Intelligent sweeping method and device of sweeper and computer readable storage medium

Abstract

The invention discloses an intelligent sweeping method and device of a sweeper and a computer readable storage medium. The method comprises the following steps: receiving a current environment video image transmitted by a home host; acquiring current position information of the sweeper; inputting the current environment video image and the current position information into a path planning model, and processing the current environment video image and the current position information by using the path planning model to obtain a stain cleaning path; and the stain cleaning path is transmitted to the home host, so that the home host issues the stain cleaning path to the sweeper, and the sweeper performs cleaning according to the stain cleaning path after receiving the stain cleaning path. The technical problems that in the prior art, a sweeper usually conducts sweeping according to a preset fixed path, stains cannot be effectively recognized, the sweeping path cannot be dynamically adjusted, the sweeping efficiency is low, and omission is likely to happen are solved.

Description

Technical Field

[0001] The present invention relates to the field of household appliance control technology, and in particular to an intelligent cleaning method and device for a sweeping machine, and a computer-readable storage medium. Background Art

[0002] As an important part of the smart home cleaning field, the level of intelligence of sweepers directly affects the quality of life and experience of users. However, although the sweepers on the current market have certain autonomous navigation and cleaning capabilities, they still have many shortcomings in accurately identifying stains and efficiently cleaning specific areas.

[0003] First, traditional sweepers often use random or preset paths to clean, lacking the ability to perceive and dynamically adjust to changes in the home environment in real time. This cleaning method is not only inefficient and easy to miss stains, but also may waste energy and time due to repeated cleaning.

[0004] Secondly, although some sweepers are equipped with basic obstacle avoidance sensors that can avoid collisions with furniture and other obstacles to a certain extent, their obstacle avoidance effect is still limited when facing complex home environments. In particular, traditional sweepers often have difficulty effectively identifying and cleaning stains hidden in corners, under furniture or on carpets.

[0005] In addition, with the rapid development of the Internet of Things and artificial intelligence technologies, home cameras have gradually become popular in thousands of households. These cameras can not only provide real-time monitoring of home security, but also have the ability of image recognition and intelligent analysis. However, at present, the application of most home cameras is still at the level of security monitoring, and its potential in the field of home cleaning has not yet been fully explored.

[0006] Traditional sweepers have the following shortcomings in cleaning: (1) Difficulty in accurately identifying stains: Traditional sweepers are unable to effectively identify and locate stains during the cleaning process, resulting in low cleaning efficiency and easy omissions; (2) Poor cleaning path planning: Existing sweepers mostly use random or preset paths for cleaning, and lack adaptability to the complexity of home environments and changes in stain distribution; (3) Insufficient obstacle avoidance and adaptability: Traditional sweepers have limitations in obstacle avoidance and adapting to complex environments, and are prone to collisions with obstacles such as furniture and pets; (4) User experience and personalized needs: Existing sweepers are lacking in user experience and personalized services, making it difficult to meet the diverse needs of users.

[0007] Currently, no effective solution has been proposed for the problem that the sweeping machines in the above-mentioned related technologies usually clean according to a preset fixed path, cannot effectively identify stains and dynamically adjust the cleaning path, resulting in low cleaning efficiency and easy omissions. Summary of the invention

[0008] The embodiments of the present invention provide an intelligent cleaning method and device for a sweeping machine, and a computer-readable storage medium, so as to at least solve the technical problems in the related art that sweeping machines usually clean according to a preset fixed path, cannot effectively identify stains and dynamically adjust the cleaning path, resulting in low cleaning efficiency and easy omissions.

[0009] According to one aspect of an embodiment of the present invention, there is provided an intelligent cleaning method of a sweeping machine, comprising: receiving a current environment video image transmitted by a home host, wherein the current environment video image is an image captured by an image acquisition device of a target room and transmitted to the home host, and the target room is a room that the sweeping machine needs to clean; obtaining current position information of the sweeping machine, wherein the current position information is position information of the current position of the sweeping machine; inputting the current environment video image and the current position information into a path planning model, so as to use the path planning model to calculate the current environment video image and the current position information; The current position information is processed to obtain a stain cleaning path, wherein the path planning model is trained by means of machine learning using multiple groups of first training data, and each of the multiple groups of first training data includes: a sample current environment video image, a sample current position information, and a sample stain cleaning path corresponding to the sample current environment video image and the sample current position information; the stain cleaning path is transmitted to the home host, so that the home host sends the stain cleaning path to the sweeping machine, wherein the sweeping machine cleans according to the stain cleaning path after receiving the stain cleaning path.

[0010] Optionally, receiving the current environment video image transmitted by the home host includes: receiving a communication connection request sent by the home host, and establishing a first communication channel with the home host based on the communication connection request, wherein the first communication channel is a channel for data transmission with the home host, and the home host receives the current environment video image through a second communication channel, and the second communication channel is a channel for transmitting data between the home host and the image acquisition device; based on the first communication channel, receiving the current environment video image transmitted by the home host.

[0011] Optionally, obtaining the current position information of the sweeping machine includes at least one of the following: parsing the current environment video image to obtain the current position information of the sweeping machine; receiving the position information transmitted by the home host, and determining that the position information is the current position information of the sweeping machine, wherein the position information is collected by a sensor integrated in the sweeping machine and transmitted to the home host through a third communication channel, and the third communication channel is a channel for transmitting data between the home host and the sweeping machine.

[0012] Optionally, the current environment video image and the current position information are input into a path planning model, and the path planning model is used to process the current environment video image and the current position information to obtain a stain cleaning path, including: parsing the current environment video image to obtain the stain area in the target room; determining the cleaning priority of each stain area; inputting the current environment video image, the stain area, the cleaning priority and the current position information into the path planning model, and the path planning model is used to process the current environment video image, the stain area, the cleaning priority and the current position information to obtain the stain cleaning path.

[0013] Optionally, determining the cleaning priority of each of the stained areas includes: obtaining a historical stain cleaning path when the sweeper performs a cleaning operation within a historical time period; determining a cleaning order when the sweeper cleans the historical stained areas according to the historical stain cleaning path; determining a stain cleaning priority of the stain type according to the cleaning order and the stain type corresponding to the historical stain area; determining a current stain type corresponding to each of the stained areas; and determining the cleaning priority of each of the stained areas according to the stain cleaning priority and the current stain type corresponding to each of the stained areas.

