Control method of intelligent operation equipment and intelligent operation equipment

Abstract

The invention relates to a control method of intelligent operation equipment and the intelligent operation equipment. The method comprises the steps of monitoring event data in an operation process in the operation process of the intelligent operation equipment; when the event data is monitored, according to a processing efficiency value corresponding to the event data, a traffic efficiency value of a target area in a traffic efficiency map of the intelligent operation equipment is updated, and the target area comprises an area where the event data is monitored; the processing efficiency value is used for representing the efficiency of the intelligent operation equipment for processing events corresponding to the event data; the passing efficiency value is used for representing the efficiency of the intelligent operation equipment passing through the target area; and updating the forbidden area in the operation map of the intelligent operation equipment based on the updated passing efficiency value. According to the method, real-time updating is carried out according to the processing efficiency value of the event data, reliable real-time data support is provided, and the passing forbidden zone in the operation map can be updated more accurately.

Description

Technical Field

[0001] This application relates to the field of intelligent control technology, and particularly to a control method and an intelligent operation device for an intelligent operation device. Background Art

[0002] During the operation of an intelligent operation device, it is usually necessary to guide the device to perform corresponding actions based on a corresponding operation map. For example, taking a sweeping robot as an example, during the process of the sweeping robot cleaning the ground, it is necessary to provide map data support for the cleaning route planning of the sweeping robot based on the operation map of the area to be cleaned pre-constructed. The cleaning route formed based on the operation map can guide the sweeping robot to avoid obstacles such as furniture, sundries, steps or walls in the area to be cleaned during the cleaning process.

[0003] In the traditional technical solution, in order to prevent the sweeping robot from moving to an area with low cleaning efficiency, such as an area with furniture, sundries, steps or walls, resulting in the obstruction or interruption of the cleaning operation, it is usually necessary for the user to actively observe the cleaning process of the sweeping robot and manually set the area with low cleaning efficiency as described above as a restricted area to improve the operation efficiency of the sweeping robot.

[0004] However, the method of manually setting restricted areas in the traditional technical solution has a lag in the division marks of restricted areas due to subjective judgment errors or mistakes, or unexpected events that may occur at any time during the cleaning process of the sweeping robot, such as the accidental fall of furniture or the intrusion of pets into the operation map. Therefore, the method of determining restricted areas in the operation map in the traditional technical solution has relatively low accuracy. Summary of the Invention

[0005] Based on this, it is necessary to provide a control method, device, intelligent operation device, computer-readable storage medium and computer program product for an intelligent operation device with higher accuracy in view of the above technical problems.

[0006] In a first aspect, this application provides a control method for an intelligent operation device. The method includes:

[0007] During the operation of the intelligent operation device, monitor the event data during the operation;

[0008] When the event data is monitored, update the passing efficiency value of the target area in the passing efficiency map of the intelligent operation device according to the processing efficiency value corresponding to the event data, where the target area includes the area where the event data is monitored; the processing efficiency value is used to represent the efficiency of the intelligent operation device in processing the event corresponding to the event data; the passing efficiency value is used to represent the efficiency of the intelligent operation device in passing through the target area;

[0009] Update the no-go area in the operation map of the intelligent operation device based on the updated traffic efficiency value.

[0010] In one embodiment, the event data during the monitoring operation includes:

[0011] Obtain the sensor data of the sensors of the intelligent operation device;

[0012] Determine the monitored event data according to the sensor data and the category of the sensor.

[0013] In one embodiment, before updating the traffic efficiency value of the target area in the traffic efficiency map of the intelligent operation device according to the processing efficiency value corresponding to the event data, the method further includes:

[0014] Obtain the event location information and the influence range radius corresponding to the event data;

[0015] Determine the central coordinates of the target area in the traffic efficiency map based on the event location information;

[0016] Determine the target area in the traffic efficiency map according to the central coordinates and the influence range radius.

[0017] In one embodiment, the traffic efficiency map includes a plurality of unit grids;

[0018] The determining the target area in the traffic efficiency map according to the central coordinates and the influence range radius includes:

[0019] Based on the central coordinates, screen and determine the central grid from the plurality of unit grids;

[0020] Obtain the target grid by screening from the plurality of unit grids according to the event influence range formed by the central grid and the influence range radius;

[0021] Determine the target area in the traffic efficiency map based on the target grid.

[0022] In one embodiment, the updating the no-go area in the operation map of the intelligent operation device based on the updated traffic efficiency value includes:

[0023] When there is a target traffic efficiency value in the updated traffic efficiency value, obtain the no-go area expansion radius corresponding to the operation map, and the target traffic efficiency value is not less than the traffic efficiency threshold corresponding to the intelligent operation device;

[0024] Update the no-go area in the operation map of the intelligent operation device based on the area corresponding to the target passing efficiency value and the no-go area expansion radius.

[0025] In one embodiment, before updating the no-go area in the operation map of the intelligent operation device based on the area corresponding to the target passing efficiency value and the no-go area expansion radius, the method further includes:

[0026] Determine the operation map corresponding to the intelligent operation device according to the operation task information of the intelligent operation device;

[0027] Mark the corresponding no-go area in the operation map according to the preset no-go area information in the operation task information.

[0028] In one embodiment, the updating the no-go area in the operation map of the intelligent operation device based on the area corresponding to the target passing efficiency value and the no-go area expansion radius includes:

[0029] Generate a no-go area image based on the area corresponding to the target passing efficiency value and the no-go area expansion radius;

[0030] Perform image dilation processing or image erosion processing on the no-go area image according to the target coverage rate corresponding to the operation map;

[0031] Update the no-go area in the operation map of the intelligent operation device based on the no-go area image after image dilation processing or image erosion processing

[0032] In one embodiment, the performing image dilation processing or image erosion processing on the no-go area image according to the coverage rate corresponding to the operation map includes:

[0033] Obtain an image template corresponding to the preset map coverage area;

[0034] If the target coverage rate corresponding to the operation map is greater than the preset coverage rate corresponding to the image template, perform image dilation processing on the no-go area image;

[0035] If the target coverage rate corresponding to the operation map is less than or equal to the preset coverage rate corresponding to the image template, perform image erosion processing on the no-go area image.

[0036] In one embodiment, the control method of the intelligent operation device further includes:

[0037] After the operation process of the intelligent operation device ends, obtain the operation data of the operation process;

[0038] Determine the efficiency update value of each area in the passing efficiency map based on the operation data;

[0039] Update the traffic efficiency values of each area in the line efficiency map by the efficiency update values of each area.

[0040] In a second aspect, the present application provides an intelligent operation device, including a fuselage, a driving component, a cleaning component, a detection sensor, a memory, and a processor. The driving component, the cleaning component, and the detection sensor are all installed on the fuselage. The driving component is used to drive the fuselage to move on the working surface. The cleaning component is used to clean the working surface. The memory stores a computer program, and when the processor executes the computer program, the steps of the method described in any one of the first aspects are implemented.

