Intelligent partitioning method, apparatus, device, and computer-readable storage medium

Abstract

The application discloses an intelligent partition method, device and equipment and a computer readable storage medium. The method comprises the following steps: obtaining a space state graph; obtaining a first state graph according to the space state graph; performing a first processing on the first state graph for a preset number of times; recording a first connected domain in a free area in the first state graph every time the first processing is performed once; recording a target number of times of performing the first processing on the closed first connected domain; and updating the recorded first connected domain to an occupied area in the first space state graph after the first processing; performing the first processing on the first state graph for the preset number of times; performing inflation processing on each first connected domain in the space state graph to obtain an inflation-processed space state graph; marking each second connected domain in the inflation-processed space state graph to obtain a target state graph; and determining a partition graph of a to-be-processed area according to the target state graph. The application improves the completeness and accuracy of the partition processing on the to-be-processed area.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image processing, and in particular to an intelligent partitioning method, device, equipment and computer readable storage medium. BACKGROUND

[0002] With the improvement of living standards and the development of science and technology, the sweeping robot gradually enters people's life. When sweeping, the sweeping robot will obtain the structure map of the to-be-cleaned area to clean the to-be-cleaned area according to the structure map of the to-be-cleaned area. In actual use, the structure map of the to-be-cleaned area can also be divided into multiple cleaning areas according to the room distribution of the to-be-cleaned area or the user's demand, so as to provide the sweeping robot with customized cleaning for each cleaning area. However, in daily life, the to-be-cleaned area can be an irregular area, so when the structure map of the to-be-cleaned area is divided into multiple cleaning areas, part of the area is easily missed, which leads to incomplete partitioning of the to-be-cleaned area, so that the sweeping robot misses the part of the area when cleaning according to the partitioning map, thereby reducing the cleaning quality of the sweeping robot.

[0003] The above content is only used to assist in understanding the technical solutions of the present application and does not represent the acknowledgement of the above content as prior art. SUMMARY

[0004] The main purpose of the present application is to provide an intelligent partitioning method, device, equipment and computer readable storage medium, which aims to solve the technical problem that incomplete intelligent partitioning leads to omission of the sweeping robot when cleaning according to the partitioning map, thereby reducing the cleaning quality of the sweeping robot.

[0005] To achieve the above purpose, the present application provides an intelligent partitioning method, which comprises the following steps:

[0006] obtaining a space state map of a to-be-processed area, wherein the to-be-processed area in the space state map is divided into an occupied area, a free area and an unknown area;

[0007] obtaining a first state map according to the space state map, performing a first processing on the first state map for a preset number of times, recording a closed first connected domain in the free area of the first state map and recording the target number of times of performing the first processing corresponding to the closed first connected domain after performing the first processing once, and updating the recorded first connected domain to the occupied area in the first space state map after the first processing, wherein the first processing is an inflation processing on the occupied area in the first state map or an erosion processing on the free area in the first state map, and the area of the first connected domain is less than a preset first area;

[0008] After the first processing is performed on the first state graph for the preset number of times, each first connected domain in the spatial state graph is dilated to obtain a dilated spatial state graph, and each second connected domain in the dilated spatial state graph is labeled to obtain a target state graph, wherein the number of times of dilating the first connected domain is equal to the target number corresponding to the first connected domain, and the second connected domain is a free region corresponding to the first connected domain after dilating.

[0009] A partition map of the to-be-processed region is determined according to the target state graph.

[0010] Optionally, the step of obtaining the first state graph according to the spatial state graph comprises:

[0011] In a second state graph same as the spatial state graph, unknown regions surrounded by free regions and occupied regions are denoised to obtain the first state graph.

[0012] Optionally, the step of denoising the unknown regions surrounded by free regions and the occupied regions to obtain the first state graph comprises:

[0013] A third connected domain in the unknown regions in the second state graph is identified, and the third connected domain surrounded by free regions in the second state graph is updated to a free region to obtain a denoised second state graph.

[0014] A fourth connected domain in the occupied regions in the denoised second state graph is identified, and the fourth connected domain not connected to the unknown regions in the denoised second state graph is updated to a free region to obtain the first state graph.

[0015] Optionally, the step of determining the partition map of the to-be-processed region according to the target state graph comprises:

[0016] When it is determined that there is no overlapping region in the target state graph, the target state graph is taken as the partition map, wherein the overlapping region is a free region corresponding to the same pixel point in each second connected domain or a free region marked with multiple labels.

[0017] When it is determined that there is the overlapping region in the target state graph, the overlapping region in the target state graph is labeled to obtain a third state graph, and the third state graph is taken as the partition map.

[0018] Optionally, the step of labeling the overlapping region in the target state graph to obtain a third state graph comprises:

[0019] acquiring vertices of a circumscribed quadrilateral of the overlapping region, determining a first vertex, a second vertex and a third vertex from the vertices, wherein the first vertex and the second vertex are vertices of the circumscribed quadrilateral connected with an unknown region, and the third vertex is a vertex of the circumscribed quadrilateral in the second connected domain under the overlapping region;

[0020] connecting the first vertex and the third vertex to obtain a first connection line in the same first processing graph as the target state graph, and extending the first connection line to divide the second connected domain under the overlapping region into a plurality of fifth connected domains;

[0021] connecting the second vertex and the third vertex to obtain a second connection line in the same second processing graph as the target state graph, and extending the second connection line to divide the second connected domain under the overlapping region into a plurality of sixth connected domains;

[0022] taking the smallest connected domain in each of the fifth connected domains and the sixth connected domains as a region to be marked, and updating an identifier of the region to be marked according to an identifier of the second connected domain above the overlapping region in the target state graph to obtain the third state graph.

[0023] Optionally, the step of determining the partition graph of the region to be processed according to the target state graph comprises:

[0024] when it is determined that there is no unmarked region in the target state graph, taking the target state graph as the partition graph;

[0025] when it is determined that there is the unmarked region in the target state graph, detecting whether an area of the unmarked region is greater than a preset second area;

[0026] when it is determined that the area of the unmarked region is greater than the second area, marking the unmarked region in the target state graph to obtain a fourth state graph, and taking the fourth state graph as the partition graph.