[0014] Optionally, determining the cleaning priority of each of the stained areas includes: receiving cleaning priority instruction information uploaded by a terminal device or the home host; and determining the cleaning priority of each of the stained areas according to the cleaning priority instruction information.

[0015] Optionally, the intelligent cleaning method of the sweeping machine further includes: receiving updated position information transmitted by the home host during the process in which the sweeping machine cleans according to the stain cleaning path, wherein the updated position information is position information after the sweeping machine moves according to the obstacle avoidance path, and the obstacle avoidance path is a path generated by an obstacle avoidance path generation model built into the sweeping machine when there is an obstacle within a predetermined range of the sweeping machine, and the obstacle avoidance path generation model is trained by deep learning using multiple sets of second training data, and each of the multiple sets of second training data includes: sample obstacle information, Sample current position information, and a sample obstacle avoidance path corresponding to the sample obstacle information and the sample current position information; inputting the current environment video image and the updated position information into the path planning model, so as to use the path planning model to process the current environment video image and the updated position information to obtain a target stain cleaning path; transmitting the target stain cleaning path to the home host, so that the home host sends the target stain cleaning path to the sweeping machine, wherein the sweeping machine cleans according to the target stain cleaning path after receiving the target stain cleaning path.

[0016] According to another aspect of an embodiment of the present invention, there is also provided an intelligent cleaning device of a sweeping machine, comprising: a first receiving unit, for receiving a current environment video image transmitted by a home host, wherein the current environment video image is an image of a target room currently captured by an image acquisition device and transmitted to the home host, and the target room is a room that the sweeping machine needs to clean; a first acquisition unit, for acquiring current position information of the sweeping machine, wherein the current position information is position information of the current position of the sweeping machine; a second acquisition unit, for inputting the current environment video image and the current position information into a path planning model, so as to use the path planning model to obtain the current position information of the sweeping machine; The front environment video image and the current position information are processed to obtain a stain cleaning path, wherein the path planning model is trained by means of machine learning using multiple groups of first training data, and each of the multiple groups of first training data includes: a sample current environment video image, a sample current position information, and a sample stain cleaning path corresponding to the sample current environment video image and the sample current position information; a first transmission unit is used to transmit the stain cleaning path to the home host, so that the home host sends the stain cleaning path to the sweeper, wherein the sweeper cleans according to the stain cleaning path after receiving the stain cleaning path.

[0017] Optionally, the first receiving unit includes: a first receiving module, used to receive a communication connection request sent by the home host, and establish a first communication channel with the home host based on the communication connection request, wherein the first communication channel is a channel for data transmission with the home host, and the home host receives the current environment video image through a second communication channel, and the second communication channel is a channel for transmitting data between the home host and the image acquisition device; a second receiving module, used to receive the current environment video image transmitted by the home host based on the first communication channel.

[0018] Optionally, the first acquisition unit includes at least one of the following: a first acquisition module, used to parse the current environment video image to obtain the current position information of the sweeping machine; a third receiving module, used to receive the position information transmitted by the home host, and determine that the position information is the current position information of the sweeping machine, wherein the position information is collected by a sensor integrated in the sweeping machine and transmitted to the home host through a third communication channel, and the third communication channel is a channel for transmitting data between the home host and the sweeping machine.

[0019] Optionally, the second acquisition unit includes: a second acquisition module, used to analyze the current environment video image to obtain the stain area in the target room; a determination module, used to determine the cleaning priority of each stain area; a third acquisition module, used to input the current environment video image, the stain area, the cleaning priority and the current position information into the path planning model, so as to use the path planning model to process the current environment video image, the stain area, the cleaning priority and the current position information to obtain the stain cleaning path.

[0020] Optionally, the determination module includes: an acquisition submodule, used to acquire the historical stain cleaning path when the sweeper performs the cleaning operation within the historical time period; a first determination submodule, used to determine the cleaning order of the sweeper when cleaning the historical stain area according to the historical stain cleaning path; a second determination submodule, used to determine the stain cleaning priority of the stain type according to the cleaning order and the stain type corresponding to the historical stain area; a third determination submodule, used to determine the current stain type corresponding to each of the stain areas; and a fourth determination submodule, used to determine the cleaning priority of each of the stain areas according to the stain cleaning priority and the current stain type corresponding to each of the stain areas.

[0021] Optionally, the determination module includes: a receiving submodule, used to receive cleaning priority instruction information uploaded by the terminal device or the home host; and a fifth determination submodule, used to determine the cleaning priority of each of the stained areas according to the cleaning priority instruction information.

[0022] Optionally, the intelligent cleaning device of the sweeping machine further includes: a third receiving unit, used to receive updated position information transmitted by the home host during the process of the sweeping machine cleaning according to the stain cleaning path, wherein the updated position information is the position information of the sweeping machine after the sweeping machine moves according to the obstacle avoidance path, and the obstacle avoidance path is a path generated by an obstacle avoidance path generation model built into the sweeping machine when there is an obstacle within a predetermined range of the sweeping machine, and the obstacle avoidance path generation model is trained by deep learning using multiple sets of second training data, and each of the multiple sets of second training data includes: sample obstacle information, sample current position information, and a sample obstacle avoidance path corresponding to the sample obstacle information and the sample current position information; a third acquisition unit, used to input the current environment video image and the updated position information into the path planning model, so as to use the path planning model to process the current environment video image and the updated position information to obtain a target stain cleaning path; a second transmission unit, used to transmit the target stain cleaning path to the home host, so that the home host sends the target stain cleaning path to the sweeping machine, wherein the sweeping machine cleans according to the target stain cleaning path after receiving the target stain cleaning path.

[0023] According to another aspect of an embodiment of the present invention, an intelligent cleaning system for a sweeping machine is further provided. The intelligent cleaning system for a sweeping machine uses any one of the intelligent cleaning methods for a sweeping machine described above.

[0024] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is further provided, wherein the computer-readable storage medium includes a stored program, wherein the program executes any one of the above-described intelligent cleaning methods for a sweeping machine.

[0025] According to another aspect of an embodiment of the present invention, a processor is further provided, and the processor is used to run a program, wherein the program executes any one of the above-mentioned intelligent cleaning methods of a sweeping machine when running.