[0041] The above-mentioned control method, device, and intelligent operation device of the intelligent operation device can, during the operation process of the intelligent operation device, monitor various event data in real time during the operation process, and based on the monitored event data, finally update the restricted areas in the operation map. Different from the subjective setting method, based on the real-time acquisition of event data during the traffic process, it can provide reliable data support for the update process of the restricted areas, overcoming the lag defect of the manual marking of restricted areas. And, during the process of the restricted areas based on the event data, the traffic efficiency values of the target areas in the traffic efficiency map will be updated according to the processing efficiency values corresponding to the event data, and the areas where the event data is monitored are also covered in the target areas. Finally, based on the updated traffic efficiency values, the restricted areas in the operation map are updated. Compared with subjective judgment and selection, the method of updating the restricted areas through the traffic efficiency values can identify and determine the restricted areas more objectively and accurately. Further, real-time updating according to the processing efficiency values of the event data provides reliable real-time data support and can update the traffic restricted areas in the operation map more accurately. Description of the Drawings

[0042] Figure 1 It is an application environment diagram of the control method of the intelligent operation device in an embodiment;

[0043] Figure 2 It is a schematic flow chart of the control method of the intelligent operation device in an embodiment;

[0044] Figure 3 It is a schematic flow chart of the sub-step of monitoring event data in an embodiment;

[0045] Figure 4 It is a schematic diagram of the event impact area map in an embodiment;

[0046] Figure 5 It is a schematic diagram of the initial traffic efficiency map in an embodiment;

[0047] Figure 6 It is a schematic diagram of the updated traffic efficiency map in an embodiment;

[0048] Figure 7 It is a schematic flowchart of the control method of the intelligent operation device in another embodiment;

[0049] Figure 8 It is a structural block diagram of the control device of the intelligent operation device in an embodiment;

[0050] Figure 9 It is an internal structure diagram of the intelligent operation device in an embodiment. Specific Embodiments

[0051] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application 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 only used to explain the present application and are not used to limit the present application.

[0052] In the traditional technical solution, a manual marking method is usually adopted to set corresponding traffic restricted areas in the operation map, so that the intelligent operation device can avoid the traffic restricted areas and successfully complete the operation task during the operation based on the operation map. However, the manual setting method adopted by the traditional technical solution may have subjective judgment deviations and misjudgments, and the manual setting does not have real-time performance and cannot cope with the situations that occur in real time in the operation map, thus resulting in a low accuracy of the traffic restricted areas delimited in the operation map.

[0053] To overcome the above defects existing in the traditional technical solution, the control method of the intelligent operation device provided by the embodiments of the present application can be applied to an application environment as Figure 1 shown. Taking a sweeping robot performing a cleaning task as an example, Figure 1In the application environment shown, the floor cleaning robot 102 communicates with the server 104 via a network. Among them, the server 104 is built-in with a data storage system, which can store data related to the floor cleaning tasks performed by the floor cleaning robot, such as the operation map data of the floor cleaning robot and the records of the cleaning tasks that the floor cleaning robot has completed. This data storage system can be integrated on the server 104, or implemented in the form of the cloud and a distributed storage architecture; and the server 104 can be implemented with an independent server or a server cluster composed of multiple servers. In this application environment, the floor cleaning robot 102 starts to execute the cleaning task in response to the cleaning task instruction and cleans the floor; among them, the cleaning task instruction can be a control instruction issued by the server 104 or other mobile terminals, which is used to start the floor cleaning robot 102 and execute the cleaning task based on the operation map corresponding to the cleaning task instruction. During the process of the floor cleaning robot 102 executing the cleaning task, it can monitor the event data in real time during the cleaning operation; for example, various sensors built into the floor cleaning robot 102 can be used to collect the real-time data during the cleaning process; for another example, the collected real-time data can refer to the situation that the floor cleaning robot 102 is trapped due to debris blockage when it travels to a certain specific area, and then the sensors are called to collect the trapped data content. During the process of the floor cleaning robot 102 executing the cleaning task, if similar trapped events occur during the cleaning operation are collected through the sensors, the real-time data related to the event will be uploaded to the server 104, and further the server 104 will perform subsequent processing operations to update the no-go areas in the operation map, so as to guide the floor cleaning robot 102 to avoid the target area corresponding to the event data. Specifically, the server 104 receives the real-time data from the floor cleaning robot 102 and based on this real-time data to monitor the event data in real time during the cleaning operation. After the server 104 monitors the event data of a similar trapped event; it is necessary to further obtain the processing efficiency value corresponding to the event data. And before the server 104 forms the operation map of the floor cleaning robot 102, it can also determine the traffic efficiency values of each area in the operation map based on the traffic efficiency map, that is, this traffic efficiency map can record the traffic efficiency values corresponding to each area. Then, the server 104 will form an initial traffic no-go area in the operation map based on the traffic efficiency values in each area. It should be noted that both the processing efficiency value and the traffic efficiency value in the embodiment can be represented in the form of discrete processing and in the form of identification symbols to represent the processing efficiency values of each area. Before determining the processing efficiency value corresponding to the event data, the server 104 will also determine the target area corresponding to the event data in the traffic efficiency map based on the area information of the monitored event data. After determining the processing efficiency value corresponding to the event data, the server 104 will update the traffic efficiency value of the target area in the traffic efficiency map based on the processing efficiency value corresponding to the event data.After updating the traffic efficiency value of the target area, the server 104 will determine whether the events occurring in the target area will obstruct the operation process of the sweeping robot 102 based on the updated traffic efficiency value. In the case where it is determined that the target area will obstruct the operation process, the server defines the target area as a new no-go area and marks it correspondingly in the operation map of the cleaning task to achieve real-time update of the no-go area in the operation map.

[0054] To elaborate more specifically on the implementation process of the method provided in this application, as Figure 2 shown, in one embodiment, a control method for an intelligent operation device is provided. Taking the method applied to the Figure 1 server 104 in it as an example for illustration, it includes the following steps:

[0055] Step 202, during the operation process of the intelligent operation device, monitor the event data during the operation process.

[0056] In the embodiment, the intelligent operation device refers to an operation device whose operation process requires the guidance of a corresponding operation map to complete a specified operation task, such as a sweeping robot or a handling robot, etc. The operation process in the embodiment refers to the process in which the intelligent operation device executes the corresponding operation task. For example, the process in which the sweeping robot executes the cleaning task for cleaning. The event data in the embodiment refers to the data content collected by the intelligent operation device when facing various situations during the operation process. Further, the events in the embodiment specifically refer to unexpected situations that may affect the operation efficiency of the intelligent operation device, and can also be recorded as low-efficiency events. For example, collision events, cliff events, fall events, slip events, trapped events, device overcurrent events, and device detachment events, etc.

