Unmanned aerial vehicle flight monitoring method, device, equipment, storage medium and program product

Abstract

The invention provides an unmanned aerial vehicle flight monitoring method and device, equipment, a storage medium and a program product, and relates to the technical field of unmanned aerial vehicles, and the method comprises the steps: monitoring and obtaining the flight data of an unmanned aerial vehicle; determining whether there is abnormal data in the flight data of the unmanned aerial vehicle; if abnormal data exist in the flight data of the unmanned aerial vehicle, judging whether the unmanned aerial vehicle equipment is abnormal or not based on a linear regression prediction function; if the unmanned aerial vehicle equipment is abnormal, performing abnormal type matching based on historical abnormal type data to obtain an abnormal type matching result; and if the abnormal type matching result is matching failure, determining the equipment abnormal type of the unmanned aerial vehicle equipment based on a deep learning algorithm. Through the above mode, the method does not need to excessively depend on a high-precision deep learning algorithm, thereby improving the anomaly analysis efficiency, rapidly generating the analysis result, and meeting the actual monitoring demands while guaranteeing the anomaly analysis precision.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicles, and particularly to a method, device, equipment, storage medium and program product for monitoring the flight of unmanned aerial vehicles. Background Art

[0002] Unmanned aerial vehicle flight monitoring refers to monitoring the flight state parameters, power system state, communication link state, environmental perception information, etc. of unmanned aerial vehicles, and using the above information to perform anomaly analysis, management and control on unmanned aerial vehicles.

[0003] In the existing unmanned aerial vehicle flight monitoring methods, anomaly analysis needs to rely on high-precision algorithms and comprehensively analyze and process a large amount of data.

[0004] However, although the existing unmanned aerial vehicle flight monitoring methods can ensure the accuracy of anomaly analysis, the efficiency of anomaly analysis is low, it is difficult to quickly generate analysis results, and it cannot meet the actual monitoring requirements. Summary of the Invention

[0005] The present invention provides a method, device, equipment, storage medium and program product for monitoring the flight of unmanned aerial vehicles, so as to solve the problem of low efficiency of anomaly analysis existing in the existing unmanned aerial vehicle flight monitoring methods, which is difficult to quickly generate analysis results and cannot meet the actual monitoring requirements.

[0006] The present invention provides a method for monitoring the flight of unmanned aerial vehicles, including: monitoring and acquiring unmanned aerial vehicle flight data; determining whether there is abnormal data in the unmanned aerial vehicle flight data; if there is abnormal data in the unmanned aerial vehicle flight data, then based on a linear regression prediction function, determining whether the unmanned aerial vehicle equipment is abnormal; if the unmanned aerial vehicle equipment is abnormal, then based on historical abnormal type data, performing abnormal type matching to obtain an abnormal type matching result; if the abnormal type matching result is a failure to match, then based on a deep learning algorithm, determining the equipment abnormal type of the unmanned aerial vehicle equipment.

[0007] According to a method for monitoring the flight of unmanned aerial vehicles provided by the present invention, determining whether the unmanned aerial vehicle equipment is abnormal based on a linear regression prediction function includes: determining at least one target data based on the abnormal data; the target data is the unmanned aerial vehicle flight data that changes when the abnormal data is greater than or equal to the abnormal data judgment threshold; substituting all the target data into the linear regression prediction function to calculate an abnormal prediction value of the unmanned aerial vehicle equipment; determining whether the abnormal prediction value is greater than or equal to a preset threshold; if the abnormal prediction value is greater than or equal to the preset threshold, then determining that the unmanned aerial vehicle equipment is abnormal.

[0008] A method for monitoring the flight of an unmanned aerial vehicle provided by the present invention, after determining whether the unmanned aerial vehicle device is abnormal based on a linear regression prediction function, further includes: if the unmanned aerial vehicle device is normal, obtaining the voice text of the user; extracting information from the voice text to obtain first target information; the first target information is the command information for controlling the unmanned aerial vehicle device; presenting the first target information to the user and determining whether the first target information is confirmed by the user; if the first target information is not confirmed by the user, generating an information missing reminder and returning to the step of obtaining the voice text of the user until the first target information is confirmed by the user, generating second target information; the second target information is the target information confirmed by the user; controlling the unmanned aerial vehicle device based on the second target information.

