Method and apparatus for intelligent partitioning of regions

Abstract

The application discloses a kind of regional intelligent division method and device, comprising: obtaining the initial area map for any target scene, target scene includes multiple division areas, initial area map includes the initial area submap corresponding to each division area;Based on the target image of target division area collected by cleaning equipment, target division area is any area in all division areas;Analysis target image, obtain the article contained in target image, and the article information of article;Based on the article information of article, update the initial area submap corresponding to target division area, obtain the target area submap corresponding to target division area, and then realize the update of initial area map of target scene.It can be seen that the implementation of the present application can realize the intelligent division of the region based on the article in the target area, which can improve the accuracy of the intelligent division result of the region while avoiding manual setting of markers.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of intelligent devices, in particular to a method and device for intelligent division of areas. BACKGROUND

[0002] In order to realize the movement and cleaning of the cleaning equipment in each area, it is usually necessary to intelligently divide the areas and construct the corresponding area map. At present, the existing technology mainly sets markers or reference objects on the area boundary by artificial means, such as setting markers on the door frame of a room by artificial means, identifying the boundary of the area according to the markers or reference objects set by artificial means, and then realizing the division of the area. It can be seen that the existing technology relies on artificial markers, and the operation is complicated and inefficient. At the same time, when there is no marker set on the boundary of the area in advance, the boundary of each area cannot be accurately identified, and thus an accurate division result of the area cannot be obtained. Therefore, how to improve the accuracy of the intelligent division result of the area is a technical problem to be solved in the field. SUMMARY

[0003] The technical problem to be solved by the present application is how to improve the accuracy of the intelligent division result of the area, and to provide a method and device for intelligent division of areas, which can realize the intelligent division of areas simply and efficiently by identifying the objects in the area.

[0004] In order to solve the above technical problem, the first aspect of the present application discloses a method for intelligent division of areas, which comprises:

[0005] obtaining an initial area map for any target scene, the target scene comprising a plurality of division areas, the initial area map comprising an initial area sub-map corresponding to each division area;

[0006] collecting a target image of a target division area by a cleaning equipment, the target division area being any area in all the division areas;

[0007] analyzing the target image to obtain an object contained in the target image and object information of the object;

[0008] updating the initial area sub-map corresponding to the target division area based on the object information of the object to obtain a target area sub-map corresponding to the target division area;

[0009] updating the initial area map of the target scene according to the target area sub-map corresponding to the target division area.

[0010] As an optional implementation, in the first aspect of the present application, the item information of the item comprises type information of the item and first position information of the item, wherein the first position information of the item is position information of the item in an initial region submap corresponding to the target division region;

[0011] The updating of the initial region submap corresponding to the target division region based on the item information of the item comprises:

[0012] According to the type information of the item, it is determined whether the item is a boundary type item;

[0013] If it is determined that the item is a non-boundary type item, a distribution subregion where the item is located in the initial region submap corresponding to the target division region is determined based on the first position information of the item, and the initial region submap corresponding to the target division region is updated according to the distribution subregion, wherein the distribution subregion where the item is located is used to represent the distribution of the item in the target division region;

[0014] If it is determined that the item is a boundary type item, it is determined whether the first position information of the item matches initial boundary position information, wherein the initial boundary position information is initial boundary position information corresponding to the item in the initial region submap corresponding to the target division region;

[0015] If it is determined that the first position information of the item does not match the initial boundary position information, the initial boundary position information is updated based on the first position information of the item to obtain target boundary position information, and the initial region submap corresponding to the target division region is updated according to the target boundary position information.

[0016] As an optional implementation, in the first aspect of the present application, the item information of the item further comprises size information of the item, wherein the size information of the item is size information of the item in the initial region submap corresponding to the target division region;

[0017] After it is determined that the first position information of the item does not match the initial boundary position information, and before the initial boundary position information is updated based on the first position information of the item to obtain target boundary position information, and the initial region submap corresponding to the target division region is updated according to the target boundary position information, the method further comprises:

[0018] determine an object edge position point of the object in the initial region submap corresponding to the target division region based on the size information of the object and the first position information of the object, wherein the object edge position point of the object is used to represent an edge position of the object, and the object edge position point of the object is a plurality of object edge position points;

[0019] control the cleaning device to move in the to-be-tested region corresponding to the object, and record a moving track of the cleaning device in the initial region submap corresponding to the target division region, wherein the to-be-tested region corresponding to the object is a region containing all object edge position points of the object;

[0020] determine whether the moving track of the cleaning device is a closed track, and whether all object edge position points of the object are contained in the moving track of the cleaning device;

[0021] if the moving track of the cleaning device is a closed track, and all object edge position points of the object are contained in the moving track of the cleaning device, determine a distribution subregion in which the object is located in the initial region submap corresponding to the target division region based on the first position information of the object, and update the initial region submap corresponding to the target division region according to the distribution subregion;

[0022] if the moving track of the cleaning device is not a closed track, or all object edge position points of the object are not contained in the moving track of the cleaning device, perform the operation of updating the initial boundary position information based on the first position information of the object to obtain target boundary position information, and updating the initial region submap corresponding to the target division region according to the target boundary position information.

[0023] As an optional implementation, in the first aspect of the present application, the object information of the object further includes size information of the object, wherein the size information of the object is size information of the object in the initial region submap corresponding to the target division region.

[0024] The operation of determining a distribution subregion in which the object is located in the initial region submap corresponding to the target division region based on the first position information of the object, and updating the initial region submap corresponding to the target division region according to the distribution subregion, includes:

[0025] determine a current distribution subregion in which the object is located in the initial region submap corresponding to the target division region according to the first position information of the object and the size information of the object;

[0026] determine whether there is an initial distribution subregion corresponding to the object in the initial region submap corresponding to the target division region.

[0027] If not, updating the initial regional submap corresponding to the target partition region according to the current distribution subregion where the object is located;

[0028] If yes, obtaining the initial distribution subregion corresponding to the object, and determining whether the initial distribution subregion corresponding to the object matches the current distribution subregion where the object is located;

[0029] If not, updating the initial distribution subregion corresponding to the object based on the current distribution subregion where the object is located to obtain a target distribution subregion of the object, and updating the initial regional submap corresponding to the target partition region according to the target distribution subregion of the object.

[0030] As an optional implementation, in the first aspect of the present application, before the initial regional submap corresponding to the target partition region is updated based on the object information of the object, the method further comprises:

[0031] determining initial boundary position information corresponding to the object in the initial regional submap corresponding to the target partition region;

[0032] The determination of the initial boundary position information corresponding to the object in the initial regional submap corresponding to the target partition region comprises:

[0033] determining a collection direction when the target image of the target partition region is collected by the cleaning device;

[0034] obtaining an initial boundary in the initial regional submap corresponding to the target partition region that matches the collection direction when the target image of the target partition region is collected by the cleaning device, and determining position information corresponding to the initial boundary as the initial boundary position information corresponding to the object in the initial regional submap corresponding to the target partition region.

[0035] As an optional implementation, in the first aspect of the present application, the method further comprises:

[0036] obtaining all objects in the target partition region and category information to which each object belongs;

[0037] determining whether the objects in the target partition region include an object whose category information is a region-limited category, the region-limited category being used to represent that a probability that the corresponding object belongs to a certain determined region is greater than or equal to a preset probability threshold;

[0038] If all the items in the target partitioned region include the item whose category information is the region-restricted category, a target item is obtained from all the items in the target partitioned region, and a region attribute corresponding to the target item is determined as the attribute of the target partitioned region, where the target item is the item whose category information is the region-restricted category.

[0039] If all the items in the target partitioned region do not include the item whose category information is the region-restricted category, a region attribute corresponding to each of the items in the target partitioned region is obtained.

[0040] According to the region attribute corresponding to each of the items in the target partitioned region, an intersection region attribute of all the items in the target partitioned region is determined, and the intersection region attribute is determined as the attribute of the target partitioned region.

[0041] The attribute of the target partitioned region is determined as the attribute of a target region submap corresponding to the target partitioned region.

[0042] As an optional implementation, in the first aspect of the present application, after the intersection region attribute of all the items in the target partitioned region is determined, and before the intersection region attribute is determined as the attribute of the target partitioned region, the method further comprises:

[0043] It is determined whether the intersection region attribute is unique.

[0044] If the intersection region attribute is unique, the operation of determining the intersection region attribute as the attribute of the target partitioned region is performed.

[0045] If the intersection region attribute is not unique, a target intersection region attribute with the highest priority is obtained from the intersection region attribute according to a preset region attribute priority, and the target intersection region attribute is determined as the attribute of the target partitioned region.

[0046] As an optional implementation, in the first aspect of the present application, after the target image is analyzed to obtain the items contained in the target image and the item information of the items, and before the initial region submap corresponding to the target partitioned region is updated based on the item information of the items to obtain the target region submap corresponding to the target partitioned region, the method further comprises:

[0047] The item recognition probability of the item is determined.

[0048] It is determined whether the item recognition probability of the item is greater than or equal to a preset threshold.

[0049] If the object recognition probability of the object is greater than or equal to a preset threshold, the operation of updating the initial region sub-map corresponding to the target division region based on the object information of the object is performed to obtain a target region sub-map corresponding to the target division region.