[0057] For another example, taking the specific scenario where a floor cleaning robot performs a cleaning task on the floor of a house as an example, after receiving a cleaning task instruction, the floor cleaning robot will drive out from the storage bin of the cleaning base station in response to this instruction and start performing the cleaning operation. It should be noted that the cleaning task instruction in the embodiment can be a task instruction sent by a terminal or a server to the floor cleaning robot; for example, a user can trigger a cleaning task instruction through an operation of touching a control component on the interactive control interface of the terminal, and send this cleaning task instruction to the floor cleaning robot through the communication method of narrowband Internet of Things. In order to be able to monitor in real time various unexpected situations that the floor cleaning robot may face during the execution of the cleaning task, the server in the embodiment can collect the self-state data and surrounding environment information of the floor cleaning robot during the cleaning task by calling various sensor components built in the floor cleaning robot. More specifically, the self-state data in the embodiment includes but is not limited to the traveling speed, acceleration, cleaning time of the robot, and various state parameters of internal components; the surrounding environment information includes but is not limited to the distances between the floor cleaning robot and various obstacles, walls, and steps. The two data information are combined to form event data and synchronously uploaded to the server to realize the real-time monitoring of the event data during the cleaning task, and provide necessary and reliable data support for the subsequent update process of the restricted area.

[0058] Step 204, when the event data is detected, update the passing efficiency value of the target area in the passing efficiency map of the intelligent operation device according to the processing efficiency value corresponding to the event data, where the target area includes the area where the event data is detected, and the processing efficiency value is used to represent the efficiency of the intelligent operation device in processing the event corresponding to the event data; the passing efficiency value is used to represent the efficiency of the intelligent operation device in passing through the target area.

[0059] In the embodiment, the processing efficiency value refers to the efficiency of the intelligent operation device in coping with and processing the corresponding event; for example, taking the event data of detecting that the floor cleaning robot is trapped as an example, the processing efficiency value can refer to the processing efficiency of the floor cleaning robot detecting being trapped, making adjustments and successfully getting out of trouble. Exemplarily, taking the floor cleaning robot performing a cleaning task as an example, during the cleaning process, the processing efficiency value can be determined by the ratio between the time for the floor cleaning robot to process the event and the total time from the floor cleaning robot entering the target area to leaving the target area (completing the cleaning of the target area); for example, in the embodiment, the time for the floor cleaning robot to process the trapped event and return to the normal cleaning operation state is denoted as , and the total time from the floor cleaning robot entering the target area to leaving the target area (completing the cleaning of the target area) is denoted as , and then the efficiency of the floor cleaning robot in processing the trapped event is / . The passage efficiency value in the embodiment can be determined as the ratio between the area of the cleaning target area completed by the floor sweeping robot and the total time from the floor sweeping robot entering the target area to leaving the target area (completing the cleaning of the target area); for example, the passage efficiency of a certain target area is , ; where is the area of the target area.

[0060] . Further, after the intelligent operation device in the embodiment completes the operation task, a corresponding task record will be formed. The server can store the task record and statistically analyze the processing efficiency value corresponding to the event data based on the historical event data formed by multiple historical task records to form a corresponding relationship between the event data and the processing efficiency value, so that when a specific event data is monitored, the processing efficiency value corresponding to the event data can be directly retrieved based on the foregoing corresponding relationship. In addition, new unexpected events may also be faced during the operation process. For the event data monitored for the first time, the server can use a deep learning model to learn the event data monitored for the first time and predict the processing efficiency value corresponding to the event data; among them, the deep learning model can be trained based on the historical event data and the processing efficiency value corresponding to the historical event data.

[0061] . Further, the processing efficiency value in the embodiment can be described in a hierarchical manner by means of discretization, and specific identification characters are used to generally describe the high or low of the processing efficiency value. For example, in the embodiment, the processing efficiency value of the floor sweeping robot for processing various events is standardized and binned, and then the numbers 1, 2, and 3 are used to describe high processing efficiency, general processing efficiency, and low processing efficiency respectively. The passage efficiency value in the embodiment refers to the efficiency value when the intelligent operation device normally passes through a certain specific area, and this efficiency value is calculated based on the area of the specific area and the time consumed for completing the corresponding operation task; similarly, the passage efficiency value can also be characterized by means of discretization and identification characters. The passage efficiency map in the embodiment is used to describe the passage efficiency of the intelligent operation device when passing through each area; in addition, the passage efficiency map can divide the map area in the form of blocks or grids and mark the corresponding passage efficiency value for each block or grid. The passage efficiency map in the embodiment includes but is not limited to forms such as two-dimensional / three-dimensional grid maps, two-dimensional / three-dimensional cost maps, and two-dimensional / three-dimensional point cloud maps. The target area in the embodiment refers to the area range formed by the area where the event data is monitored and its surrounding areas. It should be noted that the target area in the embodiment can be adjusted according to the requirements of different operation tasks.

[0062] For example, taking the operation process of a sweeping robot as an example, after the sweeping robot receives the cleaning task instruction and before starting to perform the cleaning task, it is necessary to obtain the initial operation map from the server so that the sweeping robot can perform the cleaning task based on the initial operation map. In the process of the server forming the initial operation map, it is first necessary to determine the area to be cleaned for performing the cleaning task, and obtain the positioning map corresponding to the area to be cleaned, which can clearly describe the boundary information of the area to be cleaned. Then, the server will retrieve the historical cleaning task data associated with the area information based on the area information of the area to be cleaned; specifically, the server can search and retrieve the historical cleaning task data of the living room based on the name of the area to be cleaned, such as the living room. After obtaining the historical cleaning task data, based on the area area corresponding to each area in the positioning map and the historical cleaning time, the cleaning efficiency value of the sweeping robot in each area is calculated, and the cleaning efficiency value is discretized and mapped to the corresponding efficiency label, with the label value 1 representing the highest cleaning efficiency, the label value 2 second, and the label value 3 representing the lowest cleaning efficiency. Each area in the positioning map is marked with an efficiency label corresponding to the cleaning efficiency value to form a traffic efficiency map. After obtaining the traffic efficiency map, the server will select the area with a label value of 3 in the traffic efficiency map as the initial restricted area, and mark the restricted area in the positioning map accordingly. The positioning map after the restricted area marking is completed is the initial operation map. At this point, the server has constructed the initial operation map for the cleaning task. The restricted area is clearly marked in the initial operation map so that the sweeping robot can avoid the restricted area in the map based on the guidance of the initial operation map, ensuring that the sweeping robot can complete the cleaning task smoothly and efficiently.