[0009] A method for monitoring the flight of an unmanned aerial vehicle provided by the present invention, controlling the unmanned aerial vehicle device based on the second target information, includes: generating a first control instruction based on the second target information; simulating the execution of the first control instruction to generate a simulation execution result; presenting the simulation execution result to the user and determining whether the simulation execution result is confirmed by the user; if the simulation execution result is not confirmed by the user, returning to the step of obtaining the voice text of the user until the simulation execution result is confirmed by the user, generating a second control instruction; the second control instruction is the control instruction whose simulation execution result is confirmed by the user; controlling the unmanned aerial vehicle device based on the second control instruction.

[0010] A method for monitoring the flight of an unmanned aerial vehicle provided by the present invention, after monitoring and obtaining the flight data of the unmanned aerial vehicle, further includes: determining the current communication network of the unmanned aerial vehicle device and obtaining the communication quality information of the current communication network; the communication quality information includes signal strength, bandwidth, and delay; determining the data transmission stability of the current communication network based on the signal strength, bandwidth, and delay; judging whether network switching processing is required based on the data transmission stability; if network switching processing is required, determining a target communication network from multiple alternative communication networks and switching the current communication network to the target communication network; wherein, the target communication network is the communication network with the highest data transmission stability among the multiple alternative communication networks.

[0011] According to a method for monitoring the flight of an unmanned aerial vehicle provided by the present invention, the target communication network is any one of a 5G-A network, a satellite internet, a self-organizing network, and an A2X communication network.

[0012] The present invention also provides a drone flight monitoring device, including: a data acquisition module for monitoring and acquiring drone flight data; an anomaly analysis module for determining whether there is anomalous data in the drone flight data; if there is anomalous data in the drone flight data, determining whether the drone device is anomalous based on a linear regression prediction function; if the drone device is anomalous, performing anomaly type matching based on historical anomaly type data to obtain an anomaly type matching result; if the anomaly type matching result is a failure, determining the device anomaly type of the drone device based on a deep learning algorithm.

[0013] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where when the processor executes the computer program, it implements any one of the above drone flight monitoring methods.

[0014] The present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements any one of the above drone flight monitoring methods.

[0015] The present invention also provides a computer program product, including a computer program, and when the computer program is executed by a processor, it implements any one of the above drone flight monitoring methods.

[0016] The drone flight monitoring method, device, equipment, storage medium, and program product provided by the present invention adopt a combination of primary analysis and advanced analysis, and introduce an anomaly type matching mechanism. When there is anomalous data in the drone flight data, first perform primary analysis based on a linear regression prediction function to determine whether the drone device is anomalous. If it is determined that the drone device is anomalous, then perform anomaly type matching based on historical anomaly type data, and in the case of a failure in anomaly type matching, perform advanced analysis based on a deep learning algorithm to determine the device anomaly type of the drone device. Since most device anomaly types will be identified during the primary analysis and anomaly type matching process, there is no need to rely too much on a high-precision deep learning algorithm. Therefore, while ensuring the accuracy of anomaly analysis, the efficiency of anomaly analysis can be improved, and the analysis result can be generated quickly to meet the actual monitoring requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0018] Figure 1 is one of the flow diagrams of the drone flight monitoring method provided by the present invention.

[0019] Figure 2 It is a schematic structural diagram of the UAV flight monitoring system provided by the present invention.

[0020] Figure 3 It is a schematic structural diagram of the anomaly analysis module provided by the present invention.

[0021] Figure 4 It is the second schematic flow diagram of the UAV flight monitoring method provided by the present invention.

[0022] Figure 5 It is a schematic structural diagram of the intelligent management module provided by the present invention.

[0023] Figure 6 It is a schematic structural diagram of the low-altitude intelligent networking module provided by the present invention.

[0024] Figure 7 It is a schematic structural diagram of the communication sub-module provided by the present invention.

[0025] Figure 8 It is a schematic structural diagram of the network condition evaluation sub-module provided by the present invention.

[0026] Figure 9 It is a schematic structural diagram of the UAV flight monitoring device provided by the present invention.

[0027] Figure 10 It is a schematic structural diagram of the electronic device provided by the present invention. Detailed implementation manners

[0028] To make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions in the present invention will be clearly and completely described below with reference to the accompanying drawings in the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art without making creative efforts based on the embodiments in the present invention belong to the scope of protection of the present invention.

