neural network model or a mathematical model. It is a model determined by continuously training the cleaning equipment with known training data during the research and development process. In other words, the cleaning equipment already has this initial model, and the initial cleaning parameters are determined based on this model.

[0057] The known training data includes material identification data and resistance data for different materials. This data is then input into the neural network model, which outputs parameters applicable to cleaning. Through continuous training, the cleaning level corresponding to the output parameters is improved, and the parameters of the neural network model are determined.

[0058] Input the material information into the initial model and output the initial cleaning parameters corresponding to the cleaning area.

[0059] S130: Clean the cleaning area based on the initial cleaning parameters.

[0060] The cleaning module of the cleaning equipment can be controlled based on the initial cleaning parameters. The control commands corresponding to the initial cleaning parameters are used to control the cleaning module to clean the cleaning area.

[0061] The control method of the cleaning equipment determines the material information and inputs it into the initial model to obtain the corresponding cleaning parameters. Based on these cleaning parameters, the cleaning area is cleaned to achieve cleaning of different materials and different levels of dirt, thereby improving the cleaning effect of the cleaning equipment.

[0062] The above embodiments focus on how the cleaning equipment improves cleaning efficiency, in order to enhance the adaptability of the cleaning equipment to various application scenarios and improve the cleaning capabilities of the cleaning equipment. Figure 2 This is a flowchart of a control method for a cleaning device provided in an embodiment of this application. Figure 2 As shown, the control method includes the following steps:

[0063] S210. Obtain the initial data corresponding to the cleaning area, including material identification data and resistance data.

[0064] It should be understood that the cleaning equipment gradually cleans the corresponding space of the entire scene while moving. The entire scene contains multiple cleaning areas, that is, it cleans each cleaning area in the space in order to achieve the cleaning of the entire scene.

[0065] The cleaning area refers to the area corresponding to the location of the cleaning equipment. This area can be the area covered by the cleaning module of the cleaning equipment, the area covered by the cleaning equipment itself, or the area within a preset range surrounding the cleaning equipment.

[0066] If the cleaning area refers to the area covered by the cleaning module in the cleaning equipment, then the cleaning module and sensor module in the cleaning equipment can be set in the same area to improve subsequent judgments based on initial data.

[0067] For example, if the area projected onto the ground by the cleaning equipment is 40cm*40cm, the cleaning area can be either that 40cm*40cm area or an area that includes that 40cm*40cm area and reaches 60cm*60cm.

[0068] The initial data includes material identification data and resistance data. The material identification data is obtained by the sensors in the cleaning equipment that identify the materials, and the resistance data is obtained by detecting the motor in the cleaning equipment.

[0069] It should be understood that material identification data may include one or more types of data.

[0070] In some embodiments, the accuracy of material identification can be improved by increasing the variety of types in the material identification data.

[0071] In some embodiments, material identification can be performed using material identification data containing a type of data, thereby enhancing the device's computing power, improving data processing efficiency, and increasing the overall efficiency of the device.

[0072] It should also be understood that there is more than one type of motor in cleaning equipment, including at least a first motor that controls the suction and a second motor that controls the roller brush. Therefore, the resistance data includes multiple data corresponding to at least the fan resistance data and the roller brush resistance data.

[0073] In some embodiments, a third motor for controlling movement is also included; therefore, the resistance data also includes various data corresponding to the movement resistance data.

[0074] In some embodiments, the initial data may include ultrasonic data, imaging data, rotational speed data, and current data, wherein the material identification data is determined by the ultrasonic data, or by the ultrasonic data and imaging data, and the resistance data is determined by the rotational speed data and current data.

[0075] Ultrasonic data refers to data on the varying echo intensities produced by different materials, while the captured data includes at least an image or video of the cleaned area. Therefore, material identification data can be determined based on ultrasonic data, or a combination of ultrasonic data and captured data.

[0076] It should be understood that combining ultrasonic data and imaging data improves the accuracy of material identification.

[0077] In some embodiments, the rotational speed of the motor is detected by measuring its rotational speed and obtaining speed data. This can be achieved by using pulse signals output from a coaxial grating. For example, the coaxial grating consists of a series of grating stripes, which are coaxially mounted with the motor's rotating shaft. When the motor rotates, the grating stripes pass through a photoelectric sensor or other detection device, generating a series of pulse signals. The frequency of these pulse signals is proportional to the motor's rotational speed. By counting or timing the pulse signals, the motor's rotational speed or position can be determined. In other words, the faster the motor rotates, the denser the pulses.

