Patrol control method and device and nonvolatile storage medium

Abstract

The application discloses a kind of inspection control method, device and nonvolatile storage medium.Therein, the method includes: determining target area, and the multiple risk zones included in the target area, wherein the multiple risk zones correspond to different area risk levels respectively;In the case where an abnormal signal is received, determine the alarm level corresponding to the abnormal signal, the target position corresponding to the abnormal signal, and the target risk zone in which the target position is located in the multiple risk zones, wherein the abnormal signal is the signal that the predetermined sensor detects meets the predetermined alarm condition;Based on the alarm level and the target risk level corresponding to the target risk zone, determine the target inspection device in the predetermined multiple candidate inspection devices.The present application solves the technical problem of the related art that the inspection efficiency is not ideal.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of inspection, in particular to an inspection control method and device and a nonvolatile storage medium. BACKGROUND

[0002] In high-temperature, high-humidity, toxic, dangerous environment, industrial robots have been able to replace technical personnel, engaged in high-risk industries, can effectively protect personal safety. There are different inspection devices in the related art, for abnormal conditions with explosion risk, technical personnel need to make instructions in a very short time, which is easy to lead to the selection of the inspection device to check the abnormal place is not the best choice, resulting in the inspection efficiency is not ideal, and further unable to perceive the abnormal situation in time, which exists safety hidden danger.

[0003] For the above problems, there is no effective solution at present. SUMMARY

[0004] The embodiments of the present application provide an inspection control method, device and nonvolatile storage medium, to at least solve the technical problem of the inspection efficiency not being ideal in the related art.

[0005] According to an aspect of the embodiments of the present application, an inspection control method is provided, comprising: determining a target area and a plurality of risk areas included in the target area, wherein the plurality of risk areas correspond to different regional risk levels respectively; in the case of receiving an abnormal signal, determining an alarm level corresponding to the abnormal signal, a target position corresponding to the abnormal signal, and a target risk area in which the target position is located in the plurality of risk areas, wherein the abnormal signal is a signal detected by a preset sensor that meets a predetermined alarm condition; and determining a target inspection device in a plurality of candidate inspection devices based on the alarm level and a target risk level corresponding to the target risk area.

[0006] According to another aspect of the embodiments of the present application, an inspection control device is provided, comprising: a determination module configured to determine a target area and a plurality of risk areas included in the target area, wherein the plurality of risk areas correspond to different regional risk levels respectively; an abnormal processing module configured to, in the case of receiving an abnormal signal, determine an alarm level corresponding to the abnormal signal, a target position corresponding to the abnormal signal, and a target risk area in which the target position is located in the plurality of risk areas, wherein the abnormal signal is a signal detected by a preset sensor that meets a predetermined alarm condition; and a selection module configured to determine a target inspection device in a plurality of candidate inspection devices based on the alarm level and a target risk level corresponding to the target risk area.

[0007] According to another aspect of the embodiments of the present application, there is provided a non-transitory storage medium storing a plurality of instructions adapted to be loaded and executed by a processor to perform any of the inspection control methods.

[0008] In the embodiments of the present application, by determining a target region and a plurality of risk zones included in the target region, wherein the plurality of risk zones correspond to different risk levels of different regions respectively, in the case of receiving an abnormal signal, determining an alarm level corresponding to the abnormal signal, a target position corresponding to the abnormal signal, and a target risk zone in which the target position is located in the plurality of risk zones, wherein the abnormal signal is a signal detected by a preset sensor that meets a predetermined alarm condition; determining a target inspection device in a plurality of candidate inspection devices based on the alarm level and a target risk level corresponding to the target risk zone. The purpose of improving the efficiency of selecting an inspection device according to the alarm level and the risk level is achieved, and the technical effect of improving the inspection efficiency by using appropriate inspection devices is achieved, thereby solving the technical problem of unsatisfactory inspection efficiency in the related art. BRIEF DESCRIPTION OF DRAWINGS

[0009] The accompanying drawings, which are included to provide a further understanding of the present application and are incorporated in and constitute a part of this application, illustrate embodiments of the present application and serve to explain the present application. In the drawings:

[0010] Figure 1 is a flowchart of an optional inspection control method according to an embodiment of the present application;

[0011] Figure 2 is a flowchart of an optional inspection control method according to an embodiment of the present application;

[0012] Figure 3 is a flowchart of an optional inspection control method according to an embodiment of the present application;

[0013] Figure 4 is a schematic diagram of an optional inspection control device according to an embodiment of the present application. DETAILED DESCRIPTION

[0014] In order to enable persons skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings of the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by persons skilled in the art without creative work should fall within the protection scope of the present application.

[0015] It is to be understood that the terminology "first", "second" and the like used in the specification and the claims of the application as well as the foregoing drawings is merely intended to distinguish between similar objects and not necessarily for describing a particular sequential order. It is to be understood that the use of such terms can be interchanged in suitable circumstances so that the embodiments of the application described herein are capable of being practiced in other than the order illustrated or described herein. Furthermore, the terms "comprise", "comprising", "include", "including" and the like used in the description and the claims of the application are intended to be inclusive or open-ended and not restrictive; the process, method, article, or apparatus that includes, comprises, or consists of any of the features recited herein can consist of, in addition to or in lieu of those features, any other feature or combination of features disclosed herein.

[0016] According to an embodiment of the application, a method for inspection control is provided. It is to be understood that the steps shown in the flowcharts of the drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0017] Figure 1 is a flowchart of an optional method for inspection control according to an embodiment of the application, as shown in Figure 1 the method comprises the following steps:

[0018] Step S102, determining a target area, and a plurality of risk zones included in the target area, wherein the plurality of risk zones correspond to different area risk levels respectively;

[0019] It can be understood that the target area is the range in which the inspection is performed, and the target area includes a plurality of risk zones corresponding to different area risk levels. Different area risk levels have different requirements for the types of equipment performing the inspection therein.