[0063] During the execution of the cleaning task in the embodiment, the server will monitor the event data during the cleaning process of the floor cleaning robot in real time. After the server detects an unexpected event during the cleaning process of the floor cleaning robot and obtains the event data of the unexpected event, it will adjust or update the no-go area in the operation map based on the event data. Exemplarily, during the cleaning process, a book accidentally falls from a bookshelf to the ground in the front area where the floor cleaning robot is moving, which hinders the cleaning task performed by the floor cleaning robot; the server monitors the ranging data of the distance sensor of the floor cleaning robot through implementation, and determines that there is an obstacle in front of the floor cleaning robot based on the ranging data (that is, determines that a traffic obstruction event occurs); triggers the response processing flow for the traffic obstruction event. Specifically, in this response processing flow, the server responds to the event trigger signal of the traffic obstruction event, and based on the time name or number of the traffic obstruction event, performs event matching search in the record of historical cleaning task data, and retrieves the processing efficiency values of multiple traffic obstruction historical events from the historical cleaning task data. It should be noted that in the embodiment, the processing method of the processing efficiency value should be consistent with that of the traffic efficiency value. Therefore, the processing efficiency value in the embodiment also needs to be discretized and mapped to the corresponding efficiency label. The event processing efficiency is characterized by the label value 1 being the highest, the label value 2 being the second, and the label value 3 being the lowest for the event processing efficiency. The server calculates the average processing efficiency of the traffic obstruction event based on the processing efficiency values corresponding to multiple traffic obstruction historical events, and determines that the label value corresponding to this average processing efficiency is 2 based on the mapping relationship between the processing efficiency value and the efficiency label. At the same time, the server will also determine the target area where the event occurs in the traffic efficiency map constructed above based on the regional location information of the traffic obstruction event, and obtain the initial traffic efficiency value (that is, the efficiency label) of the target area in the traffic efficiency map; for example, the label value corresponding to the initial efficiency label of the target area is 1. After simultaneously determining the processing efficiency value of the event data and the (initial) traffic efficiency value corresponding to the target area, the server will update the (initial) traffic efficiency value of the target area based on the processing efficiency value. Specifically, in the embodiment, the values of the efficiency labels corresponding to the two efficiency values can be summed to obtain the updated efficiency label. For example, the label value corresponding to the traffic obstruction event is 2, and the label value corresponding to the efficiency label where this traffic obstruction event occurs is 1, and the calculated updated label value is 3; the label value recorded by this efficiency label represents that the updated traffic efficiency value will become lower. The traffic efficiency value updated by the server will be used in the subsequent steps for determining and planning the no-go area.

[0064] Step 206: Update the no-go area in the operation map of the intelligent operation device based on the updated traffic efficiency value.

[0065] In an embodiment, the operation map is a map used to guide an intelligent operation device to perform an operation task; in an embodiment, the operation map includes, but is not limited to, forms of a two-dimensional / three-dimensional grid map, a two-dimensional / three-dimensional cost map, and a two-dimensional / three-dimensional point cloud map. The no-go area in the embodiment represents an area where it is not expected that the intelligent operation device will enter during the operation process; alternatively, the no-go area in the embodiment may refer to an area that may impede the operation process or interrupt the operation process.

[0066] Exemplarily, in the embodiment, during the process of constructing the initial operation map, it can be determined whether to set a region as a no-go area based on the corresponding traffic efficiency value of each region and form a rule for setting up the no-go area; for example, setting the region with an efficiency label value of 3 as a no-go area. Further, during the process of the sweeping robot performing the cleaning task, this rule for setting up the no-go area will also be maintained; for example, after determining a traffic obstruction event through the processing process of the foregoing embodiment, the server updates the traffic efficiency value of the region where the event occurs based on the processing efficiency value of the traffic obstruction event. And after completing the update of the traffic efficiency value, when a new region with an efficiency label value of 3 appears in the traffic efficiency map, the server will, based on the rule for setting up the no-go area, set this region as a new traffic restricted area to update the initial operation map, and finally guide the sweeping robot to complete the cleaning task based on the updated operation map.

[0067] The above control method for the intelligent operation device can, during the operation process of the intelligent operation device, monitor various event data during the operation process in real time, and finally update the no-go area in the operation map based on the monitored event data. Different from the subjective setting method, based on the real-time acquisition of event data during the traffic process, it can provide reliable data support for the process of updating the no-go area, overcoming the lag defect of the manual marking of restricted areas. And, during the process of the no-go area based on event data, the traffic efficiency value of the target area in the traffic efficiency map will be updated according to the processing efficiency value corresponding to the event data, and the area where the event data is monitored is also covered in this target area. Finally, based on the updated traffic efficiency value, the no-go area in the operation map is updated. Compared with subjective judgment and selection, the method of updating the no-go area through the traffic efficiency value can more objectively and accurately identify and determine the no-go area. Further, real-time updating according to the processing efficiency value of event data provides reliable real-time data support and can more accurately update the traffic restricted area in the operation map.

[0068] In one embodiment, as Figure 3 shown, the process of monitoring event data during the operation process in the method may include the following steps:

[0069] Step 200, obtain the sensor data of the sensors in the intelligent operation device.

[0070] Step 201, determine the monitored event data according to the sensor data and the category of the sensors.

[0071] In the embodiment, the sensors in the intelligent operation device include but are not limited to collision sensors, cliff sensors, wheel drop sensors, infrared proximity sensors, infrared ranging sensors, image acquisition sensors, ammeters, gyroscopes, accelerometers, Hall sensors, etc.

[0072] Specifically in the embodiment, the server can obtain the sensor data in real time through the communication protocol with the intelligent operation device. For example, based on the full-duplex communication protocol, the sensor data collected by each sensor in the intelligent operation device is obtained. The sensor data obtained by the server in real time can be identified based on the type of the sensor from which the sensor data is sourced; further, the server can determine the monitored event data based on the sensor data and the data source (the category of the sensor). For example, the sensors built in the intelligent operation device in the embodiment can include collision sensors, cliff sensors, wheel drop sensors, infrared proximity sensors, infrared ranging sensors, and Hall sensors, etc. Correspondingly, the event data detected in the embodiment can include collision events, cliff events, drop events, skidding events, trapped events, and device overcurrent events, etc. Exemplarily, taking the trapped event as an example, the server obtains the infrared ranging data of the infrared proximity sensor and the infrared ranging sensor, and determines that the distance between the current intelligent operation device and the obstacle is less than 1 meter; at the same time, the infrared ranging data will carry the sensor number, name or ID information of the infrared proximity sensor and the infrared ranging sensor when uploaded to the server. The server can determine that the event described by the obtained infrared ranging data is a trapped event based on the sensor number, name or ID information. By setting various types of sensors and identifying the sensor data according to the category of the sensors, the embodiment can more clearly and accurately determine the specific event information corresponding to the event data.

[0073] To enable the operation map to more accurately guide the intelligent operation device, in one embodiment, before updating the traffic efficiency value of the target area in the traffic efficiency map of the intelligent operation device according to the processing efficiency value corresponding to the event data, the method further includes the following steps:

[0074] Step 1, obtain the event location information and the influence range radius corresponding to the event data.

[0075] Step 2, determine the center coordinates of the target area in the traffic efficiency map based on the event location information.

[0076] Step 3: Determine the target area in the traffic efficiency map according to the central coordinates and the influence range radius.