[0078] Motor speed can be detected through open-loop or closed-loop control. In open-loop control, the greater the resistance, the greater the speed, and open-loop control has the characteristic of fast response. In closed-loop control, the greater the resistance, the larger the pulse width modulation (PWM) duty cycle needs to be. Closed-loop control introduces feedback signals, compares the output with the desired target, and adjusts according to the comparison results to correct deviations and improve control accuracy.

[0079] Current data can be determined by a sampling resistor connected in series in the motor circuit. The voltage value of the sampling resistor is converted into a current value. The greater the resistance, the greater the current.

[0080] Therefore, based on the rotational speed data and current data, the resistance data is determined, which can be used to determine the subsequent material information.

[0081] S220. Based on the initial data, identify the material information of the target object in the cleaning area.

[0082] As described above, the initial data includes material identification data and resistance data. For this step, the material information of the target object in the cleaning area can be identified based on the material identification data in the initial data, or the material identification data and resistance data in the initial data can be used to identify the material information of the target object in the cleaning area.

[0083] The target object can refer to materials laid on the ground, such as flooring, carpets, and mats.

[0084] For example, carpets come in many varieties. Based on their material, they can be categorized as wool carpets, synthetic fiber carpets, handmade carpets, and blended carpets. Based on the length of their pile, they can be categorized as long-pile carpets and short-pile carpets. Therefore, the resistance data obtained by cleaning equipment will differ depending on the type of carpet. Thus, based on the material identification data and resistance data in the initial data, the material information of the target object in the cleaning area can be identified, further improving the accuracy of material information identification in the cleaning area.

[0085] S230. Based on material information, initial data, and initial model, determine the initial cleaning parameters corresponding to the cleaning area.

[0086] The initial model is determined based on known training data.

[0087] Input the material information and initial data into the initial model, and output the initial cleaning parameters corresponding to the cleaning area.

[0088] Based on the above process, the module corresponding to the initial model is set in the cleaning equipment so that the cleaning equipment can determine the initial cleaning parameters corresponding to the material information and initial data based on the initial module.

[0089] In this embodiment of the application, by embedding the initial module into the cleaning device, the cleaning device's ability to clean the entire area during initial use is improved, thereby enhancing the cleaning effect.

[0090] S240. Adjust the initial model based on the initial cleaning parameters corresponding to the first degree of cleanliness of the cleaning area.

[0091] It should be understood that during the cleaning process, the initial module adjusts the parameters of the initial model by comparing it with previously known training data, so that the cleaning equipment can be better adapted to actual cleaning scenarios.

[0092] When cleaning a clean area based on initial cleaning parameters, a first degree of cleanliness can be determined for that clean area, which represents the degree of cleanliness of the clean area.

[0093] Based on the initial cleanliness level of the current cleaning area, the parameters of the initial model are adjusted to improve the adaptability of the adjusted initial model. This allows for adaptive adjustment of the initial model's parameters to different materials and levels of dirt, thereby enhancing the cleaning effect of the cleaning equipment.

[0094] S250. Based on the adjusted initial model, determine the target model.

[0095] After adjusting the parameters of the initial model, the corresponding model becomes the target model. The target cleaning parameters can be determined through the target model, and the cleaning area can be cleaned based on the target cleaning parameters. Compared with the initial cleaning parameters, the cleaning ability corresponding to the target cleaning parameters is higher than that corresponding to the initial cleaning parameters, thus improving the cleaning effect.

[0096] The control method for cleaning equipment provided in this application includes: acquiring initial data corresponding to a cleaning area, and identifying the material information of target objects in the cleaning area based on the initial data. The material identification data is used to identify the materials in the cleaning area, and the resistance data is used to determine the suction resistance and roller brush resistance, which also assists in material identification, accurately identifying the material information corresponding to the cleaning area. Further, based on the material information, initial data, and an initial model, initial cleaning parameters corresponding to the cleaning area are determined. The initial model is a model determined based on known training data, used to obtain the initial cleaning parameters of the cleaning equipment based on the aforementioned initial data. Further, the cleaning area is cleaned based on the initial cleaning parameters, and a first degree of cleanliness corresponding to the cleaning area is obtained. By analyzing the first degree of cleanliness, the initial model is adjusted to achieve cleaning of different materials and different levels of dirt, improving the cleaning effect of the cleaning equipment.

