Method for generating cleaning recommendation information and electronic device

Abstract

The present application relates to the technical field of robots, and discloses a method for generating cleaning suggestion information and an electronic device. The method for generating cleaning suggestion information comprises the following steps: obtaining an environment image collected when a robot performs a cleaning operation, the environment image containing at least one obstacle region, the robot being provided with a cleaning record table, the cleaning record table including cleaning information of each obstacle, determining a target obstacle type of the obstacle region according to a preset visual semantic model, updating the cleaning information of a target obstacle corresponding to the obstacle region according to the target obstacle type, obtaining an updated cleaning record table, and generating cleaning suggestion information according to the updated cleaning record table. The embodiment can provide the user with cleaning suggestion information, so as to facilitate the user to make corresponding cleaning decisions for the target obstacle, and thus the user experience is improved.

Description

Technical Field

[0001] This invention relates to the field of robotics, and more specifically to a method and electronic device for generating cleaning suggestion information. Background Technology

[0002] With the technological advancements in cleaning robots, they are gradually entering ordinary households, liberating people from tedious housework and providing great convenience. Typically, when encountering obstacles, cleaning robots will avoid them and clean along their edges. While users can set cleaning robots to clean the floor regularly, they cannot move heavier obstacles to clean the areas they occupy. As the number of times heavier obstacles have not been cleaned increases, dust and debris tend to accumulate there. Because cleaning robots do not record the number of times areas occupied by heavier obstacles have not been cleaned, these areas are often overlooked, negatively impacting the user experience. Summary of the Invention

[0003] One objective of this invention is to provide a method and electronic device for generating cleaning advice information, aiming to solve the problem that the prior art cannot provide cleaning advice information so that users can make effective cleaning decisions.

[0004] In a first aspect, embodiments of the present invention provide a method for generating cleaning recommendation information, comprising:

[0005] The robot acquires environmental images during cleaning operations, the environmental images containing at least one obstacle area, and the robot is equipped with a cleaning record table, the cleaning record table including cleaning information for each obstacle.

[0006] Based on a preset visual semantic model, the target obstacle type in the obstacle area is determined;

[0007] The cleaning information of the target obstacle corresponding to the obstacle area is updated according to the type of the target obstacle to obtain an updated cleaning record table;

[0008] Cleaning recommendations are generated based on the updated cleaning record sheet.

[0009] Optionally, updating the cleaning information of the target obstacle corresponding to the obstacle area based on the target obstacle type to obtain the updated cleaning record table includes:

[0010] The target movement type of the target obstacle is determined based on the type of the target obstacle;

[0011] Based on the target obstacle type and the target movement type, update the cleaning information of the target obstacle corresponding to the obstacle area to obtain an updated cleaning record table.

[0012] Optionally, the cleaning information includes the current number of times the obstacle has not been cleaned, and updating the cleaning information of the target obstacle corresponding to the obstacle area based on the target obstacle type and the target movement type includes:

[0013] Based on the type of the target obstacle, traverse the cleaning record table to obtain the historical number of times the target obstacle has not been cleaned;

[0014] If the target movement type is immovable, then the current number of times the target obstacle is not cleaned is calculated based on the historical number of times it has not been cleaned and a preset number of times threshold.

[0015] If the target movement type is movable, then the current number of times the target obstacle has not been cleaned is determined based on the obstacle area and preset comparison information;

[0016] The cleaning record table is updated based on the current number of times it has not been cleaned, resulting in an updated cleaning record table.

[0017] Optionally, the preset comparison information includes a reference area corresponding to the target obstacle, and determining the current number of times the target obstacle has not been cleaned based on the obstacle area and the preset comparison information includes:

[0018] Extract the longest line segment from the obstacle region;

[0019] A baseline segment is determined based on the baseline region, wherein the baseline segment is the longest segment in the baseline region;

[0020] Calculate the distance from the midpoint of the longest line segment to the midpoint of the baseline line segment;

[0021] The current number of times the target obstacle has not been cleaned is determined based on the distance.

[0022] Optionally, determining the current number of times the target obstacle has not been cleaned based on the distance includes:

[0023] If the distance is greater than a preset distance threshold, then the preset number of times threshold is used as the current number of times the target obstacle has not been cleaned;

[0024] If the distance is less than a preset distance threshold, the current number of times the target obstacle is not cleaned is calculated based on the historical number of times it has not been cleaned and the preset number of times threshold.