[0077] In the embodiment, the event location information represents the specific location information where the event occurs. For example, in the embodiment, while collecting the event data, the coordinate position information of the event occurrence location is also measured based on the ranging sensor. The influence range radius in the embodiment is used to describe the influence range of the event, and the unexpected event that occurs may affect the traffic efficiency of the intelligent operation device within this influence range. For example, when an object falls to the ground and breaks, there may be a small amount of debris or wreckage in the surrounding area where the object falls, which may affect the progress efficiency of the intelligent operation.

[0078] Exemplarily, taking the example of a sweeping robot triggering a trapped event during operation, since the obstacles that cause the sweeping robot to be blocked or trapped may be fragile items, a small amount of debris and fragments may be formed when the fragile items accidentally fall, both of which may affect the cleaning efficiency of the sweeping robot. Therefore, while the server forms the processing efficiency value of the trapped event based on multiple trapped event data in the historical events, it will also determine the influence range radius corresponding to the trapped event. More specifically, in the embodiment, the influence range radius can be predicted by the server based on a deep learning model constructed by learning from multiple historical event range data and corresponding cleaning efficiency values of the trapped event data in the historical events, and then based on this deep learning model. After detecting that there is a trapped event in front of the sweeping robot during its movement, the server measures the specific position coordinates of the obstacle triggering the trapped event through the ranging sensor, marks the specific position coordinates on the traffic efficiency map, and determines the central coordinates of the event influence area. The server will also obtain the influence range radius corresponding to the trapped event, and based on the central coordinates and the influence range radius, construct the influence range area (i.e., the target area) of the trapped event in the traffic efficiency map. It can be understood that in the influence range area of the event in the embodiment, the influence on the cleaning efficiency of the sweeping robot from the center point of the area to the area and the area edge is different. By constructing the target area in the traffic efficiency map in the embodiment to define the influence range corresponding to the event, it can better fit the actual operation scenario and effectively improve the accuracy of the traffic efficiency map.

[0079] In one embodiment, the traffic efficiency map constructed by the server can be composed of multiple unit grids. Furthermore, the process of determining the target area in the traffic efficiency map according to the central coordinates and the influence range radius in the method may include the following steps:

[0080] Step 1: Based on the central coordinates, screen and determine the central grid from multiple unit grids.

[0081] Step 2: Based on the event influence range formed by the central grid and the influence range radius, target grids are filtered from multiple unit grids.

[0082] Step 3: Based on the target grids, a target area is determined in the traffic efficiency map.

[0083] Specifically in the embodiment, when the server constructs the traffic efficiency map, it can divide the positioning map corresponding to the area to be cleaned through a rasterization processing method to form multiple unit grids, that is, the traffic efficiency map in the embodiment can be composed of multiple unit grids. Further, in the embodiment, the server can construct an event influence range based on different event types and the corresponding influence range radii of the event types.

[0084] Take Figure 4 as an example. After the server determines the central coordinates of the event through the steps of the foregoing embodiment, the central grid of the event is filtered from numerous unit grids based on the central coordinates. More specifically, since the traffic efficiency map is formed by combining multiple unit grids, the influence range radius in the embodiment is described by the number of grids. For example, if the influence range radius in the embodiment is one unit grid, then the event influence range constructed based on the central grid and the influence range radius is a nine-square grid area. Finally, the server determines all the unit grids covered by the event influence range constructed based on the central grid and the influence range radius as target grids, and combines all the target grids to form the target area of the event influence range.

[0085] It should be further noted that in the target area constructed in the embodiment, the actual influence of each target grid on the cleaning efficiency of the sweeping machine is different, and the degree of influence on the cleaning efficiency gradually decreases from the central grid of the area to the target grids at the edge. As Figure 4 shown, when the influence range radius is one unit grid, in the target area determined based on this influence range radius, the central grid has the greatest influence on the cleaning efficiency. According to the foregoing correspondence between the traffic efficiency value and the efficiency label, the value of the efficiency label of this central grid is 2, and the values of the efficiency labels of other grids in the target area are all 1. By introducing the rasterized map processing method in the embodiment, the efficiency of data processing or operation in the embodiment can be improved, enabling the method to quickly and accurately delimit the target area affected by the event.

[0086] In one embodiment, the process of updating the restricted area in the operation map of the intelligent operation device based on the updated traffic efficiency value in the method may include the following steps:

[0087] Step 1: When the updated traffic efficiency value contains a target traffic efficiency value, obtain the restricted area expansion radius corresponding to the operation map; wherein the target traffic efficiency value is not less than the traffic efficiency threshold corresponding to the intelligent operation equipment.

[0088] Step 2: Based on the area corresponding to the target traffic efficiency value and the restricted area expansion radius, update the restricted area in the operation map of the intelligent operation equipment.

[0089] In an embodiment, the target traffic efficiency value is the efficiency value obtained after updating the traffic efficiency value based on the processing efficiency corresponding to the event data, and the target traffic efficiency value is not less than the traffic efficiency threshold. In an embodiment, the traffic efficiency threshold may be a judgment threshold for determining whether to set a specific area as a prohibited area, and the server can construct a judgment rule for a restricted area based on this traffic efficiency threshold; for example, when the traffic efficiency value corresponding to a certain area is less than the traffic efficiency threshold, the area will be set as a restricted area; or when the traffic efficiency value corresponding to a certain area is not less than the traffic efficiency threshold, the area will be set as a normal traffic area. It is understood that the setting method of the traffic efficiency threshold in the embodiment may be pre-written into the server by program writing; or it may be sent to the server based on the parameter setting instruction formed by the user through the interactive operation interface. The restricted area expansion radius in the embodiment is used to characterize the safe distance that the intelligent operation equipment needs to maintain between the prohibited area in the map during the execution of different types of tasks. It is understood that the area corresponding to the target traffic efficiency value in the embodiment may refer to the central area of ​​the prohibited area.

[0090] For example, the traffic efficiency threshold and restricted zone expansion radius in the embodiment may be related to the target efficiency and target coverage of the task. For example, when the sweeping robot performs a land reclamation and cleaning task, which requires a high coverage rate but is not sensitive to efficiency, the traffic efficiency threshold is set low and the restricted zone expansion radius is set small; that is, the land reclamation and cleaning task has low traffic efficiency requirements, and the server will only set the area with extremely low traffic efficiency as a traffic restricted zone; and set the restricted zone expansion radius small to ensure the coverage rate of the task.

[0091] In one embodiment, in order to meet the requirements of a higher load operation task, before updating the prohibited area in the operation map of the intelligent operation device based on the area corresponding to the target traffic efficiency value and the restricted area expansion radius, the following steps may be included:

[0092] Step 1: Determine the operation map corresponding to the intelligent operation device according to the operation task information of the intelligent operation device.

[0093] Step 2: Mark the corresponding prohibited area in the operation map according to the prohibited area information preset in the operation task information.