[0097] In one possible scenario, the initial data may also include location data. During the cleaning process, the cleaning equipment can use the location data to build a spatial map, so that subsequent cleaning processes can be based on the spatial map, thereby improving the cleaning efficiency of the cleaning equipment.

[0098] Figure 3 This is a flowchart of a control method for a cleaning device provided in an embodiment of this application. Figure 3 As shown, the control method includes the following steps:

[0099] S310. Obtain the initial data corresponding to the cleaning area, including material identification data, resistance data, and positioning data.

[0100] Location data is used to locate the position of the cleaning equipment's corresponding cleaning area within the space to be cleaned. It should be understood that location data is continuously acquired as the cleaning equipment is used.

[0101] Positioning data can be detected by radar and gyroscope. Distance is measured by detecting the time required for ultrasonic or laser pulses to reach the surface of the object being detected and return. This data is then combined with radar data to achieve positioning.

[0102] By using the mapped location data, it is easier to mark the material information on the map corresponding to the scene, thereby improving the cleaning ability of the cleaning equipment in subsequent use.

[0103] S320. Based on location data, construct a spatial map of the space to be cleaned corresponding to the cleaning area.

[0104] During the first use of cleaning equipment in various scenarios, a spatial map of the space to be cleaned corresponding to the cleaning area can be constructed using the acquired positioning data. It should be understood that, based on the positioning data, the spatial map of each cleaning area is continuously pieced together.

[0105] It should be noted that the space to be cleaned includes various cleaning areas; that is, the space to be cleaned is divided into multiple cleaning areas.

[0106] In some embodiments, there may be overlapping areas between the various cleaning zones to improve the completeness of cleaning the space to be cleaned.

[0107] Creating a spatial map of the space to be cleaned can provide users with a visual experience. At the same time, the cleaning efficiency of the cleaning equipment can be improved based on the spatial map during the next cleaning of the scene.

[0108] It should be understood that the spatial map can be calibrated during the next cleaning process.

[0109] S330: Based on initial data, identify the material information of target objects in the cleaning area.

[0110] S340. Determine the relationship between the material information and the target object and the spatial map.

[0111] S350. Update the spatial map based on the relationships.

[0112] The material information identified above is associated with the relationship between the target object and the spatial map, and then linked to the spatial map. In other words, the material information of each ground surface can be displayed on the spatial map, and the display method can be annotation, image display, etc.

[0113] By associating material information with target objects and spatial maps, the cleaning equipment can clean based on the updated spatial map, simplifying the material identification process for the next use of the cleaning equipment. Based on material information and spatial maps, cleaning efficiency can be improved.

[0114] S360 determines the initial cleaning parameters corresponding to the cleaning area based on material information, initial data, and initial model.

[0115] S370. Adjust the initial model based on the initial cleaning parameters corresponding to the first degree of cleanliness of the cleaning area.

[0116] S380. Based on the adjusted initial model, determine the target model.

[0117] The above steps include steps that correspond to those in the aforementioned methods. You can refer to the corresponding processes in the aforementioned method embodiments.

[0118] The above embodiments focus on how the cleaning equipment improves cleaning ability and efficiency. The following embodiments will describe in detail how to adjust the initial model based on initial cleaning parameters, including:

[0119] If the first level of cleanliness reaches the preset level of cleanliness, the initial cleaning parameters output by the corresponding initial model can meet the cleanliness requirements. Therefore, the initial model does not need to be adjusted at this time.

[0120] The first cleaning level is when the preset cleaning level is reached. In other words, when the cleaning level reaches the preset cleaning level, the cleaning equipment considers the area to be clean.

[0121] If the first level of cleanliness does not reach the preset level of cleanliness, adjust the initial cleaning parameters; and based on the adjusted initial cleaning parameters, clean the clean area to determine the second level of cleanliness corresponding to the clean area; and when the second level of cleanliness reaches the preset level of cleanliness, adjust the initial model based on the corresponding material information and the adjusted initial cleaning parameters to determine the target model.