[0050] If the object recognition probability of the object is less than a preset threshold, the shooting angle of the cleaning equipment is adjusted, and the operation of collecting a target image of a target division region based on the cleaning equipment and analyzing the target image to obtain an object contained in the target image and object information of the object is performed.

[0051] The second aspect of the present application discloses an intelligent division device of a region, which comprises:

[0052] An acquisition module is configured to acquire an initial region map for any target scene, wherein the target scene comprises a plurality of division regions, and the initial region map comprises an initial region sub-map corresponding to each division region.

[0053] A collection module is configured to collect a target image of a target division region, wherein the target division region is any region in all the division regions.

[0054] An analysis module is configured to analyze the target image to obtain an object contained in the target image and object information of the object.

[0055] A first update module is configured to update the initial region sub-map corresponding to the target division region based on the object information of the object to obtain a target region sub-map corresponding to the target division region.

[0056] A second update module is configured to update the initial region map of the target scene according to the target region sub-map corresponding to the target division region.

[0057] As an optional implementation, in the second aspect of the present application, the object information of the object comprises type information of the object and first position information of the object, wherein the first position information of the object is position information of the object in the initial region sub-map corresponding to the target division region.

[0058] The first update module comprises:

[0059] A first judgment sub-module is configured to judge whether the object is a boundary type object according to the type information of the object.

[0060] The distribution updating submodule is configured to, if the first judging submodule judges that the object is a non-boundary type object, determine a distribution sub-region in which the object is located in an initial region sub-map corresponding to the target division region based on the first position information of the object, and update the initial region sub-map corresponding to the target division region according to the distribution sub-region, wherein the distribution sub-region in which the object is located is used to represent the distribution of the object in the target division region.

[0061] The second judging submodule is configured to, if the first judging submodule judges that the object is a boundary type object, judge whether the first position information of the object matches initial boundary position information, wherein the initial boundary position information is initial boundary position information corresponding to the object in the initial region sub-map corresponding to the target division region.

[0062] The boundary updating submodule is configured to, if the second judging submodule judges that the first position information of the object does not match the initial boundary position information, update the initial boundary position information based on the first position information of the object to obtain target boundary position information, and update the initial region sub-map corresponding to the target division region according to the target boundary position information.

[0063] As an optional implementation, in the second aspect of the present application, the object information of the object further includes size information of the object, wherein the size information of the object is size information of the object in the initial region sub-map corresponding to the target division region.

[0064] The first updating module further includes:

[0065] The determining submodule is configured to, after the second judging submodule judges that the first position information of the object does not match the initial boundary position information, and before the boundary updating submodule updates the initial boundary position information based on the first position information of the object to obtain target boundary position information, and updates the initial region sub-map corresponding to the target division region according to the target boundary position information, determine an object edge position point of the object in the initial region sub-map corresponding to the target division region based on the size information of the object and the first position information of the object, wherein the object edge position point of the object is used to represent an edge position of the object, and the object edge position point of the object is a plurality of.

[0066] The control submodule is configured to control a cleaning device to move in a to-be-tested region corresponding to the object, and record a moving track of the cleaning device in the initial region sub-map corresponding to the target division region, wherein the to-be-tested region corresponding to the object is a region containing all object edge position points of the object.

[0067] a third determining sub-module, configured to determine whether the moving track of the cleaning device is a closed track, and whether all edge position points of the object are contained in the moving track of the cleaning device;

[0068] The distribution updating sub-module is further configured to, if the third determining sub-module determines that the moving track of the cleaning device is a closed track, and all edge position points of the object are contained in the moving track of the cleaning device, determine a distribution sub-region in which the object is located in an initial region sub-map corresponding to the target division region based on the first position information of the object, and update the initial region sub-map corresponding to the target division region according to the distribution sub-region;

[0069] The boundary updating sub-module is further configured to, if the third determining sub-module determines that the moving track of the cleaning device is not a closed track, or all edge position points of the object are not contained in the moving track of the cleaning device, update the initial boundary position information based on the first position information of the object to obtain target boundary position information, and update the initial region sub-map corresponding to the target division region according to the target boundary position information.

[0070] As an optional implementation form, in the second aspect of the present application, the object information of the object further includes size information of the object, wherein the size information of the object is size information of the object in the initial region sub-map corresponding to the target division region.

[0071] The manner in which the distribution updating sub-module determines a distribution sub-region in which the object is located in the initial region sub-map corresponding to the target division region based on the first position information of the object, and updates the initial region sub-map corresponding to the target division region according to the distribution sub-region includes:

[0072] determining a current distribution sub-region in which the object is located in the initial region sub-map corresponding to the target division region according to the first position information of the object and the size information of the object;

[0073] determining whether there is an initial distribution sub-region corresponding to the object in the initial region sub-map corresponding to the target division region;

[0074] if not, updating the initial region sub-map corresponding to the target division region according to the current distribution sub-region in which the object is located;

[0075] if yes, obtaining the initial distribution sub-region corresponding to the object, and determining whether the initial distribution sub-region corresponding to the object matches the current distribution sub-region in which the object is located;

[0076] If the match fails, the initial distribution sub-region corresponding to the article is updated based on a current distribution sub-region where the article is located, a target distribution sub-region of the article is obtained, and the initial regional sub-map corresponding to the target division region is updated according to the target distribution sub-region of the article.

[0077] As an optional implementation, in the second aspect of the present application, the device further comprises:

[0078] The first determination module is configured to determine initial boundary position information corresponding to the article in the initial regional sub-map corresponding to the target division region before the initial regional sub-map corresponding to the target division region is updated based on the article information of the article.

[0079] The manner in which the first determination module determines the initial boundary position information corresponding to the article in the initial regional sub-map corresponding to the target division region includes:

[0080] Determining a collection direction when the cleaning equipment collects a target image of the target division region;

[0081] Obtaining an initial boundary in the initial regional sub-map corresponding to the target division region that matches the collection direction when the cleaning equipment collects a target image of the target division region, and determining position information corresponding to the initial boundary as the initial boundary position information corresponding to the article in the initial regional sub-map corresponding to the target division region.

[0082] As an optional implementation, in the second aspect of the present application, the device further comprises a second determination module configured to:

[0083] Obtain all articles in the target division region and category information to which each of the articles belongs;

[0084] Determine whether the articles in the target division region include an article whose category information is a region-limited category, the region-limited category being used to represent that a corresponding article belongs to a certain determined region with a probability greater than or equal to a preset probability threshold;

[0085] If the articles in the target division region include an article whose category information is the region-limited category, a target article is obtained from the articles in the target division region, and a region attribute corresponding to the target article is determined as the attribute of the target division region, wherein the target article is the article whose category information is the region-limited category.

[0086] If the articles in the target division region do not include an article whose category information is the region-limited category, a region attribute corresponding to each of the articles in the target division region is obtained.

[0087] determine an intersection region attribute of all the items in the target partition region, and determine the intersection region attribute as the attribute of the target partition region;

[0088] determine the attribute of the target partition region as the attribute of a target region submap corresponding to the target partition region.

[0089] As an optional implementation, in the second aspect, the second determining module is further configured to: after determining the intersection region attribute of all the items in the target partition region, and before determining the intersection region attribute as the attribute of the target partition region, determine whether the intersection region attribute is unique.

[0090] If the intersection region attribute is unique, perform the operation of determining the intersection region attribute as the attribute of the target partition region.

[0091] If the intersection region attribute is not unique, obtain a target intersection region attribute with the highest priority from the intersection region attribute according to a preset region attribute priority, and determine the target intersection region attribute as the attribute of the target partition region.

[0092] As an optional implementation, in the second aspect, the analyzing module is further configured to:

[0093] after analyzing the target image to obtain the items contained in the target image and the item information of the items, determine an item recognition probability of the items, and determine whether the item recognition probability of the items is greater than or equal to a preset threshold.

[0094] The first updating module is further configured to: if the analyzing module determines that the item recognition probability of the items is greater than or equal to the preset threshold, perform the operation of updating the initial region submap corresponding to the target partition region based on the item information of the items to obtain the target region submap corresponding to the target partition region.

[0095] The collecting module is further configured to: if the analyzing module determines that the item recognition probability of the items is less than the preset threshold, adjust a shooting angle of the cleaning device, and perform the operation of collecting a target image of the target partition region based on the cleaning device, and analyzing the target image to obtain the items contained in the target image and the item information of the items.

[0096] A third aspect of the present application discloses another intelligent partitioning device for a region, which comprises:

[0097] a memory storing executable program codes;

[0098] a processor coupled to the memory;

[0099] The processor invokes the executable program code stored in the memory to execute the intelligent division method of the region disclosed in the first aspect of the application.

[0100] The fourth aspect of the application discloses a cleaning device for executing the intelligent division method of the region disclosed in the first aspect of the application.

[0101] The fifth aspect of the application discloses a computer storage medium, which stores computer instructions, and when the computer instructions are invoked, the intelligent division method of the region disclosed in the first aspect of the application is executed.

