Target cleaning method and device, cleaning equipment and storage medium

Abstract

The invention provides a target cleaning method and device, cleaning equipment and a storage medium, the method is applied to the field of cleaning equipment, and the method comprises the steps that the target type of a first cleaning target in a first cleaning area is acquired; if the target type is a first type, a first cleaning mode is adopted to clean the first cleaning target; if the cleaning frequency of the first cleaning target reaches a preset frequency threshold value and the first cleaning target is not cleaned, cleaning of the first cleaning target is stopped, and the target position of the first cleaning target in the first cleaning area is obtained; and the target information and the target position of the first cleaning target are stored in the cleaning pause list, so that the overall cleaning efficiency of the cleaning equipment is effectively improved.

Description

Technical Field

[0001] The present application relates to the field of cleaning equipment, and in particular to a target cleaning method, device, cleaning equipment and storage medium. Background Art

[0002] When cleaning garbage underwater, relevant underwater cleaning equipment often falls into a vicious cycle of repetitive cleaning operations due to inaccurate perception and rigid cleaning strategies, resulting in energy waste and multiple flushing of the same area. Ultimately, due to the system's lack of dynamic adjustment and data feedback capabilities, it is difficult to optimize the strategy and the cleaning efficiency is greatly reduced. Summary of the Invention

[0003] This application provides a target cleaning method, apparatus, cleaning equipment, and storage medium, aiming to improve the cleaning efficiency of the cleaning equipment. The technical solution is as follows:

[0004] In the first aspect, an embodiment of the present application provides a target cleaning method, which is applied to a cleaning device, including: obtaining a target type of a first cleaning target in a first cleaning area; if the target type is the first type, cleaning the first cleaning target using a first cleaning mode; if the number of cleaning times for the first cleaning target reaches a preset number threshold and the first cleaning target has not been cleaned, stopping the cleaning of the first cleaning target and obtaining the target position of the first cleaning target in the first cleaning area; storing the target information and target position of the first cleaning target in a paused cleaning list.

[0005] In the above technical solution, by identifying the target type of the first cleaning target, the cleaning equipment is adapted to the cleaning mode corresponding to the target type, thereby ensuring that the first cleaning target is processed in a targeted manner; when it is detected that the number of cleaning times for the first cleaning target reaches the preset threshold and it still cannot be cleared, the invalid cleaning cycle for the first cleaning target is actively terminated to avoid the cleaning equipment from falling into local repeated operations and causing power loss and time waste; at the same time, the target position and target information of the first cleaning target are saved to the paused cleaning list, which not only provides data support for subsequent centralized processing or manual intervention, but also prevents the global cleaning path from being repeatedly interrupted, thereby effectively improving the overall cleaning efficiency of the cleaning equipment.

[0006] In combination with the first aspect, in some possible implementations, obtaining the target type of the first cleaning target in the first cleaning area includes: obtaining historical cleaning data corresponding to the first cleaning area; determining the number of cleaning times of each area position in the first cleaning area by the cleaning equipment from the historical cleaning data, and determining the area position whose cleaning times are greater than or equal to a preset number threshold as the location of stubborn garbage; if the first cleaning target is at the location of stubborn garbage, determining the target type of the first cleaning target as the first type.

[0007] In the above technical solution, by mining the historical cleaning data in the historical cleaning data, it is possible to accurately identify high-frequency cleaning areas and mark them as potential locations of stubborn garbage, thereby building a dynamically updated garbage distribution knowledge base; when the cleaning equipment detects that the first cleaning target is located in such a predicted area, the target type of the first cleaning target is determined to be the first type, thereby reducing excessive reliance on real-time detection, and can also preset targeted cleaning strategies in advance, effectively avoiding energy waste and mechanical wear caused by repeated attempts at ineffective cleaning.

[0008] In combination with the first aspect, in some possible implementations, obtaining the target type of the first cleaning target in the first cleaning area includes: obtaining a historical pause cleaning list corresponding to the first cleaning area; if the location of the first cleaning target matches the historical location of any historical stubborn garbage in the historical pause cleaning list, then the target type of the first cleaning target is determined to be the first type.

[0009] In the above technical solution, by comparing the current target position with the stubborn garbage position recorded in the history list, the target type that may be difficult to clean can be directly identified, thereby triggering the adapted first type of cleaning mode in advance, avoiding repeated execution of the routine detection process, and reducing the triggering frequency of invalid cleaning actions. It not only shortens the cleaning decision time, but also reduces the energy consumption and wear risk of cleaning equipment caused by repeated attempts in known stubborn areas. At the same time, the continuity of the regional cleaning strategy is enhanced by reusing historical stubborn position data.

[0010] In combination with the first aspect, in some possible implementations, obtaining the target type of the first cleaning target in the first cleaning area includes: obtaining feature data of the first cleaning target, and determining the semantic information of the first cleaning target based on the feature data; if the semantic information matches any semantic word in a preset first type semantic library, then determining the target type of the first cleaning target as the first type; if the semantic information matches any semantic word in a preset second type semantic library, then determining the target type of the first cleaning target as the second type.

[0011] In combination with the first aspect, in some possible implementations, if the semantic information matches any semantic word in a preset second-type semantic library, then after the target type of the first cleaning target is determined to be the second type, it includes: enabling the preset second cleaning mode to clean the first cleaning target, and the cleaning intensity of the second cleaning mode is less than the cleaning intensity of the first cleaning mode; if the number of cleaning times reaches the preset number threshold and the first cleaning target is not cleaned, then the cleaning of the first cleaning target is stopped, and the target information of the first cleaning target and the target position of the first cleaning target in the first cleaning area are stored in the paused cleaning list.

[0012] In the above technical solution, the real-time determination of the target type of the first cleaning target is achieved by mapping and transforming the physical features of the first cleaning target and the semantic space, so that the classification decision retains the objectivity of the sensor data and has the abstract expression ability of semantic logic. The hierarchical matching strategy of the dual-type semantic library is adopted to reduce the computational complexity while enhancing the adaptability to the dynamic environment. It not only avoids the risk of misjudgment that may be caused by a single feature library, but also ensures the targeted response to specific cleaning targets through the construction of type-specific semantic sets, thereby effectively improving the accuracy and reliability of target identification. Through the forced termination mechanism of the preset number of thresholds, the invalid cycle of repeated cleaning is cut off, and the equipment resources are released to turn to other processable areas, thereby ensuring the continuity of the global cleaning progress.

[0013] In combination with the first aspect, in some possible implementations, before obtaining the target type of the first cleaning target in the first cleaning area, it includes: obtaining regional environmental data of the cleaning area, dividing the cleaning area into regions based on the regional environmental data, and obtaining a cleaning area set; determining the first cleaning area from the cleaning area set based on the spatial position of the cleaning equipment in the cleaning area, the first cleaning area being the cleaning area closest to the cleaning equipment.