[0029] Please refer to Figure 1 and Figure 2 , Figure 1 is the first schematic flow diagram of the UAV flight monitoring method provided by the present invention, Figure 2 is a schematic structural diagram of the UAV flight monitoring system provided by the present invention. In this embodiment, the UAV flight monitoring method is applied to the UAV flight monitoring system. The UAV flight monitoring method includes steps S110 to S150, and the specific steps are as follows: S110: Monitor and obtain UAV flight data.

[0030] Such as Figure 2As shown in the figure, the drone flight monitoring system based on the low-altitude intelligent network includes a data acquisition module, a data storage module, a display module, a control module, an anomaly analysis module, an intelligent management module, and a low-altitude intelligent network module.

[0031] Among them, the data acquisition module establishes a data connection with the low-altitude intelligent network module, the low-altitude intelligent network module establishes a data connection with the data storage module, the data storage module respectively establishes data connections with the display module, the anomaly analysis module, and the intelligent management module, and the intelligent management module establishes a data connection with the control module.

[0032] Specifically, the drone flight data is monitored and acquired through the data acquisition module, and the drone flight data collected by the data acquisition module will be stored in the data storage module.

[0033] Optionally, the drone flight data includes position information, altitude information, speed information, attitude angle information, and device status information.

[0034] S120: Determine whether there is abnormal data in the drone flight data.

[0035] Please refer to Figure 3 , Figure 3 which is the schematic structural diagram of the anomaly analysis module provided by the present invention.

[0036] As Figure 3 shown, the anomaly analysis module includes an abnormal data judgment sub-module, an anomaly analysis sub-module, and an alarm notification sub-module; the abnormal data judgment sub-module establishes a data connection with the anomaly analysis sub-module, and the anomaly analysis sub-module establishes a data connection with the alarm notification sub-module.

[0037] Among them, the abnormal data judgment sub-module is used to judge whether there is abnormal data in the drone flight data, the anomaly analysis sub-module is used to judge whether the drone device is abnormal and determine the type of abnormality of the drone device, and the alarm notification sub-module is used to issue an alarm for device abnormality.

[0038] The anomaly analysis sub-module includes a primary analysis unit, an anomaly type matching unit, and a high-level analysis unit; the primary analysis unit can call a linear regression algorithm to analyze whether the drone device is abnormal; the anomaly type matching unit can match the device anomaly type corresponding to similar abnormal data through similarity analysis; the high-level analysis unit can call a deep learning algorithm to deeply analyze the device anomaly type.

[0039] Specifically, in this embodiment, the abnormal data judgment sub-module can judge whether there is abnormal data in the drone flight data through a threshold method.

[0040] It should be noted that the drone flight data includes various types of data such as position, altitude, speed, attitude angle, and device status. For each type of data, an abnormal data judgment threshold corresponding to this type of data can be set in advance. When this type of data is greater than or equal to the corresponding abnormal data judgment threshold, it can be determined that this type of data is abnormal data.

[0041] S130: If there is abnormal data in the drone flight data, then based on the linear regression prediction function, determine whether the drone device is abnormal.

[0042] If the abnormal data judgment sub-module determines that there is abnormal data in the drone flight data through the threshold method, the primary analysis unit can call the linear regression algorithm, and based on the linear regression prediction function of the linear regression algorithm, combined with the changes in other drone flight data when the abnormal data appears, determine whether the drone device is abnormal.

[0043] Specifically, if the abnormal data judgment sub-module determines that there is abnormal data in the drone flight data through the threshold method, the primary analysis unit can determine at least one target data according to the abnormal data. Among them, the target data is the drone flight data that changes when the abnormal data is greater than or equal to the abnormal data judgment threshold and triggers the judgment of abnormal data.

[0044] Furthermore, substitute all the changed target data into the linear regression prediction function, calculate the abnormal prediction value of the drone device, and determine whether the abnormal prediction value is greater than or equal to the preset threshold.

[0045] If the abnormal prediction value is greater than or equal to the preset threshold, it is determined that the drone device is abnormal.

[0046] In this embodiment, if the judgment result is that the drone device is abnormal, the abnormal type matching can be continued; if the judgment result is that the drone device is normal, it is regarded as a false alarm.

