WO2022166640A1

WO2022166640A1 - Control method for intelligent cleaning device, and intelligent cleaning device

Info

Publication number: WO2022166640A1
Application number: PCT/CN2022/073423
Authority: WO
Inventors: 孙佳佳; 陈巧珊; 丘伟楠
Original assignee: 追觅创新科技(苏州)有限公司
Priority date: 2021-02-03
Filing date: 2022-01-24
Publication date: 2022-08-11
Also published as: CN112971615A

Abstract

A control method for an intelligent cleaning device, and the intelligent cleaning device. The method comprises: acquiring an environment image of the surrounding environment in a process of performing a cleaning task (S202); when the recognition result is that a target feature of a target object is recognized from an image feature of the environment image, setting the region where the target feature is located as a target region (S204); and performing a corresponding cleaning policy on the target region (S206), i.e., distinguishing from other regions, performing a corresponding cleaning policy. On the basis of the image recognition environment information, a corresponding cleaning policy is performed on a target region having a specific environment feature, thereby improving the cleaning efficiency and reducing the possibility of mistakenly damaging an article.

Description

A kind of control method of intelligent cleaning equipment and intelligent cleaning equipment

【Technical field】

The present invention relates to the field of artificial intelligence, in particular, to a control method of an intelligent cleaning device and an intelligent cleaning device.

【Background technique】

Intelligent cleaning equipment is a device that can intelligently perform cleaning work, such as sweeping robots, sweeping and mopping robots, and mopping robots. Smart cleaning equipment can intelligently perform cleaning tasks such as sweeping and mopping the work area. During the cleaning process of the working area, the intelligent cleaning equipment cleans according to the same cleaning mode.

However, for areas where there are living bodies such as people and pets, the walking of the intelligent cleaning device and the sound generated during work may cause inconvenience to people and pets; for areas with many obstacles (such as toy areas, etc.), it is not suitable for Smart cleaning equipment walks and cleans. Smart cleaning equipment has low cleaning efficiency in such areas and may damage household items by mistake.

In the related art, the intelligent cleaning equipment cleans the work area according to the same cleaning mode, and has not yet proposed an effective solution to the problem that the cleaning efficiency of the area with many obstacles is low and the items may be damaged by mistake.

Therefore, it is necessary to improve the related art to overcome the disadvantages of the related art.

[Content of the Invention]

The purpose of the present invention is to provide a control method of an intelligent cleaning device and an intelligent cleaning device, so as to at least solve the problem of cleaning according to the same cleaning mode during the cleaning process of the intelligent cleaning device in the related art for the working area, and for areas with many obstacles The problem of inefficient cleaning and possible accidental damage to items.

According to an optional embodiment of the present application, a control method for an intelligent cleaning device is provided, including:

During the execution of cleaning tasks, obtain environmental images of the surrounding environment;

When the recognition result is that the target feature of the target object is recognized from the image feature of the environment image, the area where the target feature is located is set as the target area;

A corresponding cleaning strategy is performed on the target area.

Optionally, after acquiring the environment image of the surrounding environment, the method further includes:

Sending the environmental image to a server, and receiving the recognition result sent by the server, wherein the recognition result is obtained by the server recognizing the target feature from the image features obtained by performing feature extraction on the environmental image result; or

Feature extraction is performed on the environmental image to obtain image features, and the target feature is identified from the image features to obtain the identification result.

Optionally, setting the region where the target feature is located as the target region includes:

Obtain the target mark frame formed by the display interface of the mobile terminal; or obtain the target mark frame obtained after adjusting the size and/or position of the first adjustment instruction received through the display interface; or obtain the target mark frame obtained by the display the target marker frame generated by the save instruction received by the interface;

The area where the target marker frame is located is set as the target area.

Optionally, after generating a target marker frame for the target area in the display interface, the method further includes:

receiving a second adjustment instruction for adjusting the size and/or position of the target marker frame;

The size and/or position of the target marker frame is adjusted according to the second adjustment instruction.