[0102] Compared with the prior art, the embodiments of the application have the following beneficial effects:

[0103] In the embodiments of the application, an initial region map for any target scene is obtained, the target scene includes a plurality of division regions, and the initial region map includes an initial region sub-map corresponding to each division region; a target image of a target division region is collected by the cleaning device, the target division region is any region in all division regions; the target image is analyzed to obtain an article contained in the target image and article information of the article; based on the article information of the article, the initial region sub-map corresponding to the target division region is updated to obtain a target region sub-map corresponding to the target division region, and the update of the initial region map of the target scene is realized. It can be seen that the intelligent division of the region can be realized based on the article in the target region by implementing the application, and the accuracy of the intelligent division result of the region can be improved while avoiding manual setting of markers. BRIEF DESCRIPTION OF DRAWINGS

[0104] In order to more clearly illustrate the technical solutions in the embodiments of the application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative labor.

[0105] Figure 1 is a flowchart of the intelligent division method of the region disclosed in the embodiments of the application;

[0106] Figure 2 is a flowchart of updating the initial region sub-map corresponding to the target division region based on the article information of the article disclosed in the embodiments of the application;

[0107] Figure 3is a flowchart of an embodiment of the application for updating an initial region submap corresponding to a target division region based on a distribution subregion where an object is located;

[0108] Figure 4 is a flowchart of another embodiment of the application for intelligent division of a region;

[0109] Figure 5 is a flowchart of an embodiment of the application for determining the attributes of a target region submap corresponding to a target division region;

[0110] Figure 6 is a structural diagram of an embodiment of the application for an intelligent division device of a region;

[0111] Figure 7 is a structural diagram of an embodiment of the application for a first updating module;

[0112] Figure 8 is a structural diagram of another embodiment of the application for an intelligent division device of a region;

[0113] Figure 9 is a structural diagram of another embodiment of the application for an intelligent division device of a region. DETAILED DESCRIPTION

[0114] In order to enable persons skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by persons skilled in the art without creative labor fall within the scope of protection of the present application.

[0115] The terms "first", "second", and the like in the specification and claims of the present application and the above-described drawings are used to distinguish different objects, and are not used to describe a specific order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, device, product, or end including a series of steps or units is not limited to the listed steps or units, but can optionally include steps or units not listed or can optionally include other steps or units inherent to the process, method, product, or end.

[0116] Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase "in an embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are they necessarily mutually exclusive of one another. It is expressly understood that any of the embodiments described herein can be combined with any of the other embodiments unless specifically noted otherwise.

[0117] The application discloses a region intelligent division method and device and a cleaning device, which can realize intelligent division of a region based on objects in a target region and improve the accuracy of the intelligent division result of the region. The following will be described in detail.

[0118] Embodiment one

[0119] Please refer to Figure 1 , Figure 1 is a flowchart of a region intelligent division method disclosed by an embodiment of the application. Wherein, Figure 1 The described region intelligent division method can be applied to an intelligent cleaning device or a server, and the embodiments of the application are not limited. As Figure 1 shown, the region intelligent division method can include the following operations:

[0120] S1, obtaining an initial region map for any target scene, the target scene including a plurality of division regions, and the initial region map including an initial region sub-map corresponding to each division region.

[0121] In the embodiments of the application, before performing the region intelligent division, an initial region map of the target scene is obtained as a reference region map for intelligent division of the region boundary and intelligent division of the region distribution. Optionally, the initial region map of the target scene can be obtained by scanning the target scene by a laser radar, can be obtained based on a manually set boundary marker, or can be obtained by downloading a pre-stored scene initial map in a database, and the embodiments of the application are not limited. The target scene is specifically a scene with a region division requirement, which can be an indoor scene including a plurality of division regions or other scenes with a region division requirement. The obtained target scene includes a plurality of division regions, and correspondingly, the obtained initial region map of the target scene includes an initial region sub-map corresponding to each division region.

[0122] S2, based on the target image of the target division region collected by the cleaning device, the target division region being any region in all the division regions.

[0123] In the embodiment of the present application, the cleaning equipment comprises a collection device, which can be a monocular camera device, a multi-view camera device, or a camera device comprising a holder, and the embodiment of the present application is not limited in this regard. The cleaning equipment can collect a target image of any one of the plurality of divided regions of the target scene, and the collected target image can be one or more of a single image of the target divided region, a plurality of images of different directions and angles of the target divided region, and a panoramic image of the target divided region.

[0124] S3, analyzing the target image to obtain an article contained in the target image and article information of the article.

[0125] In the embodiment of the present application, the target image collected by the cleaning equipment comprises an article in the target divided region. The article in the target divided region contained in the target image can be one or more. By analyzing the collected target image, the article contained in the target image and the article information of the article can be identified. Optionally, the article information of the article can comprise type information of the article and first position information of the article, and can further comprise size information of the article. The type information of the article can be a boundary type or a non-boundary type, and exemplarily, such as analyzing that the target image comprises a door or a door frame, a tea table or a dining table, and further obtaining that the type information of the door or the door frame is a boundary type, and the type information of the tea table or the dining table is a non-boundary type. At the same time, the first position information of the article is the position information of the article in the initial region sub-map corresponding to the target divided region, and the article can be located in the initial region sub-map by the first position information of the article. In addition, the size information of the article is the size information of the article in the initial region sub-map corresponding to the target divided region, and the space region size occupied by the article can be marked in the initial region sub-map by the size information of the article.

[0126] S4, updating the initial region sub-map corresponding to the target divided region based on the article information of the article to obtain a target region sub-map corresponding to the target divided region.

[0127] In the embodiment of the present application, the region boundary or region distribution of the initial region sub-map can be updated based on the article information of the article obtained by analysis, and then the target region sub-map corresponding to the intelligently divided target divided region is obtained.

[0128] S5, updating the initial region map of the target scene according to the target region sub-map corresponding to the target divided region.

[0129] In the embodiment of the present application, after the initial region sub-map corresponding to the target divided region is updated by the article information of the article, and the target region sub-map corresponding to the target divided region is obtained, the update of the region map of the target scene can be realized accordingly.

[0130] It can be seen that the intelligent division of the region as described can achieve intelligent division of the region based on the items in the target region, while avoiding manual setting of markers and improving the accuracy of the intelligent division result of the region. Figure 1

[0131] In an optional embodiment, please refer to Figure 2 Figure 2 is a flowchart of the process of updating the initial region submap corresponding to the target division region based on the item information of the item disclosed in the embodiments of the present application. The step S4 of updating the initial region submap corresponding to the target division region based on the item information of the item can include the following steps:

[0132] S401, according to the type information of the item, it is judged whether the item is a boundary type item. If it is judged that the item is a non-boundary type item, step S402 is executed; if it is judged that the item is a boundary type item, steps S403-S404 are executed.

[0133] In this optional embodiment, according to the type information of the item identified in step S3, it is judged whether the item is a boundary type item. When it is judged in step S401 that the item is a boundary type item, the initial region submap boundary can be corrected according to the boundary type item; when it is judged in step S401 that the item is a non-boundary type item, the item cannot be used as an item for correcting the initial region submap boundary, but can be used as an item for correcting the initial region submap distribution region.

[0134] S402, the first position information of the item is used to determine the distribution subregion where the item is located in the initial region submap corresponding to the target division region, and the initial region submap corresponding to the target division region is updated according to the distribution subregion, wherein the distribution subregion where the item is located is used to represent the distribution of the item in the target division region.

[0135] In this optional embodiment, when the item is a non-boundary type item, the initial region submap distribution region can be corrected according to the item. Specifically, the distribution of the item in the target division region can be determined according to the distribution subregion where the item is located in the initial region submap corresponding to the target division region.

[0136] S403, it is judged whether the first position information of the item matches the initial boundary position information, wherein the initial boundary position information is the initial boundary position information corresponding to the item in the initial region submap corresponding to the target division region. If it is judged that the first position information of the item does not match the initial boundary position information, step S404 is executed.

[0137] ​​In the optional embodiment, when it is judged that the first position information of the object matches the initial boundary position information, the initial boundary position information corresponding to the object in the initial regional submap corresponding to the target division region is accurate and does not need to be corrected by the position information of the object. When it is judged that the first position information of the object does not match the initial boundary position information, the initial boundary position information corresponding to the object in the initial regional submap corresponding to the target division region is inaccurate and needs to be corrected by the object information of the recognized object.

[0138] S404, updating the initial boundary position information based on the first position information of the object to obtain target boundary position information, and updating the initial regional submap corresponding to the target division region according to the target boundary position information.

[0139] In the optional embodiment, the initial boundary position information needs to be corrected by the object information of the recognized object. Specifically, the initial boundary position information corresponding to the object in the initial regional submap corresponding to the target division region is corrected according to the first position information of the object to obtain corrected target boundary position information, and then the initial regional submap corresponding to the target division region is updated according to the corrected target boundary position information.

[0140] It can be seen that by implementing the optional embodiment, the content to be updated of the initial regional submap can be determined according to the type information of the object, and further the boundary position / distribution region of the initial regional submap corresponding to the target division region can be corrected or updated by the position information of the object, so that a more accurate regional submap of the target division region is obtained.

[0141] In the optional embodiment, further, whether the object whose type is the boundary type is placed at the boundary position in the target scene needs to be further verified. That is, after it is judged in step S403 that the first position information of the object does not match the initial boundary position information, before step S404 of updating the initial boundary position information based on the first position information of the object to obtain target boundary position information and updating the initial regional submap corresponding to the target division region according to the target boundary position information, the method further includes:

[0142] S405, determining the object edge position points of the object in the initial regional submap corresponding to the target division region based on the size information of the object and the first position information of the object, wherein the object edge position points of the object are used to represent the edge position of the object, and the object edge position points of the object are multiple.