[0014] In the above technical solution, the cleaning area is partitioned based on the regional environmental data of the cleaning area, so that the overall cleaning area is deconstructed into independent task units suitable for cleaning equipment, forming an accurate mapping of physical space and cleaning needs; at the same time, by obtaining the equipment location in real time and giving priority to the nearest area, the moving path of the cleaning equipment during the startup phase is directly shortened, eliminating the time loss of empty movement across areas.

[0015] In combination with the first aspect, in some possible implementations, after the target information and target position of the first cleaning target are stored in the paused cleaning list, it includes: if there is no second type of garbage in the first cleaning area, sorting the first cleaning targets in the paused cleaning list based on the target information of each first cleaning target in the paused cleaning list and the relative distance between each first cleaning target and the cleaning equipment to obtain a sorted cleaning list; calling the cleaning equipment to sequentially clean each first cleaning target in the sorted cleaning list in the first cleaning mode.

[0016] In combination with the first aspect, in some possible implementations, after calling the cleaning device to sequentially clean each first cleaning target in the sorted cleaning list in the first cleaning mode, it includes: if it is detected that the cleaning device moves from the first cleaning area to the second cleaning area, then the paused cleaning list is cleared, and the first cleaning area and the second working area are any two different cleaning areas in the cleaning area set.

[0017] In the above technical solution, when confirming that there is no second type of garbage in the first cleaning area, the suspended cleaning list is sorted based on the real-time location of the cleaning equipment to generate the optimal path sequence, thereby effectively reducing the cleaning equipment's idle movement losses. By automatically updating the suspended cleaning list of the previous work area when a change in the cleaning equipment's work area is detected, the task context of different areas is isolated. This not only avoids path conflicts caused by cross-area task redundancy, but also ensures that the cleaning equipment can quickly establish a cleaning strategy that matches the current spatial characteristics in the new work area, thereby further improving the cleaning efficiency of the cleaning equipment.

[0018] In a second aspect, an embodiment of the present application provides a target cleaning device, which is applied to a cleaning device, comprising:

[0019] A type acquisition unit, configured to acquire a target type of a first cleaning target in a first cleaning area;

[0020] a target cleaning unit, configured to clean the first cleaning target using a first cleaning mode if the target type is a first type;

[0021] a position acquisition unit, configured to stop cleaning the first cleaning target and acquire a target position of the first cleaning target in the first cleaning area if the number of cleaning operations for the first cleaning target reaches a preset number threshold and the first cleaning target has not been cleaned;

[0022] The data writing unit is configured to store the target information and the target position of the first cleaning target into the pause cleaning list.

[0023] In a third aspect, an embodiment of the present application provides a cleaning device, which includes: a memory, a processor, and a computer program stored in the memory and runnable on the processor, and when the computer program is executed by the processor, it implements any of the target cleaning methods above.

[0024] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed, any of the target cleaning methods described above is implemented.

[0025] In the above technical solution, by identifying the target type of the first cleaning target, the cleaning equipment is adapted to the cleaning mode corresponding to the target type, thereby ensuring that the first cleaning target is processed in a targeted manner; when it is detected that the number of cleaning times for the first cleaning target reaches the preset threshold and it still cannot be cleared, the invalid cleaning cycle for the first cleaning target is actively terminated to avoid the cleaning equipment from falling into local repeated operations and causing power loss and time waste; at the same time, the target position and target information of the first cleaning target are saved to the paused cleaning list, which not only provides data support for subsequent centralized processing or manual intervention, but also prevents the global cleaning path from being repeatedly interrupted, thereby effectively improving the overall cleaning efficiency of the cleaning equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without paying any creative work.

[0027] Figure 1 This is a schematic diagram of a scenario of a target cleaning method provided in an embodiment of the present application;

[0028] Figure 2 This is a flow chart of a target cleaning method provided in an embodiment of the present application;

[0029] Figure 3 This is a flow chart of a target cleaning method provided in an embodiment of the present application;

[0030] Figure 4 This is a flow chart of a target cleaning method provided in an embodiment of the present application;

[0031] Figure 5 This is a flow chart of a target cleaning method provided in an embodiment of the present application;

[0032] Figure 6 This is a flow chart of a target cleaning method provided in an embodiment of the present application;

[0033] Figure 7 This is a flow chart of a target cleaning method provided in an embodiment of the present application;

[0034] Figure 8 This is a schematic structural diagram of a target cleaning device provided in an embodiment of the present application;

[0035] Figure 9 It is a structural schematic diagram of a cleaning device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0036] To make the features and advantages of this application more obvious and easy to understand, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts shall fall within the scope of protection of this application.

[0037] The following will clearly and thoroughly describe the technical solutions in this application in conjunction with the accompanying drawings. In the description of the embodiments of this application, unless otherwise specified, " / " means or, for example, A / B can mean A or B: "and / or" in the text is only a description of the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of this application, "multiple" means two or more than two.

[0038] In the following, the terms "first" and "second" are used for descriptive purposes only and should not be understood to imply or suggest relative importance or implicitly indicate the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features.

[0039] The embodiment of the present application provides a target cleaning method, the execution subject of which is a target cleaning device or a cleaning device with a target cleaning device. The following is a detailed description. It should be noted that the description order of the following embodiments does not limit the preferred order of the embodiments. Figure 1 , Figure 1 This is a schematic diagram of a target cleaning method provided in an embodiment of the present application. The specific process of the target cleaning method can be as follows:

[0040] See also Figure 1 , Figure 1 This is a scene diagram of a target cleaning method provided by an embodiment of the present application. Figure 1 As shown, the cleaning device is composed of at least a processor, a sensor, a positioning module and an identification module, wherein the sensor includes at least a visual sensor and an acoustic sensor. The following provides a preferred embodiment combined with Figure 1 The following scene diagram is used for combination description:

[0041] In actual scenarios, when the cleaning device is in the cleaning area and the automatic cleaning function of the cleaning device is enabled, the cleaning device first calls the visual sensor and ultrasonic sensor to collect the regional environmental data of the cleaning area, and calls the preset algorithm to perform spatial structure analysis on the regional environmental data to divide the cleaning area into multiple cleaning sub-areas. After integrating the cleaning sub-areas, a cleaning area set is obtained.

[0042] The cleaning sub-area closest to the cleaning equipment in the cleaning area cluster is identified as the first cleaning area. A visual sensor and an acoustic sensor are used to search for a target in the first cleaning area to identify a first cleaning target in the first cleaning area. The visual sensor and the acoustic sensor are used to obtain feature data of the first cleaning target, wherein the feature data includes at least but is not limited to morphological features and / or echo reflection data of the first cleaning target. The feature data is input into a recognition module, and semantic information corresponding to the first cleaning target is obtained using a semantic parsing model pre-installed in the recognition module.

[0043] The semantic information of the first cleaning target is matched with a preset first-type semantic library, wherein the first-type semantic library records semantic words corresponding to stubborn garbage. If the semantic information of the first cleaning target successfully matches any semantic word in the first-type semantic library, the first cleaning target is marked as the first type.