[0026] According to another aspect of an embodiment of the present invention, a computer program product is further provided, comprising computer instructions, wherein when the computer instructions are executed by a processor, any one of the above-mentioned intelligent cleaning methods for a sweeping machine is executed.

[0027] In an embodiment of the present invention, a current environment video image transmitted by a home host is received, wherein the current environment video image is an image of a target room currently captured by an image acquisition device and transmitted to the home host, and the target room is a room that a sweeper needs to clean; current position information of the sweeper is obtained, wherein the current position information is position information of the current position of the sweeper; the current environment video image and the current position information are input into a path planning model, so as to process the current environment video image and the current position information using the path planning model to obtain a stain cleaning path, wherein the path planning model is trained using multiple groups of first training data by machine learning, and each of the multiple groups of first training data includes: a sample current environment video image, a sample current position information, and a sample stain cleaning path corresponding to the sample current environment video image and the sample current position information; the stain cleaning path is transmitted to the home host, so that the home host sends the stain cleaning path to the sweeper, wherein the sweeper cleans according to the stain cleaning path after receiving the stain cleaning path. Through the above technical scheme, the home host controls the camera to collect image data in the room in real time, and transmits the image data to the cloud, so that the cloud plans the cleaning path of the sweeper based on the image data, and then the home host sends the cleaning path transmitted from the cloud to the sweeper, so that the sweeper cleans according to the cleaning path. The technical effect of dynamically adjusting the cleaning path of the sweeper in real time according to the changes in the environment in the room is achieved, the flexibility and accuracy of the sweeper's cleaning is improved, and the cleaning efficiency of the sweeper is improved, thereby solving the technical problems in the related technology that the sweeper usually cleans according to a preset fixed path, cannot effectively identify stains and dynamically adjust the cleaning path, resulting in low cleaning efficiency and easy omissions. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0029] Figure 1 It is a hardware structure block diagram of a mobile terminal of an intelligent cleaning method of a sweeping machine according to an embodiment of the present invention;

[0030] Figure 2 is a flow chart of an intelligent cleaning method of a sweeping machine according to an embodiment of the present invention;

[0031] Figure 3 is a schematic diagram of an intelligent cleaning system of a sweeping machine according to an embodiment of the present invention;

[0032] Figure 4 is a flow chart of an optional intelligent cleaning method of a sweeping machine according to an embodiment of the present invention;

[0033] Figure 5 is a schematic diagram of an intelligent cleaning device of a sweeping machine according to an embodiment of the present invention. DETAILED DESCRIPTION

[0034] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0035] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0036] As introduced in the background technology, in the related art, the sweeping machine usually cleans according to a preset fixed path, cannot effectively identify stains and dynamically adjust the cleaning path, resulting in low cleaning efficiency and easy omissions. In view of the above defects, an intelligent cleaning method and device for a sweeping machine and a computer-readable storage medium are provided in the embodiments of the present invention.

[0037] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0038] The method embodiments provided in the embodiments of the present invention can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 1 is a hardware structure block diagram of a mobile terminal of an intelligent cleaning method of a sweeping machine according to an embodiment of the present invention. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0039] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the intelligent cleaning method of the sweeper in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, the above method is implemented. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. The transmission device 106 is used to receive or send data via a network. The above-mentioned specific examples of the network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0040] According to an embodiment of the present invention, a method embodiment of an intelligent cleaning method for a sweeping machine is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0041] Figure 2 is a flow chart of an intelligent cleaning method of a sweeping machine according to an embodiment of the present invention. Figure 2 As shown, the method comprises the following steps:

[0042] Step S202, receiving the current environment video image transmitted by the home host, wherein the current environment video image is an image captured by the image acquisition device of the target room and transmitted to the home host, and the target room is the room that the vacuum cleaner needs to clean.

[0043] Optionally, the above-mentioned image acquisition device may include but is not limited to: a camera, a smart camera, an infrared sensor and other devices that can be used to acquire images.

[0044] Combine the following Figure 3 and Figure 4 The above embodiments of the present invention are described in detail. Figure 3 is a schematic diagram of an intelligent cleaning system of a sweeper according to an embodiment of the present invention, Figure 4 It is a flow chart of an optional intelligent cleaning method of a sweeping machine according to an embodiment of the present invention.

[0045] like Figure 3 As shown, the intelligent cleaning system of the sweeping machine provided by the embodiment of the present invention is composed of four parts, namely, a home host, a cloud, a camera and a sweeping machine. The home host serves as an intermediate control platform between the cloud and the camera and the sweeping machine, and is responsible for receiving the image data collected by the camera and the sensor data sensed by the sensors on the sweeping machine and transmitting them to the cloud for processing. The cloud is responsible for running the intelligent learning model and the path planning algorithm according to the data transmitted by the home host to generate a corresponding cleaning path, and transmitting the generated path to the home host, which is then sent down to the sweeping machine by the home host to control the sweeping machine to perform the corresponding cleaning operation according to the path. In short, the home host is an intermediate control platform, responsible for transmitting data and simple processing, the camera is responsible for collecting environmental video images in the room, the sweeping machine is equipped with a variety of sensors such as lidar, gyroscope, collision sensor, etc., for real-time perception of the surrounding environment, and the cloud service platform is used for data processing, remote monitoring, model updating and data analysis.

[0046] According to the above embodiment of the present invention, in the above step S202, receiving the current environment video image transmitted by the home host includes: receiving a communication connection request sent by the home host, and establishing a first communication channel with the home host based on the communication connection request, wherein the first communication channel is a channel for data transmission with the home host, and the home host receives the current environment video image through a second communication channel, and the second communication channel is a channel for transmitting data between the home host and the image acquisition device; based on the first communication channel, receiving the current environment video image transmitted by the home host.

[0047] As above Figure 4As shown, after the camera acquires the image data, it transmits it to the home host, which then transmits it to the cloud; here, there is a communication connection relationship between the home host and the cloud, the camera and the sweeper to facilitate data transmission. For example, the home host and the cloud can transmit data through a first communication channel (such as the home host can transmit the image data transmitted by the camera and the sensor data transmitted by the sweeper to the cloud through the first communication channel, and the cloud can also transmit the generated cleaning path to the home host through the first communication channel), the home host and the camera can transmit data through a second communication channel (such as the home host can transmit the image acquisition instruction to the camera through the second communication channel, and the camera can also transmit the acquired image data to the home host through the second communication channel), and the home host and the sweeper can transmit data through a third communication channel (such as the sweeper can transmit the perceived data to the home host through the third communication channel, and the home host can also transmit the cleaning path transmitted from the cloud to the sweeper through the third communication channel).