[0020] In an optional embodiment, determining the target area comprises: in the case where the plurality of candidate inspection devices include a ground robot and a drone, acquiring first map data collected by at least one first sensor mounted on the ground robot; acquiring second map data collected by at least one second sensor mounted on the drone; and generating an electronic map of the target area based on the first map data and the second map data.

[0021] It can be understood that, for the paths, facilities, devices and the like marked in the target area electronic map, in order to efficiently obtain the geographic information of the target area, the electronic map of the target area is generated based on the data collected by the ground robot and the unmanned aerial vehicle respectively, through the above processing, the efficiency of perceiving the geographic information of the target area can be more efficient, and the generated electronic map is more accurate in combination with the ground robot and the unmanned aerial vehicle.

[0022] Optionally, the at least one first sensor is, for example, a depth camera, a three-dimensional laser radar, a GPS (Global Positioning System), an IMU (Inertial Measurement Unit), a mileage meter, etc.; and the at least one second sensor is, for example, a three-dimensional ranging sensor (such as a three-dimensional laser radar and a depth camera, a binocular camera) and a GNSS (Global Navigation Satellite System) positioning device. The GNSS is a global satellite navigation system, which can locate, measure and monitor objects or positions.

[0023] Optionally, the electronic map can be generated in various ways, for example, by using a laser SLAM (Simultaneous Localization and Mapping) method, a visual SLAM method, a laser SLAM method and a visual SLAM method, etc. SLAM refers to simultaneous localization and mapping, which is a technology that allows a robot or mobile device to perceive the environment and simultaneously complete localization and mapping without external reference. Sensors such as laser radars and cameras are used to collect environmental information, and algorithms are used to process this information into a 3D model that can represent the characteristics of the environment, thereby achieving accurate positioning and visual presentation of the current position and surrounding environment.

[0024] Optionally, the first map data and the second map data can be obtained in various ways, for example, by moving the remote control inspection device in the target area, and by using heuristic mapping. The heuristic mapping needs to be limited by boundaries, and the ways that can be used include setting a fence outside the well site to limit the mapping range (such as 50 meters by 50 meters).

[0025] In step S104, in the case where the abnormal signal is received, the alarm level corresponding to the abnormal signal, the target position corresponding to the abnormal signal, and the target risk area in which the target position is located in the multi-level risk area are determined, wherein the abnormal signal is a signal detected by a preset sensor that meets a predetermined alarm condition.

[0026] It can be understood that in the case of receiving an abnormal signal, it is considered that a signal meeting a predetermined alarm condition is detected by a preset sensor. Due to the limited collection accuracy of the sensor itself or the existence of signal fluctuations, the relevant technical personnel need to check the target position of the abnormal target. In the case of an abnormal signal, there is a risk of personal injury, and the target risk area where the alarm level and target position are located needs to be determined, which is beneficial to subsequent determination of the target inspection equipment suitable for checking the target position.

[0027] Step S106, determining a target inspection equipment from a plurality of candidate inspection equipments based on the alarm level and a target risk level corresponding to the target risk area;

[0028] It can be understood that based on the alarm level and the target risk level corresponding to the target risk area, the danger degree of the target position can be determined, which is beneficial to determining the target inspection equipment for checking the target position from the plurality of candidate inspection equipments.

[0029] In an optional embodiment, the above determining a target inspection equipment from a plurality of candidate inspection equipments based on the alarm level and a target risk level corresponding to the target risk area includes: in the case that the alarm level is a first-level alarm, determining that the target inspection equipment is a target unmanned aerial vehicle closest to the target position; taking the target unmanned aerial vehicle as the target inspection equipment; in the case that the alarm level is a second-level alarm and the target risk level is higher than a predetermined risk level, determining a first number of explosion-proof equipments from the plurality of candidate inspection equipments, wherein the plurality of candidate inspection equipments correspond to different priorities respectively, and the risk of the first-level alarm is higher than the risk of the second-level alarm; selecting a target explosion-proof equipment with the highest priority from the first number of explosion-proof equipments; and taking the target explosion-proof equipment as the target inspection equipment.

[0030] It can be understood that in the case of a first alarm level, it is considered that an abnormal condition that may occur a great security risk needs to be checked, and no matter whether the area where the inspection device is located has an explosion risk or not, the inspection device has an explosion-proof capability, the inspection device that can reach the target position the fastest needs to be mobilized to respond, so as to prevent the abnormal condition at the target position from being further deteriorated due to the suboptimal inspection efficiency. Based on the above reasons, the target inspection device is determined as the target unmanned aerial vehicle closest to the target position. For the case of a second alarm level, the target risk level corresponding to the target position needs to be determined, and the danger degree of the second alarm is lower than that of the first alarm. In the case where the target risk level is also higher than the predetermined risk level, it is considered that an explosion-proof device with an explosion-proof capability needs to be selected. The plurality of candidate inspection devices correspond to respective priority levels, and the target explosion-proof device with the highest priority level is selected from the first number of explosion-proof devices as the target inspection device. Through the above processing, the alarm level can be used to represent the criticality of the abnormal condition, and the target risk level can be used to represent the demand for explosion-proof capability, and the currently applicable target inspection device is determined from multiple dimensions.