[0122] It should be understood that after determining the second level of cleanliness, the relationship between the second level of cleanliness and the preset level of cleanliness is further evaluated. If the second level of cleanliness reaches the preset level of cleanliness, it indicates that the corresponding adjusted initial cleaning parameters can meet the cleaning requirements. Based on the corresponding material information and the adjusted initial cleaning parameters, the initial model is adjusted. If the second level of cleanliness does not reach the preset level of cleanliness, the initial cleaning parameters need to be further adjusted.

[0123] By comparing data related to the degree of cleanliness, the parameters of the initial model are adjusted so that the cleaning equipment can better adapt to different scene spaces.

[0124] It should be understood that adjustments to the initial model are made by fine-tuning the model using representative data.

[0125] The corresponding material information is used as the input data for the initial model, and the adjusted initial cleaning parameters are used as the output data for the initial model to adjust the parameters of the initial model.

[0126] In some embodiments, the model can be iteratively trained and its parameters updated using selected fine-tuning methods and hyperparameters. There are many fine-tuning methods, such as stochastic gradient descent, and appropriate hyperparameters such as learning rate and decay rate can be selected based on the characteristics of the model and data.

[0127] In some embodiments, better adjustment results can be achieved by adjusting different hyperparameters or fine-tuning methods.

[0128] Figure 4 This is a flowchart illustrating the adjustment of the initial model in the control method for the cleaning equipment provided in this application embodiment. For example... Figure 4 As shown, adjusting the initial model based on the first cleanliness level of the clean area corresponding to the initial cleaning parameters also includes:

[0129] Receive the first cleaning level.

[0130] The 410 step determines whether the cleanliness level has reached the preset cleanliness level.

[0131] If the first level of cleanliness reaches the preset level, the cleaning equipment moves to the next cleaning area to clean that area.

[0132] If the first level of cleanliness does not reach the preset level of cleanliness, the following steps are executed in sequence: 420, adjust the initial cleaning parameters; 430, clean the cleaning area based on the adjusted initial cleaning parameters; 440, determine the second level of cleanliness corresponding to the cleaning area; and send the second level of cleanliness to 410.

[0133] The new second level of cleanliness is assessed again using a 450-degree scale.

[0134] If the second level of cleanliness reaches the preset level of cleanliness, proceed to step 460: Based on the corresponding material information and the adjusted initial cleaning parameters, adjust the initial model and determine the target model.

[0135] If the second level of cleanliness does not reach the preset level of cleanliness, the initial cleaning parameters are further adjusted until the corresponding new level of cleanliness reaches the preset level of cleanliness.

[0136] It should be understood that the above examples are provided to help those skilled in the art understand the embodiments of this application, and are not intended to limit the embodiments of this application to the specific values ​​or scenarios illustrated. Those skilled in the art can obviously make various equivalent modifications or changes based on the above examples, and such modifications or changes also fall within the scope of the embodiments of this application.

[0137] The above text combined Figures 1 to 4 The control method of the cleaning equipment according to the embodiments of this application is described in detail below. Figure 5 This document describes in detail embodiments of the control device for the cleaning equipment of this application. It should be understood that the control device for the cleaning equipment in these embodiments can execute the various control methods for the cleaning equipment described in the foregoing embodiments of this application. Specifically, the specific working processes of the various products described below can be referenced to the corresponding processes in the foregoing method embodiments.

[0138] Figure 5 This is a schematic diagram of the control device for the cleaning equipment provided in an embodiment of this application. Figure 5 As shown, the control device 500 of the cleaning equipment includes a data acquisition unit 510, a data processing unit 520, and a model adjustment unit 530.

[0139] The data acquisition unit is used to acquire the initial data corresponding to the cleaning area, including material identification data and resistance data.

[0140] The data processing unit is used to identify the material information of the target object in the cleaning area based on the initial data; and to determine the initial cleaning parameters corresponding to the cleaning area based on the material information, the initial data and the initial model, wherein the initial model is a model determined based on known training data.

[0141] The model adjustment unit is used to adjust the initial model based on the initial cleaning parameters corresponding to the first degree of cleanliness of the clean area.

[0142] The model adjustment unit is also used to determine the target model based on the adjusted initial model, and the target model is used to determine the target cleaning parameters.