Optionally, after setting the area where the target feature is located as the target area, the method further includes:

Receive a setting instruction for setting a cleaning strategy for the target area through the display interface; set a corresponding cleaning strategy for the target area according to the setting instruction, wherein the cleaning parameters of the cleaning strategy include at least one of the following: wind power , suction, water output, cleaning times, cleaning time, cleaning sequence.

Optionally, after setting the corresponding cleaning strategy for the target area according to the setting instruction, the method further includes:

The target marker frame is stored in a map, and the corresponding relationship between the target area and the cleaning strategy is saved.

Optionally, performing a corresponding cleaning strategy on the target area includes one of the following:

performing cleaning work on the target area in a preset working mode;

Setting the target area as a forbidden area, and prohibiting cleaning of the target area;

Setting the target area as a forbidden area or a cleaning area with the lowest priority, and cleaning the target area after the area other than the target area is cleaned;

The target area is set as a forbidden area or a cleaning area with the lowest priority, and after the cleaning of areas other than the target area is completed, the target area is cleaned according to whether there is a target object in the target area.

Optionally, cleaning the target area according to whether there is a target object in the target area includes:

Control the operation to a position with a preset distance from the target area, and collect the environmental image of the target area; send the environmental image to the server, and receive the image obtained by the server from the feature extraction of the environmental image The recognition result obtained by recognizing the target feature from the features; or, performing feature extraction on the environmental image to obtain image features, and identifying the target feature from the image features to obtain the recognition result; if the The recognition result is that the target feature of the target object is detected from the image features of the environment image, and the cleaning of the target area is abandoned, and the cleaning task is ended; if no detection is made from the image features of the environment image To the target feature, the target area is cleaned.

According to another embodiment of the present application, an intelligent cleaning device is also provided, including:

The acquisition module is used to acquire the environmental image of the surrounding environment during the execution of the cleaning task;

a first setting module, configured to set the region where the target feature is located as the target region when the recognition result is the target feature of the target object recognized from the image features of the environment image;

An execution module, configured to execute a corresponding cleaning strategy on the target area.

Optionally, the above device also includes:

a first receiving module, configured to send the environmental image to a server, and receive the recognition result sent by the server, wherein the recognition result is an image feature obtained by the server from feature extraction of the environmental image The result obtained by identifying the target feature in ; or

The recognition module is used for extracting features from the environmental image to obtain image features, and identifying the target features from the image features to obtain the recognition result.

Optionally, the above-mentioned first setting module is also used for

an acquisition sub-module for acquiring the target marker frame formed by the display interface of the mobile terminal; or, acquiring the target marker frame obtained after adjusting the size and/or position of the first adjustment instruction received through the display interface; or , obtaining the target marker frame generated by the save instruction received through the display interface;

A setting submodule is used to set the area where the target mark frame is located as the target area.

Optionally, the device further includes:

a second receiving module, configured to receive a second adjustment instruction for adjusting the size and/or position of the target marker frame;

An adjustment module, configured to adjust the size and/or position of the target marker frame according to the second adjustment instruction.

Optionally, the device further includes:

a third receiving module, configured to receive, through the display interface, a setting instruction for setting a cleaning strategy for the target area;

The second setting module is configured to set a corresponding cleaning strategy for the target area according to the setting instruction, wherein the cleaning parameters of the cleaning strategy include at least one of the following: wind force, suction force, water output, cleaning times, cleaning time , cleaning sequence.

Optionally, the device further includes:

A storage module, configured to store the target marker frame in a map, and save the corresponding relationship between the target area and the cleaning strategy.

Optionally, the execution module is also used for

Performing the corresponding cleaning strategy on the target area includes one of the following: performing cleaning work on the target area in a preset working mode; setting the target area as a forbidden area, and prohibiting cleaning of the target area; The target area is set as a forbidden area or a cleaning area with the lowest priority, and after the cleaning of areas other than the target area is completed, the target area is cleaned; the target area is set as a forbidden area or priority For the lowest cleaning area, after the area other than the target area is cleaned, the target area is cleaned according to whether there is a target object in the target area.

