Control Method, System, Device, Electronic Device and Storage Medium for Patrol Inspection of Chemical Industry Production Plant Area by Drone

Abstract

The factory patrol inspection method is easily affected by weather, space, equipment height, etc. A control method, control system, control device, and electronic device are provided to improve the efficiency of patrol inspection and the freedom of patrol inspection. 【Solution means】A control method for drone-based patrol inspection of a chemical industrial production plant area, which determines a first drone for executing a patrol inspection task in a target scene, obtains data of a target object collected by the first drone, determines the state of the target object in the target scene based on the data, and outputs presentation information that matches the preset state in the target scene when the state indicates that the target object is in the preset state in the target scene. Thereby, the efficiency of patrol inspection can be improved, the freedom of patrol inspection can be improved, and the normal operation of the chemical industrial production plant area and the safety of the chemical industrial production plant area can be guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent chemical fiber industry, and particularly relates to a control method and a control device for the patrol inspection of a chemical industrial production plant area by a drone.

Background Art

[0002] In a chemical industrial production plant area, there are various large-scale devices and various small-scale devices arranged. Usually, in order to maintain the normal operation of the plant area, it is necessary to conduct a patrol inspection of various large-scale devices and various small-scale devices in the plant area. However, the conventional patrol inspection method is easily affected by weather, space, the height of the devices, etc., so that the efficiency of the patrol inspection becomes low or the patrol inspection cannot be carried out. Therefore, how to realize an efficient patrol inspection and improve the safety of the plant area has become a technical problem to be solved.

Summary of the Invention

[0003] The present disclosure provides a control method, a system, a device, an electronic device, and a storage medium for the patrol inspection of a chemical industrial production plant area by a drone. According to a first aspect of the present disclosure, there is provided a control method for the patrol inspection of a chemical industrial production plant area by a drone, comprising: determining a first drone for executing a preset patrol inspection task in a target scene, the first drone being responsible for the preset patrol inspection task of the chemical industrial production plant area; acquiring data of a target object collected by the first drone in the target scene; determining the state of the target object in the target scene based on the data of the target object; when the state indicates that the target object is in a preset state in the target scene, outputting prompt information that matches the preset state in the target scene; for the preset patrol inspection task, When the target scene belongs to the active patrol inspection scene and the target object is a device, the preset patrol inspection task is a regular patrol inspection task or a sampling patrol inspection task. When the target scene belongs to the active patrol inspection scene and the target object is a person, the preset patrol inspection task is a regular patrol inspection task or a sampling patrol inspection task. When the target scene belongs to the passive patrol inspection scene and the target object is a device, the preset patrol inspection task is exclusively the first specialized patrol inspection task for the target object. When the target scene belongs to the passive patrol inspection scene and the target object is a person, a control method is provided in which the preset patrol inspection task is a second specialized patrol inspection task created based on the requirements of the target object.

[0004] According to a second aspect of the present disclosure, there is provided a control system for patrolling a chemical industrial production plant area by a drone, a first drone for executing a preset patrol inspection task in a target scene, determining a first drone responsible for the preset patrol inspection task in the chemical industrial production plant area, obtaining data of a target object collected by the first drone in the target scene, determining the state of the target object in the target scene based on the data of the target object, and when the state indicates that the target object is in a preset state in the target scene, outputting presentation information matching the preset state in the target scene; a control device; a first drone for executing a preset patrol inspection task, and a control system including the same.

[0005] According to a third aspect of the present disclosure, there is provided a control device for patrolling a chemical industrial production plant area by a drone, a first drone for executing a preset patrol inspection task in a target scene, a first determination module for determining a first drone responsible for the preset patrol inspection task in the chemical industrial production plant area, An acquisition module that acquires data of a target object collected by a first drone in a target scene; A second determination module that determines the state of the target object in the target scene based on the data of the target object; When the state indicates that the target object is in a preset state in the target scene, an output module that outputs presentation information matching the preset state in the target scene, to provide a control device.

[0006] Here, regarding the preset patrol inspection task, When the target scene belongs to an active patrol inspection scene and the target object is a device, the preset patrol inspection task is a regular patrol inspection task or a sampling patrol inspection task; When the target scene belongs to an active patrol inspection scene and the target object is a person, the preset patrol inspection task is a regular patrol inspection task or a sampling patrol inspection task; When the target scene belongs to a passive patrol inspection scene and the target object is a device, the preset patrol inspection task is exclusively a first specialized patrol inspection task for the target object; When the target scene belongs to a passive patrol inspection scene and the target object is a person, the preset patrol inspection task is a second specialized patrol inspection task created based on the requirements of the target object.

[0007] According to a fourth aspect of the present disclosure, an electronic device, At least one processor; A memory communicably connected to the at least one processor, including: Instructions executable by the at least one processor are stored in the memory, and the instructions are executed by the at least one processor to cause the at least one processor to execute any method in the embodiments of the present disclosure, to provide an electronic device.

[0008] According to a fifth aspect of the present disclosure, there is provided a computer-readable non-transitory storage medium storing computer instructions for causing a computer to execute any of the methods in the embodiments of the present disclosure. According to the technology of the present disclosure, first, a first drone for executing a preset patrol inspection task in a target scene is determined. Next, data of a target object is collected by the first drone. Next, the state of the target object in the target scene is determined based on the data of the target object. When the state indicates that the target object is in a preset state in the target scene, presentation information matching the preset state in the target scene is output. In this way, manual patrol inspection is not required, and ground patrol inspection equipment is not required either. The drone can complete an effective patrol inspection of the chemical industrial production plant area, improve the efficiency of the patrol inspection, improve the freedom of the patrol inspection, make it easy to grasp the state of the target object in the chemical industrial production plant area, and take corresponding solutions when the state of the target object is an abnormal state, thereby ensuring the normal operation of the chemical industrial production plant area and the safety of the chemical industrial production plant area.

[0009] It should be understood that the content described in the Summary of the Invention section does not limit the key points or important features of the embodiments of the present disclosure, nor does it limit the scope of the present disclosure. Other features of the present disclosure will be easily understood from the following description.

[0010] The above and other features, advantages and aspects of each embodiment of the present disclosure will become more apparent by referring to the accompanying drawings and the following detailed description. In the drawings, the same or similar reference numerals indicate the same or similar elements.

Brief Description of the Drawings

[0011]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Embodiments for Carrying Out the Invention

[0012] Hereinafter, exemplary embodiments of the present disclosure will be described with reference to the drawings. Although various details of the embodiments of the present disclosure are included for ease of understanding, it should be understood that they are merely exemplary. Therefore, those skilled in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of known functions and structures are omitted in the following description.

[0013] Terms such as "first", "second", and "third" in the embodiments, claims, and the above drawings of the present disclosure are for distinguishing similar objects and do not explain a specific order or sequence before and after. Also, the terms "include" and "have" and any variations thereof mean non-exclusive "include", for example, it is intended to include a series of steps or units. A method, system, product, or device is not limited to the explicitly listed steps or units, and can include steps or units not explicitly listed, or other steps or units inherent to these processes, methods, products, or devices.

[0014] In the related art, due to the large area of the chemical industrial production plant area, the manual inspection route is long, the efficiency is unstable, and it is difficult to conduct inspections during bad weather. In addition, in the chemical industrial production plant area, various large-scale devices and various small-scale devices are arranged. Some of the large-scale devices are high in height, limited in space, and noisy, so it is difficult to obtain device status and device data through manual inspections, and the devices are in a "passive state". The conventional inspection method has defects such as long time intervals, dead ends in inspections, and strong subjectivity. Moreover, manual inspections have high requirements for the skills of inspection staff. Due to the presence of harmful factors such as noise and toxic gases in the chemical industrial production plant area, the safety of inspection staff is low.