[0143] It should be understood that the control device 500 of the cleaning equipment can perform... Figures 1 to 4 The control method for the cleaning equipment shown.

[0144] It should be noted that the control device 500 of the aforementioned cleaning equipment is embodied in the form of a functional unit. The term "unit" here can be implemented in software and / or hardware, without specific limitations.

[0145] For example, a "unit" can be a software program, a hardware circuit, or a combination of both that implements the above functions. The hardware circuit may include an application-specific integrated circuit (ASIC), electronic circuitry, a processor (e.g., a shared processor, a proprietary processor, or a group processor) and memory for executing one or more software or firmware programs, integrated logic circuitry, and / or other suitable components that support the described functions.

[0146] Therefore, the units of the various examples described in the embodiments of this application can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0147] The above text combined Figures 1 to 4 The control method of the cleaning equipment in the embodiments of this application is described in detail below. Figures 6 to 7 The cleaning equipment provided in the embodiments of this application will be described in detail. It should be understood that the cleaning equipment in the embodiments of this application can execute the control methods of various cleaning equipment in the foregoing embodiments of this application, and the corresponding processes in the foregoing method embodiments can be referred to.

[0148] Figure 6 This is a schematic diagram of the cleaning equipment provided in the embodiments of this application, such as... Figure 6 As shown, the cleaning device 600 includes a sensor module 610, a cleaning module 620, a model module 630, and a control module 640.

[0149] It should be understood that the cleaning device 600 also includes basic modules for completing the cleaning function, such as a charging module, an energy storage module, a storage module, and even a motor module for movement. The cleaning device proposed in this application embodiment is based on existing cleaning devices, and by adding a sensor module 610, a cleaning module 620, a model module 630, and a control module 640, it achieves a better cleaning effect on the scene space.

[0150] The sensor module 610 is used to collect initial data corresponding to the cleaning area, which is the area corresponding to the location of the cleaning equipment.

[0151] The sensor module 610 may include an ultrasonic sensor, a speed sensor, and a current sensor.

[0152] The ultrasonic sensor is used to acquire ultrasonic data in the clean area. If there is only one device in the sensor module 610 for detecting material identification data, then the material identification data in the initial data is determined at least by the ultrasonic data, or in other words, the material identification data includes the ultrasonic data.

[0153] Ultrasonic sensors are characterized by being non-contact, highly accurate, and fast-responding. Therefore, the process of determining material identification data using ultrasonic sensors is highly accurate and fast.

[0154] The speed sensor is used to detect the speed data of the motor in the cleaning equipment; the current sensor is used to detect the current data of the motor; the resistance data is determined by the speed data and the current data, or in other words, the resistance data includes the speed data and the current data.

[0155] In some embodiments, the sensor module 610 further includes a camera; the camera is used to acquire shooting data, which includes at least an image or video corresponding to the cleaning area, and may also include both an image and a video corresponding to the cleaning area. In this case, the material identification data is determined by the ultrasonic data and the shooting data, or in other words, the material identification data includes both ultrasonic data and the shooting data.

[0156] It should be understood that regardless of whether the material identification data is already determined or a collection of multiple data, it can be further processed by the control module 640 in the cleaning equipment 600 to determine the data required for subsequent processing, such as material information.

[0157] In some embodiments, the sensor module 610 further includes a radar sensor and a gyroscope; the radar sensor is used to detect the positional characteristics of objects around the cleaning equipment, wherein the positional characteristics include the object's velocity, distance, and orientation; the gyroscope detects the dynamic characteristics of objects around the cleaning equipment, wherein the dynamic characteristics include the object's angular velocity and angle changes; and positioning data is determined based on the positional characteristics and dynamic characteristics.

[0158] Figure 7 This is a structural diagram of the cleaning equipment provided in the embodiments of this application, such as... Figure 7 As shown, the sensor module 610 includes an ultrasonic sensor 611, a camera 612, a speed sensor 613, a current sensor 614, a radar sensor 615, and a gyroscope 616.

[0159] The cleaning module 620 is used to clean the cleaning area based on initial cleaning parameters or target cleaning parameters.