[0027] Optionally, after the step of detecting whether the area of the unmarked region is greater than the second area, the method further comprises:

[0028] when it is determined that the area of the unmarked region is not greater than the second area, detecting whether the unmarked region is connected with a marked region;

[0029] when it is determined that the unmarked region is not connected with the marked region, updating the unmarked region to an unknown region in the target state graph to obtain a fifth state graph, and taking the fifth state graph as the partition graph;

[0030] when it is determined that the unmarked region is connected to a plurality of different marked regions, determining whether the unmarked region is connected to a plurality of different marked regions;

[0031] when it is determined that the unmarked region is not connected to a plurality of different marked regions, marking the unmarked region according to the identification of the marked region to obtain a sixth state graph, and taking the sixth state graph as the partition graph;

[0032] when it is determined that the unmarked region is connected to a plurality of different marked regions, determining a target region from each of the marked regions, marking the unmarked region according to the identification of the target region to obtain a seventh state graph, and taking the seventh state graph as the partition graph, wherein the target region has a contact area with the unmarked region that exceeds a preset threshold proportion of a sum of contact areas of each of the marked regions with the unmarked region, or is the marked region with the most contained pixel points.

[0033] To achieve the above object, the application further provides an intelligent partition device, which comprises:

[0034] an acquisition module, configured to acquire a space state graph of a to-be-processed region, wherein the to-be-processed region in the space state graph is divided into an occupied region, a free region and an unknown region;

[0035] a processing module, configured to acquire a first state graph according to the space state graph, and perform a first processing on the first state graph for a preset number of times, record a first connected domain that is closed in the free region in the first state graph and a target number of times of performing the first processing for closing the first connected domain after performing the first processing once each time, and update the first connected domain that has been recorded to the occupied region in the first space state graph after the first processing, wherein the first processing is an expansion processing on the occupied region in the first state graph or an erosion processing on the free region in the first state graph, and the area of the first connected domain is less than a preset first area;

[0036] the processing module is further configured to, after performing the first processing on the first state graph for the preset number of times, perform an expansion processing on each of the first connected domains in the space state graph to obtain a space state graph after the expansion processing, and perform marking on each of second connected domains in the space state graph after the expansion processing to obtain a target state graph, wherein the number of times of performing the expansion processing on the first connected domain is equal to the target number of times corresponding to the first connected domain, and the second connected domain is a free region corresponding to the first connected domain after the expansion processing;

[0037] a determination module, configured to determine a partition graph of the to-be-processed region according to the target state graph.

[0038] To achieve the above object, the present application further provides an intelligent partition device, comprising a memory, a processor and an intelligent partition program stored in the memory and executable on the processor, wherein the intelligent partition program implements the steps of the intelligent partition method when executed by the processor.

[0039] In addition, to achieve the above object, the present application further provides a computer readable storage medium, wherein the computer readable storage medium stores an intelligent partition program, and the intelligent partition program implements the steps of the intelligent partition method when executed by a processor.

[0040] In the present application, by acquiring a space state graph of a to-be-processed region, a first state graph is acquired according to the space state graph, the first state graph is subjected to a first processing for a preset number of times, after each first processing, a first connected domain enclosed in a free region in the first state graph is recorded, a target number of times of first processing corresponding to the first connected domain is recorded, the first connected domain that has been recorded is updated as an occupied region in the first space state graph after the first processing, after the first state graph is subjected to the first processing for the preset number of times, each first connected domain in the space state graph is subjected to an inflation processing to obtain an inflation-processed space state graph, each second connected domain in the inflation-processed space state graph is marked to obtain a target state graph, and the partition graph of the to-be-processed region is determined according to the target state graph. The present application realizes the improvement of the completeness and accuracy of the partition processing of the to-be-processed region. BRIEF DESCRIPTION OF DRAWINGS

[0041] Figure 1 The figure is a flowchart of the first embodiment of the intelligent partition method of the present application.

[0042] Figure 2 The figure is a functional module schematic diagram of the embodiment of the intelligent partition device of the present application.

[0043] Figure 3 The figure is a structural schematic diagram of the intelligent partition device of the hardware running environment involved in the embodiment scheme of the present application.

[0044] The realization of the object, the functional features and the advantages of the present application will be further explained with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0045] It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application.

[0046] The embodiment of the present application provides an intelligent partition method, referring to Figure 1 , Figure 1A flowchart of a first embodiment of an intelligent partitioning method of the present application. It should be noted that although a logical sequence is shown in the flowchart, in some cases, the steps shown or described can be performed in an order different from that shown here. The intelligent partitioning method can be performed by a personal computer, a smartphone, a server, etc. In this embodiment, it is not limited, and for the convenience of description, the following description is omitted. In this embodiment, the intelligent partitioning method includes:

[0047] In step S10, a space state map of the region to be processed is obtained, wherein the region to be processed is divided into an occupied region, a free region, and an unknown region in the space state map.

[0048] When sweeping, the robot will obtain the structure map of the area to be cleaned, and clean the area to be cleaned according to the structure map of the area to be cleaned. In actual use, the structure map of the area to be cleaned can also be divided into multiple cleaning areas according to the room distribution of the area to be cleaned or the user's needs, so that the robot can clean each cleaning area. However, in daily life, the area to be cleaned may be an irregular area, so when the structure map of the area to be cleaned is divided into multiple cleaning areas, some areas are easily missed, which leads to incomplete partitioning of the area to be cleaned, and the robot misses some areas when cleaning according to the partitioning map, which reduces the cleaning quality of the robot.

[0049] In this embodiment, an intelligent partitioning method is proposed, which divides the area to be cleaned into multiple partitions, so that the robot does not miss the area to be cleaned when working, and improves the cleaning quality of the robot.

[0050] In this embodiment, the area to be partitioned is referred to as the region to be processed. A planar image of the region to be processed is obtained, which is divided into an occupied region, a free region, and an unknown region, and is referred to as a space state map for distinction. In the specific embodiment, the occupied region can be a region with obstacles, such as walls, tables, etc. in the region to be processed, the free region can be a region without obstacles in the region to be processed, and the unknown region can be a region that cannot be identified other than the occupied region and the free region, such as a space in the wall.