[0047] S140: If the drone device is abnormal, then based on the historical abnormal type data, perform abnormal type matching to obtain the abnormal type matching result.

[0048] If the drone device is abnormal, the abnormal type matching unit can obtain the abnormal type matching result by matching the existing data (i.e., the existing historical abnormal type data).

[0049] If the abnormal type matching result is a successful match, the device abnormal type of the matched drone device can be directly output.

[0050] S150: If the abnormal type matching result is a failed match, then based on the deep learning algorithm, determine the device abnormal type of the drone device.

[0051] If the abnormal type matching result is a failure, the advanced analysis unit can call a deep learning algorithm for in-depth analysis to determine the device abnormal type of the UAV device.

[0052] Optionally, after determining the device abnormal type of the UAV device, the current abnormal analysis result can be stored in the data storage module as a database for use by the abnormal type matching unit when performing abnormal type matching; meanwhile, the alarm notification sub-module gives an alarm reminder for the abnormal result.

[0053] The UAV flight monitoring method provided in this embodiment combines primary analysis and advanced analysis, and introduces an abnormal type matching mechanism. When there is abnormal data in the UAV flight data, it first performs primary analysis based on the linear regression prediction function to determine whether the UAV device is abnormal. If it is determined that the UAV device is abnormal, it then performs abnormal type matching based on historical abnormal type data. In the case of a failure in abnormal type matching, it performs advanced analysis based on a deep learning algorithm to determine the device abnormal type of the UAV device. Since most device abnormal types will be identified during the primary analysis and abnormal type matching processes, there is no need to overly rely on a high-precision deep learning algorithm. Therefore, while ensuring the accuracy of abnormal analysis, it can improve the efficiency of abnormal analysis, quickly generate analysis results, and meet the actual monitoring requirements.

[0054] In some embodiments, based on the linear regression prediction function, determining whether the UAV device is abnormal includes: based on the abnormal data, determining at least one target data; the target data is the UAV flight data that changes when the abnormal data is greater than or equal to the abnormal data judgment threshold; substituting all the target data into the linear regression prediction function to calculate the abnormal prediction value of the UAV device; determining whether the abnormal prediction value is greater than or equal to a preset threshold; if the abnormal prediction value is greater than or equal to the preset threshold, it is determined that the UAV device is abnormal.

[0055] Specifically, if the abnormal data judgment sub-module determines that there is abnormal data in the UAV flight data through the threshold method, the primary analysis unit can determine at least one target data according to the abnormal data; where the target data is the UAV flight data that changes when the abnormal data is greater than or equal to the abnormal data judgment threshold and triggers the abnormal data judgment.

[0056] Furthermore, substitute all the changed target data into the linear regression prediction function to calculate the abnormal prediction value of the UAV device, and determine whether the abnormal prediction value is greater than or equal to the preset threshold.

[0057] If the abnormal prediction value is greater than or equal to the preset threshold, it is determined that the UAV device is abnormal.

[0058] For example, during the operation of the motor of a drone, if the abnormal data judgment sub-module determines through the threshold method that the temperature data exceeds the abnormal data judgment threshold and triggers the abnormal data judgment, the primary analysis unit will collect the drone flight data that changes when the temperature data exceeds the abnormal data judgment threshold; assuming that when the temperature data exceeds the abnormal data judgment threshold, the changed drone flight data includes current data and vibration data, the primary analysis unit can substitute all the changed current data and vibration data into the linear regression prediction function to calculate the current abnormal prediction value of the drone device; if the current abnormal prediction value of the drone device is greater than or equal to the preset threshold, it is determined that the drone device is abnormal; if the current abnormal prediction value of the drone device is less than the preset threshold, it is determined that the drone device is normal.

[0059] In this embodiment, if the judgment result is that the drone device is abnormal, the abnormal type matching can be continued; if the judgment result is that the drone device is normal, it is regarded as a false alarm.

[0060] The drone flight monitoring method provided in this embodiment combines primary analysis and advanced analysis in the abnormal analysis module and introduces an abnormal type matching mechanism, which can improve the efficiency of abnormal analysis while ensuring the accuracy of abnormal analysis.