[0044] When determining that the target type of the first cleaning target is the first type, the processor activates the first cleaning mode preset by the cleaning device to enhance the cleaning suction and water pump pressure of the cleaning device and reduce the moving linear speed of the cleaning device to perform deep cleaning on the first cleaning target.

[0045] When the processor detects that the cleaning device has cleaned a first cleaning target a predetermined number of times, the processor uses a visual sensor to monitor whether the first cleaning target is still present. If the first cleaning target is still present, the processor stops deep cleaning the first cleaning target. The positioning module obtains the three-dimensional coordinate position of the first cleaning target in the first cleaning area, which is recorded as the target position.

[0046] At the same time, a morphological scan of the first cleaning target after deep cleaning is performed using a visual sensor to obtain target information of the first cleaning target, wherein the target information includes at least the outline, size, and spatial distribution data of the first cleaning target. The target information of the first cleaning target is associated with the target position and saved to the paused cleaning list.

[0047] In an embodiment of the present application, by identifying the target type of the first cleaning target, the cleaning equipment is adapted to the cleaning mode corresponding to the target type, thereby achieving targeted processing of the first cleaning target; when it is detected that the number of cleaning times for the first cleaning target reaches a preset threshold and still cannot be cleared, the invalid cleaning cycle of the first cleaning target is actively terminated to avoid the cleaning equipment from falling into local repeated operations and causing power loss and time waste; at the same time, the target position and target information of the first cleaning target are saved to the paused cleaning list, which not only provides data support for subsequent centralized processing or manual intervention, but also prevents the global cleaning path from being repeatedly interrupted, thereby effectively improving the overall cleaning efficiency of the cleaning equipment.

[0048] based on Figure 1 The scene diagram shown below will be combined with Figure 2-Figure 7 , a target cleaning method provided in an embodiment of the present application is introduced in detail.

[0049] See Figure 2 , Figure 2 This is a flow chart of a target cleaning method provided in an embodiment of the present application. Figure 2 As shown, the method of the embodiment of the present application may include the following steps S101 to S104.

[0050] S101 , obtaining an object type of a first cleaning object in a first cleaning area.

[0051] In an embodiment of the present application, the first cleaning target is the target detected by the cleaning equipment in the first cleaning area according to the sensor. The target type of the first cleaning target is divided into a first type and a second type, wherein the first type is specifically a stubborn garbage type and the second type is specifically an easy-to-handle garbage type.

[0052] It should be noted that the determination method for the target type of the first cleaning target includes but is not limited to the following methods:

[0053] The system traverses historical cleaning data and obtains the cleaning counts for each location in the first cleaning area based on the historical cleaning data. Areas where the cleaning counts reach or exceed a preset threshold are identified as locations of stubborn garbage. The stubborn garbage locations are compared with the locations of the first cleaning target. If the locations match, the target type of the first cleaning target is determined to be the first type.

[0054] Before executing the cleaning task for the first cleaning area, the cleaning device first queries local or cloud storage to see if there is a historical paused cleaning list corresponding to the first cleaning area. This list contains the locations of historical stubborn garbage that could not be cleaned, as recorded during the cleaning device's most recent cleaning of the first cleaning area. If a historical paused cleaning list exists, the cleaning device downloads the list and obtains the historical locations of all stubborn garbage in the first cleaning area in the historical paused cleaning list. The cleaning device then obtains the location of the first cleaning target in the first cleaning area and matches it with the locations of each stubborn garbage in the historical paused cleaning list. If a match is found with any stubborn garbage location, the target type of the first cleaning target is determined to be the first type.

[0055] The cleaning device detects the first cleaning target using its onboard visual and acoustic sensors, acquiring feature data for the first cleaning target. This feature data is then fed into a pretrained semantic parsing model to obtain semantic information for the first cleaning target. The semantic information for the first cleaning target is then matched against a pre-set first-type semantic library and a second-type semantic library. The first-type semantic library contains semantic terms corresponding to stubborn waste, while the second-type semantic library contains semantic terms corresponding to easily handled waste. If the semantic information for the first cleaning target successfully matches any semantic term in the first-type semantic library, the first cleaning target is labeled as the first type. If it successfully matches any semantic term in the second-type semantic library, the first cleaning target is labeled as the second type.

[0056] S102: If the target type is the first type, clean the first cleaning target using a first cleaning mode.

[0057] In the embodiment of the present application, the first cleaning mode is a strong cleaning mode of the cleaning device. In the first cleaning mode, the cleaning suction force and water pump pressure of the cleaning device are enhanced, and the moving linear speed of the cleaning device is reduced.

[0058] Specifically, when the target type of the first cleaning target is the first type, the first cleaning mode preset by the cleaning device is activated to enhance the cleaning suction force and water pump pressure of the cleaning device and reduce the moving linear speed of the cleaning device to perform deep cleaning on the first cleaning target.

[0059] S103: If the number of cleaning times for the first cleaning target reaches a preset number threshold and the first cleaning target is not cleaned, then the cleaning of the first cleaning target is stopped, and the target position of the first cleaning target in the first cleaning area is obtained.

[0060] In an embodiment of the present application, in order to prevent the cleaning device from falling into repeated local cleaning of the first cleaning target, thereby affecting the overall cleaning efficiency, a cleaning times threshold is set to prevent the cleaning device from falling into repeated local cleaning.

[0061] Specifically, each time the cleaning device performs a deep cleaning process on a first cleaning target, the number of cleaning times for the first cleaning target is accumulated. When it detects that the number of cleaning times for the first cleaning target has reached a preset threshold, a sensor is used to monitor whether the first cleaning target is still present. If the first cleaning target is still present, the deep cleaning process for the first cleaning target is stopped, and the three-dimensional coordinate position of the first cleaning target in the first cleaning area is obtained by the positioning module of the cleaning device and recorded as the target position.

[0062] S104: Store the target information and target position of the first cleaning target into a pause cleaning list.

[0063] In the embodiment of the present application, the target information of the first cleaning target at least includes the target area of ​​the first cleaning target.

[0064] Specifically, the cleaning device's visual sensor scans the first cleaning target after deep cleaning to obtain the first cleaning target's outline, size, and spatial distribution data. Using a pre-set image processing algorithm, the first cleaning target's outline, size, and spatial distribution data are calculated to determine the target area of ​​the first cleaning target. The target information of the first cleaning target is associated with the target position and saved to a paused cleaning list.

[0065] In an embodiment of the present application, by identifying the target type of the first cleaning target, the cleaning equipment is adapted to the cleaning mode corresponding to the target type, thereby achieving targeted processing of the first cleaning target; when it is detected that the number of cleaning times for the first cleaning target reaches a preset threshold and still cannot be cleared, the invalid cleaning cycle of the first cleaning target is actively terminated to avoid the cleaning equipment from falling into local repeated operations and causing power loss and time waste; at the same time, the target position and target information of the first cleaning target are saved to the paused cleaning list, which not only provides data support for subsequent centralized processing or manual intervention, but also prevents the global cleaning path from being repeatedly interrupted, thereby effectively improving the overall cleaning efficiency of the cleaning equipment.