[0051] Specifically, in an embodiment, the space state map can be obtained by obtaining a map obtained by slam (simultaneous localization and mapping) of the robot, or directly obtaining a pre-configured planar image of the region to be processed, which is not limited in detail.

[0052] In step S20, a first state graph is obtained according to the space state graph, a first processing is performed on the first state graph for a preset number of times, a first connected domain in a free area of the first state graph is recorded after each first processing, a target number of times of performing the first processing for closing the first connected domain is recorded, and the first connected domain that has been recorded is updated as an occupied area in the first space state graph after the first processing. The first processing is an expansion processing on the occupied area in the first state graph or an erosion processing on the free area in the first state graph, and the area of the first connected domain is less than a preset first area.

[0053] In this embodiment, a graph for partitioning (hereinafter referred to as a first state graph for the sake of distinction) is obtained according to the space state graph. In the specific embodiment, the first state graph can be obtained by copying the space state graph, or the first state graph can be obtained by drawing according to the space state graph. The specific configuration can be set according to actual needs, and is not limited herein.

[0054] The first processing is performed on the first state graph for a preset number of times to divide the free area in the first state graph into a plurality of closed connected domains. Specifically, in an embodiment, the preset number of times can be preconfigured. In another embodiment, the preset number of times can be set according to actual needs. For example, when the door of the to-be-processed area is 1 meter wide, the first processing of 15 times of 3x3 kernel is required to be performed on the space state graph to close the door of the room. At this time, the preset number of times can be updated to 15 times. The specific configuration is not limited herein.

[0055] In the specific embodiment, the first processing can be an erosion processing on the free area in the space state graph, or an expansion processing on the occupied area in the space state graph. The specific configuration is not limited herein.

[0056] In this embodiment, the connected domain in the free area is identified after each first processing. When it is determined that the first connected domain exists in the free area, the first connected domain is recorded, and the number of times of performing the first processing for closing the first connected domain (hereinafter referred to as a target number of times for the sake of distinction) is recorded. The first connected domain is a connected domain in the free area, and the area of the first connected domain is less than a preset area (hereinafter referred to as a first area for the sake of distinction).

[0057] In the specific embodiment, the first area can be preconfigured, or can be set according to user needs. For example, the first area can be updated to the maximum area among the areas of the rooms in the user's residence. The specific configuration is not limited herein, and can be set according to actual needs.

[0058] Further, in an embodiment, when the area of each connected domain obtained after the first processing is greater than the first area, a plurality of graphs identical to the first state graph after the first processing (hereinafter referred to as first copy graphs for convenience of description) are obtained, and the number of the copy graphs is equal to the number of the closed connected domains in the free area in the first state graph after the first processing.

[0059] For each copy graph, a to-be-processed connected domain is determined in the closed connected domain in the free area in the copy graph, each connected domain in the free area that is not the to-be-processed area in the copy graph is updated to an occupied area to obtain a second copy graph, and the to-be-processed connected domain is closed to a plurality of connected domains by performing the first processing on the second copy graph a certain number of times, wherein the number of times of performing the first processing on the second copy graph is the preset number of times minus the number of times of performing the first processing when the first copy graph is obtained. After each first processing on the second copy graph, the first connected domain and the target number of times are recorded.

[0060] In step S30, after the first processing on the first state graph is performed the preset number of times, each first connected domain in the space state graph is dilated to obtain a space state graph after dilation, and each second connected domain in the space state graph after dilation is marked to obtain a target state graph, wherein the number of times of dilating the first connected domain is equal to the target number of times corresponding to the first connected domain, and the second connected domain is a free area corresponding to the first connected domain after dilation.

[0061] After the first processing on the first state graph is completed the preset number of times, each first connected domain recorded is dilated in the space state graph, so that the area of each first connected domain returns to the size before the first processing. The number of times of dilating the first connected domain is equal to the target number of times corresponding to the first connected domain.

[0062] Each free area corresponding to the first connected domain in the space state graph after dilation is referred to as a second connected domain for distinction, and each second connected domain is marked to obtain a target state graph. Further, in specific embodiments, each second connected domain can be marked with a different mark, or a plurality of second connected domains can be marked with the same mark, which is not limited in specific embodiments and can be set according to actual needs. In specific embodiments, the mark can be in various forms, for example, can be a color mark, or a numerical or symbolic mark, which is not limited herein.

[0063] In specific embodiments, when each second connected domain in the space state graph is marked, the marking can be performed in a certain order, for example, in the order of recording the first connected domain, which can be set according to actual needs and is not limited herein.

[0064] Step S40, determining the partition map of the to-be-processed region according to the target state map.

[0065] In this embodiment, after marking the space state map, the partition map of the to-be-processed region can be determined according to the target state map obtained after marking.

[0066] Specifically, in an embodiment, the target state map can be used as the partition map; in another embodiment, the target state map can be processed, and the processed target state map can be used as the partition map, for example, processing of overlapping regions, and the like, which are not limited herein.

[0067] In this embodiment, by performing the first processing on the first state map of the to-be-processed region, the free region of the space state map can be closed to obtain a plurality of first connected domains, so that no partition is missed during the partition processing. The first connected domain in the space state map is processed by inflation to restore the first connected domain to the area before the first processing, and the second connected domain in the space state map after the inflation processing is marked to obtain the partition map, so that the size of each partition in the partition map conforms to the actual area, avoiding missing partitions, improving the completeness and accuracy of the partition processing of the to-be-processed region, and thus improving the cleaning quality when the cleaning robot cleans according to the partition map.

[0068] Further, based on the first embodiment, a second embodiment of the intelligent partition method of the present application is proposed. In this embodiment, the step S20 of obtaining the first state map according to the space state map comprises:

[0069] Step S50, in the second state map same as the space state map, the unknown region surrounded by the free region and the occupied region are denoised to obtain the first state map.

[0070] In this embodiment, the unknown region surrounded by the free region and the occupied region in the second state map (hereinafter referred to as the second state map for distinction) same as the space state map are denoised, and the second state map after denoising is used as the first state map, avoiding missing some regions during the partition processing, and improving the completeness and accuracy of the partition processing. In the specific embodiment, the second state map can be obtained by copying the space state map, or can be obtained by drawing according to the space state map, which is not limited herein.