[0048] Step S204, obtaining the current position information of the sweeping machine, wherein the current position information is the position information of the current position of the sweeping machine.

[0049] In this embodiment, the current location information of the sweeping machine can be obtained as the starting point for cleaning path planning.

[0050] According to the above embodiment of the present invention, in the above step S204, the current position information of the sweeping machine is obtained, including at least one of the following: parsing the current environment video image to obtain the current position information of the sweeping machine; receiving the position information transmitted by the home host, and determining that the position information is the current position information of the sweeping machine, wherein the position information is collected by a sensor integrated in the sweeping machine and transmitted to the home host through a third communication channel, and the third communication channel is a channel for transmitting data between the home host and the sweeping machine.

[0051] Specifically, the position information of the sweeping machine can be obtained by analyzing the image data collected by the camera (ie, the current environment video image), or the position information of the sweeping machine can be determined by the data sensed by the sensor of the sweeping machine.

[0052] Step S206, input the current environment video image and the current position information into the path planning model, so as to use the path planning model to process the current environment video image and the current position information to obtain the stain cleaning path, wherein the path planning model is trained by machine learning using multiple groups of first training data, and each of the multiple groups of first training data includes: a sample current environment video image, a sample current position information, and a sample stain cleaning path corresponding to the sample current environment video image and the sample current position information.

[0053] In this embodiment, the path planning model in the cloud can be used to process the received video image of the current environment in the room and the current position information of the sweeping machine to plan the path for the sweeping machine to clean stains and obtain the stain cleaning path.

[0054] According to the above embodiment of the present invention, in the above step S206, the current environment video image and the current position information are input into the path planning model, so as to use the path planning model to process the current environment video image and the current position information to obtain the stain cleaning path, including: parsing the current environment video image to obtain the stain area in the target room; determining the cleaning priority of each stain area; inputting the current environment video image, the stain area, the cleaning priority and the current position information into the path planning model, so as to use the path planning model to process the current environment video image, the stain area, the cleaning priority and the current position information to obtain the stain cleaning path.

[0055] As above Figure 4 As shown, the cloud can perform stain recognition on the received video image of the current environment to automatically identify and mark the stained area (the stains here may include but are not limited to: dust, solid stains, liquid stains, food residues, etc.). In addition to parsing the received image data in the cloud to identify the stained area, a smart camera can also be used to use the image recognition technology to automatically identify and mark the stained area in the room when the image data is collected; the position of the marked stained area can then be calculated to provide a data basis for subsequent planning of the cleaning path; in addition, the type of stained area or the use of The priority of each stain area is defined according to the cleaning order set by the user; finally, the image data, stain area, location and cleaning priority of the stain area, and the location information of the current location of the sweeper can be input into the path planning model, so that the path planning model can be used to process the input data, comprehensively consider multiple factors such as home layout, obstacle distribution, stain location, cleaning priority and historical cleaning data, so as to dynamically generate the optimal stain cleaning path; during the path planning process, the model will give priority to the stain area to ensure efficient removal of stubborn stains, and at the same time adjust the path according to the real-time status of the sweeper such as the power level and cleaning efficiency to avoid power exhaustion or repeated cleaning.

[0056] The intelligent path planning algorithm used in the path planning model used here mainly involves the reward mechanism and the balance mechanism, which are described in detail below: (1) The reward mechanism is the key to achieving the optimization of the cleaning efficiency and energy consumption balance, which is specifically implemented as follows: ① Construction of reward function: A multi-objective optimization reward function is designed, which comprehensively considers factors such as cleaning coverage, cleaning speed, energy consumption and battery life. Each item in the reward function is weighted according to its contribution to the overall cleaning benefit to ensure that the optimization of the cleaning path can take into account both efficiency and energy consumption; ② Optimization in the learning process: While the sweeper is performing the cleaning task, the home host calculates the reward value of the current cleaning path in real time, and adjusts the parameters in the path planning algorithm based on the reward value feedback. Through continuous iteration and optimization, the path planning algorithm gradually learns how to reduce energy consumption and increase cleaning speed while ensuring cleaning coverage, thereby maximizing long-term cleaning benefits; ③ User-defined priority: Users can flexibly set cleaning priorities according to their personal needs through the mobile phone APP or the home host touch screen. For example, users can choose to prioritize cleaning high-dust areas or quickly complete the whole house cleaning. These settings will directly affect the weight distribution of various indicators in the reward function, thereby guiding the sweeper to clean according to the user's expectations; (2) The balance mechanism is the key to achieving efficient cleaning of the sweeper in unknown or complex environments. The specific implementation is as follows: ① Design of intelligent balance mechanism: The balance mechanism dynamically adjusts the ratio of exploration and utilization based on the sweeper's historical cleaning data and current environmental status to ensure the dual improvement of cleaning efficiency and coverage; ② Learning curve and risk assessment: When exploring a new area, the sweeper will gradually accumulate experience and record effective paths and obstacle information during the exploration process through a learning curve. At the same time, the system also introduces a risk assessment mechanism to evaluate the risks that the sweeper may encounter when exploring new areas (such as running out of power, colliding with obstacles, etc.). Based on the risk assessment results, the system will dynamically adjust the exploration strategy to reduce ineffective exploration and improve cleaning efficiency; ③ Dynamic adjustment of cleaning strategy: During the cleaning process, the sweeper will dynamically adjust the cleaning strategy according to the current environmental status (such as obstacle distribution, stain location, etc.) and its own status (such as power, cleaning efficiency, etc.). For example, when the sweeper detects that the power is low, it will give priority to using known effective paths for cleaning to reduce ineffective exploration and energy consumption; when a new stain area is detected, the exploration intensity will be appropriately increased to ensure that the stain is removed in time.