[0061] In some embodiments, after determining whether the drone device is abnormal based on the linear regression prediction function, it further includes: if the drone device is normal, obtaining the voice text of the user; extracting information from the voice text to obtain the first target information; the first target information is the command information for controlling the drone device; presenting the first target information to the user and determining whether the first target information is confirmed by the user; if the first target information is not confirmed by the user, generating an information missing reminder and returning to the step of obtaining the voice text of the user until the first target information is confirmed by the user to generate the second target information; the second target information is the target information confirmed by the user; controlling the drone device based on the second target information.

[0062] Please refer to Figure 4 and Figure 5 , Figure 4 is the second flowchart of the drone flight monitoring method provided by the present invention, Figure 5 is the structural schematic diagram of the intelligent management module provided by the present invention.

[0063] When the existing drone flight monitoring system is in use, it requires relatively rich professional knowledge, so the training cost and training time of system managers are relatively large.

[0064] Based on this, this embodiment improves the existing drone flight monitoring system and method: such as Figure 4 and Figure 5As shown in the figure, in this embodiment, an intelligent management module is newly added to the UAV flight monitoring system. The intelligent management module can perform intelligent management. By using natural language processing technology, it obtains complete target information from human-machine interaction, generates control instructions based on the target information, and realizes the automated and intelligent operation of the system based on the control instructions. This can reduce the requirements of managers for professional knowledge and save personnel training costs and time.

[0065] Specifically, the intelligent management module includes a speech recognition sub-module, a natural language processing sub-module, a target information confirmation sub-module, an instruction generation sub-module, an instruction simulation execution sub-module, a simulation result confirmation sub-module, and a key information missing reminder sub-module.

[0066] Among them, the speech recognition sub-module establishes a data connection with the natural language processing sub-module, the natural language processing sub-module establishes a data connection with the target information confirmation sub-module, the target information confirmation sub-module respectively establishes data connections with the instruction generation sub-module and the key information missing reminder sub-module, the instruction generation sub-module establishes a data connection with the instruction simulation execution sub-module, and the instruction simulation execution sub-module establishes a data connection with the simulation result confirmation sub-module.

[0067] Optionally, if the UAV device is normal, the speech recognition sub-module can collect and recognize the user's speech information during the human-machine interaction process and convert it into text information, so as to obtain the user's speech text.

[0068] Optionally, if the UAV device is normal, the speech recognition sub-module can directly obtain the text input by the user as the speech text.

[0069] Furthermore, the natural language processing sub-module is used to extract information from the speech text to obtain the first target information; among them, the first target information is the instruction information for controlling the UAV device.

[0070] Furthermore, the target information confirmation sub-module is used to display the first target information to the user and judge whether the first target information is confirmed by the user.

[0071] If the first target information is not confirmed by the user, the key information missing reminder sub-module is used to generate an information missing reminder (i.e., the key information missing reminder) to remind the user to improve the target information, and return to the step of obtaining the user's speech text, and continue to obtain natural language information through human-machine interaction until the first target information is confirmed by the user to generate the second target information; among them, the second target information is the target information confirmed by the user.

[0072] Furthermore, based on the second target information confirmed by the user, the UAV device is controlled.

[0073] In some embodiments, controlling a drone device based on second target information includes: generating a first control instruction based on the second target information; simulating the execution of the first control instruction to generate a simulation execution result; presenting the simulation execution result to the user and determining whether the simulation execution result is confirmed by the user; if the simulation execution result is not confirmed by the user, returning to the step of obtaining the user's speech text until the simulation execution result is confirmed by the user, and generating a second control instruction; the second control instruction is a control instruction for which the simulation execution result is confirmed by the user; and controlling the drone device based on the second control instruction.

[0074] Specifically, after obtaining the second target information, the instruction generation sub-module can generate a first control instruction according to the second target information.

[0075] Further, the instruction simulation execution sub-module simulates the execution of the first control instruction to generate a simulation execution result, and presents the simulation execution result to the user through the simulation result confirmation sub-module to determine whether the simulation execution result is confirmed by the user.

[0076] If the simulation execution result is not confirmed by the user, it indicates that the target information is incomplete. At this time, it is necessary to return to the step of obtaining the user's speech text to re-complete and confirm the target information through human-computer interaction until the simulation execution result is confirmed by the user, and generate a second control instruction; the second control instruction is a control instruction for which the simulation execution result is confirmed by the user.