[0071] Specifically, in an embodiment, the unknown region and the occupied region can be denoised according to the connected domain; in another embodiment, the image denoising method based on filter, model and learning can be used for processing, which is not limited herein.

[0072] Further, in an embodiment, the step S50 comprises:

[0073] In step S501, a third connected domain in the unknown region in the second state graph is identified, and the third connected domain surrounded by the free region in the second state graph is updated as a free region to obtain the second state graph after the de-noising processing.

[0074] In this embodiment, the first state graph is obtained by de-noising processing based on the connected domains of the unknown region and the occupied region in the second state graph.

[0075] Specifically, in this embodiment, the connected domains of the unknown region in the second state graph are identified (hereinafter referred to as third connected domains for distinction), and each third connected domain can be a connected domain surrounding the occupied region and the free region, or a connected domain surrounded by the free region.

[0076] When the third connected domain is a connected domain surrounding the occupied region and the free region, the connected domain can correspond to a region on the periphery of the to-be-processed region, and in this case, the second connected domain can not be processed. When the second connected domain is a connected domain surrounded by the free region, the second connected domain can correspond to a region in the to-be-processed region, and in this case, the second connected domain can be de-noised, that is, the second connected domain is updated as a free region to obtain the second state graph after the de-noising processing, so as to avoid missing the region corresponding to the second connected domain in the partition processing.

[0077] In step S502, a fourth connected domain in the occupied region in the second state graph after the de-noising processing is identified, and the fourth connected domain not connected with the unknown region in the second state graph after the de-noising processing is updated as a free region to obtain the first state graph.

[0078] In this embodiment, the occupied region in the second state graph after the de-noising processing is processed. Specifically, the connected domains of the occupied region in the second state graph after the de-noising processing are identified (hereinafter referred to as fourth connected domains for distinction). The fourth connected domain can be a connected domain connected with the unknown region, or a connected domain not connected with the unknown region.

[0079] In the second state graph after the de-noising processing, the unknown region only retains the second connected domain on the periphery of the to-be-processed region. Therefore, when the fourth connected domain is a connected domain connected with the unknown region, the third connected domain can correspond to the outer wall of the to-be-processed region. When the third connected domain is a connected domain not connected with the unknown region, the fourth connected domain can correspond to an obstacle in the to-be-processed region, such as a table, and in this case, the fourth connected domain can be de-noised, and the fourth connected domain is updated as a free region to avoid missing the region corresponding to the third connected domain in the partition processing.

[0080] It should be noted that the occupied area and the unknown area surrounded by the free area are denoised to avoid missing some areas during the partition processing, improve the completeness and accuracy of the partition processing, and thus improve the cleaning quality when the sweeping robot cleans according to the partition map.

[0081] In this embodiment, the unknown area and the occupied area surrounded by the free area in the second state map are denoised to avoid missing some areas during the partition processing, improve the completeness and accuracy of the partition processing, and thus improve the cleaning quality when the sweeping robot cleans according to the partition map.

[0082] Further, based on the first embodiment, a third embodiment of the intelligent partition method is provided. In this embodiment, the step S40 includes:

[0083] In step S401, when it is determined that there is no overlapping area in the target state map, the target state map is taken as the partition map, wherein the overlapping area is a free area corresponding to the same pixel point in each second connected domain or a free area marked with multiple labels.

[0084] Since the area of each first connected domain is increased to obtain the second connected domain during the expansion processing of the space state map, there may be an overlapping condition of multiple second connected domains in the space state map after the expansion processing, that is, there may be an overlapping area in the space state map after the expansion processing.

[0085] In this embodiment, when it is determined that there is no overlapping area in the target state map, the target state map is taken as the partition map. The overlapping area is a free area corresponding to the same pixel point in each second connected domain or a free area marked with multiple labels.

[0086] In the specific embodiment, whether there is an overlapping area can be detected by detecting whether there is the same pixel point in the second connected domain, or whether there is a region marked with multiple labels in the free area. The specific implementation is not described here, and can be set according to actual needs.

[0087] In step S402, when it is determined that there is the overlapping area in the target state map, the overlapping area in the target state map is marked to obtain a third state map, and the third state map is taken as the partition map.

[0088] When it is determined that there is the same pixel point in each second connected domain or there is a region marked with multiple labels in the target state map, it is determined that there is an overlapping area in the target state map. At this time, the overlapping area in the target state map can be marked. The target state map after the overlapping area is marked is referred to as a third state map for distinction. The third state map is taken as the partition map.

[0089] It should be noted that when it is determined that there is no overlapping area in the target state map, the target state map is taken as the partition map. When it is determined that there is an overlapping area, the overlapping area is marked in the target state map to obtain a third state map, and the third state map is taken as the partition, so as to avoid that part of the area is repeatedly marked, improve the accuracy of the partition processing, and thus improve the cleaning quality when the sweeping robot cleans according to the partition map.

[0090] Further, in an embodiment, the step of marking the overlapping area in the target state map to obtain a third state map in the step S402 includes:

[0091] In step S4021, the vertices of the circumscribed quadrilateral of the overlapping area are obtained, and a first vertex, a second vertex and a third vertex are determined from each of the vertices, wherein the first vertex and the second vertex are the vertices of the circumscribed quadrilateral connected with the occupied area, and the third vertex is the vertex of the circumscribed quadrilateral in the second connected domain under the overlapping area;

[0092] In the embodiment, the overlapping area in the target state map is marked to obtain a third state map. The overlapping area can be a regular area, for example, when the space state map is a grid map, at this time, the overlapping area can be a regular quadrilateral area; the overlapping area can also be an irregular area, for example, when the space state map is a dot array map, the overlapping area can be an irregular area with a wavy edge, which is not limited in particular.

[0093] Specifically, in the embodiment, the vertices of the circumscribed quadrilateral of the overlapping area are obtained. The overlapping area is a region generated when the second connected domain in the space state map is marked, and the second connected domain is obtained by closing the occupied area. Therefore, the vertices of the circumscribed quadrilateral of the overlapping area can be divided into points connected with the occupied area and points surrounded by the second connected domain. Since the overlapping area is obtained by overlapping multiple second connected domains, the vertices surrounded by the second connected domain can be divided into points in the second connected domain above the overlapping area and points in the second connected domain under the overlapping area. In the embodiment, the two vertices connected with the occupied area are referred to as a first vertex and a second vertex for distinction, and the vertex in the second connected domain under the overlapping area is referred to as a third vertex for distinction.