[0057] In an optional embodiment of the present invention, the cleaning priority of each stain area is determined, including: obtaining the historical stain cleaning path when the sweeper performs cleaning operations within the historical time period; determining the cleaning order when the sweeper cleans the historical stain area according to the historical stain cleaning path; determining the stain cleaning priority of the stain type according to the cleaning order and the stain type corresponding to the historical stain area; determining the current stain type corresponding to each stain area; and determining the cleaning priority of each stain area according to the stain cleaning priority and the current stain type corresponding to each stain area.

[0058] Specifically, the priority of various stain types can be analyzed and determined based on the historical cleaning data within the historical time period and the cleaning order of the sweeper when performing the cleaning operation and the type of each stain area (data within the historical time period), and the cleaning priority of each stain area can be determined in combination with the stain type of the stain area that currently needs to be cleaned; for example, if the historical cleaning data shows that the sweeper usually gives priority to cleaning areas where stubborn stains (such as solid sticky substances) are located, it can be considered that the stain area where the stubborn stains are located has a higher cleaning priority.

[0059] In another optional embodiment of the present invention, determining the cleaning priority of each stained area includes: receiving cleaning priority instruction information uploaded by a terminal device or a home host; and determining the cleaning priority of each stained area according to the cleaning priority instruction information.

[0060] Specifically, in order to enhance the user experience, the embodiments of the present invention also provide a user-friendly interactive interface and rich personalized setting options. Users can view the cleaning progress, set the cleaning area, adjust the cleaning mode, etc. through the mobile phone APP or the home host touch screen. It also supports custom cleaning tasks. Users can flexibly set the cleaning time and cleaning area according to their personal habits and needs to implement personalized cleaning strategies. Users can flexibly set the cleaning priority according to their personal needs through the mobile phone APP or the home host touch screen; for example, users can choose to prioritize cleaning high-dust areas, or quickly complete whole-house cleaning.

[0061] It should be noted that the cleaning priority analyzed here is only one factor that the path planning model needs to consider when planning the path. The model summarizes and plans various factors when planning the path to obtain an optimal stain cleaning path. Therefore, the cleaning order of each stain area in the final cleaning path is not completely consistent with its cleaning priority. There may be some corresponding adjustments due to comprehensive consideration of other factors to ensure that the stain cleaning path is optimal overall.

[0062] Step S208, transmitting the stain cleaning path to the home host, so that the home host sends the stain cleaning path to the sweeping machine, wherein the sweeping machine cleans according to the stain cleaning path after receiving the stain cleaning path.

[0063] As above Figure 4 As shown, after the cloud generates the stain cleaning path, it will transmit it to the host, and the host will send the stain cleaning path to the sweeping machine, so that the sweeping machine cleans the stains in the room according to the received stain cleaning path.

[0064] According to the above embodiment of the present invention, the intelligent cleaning method of the sweeping machine also includes: receiving updated position information transmitted by the home host during the process of the sweeping machine cleaning according to the stain cleaning path, wherein the updated position information is the position information of the sweeping machine after moving according to the obstacle avoidance path, and the obstacle avoidance path is a path generated by the obstacle avoidance path generation model built into the sweeping machine when there is an obstacle within a predetermined range of the sweeping machine, and the obstacle avoidance path generation model is obtained by training using multiple groups of second training data through deep learning, and each of the multiple groups of second training data includes: sample obstacle information, sample current position information, and sample obstacle avoidance paths corresponding to the sample obstacle information and the sample current position information; inputting the current environment video image and the updated position information into the path planning model, so as to use the path planning model to process the current environment video image and the updated position information to obtain the target stain cleaning path; transmitting the target stain cleaning path to the home host, so that the home host sends the target stain cleaning path to the sweeping machine, wherein the sweeping machine cleans according to the target stain cleaning path after receiving the target stain cleaning path.

[0065] Specifically, while the sweeper is cleaning along the stain cleaning path, the sweeper can perceive the changes in the surrounding environment in real time through integrated lidar, gyroscope and other sensors. For example, when encountering obstacles such as furniture and pets, the sweeper will immediately activate the dynamic obstacle avoidance mechanism. Through the built-in obstacle recognition model (i.e., obstacle avoidance path generation model), the sweeper can quickly and accurately identify the type of obstacle and automatically plan the obstacle avoidance path to ensure the continuity and safety of the cleaning task. At the same time, the sweeper can also transmit the real-time position after obstacle avoidance to the cloud through the home host, so that the cloud can use the path planning model to re-plan the stain cleaning path based on the current updated position of the sweeper or dynamically adjust the original stain cleaning path, and send it to the sweeper through the home host, so that the sweeper can continue to clean the room according to the new stain cleaning path (i.e., the target stain cleaning path).

[0066] It should be noted that as the cleaning task proceeds, the system will continuously accumulate historical cleaning data. The intelligent cleaning system can use this data, combined with big data analysis and machine learning algorithms, to continuously optimize the cleaning strategy. Through the continuous iteration of the intelligent learning model, the adaptability and intelligence level of the sweeper will be significantly improved. In addition, the system also has self-learning capabilities, and can automatically adjust the cleaning strategy according to changes in the home environment and user habits, to achieve more intelligent and efficient home cleaning.

[0067] In addition, the cloud service platform (cloud) in the smart cleaning system also provides the system with functions such as remote monitoring, model update and data analysis. Through the cloud service, users can view cleaning records, receive fault alarm information and remotely control the sweeper at any time. At the same time, the cloud service is also responsible for model updates to ensure that the sweeper always maintains the latest performance. In the case of network disconnection, the built-in offline mode of the home host can continue to perform cleaning tasks based on the latest control parameters, ensuring that home cleaning is not affected by network conditions.