[0094] In an embodiment, the operation task information is used to describe the tasks that the operation equipment needs to complete, including but not limited to the time to perform the task, the frequency of performing the task, the area of ​​the operation map, and the restricted areas that need to be avoided during the operation. For example, for a sweeping robot, the operation tasks in the embodiment include but are not limited to daily cleaning tasks and land reclamation cleaning tasks; further, in this embodiment, the operation task information may include information such as the area that needs to be covered during the operation of the sweeping robot, the cleaning mode of the cleaning parts, the number of times the cleaning is performed, and the restricted areas that need to be avoided. More specifically, in the embodiment, different restricted area information can be set for different operation tasks; for example, for daily cleaning tasks, in order to efficiently complete the cleaning tasks, in the embodiment, areas that are difficult to clean and do not need to be cleaned frequently can be marked as restricted areas in the map, including but not limited to areas under the sofa and the bottom of the bed; for another example, for land reclamation cleaning tasks, in order to ensure that no cleaning dead corners are left, only inaccessible areas such as stairs and steps are marked as restricted areas in the map. Thus, in the embodiment, different restricted areas in the map can be calibrated based on different operation task information, and different operation maps can be formed to meet the needs of different operation tasks.

[0095] Furthermore, according to the restricted area expansion radius in the aforementioned embodiment, the restricted area in the operation map is optimized and adjusted more finely. When the sweeping robot performs daily cleaning tasks, it needs to complete the task efficiently and reduce disturbance to the user. The traffic efficiency threshold is set higher and the restricted area expansion radius is set larger. That is, in daily cleaning tasks, the server will set the area with a traffic efficiency value slightly lower than the traffic efficiency threshold as a restricted area, and try to expand the restricted area to improve the cleaning efficiency. In the embodiment, based on the area corresponding to the target traffic efficiency value and the restricted area expansion radius, it can more flexibly respond to the complex needs of various operation tasks.

[0096] More specifically, after the traffic efficiency map is updated based on the processing efficiency value of the event data in the embodiment, there may be a situation in which the traffic efficiency values ​​of multiple areas in the traffic efficiency map cannot meet the traffic efficiency threshold, and multiple restricted areas need to be set accordingly. Figure 5 For example, Figure 5 The grid map shown is the traffic efficiency map before updating based on the processing efficiency value of event data. In the traffic efficiency map before updating, there is only one unit grid with an efficiency label value of 3. During the operation of the intelligent operation equipment, specific event data is monitored. The event impact range (i.e., the target area) formed based on the specific event data and the restricted area expansion radius is Figure 4 The server will use the corresponding relationship between the unit grids in the two raster maps to Figure 4 and Figure 5are combined with the grid map to form Figure 6 the traffic efficiency map shown in. In Figure 6 the traffic efficiency map shown in, the value recorded in each unit grid is the efficiency label value obtained after updating based on the processing efficiency value corresponding to the event data. Obviously, in the updated traffic efficiency map, there are multiple unit grids with an efficiency label value of 3; in the embodiment, the rule for setting the traffic restricted area is based on a preset traffic efficiency threshold, and the description in terms of the efficiency label value is: when the efficiency label value is greater than or equal to 3, the corresponding unit grid will be set as the central grid of the traffic restricted area. More specifically, the expansion radius of the restricted area in the embodiment is set to one grid, so in Figure 6 the traffic area shown in, multiple traffic restricted areas need to be set. As Figure 6 shown, for the case where there are multiple traffic restricted areas, in the embodiment, the server can determine the final traffic restricted area based on the union area of the multiple traffic restricted areas. For example, in Figure 6 , the areas corresponding to all the unit grids with numerical markings will ultimately be set as traffic restricted areas.

[0097] In one embodiment, the process of updating the traffic restricted area in the operation map of the intelligent operation device based on the area corresponding to the target traffic efficiency value and the expansion radius of the restricted area may include the following steps:

[0098] Step 1, generate a restricted area image based on the area corresponding to the target traffic efficiency value and the expansion radius of the restricted area.

[0099] Step 2, perform image dilation processing or image erosion processing on the restricted area image according to the coverage rate corresponding to the operation map.

[0100] Step 3, update the traffic restricted area in the operation map of the intelligent operation device based on the restricted area image after image dilation processing or image erosion processing.

[0101] Exemplarily, in the embodiment, the coverage rate corresponding to the operation map can be set based on different types of operation tasks, and this coverage rate can be determined according to the ratio between the map area that the intelligent operation device should cover to complete the operation task and the map area of the operation map.

[0102] Specifically in the embodiments, the server in the embodiments needs to calculate the map coverage area based on the job tasks and a preset coverage rate, and construct an image template of equal area based on the map coverage area. In the process of updating the restricted area through image dilation processing or image erosion processing, the server first needs to determine the central area and the restricted area expansion radius of the restricted area according to the foregoing steps; then, preliminarily construct the restricted area based on the central area and the expansion radius, and use the image formed by projecting the restricted area on the operation map as the restricted area image. Finally, update the restricted area on the operation map according to the obtained restricted area image.

[0103] In one embodiment, performing image dilation processing or image erosion processing on the restricted area image according to the coverage rate corresponding to the operation map includes the following steps:

[0104] Step 1, obtain an image template corresponding to a preset map coverage area.

[0105] Step 2, if the target coverage rate corresponding to the operation map is greater than the preset coverage rate corresponding to the image template, perform image dilation processing on the restricted area image.

[0106] Step 3, if the target coverage rate corresponding to the operation map is less than or equal to the preset coverage rate corresponding to the image template, perform image erosion processing on the restricted area image.

[0107] Exemplarily, in the embodiment, the coverage rate of the operation map is judged by comparing the restricted area image with the image template. Specifically, when the target coverage rate corresponding to the operation map is less than or equal to the preset coverage rate corresponding to the image template, that is, when the area of the restricted area image is greater than the area of the image template, each pixel in the restricted area image is processed as follows: Place the pixel at the center of the image template, and according to the size of the image template, traverse all other pixels covered by the template, and modify the value of the pixel to the minimum value among all pixels; that is, the result of the image erosion process in the embodiment is to erode the protruding points on the periphery of the restricted area image. When the target coverage rate corresponding to the operation map is greater than the preset coverage rate corresponding to the image template, that is, when the area of the restricted area image is less than the area of the image template, each pixel in the restricted area image is processed as follows: Place the pixel at the center of the image template, and according to the size of the template, traverse all other pixels covered by the template, and modify the value of the pixel to the maximum value among all pixels; that is, the result of the image dilation process in the embodiment is to dilate the sunken points on the periphery of the restricted area image. It should be noted that during the process of image dilation or image erosion, the operation map can be grayscale processed to simplify the map information, and the passage restricted areas in the operation map are marked by different grayscale information; and the higher the grayscale value of the area, the lower the corresponding passage efficiency value. In the embodiment, based on the coverage rate corresponding to the operation map, image dilation processing or image erosion processing is performed on the restricted area image, so that the finally updated passage restricted area is more accurate.

[0108] In one embodiment, the control method for the intelligent operation device provided by the present application may further include the following steps:

[0109] Step 1, after the operation process of the intelligent operation device ends, obtain the operation data of the operation process.