[0094] In step S4022, the first vertex and the third vertex are connected in the same first processing map as the target state map to obtain a first connection line, and the first connection line is extended to divide the second connected domain under the overlapping area into a plurality of fifth connected domains.

[0095] In the embodiment, after the first vertex and the third vertex are determined, a connection line (hereinafter referred to as a first connection line for the purpose of distinction) is obtained by connecting the first vertex and the third vertex in a same graph as the target state graph (hereinafter referred to as a first processing graph for the purpose of distinction), and a plurality of fifth connected domains (hereinafter referred to as fifth connected domains for the purpose of distinction) are obtained by extending the first connection line to divide the second connected domain under the overlapping region.

[0096] In the specific embodiment, the first processing graph can be obtained by referring to step S20, and thus no further description is provided herein.

[0097] In step S4023, a second connection line is obtained by connecting the second vertex and the third vertex in the second processing graph, and a plurality of sixth connected domains are obtained by extending the second connection line to divide the second connected domain under the overlapping region.

[0098] In the embodiment, after the second vertex and the third vertex are determined, a connection line (hereinafter referred to as a second connection line for the purpose of distinction) is obtained by connecting the second vertex and the third vertex in a same graph as the target state graph (hereinafter referred to as a second processing graph for the purpose of distinction), and a plurality of sixth connected domains (hereinafter referred to as sixth connected domains for the purpose of distinction) are obtained by extending the second connection line to divide the second connected domain under the overlapping region.

[0099] In the specific embodiment, the second processing graph can be obtained by referring to step S20, and thus no further description is provided herein.

[0100] It should be noted that the first processing graph and the second processing graph are two graphs which are respectively the same as the target state graph.

[0101] In step S4024, the smallest connected domain in each of the fifth connected domains and the sixth connected domains is taken as a to-be-labeled region, and the third state graph is obtained by updating the identification of the to-be-labeled region according to the identification of the second connected domain above the overlapping region in the target state graph.

[0102] In the embodiment, after the fifth connected domains and the sixth connected domains are obtained, the smallest connected domain in each of the fifth connected domains and the sixth connected domains is taken as a to-be-labeled region, and the third state graph is obtained by updating the identification of the to-be-labeled region according to the identification of the second connected domain above the overlapping region in the target state graph.

[0103] It should be noted that by acquiring the vertices of the circumscribed quadrilateral of the overlapping region, the first vertex, the second vertex and the third vertex are determined from each vertex, the first vertex and the third vertex are connected and extended in the first processing graph, the second connected domain under the overlapping region is divided into a plurality of fifth connected domains, and the second vertex and the third vertex are connected and extended in the second processing, the second connected domain under the overlapping region is divided into a plurality of sixth connected domains. The smallest connected domain in each fifth connected domain and each sixth connected domain is taken as the to-be-labeled region, and the identification of the to-be-labeled region in the target state graph is updated according to the identification of the second connected domain in the upper layer of the overlapping region to obtain a third state graph. The processing range of the overlapping region can be more accurately determined, the accuracy of the partition processing is improved, and thus the cleaning quality when the sweeping robot cleans according to the partition graph is improved.

[0104] In the embodiment, when it is determined that the target state graph does not exist the overlapping region, the target state graph is taken as the partition graph. When it is determined that the overlapping region exists, the overlapping region in the target state graph is labeled to obtain a third state graph, and the third state graph is taken as the partition to avoid that part of the region is repeatedly labeled, improve the accuracy of the partition processing, and thus improve the cleaning quality when the sweeping robot cleans according to the partition graph.

[0105] Further, based on the first / second / third embodiments, a fourth embodiment of the intelligent partition method of the application is provided. In the embodiment, the step S40 includes:

[0106] In step S403, when it is determined that the target state graph does not exist the unmarked region, the target state graph is taken as the partition graph.

[0107] When the first state graph is processed, part of the free region with a narrow width may be processed as an occupied region. The part of the region is not recorded when the first connected domain is recorded, and the part of the region may be missed when the first connected domain (and the second connected domain) after the inflation processing is labeled. The part of the region is referred to as an unmarked region.

[0108] In the embodiment, when it is determined that the target state graph does not exist the unmarked region, the target state graph is taken as the partition graph.

[0109] In step S404, when it is determined that the target state graph exists the unmarked region, it is detected whether the area of the unmarked region is greater than a preset second area.

[0110] When it is determined that the target state graph exists the unmarked region, the unmarked region can be labeled.

[0111] Specifically, in this embodiment, it is detected whether the area of the marked region is greater than a preset area, which is referred to as a second area for the sake of distinction below. In specific embodiments, the second area can be preconfigured, or can be set according to actual requirements, for example, can be set as the area of a balcony or a corridor in a user's residence, and the specific implementation is not limited here.

[0112] In step S405, when it is determined that the area of the unmarked region is greater than the second area, the unmarked region is marked in the target state map to obtain a fourth state map, and the fourth state map is taken as the partition map.

[0113] When it is determined that the area of the unmarked region is greater than the second area, the unknown region can be a region with a smaller area in the to-be-processed region that needs to be cleaned, for example, a balcony or a corridor of a room, and at this time, the unmarked region is marked to obtain a marked target state map, which is referred to as a fourth state map for the sake of distinction below.

[0114] Specifically, in an embodiment, the unmarked region can be marked according to a preset mark, where the preset mark can be the same as or different from the existing mark in the space state map; in another embodiment, the unmarked region can also be marked according to actual requirements, and the specific implementation is not limited here.

[0115] It should be noted that when it is determined that there is no unmarked region in the target state map, the target state map is taken as the partition map. When it is determined that the area of the unmarked region is greater than the second area, the unmarked region is marked in the target state map to obtain a fourth state map, and the fourth state map is taken as the partition map, so as to avoid the existence of the unmarked region in the partition map, improve the accuracy and completeness of the partition map, and thus improve the cleaning quality when the sweeping robot cleans according to the partition map.