Optionally, the execution module is also used for

control to run to a position at a preset distance from the target area, and collect an environmental image of the target area;

Sending the environment image to a server, and receiving the recognition result obtained by the server identifying the target feature from image features obtained by performing feature extraction on the environment image; or, performing feature extraction on the environment image , obtain image features, and identify the target feature from the image features to obtain the recognition result;

If the recognition result is that the target feature of the target object is detected from the image feature of the environment image, the cleaning task is ended;

If the target feature is not detected from the image features of the environment image, the target area is cleaned.

The purpose of the present invention is to achieve through the following technical solutions: in the process of performing the cleaning task, obtain the environmental image of the surrounding environment; if the target feature of the target object is identified from the image features of the environmental image, then the area where the target feature is located is set as the target area, implement the corresponding cleaning strategy for the target area, that is, different from other areas, implement the corresponding cleaning strategy, which solves the problem that the intelligent cleaning equipment in the related art cleans the work area according to the same cleaning mode, which is more difficult for obstacles. Problems with inefficient multi-zone cleaning and the possibility of false damage to items.

The present invention has the following beneficial effects: based on the image recognition environment information, a corresponding cleaning strategy is executed for a target area with specific environmental characteristics, which improves the cleaning efficiency and reduces the possibility of mistakenly damaging items.

[Description of drawings]

1 is a hardware structural block diagram of a cleaning device according to a control method for an intelligent cleaning device according to an embodiment of the present application;

2 is a flowchart of a control method of a smart cleaning device according to an embodiment of the present application;

FIG. 3 is a structural block diagram of an intelligent cleaning device according to an embodiment of the present application.

【Detailed ways】

Hereinafter, the present application will be described in detail with reference to the accompanying drawings and in conjunction with the embodiments. It should be noted that the embodiments in the present application and the features of the embodiments may be combined with each other in the case of no conflict.

It should be noted that the terms "first", "second" and the like in the description and claims of the present invention and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific sequence or sequence.

The method embodiments provided in the embodiments of the present application may be executed in a cleaning device or a similar computing device. Taking running on a robot as an example, FIG. 1 is a hardware structural block diagram of a cleaning device according to a control method of an intelligent cleaning device according to an embodiment of the present application. As shown in FIG. 1 , the cleaning device may include one or more (only one is shown in FIG. 1 ) processors 102 (the processors 102 may include, but are not limited to, a Microprocessor Unit (MPU for short) or programmable logic A processing device such as a device (Programmable logic device, PLD for short) and a memory 104 for storing data, optionally, the above-mentioned cleaning device may also include a transmission device 106 for communication functions and an input and output device 108. Common in the art Those skilled in the art can understand that the structure shown in Fig. 1 is only for illustration, and it does not limit the structure of the above-mentioned cleaning equipment. For example, the cleaning equipment may also include more or less components than those shown in Fig. 1, or have different components than those shown in Fig. 1. The configuration shown in FIG. 1 is an equivalent function or a different configuration with more functions than that shown in FIG. 1 .

The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer programs corresponding to the control method of the cleaning device in the embodiment of the present application. Executing various functional applications and data processing implements the above-mentioned methods. Memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, memory 104 may further include memory located remotely from processor 102, which may be connected to cleaning device 10 via a network. Examples of such networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

The transmission device 106 is used to receive or transmit data via the network. The specific example of the above-mentioned network may include a wireless network provided by the communication provider of the robot 10 . In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC for short), 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 (Radio Frequency, RF for short) module, which is used to communicate with the Internet in a wireless manner.

In this embodiment, a control method for operating the above-mentioned smart cleaning device is provided. FIG. 2 is a flowchart of the control method for the smart cleaning device according to the embodiment of the present application. As shown in FIG. 2 , the process includes the following steps:

Step S202, in the process of performing the cleaning task, obtain an environmental image of the surrounding environment;

Step S204, in the case that the recognition result is that the target feature of the target object is recognized from the image feature of the environmental image, then the region where the target feature is located is set as the target region;

It should be noted that the above-mentioned target area is determined according to the recognition result obtained by recognizing the image features of the environmental image. If the recognition result includes the target feature of the target object, the target area can be determined. If the recognition result does not include the target feature. , it means that no differentiation is required.