[0110] Step 2, determine the efficiency update value of each area in the passage efficiency map based on the operation data.

[0111] Step 3, update the passage efficiency value of each area in the passage efficiency map through the efficiency update value of each area.

[0112] In an embodiment, the operation data is the data content formed after the end of an operation process and used for information related to an operation task. For example, the operation data may record the traffic efficiency values corresponding to each area (including restricted areas and non-restricted areas) in the operation map during the execution of a task. In order to eliminate the influence of too distant historical events, exclude the random events of dynamic obstacles, and narrow the existing restricted area range to improve the task completion effect, in the embodiment, the traffic efficiency at the corresponding position in the operation map after the operation process can be adjusted. For example, the efficiency label value corresponding to all areas in the operation map is decreased by one; the efficiency label value obtained after the adjustment is the efficiency update value in the embodiment. More specifically, in the embodiment, when executing the next task, the initial efficiency traffic map can be constructed by loading the efficiency update value.

[0113] Exemplarily, during the process of a sweeping robot executing a cleaning task, when it encounters a pet cat and triggers a collision event, in the operation map formed after finally completing the cleaning task, the efficiency label value corresponding to the collision area is increased by one compared to the efficiency label value in the initial traffic efficiency map, which also indicates that the traffic efficiency in the collision area has decreased. The server decreases the efficiency label value corresponding to all areas in the operation map by one after each cleaning is completed, to exclude this kind of occasional noise interference, so that in the embodiment, the process of processing the traffic efficiency value of the area is more in line with the actual situation. On the contrary, if a collision occurs at this position multiple times within a month, the collision area will be kept as a restricted area.

[0114] Combined with the attached drawings of the specification Figure 7 and taking the specific implementation scenario of a sweeping robot executing a cleaning task as an example, the complete implementation process of the control method for the intelligent operation device provided in the technical solution of the present application is described as follows:

[0115] Step 1, monitor and collect event data. After receiving a cleaning task instruction, in response to this instruction, the sweeping robot will drive out from the storage bin of the cleaning base station and start to execute the cleaning operation. In order to be able to monitor in real time various unexpected situations faced by the sweeping robot during the execution of the cleaning task, the server in the embodiment can collect the self-state data and surrounding environment information of the sweeping robot during the cleaning task process by calling various built-in sensor components of the sweeping robot. The two data information is synchronously uploaded to the server as event data to realize the real-time monitoring of the event data during the cleaning task process by the server, and provide necessary data support for the subsequent update process of the restricted area.

[0116] Step 2: Construct an initial operation map based on the processing efficiency values. After the sweeping robot receives the cleaning task instruction and before starting to execute the cleaning task, it needs to obtain the initial operation map from the server so that the sweeping robot can execute the cleaning task based on this initial operation map. In the process of the server forming this initial operation map, first, it needs to determine the area to be cleaned for the cleaning task and form a positioning map corresponding to the area to be cleaned. The boundary information of the area to be cleaned needs to be roughly reflected in this positioning map. Then, the server will, based on the area information of the area to be cleaned, retrieve the historical cleaning task data associated with this area information. After obtaining the historical cleaning task data, based on the area area corresponding to each area in the positioning map and the historical cleaning time, calculate the cleaning efficiency value of the sweeping robot in each area, and discretize the cleaning efficiency value and map it to the corresponding efficiency label. Mark each area in the positioning map with the efficiency label corresponding to the cleaning efficiency value to form a traffic efficiency map. After obtaining the traffic efficiency map, the server will select the efficiency label values corresponding to each area in the traffic efficiency map, delimit the areas with lower traffic efficiency as traffic restricted areas, and thus construct the initial operation map.

[0117] Step 3: Update the traffic efficiency value according to the processing efficiency value corresponding to the event data. After the server monitors an unexpected event during the cleaning process of the sweeping robot and obtains the event data of the unexpected event, it will adjust or update the traffic restricted areas in the operation map based on this event data. For example, after the server determines that there is a traffic obstruction event in front of the sweeping robot based on the monitored ranging data, first, according to the event trigger signal of the traffic obstruction event, based on the time name or number of the traffic obstruction event, conduct a matching search for the event in the record of the historical cleaning task data, and retrieve the processing efficiency values of multiple traffic obstruction events from the historical cleaning task data. The server calculates the average processing efficiency value of the traffic obstruction event based on the retrieved multiple processing efficiency values corresponding to the traffic obstruction events, and determines this processing efficiency average value based on the mapping relationship between the processing efficiency value and the efficiency label. At the same time, the server will also, based on the area location information of this traffic obstruction event, determine the target area where this event occurs in the previously constructed traffic efficiency map, and obtain the initial traffic efficiency value of this target area in the traffic efficiency map. After simultaneously determining the processing efficiency value of the event data and the (initial) traffic efficiency value corresponding to the target area, the server will update the (initial) traffic efficiency value of the target area based on the processing efficiency value.

[0118] Step 4: Update the no-go area in the operation map of the intelligent operation device. When it is determined that a traffic obstruction event has occurred, after updating the traffic efficiency value of the area where the event occurred based on the processing efficiency value of the traffic obstruction event, it is determined that there is a new area in the traffic efficiency map where the efficiency label value exceeds the preset normal efficiency threshold. Further, in the embodiment, based on the rule for setting up the no-go area, this area will be set as a new traffic restricted area in the initial operation map to achieve the update of the no-go area.

[0119] It should be understood that although the steps in the flowcharts involved in the above embodiments are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0120] Based on the same inventive concept, an embodiment of the present application also provides a control device for an intelligent operation device for implementing the control method of the intelligent operation device involved above. The implementation solution provided by this device for solving problems is similar to the implementation solution described in the above method. Therefore, the specific limitations in one or more embodiments of the control device for the intelligent operation device provided below can refer to the limitations on the control method of the intelligent operation device in the above text, and will not be repeated here.

[0121] In one embodiment, as Figure 8 shown, a control device for an intelligent operation device is provided, including: an event monitoring module 801, an efficiency update module 802, and a no-go area update module 803, where:

[0122] The event monitoring module 801 is configured to monitor event data during the operation of the intelligent operation device during the operation process;

[0123] The efficiency update module 802 is configured to, when the event data is monitored, update the traffic efficiency value of the target area in the traffic efficiency map of the intelligent operation device according to the processing efficiency value corresponding to the event data, and the target area includes the area where the event data is monitored;

[0124] The no-go area update module 803 is configured to update the no-go area in the operation map of the intelligent operation device based on the updated traffic efficiency value.

[0125] In one embodiment, the event monitoring module 801 is further configured to obtain the sensor data of the sensors in the intelligent operation device; and determine the monitored event data according to the sensor data and the categories of the sensors.

[0126] In one embodiment, the device 800 further includes a map generation module, which is configured to obtain the event location information and the influence range radius corresponding to the event data; determine the central coordinates of the target area in the traffic efficiency map based on the event location information; and determine the target area in the traffic efficiency map according to the central coordinates and the influence range radius.