[0031] Alternatively, the above priority level can be set in multiple ways, for example: the plurality of candidate inspection devices include a ground robot, an unmanned aerial vehicle type 1, and an unmanned aerial vehicle type 2. The priority level can be set in descending order of moving speed, corresponding to the order of the unmanned aerial vehicle type 2, the unmanned aerial vehicle type 1, and the ground robot from high to low. The priority level can also be set according to the types of collection devices carried by the inspection devices, such as setting the priority level of the inspection device carrying a binocular camera (a camera with ranging capability) to be higher than that of the inspection device carrying an ordinary camera (without ranging capability), and the like. The above setting methods are only examples and are not limited.

[0032] In an optional embodiment, the above method further comprises: in the case where the above abnormal signal is not received, obtaining a predetermined task of inspecting the target area; based on the predetermined task, determining a task risk area of a predetermined task route in the multi-level risk area; in the case where the task risk area is multiple, determining a first risk level greater than a predetermined level threshold in the risk level corresponding to each of the multiple task risk areas; and based on the first risk level, determining a first inspection device.

[0033] It can be understood that, in the case that no abnormal signal is received, a predetermined task of inspecting the target area is acquired, the predetermined task is regarded as a daily type of inspection task, and the workload of manual inspection can be reduced by means of the inspection machine. Based on the predetermined task, a task risk area that will be passed through in the execution process of the predetermined task is determined in the multiple risk areas. In the case that the task risk area is multiple, a first risk level greater than a predetermined level threshold in the area risk levels corresponding to the multiple task risk areas is taken as a basis for determining a first inspection device, and the first inspection device used for executing the predetermined task is obtained. Through the above processing, in the case that no abnormal condition occurs (i.e., no abnormal signal is received), the first inspection device is determined according to the first risk level of the inspection path, which is beneficial to avoid that the inspection device with low protection capability enters the area with high risk, and is beneficial to guarantee the safe execution of the inspection process.

[0034] Optionally, the multiple candidate inspection devices can include multiple types, for example, a ground robot, a drone, and a terminal device. The ground robot can include four parts, i.e., an execution component, a driving component, a sensing component, and a control component. For the execution component, it mainly refers to the robot body, which completes the execution of specific actions. For the driving component, the driving component is a component for driving the execution component to move, and makes the robot move according to the instruction signal sent by the control component by means of a power unit. For the sensing component, it mainly completes the input and feedback of signals, including an internal sensing system and an external sensing system. In the ground robot, commonly used sensors include distance sensors such as radar, ultrasonic, depth camera, and binocular camera, IMU sensors for inertial measurement, and image sensors such as monocular camera, binocular camera, and depth camera. According to requirements, other required sensors such as gas sensor, pressure sensor, temperature sensor, and humidity sensor can be mounted, and one or more sensors can be combined according to specific requirements. For the control component, the sensing information of the sensing component is used to realize real-time analysis and processing of the task, and a control command signal is output after decision-making.

[0035] The drone can include a flight frame, a flight control system, a propulsion system, a remote controller, a remote control signal receiver, and a gimbal camera. The flight control system generally has a built-in controller, a gyroscope, an accelerometer, and a barometer. The drone stabilizes the body by relying on these sensors, and then locks the drone at a specified position and height by cooperating with GPS and barometer data.

[0036] The terminal device can be a portable device, which includes an NFC device (Near Field Communication), a two-dimensional code scanning device, or a GPS positioning device, and is used to identify the on-site position. The terminal device can also include a radio frequency identification device, which is used to confirm the on-site situation of the target carrying the terminal.

[0037] In an optional embodiment, in the case where the first inspection device is multiple, and the multiple first inspection devices include a terminal device, a drone, and a ground robot, the drone and the ground robot are arranged to follow the terminal device respectively; a first recognition result obtained by the drone performing image recognition on a target object holding the terminal device, and a second recognition result obtained by the ground robot performing image recognition on the target object are acquired; a protection state of the target object is determined based on the first recognition result and the second recognition result; and in the case where the protection state does not satisfy a predetermined protection condition, prompt information is sent to the terminal device.

[0038] It can be understood that, in the case where the determined first inspection device includes a terminal device, a drone, and a ground robot, the drone and the ground robot can be arranged to follow the terminal device respectively, and the drone can collect images of a target object during the following process, and the ground robot can collect images of the target object during the following process. Image recognition on the images collected by the drone can obtain a part of the protection state of the target object, and image recognition on the images collected by the ground robot can obtain another part of the protection state of the target object. Based on the first recognition result and the second recognition result, the protection state of the target object is determined, and in the case where the determined protection state does not satisfy a predetermined protection condition, prompt information is sent to the terminal device. Through the above processing, the target object can be prompted for protection. Since the risk levels of different inspection routes are different, the protection state that the target object may adopt may not be adequate. In the case where the protection state does not satisfy the predetermined protection condition, it is unsafe to enter a risk area. The use of the prompt information sending mode is conducive to improving the safety of the inspection.

[0039] In an optional embodiment, after the electronic map of the target area is acquired, a predetermined position point is selected as an inspection point, wherein the inspection point is a plurality of target positions of the first inspection device on an inspection route; and based on the inspection point and at least one inspection item included in the inspection point, an inspection list for instructing the first inspection device is generated.

[0040] It can be understood that each inspection route has at least one inspection point, and the inspection point includes at least one inspection item. The inspection item can be a device, a component, a part, an instrument panel, etc. at the inspection point, which is set according to requirements.

[0041] Optionally, the information set in the inspection list can be multiple, for example, the inspection purpose can be set, the same inspection route, the inspection before starting work and the inspection after completing work, the standards for displaying normal inspection items can be different, the inspection time type can be set, including immediate inspection after issuing an inspection task, and timing inspection. The required inspection pose of the first inspection device at the inspection point can also be set.