[0015] In the related art, for some important devices in the chemical industrial production plant area, in order to determine the device status and ensure safe operation within the maintenance period, mainly the staff of the work shift conduct regular inspections, or monitor them through a data collection and monitoring control system (Supervisory Control And Data Acquisition, SCADA), so the inspection efficiency is low. In addition, when it is necessary for the staff to work at heights, it is necessary to monitor the working status of the staff in real time to ensure the safety of the staff during work. However, the method of arranging cameras has many limitations and low degrees of freedom, and it is impossible to monitor the status of all staff in real time.

[0016] The present disclosure provides a control method, system, and device for inspecting a chemical industrial production plant area by a drone to at least partially solve one or more of the above problems and other potential problems. By inspecting the chemical industrial production plant area by a drone, the inspection efficiency can be improved, thus guaranteeing the normal operation of the chemical industrial production plant area and the safety of the chemical industrial production plant area.

[0017] Embodiments of the present disclosure provide a control method for the patrol inspection of a chemical industrial production plant area by a drone. FIG. 1 is a flowchart of a control method for the patrol inspection of a chemical industrial production plant area by a drone according to an embodiment of the present disclosure, and the control method for the patrol inspection of a chemical industrial production plant area by the drone can be applied to a control device for the patrol inspection of a chemical industrial production plant area by a drone. The control device for the patrol inspection of a chemical industrial production plant area by the drone is attached to an electronic device. The electronic device includes, but is not limited to, fixed devices and / or mobile devices. For example, the fixed device includes, but is not limited to, a server. The server may be a cloud server or a general server. For example, the mobile device includes, but is not limited to, a mobile phone, a tablet computer, etc. In some possible embodiments, the control method for the patrol inspection of a chemical industrial production plant area by the drone may be realized by a processor calling computer-readable instructions stored in a memory. As shown in FIG. 1, the control method for the patrol inspection of a chemical industrial production plant area by the drone includes the following. S101: Determine a first drone for executing a preset patrol inspection task in the target scene, and the first drone is responsible for the preset patrol inspection task in the chemical industrial production plant area. S102: Obtain the data of the target object collected by the first drone in the target scene. S103: Determine the state of the target object in the target scene based on the data of the target object. S104: When the state indicates that the target object is in a preset state in the target scene, output prompt information that matches the preset state in the target scene.

[0018] In an embodiment of the present disclosure, the target scene includes, but is not limited to, a working scene in a limited space, a working scene at a high place, a certain special working scene, a production detection scene, a packaging detection scene, etc. In the case of a chemical industrial production plant area for producing a certain material, the target scene may be divided into a plurality of scenes based on the distribution of the chemical industrial production plant area for producing a certain material, or may be divided into a plurality of scenes based on the packaging flow of the chemical industrial production plant area for producing a certain material, and the chemical industrial production plant area for producing a certain material may be intelligently distinguished into a plurality of scenes by a control device. The present disclosure does not limit the type of the material. In an embodiment of the present disclosure, the preset patrol inspection task may be a task generated by the control device based on the target scene, or may be a task generated based on a manually input command. The above is only an exemplary description, and does not limit all possible acquisition methods of the preset patrol inspection task, and will not be enumerated comprehensively here.

[0019] Exemplarily, based on the map of the factory area, the control device divides the chemical industrial production plant area used for the production of chemical fibers into a plurality of scenes, such as scene 1 related to the outside of the factory building and scene 2 related to the inside of the factory building. The patrol inspection task generated by the control device based on scene 1 is a patrol inspection task for the equipment outside the factory building, a patrol inspection task for the safety outside the factory building, and a patrol inspection task for the abnormality outside the factory building. The patrol inspection task generated by the control device based on scene 2 is a patrol inspection task for the equipment inside the factory building, a patrol inspection task for the safety inside the factory building, and a patrol inspection task for the abnormality inside the factory building. Here, the preset patrol inspection task can include the name of the patrol inspection task, the content of the patrol inspection task, the route of the patrol inspection task, etc. Here, the patrol inspection task route is obtained based on the layout map of the chemical industrial production plant area stored in the data source of the control device.

[0020] FIG. 2 shows a schematic diagram of the first drone. As shown in FIG. 2, the first drone may be a light-load drone, which is a drone capable of carrying a light load. The load of the light-load drone is usually several grams to several hundred grams, and the light-load drone is equipped with a high-definition camera, a speaker, etc. Specifically, the light-load drone may be equipped with sensors such as a temperature sensor, a microphone, a gas detection sensor, an altitude sensor, and a speed sensor based on a preset patrol inspection task, and may also be equipped with other devices such as a laser scanner and a Global Positioning System (GPS) based on the preset patrol inspection task. The light-load drone can provide training data for model training as a data collector in the previous stage, and then can be used as an input for real-time monitoring. Specifically, training data, which is at least one type of image data, audio data, and video data collected by the first drone, is obtained, and the training data is input into a model to be trained for training to obtain a target model.

[0021] In an embodiment of the present disclosure, various large-scale devices, various small-scale devices, and various special devices are arranged in the chemical industrial production plant area.

[0022] In an embodiment of the present disclosure, the target object includes, but is not limited to, devices, staff, animals, floating objects in the air, etc. Here, the target object may be preset in the control device. For example, when the target object is the staff, the first drone collects only data related to the staff.

[0023] In some embodiments, the data of the target object can include image data, audio data, video data, sensor data, position data, etc. Here, the data of the target object collected by the first drone may be directly stored in the data source of the first drone or directly uploaded to the control device.

[0024] In some embodiments, the presented information is obtained by the first drone based on the target object and the target scene. The presented information is for indicating the current state of the target object. Exemplarily, when the target object is an inspection staff, presented information regarding emergency rescue is output, and the presented information can include information such as the person in need of rescue, the emergency phone number, the location of the medical room, etc. When the target object is a device, if a certain device emits abnormal sounds and needs to be inspected, presented information regarding inspection is output, and the presented information can include information such as the recommended inspector, inspection tools, inspection plan, etc. When the target object is the humidity of the workplace, if the humidity of the workplace is lower than a predetermined value, presented information regarding the humidity of the workplace is output, and the presented information can include information such as the current humidity of the workplace, the ideal humidity of the workplace, the humidification area, and the humidification amount, etc. When the target object is an abnormal item, if it is detected that there are floating plastic bags above the warehouse storage area, presented information regarding cleaning is output, and the presented information can include information such as the type of the abnormal item, the impact index on the safety of the factory area of the abnormal item, the list of cleaners, the cleaning urgency, etc.

[0025] In some embodiments, presented information that matches a preset state in the target scene is output. This includes transmitting the presented information to devices near the target object, or transmitting the presented information to the control system, or transmitting the presented information to executable devices or staff. The presented information can set different presentation states such as voice presentation, alarm presentation, light presentation, etc. Here, the presented information may be presented information on the normal operation state of the target object or presented information on the abnormal operation state. Specifically, when the presented information is presented information on the normal operation state of the target object, the presented information can be displayed in the background. When the presented information is presented information on the abnormal operation state of the target object, the presented information is directly displayed on the front-end page, and other presentation states can be added.