[0066] To improve the efficiency of cleaning equipment in identifying the type of cleaning target. Figure 3 , Figure 3 This is a flow chart of a target cleaning method provided in an embodiment of the present application. Figure 3 As shown, the method of the embodiment of the present application may include the following steps S201-S203.

[0067] S201: Acquire historical cleaning data corresponding to a first cleaning area.

[0068] Specifically, if a cleaning device without an identification module for identifying target types, or a cleaning device with an inactive or malfunctioning identification module, was used to perform cleaning tasks on the first cleaning area during historical cleaning processes, it is necessary to record in real time the number of cleanings performed by the cleaning device on each location in the first cleaning area, where the location is the area where the cleaning target is detected by the visual sensor. Each location is marked on the area map of the cleaning area and associated with the number of cleanings corresponding to each location to generate historical cleaning data.

[0069] S202 : Determine the cleaning times of each area in the first cleaning area by the cleaning device from historical cleaning data, and determine the area where the cleaning times are greater than or equal to a preset threshold as the location of stubborn garbage.

[0070] S203: If the first cleaning target is located at the location of stubborn garbage, the target type of the first cleaning target is determined to be the first type.

[0071] In an embodiment of the present application, the location and area position of the first cleaning target are three-dimensional spatial coordinate positions, wherein the three-dimensional spatial coordinate position refers to a physical space point precisely positioned by the X, Y, and Z axes of the coordinate system, wherein X and Y represent the horizontal and vertical positions on the horizontal plane, for example, the length and width directions of the area, and Z represents the vertical depth from the horizontal.

[0072] Specifically, in steps S202-S203, the historical cleaning data is traversed to obtain the cleaning counts corresponding to each area location. Area locations with cleaning counts greater than or equal to a preset threshold are determined as locations of stubborn garbage. The stubborn garbage locations are matched with locations corresponding to the first cleaning target. If the stubborn garbage locations match the locations corresponding to the first cleaning target, the target type of the first cleaning target is determined to be the first type.

[0073] In an embodiment of the present application, by mining historical cleaning data in historical cleaning data, high-frequency cleaning areas can be accurately identified and marked as potential locations of stubborn garbage, thereby building a dynamically updated garbage distribution knowledge base; when the cleaning equipment detects that the first cleaning target is located in such a predicted area, the target type of the first cleaning target is determined to be the first type, thereby reducing excessive reliance on real-time detection, and can also preset targeted cleaning strategies in advance, effectively avoiding energy waste and mechanical wear caused by repeated attempts at ineffective cleaning.

[0074] Since the cleaning equipment may have performed historical cleaning operations on the cleaning area during actual use, in this scenario, it is necessary to combine the historical cleaning data of the cleaning equipment to obtain the historical stubborn garbage, so as to improve the target type recognition speed of the first cleaning target. Figure 4 , Figure 4 This is a flow chart of a target cleaning method provided in an embodiment of the present application. Figure 4 As shown, the method of the embodiment of the present application may include the following steps S301-S302.

[0075] S301: Obtain a historical paused cleaning list corresponding to a first cleaning area.

[0076] In this embodiment of the present application, the historical paused cleaning list refers to the stubborn garbage that failed to be successfully cleaned by the cleaning device during the most recent cleaning of the first cleaning area, as well as the historical location of the stubborn garbage in the first cleaning area. The cleaning device's historical cleaning process for the first cleaning area is described in steps S101-S104 above and will not be repeated here. The historical paused cleaning list can be stored as cloud data.

[0077] Specifically, before executing the cleaning task for the first cleaning area, the cleaning device queries the cloud data to see if there is a historical pause cleaning list corresponding to the first cleaning area. If so, the historical pause cleaning list is downloaded and the historical locations of all stubborn garbage in the historical pause cleaning list in the first cleaning area are obtained.

[0078] S302: If the location of the first cleaning target matches the historical location of any stubborn garbage in the historical paused cleaning list, the target type of the first cleaning target is determined to be the first type.

[0079] In an embodiment of the present application, the location of the first cleaning target and the historical location of any historical stubborn garbage are three-dimensional spatial coordinate positions, wherein the three-dimensional spatial coordinate position refers to a physical space point precisely positioned by the X, Y, and Z axes of the coordinate system, wherein X and Y represent the horizontal and vertical positions on the horizontal plane, such as the length and width directions of the area, and Z represents the vertical depth from the horizontal.

[0080] It should be noted that in the position matching process, if the deviation between the location of the first cleaning target and the historical location of any historical stubborn garbage in the historical pause cleaning list is within the preset tolerance range, the positions will still be determined to be matched. The tolerance range can be set according to the actual scenario and is not specifically limited here.

[0081] Specifically, the cleaning equipment first obtains the location of the first cleaning target in the first area, and matches the location of the first cleaning target in the first area with the historical location of any historical stubborn garbage. If it matches the historical location of any historical stubborn garbage, the target type of the first cleaning target is determined to be the first type.

[0082] For example, the location of the first cleaning target is X=2.15m, Y=3.70m, Z=1.20m, and the historical pause cleaning list stores a historical stubborn garbage with a historical location of X=2.15m, Y=3.68m, Z=1.18m. Since the two coincide or are adjacent within the preset tolerance range, the target type of the first cleaning target is determined to be the first type.

[0083] In an embodiment of the present application, by comparing the current target position with the stubborn garbage position recorded in the history list, the target type that may be difficult to clean can be directly identified, thereby triggering the adapted first type of cleaning mode in advance, avoiding repeated execution of the routine detection process, and reducing the triggering frequency of invalid cleaning actions. This not only shortens the cleaning decision time, but also reduces the energy consumption and wear risk of the equipment due to repeated attempts in known stubborn areas. At the same time, the continuity of the regional cleaning strategy is enhanced by reusing historical stubborn position data.

[0084] In actual use scenarios, in order to avoid operational complexity, the cleaning equipment needs to be able to completely autonomously identify and clean up garbage. Figure 5 , Figure 5 This is a flow chart of a target cleaning method provided in an embodiment of the present application. Figure 5 As shown, the method of the embodiment of the present application may include the following steps S401-S405.

[0085] S401 : Acquire feature data of a first cleaning target, and determine semantic information of the first cleaning target based on the feature data.

[0086] In the embodiment of the present application, the characteristic data of the first cleaning target is data obtained by the sensor equipped with the cleaning device after collecting and analyzing data of the first cleaning target. The data type and amount of the characteristic data can be set according to the type of sensor equipped with the cleaning device in the actual application scenario and the actual usage requirements of the user. In the embodiment of the present application, the characteristic data is preferably morphological characteristics and echo reflection data for specific description.

[0087] Specifically, the cleaning device uses an onboard visual sensor to perform a morphological scan of the first cleaning target, acquiring its morphological features and echo reflection data. Morphological features include, but are not limited to, three-dimensional geometry, surface texture, and contour information. Echo reflection data is calculated by the acoustic sensor sending acoustic waves to the first cleaning target based on the acoustic wave reflection signal strength and acoustic wave reflection time difference. The morphological features and echo reflection data are then integrated to obtain the characteristic data of the first cleaning target.