[0025] Optionally, the cleaning record sheet includes the obstacle area ratio, and the method further includes:

[0026] The target obstacle is defined as the cleaning zone to which it belongs, and the area occupied by the target obstacle is determined.

[0027] The obstacle area ratio of the target obstacle is calculated based on the area of ​​the region and the total area of ​​the target cleaning zone.

[0028] Optionally, the cleaning record table includes the ratio of uncleaned area to obstacle area for each cleaning zone, and the method further includes:

[0029] Identify the areas to be cleaned within the cleaning zone;

[0030] Calculate the area ratio to be cleaned based on the area of ​​the area to be cleaned and the total area of ​​the cleaning zones;

[0031] The ratio of uncleaned areas in the cleaning zone is calculated based on the ratio of areas to be cleaned and the ratio of areas of obstacles.

[0032] Optionally, generating cleaning suggestion information based on the updated cleaning record table includes:

[0033] Based on the updated cleaning record table, obstacles with a current number of times they have not been cleaned within a preset time range that is less than a preset threshold number are selected as candidate obstacles;

[0034] If the movement type of the candidate obstacle is movable, then cleaning suggestion information for the candidate obstacle is generated.

[0035] In a second aspect, embodiments of the present invention provide a non-volatile readable storage medium storing computer-executable instructions for causing an electronic device to perform the above-described method for generating cleaning recommendation information.

[0036] In a third aspect, embodiments of the present invention provide an electronic device, comprising:

[0037] At least one processor; and,

[0038] A memory communicatively connected to the at least one processor; wherein,

[0039] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the above-described method for generating cleaning recommendation information.

[0040] In the method for generating cleaning suggestion information provided in this embodiment of the invention, firstly, this embodiment acquires environmental images collected by the robot during cleaning operations. The environmental images contain at least one obstacle area, and the robot is equipped with a cleaning record table, which includes uncleaned information for each obstacle. Secondly, this embodiment determines the target obstacle type of the obstacle area based on a preset visual semantic model. This facilitates subsequent targeted adjustment of the cleaning information of the target obstacles corresponding to the target obstacle type. Thirdly, this embodiment updates the cleaning information of the target obstacles corresponding to the obstacle area based on the target obstacle type, obtaining an updated cleaning record table. Therefore, this embodiment can update the cleaning record table in real time, so that cleaning suggestion information can be reliably generated based on the cleaning record table. Finally, this embodiment generates cleaning suggestion information based on the updated cleaning record table. Therefore, this embodiment can provide cleaning suggestion information to users, facilitating users to make corresponding cleaning decisions for target obstacles, thus improving the user experience. Attached Figure Description

[0041] One or more embodiments are illustrated by way of example with reference numerals in the accompanying drawings. These illustrations do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are denoted as similar elements. Unless otherwise stated, the figures in the drawings are not to be limited by scale.

[0042] Figure 1 A flowchart illustrating the method for generating cleaning recommendation information provided in an embodiment of the present invention;

[0043] Figure 2 A schematic diagram of the structure of the cleaning suggestion information generation device provided in the embodiments of the present invention;

[0044] Figure 3 This is a schematic diagram of the circuit structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0045] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without inventive effort are within the scope of protection of this invention.

[0046] It should be noted that, unless otherwise specified, the various features in the embodiments of this invention can be combined with each other, all of which are within the protection scope of this invention. Furthermore, although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than the module division in the device or the order in the flowchart. Moreover, the terms "first," "second," and "third" used in this invention do not limit the data or execution order, but only distinguish identical or similar items with essentially the same function and effect.

[0047] This invention provides a method for generating cleaning recommendation information. Please refer to [link / reference]. Figure 1 The method for generating cleaning recommendation information includes the following steps:

[0048] S11: Acquire environmental images collected by the robot during cleaning operations. The environmental images contain at least one obstacle area. The robot is equipped with a cleaning record sheet, which includes cleaning information for each obstacle.