[0026] Thus, first, determine a first drone for executing a preset patrol inspection task in the target scene. Next, collect data of the target object by the first drone. Then, determine the state of the target object in the target scene based on the data of the target object. When the state indicates that the target object is in a preset state in the target scene, output presentation information that matches the preset state in the target scene. In this way, manual patrol inspection is not required, and ground patrol inspection equipment is not required either. The drone can perform an effective patrol inspection on the chemical industrial production plant area, improving the efficiency of the patrol inspection, improving the freedom of the patrol inspection, making it easier to grasp the state of the target object in the chemical industrial production plant area, making it easier to take corresponding solutions when the state of the target object is an abnormal state, and guaranteeing the normal operation and safety of the chemical industrial production plant area.

[0027] In some embodiments, the follow-up command may be an audio command or an operation command issued by the patrol inspection staff to the drone.

[0028] In some embodiments, determining a first drone for executing a preset patrol inspection task in the target scene includes, in response to receiving a follow-up command transmitted from a drone, determining the drone that transmitted the follow-up command as the first drone. The follow-up command is a command issued by the patrol inspection staff to the drone that transmitted the follow-up command, and is for instructing the drone to operate following the patrol inspection staff. The follow-up command includes information representing the preset patrol inspection task.

[0029] In some embodiments, the following instruction may be an instruction generated by the control system based on the patrol task. The following instruction may include information such as the following target, following route, and patrol target. The following target information may be one or more. When there are multiple following targets, priorities may be set for the multiple following targets, and the drone preferentially follows the following target with a higher priority. Here, determining the following target may include obtaining an image of the following target and determining the target following target based on the image of the following target, or obtaining the characteristics of the following target and determining the target following target based on the characteristics of the following target.

[0030] In some embodiments, the following instruction may be an instruction generated by the patrol staff directly calling a nearby idle drone. The drone can directly receive the following instruction and report the following state and following target to the system. Specifically, the drone needs to collect an image of the patrol staff, identify the image, obtain the identification result, analyze the identification result to determine whether the patrol staff has the authority. When the patrol staff has the authority, the drone receives the following instruction and reports it to the system, updates the current operating state from the idle state to the operating state, uploads the movement trajectory in real time, or the drone uploads the following instruction of the patrol staff to the control system. After receiving the following permission instruction returned by the control system based on the following instruction, the drone follows the patrol staff to perform work.

[0031] In response to receiving the following instruction transmitted from the drone, the drone that transmitted the following instruction is determined as the first drone. The patrol task can be flexibly assigned to the drone, and by improving the utilization rate of the drone patrol, the patrol efficiency can be improved.

[0032] In some embodiments, determining a first drone for performing a preset patrol inspection task in the target scene includes, in response to receiving a work request transmitted from a terminal, determining, based on the work request and the status information of candidate drones, a first drone from the candidate drones for performing a preset patrol inspection task in the target scene for the terminal, where the work request includes information representing the preset patrol inspection task.

[0033] In some embodiments, the terminal may be a device such as a mobile phone, a notebook computer, or a personal computer. The terminal may be a dedicated terminal device within a control system for the patrol inspection of a chemical industrial production plant area by drones, or may be a terminal device related to a control system for the patrol inspection of a chemical industrial production plant area by drones.

[0034] In some embodiments, the work request may be a work request generated by manually inputting information, may be a work request generated by a control device based on the operation data of each current device, or may be a work request preset by a control system for the patrol inspection of a chemical industrial production plant area by drones. The work request may include information such as the number of required drones, the model numbers of the required drones, the work time point, the work duration, and the devices mounted on the drones.

[0035] In some embodiments, the status information of the drone may include drone operation status information, drone-mounted device information, etc. The drone operation status information may include "operating", "standing by", "under maintenance", "charging", etc., and the drone-mounted device information may include the type of the device mounted on the drone, the model number of the device mounted on the drone, the number of devices mounted on the drone, etc.

[0036] In some embodiments, the candidate drone may be any drone that can be scheduled at the chemical industrial production site, or all or some of the drones that are in an idle state at the chemical industrial production site, or a certain type of drone that is in an idle state at the chemical industrial production site, such as a light-load drone.

[0037] In this way, in response to receiving the work request sent from the terminal, a first drone is determined based on the work request and the status information of the candidate drone. The patrol inspection task can be flexibly assigned to the drone, and the utilization rate of the drone's patrol inspection is improved to improve the patrol inspection efficiency.

[0038] In some embodiments, determining a first drone for executing a preset patrol inspection task in the target scene includes, based on the status information of the candidate drone, determining a first drone for executing a preset patrol inspection task in the target scene from the candidate drones in combination with the cycle of the patrol inspection.

[0039] In some embodiments, the cycle of the patrol inspection may be determined based on the chemical industrial production working conditions by a control system for the patrol inspection of the chemical industrial production plant area by the drone. The control system for the patrol inspection of the chemical industrial production plant area by the drone may determine different preset patrol inspection tasks based on the chemical industrial production working conditions.

[0040] Here, the number of the first drones is not limited. N first drones may follow N staff members, or M first drones may follow one staff member. The M first drones are respectively located around the staff member and can execute data collection for different patrol inspection tasks.

[0041] In this way, based on the status information of the candidate drones, a first drone for executing a preset patrol inspection task in the target scene is determined in accordance with the cycle of the patrol inspection. By improving the efficiency of the drone in executing the patrol inspection task, the safety of the chemical industrial production plant area can be guaranteed.

[0042] In some embodiments, the preset patrol inspection task may include a patrol inspection of the outside of the factory building, a patrol inspection of the inside of the factory building, a patrol inspection of production safety, and a patrol inspection of staff work.

[0043] In some embodiments, the preset patrol inspection task includes at least one of the following. When the target scene belongs to an active patrol inspection scene and the target object is a device, the preset patrol inspection task is a regular patrol inspection task or a sampling patrol inspection task; when the target scene belongs to an active patrol inspection scene and the target object is a person, the preset patrol inspection task is a regular patrol inspection task or a sampling patrol inspection task; when the target scene belongs to a passive patrol inspection scene and the target object is a device, the preset patrol inspection task is a first specialized patrol inspection task specifically for the target object; when the target scene belongs to a passive patrol inspection scene and the target object is a person, the preset patrol inspection task is a second specialized patrol inspection task formulated based on the requirements of the target object.

[0044] In some embodiments, the active patrol inspection scenario can include regular patrol inspection tasks and sampling patrol inspection tasks. The objects of the active patrol inspection scenario may be staff or equipment. The regular patrol inspection task is a task preset by the control system for the drone to patrol the chemical industrial production plant area according to the actual situation, that is, when it is detected that the trigger condition of the regular patrol inspection task is met, the regular patrol inspection task is distributed. The trigger conditions can include triggering the regular patrol inspection task within a predetermined time, triggering the regular patrol inspection task at a fixed time, etc. The sampling patrol inspection task is a task randomly distributed by the control system for the drone to patrol the chemical industrial production plant area according to the actual situation. The content of the regular patrol inspection task is preset, and the content of the sampling patrol inspection task is randomly generated.

[0045] In some embodiments, the passive patrol inspection scenario can include receiving warning information sent from device A, receiving an active call from patrol inspector a, etc.

[0046] In some embodiments, the passive patrol inspection scenario can include a first specialized patrol inspection task and a second specialized patrol inspection task. The first patrol inspection task is specifically a patrol inspection task for the object. Specifically, when the object is a device, the first specialized patrol inspection task is a task set based on the attributes of the device. For example, it is a patrol inspection task set for detecting the temperature of the device. The second specialized patrol inspection task is a patrol inspection task generated based on the requirements of the object. Specifically, when the object is a person, the second specialized patrol inspection task is a task generated based on the requirements of the staff. For example, it is a patrol inspection task such as "Please perform pressure detection on L devices" issued by the staff.