[0116] Further, in an embodiment, after the step of detecting whether the area of the unmarked region is greater than the preset second area in step S404, the method further includes:

[0117] In step S406, when it is determined that the area of the unmarked region is not greater than the second area, it is detected whether the unmarked region is connected to a marked region.

[0118] When it is determined that the area of the unmarked region is not greater than the second area, it is detected whether the unmarked region is connected to a marked region.

[0119] In specific embodiments, it can be detected whether the unmarked region is connected to the marked region by detecting whether the region connected to the unmarked region has a mark, and the specific implementation is not repeated here.

[0120] Step S407, when determining that the unmarked region is not connected to the marked region, updating the unmarked region to an unknown region in the target state map to obtain a fifth state map, and taking the fifth state map as the partition map;

[0121] When it is determined that the unmarked region is not connected to the marked region, at this time, the unmarked region can not be in the free region of the space state map, and can be an area that is too small for the sweeping robot to clean, for example, an area with a width less than the size of the sweeping robot. At this time, the unmarked region can be updated to an unknown region, and the obtained picture is referred to as a fifth state map below, and the fifth state map is taken as the partition map.

[0122] Step S408, when determining that the unmarked region is connected to the marked region, detecting whether the unmarked region is connected to multiple different marked regions.

[0123] When it is determined that the unmarked region with an area less than the second area is connected to the marked region, it is detected whether the unmarked region is connected to multiple different marked regions.

[0124] The specific detection manner can be that it is detected whether multiple different labels exist in the marked regions connected to the unmarked region, which is not described herein.

[0125] Step S409, when determining that the unmarked region is not connected to multiple different marked regions, marking the unmarked region according to the labels of the marked regions to obtain a sixth state map, and taking the sixth state map as the partition map.

[0126] When it is determined that the unmarked region is not connected to multiple different marked regions, that is, when it is determined that the unmarked region is connected to the marked region with one label, the region can be a region in a partition of the to-be-processed region that is connected to multiple marked regions, for example, a region at the joint of a bedroom and a bathroom in a suite.

[0127] In this embodiment, the unmarked region is marked according to the labels of the marked regions, and the target state map after marking is referred to as a sixth state map below for distinction, and the sixth state map is taken as the partition map.

[0128] Step S410, when determining that the unmarked region is connected to multiple different marked regions, determining a target region from each of the marked regions, marking the unmarked region according to the label of the target region to obtain a seventh state map, and taking the seventh state map as the partition map, wherein the target region has a contact area with the unmarked region that accounts for more than a preset threshold proportion of the sum of the contact areas of each of the marked regions with the unmarked region, or is the marked region with the most contained pixel points.

[0129] When it is determined that the unmarked region connects multiple different marked regions, the region can be a region in which the to-be-processed region is connected to multiple sub-regions, for example, a corridor of a room. At this time, a target region can be determined from each marked region, and the unmarked region is marked according to the identification of the target region. The resulting graph is referred to as a seventh state graph, and the seventh state graph is taken as a sub-region graph.

[0130] In the specific embodiment, the proportion of the contact area of the target region and the unmarked region to the sum of the contact areas of each marked region and the unmarked region exceeds a preset threshold, or the target region is the marked region with the most contained pixel points.

[0131] It should be noted that when it is determined that the unmarked region connects multiple marked regions, the unmarked region is identified according to the identification of the marked region, so that the identification accuracy of the unmarked region is higher, and thus the sub-region processing accuracy of the to-be-processed region is higher, and the cleaning quality when the sweeping robot cleans according to the sub-region graph is improved.

[0132] In the embodiment, when it is determined that the unmarked region exists in the sub-region graph, it is detected whether the area of the unmarked region is greater than a preset second area. When it is determined that the area of the unmarked region is greater than the second area, the unmarked region is marked, which can avoid missing part of the region that needs to be sub-regionalized in the process of sub-region processing of the to-be-processed region, and improve the completeness of the sub-region processing. When it is determined that the area of the unmarked region is not greater than the second area, it is detected whether the unmarked region is connected to the marked region. When it is determined that the unmarked region is not connected to the marked region, the unmarked region can be a region with a small area that cannot be cleaned by the sweeping robot. The unmarked region is updated as an unknown region, which can avoid sub-region processing of unnecessary regions and improve the accuracy of the sub-region processing, thereby improving the cleaning quality when the sweeping robot cleans according to the sub-region graph.

[0133] The application also provides an intelligent sub-region device, referring to Figure 2 , the intelligent sub-region device comprises:

[0134] The acquisition module 10 is configured to acquire a space state graph of a to-be-processed region, wherein the to-be-processed region in the space state graph is divided into an occupied region, a free region, and an unknown region.

[0135] The processing module 20 is configured to acquire a first state graph according to the space state graph, perform a first processing on the first state graph for a preset number of times, record a first connected domain enclosed in a free region in the first state graph after each time of performing the first processing, and record a target number of times of performing the first processing corresponding to the first connected domain, update the first connected domain recorded in the first space state graph to an occupied region after the first processing, wherein the first processing is an expansion processing on the occupied region in the first state graph or an erosion processing on the free region in the first state graph, and the first connected domain has an area less than a preset first area.

[0136] The processing module 20 is further configured to perform an expansion processing on each first connected domain in the space state graph to obtain an expansion-processed space state graph after the first processing on the first state graph is performed for the preset number of times, and perform labeling on each second connected domain in the expansion-processed space state graph to obtain a target state graph, wherein a number of times of performing the expansion processing on the first connected domain is equal to the target number of times corresponding to the first connected domain, and the second connected domain is a free region corresponding to the first connected domain after the expansion processing.

[0137] The determining module 30 is configured to determine a partition graph of the to-be-processed region according to the target state graph.

[0138] Further, the processing module 20 is further configured to:

[0139] In a second state graph same as the space state graph, perform a denoising processing on an unknown region surrounded by a free region and an occupied region to obtain the first state graph.

[0140] Further, the processing module 20 is further configured to:

[0141] Identify a third connected domain in the unknown region in the second state graph, and update the third connected domain surrounded by the free region in the second state graph to the free region to obtain the second state graph after the denoising processing.

[0142] Identify a fourth connected domain in the occupied region in the second state graph after the denoising processing, and update the fourth connected domain not connected with the unknown region in the second state graph after the denoising processing to the free region to obtain the first state graph.