[0068] As can be seen from the above, through the technical solution provided by the above embodiment of the present invention, it is possible to receive the current environment video image transmitted by the home host, wherein the current environment video image is an image of the target room currently captured by the image acquisition device and transmitted to the home host, and the target room is the room that the sweeper needs to clean; obtain the current position information of the sweeper, wherein the current position information is the position information of the current position of the sweeper; input the current environment video image and the current position information into the path planning model, so as to use the path planning model to process the current environment video image and the current position information to obtain the stain cleaning path, wherein the path planning model is trained by machine learning using multiple groups of first training data, and each of the multiple groups of first training data includes: a sample current environment video image, The present invention relates to a method for controlling the cleaning path of a sample and a sample corresponding to the video image of the present environment of the sample and the present position information of the sample; transmitting the cleaning path of the sample to the home host, so that the home host sends the cleaning path of the sample to the sweeper, wherein the sweeper cleans according to the cleaning path after receiving the cleaning path of the sample, thereby achieving the goal of controlling the camera to collect image data in the room in real time through the home host, and transmitting the image data to the cloud, so that the cloud plans the cleaning path of the sweeper based on the image data, and then the home host sends the cleaning path transmitted from the cloud to the sweeper, so that the sweeper cleans according to the cleaning path, thereby achieving the technical effect of dynamically adjusting the cleaning path of the sweeper in real time in combination with the changes in the environment in the room, thereby improving the flexibility and accuracy of the sweeper's cleaning, and improving the cleaning efficiency of the sweeper.

[0069] Therefore, the technical solution provided by the above-mentioned embodiment of the present invention solves the technical problem in the related art that the sweeping machine usually cleans according to a preset fixed path, cannot effectively identify stains and dynamically adjust the cleaning path, resulting in low cleaning efficiency and easy omissions.

[0070] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0071] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0072] According to an embodiment of the present invention, there is also provided an intelligent cleaning device for a sweeping machine for implementing the intelligent cleaning method for the sweeping machine. Figure 5 is a schematic diagram of an intelligent cleaning device of a sweeper according to an embodiment of the present invention, Figure 5 As shown, the device includes: a first receiving unit 51, a first acquiring unit 53, a second acquiring unit 55 and a first transmitting unit 57. The intelligent cleaning device of the sweeper is described in detail below.

[0073] The first receiving unit 51 is used to receive the current environment video image transmitted by the home host, wherein the current environment video image is an image captured by the image acquisition device on the target room and transmitted to the home host, and the target room is the room that the vacuum cleaner needs to clean.

[0074] The first acquisition unit 53 is used to acquire the current position information of the sweeping machine, wherein the current position information is the position information of the current position of the sweeping machine.

[0075] The second acquisition unit 55 is used to input the current environment video image and the current position information into the path planning model, so as to use the path planning model to process the current environment video image and the current position information to obtain the stain cleaning path, wherein the path planning model is trained by machine learning using multiple groups of first training data, and each of the multiple groups of first training data includes: a sample current environment video image, a sample current position information, and a sample stain cleaning path corresponding to the sample current environment video image and the sample current position information.

[0076] The first transmission unit 57 is used to transmit the stain cleaning path to the home host, so that the home host sends the stain cleaning path to the sweeping machine, wherein the sweeping machine cleans according to the stain cleaning path after receiving the stain cleaning path.

[0077] It should be noted here that the above-mentioned first receiving unit 51, first acquisition unit 53, second acquisition unit 55 and first transmission unit 57 correspond to steps S202 to S208 in the above-mentioned embodiments, and the four units and the corresponding steps implement the same instances and application scenarios, but are not limited to the contents disclosed in the above-mentioned embodiments.

[0078] As can be seen from the above, in the scheme recorded in the above-mentioned embodiment of the present invention, the first receiving unit can be used to receive the current environment video image transmitted by the home host, wherein the current environment video image is an image of the target room currently captured by the image acquisition device and transmitted to the home host, and the target room is the room that the sweeper needs to clean; then the first acquisition unit is used to acquire the current position information of the sweeper, wherein the current position information is the position information of the current position of the sweeper; then the second acquisition unit is used to input the current environment video image and the current position information into the path planning model, so as to process the current environment video image and the current position information using the path planning model to obtain the stain cleaning path, wherein the path planning model is trained by machine learning using multiple groups of first training data, and each of the multiple groups of first training data includes: the current sample Environmental video image, sample current position information, and a sample stain cleaning path corresponding to the sample current environmental video image and the sample current position information; finally, the stain cleaning path is transmitted to the home host by using the first transmission unit, so that the home host sends the stain cleaning path to the sweeper, wherein the sweeper cleans according to the stain cleaning path after receiving the stain cleaning path, thereby achieving the goal of controlling the camera in the room to collect image data in real time through the home host, and transmitting the image data to the cloud, so that the cloud plans the cleaning path of the sweeper based on the image data, and then the home host sends the cleaning path transmitted from the cloud to the sweeper, so that the sweeper cleans according to the cleaning path, achieving the technical effect of dynamically adjusting the cleaning path of the sweeper in real time in combination with changes in the environment in the room, improving the flexibility and accuracy of the sweeper's cleaning, and improving the cleaning efficiency of the sweeper.

[0079] Therefore, the technical solution provided by the above-mentioned embodiment of the present invention solves the technical problem in the related art that the sweeping machine usually cleans according to a preset fixed path, cannot effectively identify stains and dynamically adjust the cleaning path, resulting in low cleaning efficiency and easy omissions.

[0080] Optionally, the first receiving unit includes: a first receiving module, used to receive a communication connection request sent by the home host, and establish a first communication channel with the home host based on the communication connection request, wherein the first communication channel is a channel for data transmission with the home host, and the home host receives the current environment video image through the second communication channel, and the second communication channel is a channel for transmitting data between the home host and the image acquisition device; a second receiving module, used to receive the current environment video image transmitted by the home host based on the first communication channel.

[0081] Optionally, the first acquisition unit includes at least one of the following: a first acquisition module, used to parse the current environment video image to obtain the current position information of the sweeping machine; a third receiving module, used to receive the position information transmitted by the home host, and determine that the position information is the current position information of the sweeping machine, wherein the position information is collected by a sensor integrated in the sweeping machine and transmitted to the home host through a third communication channel, and the third communication channel is a channel for transmitting data between the home host and the sweeping machine.

[0082] Optionally, the second acquisition unit includes: a second acquisition module, used to analyze the current environment video image to obtain the stain area in the target room; a determination module, used to determine the cleaning priority of each stain area; a third acquisition module, used to input the current environment video image, stain area, cleaning priority and current position information into the path planning model, so as to use the path planning model to process the current environment video image, stain area, cleaning priority and current position information to obtain the stain cleaning path.