[0049] In this step, the robot includes a sweeping robot, a mopping robot, a combined sweeping and mopping robot, a vacuuming robot, or a floor-washing robot, etc. The cleaning operation refers to the robot controlling the cleaning components to clean the floor. The cleaning components can be determined based on the robot's cleaning functions, such as a roller brush, a mop, or a vacuuming component. The environmental image is an image of the environment captured by the robot's camera during the cleaning operation. The obstacle area is an area on the environmental image consisting of multiple pixels corresponding to obstacles. The cleaning record table is pre-built on the ground by the robot, and it is used to represent the cleaning status of each obstacle and / or each cleaning zone. Cleaning information is used to represent the cleaning status associated with obstacles.

[0050] Please refer to Table 1. The cleaning record sheet is shown in Table 1:

[0051] Table 1

[0052]

[0053] As shown in Table 1, the cleaning record sheet can not only record the cleaning status of each cleaning zone, but also the cleaning status of each obstacle in each cleaning zone. The robot can continuously update the cleaning record sheet to provide flexible cleaning suggestions.

[0054] S12: Determine the type of target obstacle in the obstacle area based on the preset visual semantic model.

[0055] In this step, the preset visual semantic model is pre-trained and generated by the designer. This preset visual semantic model can be an artificial intelligence model, which supports corresponding machine learning algorithms. In this embodiment, images of various indoor objects are collected as training images, and each image is labeled. The labeled images are then input into a neural network for training to generate the preset visual semantic model. The loss function of the neural network can be a BCE loss function, and the activation function can be a sigmoid function, etc.

[0056] The target obstacle type is the type of obstacle that corresponds to the obstacle area. The obstacle type is used to indicate the name of the obstacle. Obstacle types include furniture, fabric, wire, stepped base, body fat scale, pet feces, household waste, bed, sofa, large cabinet, bookcase, wardrobe, TV cabinet, table, coffee table, potted plant, chair, shoe, body fat scale, sofa chair, wooden stool, stroller, etc.

[0057] S13: Update the cleaning information of the target obstacle corresponding to the obstacle area according to the type of the target obstacle to obtain the updated cleaning record table.

[0058] In this step, the target obstacle is the obstacle corresponding to the obstacle area.

[0059] S14: Generate cleaning recommendation information based on the updated cleaning record sheet.

[0060] In this step, the cleaning advice information is used to provide cleaning suggestions to users. The cleaning advice information can be presented in the form of text, images, voice, etc.

[0061] In some embodiments, the cleaning recommendation information includes the current number of times each obstacle has not been cleaned. In some embodiments, the cleaning recommendation information includes the location information and the current number of times obstacles have not been cleaned within a preset time range.

[0062] In some embodiments, the robot sends cleaning suggestion information to the terminal's APP application via a cloud server, enabling the APP application to display the cleaning suggestion information. The user then executes the corresponding cleaning strategy based on the cleaning suggestion information. For example, the cleaning suggestion information includes the location information of movable obstacles that have not been cleaned many times. The user locates the obstacle based on the location information and moves it in advance. When the robot performs cleaning operations later, it can clean the area originally occupied by the obstacle. Therefore, this embodiment can provide users with cleaning suggestion information to facilitate users in making corresponding cleaning decisions for target obstacles, thus improving the user experience.

[0063] In some embodiments, generating cleaning recommendation information based on the updated cleaning record sheet includes: generating cleaning recommendation information based on the updated cleaning record sheet according to a preset frequency.

[0064] In some embodiments, updating the cleaning information of the target obstacle corresponding to the obstacle area based on the target obstacle type to obtain an updated cleaning record table includes the following steps:

[0065] S131: Determine the target movement type of the target obstacle based on the type of the target obstacle.

[0066] S132: Update the cleaning information of the target obstacle corresponding to the obstacle area according to the target obstacle type and target movement type to obtain an updated cleaning record table.

[0067] In S131, the movement type indicates whether an obstacle can be easily moved. The movement type includes immovable and movable types. An immovable type indicates that the obstacle is not easily moved and is moved infrequently, while a movable type indicates that the obstacle can be easily moved and is moved relatively infrequently. Typically, indoor obstacles include sofas, beds, large cabinets, bookshelves, wardrobes, TV cabinets, tables, coffee tables, etc. These obstacles are of the immovable type, characterized by being difficult for users to move and being moved infrequently, such as once a year or once every six months. Other obstacles include armchairs, wooden stools, flower pots, strollers, potted plants, chairs, shoes, etc. These obstacles are of the movable type, characterized by requiring some effort to move and being moved infrequently, such as once a week, once a month, or twice a month.