[0143] Further, the determining module 30 is further configured to:

[0144] determining that the target state graph does not have an overlapping region, wherein the overlapping region is a free region corresponding to the same pixel point in each of the second connected domains or a free region marked with multiple labels, and taking the target state graph as the partition graph;

[0145] when it is determined that the target state graph has the overlapping region, marking the overlapping region in the target state graph to obtain a third state graph, and taking the third state graph as the partition graph.

[0146] Further, the determining module 30 is further configured to:

[0147] obtaining vertices of a circumscribed quadrilateral of the overlapping region, determining a first vertex, a second vertex and a third vertex from each of the vertices, wherein the first vertex and the second vertex are vertices of the circumscribed quadrilateral connected with an unknown region, and the third vertex is a vertex of the circumscribed quadrilateral in the second connected domain under the overlapping region;

[0148] connecting the first vertex and the third vertex in a first processing graph same as the target state graph to obtain a first connection line, and extending the first connection line to divide the second connected domain under the overlapping region into a plurality of fifth connected domains;

[0149] connecting the second vertex and the third vertex in a second processing graph same as the target state graph to obtain a second connection line, and extending the second connection line to divide the second connected domain under the overlapping region into a plurality of sixth connected domains;

[0150] taking each of the fifth connected domains and each of the sixth connected domains with the smallest area as a region to be marked, and updating the label of the region to be marked in the target state graph according to the label of the second connected domain above the overlapping region to obtain the third state graph.

[0151] Further, the determining module 30 is further configured to:

[0152] when it is determined that the target state graph does not have an unmarked region, taking the target state graph as the partition graph;

[0153] when it is determined that the target state graph has the unmarked region, detecting whether an area of the unmarked region is greater than a preset second area;

[0154] when it is determined that the area of the unmarked region is greater than the second area, marking the unmarked region in the target state graph to obtain a fourth state graph, and taking the fourth state graph as the partition graph.

[0155] Further, the determining module 30 is further configured to:

[0156] detect whether the unmarked region is connected to the marked region when it is determined that the area of the unmarked region is not greater than the second area;

[0157] update the unmarked region to an unknown region in the target state map to obtain a fifth state map when it is determined that the unmarked region is not connected to the marked region, and use the fifth state map as the partition map;

[0158] detect whether the unmarked region is connected to a plurality of different marked regions when it is determined that the unmarked region is connected to the marked region;

[0159] use the identification of the marked region to mark the unmarked region to obtain a sixth state map when it is determined that the unmarked region is not connected to a plurality of different marked regions, and use the sixth state map as the partition map;

[0160] determine a target region from each of the marked regions when it is determined that the unmarked region is connected to a plurality of different marked regions, use the identification of the target region to mark the unmarked region to obtain a seventh state map, and use the seventh state map as the partition map, wherein the target region is a marked region whose contact area with the unmarked region accounts for more than a preset threshold proportion of the sum of the contact areas of all the marked regions with the unmarked region, or is a marked region with the most contained pixel points.

[0161] Each embodiment of the intelligent partition device can refer to each embodiment of the intelligent partition method, and details are not described herein.

[0162] An intelligent partition device is provided in the embodiments of the present application, and the device comprises Figure 3The intelligent partitioning device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen and an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be a high-speed random access memory (RAM) or a stable non-volatile memory (NVM), such as a disk drive. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0163] Those skilled in the art will understand that Figure 3 The structure shown does not constitute a limitation on the intelligent partitioning device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0164] like Figure 3 As shown, the memory 1005, which is a computer-readable storage medium, may include an operating system, a data storage module, a network communication module, a user interface module, and an intelligent partitioning program.

[0165] exist Figure 3 In the intelligent partitioning device shown, the network interface 1004 is mainly used for data communication with other devices; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the intelligent partitioning device of the present invention can be set in the intelligent partitioning device, and the intelligent partitioning device calls the intelligent partitioning program stored in the memory 1005 through the processor 1001 and executes the steps of the intelligent partitioning method provided in the embodiment of the present invention.

[0166] All embodiments of the intelligent partitioning device of the present invention can be referred to the various embodiments of the intelligent partitioning method of the present invention, and will not be repeated here.

[0167] Furthermore, embodiments of the present invention also propose a computer-readable storage medium storing an intelligent partitioning program, which, when executed by a processor, implements the steps of the intelligent partitioning method described above.

[0168] The embodiments of the computer readable computer readable storage medium of the present application can refer to the embodiments of the intelligent partitioning method of the present application, and will not be described here.

[0169] It should be noted that in this paper, the term "including", "containing" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or system including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or includes elements inherent to such process, method, article or system. Without more limitations, the element defined by the sentence "including a" does not exclude the presence of other identical elements in the process, method, article or system including the element.

[0170] The above-mentioned embodiment numbers of the present application are only for description, not representing the advantages and disadvantages of the embodiments.

[0171] From the above description of the embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be realized by software and necessary general hardware platform, of course, also can be realized by hardware, but in many cases, the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of software product, which is stored in a computer readable storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, including a plurality of instructions to make a terminal device (which can be a mobile phone, computer, server, or network device, etc.) execute the method described in each embodiment of the present application.

[0172] The above is only the preferred embodiment of the present application, and does not limit the patent scope of the present application, and any equivalent structure or equivalent process transformation made by using the content of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method of intelligent zoning, characterized by, The intelligent partitioning method comprises the following steps: acquiring a space state map of a region to be processed, wherein the region to be processed is divided into an occupied region, a free region and an unknown region in the space state map, the occupied region is a region where an obstacle exists, the free region is a region in the region to be processed where no obstacle exists, and the unknown region is a region that cannot be identified other than the occupied region and the free region; acquiring a first state map according to the space state map, performing a first processing on the first state map for a preset number of times, recording a first connected domain in the free region of the first state map after each first processing is performed, recording a target number of times of performing the first processing for closing the first connected domain, and updating the first connected domain to the occupied region in the first state map after the first processing, wherein the first processing is an expansion processing on the occupied region in the first state map or an erosion processing on the free region in the first state map, and the area of the first connected domain is less than a preset first area; after the first processing on the first state map is performed for the preset number of times, performing an expansion processing on each first connected domain in the first state map to obtain a first state map after the expansion processing, and performing labeling on each second connected domain in the first state map after the expansion processing to obtain a target state map, wherein the number of times of performing the expansion processing on the first connected domain is equal to the target number of times corresponding to the first connected domain, and the second connected domain is a free region corresponding to the first connected domain after the expansion processing; determining a partitioning map of the region to be processed according to the target state map; wherein the step of acquiring the first state map according to the space state map comprises: in a second state map same as the space state map, performing a denoising processing on the unknown region surrounded by the free region and the occupied region to obtain the first state map.