[0047] In some embodiments, the specialized patrol inspection task may include the drone guiding the patrol inspection staff or the drone executing commands from the patrol inspection staff to perform tasks such as shooting, recording, and data analysis.

[0048] In some embodiments, the preset state includes a device abnormal state, and the target object includes a target device. When the state indicates that the target object is in the preset state in the target scene, outputting prompt information matching the preset state in the target scene includes, when the state indicates that the target device is in the device abnormal state in the target scene, outputting prompt information matching the device abnormal state in the target scene.

[0049] In some embodiments, the device abnormal state can include the device stopping operation, device operation error, some parts of the device falling off, abnormal sound of the device, and abnormal vibration of the device, etc.

[0050] In some embodiments, the target scene may be a scene restricted by space elements, a scene restricted by height elements, or a scene restricted by a special environment. Exemplarily, the target scene is a heavy rain weather, the target object is a large device outside the factory building, a sampling patrol inspection task is generated based on the target scene and the target object, a first drone for executing the sampling patrol inspection task in the target scene is determined, data of the target object collected by the drone is obtained, the state of the target object in the target scene is determined based on the data of the target object, when the state indicates that the target object is in the device abnormal state in the target scene, warning prompt information is uploaded to the system, and when the state indicates that the target object is in the device normal state in the target scene, the task continues to be executed.

[0051] In this way, when the state indicates that the target device is in a device abnormal state in the target scene, presentation information that matches the device abnormal state in the target scene is output. The state information of the target object can be accurately obtained in a complex scene, contributing to the improvement of the working efficiency in the chemical industrial production plant area.

[0052] In an embodiment of the present disclosure, the preset state includes a staff abnormal state, and the target object includes a target staff. When the state indicates that the target object is in a preset state in the target scene, outputting presentation information that matches the preset state in the target scene means that when the state indicates that the target staff is in a staff abnormal state in the target scene, it includes outputting presentation information that matches the staff abnormal state in the target scene.

[0053] In some embodiments, the staff abnormal state can include that the staff is in a dangerous environment, the behavior of the staff is abnormal, the safety protection device worn by the staff is loose, and the staff is not wearing a safety protection device, etc.

[0054] In some embodiments, the target staff may be a staff member in this factory area, or may be a person other than the staff in this factory area, such as a person who has entered the factory area.

[0055] In some embodiments, the target scene may be a scene restricted by elements of space, a scene restricted by elements of height, or a scene restricted by a special environment. Exemplarily, the target scene is a high tower, and the target object is a staff member working on a high tower outside a factory building. Based on the target scene and the target object, a regular inspection task is generated, a first drone for executing the regular inspection task in the target scene is determined, data of the target object collected by the drone is obtained, the state of the target object in the target scene is determined based on the data of the target object, and when the state indicates that the target object is in a staff abnormal state in the target scene, warning prompt information is uploaded to the system, and when the state indicates that the target object is in a staff normal state in the target scene, the task continues to be executed.

[0056] In this way, when the state indicates that the target staff is in a staff abnormal state in the target scene, prompt information matching the staff abnormal state is output in the target scene. It is possible to accurately obtain the state information of the target object in a complex scene, which contributes to improving the safety of the staff in the chemical industrial production plant area.

[0057] In the embodiments of the present disclosure, determining the state of the target object in the target scene based on the data of the target object includes obtaining a known correspondence relationship including at least the relationship between each state of the target object and the interval data corresponding thereto, and analyzing the state corresponding to the data of the target object in the target scene based on the known correspondence relationship. Here, the state can include an abnormal state or a normal state.

[0058] In some embodiments, the known correspondence relationship is used to record data information in each state of the target object. The data information may be a fixed value, a numerical range, or a plurality of numerical ranges. The form of the known correspondence relationship may be shown in the form of a table. The known correspondence relationship is usually stored in the data source of the control system for the patrol inspection of the chemical industrial production plant area by the drone. Here, the known correspondence relationship can be added, deleted, modified, and updated.

[0059] In this way, the known correspondence relationship can provide data support to determine the state of the target object in the target scene, and contribute to improving the accuracy of determining the target object in the target scene.

[0060] In the embodiments of the present disclosure, determining the state of the target object in the target scene based on the data of the target object includes inputting the data of the target object in the target scene into the state analysis model, and obtaining the state of the target object in the target scene output from the state analysis model. The state analysis model is obtained by training based on the known correspondence relationship and is used to predict the state of the target object in the target scene.

[0061] In some embodiments, the training process of the state analysis model includes obtaining training data that is the known correspondence relationship, inputting the training data into the model to be trained for training, and obtaining the state analysis model. The state analysis model is used to predict the state of the target object in the target scene.

[0062] In some embodiments, the data of the target object in the target scene is collected by a drone. The data of the target object in the target scene may be any data among image data, audio data, text data, and video data. Exemplarily, the data of the target object collected by the drone is an image indicating that a device part has fallen off, and the target object data is input into a state analysis model to obtain an analysis result that the device is in an abnormal state.

[0063] In this way, the state of the target object can be predicted based on the data of the target object collected by the drone by the state analysis model, and the efficiency of abnormal processing can be improved.

[0064] In an embodiment of the present disclosure, the control method for the drone to perform a patrol inspection of a chemical industrial production plant area further includes establishing a correspondence between the data of the target object in the target scene and the state of the target object, and updating the known correspondence based on the correspondence.

[0065] In some embodiments, establishing the correspondence between the data of the target object in the target scene and the state of the target object can be realized by monitoring and recording the working process by the drone. The drone monitors and records the working process, obtains the working experience knowledge of the target object in the target scene, and stores the working experience knowledge in an experience library. The experience library is located at the terminal of a control system for the drone to perform a patrol inspection of a chemical industrial production plant area.

[0066] In some embodiments, data of a target object in a target scene is collected by a drone, and the data may be any data among image data, video data, and audio data. The data of the target object is analyzed to obtain the state of the target object, a known correspondence relationship is obtained, and based on the known correspondence relationship, it is compared with the data and state of the target object, and a comparison result is obtained. Based on the comparison result, the known correspondence relationship is updated.

[0067] In this way, by updating in real time the data of the target object in the target scene collected by the drone, the accuracy of determining the state of the target object can be improved.

[0068] In an embodiment of the present disclosure, a control method for the drone to conduct a patrol inspection of a chemical industrial production plant area further includes receiving an article request sent from a first drone, scheduling a second drone for the first drone based on the article request, and the second drone transporting a target article to a patrol inspection staff corresponding to the first drone based on the article request. Here, the target article is the article indicated in the article request.

[0069] In some embodiments, the article request may include the model number of the required article, the number of required articles, and the location of the required articles. FIG. 3 shows a schematic diagram of the second drone. As shown in FIG. 3, the second drone is a transport drone. The second drone is for transporting the articles required by the patrol inspection staff.

[0070] In actual applications, the second drone can communicate directly with the first drone. The second drone directly receives the item request sent from the first drone, determines the location of the target item based on the item request, notifies the shipping staff to prepare the target item, and determines the optimal route, which is the shortest route or the safest route when flying to the first drone. When it is detected that the target item has been loaded onto the second drone, the target item is transported to the patrol staff corresponding to the first drone based on the optimal route. Moreover, the second drone can report its status information to the system background in real time so that the system background records the status of the second drone in real time. Here, the second drone can determine whether the target item has been loaded onto the second drone based on the collected voice data. For example, when the shipper loads the target item onto the mounting platform of the second drone, the shipper says, "Since the item XX has already been loaded, you can depart," and after the second drone recognizes the voice data, it determines that the target item has been loaded onto the second drone. Here, the second drone can determine whether the target item has been loaded onto the second drone based on the weight sensor arranged on the second drone. For example, the second drone detects the weights at the first time and the second time by the weight sensor, and if the change amount of the weight matches the weight of the target item, it can be determined that the target item has already been loaded onto the second drone. Also, when the second drone collects image data on the mounting platform of the second drone by a camera and recognizes the target item based on the image data, it can be determined that the target item has already been loaded onto the second drone.