[0068] Determining the target movement type based on the target obstacle type involves: Traversing the cleaning record table based on the target obstacle type to obtain the movement type corresponding to that type, and selecting the movement type corresponding to the target obstacle type as the target movement type. For example, if the target obstacle type is a sofa, and the corresponding movement type for a sofa is immovable, then the target movement type is immovable.

[0069] In S132, the cleaning information includes the current number of times the obstacle has not been cleaned. The current number of times the obstacle has not been cleaned is the current number of times it has not been cleaned. This current number of times is obtained by adding the historical number of times the obstacle has not been cleaned to a preset threshold. The preset threshold can be 1 or 2, etc., but is usually set to 1. This embodiment can integrate the target obstacle type and the target movement type to update the cleaning information of the target obstacle, thus enabling accurate and reliable updates to the cleaning information of both movable and immovable obstacles.

[0070] In some embodiments, updating the cleaning information of the target obstacle corresponding to the obstacle area based on the target obstacle type and the target movement type includes the following steps:

[0071] S1321: Traverse the cleaning record table according to the type of the target obstacle to obtain the historical number of times the target obstacle has not been cleaned.

[0072] S1322: If the target movement type is immovable, calculate the current number of times the target obstacle is not cleaned based on the historical number of times it has not been cleaned and the preset number of times threshold.

[0073] S1323: If the target movement type is movable, then determine the current number of times the target obstacle has not been cleaned based on the obstacle area and preset comparison information.

[0074] S1324: Update the cleaning record table based on the current number of times the table has not been cleaned, and obtain the updated cleaning record table.

[0075] In S1321, the historical number of times an obstacle was not cleaned is the number of times it was not cleaned during the historical cleaning process. The historical number of times an obstacle was not cleaned is obtained by traversing the cleaning record table according to the target obstacle type, including: obtaining the historical number of times the target obstacle type corresponds to the target obstacle type, and using the historical number of times the target obstacle type corresponds to the historical number of times the target obstacle was not cleaned.

[0076] In S1322, when the target movement type of the target obstacle is immovable, it means that the target obstacle will not usually be moved. Therefore, the robot directly adds the historical number of times it has not been cleaned to the preset number of times to obtain the current number of times the target obstacle has not been cleaned.

[0077] As shown in Table 1, when the obstacle type of the target obstacle is a sofa, since the sofa's movement type is immovable, the current number of times the sofa has not been cleaned is 2 + 1 = 3. It can be understood that, relative to the next cleaning operation, the current number of times the sofa has not been cleaned in this cleaning operation can be the historical number of times it has not been cleaned in the next cleaning operation.

[0078] In S1323, when the target obstacle's movement type is movable, it means the target obstacle can be moved. Therefore, the robot needs to determine the current number of times the target obstacle has not been cleaned based on the obstacle area and preset comparison information. As shown in Table 1, when the target obstacle type is flowerpot A, since flowerpot A's movement type is movable, the current number of times flowerpot A has not been cleaned is 4 + 1 = 5 times.

[0079] In some embodiments, the preset comparison information includes a reference area corresponding to the target obstacle, which is the original area of ​​the target obstacle when it is not moved. When the target obstacle's target movement type is movable, after moving and cleaning the original area occupied by the target obstacle, the target obstacle will be returned to its original position. However, it is understood that the area occupied by the target obstacle after being returned to its original position is not perfectly aligned with the area occupied by the target obstacle before it was moved; there will be a slight deviation. It is also understood that after the target obstacle is moved and cleaned, the robot can clean the original area occupied by the target obstacle during the above process. Therefore, even if the target obstacle has not been moved before, resulting in a high number of historical uncleaned instances, after this movement and cleaning, the robot can reset the historical uncleaned instances corresponding to the target obstacle to zero in the cleaning record table, without marking the target obstacle as having been uncleaned multiple times.

[0080] In the process of developing this invention, the inventors discovered that if a position detection algorithm is used to compare the position of the target obstacle before it was moved with the position of the target obstacle after it was returned to its original position to determine whether the position of the target obstacle before it was moved has shifted, the LiDAR is prone to data drift or other detection errors, which can easily lead to a deviation between the position of the target obstacle before it was moved and the position of the target obstacle after it was returned to its original position. Furthermore, there may be a slight deviation between the area occupied by the target obstacle after it is returned to its original position and the area occupied by the target obstacle before it was moved, even though the target obstacle has already been moved. Therefore, the method of using a position detection algorithm cannot reliably detect whether the target obstacle has been moved.