2. The intelligent partitioning method of claim 1, wherein, The step of performing the denoising processing on the unknown region surrounded by the free region and the occupied region to obtain the first state map comprises: identifying a third connected domain in the unknown region in the second state map, updating the third connected domain surrounded by the free region to the free region in the second state map to obtain the second state map after the denoising processing; identifying a fourth connected domain in the occupied region in the second state map after the denoising processing, and updating the fourth connected domain not connected with the unknown region to the free region in the second state map after the denoising processing to obtain the first state map.

3. The intelligent partitioning method of claim 1, wherein, The step of determining the partitioning map of the region to be processed according to the target state map comprises: when it is determined that there is no overlapping region in the target state map, taking the target state map as the partitioning map, wherein the overlapping region is a free region corresponding to the same pixel point in each second connected domain or a free region marked with multiple labels; when it is determined that there is the overlapping region in the target state map, performing labeling on the overlapping region in the target state map to obtain a third state map, and taking the third state map as the partitioning map.

4. The intelligent partitioning method of claim 3, wherein, The step of marking the overlapping region in the target state graph comprises: obtaining a vertex of a circumscribed quadrilateral of the overlapping region, determining a first vertex, a second vertex and a third vertex from each of the vertices, wherein the first vertex and the second vertex are vertices of the circumscribed quadrilateral connected with an unknown region, and the third vertex is a vertex of the circumscribed quadrilateral in the second connected domain under the overlapping region; connecting the first vertex and the third vertex in a first processing graph same as the target state graph to obtain a first connection line, and extending the first connection line to divide the second connected domain under the overlapping region into a plurality of fifth connected domains; connecting the second vertex and the third vertex in a second processing graph same as the target state graph to obtain a second connection line, and extending the second connection line to divide the second connected domain under the overlapping region into a plurality of sixth connected domains; taking the smallest connected domain in each of the fifth connected domains and each of the sixth connected domains as a region to be marked, and updating the identification of the region to be marked in the target state graph according to the identification of the second connected domain above the overlapping region to obtain the third state graph.

5. The intelligent zoning method of any one of claims 1 to 4, wherein, The step of determining the partition graph of the region to be processed according to the target state graph comprises: when it is determined that there is no unmarked region in the target state graph, taking the target state graph as the partition graph; when it is determined that there is the unmarked region in the target state graph, detecting whether the area of the unmarked region is greater than a preset second area; when it is determined that the area of the unmarked region is greater than the second area, marking the unmarked region in the target state graph to obtain a fourth state graph, and taking the fourth state graph as the partition graph.

6. The intelligent partitioning method of claim 5, wherein, The step of detecting whether the area of the unmarked region is greater than the second area further comprises: when it is determined that the area of the unmarked region is not greater than the second area, detecting whether the unmarked region is connected with a marked region; when it is determined that the unmarked region is not connected with the marked region, updating the unmarked region to an unknown region in the target state graph to obtain a fifth state graph, and taking the fifth state graph as the partition graph; when it is determined that the unmarked region is connected with the marked region, detecting whether the unmarked region is connected with a plurality of different marked regions; when it is determined that the unmarked region is not connected with a plurality of different marked regions, marking the unmarked region according to the identification of the marked region to obtain a sixth state graph, and taking the sixth state graph as the partition graph; When it is determined that the unmarked region connects multiple different marked regions, a target region is determined from each of the marked regions, the unmarked region is marked according to the identity of the target region to obtain a seventh state diagram, and the seventh state diagram is taken as the partition diagram, where the target region has a contact area with the unmarked region that exceeds a preset threshold proportion of a sum of contact areas of each of the marked regions with the unmarked region, or is the marked region with the most contained pixel points.

7. An intelligent zoning device, characterized by The intelligent partition device comprises: An acquisition module is configured to acquire a spatial state diagram of a to-be-processed region, wherein the to-be-processed region is divided into an occupied region, a free region and an unknown region in the spatial state diagram, the occupied region is a region in which an obstacle exists, the free region is a region in the to-be-processed region in which no obstacle exists, and the unknown region is a region that cannot be identified other than the occupied region and the free region. A processing module is configured to acquire a first state diagram according to the spatial state diagram, perform a first processing on the first state diagram for a preset number of times, record a first connected domain that is closed in the free region in the first state diagram and a target number of times of performing the first processing corresponding to the first connected domain after performing the first processing once, and update the first connected domain that has been recorded to the occupied region in the first state diagram after the first processing, wherein the first processing is an expansion processing on the occupied region in the first state diagram or an erosion processing on the free region in the first state diagram, and an area of the first connected domain is less than a preset first area. The processing module is further configured to perform an expansion processing on each of the first connected domains in the first state diagram after performing the first processing on the first state diagram for the preset number of times to obtain a first state diagram after the expansion processing, and perform marking on each of second connected domains in the first state diagram after the expansion processing to obtain a target state diagram, wherein a number of times of performing the expansion processing on the first connected domain is equal to the target number of times corresponding to the first connected domain, and the second connected domain is a free region corresponding to the first connected domain after the expansion processing. A determination module is configured to determine a partition diagram of the to-be-processed region according to the target state diagram. The processing module is further configured to perform a denoising processing on an unknown region surrounded by the free region and an occupied region in a second state diagram that is the same as the spatial state diagram to obtain the first state diagram.

8. An intelligent partitioning device, characterized by The intelligent partition device comprises a memory, a processor and an intelligent partition program stored in the memory and executable on the processor, and the intelligent partition program is configured to implement the steps of the intelligent partition method in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores an intelligent partition program, and the intelligent partition program is executed by a processor to implement the steps of the intelligent partition method in any one of claims 1 to 6.

Images