[0077] Further, the control module can control the drone device according to the second control instruction for which the simulation execution result is confirmed by the user.

[0078] In this embodiment, when obtaining the target information in the user's speech text, the system does not directly generate and execute a control instruction, but repeats the process of perfecting the target information, simulating the execution of the control instruction, and confirming the simulation execution result to ensure that the system can accurately understand the user's intention; at the same time, to ensure that the execution of the control instruction can meet the user's expectations, after repeatedly perfecting the target information through human-computer interaction and obtaining the user's confirmation, first simulate the execution of the first control instruction generated based on the target information confirmed by the user to obtain a simulation execution result. The presentation of the simulation execution result facilitates the user to confirm whether the execution of the control instruction meets the user's expectations, and then execute the second control instruction after the simulation execution result is confirmed by the user, so as to ensure that the execution of the control instruction conforms to the user's intention. This mechanism of secondary confirmation can ensure that the system accurately understands the user's intention and ensure that the execution of the control instruction meets the user's expectations.

[0079] Optionally, the intelligent management module can improve the key information missing reminder mechanism and optimize the key information missing reminder sub-module by recording and analyzing the process of confirming each simulation execution result, so as to improve the acquisition efficiency of the target information.

[0080] For the UAV flight monitoring method provided in this embodiment, the intelligent management module can adopt natural language processing technology to obtain complete target information from continuous human-machine interactions, generate control instructions based on the target information, and implement automated system operations based on the control instructions. Therefore, the professional requirements for management personnel are relatively low, and personnel training costs and time can be saved.

[0081] In some embodiments, after monitoring and acquiring UAV flight data, it further includes: determining the current communication network of the UAV device and acquiring the communication quality information of the current communication network; the communication quality information includes signal strength, bandwidth, and delay; determining the data transmission stability of the current communication network based on the signal strength, bandwidth, and delay; judging whether network switching processing is required based on the data transmission stability; if network switching processing is required, determining a target communication network from multiple alternative communication networks and switching the current communication network to the target communication network; wherein, the target communication network is the communication network with the highest data transmission stability among the multiple alternative communication networks.

[0082] Existing UAV flight monitoring systems have problems such as high data transmission latency and poor signal stability in complex environments, and are prone to communication interruptions and signal loss. Based on this, it is necessary to improve existing UAV flight monitoring systems and methods.

[0083] Please refer to Figures 6 to 8 , Figure 6 which is a schematic structural diagram of the low-altitude intelligent networking module provided by the present invention, Figure 7 which is a schematic structural diagram of the communication sub-module provided by the present invention, Figure 8 which is a schematic structural diagram of the network condition assessment sub-module provided by the present invention.

[0084] As Figures 6 to 8 shown, the low-altitude intelligent networking module is used to evaluate network quality during communication and automatically switch communication methods according to the evaluation results to achieve network intelligent connection; the low-altitude intelligent networking module includes a communication sub-module, a network condition assessment sub-module, an automatic adjustment sub-module, and a manual intervention sub-module; the communication sub-module can access 5G-A (5G-Advanced) networks, satellite Internet, ad hoc networks, and A2X (flying Internet) communication networks; the network condition assessment sub-module includes a signal strength monitoring unit, a bandwidth and delay assessment unit, and a stability assessment unit.

[0085] Among them, the communication sub-module is used to provide communication services; the network condition assessment sub-module is used to evaluate communication quality; the automatic adjustment sub-module is used to automatically switch communication networks; the manual intervention sub-module is used to manually adjust communication networks.

[0086] Specifically, while monitoring the flight data of the drone, the current communication network of the drone device can be determined through the communication sub-module, and the communication quality information of the current communication network can be obtained by using the network condition evaluation sub-module.

[0087] Optionally, the signal strength of the current communication network is collected by the signal strength monitoring unit, and the bandwidth and delay of the current communication network are collected by the bandwidth and delay evaluation unit.

[0088] Furthermore, the stability evaluation unit can determine the data transmission stability of the current communication network based on the signal strength, bandwidth, and delay.

[0089] Furthermore, the automatic adjustment sub-module can determine whether network switching processing is required based on the data transmission stability.

[0090] If network switching processing is required, the target communication network is determined from multiple alternative communication networks, and the current communication network is switched to the target communication network; where the target communication network is the communication network with the highest data transmission stability among the multiple alternative communication networks.