[0143] In the optional embodiment, the article information of the article includes size information of the article, and the multiple article edge position points of the article in the initial region sub-map corresponding to the target division region can be determined according to the size information of the article and the first position information. The article edge position points can be the vertexes of the article or any points on the edges of the article, which are not limited in the embodiments of the present application.

[0144] S406, control the cleaning equipment to move in the article corresponding to the to-be-tested region, and record the moving track of the cleaning equipment in the initial region sub-map corresponding to the target division region, wherein the article corresponding to the to-be-tested region is a region containing all the article edge position points of the article.

[0145] In the optional embodiment, the to-be-tested region containing all the article edge position points of the article can be determined according to all the article edge position points of the article, and the to-be-tested region is a virtual region in the initial region map and is not limited by the initial boundary in the initial region map. By controlling the cleaning equipment to move in the to-be-tested region, whether the article is placed at the boundary position can be determined.

[0146] S407, determine whether the moving track of the cleaning equipment is a closed track and whether all the article edge position points of the article are contained in the moving track of the cleaning equipment. If the moving track of the cleaning equipment is a closed track and all the article edge position points of the article are contained in the moving track of the cleaning equipment, step S402 is performed; if the moving track of the cleaning equipment is not a closed track or all the article edge position points of the article are not contained in the moving track of the cleaning equipment, step S404 is performed.

[0147] In the optional embodiment, when the moving track of the cleaning equipment is a closed track and all the article edge position points of the article are contained in the closed track, that is, the article is not placed at the boundary position, the article can be used as an article for correcting the distribution region of the initial region sub-map, and then step S402 is performed to determine the distribution sub-region of the article in the initial region sub-map corresponding to the target division region based on the first position information of the article, and the initial region sub-map corresponding to the target division region is updated according to the distribution sub-region.

[0148] When the moving track of the cleaning equipment cannot form a closed track or all the article edge position points of the article are not contained in the moving track of the cleaning equipment, that is, the article is placed at the boundary position, the article can be used as an article for correcting the boundary position of the initial region sub-map, and then step S404 is performed to update the initial boundary position information based on the first position information of the article to obtain target boundary position information, and the initial region sub-map corresponding to the target division region is updated according to the target boundary position information.

[0149] It can be seen that by implementing the optional embodiment, whether the article of the boundary type is placed at the boundary position can be verified by controlling the movement of the cleaning device, and then the corresponding updating operation is performed according to the verification result, so that a more accurate region division result is obtained.

[0150] In the optional embodiment, further optionally, referring to Figure 3 , Figure 3 is a flowchart of updating the initial region submap corresponding to the target division region based on the distribution subregion where the article is located, disclosed by the embodiment of the application. In step S402, the distribution subregion where the article is located in the initial region submap corresponding to the target division region is determined based on the first position information of the article, and the initial region submap corresponding to the target division region is updated according to the distribution subregion, including the following steps.

[0151] In step S4021, the current distribution subregion where the article is located in the initial region submap corresponding to the target division region is determined according to the first position information of the article and the size information of the article.

[0152] In the optional embodiment, the article information of the article includes the size information of the article, and the current distribution subregion where the article is located in the initial region submap corresponding to the target division region can be determined by the size information and the first position information of any article. The current distribution subregion where the article is located is the current distribution of the article in the target division region.

[0153] In step S4022, it is determined whether there is an initial distribution subregion corresponding to the article in the initial region submap corresponding to the target division region. If not, step S4023 is performed; if yes, steps S4024-S4025 are performed.

[0154] In the optional embodiment, it is determined whether there is an initial distribution subregion corresponding to the article in the initial region submap corresponding to the target division region. If there is no initial distribution subregion corresponding to the article in the initial region submap corresponding to the target division region, it indicates that the article is a new article, and the current distribution subregion of the article can be added to the initial region submap. If there is an initial distribution subregion corresponding to the article in the initial region submap corresponding to the target division region, it indicates that the article is not a new article, and whether the initial region submap needs to be updated can be determined by comparing the matching of the initial distribution subregion and the current distribution subregion.

[0155] In step S4023, the initial region submap corresponding to the target division region is updated according to the current distribution subregion where the article is located.

[0156] S4024, acquire the initial distribution sub-region corresponding to the article, and determine whether the initial distribution sub-region corresponding to the article matches the current distribution sub-region where the article is located. If not, perform step S4025.

[0157] In this optional embodiment, whether the initial region sub-map needs to be updated is determined by comparing the matching of the initial distribution sub-region and the current distribution sub-region. If the initial distribution sub-region matches the current distribution sub-region, the sub-region where the article is located in the initial region sub-map does not need to be corrected. If the initial distribution sub-region does not match the current distribution sub-region, the sub-region where the article is located in the initial region sub-map has changed, and needs to be updated by correction.

[0158] S4025, update the initial distribution sub-region corresponding to the article based on the current distribution sub-region where the article is located, obtain the target distribution sub-region of the article, and update the initial region sub-map corresponding to the target division region according to the target distribution sub-region of the article.

[0159] In this optional embodiment, after the current distribution sub-region where the article is located in the initial region sub-map is updated to obtain the target distribution sub-region of the article, the distribution of the article in the target division region can be determined, and then the updated initial region sub-map corresponding to the target division region is obtained.

[0160] It can be seen that by implementing this optional embodiment, the distribution of the article in the target division region can be determined according to the current distribution sub-region where the article is located, and further the distribution region of the initial region sub-map corresponding to the target division region can be updated according to the current distribution sub-region where the article is located, and then a more accurate region sub-map of the target division region is obtained.

[0161] In yet another optional embodiment, before updating the initial region sub-map corresponding to the target division region based on the article information of the article, the method further comprises:

[0162] Determine the initial boundary position information corresponding to the article in the initial region sub-map corresponding to the target division region.

[0163] In this optional embodiment, determining the initial boundary position information corresponding to the article in the initial region sub-map corresponding to the target division region comprises the following steps:

[0164] Determine the collection direction of the target image of the target division region collected by the cleaning device.

[0165] acquire an initial boundary in the initial region submap corresponding to the target partition region and matching a collection direction when the cleaning device collects the target image of the target partition region, and determine position information corresponding to the initial boundary as the initial boundary position information corresponding to the article in the initial region submap corresponding to the target partition region.

[0166] In this optional embodiment, the initial boundary position information corresponding to the article in the initial region submap corresponding to the target partition region can be determined through the collection direction when the target image of the target partition region is collected by the cleaning device. The collection direction when the target image of the target partition region is collected by the cleaning device can be determined by a direction sensor or by image recognition technology.

[0167] It can be seen that by implementing this optional embodiment, the distribution of the article in the target partition region can be determined according to the current distribution subregion where the article is located, and the distribution region of the initial region submap corresponding to the target partition region can be further updated through the current distribution subregion where the article is located, so as to obtain a more accurate region submap of the target partition region.

[0168] In yet another optional embodiment, after analyzing the target image to obtain the article contained in the target image and the article information of the article, and before updating the initial region submap corresponding to the target partition region based on the article information of the article to obtain the target region submap corresponding to the target partition region, the method further includes the following steps:

[0169] determining an article recognition probability of the article;

[0170] judging whether the article recognition probability of the article is greater than or equal to a preset threshold;

[0171] if the article recognition probability of the article is greater than or equal to the preset threshold, performing the operation of updating the initial region submap corresponding to the target partition region based on the article information of the article to obtain the target region submap corresponding to the target partition region;

[0172] if the article recognition probability of the article is less than the preset threshold, adjusting a shooting angle of the cleaning device, and performing the operation of collecting the target image of the target partition region by the cleaning device and analyzing the target image to obtain the article contained in the target image and the article information of the article.

[0173] In the optional embodiment, after the object included in the target image is identified and the object information of the object is obtained, the object recognition probability of the object included in the target image is determined. The object recognition probability is used to represent the accuracy of the identification result. Optionally, the object recognition probability can be determined by the matching degree of the current object and the standard object. When the object recognition probability exceeds the preset threshold, it indicates that the current identification result is accurate, and the identified object and the object information can be subjected to subsequent operations. When the object recognition probability does not exceed the preset threshold, it indicates that the current identification result is inaccurate, and the shooting angle of the collection device needs to be adjusted, the target division region is re-collected, and the accurate identification result is obtained through re-identification.

[0174] It can be seen that by implementing the optional embodiment, the accuracy of the identification result can be judged, and the inaccurate identification result can be adaptively changed and re-identified to prevent misjudgment. The accuracy of the object identification result is ensured, and the accuracy of the subsequent regional intelligent division is ensured.

[0175] Embodiment Two

[0176] As shown in Figure 4 , Figure 4 is a flowchart of another regional intelligent division method disclosed by the embodiments of the present application. The regional intelligent division method can include the following operations:

[0177] S1, obtaining an initial regional map for any target scene, the target scene including a plurality of division regions, and the initial regional map including an initial regional sub-map corresponding to each division region.

[0178] S2, collecting a target image of a target division region based on the cleaning device, the target division region being any region in all division regions.