[0042] Optionally, in the case that the first inspection device is multiple, and the multiple first inspection devices include a terminal device, a drone, and a ground robot, a voice interaction mode is adopted to associate the current position of the terminal device with the inspection list issued to the first inspection device, to obtain an updated inspection list. It can be understood that in the inspection process, the target object can add new inspection items to the stored inspection list in the first inspection device following the terminal device in a voice interaction mode, to obtain an updated inspection list, which can make the inspection process more flexible and reduce the limitation of the inspection route.

[0043] In an optional embodiment, after determining the target inspection device from the multiple candidate inspection devices based on the alarm level and the target risk level corresponding to the target risk area, the target inspection device performs the following processing: receiving an inspection strategy sent by the main controller, wherein the inspection strategy is used to indicate the target position of the target inspection device, the work device that issues the abnormal signal, and the target component of the work device used to verify the abnormal signal; determining the positioning information of the target component in the work device in the case that the target position is reached; determining the collection pose for signal collection of the target component based on the positioning information; obtaining an inspection result by using the collection pose, and sending the inspection result to the main controller.

[0044] It can be understood that after determining the target inspection device, the target inspection device performs the following processing: after receiving the inspection strategy sent by the main controller, the inspection strategy can indicate the target position to which the target inspection device is to go, the work device that issues the abnormal signal, and the target component of the work device used to verify the abnormal signal. In other words, the work device that issues the abnormal signal can be determined based on the target component if an abnormal condition really occurs, for example, the target component can be an instrument panel or a switch valve on the work device. In the case that the target position is reached, the positioning information of the target component in the work device is determined, that is, the relative position of the target component and the work device. According to the positioning information, the collection pose for signal collection of the target component can be correspondingly determined. Using an appropriate collection pose is conducive to improving the accuracy of the inspection result, and the inspection result is fed back to the main controller. Through the above processing, with the help of the positioning information of the target component on the work device, the accuracy of the collection pose of the target inspection device is improved.

[0045] In an optional embodiment, the determination of the acquisition pose for signal acquisition of the target component based on the positioning information comprises: in a case where the positioning information comprises a first pose of the target inspection device relative to the work device and a second pose of the target component relative to the work device, determining the acquisition pose based on the first pose and the second pose.

[0046] It can be understood that the pose comprises both the position and the attitude, and in a case where the first pose of the target inspection device relative to the work device and the second pose of the target component relative to the work device are determined, the acquisition pose with higher accuracy of the inspection result can be determined based on the first pose and the second pose.

[0047] In an optional embodiment, the determination of the positioning information of the target component in the work device comprises: identifying the target position by using a predetermined first acquisition angle to obtain a third identification result; in a case where the work device is not identified by the third identification result, performing the following processing in a loop until an updated fourth identification result is the work device is identified or an updated second acquisition angle is greater than a predetermined angle threshold: updating the first acquisition angle to obtain a second acquisition angle; in a case where the fourth identification result is the work device is identified, identifying the target position by using the second acquisition angle to obtain a fourth identification result; identifying the work device by using the updated second acquisition angle to obtain a component identification result; and determining the positioning information based on the component identification result.

[0048] It can be understood that after the target inspection device reaches the target position, the target position may comprise other facilities or irrelevant objects in addition to the work device, and the work device needs to be positioned. In a case where the work device is not identified by the third identification result obtained by using the first acquisition angle, it is considered that the acquisition angle needs to be changed on the spot, the first acquisition angle is updated to obtain a second acquisition angle, the target position is identified again by using the second acquisition angle to obtain a fourth identification result, and the processing is performed in a loop in this way until the work device is identified by the updated fourth identification result or the processing is stopped when the updated second acquisition angle is greater than the predetermined angle threshold. The work device is identified by using the updated second acquisition angle to obtain a component identification result, and the positioning information is determined.

[0049] In an optional embodiment, in the case that the updated second collection angle is greater than the predetermined angle threshold, and the updated fourth recognition result is that the work equipment is not recognized, the component type of the target component is determined; the target position is recognized by using a plurality of predetermined detection angles respectively, to obtain fifth recognition results corresponding to the plurality of detection angles respectively; in the case that the fifth recognition results corresponding to the plurality of detection angles respectively are at least one candidate component matching the component type, and the number of the at least one candidate component is less than a predetermined number, signal collection is performed on the at least one candidate component respectively, to obtain candidate results corresponding to the at least one candidate component respectively; image collection is performed on the at least one candidate component respectively, to obtain collection images corresponding to the at least one candidate component respectively; and the candidate results and the collection images corresponding to the at least one candidate component respectively are sent to the main controller.

[0050] It can be understood that the purpose of the target inspection equipment is to review abnormal signals, and for the abnormal condition, the relevant information of the target position needs to be obtained to the greatest extent. In the case that the work equipment is not recognized, the work equipment may be deformed or other shielding problems, which leads to the failure of recognition processing. In order to improve the recognition efficiency, the target position is recognized by using a plurality of detection angles again, to obtain a fifth recognition result. In the case that the fifth recognition result is at least one candidate component matching the component type, it is considered that the target component may exist in one of the at least one candidate component, and the number of the at least one candidate component is less than a predetermined number. By using the exhaustion idea, signal collection is performed on the at least one candidate component, to obtain candidate results corresponding to the at least one candidate component respectively, and in order to facilitate the main controller to determine the target component, collection images corresponding to the at least one candidate component are also collected and fed back to the main controller. Through the above processing, in the case that the work equipment is not recognized, it is considered that there is recognition difficulty, the candidate results and the collection images corresponding to the at least one candidate component can be obtained, to improve the inspection efficiency.