[0088] The acquired feature data is input into a pre-trained semantic parsing model, such as a multimodal fusion model based on a convolutional neural network or a Transformer. The semantic parsing model outputs the semantic information corresponding to the feature data by comparing it with a known object feature library.

[0089] S402: If the semantic information matches any semantic word in a preset first type semantic library, the target type of the first cleaning target is determined to be the first type.

[0090] Specifically, the semantic information generated in S401 is matched against semantic words in a preset first-type semantic library, which contains semantic words corresponding to stubborn garbage. This matching process typically utilizes string similarity calculations or semantic search techniques based on embedding vectors. If the semantic information successfully matches any semantic word in the first-type semantic library, the target type of the first cleaning target is marked as the first type.

[0091] For example, the semantic information of the first cleaning target is "chewing gum". "Chewing gum" is matched with the semantic words for stubborn garbage recorded in the first type semantic library, such as "paint stains", "glue marks", "chewing gum", etc. In this case, the semantic information of the first cleaning target matches the semantic word for stubborn garbage "chewing gum", and the target type of the first cleaning target is marked as the first type.

[0092] S403: If the semantic information matches any semantic word in the preset second type semantic library, the target type of the first cleaning target is determined to be the second type.

[0093] Specifically, the semantic information generated in step S401 is matched with semantic words in a preset second-type semantic library, wherein the second-type semantic library contains semantic words corresponding to easily disposable garbage. If the semantic information successfully matches any semantic word in the second-type semantic library, the target type of the first cleaning target is marked as the second type.

[0094] For example, the semantic information of the first cleaning target is "animal hair." "Hair" is matched with the easily disposable garbage semantic words in the second type semantic library. For example, the easily disposable garbage semantic words include "fallen leaves," "hair," and "tissue paper." In this case, because the semantic information of the first cleaning target matches the easily disposable garbage semantic word "hair," the target type of the first cleaning target is marked as the second type.

[0095] S404: Activate the preset second cleaning mode to clean the first cleaning target.

[0096] In the application embodiment, the second cleaning mode is the default cleaning mode of the cleaning device. In the second cleaning mode, the cleaning suction force, water pump pressure and moving linear speed of the cleaning device are all default setting parameters.

[0097] Exemplarily, the preset second cleaning mode is enabled to clean the first cleaning target: at this time, the suction cup motor of the cleaning equipment runs at the default power of 800Pa, the water pump pressure maintains the default pressure of 15kPa and moves at a uniform speed of 0.3m / s for cleaning.

[0098] S405: If the cleaning times reach the preset threshold and the first cleaning target is not cleaned, the cleaning of the first cleaning target is stopped, and the target information of the first cleaning target and the target position of the first cleaning target in the first cleaning area are stored in a paused cleaning list.

[0099] Specifically, when the target type of the first cleaning target is the second type, that is, the easy-to-handle garbage type, if it is monitored that the number of times the cleaning equipment cleans the first cleaning target in the second cleaning mode reaches the predetermined number threshold, then the target type of the first cleaning target is converted from the second type to the first type, and the target information of the first cleaning target and the target position of the first cleaning target in the first cleaning area are stored in the pause cleaning list. Please refer to steps S103-S104 for the specific execution process, which will not be repeated here.

[0100] In an embodiment of the present application, by mapping and converting the physical features of the first cleaning target and the semantic space, real-time determination of the target type of the first cleaning target is achieved, so that the classification decision retains the objectivity of the sensor data and has the abstract expression ability of semantic logic. The hierarchical matching strategy of the dual-type semantic library is adopted to reduce the computational complexity while enhancing the adaptability to the dynamic environment. It avoids the risk of misjudgment that may be caused by a single feature library, and ensures targeted response to specific cleaning targets through the construction of type-specific semantic sets, thereby effectively improving the accuracy and reliability of target identification. Through the forced termination mechanism of the preset number of times threshold, the invalid cycle of repeated cleaning is cut off, and the equipment resources are released to turn to other processable areas, thereby ensuring the continuity of the global cleaning progress.

[0101] Since the environment of the cleaning area is relatively complex, it is necessary to divide the cleaning area into sections to improve the cleaning efficiency of the cleaning equipment. Figure 6 , Figure 6 This is a flow chart of a target cleaning method provided in an embodiment of the present application. Figure 6 As shown, the method of the embodiment of the present application may include the following steps S501-S502.

[0102] S501 , obtaining regional environmental data of a clean area, dividing the clean area into regions based on the regional environmental data, and obtaining a clean area set.

[0103] Specifically, the cleaning equipment collects regional environmental data of the cleaning area in real time through visual sensors. The regional environmental data includes at least terrain height, surface material, spatial geometric characteristics and water state, etc. The spatial structure of the cleaning area is determined based on the regional environmental data, and the preset regional segmentation algorithm is called to divide the cleaning area into multiple discrete cleaning sub-areas. After integrating the cleaning sub-areas, a cleaning area set is obtained.

[0104] S502 : Determine a first cleaning area from the cleaning area set based on the spatial position of the cleaning device in the cleaning area. The first cleaning area is the cleaning area closest to the cleaning device.

[0105] Specifically, the three-dimensional coordinates of the cleaning equipment in the cleaning area are obtained through the positioning module to determine the spatial position of the cleaning equipment in the cleaning area, the boundary information of each cleaning sub-area in the cleaning area set is traversed, and the spatial proximity between the spatial position of the cleaning equipment and the domain of each cleaning sub-area is quantified through geometric projection or shortest path algorithm, and the cleaning sub-area with the closest spatial proximity to the cleaning equipment is taken as the first cleaning area.

[0106] In an embodiment of the present application, the cleaning area is partitioned based on the regional environmental data of the cleaning area, thereby deconstructing the entire cleaning area into independent task units suitable for cleaning by cleaning equipment, forming an accurate mapping of physical space and cleaning needs; at the same time, by obtaining the equipment location in real time and giving priority to the nearest area, the moving path of the cleaning equipment during the startup phase is directly shortened, eliminating the time loss of cross-regional empty-load movement.

[0107] In actual scenarios, after the cleaning equipment completes cleaning the first cleaning area, it needs to clean the next cleaning area. In order to eliminate the path planning conflicts and ineffective resource consumption caused by cross-area task residues, it is necessary to clear the suspended cleaning list of the first cleaning area in a timely manner. Figure 7 , Figure 7 This is a flow chart of a target cleaning method provided in an embodiment of the present application. Figure 7 As shown, the method of the embodiment of the present application may include the following steps S601-S603.

[0108] S601: If there is no second type of garbage in the first cleaning area, sort the first cleaning targets in the paused cleaning list based on the target information of the first cleaning targets and the relative distance between the first cleaning targets and the cleaning equipment to obtain a sorted cleaning list.

[0109] In an embodiment of the present application, if there is no second type of garbage in the first cleaning area, it means that all the garbage that can be cleaned in the first cleaning area has been cleaned by the cleaning equipment, wherein the suspended cleaning list records the first type of first cleaning target that the cleaning equipment temporarily gives up cleaning.