[0179] S3, analyzing the target image to obtain an object included in the target image and object information of the object.

[0180] S4, updating the initial regional sub-map corresponding to the target division region based on the object information of the object to obtain a target regional sub-map corresponding to the target division region.

[0181] S5, updating the initial regional map of the target scene according to the target regional sub-map corresponding to the target division region.

[0182] S6, determining the attribute of the target regional sub-map corresponding to the target division region.

[0183] In the embodiment of the present application, for other detailed description of steps S1-S5, please refer to the detailed description of steps S1-S5 in embodiment one, and the embodiment of the present application will not be repeated. It should be noted that step S6 can be executed before step S5 or after step S5, and the embodiment of the present application is not limited.

[0184] In the embodiment of the present application, step S6, determining the attribute of the target area sub-map corresponding to the target division area, comprises the following steps:

[0185] S601, obtaining all items in the target division area and the category information of each item.

[0186] In the embodiment of the present application, the target division area includes one or more items, and all items included in the target division area can be obtained through a single, multiple or panoramic target image. And the category information of each item included in the target division area is identified through image recognition technology. For example, the target division area includes item 1, item 2 and item 3, the category information of item 1 is identified as a dining table, the category information of item 2 is identified as a tea table, and the category information of item 3 is identified as a sofa.

[0187] S602, determining whether all items in the target division area include an item with category information as a region-limited category, the region-limited category is used to represent that the corresponding item belongs to a certain determined region with a probability greater than or equal to a preset probability threshold. If all items in the target division area include an item with category information as a region-limited category, steps S603 and S606 are executed; if all items in the target division area do not include an item with category information as a region-limited category, steps S604-S606 are executed.

[0188] In the embodiment of the present application, the region-limited category is used to represent that the corresponding item belongs to a certain determined region with a probability greater than or equal to a preset probability threshold, and the preset probability threshold can be set according to the needs of the actual application scene. For example, if the category information of item 4 is a range hood, the range hood category information can be set as a region-limited category, which means that the probability of item 4 belonging to the kitchen is greater than or equal to a preset probability threshold.

[0189] S603, obtaining a target item from all items in the target division area, and determining the region attribute corresponding to the target item as the attribute of the target division area, wherein the target item is an item with category information as a region-limited category.

[0190] In the embodiment of the present application, when the target division region includes an item with the category information of the region-limited category, the item with the category information of the region-limited category is obtained, for example, when the target division region includes item 4 (with the category information of a range hood), item 4 is taken as the target item, and the region attribute (kitchen) corresponding to item 4 is determined as the attribute (kitchen) of the target division region.

[0191] S604, the region attribute corresponding to each item in the target division region is obtained.

[0192] In the embodiment of the present application, when the target division region does not include an item with the category information of the region-limited category, the attribute of the target division region is determined by the region attributes of the items in the target division region, for example, the region attribute of item 1 in the target division region is dining room and living room, the region attribute of item 2 is living room, and the region attribute of item 3 is living room and bedroom.

[0193] S605, the intersection region attribute of all items in the target division region is determined according to the region attribute corresponding to each item in the target division region, and the intersection region attribute is determined as the attribute of the target division region.

[0194] In the embodiment of the present application, the intersection region attribute set of the target division region can be obtained according to the intersection region attribute of all items in the target division region, and the region attribute in the intersection region attribute set can be taken as the candidate attribute of the target division region, for example, when the intersection region attribute of all items in the target division region is living room, the living room is determined as the attribute of the target division region.

[0195] Optionally, after step S605 determines the intersection region attribute of all items in the target division region, and before the intersection region attribute is determined as the attribute of the target division region, the method further includes:

[0196] determining whether the intersection region attribute is unique.

[0197] If the intersection region attribute is unique, the operation of determining the intersection region attribute as the attribute of the target division region is performed.

[0198] If the intersection region attribute is not unique, the target intersection region attribute with the highest priority is obtained from the intersection region attribute according to the preset region attribute priority, and the target intersection region attribute is determined as the attribute of the target division region.

[0199] In an optional embodiment of the present application, if there is only one intersection region attribute in the intersection region attribute set, the intersection region attribute can be determined as the attribute of the target division region. If there are multiple intersection region attributes in the intersection region attribute set, the target intersection region attribute with the highest priority can be determined through a preset region attribute priority, and the target intersection region attribute with the highest priority can be determined as the attribute of the target division region. The region attribute priority can be set differently according to different target scenarios. Optionally, the other intersection region attributes in the intersection region attribute set except the target intersection region attribute can be taken as candidate attributes of the target division region for selection by an operator.

[0200] In S606, the attribute of the target division region is determined as the attribute of the target region submap corresponding to the target division region.

[0201] In the embodiment of the present application, the attribute of the target division region is determined as the attribute of the target region submap corresponding to the target division region, and is displayed in the target region submap of the target division region.

[0202] It can be seen that the implementation of the intelligent division of the region as described above can determine the attribute of the target division region based on the items in the target region, and can accurately obtain the intelligent division result of the region. Figure 4

[0203] In an optional embodiment, if it is determined that all the items in the target division region do not include the item of the region-limited category, after obtaining the region attribute corresponding to each item in the target division region, the method further comprises:

[0204] According to the region attribute corresponding to each item in the target division region, a region attribute set of the target division region is obtained.

[0205] For each region attribute in the region attribute set of the target division region, the number of items including the region attribute is counted to obtain the frequency of the region attribute.

[0206] The frequencies of all the region attributes in the region attribute set of the target division region are obtained, and all the region attributes in the region attribute set of the target division region are sorted in descending order of frequency. The region attribute at the top of the sorting is determined as the attribute of the target division region, and the attribute of the target region submap corresponding to the target division region is obtained.

[0207] It can be seen that the implementation of the optional embodiment can determine the attribute of the target region submap corresponding to the target division region through the common region attribute of multiple items in the target division region, and can accurately obtain the intelligent division result of the region.

[0208] Embodiment Three

[0209] Referring to​Figure 6 , Figure 6 is a structural schematic diagram of a regional intelligent division method and device disclosed by an embodiment of the present application. As shown in the figure, Figure 6 the regional intelligent division device comprises an acquisition module 601, a collection module 602, an analysis module 603, a first updating module 604, and a second updating module 605. Among them:

[0210] The acquisition module 601 is configured to acquire an initial regional map for any target scene, the target scene comprising a plurality of division regions, and the initial regional map comprising an initial regional sub-map corresponding to each division region.

[0211] In the embodiment of the present application, before performing regional intelligent division, an initial regional map of the target scene is needed as a reference regional map for intelligent division of the regional boundary and intelligent division of the regional distribution. Optionally, the initial regional map of the target scene can be obtained by scanning the target scene by a laser radar, can be obtained based on a manually set boundary marker, or can be obtained by downloading a pre-stored scene initial map in a database, which is not limited by the embodiment of the present application. The target scene is specifically a scene with regional division requirements, which can be an indoor scene comprising a plurality of division regions, or other scenes with regional division requirements. The acquired target scene comprises a plurality of division regions, and accordingly, the acquired initial regional map of the target scene comprises an initial regional sub-map corresponding to each division region.

[0212] The collection module 602 is configured to collect a target image of a target division region, the target division region being any region in all division regions.

[0213] In the embodiment of the present application, the collection module can be integrated into a cleaning device, and the collection module included in the cleaning device can be a monocular camera device, a multi-view camera device, or a camera device including a cloud platform, which is not limited by the embodiment of the present application. The collection module can collect a target image of any one of the plurality of division regions of the target scene, and the collected target image can be one or more of a single image of the target division region, a plurality of images of the target division region in different directions and different angles, and a panoramic image of the target division region.

[0214] The analysis module 603 is configured to analyze the target image to obtain an article contained in the target image and article information of the article.

[0215] ​In the embodiment of the present application, the target image collected by the cleaning equipment includes the object in the target division area. The object in the target division area included in the target image can be one or more. By analyzing the collected target image, the object included in the target image and the object information of the object can be identified. Optionally, the object information of the object can include the type information of the object and the first position information of the object, and can also include the size information of the object. The type information of the object can be a boundary type or a non-boundary type. For example, it is analyzed that the target image includes a door or a door frame, a tea table or a dining table, and further the type information of the door or the door frame is a boundary type, and the type information of the tea table or the dining table is a non-boundary type. At the same time, the first position information of the object is the position information of the object in the initial area sub-map corresponding to the target division area, and the object can be located in the initial area sub-map through the first position information of the object. In addition, the size information of the object is the size information of the object in the initial area sub-map corresponding to the target division area, and the space area size occupied by the object can be marked in the initial area sub-map through the size information of the object.

[0216] The first updating module 604 is configured to update the initial area sub-map corresponding to the target division area based on the object information of the object, to obtain a target area sub-map corresponding to the target division area.

[0217] In the embodiment of the present application, the region boundary or region distribution of the initial area sub-map can be updated based on the analyzed object information of the object, and then the target area sub-map corresponding to the intelligently divided target division area is obtained.

[0218] The second updating module 605 is configured to update the initial area map of the target scene according to the target area sub-map corresponding to the target division area.

[0219] In the embodiment of the present application, after the initial area sub-map corresponding to the target division area is updated by the object information of the object to obtain the target area sub-map corresponding to the target division area, the update of the region map of the target scene can be realized accordingly.