[0051] It should be noted that it is assumed that the target component is a switch valve, in the case that the work equipment is not recognized, two switch valves are recognized in the target position, and the number does not exceed a predetermined number threshold (preset as 100). Then, there is a high probability that the target component is one of the two switch valves, and the collection images and the candidate results of the two switch valves are obtained respectively and fed back to the main controller, which is beneficial to avoid the case that the inspection result cannot be obtained due to the failure to recognize the work equipment, and the response capability to the alarm condition is insufficient, which may cause secondary accident problems.

[0052] For ease of understanding, for example: the predetermined angle threshold is 360° (degrees), that is, rotate a circle in place, the first acquisition angle is initially 0°, after identifying the work equipment, rotate 90° to identify again, until the component identification result is obtained after identifying the work equipment, or the angle of rotation reaches the case where the work equipment is not identified, stop identifying the work equipment, and consider that the possible work equipment is blocked or cannot be identified. In order to maximize the identification efficiency of abnormal signals, a redundant acquisition method is used to process at least one candidate component of the same type as the target component, and the image acquisition is fed back to the main controller for processing.

[0053] Optionally, after obtaining the acquisition images and candidate results corresponding to the at least one candidate component, the main controller can compare and identify the historical images of the target component to determine the target component from the at least one candidate component.

[0054] Optionally, the signal acquisition method can be various, for example: gas sensors, pressure sensors, temperature sensors, humidity sensors, etc. can be installed to collect data of gas concentration, pressure, temperature, humidity of the inspection area.

[0055] In an optional embodiment, the target inspection equipment includes a multi-level identification model, a first-level model is a device model, and a second-level model is a component model. For example, the target device is A device, and a switch valve needs to be identified, and a component identification model of the switch valve is established to identify the device identification model of the A device. The model establishment process includes image data labeling by collecting a large number of positive and negative samples, constructing a neural network model for target identification, model training using labeled image data, and model optimization through a validation set to complete model establishment. The neural network model is only an example, and can also include a residual network model with self-attention, etc., to improve the identification accuracy.

[0056] In an optional embodiment, after obtaining the inspection result, an abnormal processing method is determined based on the inspection result; and in the case that the target inspection equipment has the ability to execute the abnormal processing method, the main controller issues a processing control strategy to the target inspection equipment.

[0057] Through the above steps, the purpose of improving the efficiency of selecting an inspection device according to the alarm level and the risk level can be achieved, the technical effect of improving the inspection efficiency by using appropriate inspection equipment is achieved, and the technical problem of unsatisfactory inspection efficiency in the related art is solved.

[0058] Based on the above embodiments and optional embodiments, the application provides an optional implementation, the target area is a well site area, which can be divided into a high-risk area, a general-risk area, a low-risk area or a non-risk area. The high-risk area includes a high-pressure operation area of the well site, and personnel are strictly prohibited from entering and leaving the high-risk area due to the risk, and even if non-personnel inspection is used, explosion-proof needs to be considered. The inspection methods that can be considered include explosion-proof unmanned aerial vehicles and explosion-proof ground robots (the explosion-proof unmanned aerial vehicles and explosion-proof ground robots can be explosion-proof unmanned aerial vehicles and explosion-proof ground robots themselves, or can be ordinary unmanned aerial vehicles and ground robots and explosion-proof devices placed to form explosion-proof unmanned aerial vehicles and explosion-proof ground robots).

[0059] The general-risk area does not need to be explosion-proof but has personal safety risks, and unmanned aerial vehicles and ground robots can be used for inspection.

[0060] The low-risk area or the non-risk area can be inspected by unmanned aerial vehicles, robots and personnel holding terminal devices. The main controller can issue a predetermined task to the terminal device held by the inspection personnel, remind and check whether the inspection personnel have done safety protection (including wearing a safety helmet) according to the requirements of the well site through the terminal device, and can set the unmanned aerial vehicles and ground robots to follow the terminal device to identify the protection state of the inspection personnel (i.e., the target object holding the terminal device) in real time and give a prompt according to the protection state. The image recognition verification system in the terminal device can also be used to perform face recognition before the inspection starts, and the recognition range includes the entire face and head, so as to confirm that the inspection personnel correctly wear the safety helmet, and the terminal device can be started to perform the inspection only after the confirmation is completed.

[0061] Figure 2 is a flowchart of an optional inspection control method provided by an embodiment of the application. A plurality of sensors are preset in a well site to monitor facilities and equipment therein. In the case of monitoring an abnormal signal, a corresponding alarm level is first determined according to the abnormal signal. For example, when the state of a well site device and a part is analyzed, it is determined that a device in a high-pressure area is suspected to have serious oil leakage, and the environmental state analysis determines that a fire is suspected to exist in the well site, and it is determined that there is a first-level alarm. For the first-level alarm, the fastest unmanned aerial vehicle inspection method needs to be used for review to determine the next response mode. At this time, the unmanned aerial vehicle can enter the high-risk area for temporary inspection regardless of whether it is explosion-proof or not, and the unmanned aerial vehicle automatically plans to reach the target position. The main controller can access the acquisition device carried by the unmanned aerial vehicle in real time to obtain the image of the operation device that sends the abnormal signal.

[0062] In the case that the abnormal signal indicates that a certain vulnerable part is about to be damaged, such as the temperature, pressure, vibration, liquid level, etc. exceeding the set value and not causing an emergency danger, the signal is determined as a secondary alarm, the danger level of the secondary alarm is less than that of the primary alarm, and the inspection equipment is selected according to the priority of the inspection mode and the level of the inspection area. In the case of a secondary alarm and a high-risk area, an unmanned aerial vehicle with a high priority and explosion-proof capability is used for inspection. In the case of a secondary alarm and a general risk area, one of the available unmanned aerial vehicles or ground robots is selected. For low-risk areas and non-dangerous areas, a robot is preferentially selected for inspection. In the case that all inspection equipment is occupied, a staff member uses a handheld terminal device for inspection.