[0091] Optionally, after determining the data transmission stability of the current communication network, the communication network can also be manually set through the manual intervention sub-module.

[0092] In some embodiments, the target communication network is any one of a 5G-A network, a satellite internet, an ad-hoc network, and an A2X communication network.

[0093] In the method for monitoring the flight of a drone provided in this embodiment, the low-altitude intelligent networking module can automatically switch the communication network based on the network performance evaluation, thereby ensuring the data transmission efficiency and signal stability of the drone device.

[0094] The present invention also provides a device for monitoring the flight of a drone. Please refer to Figure 9 , Figure 9 which is a schematic structural diagram of the device for monitoring the flight of a drone provided by the present invention. In this embodiment, the device for monitoring the flight of a drone includes a data acquisition module 910 and an anomaly analysis module 920.

[0095] The data acquisition module 910 is used to monitor and acquire the flight data of the drone.

[0096] The anomaly analysis module 920 is used to determine whether there is abnormal data in the drone flight data; if there is abnormal data in the drone flight data, it is determined whether the drone device is abnormal based on the linear regression prediction function; if the drone device is abnormal, anomaly type matching is performed based on the historical anomaly type data to obtain an anomaly type matching result; if the anomaly type matching result is a failure to match, the device anomaly type of the drone device is determined based on the deep learning algorithm.

[0097] In some embodiments, the anomaly analysis module 920 is configured to determine at least one target data based on anomaly data; the target data is the UAV flight data that changes when the anomaly data is greater than or equal to the anomaly data judgment threshold; substitute all the target data into the linear regression prediction function to calculate the anomaly prediction value of the UAV device; determine whether the anomaly prediction value is greater than or equal to a preset threshold; if the anomaly prediction value is greater than or equal to the preset threshold, it is determined that the UAV device is abnormal.

[0098] In some embodiments, the UAV flight monitoring device further includes a management and control module.

[0099] The management and control module is configured to, if the UAV device is normal, obtain the user's voice text; extract information from the voice text to obtain the first target information; the first target information is the command information for controlling the UAV device; display the first target information to the user and determine whether the first target information is confirmed by the user; if the first target information is not confirmed by the user, generate an information missing reminder and return to the step of obtaining the user's voice text until the first target information is confirmed by the user to generate the second target information; the second target information is the target information confirmed by the user; control the UAV device based on the second target information.

[0100] In some embodiments, the management and control module is configured to generate a first control instruction based on the second target information; simulate the execution of the first control instruction to generate a simulation execution result; display the simulation execution result to the user and determine whether the simulation execution result is confirmed by the user; if the simulation execution result is not confirmed by the user, return to the step of obtaining the user's voice text until the simulation execution result is confirmed by the user to generate the second control instruction; the second control instruction is the control instruction whose simulation execution result is confirmed by the user; control the UAV device based on the second control instruction.

[0101] In some embodiments, the UAV flight monitoring device further includes a network quality assessment module.

[0102] The network quality assessment module is configured to determine the current communication network of the UAV device and obtain the communication quality information of the current communication network; the communication quality information includes signal strength, bandwidth, and delay; determine the data transmission stability of the current communication network based on the signal strength, bandwidth, and delay; determine whether network switching processing is required based on the data transmission stability; if network switching processing is required, determine the target communication network from multiple alternative communication networks and switch the current communication network to the target communication network; wherein, the target communication network is the communication network with the highest data transmission stability among the multiple alternative communication networks.

[0103] In some embodiments, the target communication network is any one of a 5G-A network, a satellite internet, an ad-hoc network, and an A2X communication network.

[0104] The present invention also provides an electronic device. Figure 10 is a schematic structural diagram of the electronic device provided by the present invention. As Figure 10 shown, the electronic device may include: a processor 1010, a communications interface 1020, a memory 1030, and a communication bus 1040. Among them, the processor 1010, the communications interface 1020, and the memory 1030 complete communication with each other through the communication bus 1040. The processor 1010 can call the logical instructions in the memory 1030 to execute the unmanned aerial vehicle flight monitoring method.

[0105] In addition, when the logical instructions in the above-mentioned memory 1030 are implemented in the form of a software functional unit and sold or used as an independent product, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media such as a USB flash drive, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk, or an optical disc that can store program codes.