[0110] Specifically, when the second type of garbage does not exist in the first cleaning area, a paused cleaning list generated for the first cleaning area is obtained, target information of the first cleaning target and the target position of each first cleaning are further obtained from the paused cleaning list, and the target area of ​​the first cleaning target is extracted from the target information.

[0111] Combined with the real-time location of the cleaning equipment, the Euclidean distance formula is used to calculate the relative distance between the real-time location of the cleaning equipment and the location of each first cleaning target. The target area of ​​the first cleaning target is then extracted. The set cleaning cost function (cost = distance × area weight) is called to sort the first cleaning targets and generate a sorted cleaning list.

[0112] For example, the paused cleaning list includes the first cleaning target A, the first cleaning target B, and the first cleaning target C. The cost of the first cleaning target A is 1.13, the cost of the first cleaning target B is 1.2, and the cost of the first cleaning target C is 1.5, so the sorted cleaning list is the first cleaning target C, the first cleaning target B, and the first cleaning target A.

[0113] S602 , calling a cleaning device to sequentially clean each first cleaning target in the sorted cleaning list in a first cleaning mode.

[0114] Specifically, the cleaning device starts the first cleaning mode. At this time, the cleaning device will enhance the cleaning suction, increase the water pump pressure and reduce the moving linear speed to perform secondary deep cleaning on each first cleaning target in the sorted cleaning list. If the visual sensor detects that the first cleaning target is cleaned by the cleaning device, the cleaned first cleaning target will be deleted from the paused cleaning list.

[0115] It should be noted that when using cleaning equipment to perform deep cleaning on each first cleaning target in the sorted cleaning list, it is also necessary to record the number of times each first cleaning target is deep cleaned twice. If there is a first cleaning target whose number of times of deep cleaning twice reaches a preset threshold, the next first cleaning target in the sorted cleaning list will be cleaned.

[0116] S603: If it is detected that the cleaning device moves from the first cleaning area to the second cleaning area, a clearing operation is performed on the paused cleaning list, where the first cleaning area and the second working area are any two different cleaning areas in the cleaning area set.

[0117] Specifically, after the cleaning device has performed a secondary deep cleaning on all first cleaning targets in the sorted cleaning list of the first cleaning area, the cleaning device will move from the first cleaning area to the second cleaning area, where the second cleaning area is the cleaning sub-area of ​​the cleaning area set that is closest to the cleaning device, excluding the first cleaning area. The cleaning process for the second cleaning area is described in steps S101-S104 above and will not be repeated here.

[0118] If the battery level of the cleaning device falls below a preset battery threshold during the cleaning process, the cleaning device will exit the automatic cleaning mode and return to the preset standby position to enter standby mode, and will remind the user of the low battery level.

[0119] In an embodiment of the present application, when confirming that the first cleaning area is free of the second type of garbage, the paused cleaning list is sorted based on the real-time location of the cleaning equipment to generate an optimal path sequence, thereby effectively reducing the cleaning equipment's idle movement losses. By automatically updating the paused cleaning list of the previous work area when a change in the cleaning equipment's work area is detected, the task contexts of different areas are isolated, avoiding path conflicts caused by cross-area task redundancy and ensuring that the cleaning equipment quickly establishes a cleaning strategy that matches the current spatial characteristics in the new work area, thereby further improving the cleaning efficiency of the cleaning equipment.

[0120] In one feasible embodiment, after the cleaning device is called to perform a second deep cleaning of each first cleaning target in the sorted cleaning list in the first cleaning mode, if there are still first cleaning targets that cannot be cleaned or the power of the cleaning device is lower than a preset power threshold, the target locations of the first cleaning targets that have not been cleaned by the second deep cleaning are uploaded to local storage or cloud storage for storage. This allows the cleaning device to quickly identify the target type of the cleaning targets in the first cleaning area the next time it performs a cleaning task on the first cleaning area, thereby improving the cleaning efficiency of the cleaning device.

[0121] based on Figure 1 The following is a schematic diagram of the scene. Figure 8 , the target cleaning device provided in the embodiment of the present application is introduced in detail. It should be noted that, Figure 8 The target cleaning device in the present application is used to execute the Figure 2-Figure 7 For the convenience of explanation, only the part related to the embodiment of the present application is shown. For the specific technical details not disclosed, please refer to the present application. Figure 2-Figure 7 In the embodiment shown, the target cleaning device 700 may include a type acquisition unit 701, a target cleaning unit 702, a position acquisition unit 703, and a data writing unit 704, as follows:

[0122] A type acquisition unit 701 is configured to acquire a target type of a first cleaning target in a first cleaning area;

[0123] The target cleaning unit 702 is configured to clean the first cleaning target using a first cleaning mode if the target type is a first type;

[0124] a position acquisition unit 703 for stopping cleaning of the first cleaning target and acquiring a target position of the first cleaning target in the first cleaning area if the number of cleaning times for the first cleaning target reaches a preset number threshold and the first cleaning target is not cleaned;

[0125] The data writing unit 704 is configured to store the target information and the target position of the first cleaning target into the pause cleaning list.

[0126] In some embodiments, the type acquisition unit 701 further includes a first history data acquisition unit, a position acquisition unit, and a first position comparison unit.

[0127] A first historical data acquisition unit, configured to acquire historical cleaning data corresponding to a first cleaning area;

[0128] a position acquisition unit, configured to determine, from historical cleaning data, the number of cleaning times of each area position of the cleaning device in the first cleaning area, and determine the area position where the cleaning times are greater than or equal to a preset number threshold as the location of the stubborn garbage;

[0129] The first position comparison unit is configured to determine the target type of the first cleaning target as the first type if the first cleaning target is located at the location where the stubborn garbage is located.

[0130] In some embodiments, the type acquisition unit 701 further includes a second history data acquisition unit and a second position comparison unit.

[0131] A second historical data acquisition unit is used to acquire a historical paused cleaning list corresponding to the first cleaning area;

[0132] The second position comparison unit is configured to determine the target type of the first cleaning target as the first type if the location of the first cleaning target matches the historical location of any stubborn garbage in the historical pause cleaning list.

[0133] In some embodiments, the type acquisition unit 701 further includes a feature data acquisition unit, a first semantic determination unit, and a second semantic determination unit.

[0134] a feature data acquisition unit, configured to acquire feature data of the first cleaning target and determine semantic information of the first cleaning target based on the feature data;

[0135] a first semantic determination unit, configured to determine the target type of the first cleaning target as the first type if the semantic information matches any semantic word in a preset first type semantic library;

[0136] The second semantic determination unit is configured to determine the target type of the first cleaning target as the second type if the semantic information matches any semantic word in a preset second type semantic library.

[0137] In some embodiments, the type acquisition unit 701 further includes a mode switching unit and a target detection unit.