[0063] Figure 3 An identification flowchart of an optional inspection control method according to an embodiment of the present application is shown in FIG. 1. Figure 3 In the case that the target inspection equipment is a ground robot, a specific description is given as follows: The ground robot is set with an initial attitude and is adjusted to turn after reaching the target position, so that the robot is directed to the initial angle (i.e., the first collection angle). The ground robot stores an inspection list, which indicates the inspection items at the target position. The ground robot uses a front camera to identify the work equipment. If the target is not identified in the field of view, the ground robot continues to identify after turning through a specified angle. After the work equipment is identified, the primary target identification is completed (in the case that multiple cameras are installed on the ground robot, the identification can be performed at the same collection angle). The primary target identification identifies the work equipment related to the inspection items and the attitude of the target part on the work equipment. The first pose of the work equipment is determined by a ranging sensor (binocular camera, depth camera, etc.) installed on the ground robot. The spatial pose of the target part relative to the ground robot is calculated as the collection pose based on the second pose of the target part and the work equipment.

[0064] After the collection pose is obtained, the ground robot uses an auxiliary extension method, including moving and turning the robot in front of the target part, extending the robot arm or the lifting strut of the robot, so that the front end of the robot arm or the lifting strut reaches the front of the target part. A camera is installed at the front end of the robot arm or the lifting strut to collect images. The front end of the robot arm or the lifting strut can also be provided with a gas sensor, a pressure sensor, a temperature sensor, a humidity sensor, etc. to collect data of the gas concentration, pressure, temperature, and humidity of the inspection area, complete the secondary target identification, and obtain the inspection result.

[0065] In the case that the current ground robot has the processing capability of the abnormal condition, the main controller issues a processing control strategy to the ground robot, and the ground robot executes the processing of the abnormal condition according to the indication of the processing control strategy. After the inspection task is completed, the ground robot autonomously plans a path to return to the inspection starting point and waits for the next scheduling.

[0066] The above-mentioned optional implementation at least achieves the following effects: the inspection equipment with strong response to the current abnormal condition is selected in combination with the alarm level and the risk level of the region, so as to improve the inspection processing efficiency. For the actual application scene, the device may be blocked and cannot be identified, which leads to the problem of unsatisfactory inspection efficiency. The multi-level target identification mode is adopted to improve the identification accuracy.

[0067] It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a group of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in an order different from that shown herein.

[0068] In this embodiment, an inspection control device is also provided, which is used to implement the above-mentioned embodiments and preferred embodiments, and will not be described again. As used below, the term "module" "device" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware, or a combination of software and hardware is also possible and is contemplated.

[0069] According to the embodiment of the present application, a device embodiment for implementing the inspection control method is also provided, Figure 4 is a schematic diagram of an inspection control device according to an embodiment of the present application, as Figure 4 shown, the above-mentioned inspection control device comprises a determination module 402, an abnormality processing module 404, a selection module 406, and the device will be described below.

[0070] The determination module 402 is configured to determine a target region and a plurality of risk zones included in the target region, wherein the plurality of risk zones correspond to different region risk levels, respectively.

[0071] The abnormality processing module 404 is connected with the determination module 402 and is configured to, in the case that an abnormal signal is received, determine an alarm level corresponding to the abnormal signal, a target position corresponding to the abnormal signal, and a target risk zone in which the target position is located in the plurality of risk zones, wherein the abnormal signal is a signal detected by a preset sensor that satisfies a predetermined alarm condition.

[0072] The selection module 406 is connected with the abnormality processing module 404, and is configured to determine a target inspection device from a plurality of candidate inspection devices based on the alarm level and a target risk level corresponding to the target risk area.

[0073] The determination module 402 is configured to determine a target area and a plurality of risk areas included in the target area, wherein the plurality of risk areas correspond to different risk levels respectively. The abnormality processing module 404 is connected with the determination module 402, and is configured to, in a case where an abnormality signal is received, determine an alarm level corresponding to the abnormality signal, a target position corresponding to the abnormality signal, and a target risk area in which the target position is located in the plurality of risk areas, wherein the abnormality signal is a signal detected by a preset sensor and satisfying a predetermined alarm condition. The selection module 406 is connected with the abnormality processing module 404, and is configured to determine a target inspection device from a plurality of candidate inspection devices based on the alarm level and a target risk level corresponding to the target risk area.

[0074] It should be noted that each of the above modules can be implemented by software or hardware. For example, for the latter, the modules can be located in the same processor, or in different processors in any combination.

[0075] It should be noted that the determination module 402, the abnormality processing module 404, and the selection module 406 correspond to steps S102-S106 in the embodiments, and have the same instances and application scenarios as the corresponding steps, but are not limited to the contents disclosed in the above embodiments. It should be noted that the modules can be run in a computer terminal as part of the device.

[0076] It should be noted that the optional or preferred embodiments of the present embodiment can refer to the related descriptions in the embodiments, which will not be repeated here.

[0077] The inspection control device can further include a processor and a memory, and the determination module 402, the abnormality processing module 404, and the selection module 406 are stored in the memory as program units, and the processor executes the program units stored in the memory to realize the corresponding functions.

[0078] The processor includes a core, and the core calls corresponding program units in the memory. The core can be one or more. The memory can include a non-permanent memory in a computer readable medium, a random access memory (RAM) and / or a non-volatile memory such as a read only memory (ROM) or a flash memory (flash RAM), and the memory includes at least one memory chip.