[0081] In some embodiments, determining the current number of times a target obstacle is not cleaned based on the obstacle area and preset comparison information includes the following steps: extracting the longest line segment from the obstacle area, determining a baseline line segment based on the baseline area, calculating the distance from the midpoint of the longest line segment to the midpoint of the baseline line segment, and determining the current number of times the target obstacle is not cleaned based on the distance. The baseline line segment is the longest line segment in the baseline area. Even if there is a slight deviation between the area occupied by the target obstacle after it is moved and the area occupied by the target obstacle before it was moved, this embodiment can reliably record the current number of times the target obstacle is not cleaned by detecting whether the target obstacle has been moved based on the distance from the midpoint of the longest line segment to the midpoint of the baseline line segment.

[0082] In some embodiments, determining the current number of times a target obstacle has not been cleaned based on distance includes: if the distance is greater than a preset distance threshold, then using the preset number of times as the current number of times the target obstacle has not been cleaned; if the distance is less than the preset distance threshold, then calculating the current number of times the target obstacle has not been cleaned based on historical numbers of times it has not been cleaned and the preset number of times. The preset distance threshold is customized by the designer based on engineering experience, such as a preset distance threshold of 2 cm or 3 cm.

[0083] If the distance is greater than the preset distance threshold, it means that the target obstacle has been moved. Therefore, in this embodiment, the natural number 1 is used as the preset number threshold, and the natural number 1 is used as the current number of times the target obstacle is not cleaned. That is, since the robot cannot clean the area currently occupied by the target obstacle, the current number of times the target obstacle is not cleaned is 1. In the next cleaning operation, the current number of times not cleaned "1" is the historical number of times not cleaned.

[0084] If the distance is less than a preset distance threshold, it means that the target obstacle has not been moved. Therefore, in this embodiment, the historical number of times the obstacle has not been cleaned is added to the preset number of times it has not been cleaned to obtain the current number of times the target obstacle has not been cleaned.

[0085] This embodiment leverages the robot's ability to encounter and clean obstacles along their edges. In some embodiments, the method for generating cleaning suggestion information further includes: acquiring the contour information of the target obstacle detected by the robot during edge cleaning; updating the obstacle region extracted from the environmental image based on the contour information; and obtaining an updated obstacle region. Therefore, extracting the longest line segment from the obstacle region includes the following steps: extracting the longest line segment based on the updated obstacle region. By detecting the contour information of the target obstacle during edge cleaning and updating the obstacle region based on the contour information, a more reliable obstacle region with reliable edges can be obtained. This facilitates the extraction of the longest line segment with more reliable position, thereby enabling more reliable detection of whether the target obstacle has been moved and reliable recording of the current number of times the target obstacle has not been cleaned.

[0086] In some embodiments, if the distance is greater than a preset distance threshold, the obstacle area is used as a new reference area, and preset comparison information is generated based on the new reference area.

[0087] In S1324, the cleaning record table is updated based on the current number of times it has not been cleaned. The updated cleaning record table includes replacing the historical number of times the target obstacle has not been cleaned with the current number of times it has not been cleaned.

[0088] In some embodiments, the cleaning record table includes an obstacle area ratio, which is the ratio of the area occupied by the obstacle to the total area of ​​the cleaning zone containing the obstacle. The method for generating cleaning suggestion information further includes: determining the cleaning zone to which the target obstacle belongs as the target cleaning zone and the area occupied by the target obstacle, and calculating the obstacle area ratio of the target obstacle based on the area occupied by the obstacle and the total area of ​​the target cleaning zone. The obstacle area ratio is used to represent a fixed percentage of the target cleaning zone that is not cleaned each time. As shown in Table 1, when the first cleaning zone is the target cleaning zone and the obstacle type of the target obstacle is a sofa, the obstacle area ratio is 25%.

[0089] This embodiment calculates the area ratio of obstacles, which can then be packaged into cleaning suggestion information and presented to the user. The user can then know the area ratio of each obstacle in its respective cleaning zone, making it easier for the user to intuitively understand the status of fixed uncleaned areas in that cleaning zone.