[0071] Figure 4 shows a schematic diagram of the collaborative work between the first drone and the second drone. As shown in Figure 4, the target scene is high-altitude work, and the target object is the patrol inspection staff. The patrol inspection staff notices that the tools they have are insufficient, calls the first drone, and issues an audio command saying, "One type A wrench, two type B wrenches, and eight type W screws are needed." The first drone collects the audio of the patrol inspection staff through the receiver, converts the audio into a command text, and sends the command text to the second drone. The second drone receives the command text sent from the first drone and executes tasks based on the command text. Specifically, the second drone determines the location of the items based on the command text, then flies to the item storage area, and then broadcasts a message about the required items. The shipping staff prepares the items based on the broadcast audio and loads the required items onto the second drone. Here, the command text can further include information such as the location of the first drone and the task route. The first drone and the second drone can communicate with each other. The present disclosure does not limit the communication method between the first drone and the second drone.

[0072] In some embodiments, the second drone also has a voice recognition function, can recognize the patrol inspection staff, and can recognize commands issued by the patrol inspection staff. Exemplarily, when the second drone has loaded the required items and arrives near the patrol inspection staff, the patrol inspection staff can issue an audio command saying, "Fly lower, please."

[0073] In this way, by using the technical solution of combining the first drone and the second drone, the intelligence of the drone for patrolling the chemical industrial production plant area can be improved, and thus the efficiency of the drone for patrolling the chemical industrial production plant area can be improved.

[0074] In an embodiment of the present disclosure, a first voice recognition model is provided in the first drone, and the target object includes the patrol staff. The control method for the patrol inspection of the chemical industrial production plant area by the drone further includes transmitting the item request to the background of the system when the first drone receives the voice of the patrol staff and the first voice recognition model recognizes the item request of the patrol staff.

[0075] In some embodiments, when the first drone receives the voice of the patrol staff and the first voice recognition model recognizes the item request of the patrol staff, the item request is transmitted to the background of the system. Also, the position of the first drone and the identifier of the patrol staff may be transmitted.

[0076] Here, the first voice recognition model can extract and recognize the staff's audio, and the recognized audio may be the voice of staff in different regions or the voice in other languages.

[0077] In this way, when the first drone receives the voice of the patrol staff and the first voice recognition model recognizes the item request of the patrol staff, the item request is transmitted to the background of the system. The commands of the patrol staff can be collected in real time, contributing to improving the execution efficiency of the drone's patrol inspection task.

[0078] In an embodiment of the present disclosure, a second voice recognition model is provided in the first drone. The target object includes the target device. The control method for the patrol inspection of the chemical industrial production plant area by the drone further includes, during the execution of the preset patrol inspection task by the first drone, inputting the collected sound of the target device into the second voice recognition model, and when the second voice recognition model analyzes and obtains an item request that matches the failure of the target device, transmitting the item request to the background of the system.

[0079] In some embodiments, when the first drone receives the voice of the patrol staff and analyzes the item requirements obtained by matching with the failure of the target device by the second voice recognition model, the item requirements are sent to the background of the system. Alternatively, the position of the first drone and the identifier of the patrol staff may be sent.

[0080] In some embodiments, the second voice recognition model can extract the audio of the device and analyze the audio of the device to determine the state of the device in the target scene. Specifically, the second voice recognition model can also remove the noise in the audio of the device.

[0081] Here, analyzing the audio of the device can include analyzing the intensity of the operating sound of the device, analyzing the frequency of the device operation, and analyzing the fluctuations of the device operation. For certain special devices, the intensity, frequency, and fluctuations of the operating sound in different operating states are different. Also, when the device is in an abnormal state, the sound, frequency, and fluctuations of the device are also different. By analyzing the audio of the device, information such as the necessary maintenance tools and damaged components can be obtained.

[0082] In this way, during the execution of the preset patrol inspection task by the first drone, the collected sound of the target device is input into the second voice recognition model, the second voice recognition model analyzes the item requirements that match the failure of the target device, and by sending the item requirements to the background of the system, data support can be provided to determine the device state, contributing to the improvement of the work efficiency of the patrol staff.

[0083] In the embodiments of the present disclosure, the control method for the drone to patrol the chemical industrial production plant area further includes determining a patrol inspection route for the first drone to execute a preset patrol inspection task, and sending the patrol inspection route to the first drone so that the first drone executes the preset patrol inspection task based on the patrol inspection route.

[0084] In some embodiments, the inspection route includes the names of the devices to be inspected, the inspection sequence, and the residence time.

[0085] Here, the inspection route is the optimal inspection route created for the first drone and can be obtained by a route planning model. The route planning model generates the inspection route of the first drone based on the status information of each drone, the inspection results and inspection requirements returned from other known drones.

[0086] In this way, the inspection route for the first drone to execute the preset inspection task is determined, and the inspection route is sent to the first drone so that the first drone executes the preset inspection task based on the inspection route. Thereby, the efficiency of drone inspection can be improved.

[0087] In an embodiment of the present disclosure, the object includes an inspection staff. The control method for the inspection of the chemical industrial production plant area by the drone is to receive the control command of the inspection staff sent from the first drone and the execution status record of the first drone for the control command. Here, the control command is received during the execution of the preset inspection task by the first drone, and the first drone can identify that the inspection staff has the control authority to issue the control command, and further includes storing the control command of the inspection staff and the execution status record corresponding to the control command.

[0088] In some embodiments, the execution status record can record the working process, working time, and working results of the staff.

[0089] In some embodiments, when the patrol inspection staff has the authority to control the drone, the drone executes the commands of the patrol inspection staff. For example, when patrol inspection staff A has the authority to control the drone, patrol inspection staff A can issue commands such as "Please take a top view photo of the XX device being inspected", "Please take a front view photo of the XX device being inspected", "Please take a side view photo of the XX device", "Please record the sound of the XX device for 10 seconds", and "Please record a video of the XX device being repaired".

[0090] In this way, by receiving the control commands of the patrol inspection staff sent from the first drone and the execution status record of the first drone for the control commands, the work status of the patrol inspection staff can be recorded, the work specifications of the patrol inspection staff can be recorded, and it contributes to providing empirical data for subsequent work.

[0091] The embodiments of the present disclosure further provide a control system for drone-based patrol inspection of a chemical industrial production plant area that can execute the control method for drone-based patrol inspection of a chemical industrial production plant area. FIG. 5 is a schematic block diagram of a control system 500 for drone-based patrol inspection of a chemical industrial production plant area according to an embodiment of the present disclosure. As shown in FIG. 5, the control system 500 for drone-based patrol inspection of a chemical industrial production plant area includes a first drone 520 for executing a preset patrol inspection task in a target scene, which determines the first drone 520 responsible for the preset patrol inspection task in the chemical industrial production plant area, acquires data of a target object collected by the first drone 520 in the target scene, determines the state of the target object in the target scene based on the data of the target object, and when the state indicates that the target object is in a preset state in the target scene, a control device 510 for outputting prompt information matching the preset state in the target scene, and the first drone 520 for executing the preset patrol inspection task.