[0127] In one embodiment, the traffic efficiency map includes a plurality of unit grids. Further, the map generation module is further configured to screen and determine the central grid from the plurality of unit grids based on the central coordinates; obtain the target grids by screening from the plurality of unit grids according to the event influence range formed by the central grid and the influence range radius; and determine the target area in the traffic efficiency map based on the target grids.

[0128] In one embodiment, when there is a target traffic efficiency value in the updated traffic efficiency values, the efficiency update module 802 is further configured to obtain the restricted area expansion radius corresponding to the operation map, and the target traffic efficiency value is not less than the traffic efficiency threshold corresponding to the intelligent operation device; and update the restricted area in the operation map of the intelligent operation device based on the area corresponding to the target traffic efficiency value and the restricted area expansion radius.

[0129] In one embodiment, the efficiency update module 802 is further configured to generate a restricted area image based on the area corresponding to the target traffic efficiency value and the restricted area expansion radius; perform image dilation processing or image erosion processing on the restricted area image according to the coverage rate corresponding to the operation map; and update the restricted area in the operation map of the intelligent operation device based on the restricted area image after the image dilation processing or the image erosion processing.

[0130] In one embodiment, the device 800 further includes a data sorting module, which is configured to obtain the operation data of the operation process after the operation process of the intelligent operation device ends; determine the efficiency update values of the areas in the traffic efficiency map based on the operation data; and update the traffic efficiency values of the areas in the traffic efficiency map through the efficiency update values of the areas.

[0131] Each module in the control device of the above intelligent operation device can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor in the intelligent operation device in the form of hardware or be independent of the processor, or be stored in the memory in the intelligent operation device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0132] In one embodiment, an intelligent operation device is provided, and the internal structure diagram of the intelligent operation device can be as Figure 9As shown. The intelligent operation device may include a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the intelligent operation device is used to provide computing and control capabilities. The memory of the intelligent operation device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the intelligent operation device is used to store task-related data of the intelligent operation device, such as task-related map data and historical task data, etc. The input / output interface of the intelligent operation device is used to exchange information between the processor and external devices. The communication interface of the intelligent operation device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a control method for an intelligent operation device.

[0133] Those skilled in the art can understand that Figure 9 the structure shown in is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the intelligent operation device to which the solution of this application is applied. The specific intelligent operation device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0134] In one embodiment, an intelligent operation device is further provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are implemented.

[0135] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by the processor, the steps in the above method embodiments are implemented.

[0136] In one embodiment, a computer program product is provided, including a computer program. When the computer program is executed by the processor, the steps in the above method embodiments are implemented.

[0137] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0138] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0139] The above embodiments only represent several implementation manners of the present application. Their descriptions are relatively specific and detailed, but they should not be construed as limiting the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A control method for an intelligent operation device, characterized in that, The method includes: During the operation of the intelligent operation device, monitoring the event data during the operation; According to the processing efficiency value corresponding to the event data, updating the traffic efficiency value of the target area in the traffic efficiency map of the intelligent operation device, where the target area includes the area where the event data is monitored; the processing efficiency value is used to characterize the efficiency of the intelligent operation device in processing the event corresponding to the event data; the traffic efficiency value is used to characterize the efficiency of the intelligent operation device passing through the target area; Based on the updated traffic efficiency value, updating the no-go area in the operation map of the intelligent operation device.

2. The method according to claim 1, characterized in that The monitoring of the event data during the operation includes: Obtaining the sensor data of the sensors of the intelligent operation device; Determining the monitored event data according to the sensor data and the category of the sensor.

3. The method according to claim 1, characterized in that Before updating the traffic efficiency value of the target area in the traffic efficiency map of the intelligent operation device according to the processing efficiency value corresponding to the event data, the method further includes: Obtaining the event location information and the influence range radius corresponding to the event data; Based on the event location information, determining the central coordinates of the target area in the traffic efficiency map; According to the central coordinates and the influence range radius, determining the target area in the traffic efficiency map.

4. The method according to claim 3, characterized in that, The traffic efficiency map includes a plurality of unit grids; The determining the target area in the traffic efficiency map according to the central coordinates and the influence range radius includes: Based on the central coordinates, screening and determining the central grid from the plurality of unit grids; According to the event influence range formed by the central grid and the influence range radius, screening the target grid from the plurality of unit grids; Based on the target grid, determining the target area in the traffic efficiency map.

5. The method according to claim 1, wherein The updating the no-go area in the operation map of the intelligent operation device based on the updated traffic efficiency value includes: When there is a target traffic efficiency value in the updated traffic efficiency value, obtaining the no-go area expansion radius corresponding to the operation map, and the target traffic efficiency value is not less than the traffic efficiency threshold corresponding to the intelligent operation device; Based on the area corresponding to the target traffic efficiency value and the no-go area expansion radius, updating the no-go area in the operation map of the intelligent operation device.

6. The method according to claim 5, wherein Before updating the no-go area in the operation map of the intelligent operation device based on the area corresponding to the target traffic efficiency value and the no-go area expansion radius, the method further includes: Determining the operation map corresponding to the intelligent operation device according to the operation task information of the intelligent operation device; According to the preset no-go area information in the operation task information, marking the corresponding no-go area in the operation map.

7. The method according to claim 5, wherein The updating the no-go area in the operation map of the intelligent operation device based on the area corresponding to the target traffic efficiency value and the no-go area expansion radius includes: Generating a no-go area image based on the area corresponding to the target traffic efficiency value and the no-go area expansion radius; Performing image dilation processing or image erosion processing on the no-go area image according to the target coverage rate corresponding to the operation map; Update the no-go area in the operation map of the intelligent operation device based on the restricted area image after image dilation processing or image erosion processing.

8. The method according to claim 7, wherein Performing image dilation processing or image erosion processing on the restricted area image according to the coverage rate corresponding to the operation map includes: Obtain an image template corresponding to a preset map coverage area; If the target coverage rate corresponding to the operation map is greater than the preset coverage rate corresponding to the image template, perform image dilation processing on the restricted area image; If the target coverage rate corresponding to the operation map is less than or equal to the preset coverage rate corresponding to the image template, perform image erosion processing on the restricted area image.

9. The method according to any one of claims 1-6, characterized in that The method further includes: After the operation process of the intelligent operation device ends, obtain the operation data of the operation process; Determine the efficiency update value of each area in the traffic efficiency map based on the operation data; Update the traffic efficiency value of each area in the traffic efficiency map through the efficiency update value of each area.

10. An intelligent operation device, characterized in that, It includes a fuselage, a driving component, a cleaning component, a detection sensor, a memory, and a processor. The driving component, the cleaning component, and the detection sensor are all installed on the fuselage. The driving component is used to drive the fuselage to move on the working surface. The cleaning component is used to clean the working surface. The memory stores a computer program. When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 9.

Images