[0160] It should be understood that the cleaning module 620 includes at least a fan, a roller brush, a side brush, a mop, and wheels. In other words, the cleaning parameters are execution parameters for the fan, roller brush, side brush, mop, and wheels, respectively, used to control each part of the cleaning module 620 to perform the corresponding cleaning.

[0161] For example, when the cleaning equipment detects that the material of the current cleaning area is carpet, since carpets easily hide dirt, the cleaning equipment will increase the power of the fan to increase the pressure, achieve a large negative pressure to suck away the dirt, and the walking motor will reduce the walking speed, and the roller brush motor will also increase the output to carry out the debris in the carpet, thereby achieving the goal of better cleaning.

[0162] It should be understood that the above-mentioned situation where the cleaning equipment detects that the material of the current cleaning area is carpet refers to the general case. It can further identify the type of carpet and, based on the various types of carpet, the cleaning module 620 will perform corresponding cleaning parameters.

[0163] When the cleaning equipment detects that the material of the area being cleaned is tile, the equipment can start the mop to clean the floor because tiles are waterproof, making the floor cleaner.

[0164] When the cleaning equipment detects that the material of the current cleaning area is wood flooring, since wood flooring is relatively smooth and not suitable for soaking in water, the cleaning equipment will only turn on the fan, roller brush, and side brush for normal cleaning, and will not turn on the mop or pressurize.

[0165] The model module 630 is used to store the initial model, adjust the initial model, and determine the target model. Specifically, it can determine the initial cleaning parameters corresponding to the cleaning area based on material information and the initial model, or based on material information, initial data, and the initial model, or based on the target model.

[0166] The control module 640 is used to perform the following: acquiring initial data, including material identification data and resistance data; identifying the material information of the target object in the cleaning area based on the initial data; determining the initial cleaning parameters corresponding to the cleaning area based on the material information, the initial data, and the initial model, wherein the initial model is a model determined based on known training data; adjusting the initial model based on the first degree of cleanliness of the cleaning area corresponding to the initial cleaning parameters; and receiving the target model returned by the model module 630, which is used to determine the target cleaning parameters.

[0167] In some embodiments, the control module 640 is configured to: determine the material information of the target object in the cleaning area, the material information being determined through initial data and used to characterize the material of the target object; send the material information to the model module 630; receive the initial cleaning parameters fed back by the model module 630, and send the initial cleaning parameters to the cleaning module 620.

[0168] In one possible implementation, the control module 640 is also used to perform: determining a first degree of cleanliness of the cleaning area; if the first degree of cleanliness does not reach the preset cleanliness, adjusting the initial cleaning parameters, and sending the material information and the adjusted initial cleaning parameters to the model module 630; receiving the target cleaning parameters fed back by the model module 630, and sending the target cleaning parameters to the cleaning module 620.

[0169] In some embodiments, if the sensor module 610 further includes a radar sensor 615 and a gyroscope 616, the control module 640 is further configured to perform: based on the positioning data, construct a spatial map of the space to be cleaned corresponding to the cleaning area, wherein the space to be cleaned includes the cleaning area.

[0170] In some embodiments, the control module 640 is further configured to: determine the association between the target object corresponding to the material information and the spatial map; and update the spatial map based on the association.

[0171] In some embodiments, the control module 640 is further configured to perform: if the first degree of cleanliness does not reach the preset degree of cleanliness, adjust the initial cleaning parameters and send the adjusted initial cleaning parameters to the cleaning module 620; and obtain the second degree of cleanliness corresponding to the clean area, wherein the second degree of cleanliness is the result of cleaning the clean area based on the adjusted initial cleaning parameters.

[0172] If the second level of cleanliness reaches the preset level of cleanliness, the material information, initial data and initial cleaning parameters corresponding to the second level of cleanliness are sent to the model module 630 so that the model module 630 can adjust the initial model and determine the target model.

[0173] It should be understood that the control module can be implemented through a controller, such as a microcontroller, a programmable logic controller (PLC), a distributed control system (DCS), etc., or it can be a processor, such as an advanced RISC machine (ARM).

[0174] In some embodiments, the control module and the model module may be implemented in different hardware or in the same hardware.

[0175] This application also provides a computer program product that, when executed by a processor, implements the control method for the cleaning equipment described in any of the method embodiments of this application.

[0176] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a computer, implements the control method of the cleaning device in any of the method embodiments of this application. The computer program may be a high-level language program or an executable object program.