[0092] In this way, by having the drone conduct a patrol inspection of the chemical industrial production plant area, the efficiency of the patrol inspection can be improved, thereby ensuring the normal operation of the chemical industrial production plant area and the safety of the chemical industrial production plant area.

[0093] In an embodiment of the present disclosure, as shown in FIG. 5, the control system for the patrol inspection of the chemical industrial production plant area by the drone further includes a second drone 530 that receives the scheduling command of the control device 510 and conveys the target item to the patrol inspection staff corresponding to the first drone 520 based on the scheduling command. The scheduling command is determined based on the item request transmitted from the first drone 520 by the control device 510.

[0094] Here, the patrol inspection staff is the staff that the first drone follows. In this way, the collaborative work between the first drone and the second drone can be realized, and by improving the intelligence of the drone's patrol inspection of the chemical industrial production plant area, the patrol inspection efficiency of the drone for the chemical industrial production plant area can be improved.

[0095] It should be noted that the flowcharts shown in FIGS. 2 to 5 are merely exemplary and not restrictive. The above flow can be adaptively adjusted or changed according to the work requirements, and the description is omitted here. Those skilled in the art can make various obvious changes and / or substitutions based on the examples in FIGS. 2 to 5, and the technical solutions thereby still belong to the disclosure scope of the embodiments of the present disclosure.

[0096] The embodiments of the present disclosure provide a control device for the patrol inspection of the chemical industrial production plant area by the drone. As shown in FIG. 6, the control device for the patrol inspection of the chemical industrial production plant area by the drone includes a first determination module 610 for determining a first drone that is a first drone for executing a preset patrol inspection task in a target scene and is responsible for the preset patrol inspection task of the chemical industrial production plant area, An acquisition module 620 that acquires data of a target object collected by a first drone in a target scene; A second determination module 630 that determines the state of the target object in the target scene based on the data of the target object; An output module 640 that outputs presentation information matching a preset state in the target scene when the state indicates that the target object is in a preset state in the target scene. It can include these. Regarding the preset patrol inspection task, When the target scene belongs to an active patrol inspection scene and the target object is a device, the preset patrol inspection task is a regular patrol inspection task or a sampling patrol inspection task. When the target scene belongs to an active patrol inspection scene and the target object is a person, the preset patrol inspection task is a regular patrol inspection task or a sampling patrol inspection task. When the target scene belongs to a passive patrol inspection scene and the target object is a device, the preset patrol inspection task is exclusively the first specialized patrol inspection task for the target object. When the target scene belongs to a passive patrol inspection scene and the target object is a person, the preset patrol inspection task is the second specialized patrol inspection task generated based on the requirements of the target object.

[0097] In some embodiments, the first determination module 610 includes a first determination sub-module for determining the drone that sent the follow-up command as the first drone in response to the follow-up command sent from the drone. The follow-up command is a command issued by the patrol inspection staff to the drone that sends the follow-up command, and is used to instruct the drone to operate following the patrol inspection staff. The follow-up command includes information representing the preset patrol inspection task.

[0098] In some embodiments, in response to receiving a work request transmitted from a terminal, the first determination module 610 includes a second determination sub-module for determining, based on the work request and the status information of candidate drones, a first drone from the candidate drones for executing a preset patrol inspection task in a target scene for the terminal. The work request includes information representing a preset patrol inspection task.

[0099] In some embodiments, the first determination module 610 includes a third determination sub-module for determining, based on the status information of candidate drones and according to a patrol inspection period, a first drone from the candidate drones for executing a preset patrol inspection task in a target scene.

[0100] In some embodiments, the preset patrol inspection task includes at least one of the following. When the target scene belongs to an active patrol inspection scene and the target object is a device, the preset patrol inspection task is a regular patrol inspection task or a sampling patrol inspection task. When the target scene belongs to an active patrol inspection scene and the target object is a person, the preset patrol inspection task is a regular patrol inspection task or a sampling patrol inspection task. When the target scene belongs to a passive patrol inspection scene and the target object is a device, the preset patrol inspection task is exclusively a first specialized patrol inspection task for the target object. When the target scene belongs to a passive patrol inspection scene and the target object is a person, the preset patrol inspection task is a second specialized patrol inspection task generated based on the requirements of the target object.

[0101] In some embodiments, the preset state includes a device abnormal state, and the target object includes a target device. The output module 640 includes a first output sub-module for outputting prompt information matching the device abnormal state in the target scene when the state represents that the target device is in a device abnormal state in the target scene.

[0102] In some embodiments, the preset state includes a staff abnormal state, and the target object includes the target staff. The output module 640 includes a second output sub-module for outputting presentation information that matches the staff abnormal state in the target scene when the state indicates that the target staff is in the staff abnormal state in the target scene.

[0103] In some embodiments, the second determination module 630 includes a first acquisition sub-module for acquiring a known correspondence relationship including at least the relationship between each state of the target object and the interval data corresponding thereto, and an analysis sub-module for analyzing the state corresponding to the data of the target object in the target scene based on the known correspondence relationship.

[0104] In some embodiments, the second determination module 630 includes an input sub-module for inputting the data of the target object in the target scene into the state analysis model, and a second acquisition sub-module for acquiring the state of the target object in the target scene output from the state analysis model. Here, the state analysis model is obtained by training based on the known correspondence relationship and is for predicting the state of the target object in the target scene.

[0105] In some embodiments, the control device for the drone to perform a patrol inspection of the chemical industrial production plant area further includes an establishment module (not shown in FIG. 6) for establishing a correspondence relationship between the data of the target object in the target scene and the state of the target object, and an update module (not shown in FIG. 6) for updating the known correspondence relationship based on the correspondence relationship.

[0106] In some embodiments, the control device for the drone to patrol the chemical industrial production plant area further includes a first receiving module (not shown in FIG. 6) for receiving the item requests transmitted from the first drone, and a scheduling module (not shown in FIG. 6) for scheduling the second drone for the first drone based on the item requests, such that the second drone conveys the target item to the patrol staff corresponding to the first drone based on the item requests.

[0107] In some embodiments, the first drone is provided with a first voice recognition model, the target object includes the patrol staff, and the control device for the drone to patrol the chemical industrial production plant area further includes a first transmitting module (not shown in FIG. 6) for transmitting the item request to the background of the system when the first voice recognition model recognizes the item request of the patrol staff when the first drone receives the voice of the patrol staff.

[0108] In some embodiments, the control device for the drone to patrol the chemical industrial production plant area further includes a second transmitting module (not shown in FIG. 6) for transmitting the item request to the background of the system when, during the execution of the preset patrol task by the first drone, the collected sound of the target device is input into the second voice recognition model and the second voice recognition model analyzes and obtains an item request that matches the failure of the target device.

[0109] In some embodiments, the control device for the drone to patrol the chemical industrial production plant area further includes a third determination module (not shown in FIG. 6) for determining the patrol route for the first drone to execute the preset patrol task, and a third transmitting module (not shown in FIG. 6) for transmitting the patrol route to the first drone such that the first drone executes the preset patrol task based on the patrol route.

[0110] In some embodiments, the target object includes the patrol staff. The control device for the patrol inspection of the chemical industrial production plant area by the drone further includes a second receiving module (not shown in FIG. 6) for receiving the control command of the patrol staff transmitted from the first drone and the execution status record of the first drone corresponding to the control command, and a storage module (not shown in FIG. 6) for storing the control command of the patrol staff and the execution status record corresponding to the control command. Here, the control command is received during the execution of the preset patrol inspection task by the first drone, and the first drone can identify that the patrol staff has the control authority to transmit the control command.

