Unmanned aerial vehicle inspection task list generation method and device, terminal equipment and storage medium

Abstract

The invention discloses an unmanned aerial vehicle inspection task list generation method and device, terminal equipment and a storage medium, and belongs to the technical field of unmanned aerial vehicles, and the method comprises the steps: inputting user identity information and an unmanned aerial vehicle inspection instruction text inputted by a user last time into a user habit analysis model, the user habit analysis model outputs language habit features of the user; according to the language habit characteristics of the user and the inspection interval text, outputting inspection task parameters; according to the inspection task starting time text and the inspection task ending time text, inspection task starting time and inspection task ending time are determined; and generating an inspection task list according to the inspection task parameters, the inspection task starting time and the inspection task ending time. The problem that the generated unmanned aerial vehicle inspection task list is inaccurate due to the fact that the instruction text input by the user is extracted by adopting a fixed template and cannot adapt to the language expression habit of the user can be solved.

Description

Technical Field

[0001] The present invention relates to the field of drone technology, and in particular to a method, device, terminal equipment, and storage medium for generating a drone inspection task list. Background Art

[0002] During a power inspection, a drone will create an inspection plan, which typically includes several inspection tasks, along with their start and end times. However, users don't create a plan by entering the details for each task individually. Instead, they enter a text file containing the overall inspection start, end, and interval time for each task. For example, "Inspections will be conducted every four months from January 1, 2023, to December 31, 2024" is used as input. This allows the existing natural language processing model to output a corresponding list of inspection tasks. However, for different users, their different user habits will lead to different input texts. For example, when another user formulates the above-mentioned inspection task, the input text entered is "From January 1, 2023 to December 31, 2024, an inspection will be carried out every 4 months." The existing natural language processing model usually uses a general template to extract keywords and then formulates a task list, without considering the language input habits of different users. This results in the template in the natural language processing model being adapted to the first user, and the instruction text entered by the second user being difficult to recognize or being misrecognized, ultimately resulting in the second user inputting text unable to obtain the desired inspection task list. Summary of the Invention

[0003] The embodiments of the present invention provide a method, apparatus, terminal device and storage medium for generating a drone inspection task list, which can solve the problem that the existing technology uses a fixed template to extract user input instruction text when generating a drone inspection task list, and is unable to adapt to the user's language expression habits, resulting in the generated drone inspection task list being inaccurate and not meeting user needs.

[0004] An embodiment of the present invention provides a method for generating a drone inspection task list, comprising:

[0005] Obtain the unmanned aerial vehicle inspection instruction text to be processed, user identity information, and the unmanned aerial vehicle inspection instruction text input by the user; wherein the unmanned aerial vehicle inspection instruction text to be processed includes: inspection task start time text, inspection task end time text, and inspection interval text;

[0006] Inputting the user identity information and the drone inspection instruction text input by the user last time into the user habit analysis model, so that the user habit analysis model outputs the user's language habit characteristics;

[0007] Output inspection task parameters according to the user's language habit characteristics and inspection interval text; wherein the inspection task parameters include: interval type, interval unit, interval number and deadline;

[0008] Determine the inspection task start time and inspection task end time according to the inspection task start time text and inspection task end time text;

[0009] Generate an inspection task list according to the inspection task parameters, the inspection task start time and the inspection task end time.

[0010] Furthermore, the construction of the user habit analysis model includes:

[0011] Obtaining a number of sample users and a number of historical input samples of each sample user; wherein each historical input sample includes the language habit features of the sample user's previous historical input sample, the sample user's identity information, and the sample user's previous historical input sample;

[0012] For each sample user, generate an initial user habit analysis sub-model for the current sample user based on the user identity information of the current sample user;

[0013] The user habit analysis sub-model is generated by training the sample user identity information and the sample user's previous historical input sample as input to the initial user habit analysis sub-model and outputting the language habit features of the sample user's previous historical input sample until the initial user habit analysis sub-model converges.

[0014] Construct a user habit analysis model based on each user habit analysis sub-model.

[0015] Furthermore, the interval type includes a periodic interval and a fixed date. When the interval type is a periodic interval, the deadline is empty.

[0016] Generating the inspection task list according to the inspection task parameters, the inspection task start time and the inspection task end time includes:

[0017] When the interval type is periodic interval, the inspection span is determined based on the interval unit and the number of intervals, and the inspection task list is generated based on the inspection span, the inspection task start time, and the inspection task end time;

[0018] When the interval type is a fixed date, several inspection time nodes are determined according to the interval unit, interval quantity and deadline, and an inspection task list is generated according to the several inspection time nodes, the inspection task start time and the inspection task end time.

[0019] Furthermore, the output of inspection task parameters according to the user's language habit characteristics and the inspection interval text includes:

[0020] Determining the user's usual interval type description form, usual interval unit description form, usual interval quantity description form, and usual deadline description form according to the user's language habit characteristics;

[0021] The information in the inspection interval text is extracted according to the user's usual interval type description form, usual interval unit description form, usual interval quantity description form and usual deadline description form, and the inspection task parameters are output.