[0090] In some embodiments, the cleaning record table includes the ratio of uncleaned area to obstacle area and the method for generating cleaning recommendation information for each cleaning zone. The method further includes: determining the areas to be cleaned within the cleaning zone; calculating the ratio of areas to be cleaned based on the area of ​​the areas to be cleaned and the total area of ​​the cleaning zone; and calculating the ratio of uncleaned area to the cleaning zone based on the ratio of areas to be cleaned and the ratio of obstacle area. The ratio of uncleaned area is used to represent the overall situation of uncleaned areas within the cleaning zone. As shown in Table 1, when the first cleaning zone is the target cleaning zone, the ratio of uncleaned area is 35%.

[0091] This embodiment calculates the ratio of uncleaned areas in a clean zone, and then packages the uncleaned area ratio into cleaning suggestion information, which is then presented to the user so that the user can intuitively understand the hygiene status of the clean zone.

[0092] In some embodiments, generating cleaning suggestion information based on an updated cleaning record table includes the following steps: filtering obstacles whose current number of times they have not been cleaned within a preset time range is less than a preset threshold as candidate obstacles based on the updated cleaning record table; if the movement type of a candidate obstacle is movable, generating cleaning suggestion information for the candidate obstacle; if the movement type of a candidate obstacle is immovable, determining the movement type of another candidate obstacle.

[0093] The preset time range is customized by the designer based on engineering experience, such as the most recent 1 month, 2 months, or 3 months. The preset number of times threshold is also customized by the designer based on engineering experience, such as 5 times or 10 times.

[0094] In this embodiment, the updated cleaning record table is traversed, and obstacles with fewer than 5 current uncleaned times in the past month are selected as candidate obstacles. As shown in Table 1, since the body fat scale is a movable type and its current uncleaned times (historical uncleaned times) are less than 5, this embodiment generates cleaning suggestion information for the body fat scale so that the user can move the scale during the next cleaning session, allowing the robot to clean the original area occupied by the scale.

[0095] It should be noted that in the above embodiments, there is no necessarily a certain order between the steps. Those skilled in the art can understand from the description of the embodiments of the present invention that the above steps may have different execution orders in different embodiments, that is, they may be executed in parallel or in turn, etc.

[0096] As another aspect of the embodiments of the present invention, an embodiment of the present invention provides a cleaning recommendation information generation apparatus. The cleaning recommendation information generation apparatus can be a software module, which includes several instructions stored in a memory. A processor can access the memory, invoke the instructions for execution, and complete the cleaning recommendation information generation method described in the above embodiments.

[0097] In some embodiments, the cleaning recommendation information generation device can also be constructed from hardware devices. For example, the cleaning recommendation information generation device can be constructed from one or more chips, which can work together to complete the cleaning recommendation information generation method described in the above embodiments. As another example, the cleaning recommendation information generation device can also be constructed from various logic devices, such as general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), microcontrollers, ARM (ArcRISC Machinie) or other programmable logic devices, discrete gate or transistor logic, discrete hardware components, or any combination of these components.

[0098] Please see Figure 2 The cleaning suggestion information generation device 200 includes an image acquisition module 21, an obstacle determination module 22, an update module 23, and an information generation module 24.

[0099] Image acquisition module 21 is used to acquire environmental images collected during the robot's cleaning operation. The environmental images contain at least one obstacle area. The robot is equipped with a cleaning record table, which includes cleaning information for each obstacle. Obstacle determination module 22 is used to determine the target obstacle type of the obstacle area based on a preset visual semantic model. Update module 23 is used to update the cleaning information of the target obstacle corresponding to the obstacle area based on the target obstacle type, resulting in an updated cleaning record table. Information generation module 24 is used to generate cleaning suggestion information based on the updated cleaning record table.

[0100] This embodiment generates cleaning suggestion information based on the updated cleaning record sheet. Therefore, this embodiment can provide users with cleaning suggestion information to facilitate users to make corresponding cleaning decisions for target obstacles, which helps to improve the user experience.

[0101] In some embodiments, the updating module 23 is specifically used to: determine the target movement type of the target obstacle according to the target obstacle type, update the cleaning information of the target obstacle corresponding to the obstacle area according to the target obstacle type and the target movement type, and obtain an updated cleaning record table.