Step S206, executing the corresponding cleaning strategy on the target area.

Through the above technical solution, the environmental image of the surrounding environment can be acquired during the cleaning task process, and then when the recognition result is that the target feature of the target object is recognized from the image features of the environmental image, the area where the target feature is located is set. For the target area, the corresponding cleaning strategy is executed on the target area, that is, different from other areas, the corresponding cleaning strategy is executed, which solves the problem that the intelligent cleaning equipment in the related art cleans the working area according to the same cleaning mode. For areas with many obstacles, the cleaning efficiency is low and the items may be damaged by mistake.

In an optional embodiment, in order to obtain the recognition result accurately, after acquiring the environmental image of the surrounding environment, the cleaning device sends the environmental image to the server, and the server performs feature extraction on the image, and identifies the target feature from the image features, Receive the recognition result sent by the server, wherein the recognition result is the presence of target features or the absence of target features; or perform feature extraction on an environmental image to obtain image features, and identify the target features from the image features to obtain the recognition result . In one embodiment, when the identification result is that the target feature exists, the identification result may further include the type of the target feature. According to the type of the target feature, the intelligent cleaning device executes a corresponding cleaning strategy on the target area. Of course, the image features obtained by feature extraction of the environmental image by the cleaning device can also be used, and the target features can be identified from the image features to obtain the identification result.

That is, the server performs feature extraction on the target environment image, and sends the obtained recognition result of the target feature to the cleaning device. Of course, the cleaning device can also perform feature extraction to obtain image features, and identify the target features from the image features. As a result, the target area is determined. If the recognition result is that the target object is included in the environmental image and the target feature of the target object is included in the image features of the environmental image, then the area where the target feature is located is determined as the target area. Of course, when the target area is specifically determined, you can also use The area including the target object is determined as the target area.

In the above-mentioned step S204, the mode of determining the target area can have many kinds, in an optional embodiment, the area where the target feature is located is set as the target area, which can be mainly realized in the following ways:

Obtaining the target marker frame formed through the display interface of the mobile terminal, that is, generating the target marker frame for the area where the target feature is located in the display interface, and the intelligent cleaning device directly obtains the target marker frame; or, obtaining the first received through the display interface. The target marker frame obtained after adjusting the size and/or position of the adjustment instruction, specifically, in the display interface, a suggested marker frame is generated for the region where the target feature is located, and a first adjustment instruction for adjusting the size and/or position of the suggested marker frame is received, Adjust the size and/or position of the suggested marker frame according to the first adjustment instruction to obtain the target marker frame, and then the intelligent cleaning device obtains the target marker frame; In the display, a target marker frame is generated for the area where the target feature is located, prompting the user whether to save the target marker frame, receiving a user-triggered save instruction, and determining the target marker frame according to the save instruction; setting the area where the target marker frame is located as the target area .

That is, a target marker frame can be generated for the target area in the display interface, or a suggested marker frame can be generated first, and then the size and/or position can be adjusted according to the adjustment instruction to obtain the target marker frame, and finally the target area can be displayed through the target marker frame.

In this embodiment of the present application, in order to accurately determine the target marker frame, after the target marker frame is generated for the target area in the display interface, the following steps may be performed: receiving a second adjustment of the size and/or position of the target marker frame. Adjustment instruction; adjust the size and/or position of the target marker frame according to the second adjustment instruction.

That is, after the target marker frame is generated, the position and/or size of the target marker frame can be adjusted according to the received adjustment instruction, so that the target marker frame can be set according to actual needs.