[0022] Based on the above method embodiment, the present invention provides a corresponding device embodiment;

[0023] An embodiment of the present invention provides a device for generating a patrol inspection task list for a drone, comprising: a data acquisition module, a user analysis module, and a patrol inspection task list generation module;

[0024] The data acquisition module is used to obtain the unmanned aerial vehicle inspection instruction text to be processed, the user's identity information, and the unmanned aerial vehicle inspection instruction text input by the user last time; wherein the unmanned aerial vehicle inspection instruction text to be processed includes: the inspection task start time text, the inspection task end time text, and the inspection interval text;

[0025] The user analysis module is configured to input the user identity information and the drone inspection instruction text input by the user last time into a user habit analysis model, so that the user habit analysis model outputs the user's language habit characteristics;

[0026] The inspection task list generation module is used to output inspection task parameters based on the user's language habit characteristics and the inspection interval text; wherein the inspection task parameters include: interval type, interval unit, interval number and deadline; determine the inspection task start time and inspection task end time based on the inspection task start time text and the inspection task end time text; generate an inspection task list based on the inspection task parameters, the inspection task start time and the inspection task end time.

[0027] Furthermore, it also includes a user habit analysis model construction module;

[0028] The user habit analysis model building module is used to obtain a number of sample users and a number of historical input samples of each sample user; wherein each historical input sample includes the language habit characteristics of the sample user's previous historical input sample, the sample user's identity information and the sample user's previous historical input sample;

[0029] For each sample user, generate an initial user habit analysis sub-model for the current sample user based on the user identity information of the current sample user;

[0030] The user habit analysis sub-model is generated by training the sample user identity information and the sample user's previous historical input sample as input to the initial user habit analysis sub-model and outputting the language habit features of the sample user's previous historical input sample until the initial user habit analysis sub-model converges.

[0031] Construct a user habit analysis model based on each user habit analysis sub-model.

[0032] Furthermore, the interval type includes a periodic interval and a fixed date. When the interval type is a periodic interval, the deadline is empty.

[0033] Generating the inspection task list according to the inspection task parameters, the inspection task start time and the inspection task end time includes:

[0034] When the interval type is periodic interval, the inspection span is determined based on the interval unit and the number of intervals, and the inspection task list is generated based on the inspection span, the inspection task start time, and the inspection task end time;

[0035] When the interval type is a fixed date, several inspection time nodes are determined according to the interval unit, interval quantity and deadline, and an inspection task list is generated according to the several inspection time nodes, the inspection task start time and the inspection task end time.

[0036] Furthermore, the output of inspection task parameters according to the user's language habit characteristics and the inspection interval text includes:

[0037] Determining the user's usual interval type description form, usual interval unit description form, usual interval quantity description form, and usual deadline description form according to the user's language habit characteristics;

[0038] The information in the inspection interval text is extracted according to the user's usual interval type description form, usual interval unit description form, usual interval quantity description form and usual deadline description form, and the inspection task parameters are output.

[0039] Another embodiment of the present invention provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the method for generating a drone inspection task list described in the above-mentioned embodiment of the invention.

[0040] Another embodiment of the present invention provides a storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute a method for generating a drone inspection task list as described in the above-mentioned embodiment of the invention.

[0041] The following beneficial effects are achieved by implementing the present invention:

[0042] The present invention provides a method, device, terminal device and storage medium for generating a drone inspection task list. The method includes obtaining a to-be-processed drone inspection instruction text input by a user, user identity information and the drone inspection instruction text input by the user last time, and then inputting the user identity information and the drone inspection instruction text input by the user last time into a user habit analysis model, outputting the user's language habit characteristics through the user habit analysis model, and then determining the inspection task parameters in the inspection interval text based on the language habit characteristics. By introducing the user's language habit characteristics, the inspection task parameters can be obtained from the inspection interval text more accurately, so that the inspection task list generated according to the inspection task parameters, the inspection task start time and the inspection task end time is more accurate and more in line with user needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 The present invention provides a flowchart of a method for generating a UAV inspection task list.

[0044] Figure 2 The present invention provides a schematic structural diagram of a device for generating a UAV inspection task list according to an embodiment of the present invention. DETAILED DESCRIPTION

[0045] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0046] To make the objectives, technical solutions, and advantages of this application more clear, the technical solutions in this application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making any creative efforts are within the scope of protection of this application.

[0047] like Figure 1 As shown, in order to solve the problem that the existing technology uses a fixed template to extract the user input instruction text when generating a drone inspection task list, which cannot adapt to the user's language expression habits and causes the generated drone inspection task list to be inaccurate and not meet the user's needs, an embodiment of the present invention provides a drone inspection task list generation method, including:

[0048] Step S1: Obtain the unmanned aerial vehicle inspection instruction text to be processed, the user's identity information, and the unmanned aerial vehicle inspection instruction text entered by the user last time; wherein the unmanned aerial vehicle inspection instruction text to be processed includes: inspection task start time text, inspection task end time text, and inspection interval text;

[0049] Step S2: inputting the user identity information and the drone inspection instruction text input by the user last time into the user habit analysis model, so that the user habit analysis model outputs the user's language habit characteristics;

[0050] Step S3: Outputting inspection task parameters according to the user's language habit characteristics and the inspection interval text; wherein the inspection task parameters include: interval type, interval unit, interval number and deadline;

[0051] Step S4: Determine the inspection task start time and inspection task end time according to the inspection task start time text and the inspection task end time text;

[0052] Step S5: Generate an inspection task list according to the inspection task parameters, the inspection task start time and the inspection task end time.