[0083] Optionally, the determination module includes: an acquisition submodule, used to acquire the historical stain cleaning path when the sweeper performs cleaning operations within a historical time period; a first determination submodule, used to determine the cleaning order of the sweeper when cleaning the historical stain area according to the historical stain cleaning path; a second determination submodule, used to determine the stain cleaning priority of the stain type according to the cleaning order and the stain type corresponding to the historical stain area; a third determination submodule, used to determine the current stain type corresponding to each stain area; and a fourth determination submodule, used to determine the cleaning priority of each stain area according to the stain cleaning priority and the current stain type corresponding to each stain area.

[0084] Optionally, the determination module includes: a receiving submodule, used to receive cleaning priority instruction information uploaded by a terminal device or a home host; and a fifth determination submodule, used to determine the cleaning priority of each stained area according to the cleaning priority instruction information.

[0085] Optionally, the intelligent cleaning device of the sweeping machine further includes: a third receiving unit, used to receive updated position information transmitted by the home host while the sweeping machine is cleaning along the stain cleaning path, wherein the updated position information is the position information of the sweeping machine after the sweeping machine moves along the obstacle avoidance path, and the obstacle avoidance path is a path generated by an obstacle avoidance path generation model built into the sweeping machine when there is an obstacle within a predetermined range of the sweeping machine, and the obstacle avoidance path generation model is trained by using multiple sets of second training data through deep learning, and each of the multiple sets of second training data includes: sample obstacle information information, sample current position information, and a sample obstacle avoidance path corresponding to the sample obstacle information and the sample current position information; a third acquisition unit is used to input the current environment video image and the updated position information into the path planning model, so as to use the path planning model to process the current environment video image and the updated position information to obtain a target stain cleaning path; a second transmission unit is used to transmit the target stain cleaning path to the home host, so that the home host sends the target stain cleaning path to the sweeping machine, wherein the sweeping machine cleans according to the target stain cleaning path after receiving the target stain cleaning path.

[0086] According to another aspect of an embodiment of the present invention, an intelligent cleaning system for a sweeping machine is further provided. The intelligent cleaning system for a sweeping machine uses any one of the above-mentioned intelligent cleaning methods for a sweeping machine.

[0087] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is further provided, the computer-readable storage medium including a stored program, wherein the program executes any one of the above-mentioned intelligent cleaning methods of a sweeping machine.

[0088] Optionally, in this embodiment, the computer-readable storage medium may be located in any one of the computer terminals in a computer terminal group in a computer network, or in any one of the communication devices in a communication device group.

[0089] Optionally, in this embodiment, the computer-readable storage medium is configured to store program codes for executing the following steps: receiving a current environment video image transmitted by a home host, wherein the current environment video image is an image of a target room currently captured by an image acquisition device and transmitted to the home host, and the target room is a room that needs to be cleaned by a sweeper; obtaining current position information of the sweeper, wherein the current position information is position information of the current position of the sweeper; inputting the current environment video image and the current position information into a path planning model, so as to process the current environment video image and the current position information using the path planning model to obtain a stain cleaning path, wherein the path planning model is trained using multiple groups of first training data by machine learning, and each of the multiple groups of first training data includes: a sample current environment video image, a sample current position information, and a sample stain cleaning path corresponding to the sample current environment video image and the sample current position information; transmitting the stain cleaning path to the home host, so that the home host sends the stain cleaning path to the sweeper, wherein the sweeper cleans according to the stain cleaning path after receiving the stain cleaning path.

[0090] Optionally, in this embodiment, the computer-readable storage medium is configured to store program codes for executing the following steps: receiving a communication connection request sent by the home host, and establishing a first communication channel with the home host based on the communication connection request, wherein the first communication channel is a channel for data transmission with the home host, the home host receives the current environment video image through the second communication channel, and the second communication channel is a channel for transmitting data between the home host and the image acquisition device; based on the first communication channel, receiving the current environment video image transmitted by the home host.

[0091] Optionally, in this embodiment, the computer-readable storage medium is configured to store program codes for executing the following steps: parsing the current environment video image to obtain the current position information of the sweeping machine; receiving the position information transmitted by the home host, and determining that the position information is the current position information of the sweeping machine, wherein the position information is collected by a sensor integrated in the sweeping machine and transmitted to the home host through a third communication channel, and the third communication channel is a channel for transmitting data between the home host and the sweeping machine.

[0092] Optionally, in this embodiment, the computer-readable storage medium is configured to store program codes for executing the following steps: parsing the current environment video image to obtain the stain area in the target room; determining the cleaning priority of each stain area; inputting the current environment video image, stain area, cleaning priority and current position information into a path planning model, so as to use the path planning model to process the current environment video image, stain area, cleaning priority and current position information to obtain a stain cleaning path.

[0093] Optionally, in this embodiment, the computer-readable storage medium is configured to store program codes for executing the following steps: obtaining a historical stain cleaning path when the sweeper performs a cleaning operation within a historical time period; determining a cleaning order when the sweeper cleans the historical stain area based on the historical stain cleaning path; determining a stain cleaning priority for the stain type based on the cleaning order and the stain type corresponding to the historical stain area; determining a current stain type corresponding to each stain area; and determining a cleaning priority for each stain area based on the stain cleaning priority and the current stain type corresponding to each stain area.

[0094] Optionally, in this embodiment, the computer-readable storage medium is configured to store program codes for executing the following steps: receiving cleaning priority instruction information uploaded by a terminal device or a home host; and determining the cleaning priority of each stained area according to the cleaning priority instruction information.

[0095] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for executing the following steps: receiving updated position information transmitted by the home host during the process of the sweeping machine cleaning according to the stain cleaning path, wherein the updated position information is the position information of the sweeping machine after the sweeping machine moves according to the obstacle avoidance path, the obstacle avoidance path is a path generated by an obstacle avoidance path generation model built into the sweeping machine when there is an obstacle within a predetermined range of the sweeping machine, and the obstacle avoidance path generation model is obtained by training using multiple groups of second training data through deep learning, and each of the multiple groups of second training data includes: sample obstacle information, sample current position information, and sample obstacle avoidance paths corresponding to the sample obstacle information and the sample current position information; inputting the current environment video image and the updated position information into the path planning model, so as to use the path planning model to process the current environment video image and the updated position information to obtain a target stain cleaning path; transmitting the target stain cleaning path to the home host, so that the home host sends the target stain cleaning path to the sweeping machine, wherein the sweeping machine cleans according to the target stain cleaning path after receiving the target stain cleaning path.