In this embodiment of the present application, in order to accurately control the cleaning device, after the target area is displayed through the target marker frame, the following step may be performed: receiving, through the display interface, a setting instruction for setting a cleaning strategy for the target area ; Set a corresponding cleaning strategy for the target area according to the setting instruction, wherein the cleaning parameters of the cleaning strategy include at least one of the following: wind power, suction, water output, cleaning times, cleaning time, cleaning sequence, for example, Wind power includes: first-grade wind (large), second-grade wind (medium), third-grade wind (small), suction is 1800-2200Pa, and water output includes first-grade (large), second-grade (medium), and third-grade (Small), cleaning times include: 1 time, 2 times, 3 times, any integer greater than 3 times (can be set according to the situation), cleaning time includes date and time, such as January 20, 2020, 0:00 to 24:00 It can be set at any time, and the cleaning order includes the order of cleaning targets, such as bedroom, living room, kitchen, etc.

For example, the detected target feature corresponds to a person or other living body. For the target area, a low-noise cleaning mode is set, and the relevant cleaning parameters in the cleaning strategy can also be displayed on the display interface, thereby facilitating the setting of cleaning parameters.

It should be noted that, in addition to the setting of cleaning parameters such as wind power, water output, cleaning times, cleaning time, etc., the above cleaning strategy may also include working modes, such as low power consumption modes, etc. In actual operation, you can also The above cleaning strategy is otherwise limited, which is not limited in the embodiments of the present application.

In the above steps, there may be various cleaning strategies to be performed on the target area. In an optional embodiment, performing the corresponding cleaning strategy on the target area includes one of the following: performing the cleaning strategy on the target area in a preset working mode. Cleaning work; set the target area as a forbidden area, and prohibit cleaning of the target area; set the target area as a forbidden area or the cleaning area with the lowest priority, and clean in areas other than the target area After completion, clean the target area; set the target area as a forbidden area or a cleaning area with the lowest priority, after the cleaning of areas other than the target area is completed, according to whether there is a target in the target area The subject performs a cleaning process on the target area.

That is, different cleaning levels can be set for the target area, including cleaning, prohibited cleaning and final cleaning, and cleaning is performed in different cleaning sequences according to the cleaning levels.

In the above steps, there may be various ways to clean the target area according to the target object. In an optional embodiment, cleaning the target area according to whether there is a target object in the target area may specifically include: controlling the operation to a preset distance from the target area, and collect the environmental image of the target area; send the environmental image to the server, and receive the recognition result sent by the server; if the recognition result is from the If the target feature of the target object is detected in the image feature of the environment image, the cleaning task is ended; if the target feature is not detected from the image feature of the environment image, the target area is cleaned.

That is, you can first control the cleaning equipment to run to a position that meets the preset distance conditions, and then collect the environmental image of the target area and send it to the server for identification. If no target object is detected, the target area is cleaned.

For example, the smart cleaning device acquires environmental images of the surrounding environment during the work process of performing the cleaning task. The intelligent cleaning equipment processes the environmental image and recognizes the image features in the environmental image. If the target feature is identified, the area where the target feature is located is set as the target area, and a corresponding cleaning strategy is executed for the target area. The target features can be living bodies such as people and animals, and can also be dense obstacles. If the target feature is identified, it can be done by:

Implementation mode 1: A virtual frame can be automatically formed and displayed in the area corresponding to the target feature on the working interface of the mobile terminal (such as a mobile phone, remote control, computer, etc.); for example, the location of the target feature on the map displayed by the mobile terminal The corresponding area is automatically formed and displayed as a virtual frame.

Implementation mode 2: The suggested virtual frame can be displayed on the working interface of the mobile terminal in the area corresponding to the target feature, and the virtual frame is saved if an instruction from the user to confirm the use of the virtual frame is received. The area corresponding to the virtual box is the target area.

For the second implementation, the user can adjust the virtual frame and then save the virtual frame. For example, the size, position, etc. of the virtual frame can be adjusted. For implementation mode 1 and implementation mode 2, the user can set working parameters such as wind power, water output, cleaning times, and cleaning sequence for the target area where the virtual frame is located.

Among them, virtual boxes can be saved to the map for future cleaning tasks. Specifically, the intelligent cleaning device can automatically save the virtual frame, or can receive a user instruction to save the virtual frame, and a future cleaning task executes a corresponding cleaning strategy for the target area corresponding to the virtual frame.