[0106] The present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it is configured to execute the unmanned aerial vehicle flight monitoring method provided by the above-mentioned various methods.

[0107] The present invention also provides a computer program product. The computer program product includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the unmanned aerial vehicle flight monitoring method provided by the above-mentioned various methods.

[0108] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative work.

[0109] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0110] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of each embodiment of the present invention.

Claims

1. A method for monitoring the flight of an unmanned aerial vehicle, characterized in that: include: Monitor and obtain drone flight data; Determining whether there is abnormal data in the UAV flight data; If there is abnormal data in the UAV flight data, judging whether the UAV device is abnormal based on the linear regression prediction function; If the drone device is abnormal, an abnormal type match is performed based on historical abnormal type data to obtain an abnormal type matching result; If the abnormality type matching result is a matching failure, the device abnormality type of the drone device is determined based on a deep learning algorithm.

2. The method for monitoring the flight of an unmanned aerial vehicle according to claim 1, characterized in that: The method of judging whether the drone device is abnormal based on the linear regression prediction function includes: Based on the abnormal data, at least one target data is determined; the target data is the flight data of the UAV that changes when the abnormal data is greater than or equal to the abnormal data judgment threshold; Substituting all the target data into the linear regression prediction function, and calculating the abnormal prediction value of the UAV device; Determine whether the abnormal prediction value is greater than or equal to a preset threshold; If the abnormal prediction value is greater than or equal to the preset threshold, it is determined that the drone equipment is abnormal.

3. The method for monitoring the flight of an unmanned aerial vehicle according to claim 1, characterized in that: After judging whether the drone device is abnormal based on the linear regression prediction function, the method further includes: If the drone device is normal, obtaining the user's voice text; Extracting information from the voice text to obtain first target information; the first target information is instruction information for controlling the drone device; Displaying the first target information to the user, and determining whether the first target information is confirmed by the user; If the first target information is not confirmed by the user, an information missing reminder is generated, and the process returns to the step of obtaining the user's voice text until the first target information is confirmed by the user, and the second target information is generated; the second target information is the target information confirmed by the user; Based on the second target information, the drone device is controlled.

4. The method for monitoring the flight of an unmanned aerial vehicle according to claim 3, characterized in that: The controlling the UAV device based on the second target information includes: generating a first control instruction based on the second target information; Simulate and execute the first control instruction to generate a simulation execution result; Displaying the simulation execution result to the user, and determining whether the simulation execution result is confirmed by the user; If the simulation execution result is not confirmed by the user, the process returns to the step of obtaining the user's voice text until the simulation execution result is confirmed by the user, and a second control instruction is generated; the second control instruction is a control instruction for which the simulation execution result is confirmed by the user; Based on the second control instruction, the drone device is controlled.

5. The method for monitoring the flight of a drone according to claim 1, characterized in that: After monitoring and acquiring the UAV flight data, the following steps are also included: Determine the current communication network of the drone device and obtain communication quality information of the current communication network; the communication quality information includes signal strength, bandwidth and latency; Determining the data transmission stability of the current communication network based on the signal strength, the bandwidth and the delay; Based on the data transmission stability, determining whether network switching is required; If network switching is required, determining a target communication network from a plurality of candidate communication networks, and switching the current communication network to the target communication network; The target communication network is a communication network with the highest data transmission stability among the multiple candidate communication networks.

6. The method for monitoring the flight of an unmanned aerial vehicle according to claim 5, characterized in that: The target communication network is any one of a 5G-A network, a satellite Internet, a self-organizing network and an A2X communication network.

7. A UAV flight monitoring device, characterized in that: include: Data acquisition module, used to monitor and obtain UAV flight data; An abnormality analysis module, used to determine whether there is abnormal data in the UAV flight data; If there is abnormal data in the drone flight data, whether the drone equipment is abnormal is determined based on a linear regression prediction function; if the drone equipment is abnormal, an abnormal type match is performed based on historical abnormal type data to obtain an abnormal type matching result; if the abnormal type matching result is a matching failure, the equipment abnormality type of the drone equipment is determined based on a deep learning algorithm.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the drone flight monitoring method as described in any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the drone flight monitoring method according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the drone flight monitoring method according to any one of claims 1 to 6 is implemented.

Images