[0177] In this application, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0178] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0179] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0180] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for example, the division of units is merely a logical functional division, and other division methods may exist in actual implementation; for example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0181] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0182] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0183] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A control method for cleaning equipment, characterized in that, include: Acquire initial data corresponding to the cleaning area, wherein the initial data includes at least material identification data and resistance data; the material identification data is determined by the acquired ultrasonic data and imaging data, wherein the imaging data includes at least an image or a video corresponding to the cleaning area, and the resistance data is determined by the acquired rotational speed data and current data; Based on the material identification data and the resistance data, the material information of the target object in the cleaning area is determined, and the material information is used to characterize the material of the target object; Based on the material information and the initial model, the initial cleaning parameters corresponding to the cleaning area are determined, wherein the initial model is a model determined based on known training data; The cleaning area is cleaned based on the initial cleaning parameters, and a first degree of cleanliness of the cleaning area is determined. If the first degree of cleanliness does not reach the preset degree of cleanliness, the initial cleaning parameters are adjusted; and based on the adjusted initial cleaning parameters, the cleaning of the clean area is performed to determine the second degree of cleanliness corresponding to the clean area. When the second level of cleanliness reaches the preset level of cleanliness, the initial model is adjusted based on the corresponding material information and the adjusted initial cleaning parameters to determine the target model.

2. The control method for the cleaning equipment according to claim 1, characterized in that, After determining a first degree of cleanliness in the cleaned area, the method further includes: Based on the first level of cleanliness, the initial model is adjusted to determine the target model; Based on the target model, target cleaning parameters are determined, and the cleaning area is cleaned based on the target cleaning parameters.

3. The control method for the cleaning equipment according to claim 1, characterized in that, The initial data also includes location data, and the method further includes: Based on the location data, a spatial map of the space to be cleaned corresponding to the cleaning area is constructed, wherein the space to be cleaned includes the cleaning area. After determining the material information of the cleaning area, the method further includes: Determine the association between the target object corresponding to the material information and the spatial map; Based on the aforementioned relationships, the spatial map is updated so that the cleaning equipment performs cleaning based on the updated spatial map.

4. A cleaning device, characterized in that, It includes a sensor module, a cleaning module, a model module, and a control module; The sensor module is used to collect initial data corresponding to the cleaning area, which is the area corresponding to the location of the cleaning equipment. The sensor module includes an ultrasonic sensor, a speed sensor, a current sensor, and a camera. The ultrasonic sensor is used to acquire ultrasonic data of the target object in the cleaning area, the speed sensor is used to detect the speed data of the motor in the cleaning equipment, the current sensor is used to detect the current data of the motor, and the camera is used to acquire shooting data, which includes at least an image or a video corresponding to the cleaning area. The initial data includes at least material identification data and resistance data. The material identification data is determined by the ultrasonic data and the imaging data, and the resistance data is determined by the rotational speed data and the current data. The control module is configured to perform the following actions: determine the material information of the target object in the cleaning area and send the material information to the model module, wherein the material information is determined by the initial data and is used to characterize the material of the target object; receive the initial cleaning parameters fed back by the model module and send the initial cleaning parameters to the cleaning module; The cleaning module is used to clean the cleaning area based on the initial cleaning parameters; The model module is used to determine the initial cleaning parameters corresponding to the cleaning area based on the material information and the initial model, wherein the initial model is a model determined based on known training data; The control module is further configured to determine a first degree of cleanliness of the cleaning area; if the first degree of cleanliness does not reach a preset degree of cleanliness, adjust the initial cleaning parameters and send the material information and the adjusted initial cleaning parameters to the model module; and determine a second degree of cleanliness corresponding to the cleaning area; when the second degree of cleanliness reaches the preset degree of cleanliness, adjust the initial model based on the corresponding material information and the adjusted initial cleaning parameters, and determine the target model.

5. The cleaning equipment according to claim 4, characterized in that, The control module is also used to perform: Receive the target cleaning parameters fed back by the model module, and send the target cleaning parameters to the cleaning module; The cleaning module is used to clean the cleaning area based on the target cleaning parameters; The model module is also used to determine a target model based on adjusting the initial model, and to determine target cleaning parameters based on the target model.

Images