[0102] In some embodiments, the cleaning information includes the current number of times the object has not been cleaned. The update module 23 is further configured to: traverse the cleaning record table according to the target obstacle type to obtain the historical number of times the target obstacle has not been cleaned; if the target movement type is an immovable type, calculate the current number of times the target obstacle has not been cleaned according to the historical number of times the object has not been cleaned and a preset number of times threshold; if the target movement type is a movable type, determine the current number of times the target obstacle has not been cleaned according to the obstacle area and preset comparison information; and update the cleaning record table according to the current number of times the object has not been cleaned to obtain an updated cleaning record table.

[0103] In some embodiments, the preset comparison information includes a reference area corresponding to the target obstacle, and the update module 23 is further specifically used to: extract the longest line segment according to the obstacle area, determine a reference line segment according to the reference area, wherein the reference line segment is the line segment with the longest length in the reference area, calculate the distance from the midpoint of the longest line segment to the midpoint of the reference line segment, and determine the current number of times the target obstacle has not been cleaned according to the distance.

[0104] In some embodiments, the updating module 23 is further configured to: if the distance is greater than a preset distance threshold, use the preset number threshold as the current number of times the target obstacle is not cleaned; if the distance is less than the preset distance threshold, calculate the current number of times the target obstacle is not cleaned based on the historical number of times it is not cleaned and the preset number threshold.

[0105] In some embodiments, the cleaning record sheet includes an obstacle area ratio; please refer to [link / reference needed]. Figure 2 The cleaning suggestion information generation device 200 further includes a first calculation module 25, which is used to determine the cleaning zone to which the target obstacle belongs as the target cleaning zone and the area occupied by the target obstacle, and calculate the obstacle area ratio of the target obstacle based on the area of ​​the area and the total area of ​​the target cleaning zone.

[0106] In some embodiments, the cleaning record sheet includes the ratio of uncleaned area to obstacle area for each cleaned zone. Please refer to [link / reference]. Figure 2 The cleaning suggestion information generation device 200 further includes a second calculation module 26, which is used to determine the area to be cleaned in the cleaning zone, calculate the area ratio to be cleaned based on the area of ​​the area to be cleaned and the total area of ​​the cleaning zone, and calculate the uncleaned area ratio of the cleaning zone based on the area ratio to be cleaned and the obstacle area ratio.

[0107] In some embodiments, the information generation module 24 is specifically used to: filter out obstacles whose current number of times they have not been cleaned is less than a preset number threshold within a preset time range as candidate obstacles according to the updated cleaning record table; and if the movement type of the candidate obstacle is movable, generate cleaning suggestion information for the candidate obstacle.

[0108] It should be noted that the above-mentioned cleaning suggestion information generation device can execute the cleaning suggestion information generation method provided in the embodiments of the present invention, and has the corresponding functional modules and beneficial effects of the method. Technical details not described in detail in the embodiments of the cleaning suggestion information generation device can be found in the cleaning suggestion information generation method provided in the embodiments of the present invention.

[0109] Please see Figure 3 , Figure 3 This is a circuit structure diagram of an electronic device provided in an embodiment of the present invention, wherein the electronic device can be a robot or a server. Figure 3 As shown, the electronic device 300 includes one or more processors 31 and a memory 32. Wherein, Figure 3 Take a processor 31 as an example.

[0110] Processor 31 and memory 32 can be connected via a bus or other means. Figure 3 Taking the example of a connection between China and Israel via a bus.

[0111] The memory 32, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as the program instructions / modules corresponding to the cleaning recommendation information generation method in the embodiments of the present invention. The processor 31 executes various functional applications and data processing of the cleaning recommendation information generation device by running the non-volatile software programs, instructions, and modules stored in the memory 32, thereby realizing the functions of the cleaning recommendation information generation method provided in the above method embodiments and the various modules or units in the above device embodiments.

[0112] Memory 32 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, memory 32 may optionally include memory remotely located relative to processor 31, which can be connected to processor 31 via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0113] The program instructions / modules are stored in the memory 32 and, when executed by one or more processors 31, execute the method for generating cleaning recommendation information in any of the above method embodiments.

[0114] This invention also provides a non-volatile computer storage medium storing computer-executable instructions that are executed by one or more processors, for example... Figure 3 One of the processors 31 can enable the one or more processors to execute the method for generating cleaning recommendation information in any of the above method embodiments.