[0079] The embodiment of the present application provides a non-volatile storage medium, which stores a program, and the program is executed by a processor to implement the patrol control method.

[0080] The embodiment of the present application provides an electronic device, which includes a processor, a memory, and a program stored in the memory and executable on the processor, and the processor executes the program to implement any one of the patrol control methods. The device in the present application can be a server, a PC, or the like.

[0081] The present application also provides a computer program product, which is suitable for executing the initialization program to execute any one of the patrol control methods when executed on a data processing device.

[0082] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt a computer program product in the form of being implemented on one or more computer usable storage media (including but not limited to a disk memory, a CD-ROM, an optical memory, etc.) containing computer usable program codes.

[0083] The present application is described with reference to flowcharts and / or block diagrams of the method, device (system), and computer program product according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a means for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 The means for implementing each flow or multiple flows and / or blocks Figure 1 The means for implementing each flow or multiple flows and / or blocks

[0084] These computer program instructions can also be stored in a computer readable memory capable of guiding a computer or other programmable data processing devices to work in a specific manner, so that the instructions stored in the computer readable memory produce a product including instruction means, which implements the functions specified in the flowcharts and / or block diagrams. Figure 1one or more processes and / or blocks Figure 1 the function(s) specified in the block or blocks.

[0085] These computer program instructions can also be loaded into computer or other programmable data processing devices to cause a series of operational steps to be performed on the computer or other programmable devices to produce a computer implemented process such that the instructions which execute on the computer or other programmable devices provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more processes and / or blocks Figure 1 the function(s) specified in the block or blocks.

[0086] In one typical configuration, the computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0087] The memory can include non-persistent memory and / or volatile memory, such as random access memory (RAM) about which the computer stores information about the operating environment. The memory can also include non-volatile memory, such as read only memory (ROM), EPROM, EEPROM, or flash memory, about which the computer stores information, such as firmware for graphics processing. Examples of computer-readable media include but are not limited to phase-change RAM, static RAM, dynamic RAM, other types of random access memory, read-only memory, programmable ROM, erasable programmable ROM, electrically erasable programmable ROM, flash memory, or other memory technology, compact discs, digital versatile discs, or other optical storage, magnetic cassettes, magnetic tapes, magnetic disk storage, or other magnetic storage devices, or any other non-transmission medium that can be used to store information for access by a computing device. In accordance with the teachings herein, computer-readable media does not include transitory media, such as modulated data signals and carrier waves.

[0088] Computer-readable media includes permanent and non-permanent, removable and non-removable media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact discs read-only memory (CD-ROM), digital versatile discs (DVD) or other optical storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. In accordance with the definition herein, computer-readable media does not include transitory media, such as modulated data signals and carrier waves.

[0089] It should also be noted that the terms "comprising", "comprises", "including", "includes" or any other variation thereof are intended to cover a non-exclusive inclusion, such that a process, method, article or apparatus that comprises a list of elements does not include only those elements recited, but can also include other elements not expressly listed or inherent to such process, method, article or apparatus. Without further limitation, an element preceded by "comprises a" does not, without more constraints, foreclose the existence of additional identical elements in the process, method, article or apparatus that includes the element.

[0090] Those skilled in the art will appreciate that embodiments of the present application can be devised for a method, a system or a computer program product. Accordingly, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application can take the form of a computer program product on one or more computer readable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, etc.) embodying computer readable program code thereon for use by or in connection with an instruction execution system. For the purposes of this description, a computer usable or computer readable storage medium can be any apparatus that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.

[0091] The foregoing is merely illustrative of the embodiments of the present application and is not used to limit the present application. The present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. within the spirit and principle of the present application should be included in the scope of claims of the present application.

Claims

1. A method of patrol control, characterized by, The method comprises: determining a target area and a plurality of risk zones included in the target area, wherein the plurality of risk zones correspond to different regional risk levels respectively; in the case of receiving an abnormal signal, determining an alarm level corresponding to the abnormal signal, a target position corresponding to the abnormal signal, and a target risk zone in which the target position is located in the plurality of risk zones, wherein the abnormal signal is a signal detected by a preset sensor that meets a predetermined alarm condition; determining a target inspection device from a plurality of candidate inspection devices based on the alarm level and a target risk level corresponding to the target risk zone; wherein the determination of the target inspection device from the plurality of candidate inspection devices based on the alarm level and the target risk level corresponding to the target risk zone comprises: in the case of the alarm level being a first-level alarm, determining the target inspection device as a target unmanned aerial vehicle closest to the target position; taking the target unmanned aerial vehicle as the target inspection device; in the case of the alarm level being a second-level alarm and the target risk level being higher than a predetermined risk level, determining a first number of explosion-proof devices from the plurality of candidate inspection devices, wherein the plurality of candidate inspection devices correspond to different priorities respectively, and the risk of the first-level alarm is higher than the risk of the second-level alarm; selecting a target explosion-proof device with the highest priority from the first number of explosion-proof devices; and taking the target explosion-proof device as the target inspection device.

2. The method of claim 1, wherein, The method further comprises: in the case of not receiving the abnormal signal, obtaining a predetermined task of inspecting the target area; determining a task risk zone of the predetermined task in the plurality of risk zones based on the predetermined task; in the case of the task risk zone being a plurality of task risk zones, determining a first risk level greater than a predetermined level threshold in the regional risk levels corresponding to the plurality of task risk zones respectively; determining a first inspection device based on the first risk level.