[0138] A mode switching unit, configured to enable a preset second cleaning mode to clean the first cleaning target, wherein the cleaning force of the second cleaning mode is less than the cleaning force of the first cleaning mode;

[0139] The target detection unit is used to stop cleaning the first cleaning target if the cleaning times reach a preset threshold and the first cleaning target has not been cleaned, and store the target information of the first cleaning target and the target position of the first cleaning target in the first cleaning area into a paused cleaning list.

[0140] In some embodiments, the type acquisition unit 701 further includes a regional environment data acquisition unit and a regional division unit.

[0141] A regional environment data acquisition unit is used to acquire regional environment data of a clean area, and divide the clean area into regions based on the regional environment data to obtain a clean area set;

[0142] The area division unit is configured to determine a first cleaning area from the cleaning area set based on a spatial position of the cleaning device in the cleaning area, where the first cleaning area is the cleaning area closest to the cleaning device.

[0143] In some embodiments, the data writing unit 704 further includes a data sorting unit and a device calling unit.

[0144] a data sorting unit, configured to sort the first cleaning targets in the suspended cleaning list based on target information of the first cleaning targets and a relative distance between the first cleaning targets and the cleaning device, to obtain a sorted cleaning list if the second type of garbage does not exist in the first cleaning area;

[0145] The device calling unit is used to call the cleaning device to sequentially clean each first cleaning target in the sorted cleaning list in a first cleaning mode.

[0146] In some embodiments, the data writing unit 704 further includes a data cleaning unit.

[0147] The data cleaning unit is used to clear the paused cleaning list if it is detected that the cleaning device moves from the first cleaning area to the second cleaning area. The first cleaning area and the second working area are any two different cleaning areas in the cleaning area set.

[0148] In an embodiment of the present application, by identifying the target type of the first cleaning target, the cleaning equipment is adapted to the cleaning mode corresponding to the target type, thereby ensuring that the first cleaning target is processed in a targeted manner; when it is detected that the number of cleaning times for the first cleaning target reaches a preset threshold and still cannot be cleared, the invalid cleaning cycle for the first cleaning target is actively terminated to avoid the cleaning equipment from falling into local repeated operations and causing power loss and time waste; at the same time, the target position and target information of the first cleaning target are saved to the paused cleaning list, which not only provides data support for subsequent centralized processing or manual intervention, but also prevents the global cleaning path from being repeatedly interrupted, thereby effectively improving the overall cleaning efficiency of the cleaning equipment.

[0149] In addition, the target cleaning device provided in the above embodiment and a target cleaning method embodiment belong to the same concept, and the implementation process thereof is detailed in the method embodiment and will not be repeated here.

[0150] The serial numbers of the embodiments of the present application are for descriptive purposes only and do not represent the merits of the embodiments. In some cases, the actions or steps described in the claims may be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0151] See Figure 9 , provides a schematic structural diagram of a cleaning device according to an embodiment of the present application. Figure 9 As shown, the cleaning device 800 includes a processor 801 and a memory 802. The processor 801 is electrically connected to the memory 802.

[0152] Processor 801 is the control center of cleaning equipment 800 and may include one or more processing cores. Processor 801 utilizes various interfaces and lines to connect the various parts of the entire cleaning equipment, and by running or calling the computer program stored in memory 802, and calling the data stored in memory 802, performs the various functions of cleaning equipment and processes data, thereby conducting overall management and control of cleaning equipment. Optionally, processor 801 may be implemented using at least one hardware form in digital signal processing (DSP), field programmable gate array (FPGA), or programmable logic array (PLA). Processor 801 may be integrated with one or more combinations of a CPU, a target cleaner (GPU), and a modem. Among them, CPU primarily processes operating systems, user pages, and applications; GPU is used to be responsible for rendering and drawing display content; and modem is used to process wireless communications. It is understandable that the above-mentioned modem may also not be integrated into processor 801 and may be implemented separately by a communication chip.

[0153] Memory 802 can be used to store software programs and modules. Processor 801 executes various functional applications and data processing by running computer programs and modules stored in memory 802. Memory 802 can mainly include a program storage area and a data storage area. The program storage area can store an operating system, computer programs required for at least one function, etc.; the data storage area can store data generated based on the use of the cleaning device, etc.

[0154] In addition, the memory 802 may include a high-speed random access memory and a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage device. Accordingly, the memory 802 may also include a memory controller to provide the processor 801 with access to the memory 802.

[0155] In the embodiment of the present application, the processor 801 in the cleaning device 800 loads instructions corresponding to one or more computer program processes into the memory 802 according to the following steps, and the processor 801 runs the computer program stored in the memory 802 to implement various functions as follows:

[0156] Obtaining a target type of a first cleaning target in a first cleaning area;

[0157] If the target type is the first type, the first cleaning mode is used to clean the first cleaning target;

[0158] If the number of cleaning times for the first cleaning target reaches a preset number threshold and the first cleaning target is not cleaned, stopping the cleaning of the first cleaning target and obtaining a target position of the first cleaning target in the first cleaning area;

[0159] The target information and the target position of the first cleaning target are stored in a pause cleaning list.

[0160] Optionally, when executing to obtain the target type of the first cleaning target in the first cleaning area, the processor 801 specifically performs the following: obtaining historical cleaning data corresponding to the first cleaning area; determining the number of cleaning times of each area position in the first cleaning area by the cleaning equipment from the historical cleaning data, and determining the area position whose cleaning times are greater than or equal to a preset number threshold as the location of the stubborn garbage; if the first cleaning target is at the location of the stubborn garbage, determining the target type of the first cleaning target as the first type.

[0161] Optionally, when executing to obtain the target type of the first cleaning target in the first cleaning area, the processor 801 specifically performs: obtaining the historical pause cleaning list corresponding to the first cleaning area; if the location of the first cleaning target matches the historical location of any historical stubborn garbage in the historical pause cleaning list, the target type of the first cleaning target is determined to be the first type.

[0162] Optionally, when executing to obtain the target type of the first cleaning target in the first cleaning area, the processor 801 specifically performs: obtaining feature data of the first cleaning target, and determining semantic information of the first cleaning target based on the feature data; if the semantic information matches any semantic word in a preset first type semantic library, the target type of the first cleaning target is determined to be the first type; if the semantic information matches any semantic word in a preset second type semantic library, the target type of the first cleaning target is determined to be the second type.

[0163] Optionally, after the processor 801 determines the target type of the first cleaning target as the second type if the semantic information matches any semantic word in the preset second type semantic library, it specifically executes: enabling the preset second cleaning mode to clean the first cleaning target, and the cleaning intensity of the second cleaning mode is less than the cleaning intensity of the first cleaning mode; if the number of cleaning times reaches the preset number threshold and the first cleaning target is not cleaned, the cleaning of the first cleaning target is stopped, and the target information of the first cleaning target and the target position of the first cleaning target in the first cleaning area are stored in the paused cleaning list.

[0164] Optionally, before executing the acquisition of the target type of the first cleaning target in the first cleaning area, the processor 801 specifically performs the following: obtaining the regional environmental data of the cleaning area, dividing the cleaning area into regions based on the regional environmental data, and obtaining a cleaning area set; determining the first cleaning area from the cleaning area set based on the spatial position of the cleaning equipment in the cleaning area, the first cleaning area being the cleaning area closest to the cleaning equipment.