Among them, the cleaning strategies corresponding to the target area can be as follows:

Cleaning strategy 1: Perform cleaning work on the target area in a preset working mode, such as a low-noise mode with low wind.

Cleaning strategy 2: Set the target area as a forbidden area, and prohibit intelligent cleaning equipment from carrying out the target area.

Cleaning strategy 3: Set the target area as the area with the lowest priority, and then perform the cleaning work of the target area after completing the cleaning work of other areas. For this strategy, after completing the cleaning work in other areas, you can continue to identify whether the target area still has target features. If so, perform cleaning work on the target area in the preset work mode; if not, use the original work. mode to perform cleaning work on the target area.

Cleaning strategy 4: Set the target area as a forbidden area. After the smart cleaning device completes the cleaning task, after a predetermined time, the smart cleaning device walks near the target area to determine whether the target features still exist. If so, return to the charging station. If it exists, the cleaning job is performed on the target area.

From the description of the above embodiments, 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 can also be implemented by hardware, but in many cases the former is better implementation. Based on this understanding, the technical solutions of the present application can be embodied in the form of software products in essence or the parts that make contributions to the prior art. Memory, referred to as ROM), Random Access Memory (Random Access Memory, referred to as RAM), magnetic disk, optical disk), including several instructions to make a terminal device (can be a mobile phone, computer, server, or network device) etc.) to perform the methods described in the various embodiments of the present application.

In this embodiment, an intelligent cleaning device is also provided, and the intelligent cleaning device is used to implement the above-mentioned embodiments and preferred implementations, which have been described and will not be repeated. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, implementations in hardware, or a combination of software and hardware, are also possible and contemplated.

FIG. 3 is a structural block diagram of an intelligent cleaning device according to an embodiment of the present application. As shown in FIG. 3 , the device includes:

an acquisition module 32, configured to acquire an environmental image of the surrounding environment during the execution of the cleaning task;

The first setting module 34 is used to set the region where the target feature is located as the target region when the recognition result is that the target feature of the target object is recognized from the image feature of the environment image;

It should be noted that the above setting conditions of the target area are limitations on image characteristics of environmental conditions. In actual operation, other settings may also be performed on the above setting conditions, which are not limited in this embodiment of the present application.

The execution module 36 is configured to execute the corresponding cleaning strategy on the target area.

Through the above technical solution, since the environmental image of the surrounding environment can be acquired during the cleaning task process, and then when the recognition result is that the target feature of the target object is recognized from the image features of the environmental image, the The area where the target feature is located is set as the target area, and the corresponding cleaning strategy is executed on the target area, that is, different from other areas, the corresponding cleaning strategy is executed, which solves the problem that the cleaning process of the intelligent cleaning equipment in the related art for the working area, according to the same. The cleaning mode is used for cleaning, which is less efficient for areas with many obstacles and may damage items by mistake.

In the embodiment of the present application, in order to accurately acquire the target feature, the above-mentioned device further includes: a first receiving module, configured to send the environment image to a server, and receive the identification result sent by the server, wherein the identification The result is the result obtained by the server identifying the target feature from the image features obtained by performing feature extraction on the environment image; or

The recognition module is used for extracting features from the environment image to obtain image features, and identifying the target features from the image features to obtain the recognition result.

That is, the server performs feature extraction on the target environment image, and sends the obtained target feature recognition result to the intelligent cleaning device.

The above-mentioned setting module 34 also includes:

an acquisition submodule for acquiring the target marker frame formed by the display interface of the mobile terminal; or, acquiring the target marker frame obtained after adjusting the size and/or position of the first adjustment instruction received through the display interface; or , obtaining the target marker frame generated by the save instruction received through the display interface;

In this embodiment of the present application, in order to accurately determine the target marker frame, the device further includes:

That is, after the target marker frame is generated, the position or size of the target marker frame can be adjusted according to the received adjustment instruction.

In the embodiment of the present application, in order to accurately control the cleaning equipment, the device further includes:

That is, after the target area is displayed through the target marker frame, the cleaning strategy can be set for the target area according to the setting instruction received by the display interface.