3. The method of claim 2, wherein: in the case of the first inspection device being a plurality of first inspection devices including a terminal device, an unmanned aerial vehicle, and a ground robot, the unmanned aerial vehicle and the ground robot are arranged to follow the terminal device respectively; obtaining a first recognition result of the target object holding the terminal device obtained by the unmanned aerial vehicle performing image recognition on the target object, and a second recognition result of the target object obtained by the ground robot performing image recognition on the target object; determining a protection state of the target object based on the first recognition result and the second recognition result; in the case of the protection state not meeting a predetermined protection condition, sending a prompt information to the terminal device.

4. The method according to any one of claims 1 to 3, characterized in that, After the determination of the target inspection device from the plurality of candidate inspection devices based on the alarm level and the target risk level corresponding to the target risk zone, the following processing is performed by the target inspection device: receive a patrol strategy sent by a master controller, wherein the patrol strategy is used to indicate a target patrol device, a target position, an abnormal signal sending device, and a target component on the abnormal signal sending device for checking the abnormal signal; determine positioning information of the target component in the abnormal signal sending device when the target position is reached; determine a collection pose for signal collection of the target component based on the positioning information; obtain a patrol result by using the collection pose, and send the patrol result to the master controller.

5. The method of claim 4, wherein, The method further comprises: determine a component type of the target component when the updated second collection angle is greater than the predetermined angle threshold and the updated fourth identification result is not the abnormal signal sending device; 6. The method of claim 4, wherein, identify the target position by using a plurality of predetermined detection angles respectively, to obtain fifth identification results corresponding to the plurality of detection angles respectively; collect signals of at least one candidate component respectively when the fifth identification results corresponding to the plurality of detection angles respectively are at least one candidate component matched with the component type, and the number of the at least one candidate component is less than a predetermined number; collect images of the at least one candidate component respectively to obtain collection images corresponding to the at least one candidate component respectively; send the candidate results and the collection images corresponding to the at least one candidate component respectively to the master controller. The method further comprises:

7. The method of claim 6, wherein, determine a component type of the target component when the updated second collection angle is greater than the predetermined angle threshold and the updated fourth identification result is not the abnormal signal sending device; identify the target position by using a plurality of predetermined detection angles respectively, to obtain fifth identification results corresponding to the plurality of detection angles respectively; collect signals of at least one candidate component respectively when the fifth identification results corresponding to the plurality of detection angles respectively are at least one candidate component matched with the component type, and the number of the at least one candidate component is less than a predetermined number; collect images of the at least one candidate component respectively to obtain collection images corresponding to the at least one candidate component respectively; send the candidate results and the collection images corresponding to the at least one candidate component respectively to the master controller. The method further comprises:

8. A patrol control device characterized by comprising: determine a component type of the target component when the updated second collection angle is greater than the predetermined angle threshold and the updated fourth identification result is not the abnormal signal sending device; identify the target position by using a plurality of predetermined detection angles respectively, to obtain fifth identification results corresponding to the plurality of detection angles respectively; collect signals of at least one candidate component respectively when the fifth identification results corresponding to the plurality of detection angles respectively are at least one candidate component matched with the component type, and the number of the at least one candidate component is less than a predetermined number; collect images of the at least one candidate component respectively to obtain collection images corresponding to the at least one candidate component respectively; send the candidate results and the collection images corresponding to the at least one candidate component respectively to the master controller. The method further comprises: determine a component type of the target component when the updated second collection angle is greater than the predetermined angle threshold and the updated fourth identification result is not the abnormal signal sending device; identify the target position by using a plurality of predetermined detection angles respectively, to obtain fifth identification results corresponding to the plurality of detection angles respectively; collect signals of at least one candidate component respectively when the fifth identification results corresponding to the plurality of detection angles respectively are at least one candidate component matched with the component type, and the number of the at least one candidate component is less than a predetermined number; collect images of the at least one candidate component respectively to obtain collection images corresponding to the at least one candidate component respectively; send the candidate results and the collection images corresponding to the at least one candidate component respectively to the master controller. The method further comprises: determine a component type of the target component when the updated second collection angle is greater than the predetermined angle threshold and the updated fourth identification result is not the abnormal signal sending device; identify the target position by using a plurality of predetermined detection angles respectively, to obtain fifth identification results corresponding to the plurality of detection angles respectively; collect signals of at least one candidate component respectively when the fifth identification results corresponding to the plurality of detection angles respectively are at least one candidate component matched with the component type, and the number of the at least one candidate component is less than a predetermined number; collect images of the at least one candidate component respectively to obtain collection images corresponding to the at least one candidate component respectively; send the candidate results and the collection images corresponding to the at least one candidate component respectively to the master controller. The abnormality processing module is configured to, in a case where an abnormal signal is received, determine an alarm level corresponding to the abnormal signal, a target position corresponding to the abnormal signal, and a target risk area in which the target position is located in the multiple risk areas. The selection module is configured to determine a target inspection device from multiple candidate inspection devices based on the alarm level and a target risk level corresponding to the target risk area. In a case where the alarm level is a first alarm, the selection module is configured to determine the target inspection device as a target unmanned aerial vehicle closest to the target position, and determine the target unmanned aerial vehicle as the target inspection device. In a case where the alarm level is a second alarm and the target risk level is higher than a predetermined risk level, the selection module is configured to determine a first number of explosion-proof devices from the multiple candidate inspection devices, wherein the multiple candidate inspection devices correspond to different priorities, the risk of the first alarm is higher than the risk of the second alarm, select a target explosion-proof device with the highest priority from the first number of explosion-proof devices, and determine the target explosion-proof device as the target inspection device.

9. A non-volatile storage medium, comprising: The non-volatile storage medium stores a plurality of instructions, and the instructions are adapted to be loaded and executed by the processor to perform the inspection control method in any one of claims 1 to 7.

Images