[0115] This invention also provides a computer program product, the computer program product including a computer program stored on a non-volatile computer-readable storage medium, the computer program including program instructions, which, when executed by an electronic device, cause the electronic device to perform any of the cleaning recommendation information generation methods described above.

[0116] The device or equipment embodiments described above are merely illustrative. The unit modules described as separate components may or may not be physically separate. The components shown as module units may or may not be physical units; that is, they may be located in one place or distributed across multiple network module units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0117] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented using software plus a general-purpose hardware platform, or of course, using hardware. Based on this understanding, the above technical solutions, in essence or the parts that contribute to the related technology, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0118] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; under the concept of the present invention, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of the present invention as described above, which are not provided in detail for the sake of brevity; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for generating cleaning recommendation information, characterized in that, include: The robot acquires environmental images collected during cleaning operations. The environmental images contain at least one obstacle area. The robot is equipped with a cleaning record table, which includes cleaning information for each obstacle, including the number of times the obstacle has not been cleaned. Based on a preset visual semantic model, the target obstacle type in the obstacle area is determined; The process involves updating the cleaning information of the target obstacle corresponding to the obstacle area based on the target obstacle type to obtain an updated cleaning record table. This includes: determining the target movement type of the target obstacle based on the target obstacle type; traversing the cleaning record table according to the target obstacle type to obtain the historical number of times the target obstacle has not been cleaned; if the target movement type is a non-movable type, calculating the current number of times the target obstacle has not been cleaned based on the historical number of times it has not been cleaned and a preset number of times it has not been cleaned; if the target movement type is a movable type, determining the current number of times the target obstacle has not been cleaned based on the obstacle area and preset comparison information; and updating the cleaning record table based on the current number of times it has not been cleaned to obtain an updated cleaning record table. Cleaning recommendations are generated based on the updated cleaning record sheet.

2. The method according to claim 1, characterized in that, The preset comparison information includes a reference area corresponding to the target obstacle, and determining the current number of times the target obstacle has not been cleaned based on the obstacle area and the preset comparison information includes: Extract the longest line segment from the obstacle region; A baseline segment is determined based on the baseline region, wherein the baseline segment is the longest segment in the baseline region; Calculate the distance from the midpoint of the longest line segment to the midpoint of the baseline line segment; The current number of times the target obstacle has not been cleaned is determined based on the distance.

3. The method according to claim 2, characterized in that, Determining the current number of times the target obstacle has not been cleaned based on the distance includes: If the distance is greater than a preset distance threshold, then the preset number of times threshold is used as the current number of times the target obstacle has not been cleaned; If the distance is less than a preset distance threshold, the current number of times the target obstacle is not cleaned is calculated based on the historical number of times it has not been cleaned and the preset number of times threshold.

4. The method according to claim 1, characterized in that, The cleaning record sheet includes the area ratio of the obstacles, and the method further includes: The target obstacle is defined as the cleaning zone to which it belongs, and the area occupied by the target obstacle is determined. The obstacle area ratio of the target obstacle is calculated based on the area of ​​the region and the total area of ​​the target cleaning zone.

5. The method according to claim 1, characterized in that, The cleaning record sheet includes the ratio of uncleaned area to obstacle area for each cleaning zone, and the method further includes: Identify the areas to be cleaned within the cleaning zone; Calculate the area ratio to be cleaned based on the area of ​​the area to be cleaned and the total area of ​​the cleaning zones; The ratio of uncleaned areas in the cleaning zone is calculated based on the ratio of areas to be cleaned and the ratio of areas of obstacles.

6. The method according to any one of claims 1 to 5, characterized in that, The step of generating cleaning suggestion information based on the updated cleaning record table includes: Based on the updated cleaning record table, obstacles with a current number of times they have not been cleaned within a preset time range that is less than a preset threshold number are selected as candidate obstacles; If the movement type of the candidate obstacle is movable, then cleaning suggestion information for the candidate obstacle is generated.

7. A non-volatile readable storage medium, characterized in that, The device stores computer-executable instructions for causing an electronic device to perform a method for generating cleaning recommendation information as described in any one of claims 1 to 6.

8. An electronic device, characterized in that, include: At least one processor; as well as, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method for generating cleaning recommendation information as described in any one of claims 1 to 6.

Images