[0220] It can be seen that the intelligent division of the region as described in the embodiment of the present application can realize the intelligent division of the region based on the object in the target region, and improve the accuracy of the intelligent division result of the region while avoiding manual setting of markers. Figure 6

[0221] In an optional embodiment, refer to Figure 7 , Figure 7 FIG. 1 is a structural schematic diagram of the first updating module disclosed in the embodiment of the present application. The first updating module 604 includes a first judgment sub-module 6041, a distribution updating sub-module 6042, a second judgment sub-module 6043, and a boundary updating sub-module 6044. ​

[0222] The first judging sub-module 6041 is configured to judge whether the item is a boundary type item according to the type information of the item.

[0223] In the optional embodiment, whether the item is a boundary type item is judged according to the type information of the item obtained by the analyzing module 603. When the first judging sub-module 6041 judges that a certain item is a boundary type item, the initial region sub-map boundary can be corrected according to the boundary type item; when the first judging sub-module 6041 judges that the item is a non-boundary type item, the item cannot be used as an item for correcting the initial region sub-map boundary, but can be used as an item for correcting the initial region sub-map distribution region.

[0224] The distribution updating sub-module 6042 is configured to, if the first judging sub-module 6041 judges that the item is a non-boundary type item, determine a distribution sub-region where the item is located in the initial region sub-map corresponding to the target division region based on the first position information of the item, and update the initial region sub-map corresponding to the target division region according to the distribution sub-region, wherein the distribution sub-region where the item is located is used to represent the distribution of the item in the target division region.

[0225] In the optional embodiment, when the item is a non-boundary type item, the initial region sub-map distribution region can be corrected according to the item. Specifically, the distribution of the item in the target division region can be determined according to the distribution sub-region where the item is located in the initial region sub-map corresponding to the target division region.

[0226] The second judging sub-module 6043 is configured to, if the first judging sub-module 6041 judges that the item is a boundary type item, judge whether the first position information of the item matches the initial boundary position information, wherein the initial boundary position information is the initial boundary position information corresponding to the item in the initial region sub-map corresponding to the target division region.

[0227] In the optional embodiment, when the second judging sub-module 6043 judges that the first position information of the item matches the initial boundary position information, the initial boundary position information corresponding to the item in the initial region sub-map corresponding to the target division region is accurate and does not need to be corrected by the position information of the item. When the second judging sub-module 6043 judges that the first position information of the item does not match the initial boundary position information, the initial boundary position information corresponding to the item in the initial region sub-map corresponding to the target division region is inaccurate and needs to be corrected by the item information of the recognized item.

[0228] The boundary updating submodule 6044 is configured to, if the second determining submodule 6043 determines that the first position information of the object does not match the initial boundary position information, update the initial boundary position information based on the first position information of the object to obtain target boundary position information, and update the initial region submap corresponding to the target division region according to the target boundary position information.

[0229] In this optional embodiment, the initial boundary position information needs to be corrected based on the object information of the identified object. Specifically, the initial boundary position information corresponding to the object in the initial region submap corresponding to the target division region is corrected according to the first position information of the object to obtain corrected target boundary position information, and then the initial region submap corresponding to the target division region is updated according to the corrected target boundary position information.

[0230] It can be seen that, by implementing this optional embodiment, the content to be updated of the initial region submap can be determined according to the type information of the object, and the boundary position / distribution region of the initial region submap corresponding to the target division region can be further corrected or updated based on the position information of the object, so that a more accurate region submap of the target division region can be obtained.

[0231] In this optional embodiment, further, the first updating module 604 further includes a determining submodule 6045, a control submodule 6046, and a third determining submodule 6047.

[0232] The determining submodule 6045 is configured to, after the second determining submodule 6043 determines that the first position information of the object does not match the initial boundary position information, before the boundary updating submodule updates the initial boundary position information based on the first position information of the object to obtain target boundary position information and updates the initial region submap corresponding to the target division region according to the target boundary position information, determine the object edge position points of the object in the initial region submap corresponding to the target division region based on the size information of the object and the first position information of the object, where the object edge position points of the object are used to represent the edge positions of the object, and the object edge position points of the object are a plurality of.

[0233] In this optional embodiment, in the target scene, it is further needed to verify whether the object whose type is the boundary type is placed at the boundary position. The object information of the object includes the size information of the object, and the size information of the object and the first position information of the object can be used to determine a plurality of object edge position points of the object in the initial region submap corresponding to the target division region. The object edge position points of the object can be the vertices of the object or any point on the edge of the object, which is not limited in the embodiments of the present application.

[0234] The control submodule 6046 is configured to control the cleaning device to move in the to-be-tested region corresponding to the article, and record the movement track of the cleaning device in the initial region submap corresponding to the target division region. The to-be-tested region corresponding to the article is a region containing all article edge position points of the article.

[0235] In the optional embodiment, the to-be-tested region containing all article edge position points of the article can be determined according to the article edge position points of the article. The to-be-tested region is a virtual region in the initial region map, and is not limited by the initial boundary in the initial region map. By controlling the cleaning device to move in the to-be-tested region, it can be determined whether the article is placed at the region boundary position.

[0236] The third judgment submodule 6047 is configured to judge whether the movement track of the cleaning device is a closed track, and whether all article edge position points of the article are contained in the movement track of the cleaning device.

[0237] The distribution updating submodule 6042 is further configured to, if the third judgment submodule judges that the movement track of the cleaning device is a closed track, and all article edge position points of the article are contained in the movement track of the cleaning device, determine the distribution subregion in which the article is located in the initial region submap corresponding to the target division region based on the first position information of the article, and update the initial region submap corresponding to the target division region according to the distribution subregion.

[0238] The boundary updating submodule 6044 is further configured to, if the third judgment submodule judges that the movement track of the cleaning device is not a closed track, or all article edge position points of the article are not contained in the movement track of the cleaning device, update the initial boundary position information based on the first position information of the article to obtain target boundary position information, and update the initial region submap corresponding to the target division region according to the target boundary position information.

[0239] When the third judgment submodule 6047 judges that the movement track of the cleaning device is a closed track, and all article edge position points of the article are contained in the closed track, i.e., the article is not placed at the boundary position, the article can be used as an article for correcting the distribution region of the initial region submap, and the distribution updating submodule 6042 is used to determine the distribution subregion in which the article is located in the initial region submap corresponding to the target division region based on the first position information of the article, and update the initial region submap corresponding to the target division region according to the distribution subregion.

[0240] When the third determining sub-module 6047 determines that the moving track of the cleaning device cannot form a closed track, or the moving track of the cleaning device does not contain all edge position points of the object, i.e., the object is placed on the boundary position, the object can be used as an object for correcting the initial region sub-map boundary position. Then, the initial boundary position information is updated based on the first position information of the object by the boundary updating sub-module 6044 to obtain target boundary position information, and the initial region sub-map corresponding to the target division region is updated according to the target boundary position information.

[0241] It can be seen that by implementing the optional embodiment, whether the object of the boundary type is placed on the boundary position can be verified by controlling the movement of the cleaning device, and then the corresponding updating operation is performed according to the verification result, so that a more accurate region division result can be obtained.

[0242] In the optional embodiment, further optionally, the distribution updating sub-module 6042 determines the distribution sub-region in which the object is located in the initial region sub-map corresponding to the target division region based on the first position information of the object, and the manner in which the initial region sub-map corresponding to the target division region is updated according to the distribution sub-region includes:

[0243] The current distribution sub-region in which the object is located in the initial region sub-map corresponding to the target division region is determined according to the first position information of the object and the size information of the object.

[0244] It is determined whether the initial distribution sub-region corresponding to the object exists in the initial region sub-map corresponding to the target division region.

[0245] If not, the initial region sub-map corresponding to the target division region is updated according to the current distribution sub-region in which the object is located.

[0246] If yes, the initial distribution sub-region corresponding to the object is obtained, and it is determined whether the initial distribution sub-region corresponding to the object matches the current distribution sub-region in which the object is located.

[0247] If not, the initial distribution sub-region corresponding to the object is updated based on the current distribution sub-region in which the object is located to obtain a target distribution sub-region of the object, and the initial region sub-map corresponding to the target division region is updated according to the target distribution sub-region of the object.

[0248] In the optional embodiment, the object information of the object includes the size information of the object. The current distribution sub-region in which the object is located in the initial region sub-map corresponding to the target division region can be determined by the size information and the first position information of any object. The current distribution sub-region in which the object is located is the current distribution of the object in the target division region.

[0249] If the initial distribution sub-region corresponding to the article does not exist in the initial regional sub-map corresponding to the target division region, it is indicated that the article is a newly added article, and the current distribution sub-region of the article can be added to the initial regional sub-map. If the initial distribution sub-region corresponding to the article exists in the initial regional sub-map corresponding to the target division region, it is indicated that the article is not a newly added article, and whether the initial regional sub-map needs to be updated can be determined by comparing the matching of the initial distribution sub-region and the current distribution sub-region.