[0111] Those skilled in the art can understand the functions of each processing module in the control device for the patrol inspection of the chemical industrial production plant area by the drone according to the embodiments of the present disclosure by referring to the relevant descriptions of the control method for the patrol inspection of the chemical industrial production plant area by the drone described above, and that each processing module in the control device for the patrol inspection of the chemical industrial production plant area by the drone according to the embodiments of the present disclosure may be realized by an analog circuit that realizes the functions according to the embodiments of the present disclosure, or may be realized by executing software for executing the functions according to the embodiments of the present disclosure on an electronic device.

[0112] The control device for the patrol inspection of the chemical industrial production plant area by the drone according to the embodiments of the present disclosure can improve the efficiency of the patrol inspection and the freedom of the patrol inspection by the drone patrolling the chemical industrial production plant area, thereby guaranteeing the normal operation of the chemical industrial production plant area and the safety of the chemical industrial production plant area.

[0113] According to the embodiments of the present disclosure, the present disclosure further provides an electronic device and a readable storage medium.

[0114] FIG. 7 is a block diagram of an electronic device according to an embodiment of the present disclosure. As shown in FIG. 7, the electronic device includes a memory 710 and a processor 720. The memory 710 stores a computer program executable by the processor 720. The number of the memory 710 and the processor 720 may be one or plural. The memory 710 may store one or more computer programs. When the one or more computer programs are executed by the electronic device, the electronic device can be caused to execute the method according to the above method embodiment. The electronic device may further include a communication interface 730 for communicating with an external device and performing data exchange and transmission.

[0115] If the memory 710, the processor 720, and the communication interface 730 are separate, the memory 710, the processor 720, and the communication interface 730 can be connected to each other via a bus and communicate with each other. The bus may be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The bus can be divided into an address bus, a data bus, a control bus, and the like. For convenience, in FIG. 7, only one thick line is shown, but it does not mean that there is only one bus or one type of bus.

[0116] Optionally, when specifically implemented, if the memory 710, the processor 720, and the communication interface 730 are integrated on one chip, the memory 710, the processor 720, and the communication interface 730 can communicate with each other via an internal interface.

[0117] The processor may be a Central Processing Unit (CPU), or may be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other programmable logic devices, discrete gates, transistor logic devices, discrete hardware components, etc. It should be understood that general-purpose processors may be microprocessors or any ordinary processors, etc. Note that the processor may also be a processor capable of corresponding to the Advanced RISC Machine (ARM) architecture.

[0118] Furthermore, optionally, the memory can include a read-only memory and a random access memory, and can further include a non-volatile random access memory. The memory can be a volatile memory or a non-volatile memory, or can include both a volatile memory and a non-volatile memory. The non-volatile memory can include a ROM (Read-Only Memory), a programmable read-only memory (Programmable ROM, PROM), an EPROM (Erasable PROM), an EEPROM (Electrically EPROM), or a flash memory. The volatile memory can include a random access memory (Random Access Memory, RAM) used as an external cache. The above description is merely illustrative and not restrictive. Many forms of RAM can be used. For example, a static random access memory (Static RAM, SRAM), a dynamic random access memory (Dynamic Random Access Memory, DRAM), a synchronous dynamic random access memory (Synchronous DRAM, SDRAM), a double data rate synchronous dynamic random access memory (Double Data Date SDRAM, DDR SDRAM), an enhanced synchronous dynamic random access memory (Enhanced SDRAM, ESDRAM), a synchlink dynamic random access memory (Synchlink DRAM, SLDRAM), and a direct memory bus random access memory (Direct RAM BUS RAM, DR RAM) may be used.

[0119] In the above embodiments, all or part of them may be implemented by software, hardware, firmware, or any combination thereof. When implemented using software, all or part of them can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed by a computer, all or part of the flow or functions described in the embodiments of the present disclosure are generated. The computer may be a general-purpose computer, a dedicated computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or may be transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (such as coaxial cable, optical fiber, Digital Subscriber Line (DSL)) or wireless (such as infrared, Bluetooth (registered trademark), microwave, etc.). The computer-readable storage medium may be any available medium accessible by a computer, or may be a data storage device such as a server or a data center that includes one or more available media integrated. The available medium may be a magnetic medium (such as a floppy (registered trademark) disk, a hard disk, or a magnetic tape), an optical medium (such as a Digital Versatile Disc (DVD)), a semiconductor medium (such as a Solid State Disk (SSD)), etc. It should be noted that the computer-readable storage medium according to the present disclosure may be a non-volatile storage medium, in other words, a non-temporary storage medium.

[0120] A person skilled in the art can understand that all or part of the steps for implementing the above embodiments may be completed by hardware, or may be completed by instructing the relevant hardware by a program. The program may be stored in a computer-readable storage medium, and the storage medium may be a read-only memory, a magnetic disk, an optical disk, or the like.

[0121] In the description of the embodiments of the present disclosure, the descriptions of terms such as "one embodiment", "some embodiments", "exemplification", "specific exemplification", or "some exemplifications" mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or exemplification are included in at least one embodiment or exemplification of the present disclosure. Also, the specific features, structures, materials, or characteristics described can be combined in any one or more embodiments or exemplifications in a suitable manner. Also, unless they are mutually contradictory, a person skilled in the art can combine different embodiments or exemplifications described in this specification and the features in different embodiments or exemplifications.

[0122] In the description of the embodiments of the present disclosure, unless otherwise specified, " / " means "or". For example, "A / B" can represent "A" or "B". The "and / or" in this specification is only a relationship for describing related objects and means that there are three possible relationships. For example, "A and / or B" can indicate three situations where "A" exists alone, "A" and "B" exist simultaneously, and "B" exists alone.

[0123] In the description of the embodiments of the present disclosure, the terms "first", "second", etc. are for description only and should not be understood as indicating or implying relative importance or implying the number of the indicated components. Thus, the features limited by "first", "second" can include one or more of such features explicitly or implicitly. In the description of the embodiments of the present disclosure, unless otherwise specified, the meaning of "a plurality" is two or more.

[0124] The above are only exemplary embodiments of the present disclosure and do not limit the present disclosure. Any modifications, equivalent substitutions, improvements, etc. made in accordance with the spirit and principles of the present disclosure should all be included within the scope of the claims of the present disclosure.

Claims

1. A control method applied to a control system for patrol inspection of a chemical industrial production plant area by a drone, the control system including a control device and a first drone, the control method including: The control device determines a first drone for performing a preset patrol inspection task in a target scene, the first drone being responsible for the preset patrol inspection task in the chemical industry production plant area; Acquiring data of a target object collected by the first drone in the target scene; determining a state of the target object in the target scene based on the data of the target object; if the state represents that the target object is in a preset state in the target scene, outputting presentation information matching the preset state in the target scene; Regarding the preset inspection task, When the target scene belongs to an active inspection scene and the target object is an equipment, the preset inspection task is a regular inspection task whose content is preset, or a sampling inspection task whose content is randomly generated; If the target scene belongs to an active inspection scene and the target object is a person, the preset inspection task is a regular inspection task or a sampling inspection task; When the target scene belongs to a passive inspection scene and the target object is an equipment, the preset inspection task is a first specialized inspection task set according to the attributes of the equipment; A control method characterized in that, when the target scene belongs to a passive patrol inspection scene and the target object is a person, the preset patrol inspection task is a second specialized patrol inspection task generated based on staff requests.

2. Determining a first drone to perform a preset inspection task in the target scene includes: In response to receiving a follow command forwarded by a drone, determining the drone that forwarded the follow command as the first drone; The following command is a command issued to the drone by a patrol inspection staff member and is used to instruct the drone to operate by following the patrol inspection staff member; The control method according to claim 1 , wherein the tracking command includes information representative of the preset patrol inspection task.