[0096] According to another aspect of an embodiment of the present invention, a processor is further provided, and the processor is used to run a program, wherein when the program is run, any one of the above-mentioned intelligent cleaning methods of a sweeping machine is executed.

[0097] According to another aspect of an embodiment of the present invention, a computer program product is further provided, comprising computer instructions, and when the computer instructions are executed by a processor, any one of the above-mentioned intelligent cleaning methods for a sweeping machine is executed.

[0098] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0099] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0100] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0101] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0102] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0103] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0104] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. An intelligent cleaning method for a sweeping machine, characterized in that: include: Receive a current environment video image transmitted by the home host, wherein the current environment video image is an image captured by an image acquisition device of a target room and transmitted to the home host, and the target room is a room that needs to be cleaned by the vacuum cleaner; Acquire the current position information of the sweeping machine, wherein the current position information is the position information of the current position of the sweeping machine; The current environment video image and the current position information are input into a path planning model, so as to process the current environment video image and the current position information using the path planning model to obtain a stain cleaning path, wherein the path planning model is trained by machine learning using multiple sets of first training data, and each of the multiple sets of first training data includes: a sample current environment video image, a sample current position information, and a sample stain cleaning path corresponding to the sample current environment video image and the sample current position information; The stain cleaning path is transmitted to the home host, so that the home host sends the stain cleaning path to the sweeping machine, wherein the sweeping machine cleans according to the stain cleaning path after receiving the stain cleaning path.

2. The intelligent cleaning method of a sweeper according to claim 1, characterized in that: Receive the current environment video image transmitted by the home host, including: receiving a communication connection request sent by the home host, and establishing a first communication channel with the home host based on the communication connection request, wherein the first communication channel is a channel for data transmission with the home host, the home host receives the current environment video image through a second communication channel, and the second communication channel is a channel for data transmission between the home host and the image acquisition device; Based on the first communication channel, the current environment video image transmitted by the home host is received.

3. The intelligent cleaning method of a sweeper according to claim 1, characterized in that: Get the current location information of the sweeper, including at least one of the following: Analyze the current environment video image to obtain the current position information of the sweeping robot; Receive location information transmitted by the home host, and determine that the location information is the current location information of the sweeping machine, wherein the location information is collected by a sensor integrated in the sweeping machine and transmitted to the home host through a third communication channel, and the third communication channel is a channel for transmitting data between the home host and the sweeping machine.

4. The intelligent cleaning method of a sweeper according to claim 1, characterized in that: Inputting the current environment video image and the current position information into a path planning model, and using the path planning model to process the current environment video image and the current position information to obtain a stain cleaning path, including: Parsing the current environment video image to obtain the stain area in the target room; Determining the cleaning priority of each of the stained areas; The current environment video image, the stained area, the cleaning priority and the current position information are input into the path planning model, so as to use the path planning model to process the current environment video image, the stained area, the cleaning priority and the current position information to obtain the stain cleaning path.

5. The intelligent cleaning method of a sweeping machine according to claim 4, characterized in that: Determine the cleaning priority for each of the stained areas, including: Obtaining a historical dirt cleaning path when the sweeper performs a cleaning operation within a historical time period; Determining a cleaning order when the sweeper cleans the historical stain area according to the historical stain cleaning path; Determining the stain cleaning priority of the stain type according to the cleaning sequence and the stain type corresponding to the historical stain area; Determine the current stain type corresponding to each of the stain areas; The cleaning priority of each of the stained areas is determined according to the stain cleaning priority and the current stain type corresponding to each of the stained areas.

6. The intelligent cleaning method of a sweeper according to claim 4, characterized in that: Determine the cleaning priority for each of the stained areas, including: Receiving cleaning priority instruction information uploaded by the terminal device or the home host; The cleaning priority of each of the stained areas is determined according to the cleaning priority instruction information.

7. The intelligent cleaning method of a sweeping machine according to claim 1, characterized in that: Also includes: In the process of the sweeping machine sweeping according to the stain cleaning path, receiving updated position information transmitted by the home host, wherein the updated position information is the position information of the sweeping machine after the sweeping machine moves according to the obstacle avoidance path, the obstacle avoidance path is a path generated by an obstacle avoidance path generation model built into the sweeping machine when there is an obstacle within a predetermined range of the sweeping machine, the obstacle avoidance path generation model is obtained by training using multiple sets of second training data through deep learning, and each of the multiple sets of second training data includes: sample obstacle information, sample current position information, and a sample obstacle avoidance path corresponding to the sample obstacle information and the sample current position information; Inputting the current environment video image and the updated position information into the path planning model, so as to process the current environment video image and the updated position information using the path planning model to obtain a target stain cleaning path; The target stain cleaning path is transmitted to the home host, so that the home host sends the target stain cleaning path to the sweeping machine, wherein the sweeping machine cleans according to the target stain cleaning path after receiving the target stain cleaning path.

8. An intelligent cleaning device for a sweeping machine, characterized in that: include: A first receiving unit is used to receive a current environment video image transmitted by a home host, wherein the current environment video image is an image captured by an image acquisition device on a target room and transmitted to the home host, and the target room is a room that needs to be cleaned by the vacuum cleaner; A first acquisition unit is used to acquire current position information of the sweeping machine, wherein the current position information is position information of the current position of the sweeping machine; A second acquisition unit is used to input the current environment video image and the current position information into a path planning model, so as to process the current environment video image and the current position information using the path planning model to obtain a stain cleaning path, wherein the path planning model is trained by machine learning using multiple sets of first training data, and each of the multiple sets of first training data includes: a sample current environment video image, a sample current position information, and a sample stain cleaning path corresponding to the sample current environment video image and the sample current position information; The first transmission unit is used to transmit the stain cleaning path to the home host, so that the home host sends the stain cleaning path to the sweeping machine, wherein the sweeping machine cleans according to the stain cleaning path after receiving the stain cleaning path.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein the program executes the intelligent cleaning method of the sweeping machine described in any one of claims 1 to 7.

10. A computer program product comprising computer instructions, characterized in that: When the computer instructions are executed by the processor, the intelligent cleaning method of the sweeping machine described in any one of claims 1 to 7 is performed.

Images