[0250] Whether the initial regional sub-map needs to be updated can be determined by comparing the matching of the initial distribution sub-region and the current distribution sub-region. If the initial distribution sub-region and the current distribution sub-region match, the sub-region where the article is located in the initial regional sub-map does not need to be corrected. If the initial distribution sub-region and the current distribution sub-region do not match, the sub-region where the article is located in the initial regional sub-map has changed, and needs to be updated by correction.

[0251] The current distribution sub-region of the article in the initial regional sub-map is updated to obtain the target distribution sub-region of the article after the initial distribution sub-region corresponding to the article is updated. The distribution of the article in the target division region can be determined, and the initial regional sub-map corresponding to the target division region after updating can be obtained.

[0252] It can be seen that by implementing the optional embodiment, the distribution of the article in the target division region can be determined according to the current distribution sub-region of the article, and the distribution region of the initial regional sub-map corresponding to the target division region can be further updated by the current distribution sub-region of the article, and a more accurate regional sub-map of the target division region can be obtained.

[0253] In another optional embodiment, referring to Figure 8 , Figure 8 is another structure diagram of the regional intelligent division device disclosed in the embodiment of the application, and the device further includes:

[0254] The first determination module 606 is configured to determine the initial boundary position information corresponding to the article in the initial regional sub-map corresponding to the target division region before updating the initial regional sub-map corresponding to the target division region based on the article information of the article.

[0255] The manner in which the first determination module 606 determines the initial boundary position information corresponding to the article in the initial regional sub-map corresponding to the target division region includes:

[0256] The collection direction of the cleaning equipment when collecting the target image of the target division region is determined.

[0257] The acquisition direction when the cleaning device collects the target image of the target division area is matched with the initial boundary in the initial area submap corresponding to the target division area, and position information corresponding to the initial boundary is determined as the initial boundary position information corresponding to the article in the initial area submap corresponding to the target division area.

[0258] In this optional embodiment, the initial boundary position information corresponding to the article in the initial area submap corresponding to the target division area can be determined through the acquisition direction when the cleaning device collects the target image of the target division area. The acquisition direction when the cleaning device collects the target image of the target division area can be determined through a direction sensor or through image recognition technology.

[0259] It can be seen that by implementing this optional embodiment, the distribution of the article in the target division area can be determined according to the current distribution subarea of the article, and the distribution area of the initial area submap corresponding to the target division area can be further updated through the current distribution subarea of the article, so as to obtain a more accurate area submap of the target division area.

[0260] In yet another optional embodiment, the analysis module 603 is further configured to:

[0261] After analyzing the target image to obtain the article contained in the target image and the article information of the article, the article recognition probability of the article is determined, and it is determined whether the article recognition probability of the article is greater than or equal to a preset threshold value.

[0262] The first updating module 604 is further configured to, if the analysis module 603 determines that the article recognition probability of the article is greater than or equal to the preset threshold value, perform the operation of updating the initial area submap corresponding to the target division area based on the article information of the article to obtain the target area submap corresponding to the target division area.

[0263] The acquisition module 602 is further configured to, if the analysis module 603 determines that the article recognition probability of the article is less than the preset threshold value, adjust the shooting angle of the cleaning device, and perform the operation of collecting the target image of the target division area by the cleaning device and analyzing the target image to obtain the article contained in the target image and the article information of the article.

[0264] In the optional embodiment, after identifying the item included in the target image and the item information of the item, the item recognition probability of the item included in the target image is determined. The item recognition probability is used to represent the accuracy of the identification result. Optionally, the item recognition probability can be determined by the matching degree of the current item and the standard item. When the item recognition probability exceeds the preset threshold, it indicates that the current identification result is accurate, and the identified item and the item information can be subjected to subsequent operations. When the item recognition probability does not exceed the preset threshold, it indicates that the current identification result is not accurate, and the shooting angle of the collection device needs to be adjusted, the target division region is re-collected, and the accurate identification result is obtained by re-identification.

[0265] It can be seen that by implementing the optional embodiment, the accuracy of the identification result can be judged, and the inaccurate identification result can be adaptively changed and re-identified to prevent misjudgment. The accuracy of the item identification result is ensured, and the accuracy of the subsequent regional intelligent division is ensured.

[0266] In another optional embodiment, the apparatus further includes a second determination module 607 configured to:

[0267] All items in the target division region and the category information of each item are obtained.

[0268] In the optional embodiment of the present application, the target division region includes one or more items, and all items included in the target division region can be obtained through a single, multiple or panoramic target image. The category information of each item included in the target division region is identified through image recognition technology. For example, the target division region includes item 1, item 2 and item 3, the category information of item 1 is identified as a dining table, the category information of item 2 is identified as a tea table, and the category information of item 3 is identified as a sofa.

[0269] It is judged whether all items in the target division region include an item with category information as a region-limited category. The region-limited category is used to represent that the probability of the corresponding item belonging to a certain determined region is greater than or equal to a preset probability threshold.

[0270] In the optional embodiment of the present application, the region-limited category is used to represent that the probability of the corresponding item belonging to a certain determined region is greater than or equal to a preset probability threshold. The preset probability threshold can be set according to the needs of the actual application scene. For example, if the category information of item 4 is a range hood, the range hood category information can be set as a region-limited category, which means that the probability of item 4 belonging to the kitchen is greater than or equal to a preset probability threshold.

[0271] If all the items in the target division region include the item of the region-limited category, the target item is obtained from all the items in the target division region, and the region attribute corresponding to the target item is determined as the attribute of the target division region, wherein the target item is the item of the region-limited category.

[0272] In an optional embodiment of the present application, if all the items in the target division region include the item of the region-limited category, the item of the region-limited category is obtained, for example, if all the items in the target division region include item 4 (the category information of which is a range hood), item 4 is taken as the target item, and the region attribute (kitchen) corresponding to item 4 is determined as the attribute (kitchen) of the target division region.

[0273] If all the items in the target division region do not include the item of the region-limited category, the region attribute corresponding to each item in the target division region is obtained.

[0274] According to the region attribute corresponding to each item in the target division region, the intersection region attribute of all the items in the target division region is determined, and the intersection region attribute is determined as the attribute of the target division region.

[0275] In an optional embodiment of the present application, if all the items in the target division region do not include the item of the region-limited category, the attribute of the target division region needs to be determined through the region attributes of multiple items in the target division region. For example, the region attribute of item 1 in the target division region is dining room and living room, the region attribute of item 2 is living room, and the region attribute of item 3 is living room and bedroom. According to the intersection region attribute of all the items in the target division region, the intersection region attribute set of the target division region can be obtained, and the region attribute in the intersection region attribute set can be taken as the candidate attribute of the target division region. For example, the intersection region attribute of all the items in the target division region is living room, and the living room is determined as the attribute of the target division region.

[0276] The attribute of the target division region is determined as the attribute of the target region sub-map corresponding to the target division region.

[0277] In an optional embodiment of the present application, the attribute of the target division region is determined as the attribute of the target region sub-map corresponding to the target division region, and is displayed in the target region sub-map of the target division region.

[0278] It can be seen that, by implementing the optional embodiment, the attribute of the target division region can be determined based on the items in the target region, and the region intelligent division result can be accurately obtained.

[0279] In an optional embodiment of the present application, further optionally, the second determining module 607 is further configured to: after determining the intersection region attribute of all the items in the target division region, determine the intersection region attribute as the attribute of the target division region before:

[0280] determine whether the intersection region attribute is unique.

[0281] If the intersection region attribute is unique, perform the operation of determining the intersection region attribute as the attribute of the target division region.

[0282] If the intersection region attribute is not unique, obtain a target intersection region attribute with the highest priority from the intersection region attribute according to a preset region attribute priority, and determine the target intersection region attribute as the attribute of the target division region.

[0283] In an optional embodiment of the present application, if there is only one intersection region attribute in the intersection region attribute set, the intersection region attribute can be determined as the attribute of the target division region. If there are multiple intersection region attributes in the intersection region attribute set, a target intersection region attribute with the highest priority can be determined through a preset region attribute priority, and the target intersection region attribute with the highest priority is determined as the attribute of the target division region. The region attribute priority can be set differently according to different target scenarios. Optionally, other intersection region attributes in the intersection region attribute set except the target intersection region attribute are taken as candidate attributes of the target division region for selection by an operator.

[0284] In an optional embodiment of the present application, further optionally, the second determining module 607 is further configured to: if it is determined that none of the items in the target division region includes an item of a region-limited category, after obtaining the region attribute corresponding to each item in the target division region:

[0285] obtain a region attribute set of the target division region according to the region attribute corresponding to each item in the target division region.

[0286] For each region attribute in the region attribute set of the target division region, the number of items including the region attribute is counted to obtain the frequency of the region attribute.

[0287] The frequencies of all the region attributes in the region attribute set of the target division region are obtained, and all the region attributes in the region attribute set of the target division region are sorted in descending order of frequency, the region attribute at the top of the sorting is determined as the attribute of the target division region, and then the attribute of the target region sub-map corresponding to the target division region is obtained.

[0288] It can be seen that by implementing the optional embodiment, the attribute of the target area sub-map corresponding to the target division area can be determined through the common area attribute of the plurality of items in the target division area, and the intelligent division result of the area can be accurately obtained.

[0289] Embodiment four

[0290] Please refer to Figure 9 , Figure 9 is another structural schematic diagram of the intelligent division device of the area according to an embodiment of the present application. As shown in the figure, Figure 9 the intelligent division device of the area can include:

[0291] The memory 901 stores executable program codes.