It should be noted that the above cleaning strategy is a limitation on the output power of the cleaning module and the number of times of cleaning. In actual operation, other limitations may also be imposed on the above cleaning strategy, which is not limited in this embodiment of the present application.

Optionally, the device further includes:

Optionally, the execution module 36 is also used for

That is, different cleaning levels can be set for the target area, including cleaning, prohibited cleaning, priority cleaning and final cleaning, and cleaning is performed in different cleaning sequences according to the cleaning levels.

Optionally, the execution module 36 is further configured to control the operation to a position at a preset distance from the target area, and collect an environmental image of the target area; send the environmental image to the server, and receive the The recognition result obtained by the server recognizing the target feature from the image features obtained by performing feature extraction on the environment image; or, performing feature extraction on the environment image to obtain image features, and identifying the image features from the image features The target feature obtains the recognition result; if the recognition result is that the target feature of the target object is detected from the image features of the environment image, the cleaning task is ended; The target feature is not detected in the features, and the target area is cleaned.

It should be noted that the above modules can be implemented by software or hardware, and the latter can be implemented in the following ways, but not limited to this: the above modules are all located in the same processor; or, the above modules can be combined in any combination The forms are located in different processors.

Embodiments of the present application also provide an intelligent cleaning device, which includes: a main body, a driving component, a cleaning component, an image capturing component, and a controller. The drive assembly is used to drive the intelligent cleaning equipment to walk in the work area. The cleaning component is used to clean the surface of the work area, including but not limited to sweeping, mopping, etc. The image acquisition component is used to acquire environmental images of the surrounding environment. The controller is used to perform a predetermined operation according to the recognition result of the environmental image during the execution of the cleaning task. If the recognition result is the target feature of the target object recognized from the image feature of the environmental image, the area where the target feature is located is set as the target area; Perform the corresponding cleaning strategy on the target area.

Optionally, for specific examples in this embodiment, reference may be made to the examples described in the foregoing embodiments and optional implementation manners, and details are not described herein again in this embodiment.

Embodiments of the present application further provide a computer-readable storage medium, where a computer program is stored in the storage medium, wherein the computer program is configured to execute the steps in any one of the above method embodiments when running.

Optionally, in this embodiment, the above-mentioned storage medium may be configured to store a computer program for executing the following steps:

S1, in the process of performing the cleaning task, obtain an environmental image of the surrounding environment;

S2, when the recognition result is that the target feature of the target object is recognized from the image feature of the environment image, then the area where the target feature is located is set as the target area;

S3: Execute a corresponding cleaning strategy on the target area.

Optionally, in this embodiment, the above-mentioned storage medium may include, but is not limited to: U disk, read-only memory ROM, random access memory RAM, removable hard disk, magnetic disk or optical disk and other media that can store computer programs.

Embodiments of the present application further provide an electronic device, including a memory and a processor, where a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

Optionally, the above-mentioned electronic device may further include a transmission device and an input-output device, wherein the transmission device is connected to the above-mentioned processor, and the input-output device is connected to the above-mentioned processor.

Optionally, in this embodiment, the above-mentioned processor may be configured to execute the following steps through a computer program:

S3: Execute a corresponding cleaning strategy on the target area.

Obviously, those skilled in the art should understand that the above-mentioned modules or steps of the present application can be implemented by a general-purpose computing device, and they can be centralized on a single computing device, or distributed in a network composed of multiple computing devices Alternatively, they may be implemented in program code executable by a computing device, such that they may be stored in a storage device and executed by the computing device, and in some cases, in a different order than here The steps shown or described are performed either by fabricating them separately into individual integrated circuit modules, or by fabricating multiple modules or steps of them into a single integrated circuit module. As such, the present application is not limited to any particular combination of hardware and software.

The above descriptions are only preferred embodiments of the present application, and are not intended to limit the present application. For those skilled in the art, the present application may have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the principles of this application shall be included within the protection scope of this application.