[0165] Optionally, after storing the target information and target position of the first cleaning target in the paused cleaning list, the processor 801 specifically performs the following: if there is no second type of garbage in the first cleaning area, sorting the first cleaning targets in the paused cleaning list based on the target information of each first cleaning target in the paused cleaning list and the relative distance between each first cleaning target and the cleaning device to obtain a sorted cleaning list; calling the cleaning device to sequentially clean each first cleaning target in the sorted cleaning list in the first cleaning mode.

[0166] Optionally, after executing the call to the cleaning device to sequentially clean each first cleaning target in the sorted cleaning list in the first cleaning mode, the processor 801 specifically performs the following: if it is detected that the cleaning device moves from the first cleaning area to the second cleaning area, the paused cleaning list is cleared, and the first cleaning area and the second working area are any two different cleaning areas in the cleaning area set.

[0167] In an embodiment of the present application, by identifying the target type of the first cleaning target, the cleaning equipment is adapted to the cleaning mode corresponding to the target type, thereby ensuring that the first cleaning target is processed in a targeted manner; when it is detected that the number of cleaning times for the first cleaning target reaches a preset threshold and still cannot be cleared, the invalid cleaning cycle for the first cleaning target is actively terminated to avoid the cleaning equipment from falling into local repeated operations and causing power loss and time waste; at the same time, the target position and target information of the first cleaning target are saved to a paused cleaning list, which not only provides data support for subsequent centralized processing or manual intervention, but also prevents the global cleaning path from being repeatedly interrupted, thereby effectively improving the overall cleaning efficiency of the cleaning equipment.

[0168] In addition, the device provided in the embodiment of the present application can specifically be a chip, component or module, and the chip may include a connected processor and memory; wherein the memory is used to store instructions, and when the processor calls and executes the instructions, the chip can execute a target cleaning method provided in the above embodiment.

[0169] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program runs on a computer, the computer executes the above-mentioned related method steps to implement a target cleaning method provided by the above-mentioned embodiment.

[0170] An embodiment of the present application also provides a computer program product. When the computer program product is run on a computer, it enables the computer to execute the above-mentioned related steps to implement a target cleaning method provided by the above-mentioned embodiment.

[0171] Among them, the device, computer-readable storage medium, computer program product or chip provided in the embodiments of the present application are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding methods provided above, and will not be repeated here.

[0172] Through the description of the above implementation methods, technical personnel in the relevant field can understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0173] In the embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the coupling or direct coupling or communication connection between the related ones shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0174] The above content is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A target cleaning method, characterized in that: Applied to cleaning equipment, the method comprises: Obtaining a target type of a first cleaning target in a first cleaning area; If the target type is the first type, the first cleaning target is cleaned using the first cleaning mode; If the number of cleaning times for the first cleaning target reaches a preset number threshold and the first cleaning target is not cleaned, stopping the cleaning of the first cleaning target and obtaining a target position of the first cleaning target in the first cleaning area; The target information of the first cleaning target and the target position are stored in a pause cleaning list.

2. The method according to claim 1, characterized in that The acquiring the target type of the first cleaning target in the first cleaning area includes: Obtaining historical cleaning data corresponding to the first cleaning area; Determining the cleaning times of each area in the first cleaning area by the cleaning device from the historical cleaning data, and determining the area where the cleaning times are greater than or equal to a preset threshold as the location of the stubborn garbage; If the first cleaning target is located at the location of the stubborn garbage, the target type of the first cleaning target is determined to be the first type.

3. The method according to claim 1, characterized in that The acquiring the target type of the first cleaning target in the first cleaning area includes: Get the historical paused cleaning list corresponding to the first cleaning area; If the location of the first cleaning target matches the historical location of any historical stubborn garbage in the historical pause cleaning list, the target type of the first cleaning target is determined to be the first type.

4. The method according to claim 1, wherein The acquiring the target type of the first cleaning target in the first cleaning area includes: Acquiring feature data of a first cleaning target, and determining semantic information of the first cleaning target based on the feature data; If the semantic information matches any semantic word in the preset first type semantic library, the target type of the first cleaning target is determined to be the first type; If the semantic information matches any semantic word in a preset second type semantic library, the target type of the first cleaning target is determined to be the second type.

5. The method according to claim 4, characterized in that If the semantic information matches any semantic word in the preset second type semantic library, then after determining the target type of the first cleaning target as the second type, the method further includes: Activate a preset second cleaning mode to clean the first cleaning target, wherein the cleaning force of the second cleaning mode is less than the cleaning force of the first cleaning mode; If the cleaning times reaches a preset threshold and the first cleaning target is not cleaned, the cleaning of the first cleaning target is stopped, and the target information of the first cleaning target and the target position of the first cleaning target in the first cleaning area are stored in a paused cleaning list.

6. The method according to claim 1, characterized in that Before acquiring the target type of the first cleaning target in the first cleaning area, the method further includes: Acquiring regional environmental data of a cleaning area, and dividing the cleaning area into regions based on the regional environmental data to obtain a cleaning area set; A first cleaning area is determined from the cleaning area set based on a spatial position of the cleaning device in the cleaning area, where the first cleaning area is the cleaning area closest to the cleaning device.

7. The method according to claim 1, characterized in that After storing the target information of the first cleaning target and the target position in the pause cleaning list, the method includes: If the second type of garbage does not exist in the first cleaning area, sorting the first cleaning targets in the paused cleaning list based on the target information of the first cleaning targets and the relative distance between the first cleaning targets and the cleaning device to obtain a sorted cleaning list; The cleaning device is called to sequentially clean each of the first cleaning targets in the sorted cleaning list in a first cleaning mode.

8. The method according to claim 7, characterized in that After calling the cleaning device to sequentially clean each of the first cleaning targets in the sorted cleaning list in the first cleaning mode, the method includes: If it is detected that the cleaning device moves from the first cleaning area to the second cleaning area, the pause cleaning list is cleared, and the first cleaning area and the second working area are any two different cleaning areas in the cleaning area set.

9. A target cleaning device, characterized in that: Applied to cleaning equipment, the device comprises: A type acquisition unit, configured to acquire a target type of a first cleaning target in a first cleaning area; a target cleaning unit, configured to clean the first cleaning target using a first cleaning mode if the target type is a first type; a position acquiring unit, configured to stop cleaning the first cleaning target and acquire a target position of the first cleaning target in the first cleaning area if the number of cleaning operations for the first cleaning target reaches a preset number threshold and the first cleaning target is not cleaned; The data writing unit is configured to store the target information of the first cleaning target and the target position into a pause cleaning list.

10. A cleaning device, characterized in that: The cleaning equipment comprises: a memory for storing executable program code; A processor is configured to call and run the executable program code from the memory, so that the cleaning device performs the target cleaning method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed, the target cleaning method according to any one of claims 1 to 8 is implemented.

Images