[0292] The processor 902 is coupled to the memory 901.

[0293] The processor 902 invokes the executable program codes stored in the memory 901 to execute the steps in the intelligent division method of the area described in Embodiment One or Embodiment Two of the present application.

[0294] Embodiment five

[0295] An embodiment of the present application discloses a cleaning device for performing the intelligent division method of the area described in Embodiment One or Embodiment Two of the present application.

[0296] Embodiment six

[0297] An embodiment of the present application discloses a computer storage medium storing computer instructions, which when invoked, are used to execute the steps in the intelligent division method of the area described in Embodiment One or Embodiment Two of the present application.

[0298] Embodiment seven

[0299] An embodiment of the present application discloses a computer program product including a non-transitory computer readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute the steps in the intelligent division method of the area described in Embodiment One or Embodiment Two.

[0300] The above-described device embodiments are only schematic, wherein the modules illustrated as separate components can or can not be physically separate, and the components illustrated as modules can or can not be physical modules, i.e., can be located in one place, or can be distributed on multiple network modules. Part or all of the modules can be selected according to actual needs to achieve the purpose of the present embodiment. Those skilled in the art can understand and implement without creative labor.

[0301] Through the specific description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be realized by means of software and the necessary general hardware platform, and of course, can also be realized by hardware. Based on such understanding, the above technical solutions, essentially or in terms of contribution to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer readable storage medium, including a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disk storage, a magnetic disk storage, a magnetic tape storage, or any other medium that can be used to carry or store data in a computer readable manner.

[0302] Finally, it should be noted that: the disclosed regional intelligent partitioning method and device disclosed by the embodiments of the present application are only the preferred embodiments of the present application, and are used to illustrate the technical solutions of the present application, but not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: the technical solutions recorded in the foregoing embodiments can still be modified, or some technical features can be replaced by equivalents; and these modifications or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for intelligently dividing regions, characterized in that, The method comprises: obtaining an initial area map for any target scene, the target scene comprising a plurality of divided areas, the initial area map comprising an initial area sub-map corresponding to each of the divided areas; based on the target image collected by the cleaning device in the target divided area, the target divided area being any of all the divided areas; analyzing the target image to obtain an article contained in the target image and article information of the article; updating the initial area sub-map corresponding to the target divided area based on the article information of the article to obtain a target area sub-map corresponding to the target divided area; updating the initial area map of the target scene according to the target area sub-map corresponding to the target divided area; the article information of the article comprises type information of the article and first position information of the article, wherein the first position information of the article is position information of the article in the initial area sub-map corresponding to the target divided area; the updating of the initial area sub-map corresponding to the target divided area based on the article information of the article comprises: determining whether the article is a boundary type article according to the type information of the article; if it is determined that the article is a non-boundary type article, determining a distribution sub-area where the article is located in the initial area sub-map corresponding to the target divided area based on the first position information of the article, and updating the initial area sub-map corresponding to the target divided area according to the distribution sub-area, wherein the distribution sub-area where the article is located is used to represent the distribution of the article in the target divided area; if it is determined that the article is a boundary type article, determining whether the first position information of the article matches the initial boundary position information, wherein the initial boundary position information is the initial boundary position information corresponding to the article in the initial area sub-map corresponding to the target divided area; if it is determined that the first position information of the article does not match the initial boundary position information, determining an article edge position point of the article in the initial area sub-map corresponding to the target divided area based on the size information of the article and the first position information of the article, wherein the article edge position point of the article is used to represent the edge position of the article, and the article edge position point of the article is a plurality of; controlling the cleaning device to move in a to-be-tested area corresponding to the article, and recording a moving track of the cleaning device in the initial area sub-map corresponding to the target divided area, wherein the to-be-tested area corresponding to the article is an area containing all article edge position points of the article; determining whether the moving track of the cleaning device is a closed track and whether all article edge position points of the article are contained in the moving track of the cleaning device. If the movement trajectory of the cleaning device is a closed trajectory, and the movement trajectory of the cleaning device includes all the edge position points of the item, then based on the first position information of the item, the distribution sub-region where the item is located in the initial sub-map corresponding to the target division area is determined, and the initial sub-map corresponding to the target division area is updated according to the distribution sub-region. If the movement trajectory of the cleaning device is not a closed trajectory, or if the movement trajectory of the cleaning device does not include all the edge position points of the item, then the initial boundary position information is updated based on the first position information of the item to obtain the target boundary position information, and the initial sub-map corresponding to the target division area is updated according to the target boundary position information.

2. The method for intelligent partition of regions according to claim 1, wherein, The item information also includes the item's size information, wherein the item's size information is the size information of the item in the initial region sub-map corresponding to the target division region; The step of determining the distribution sub-region where the item is located in the initial sub-map corresponding to the target division region based on the item's first location information, and updating the initial sub-map corresponding to the target division region according to the distribution sub-region, includes: Based on the first location information and the size information of the item, determine the current distribution sub-region of the item in the initial sub-map corresponding to the target division region; Determine whether the item's initial distribution sub-region exists in the initial sub-map corresponding to the target division area; If it does not exist, update the initial sub-map of the target partitioned area according to the current distribution sub-area where the item is located; If it exists, obtain the initial distribution sub-region corresponding to the item, and determine whether the initial distribution sub-region corresponding to the item matches the current distribution sub-region where the item is located; If there is no match, the initial distribution sub-region corresponding to the item is updated based on the current distribution sub-region where the item is located to obtain the target distribution sub-region of the item, and the initial region sub-map corresponding to the target division region is updated according to the target distribution sub-region of the item.

3. The method of claim 1, wherein, Before updating the initial sub-map corresponding to the target partitioned region based on the item information, the method further includes: Determine the initial boundary position information corresponding to the item in the initial sub-map of the target region; The step of determining the initial boundary position information corresponding to the item in the initial sub-map of the target division region includes: Determine the acquisition direction when the cleaning device acquires the target image of the target segmentation area; Obtain the initial boundary in the initial sub-map corresponding to the target area that matches the acquisition direction when the cleaning device acquires the target image of the target area, and determine the position information corresponding to the initial boundary as the initial boundary position information corresponding to the item in the initial sub-map corresponding to the target area.

4. The method for intelligent partition of regions according to claim 1 or 2, characterized in that, The method further includes: acquire all the items in the target division area and category information to which each of the items belongs; determine whether the items in the target division area include an item whose category information is a region-limited category, the region-limited category being used to represent that a corresponding item belongs to a certain determined region with a probability greater than or equal to a preset probability threshold; if the items in the target division area include the item whose category information is the region-limited category, acquire a target item from the items in the target division area, and determine a region attribute corresponding to the target item as an attribute of the target division area, wherein the target item is the item whose category information is the region-limited category; if the items in the target division area do not include the item whose category information is the region-limited category, acquire a region attribute corresponding to each of the items in the target division area; determine an intersection region attribute of the items in the target division area according to the region attribute corresponding to each of the items in the target division area, and determine the intersection region attribute as the attribute of the target division area; determine the attribute of the target division area as an attribute of a target region submap corresponding to the target division area.

5. The method for intelligent partition of regions according to claim 4, characterized in that, After the intersection region attribute of the items in the target division area is determined, before the intersection region attribute is determined as the attribute of the target division area, the method further includes: determine whether the intersection region attribute is unique; if the intersection region attribute is unique, perform the operation of determining the intersection region attribute as the attribute of the target division area; if the intersection region attribute is not unique, acquire a target intersection region attribute with the highest priority from the intersection region attribute according to a preset region attribute priority, and determine the target intersection region attribute as the attribute of the target division area.

6. The method of claim 1, wherein, After the target image is analyzed to obtain the items contained in the target image and the item information of the items, and before the initial region submap corresponding to the target division area is updated based on the item information of the items to obtain the target region submap corresponding to the target division area, the method further includes: determine an item recognition probability of the items; determine whether the item recognition probability of the items is greater than or equal to a preset threshold; if the item recognition probability of the items is greater than or equal to the preset threshold, perform the operation of updating the initial region submap corresponding to the target division area based on the item information of the items to obtain the target region submap corresponding to the target division area; if the item recognition probability of the items is less than the preset threshold, adjust a shooting angle of the cleaning device, and perform the operations of capturing a target image of the target division area by the cleaning device, and analyzing the target image to obtain the items contained in the target image and the item information of the items.

7. A smart area division device, characterized in that, The device is used to perform the intelligent division method of a region according to any one of claims 1-6, and the device includes: An acquisition module is configured to acquire an initial area map for any target scene, the target scene including a plurality of divided areas, and the initial area map including an initial area sub-map corresponding to each of the divided areas; A collection module is configured to collect a target image of a target divided area, the target divided area being any of all the divided areas; An analysis module is configured to analyze the target image to obtain an article contained in the target image and article information of the article; A first updating module is configured to update the initial area sub-map corresponding to the target divided area based on the article information of the article to obtain a target area sub-map corresponding to the target divided area; A second updating module is configured to update the initial area map of the target scene according to the target area sub-map corresponding to the target divided area.

8. A cleaning apparatus characterized by comprising: The cleaning device is configured to perform the intelligent division method of the area according to any one of claims 1-6.

Images