Claims

A control method for an intelligent cleaning device, comprising:

During the execution of cleaning tasks, obtain environmental images of the surrounding environment;

When the recognition result is that the target feature of the target object is recognized from the image feature of the environment image, the region where the target feature is located is set as the target region;

A corresponding cleaning strategy is performed on the target area.
The method according to claim 1, characterized in that after acquiring the environmental image of the surrounding environment, the method further comprises:

Sending the environmental image to a server, and receiving the recognition result sent by the server, wherein the recognition result is obtained by the server recognizing the target feature from the image features obtained by performing feature extraction on the environmental image result; or

Feature extraction is performed on the environmental image to obtain image features, and the target feature is identified from the image features to obtain the identification result.
The method according to claim 1, wherein setting the region where the target feature is located as the target region comprises:

Obtain the target mark frame formed by the display interface of the mobile terminal; or obtain the target mark frame obtained after adjusting the size and/or position of the first adjustment instruction received through the display interface; or obtain the target mark frame obtained by the display the target marker frame generated by the save instruction received by the interface;

The area where the target marker frame is located is set as the target area.
The method according to claim 3, wherein after generating a target mark frame for the target area in the display interface, the method further comprises:

receiving a second adjustment instruction for adjusting the size and/or position of the target marker frame;

The size and/or position of the target marker frame is adjusted according to the second adjustment instruction.
The method according to claim 3, wherein after setting the region where the target feature is located as the target region, the method further comprises:

receiving, through the display interface, a setting instruction for setting a cleaning strategy for the target area;

A corresponding cleaning strategy is set for the target area according to the setting instruction, wherein the cleaning parameters of the cleaning strategy include at least one of the following: wind force, suction force, water output, cleaning times, cleaning time, and cleaning sequence.
The method according to claim 5, wherein after setting the corresponding cleaning strategy for the target area according to the setting instruction, the method further comprises:

The target marker frame is stored in a map, and the corresponding relationship between the target area and the cleaning strategy is saved.
The method according to claim 1, wherein performing a corresponding cleaning strategy on the target area comprises one of the following:

performing cleaning work on the target area in a preset working mode;

Setting the target area as a forbidden area, and prohibiting cleaning of the target area;

Setting the target area as a forbidden area or a cleaning area with the lowest priority, and cleaning the target area after the area other than the target area is cleaned;

The target area is set as a forbidden area or a cleaning area with the lowest priority, and after the cleaning of areas other than the target area is completed, the target area is cleaned according to whether there is a target object in the target area.
The method according to claim 7, wherein cleaning the target area according to whether there is a target object in the target area comprises:

control to run to a position at a preset distance from the target area, and collect an environmental image of the target area;

Sending the environment image to a server, and receiving the recognition result obtained by the server identifying the target feature from image features obtained by performing feature extraction on the environment image; or, performing feature extraction on the environment image , obtain image features, and identify the target feature from the image features to obtain the recognition result;

If the recognition result is that the target feature of the target object is detected from the image feature of the environment image, the cleaning task is ended;

If the target feature is not detected from the image features of the environment image, the target area is cleaned.
The method according to claim 1, wherein when the recognition result is that the target feature of the target object is recognized from the image features of the environment image, the recognition result further includes the type of the target feature ,

The execution of the corresponding cleaning strategy to the target area includes:

According to the type of the target feature, a corresponding cleaning strategy is performed on the target area.
A kind of intelligent cleaning equipment, is characterized in that, comprises:

The acquisition module is used to acquire the environmental image of the surrounding environment during the execution of the cleaning task;

a first setting module, configured to set the region where the target feature is located as the target region when the recognition result is the target feature of the target object recognized from the image features of the environment image;

An execution module, configured to execute a corresponding cleaning strategy on the target area.
A computer-readable storage medium, characterized in that a computer program is stored in the storage medium, wherein the computer program is configured to execute the method described in any one of claims 1 to 9 when running .
An electronic device comprising a memory and a processor, characterized in that, a computer program is stored in the memory, and the processor is configured to run the computer program to execute any one of the claims 1 to 9. method described.