3. Determining a first drone to perform a preset inspection task in the target scene includes: In response to receiving a task request transmitted from a terminal, determining the first drone for performing the preset patrol inspection task in the target scene from the candidate drone to the terminal based on the task request and state information of the candidate drones; The method of claim 1 , wherein the work request includes information representative of the preset tour inspection task.

4. Determining a first drone to perform a preset inspection task in the target scene includes: The control method according to claim 1, further comprising determining the first drone for performing the preset patrol inspection task in the target scene from among the candidate drones based on state information of the candidate drones in conjunction with a patrol inspection period.

5. The preset state includes an equipment abnormal state, and the target object includes a target equipment; When the state represents that the target object is in a preset state in the target scene, outputting presentation information matching the preset state in the target scene includes: The control method according to claim 1, further comprising, when the state indicates that the target device is in an abnormal device state in the target scene, outputting presentation information that matches the abnormal device state in the target scene.

6. The preset state includes a staff abnormal state, and the target object includes a target staff; When the state represents that the target object is in a preset state in the target scene, outputting presentation information matching the preset state in the target scene includes: The control method of claim 1, further comprising, when the state indicates that the target staff member is in an abnormal staff state in the target scene, outputting presentation information that matches the abnormal staff state in the target scene.

7. Determining a state of the target object in the target scene based on the data of the target object includes: obtaining a known correspondence including at least a relationship between each state of the target object and corresponding section data; and analyzing the state corresponding to the data of the target object in the target scene based on the known correspondence.

8. Determining a state of the target object in the target scene based on the data of the target object includes: inputting the data of the target object in the target scene into a state analysis model, the state analysis model being obtained by training based on known correspondences, for predicting the state of the target object in the target scene; and obtaining the state of the target object in the target scene output from the state analysis model.

9. The control method includes: The control device, establishing a correspondence between the data of the target object in the target scene and the state of the target object; 8. The method of claim 7, further comprising: updating the known correspondence based on the correspondence.

10. The control method includes: The control device, receiving an item request transmitted from the first drone; 2. The control method of claim 1, further comprising: scheduling the second drone relative to the first drone based on the item request such that the second drone transports a target item to a traveling inspection staff member corresponding to the first drone based on the item request.

11. The first drone is provided with a first voice recognition model, and the target object includes a patrol inspection staff; The control method includes: The control method of claim 10, further comprising the control device executing, when the first drone receives a voice of an inspection patrol inspection staff, sending the item request to the background of the system if the item request of the inspection patrol inspection staff is recognized by the first voice recognition model.

12. The first drone is provided with a second voice recognition model, and the target object includes a target device; The control method includes: The control method of claim 10, further comprising: inputting the collected sound of the target equipment into the second voice recognition model during the execution of the preset patrol inspection task by the first drone; and, if an item request matching a fault of the target equipment is obtained by analyzing the item request using the second voice recognition model, transmitting the item request to a background of a system.

13. The control method includes: The control device, Determine a patrol inspection route for the first drone to perform the preset patrol inspection task; 2. The control method of claim 1, further comprising: transmitting the patrol inspection route to the first drone so that the first drone performs the preset patrol inspection task based on the patrol inspection route.

14. The target object includes a traveling inspection staff, The control method includes: The control device, Receiving a control command of the patrol inspection staff transmitted from the first drone and an execution status record of the first drone in response to the control command; The method further includes storing the control command of the visiting inspection staff and the execution status record for the control command; Here, the control command is received during execution of the preset patrol inspection task by the first drone, The control method according to claim 1, characterized in that the first drone is able to identify that the patrol inspection staff has control authority to issue the control command.

15. A control system for patrol inspection of a chemical industry production plant area by a drone, comprising: a control device for performing a preset patrol inspection task in a target scene, the control device being configured to determine a first drone responsible for the preset patrol inspection task in the chemical industrial production plant area, acquire data of a target object collected by the first drone in the target scene, determine a state of the target object in the target scene based on the data of the target object, and output presentation information matching the preset state in the target scene when the state indicates that the target object is in a preset state in the target scene; a first drone for performing the preset inspection task; Regarding the preset inspection task, When the target scene belongs to an active inspection scene and the target object is an equipment, the preset inspection task is a regular inspection task whose content is preset, or a sampling inspection task whose content is randomly generated; If the target scene belongs to an active inspection scene and the target object is a person, the preset inspection task is a regular inspection task or a sampling inspection task; When the target scene belongs to a passive inspection scene and the target object is an equipment, the preset inspection task is a first specialized inspection task set according to the attributes of the equipment; A control system characterized in that, when the target scene belongs to a passive patrol inspection scene and the target object is a person, the preset patrol inspection task is a second specialized patrol inspection task generated based on a staff request.

16. The control system includes: Further comprising a second drone for receiving a scheduling command from the control device and transporting the target item to a traveling inspection staff member corresponding to the first drone based on the scheduling command; 16. The control system of claim 15, wherein the scheduling instructions are determined based on an item request transmitted from the first drone by the controller.

17. A control device for patrol inspection of a chemical industrial production plant area by a drone, A first drone for performing a preset patrol inspection task in a target scene, wherein a first determination module is configured to determine the first drone responsible for the preset patrol inspection task in the chemical industry production plant area; an acquisition module for acquiring data of a target object collected by the first drone in the target scene; a second determination module for determining a state of the target object in the target scene based on the data of the target object; and an output module for outputting presentation information matching the preset state in the target scene when the state represents that the target object is in a preset state in the target scene; Regarding the preset inspection task, When the target scene belongs to an active inspection scene and the target object is an equipment, the preset inspection task is a regular inspection task whose content is preset, or a sampling inspection task whose content is randomly generated; If the target scene belongs to an active inspection scene and the target object is a person, the preset inspection task is a regular inspection task or a sampling inspection task; When the target scene belongs to a passive inspection scene and the target object is an equipment, the preset inspection task is a first specialized inspection task set according to the attributes of the equipment; A control device characterized in that, when the target scene belongs to a passive patrol inspection scene and the target object is a person, the preset patrol inspection task is a second specialized patrol inspection task generated based on a staff request.

18. At least one processor; a memory communicatively connected to the at least one processor; The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to cause the at least one processor to perform a method according to any one of claims 1 to 14.

19. A computer readable non-transitory storage medium having stored thereon computer instructions used to cause a computer to carry out the method according to any one of claims 1 to 14.

20. A program to be applied to a control system for patrol inspection of a chemical industrial production plant area by a drone, On the computer, A first drone is used to perform a preset inspection task in a target scene, and the first drone is responsible for the preset inspection task in the chemical industry production plant area; Acquiring data of a target object collected by the first drone in the target scene; determining a state of the target object in the target scene based on the data of the target object; if the state represents that the target object is in a preset state in the target scene, outputting presentation information matching the preset state in the target scene; Regarding the preset inspection task, When the target scene belongs to an active inspection scene and the target object is an equipment, the preset inspection task is a regular inspection task whose content is preset, or a sampling inspection task whose content is randomly generated; If the target scene belongs to an active inspection scene and the target object is a person, the preset inspection task is a regular inspection task or a sampling inspection task; When the target scene belongs to a passive inspection scene and the target object is an equipment, the preset inspection task is a first specialized inspection task set according to the attributes of the equipment; If the target scene belongs to a passive inspection scene and the target object is a person, the preset inspection task is a second specialized inspection task generated according to the requirements of staff. A program characterized by:

Images