[0053] For step S1, obtain the unmanned aerial vehicle inspection instruction text to be processed, the user's identity information (in the present invention, the user identity information is the user ID) and the unmanned aerial vehicle inspection instruction text entered by the user last time. Among them, the unmanned aerial vehicle inspection instruction text to be processed consists of a text containing the start time of the inspection task, a text containing the end time of the inspection task and a text corresponding to the inspection interval information. For example, if the unmanned aerial vehicle inspection instruction text to be processed entered by the user is "from January 1, 2023 to December 31, 2024, an inspection will be carried out every 4 months", then the inspection task start time text is "January 1, 2023", the inspection task end time text is "December 31, 2024", and the inspection interval text is "an inspection will be carried out every 4 months".

[0054] In step S2, the user's identity information and the drone inspection command text entered by the user are input into the user habit analysis model. The user habit analysis model indexes the user's user habit analysis sub-model based on the user's identity information, obtains the user's language habit features based on the drone inspection command text entered by the user, and outputs the language habit features.

[0055] It should be noted that user language habit features are typically stored in the user habit analysis sub-model in JSON format. This format includes the user's language habits and the weight of the user's use of these language habits. The weight of the user's use of these language habits can be determined based on the statistical results of each term in the user's historical input data, or the statistical results of each term in the user's input data within a recently selected time period. For example, the user language habit features are stored in the user habit analysis sub-model in the following format: ["Use 24-hour system", "0.9"], ["Use 12-hour system", "0.1"], ["Use every XX to represent a period", "0.8"], ["Use every XX to represent a period", "0.2"], etc., where "Use 24-hour system" indicates the user's language habit of using the 24-hour system, "0.9" indicates the weight of this language habit of using the 24-hour system is 0.9, "Use every XX to represent a period" indicates the user's language habit of using this sentence to represent a period, and "0.8" indicates the weight of the user's use of this sentence to represent a period. When outputting user language habit characteristics, the higher-weighted item is typically output. For example, based on the stored data, the user's language habit characteristics outputted might be "using a 24-hour clock" and "using every XX to represent a period." Furthermore, as user input accumulates, the data stored in the user analysis sub-model changes, and the corresponding weights are updated, ensuring real-time updates to the user's language habit characteristics.

[0056] In a preferred embodiment, the construction of the user habit analysis model includes: obtaining several sample users and several historical input samples of each sample user; wherein each historical input sample includes the language habit features of the sample user's previous historical input sample, the sample user's identity information and the sample user's previous historical input sample; for each sample user, generating an initial user habit analysis sub-model of the current sample user based on the user identity information of the current sample user; using the sample user's identity information and the sample user's previous historical input sample as inputs of the initial user habit analysis sub-model, and using the language habit features of the sample user's previous historical input sample as outputs, the initial user habit analysis sub-model is trained until the initial user habit analysis sub-model converges, generating a user habit analysis sub-model; and constructing a user habit analysis model based on each user habit analysis sub-model.

[0057] Specifically, the user habit analysis model is a large model that contains multiple user habit analysis sub-models. Each user habit analysis sub-model is only used for analyzing the language habit characteristics of one user. This single-user single-model approach enables the model to only learn the language habits of a single user and is not affected by the data of other users, so that the output user language habit characteristics can be more accurate.

[0058] First, it is necessary to obtain a number of sample users. These sample users can be obtained from the database associated with the drone inspection system, and users with the authority to issue drone inspection instructions can be obtained as sample users. For each sample user, retrieve their historical drone inspection instruction text from the database, extract keywords associated with the inspection interval from the historical drone inspection instruction text, and determine the language habit characteristics of the sample user based on these keywords. Then, construct a historical input sample based on the language habit characteristics, the identity information of the sample user, and the previous historical input sample of the sample user. The above method is used to construct a number of historical input samples for each sample user, and the initial user habit analysis sub-model is used to train each sample user. It should be noted that the historical input samples of each sample user must be time-sequential.

[0059] For each sample user's initial user habit analysis sub-model, the sample user's identity information and the sample user's previous historical input sample are used as input, and the sample user's previous historical input sample's language habit features are used as output for training. When the initial user habit analysis sub-model converges, a user habit analysis sub-model is generated. The user habit analysis sub-model generated at this time can be used to analyze the language habit features of the corresponding sample user. Preferably, after the user habit analysis sub-model is trained, it needs to be updated according to the user's new input text to make the user habit analysis sub-model real-time.

[0060] Preferably, the inspection task start time text, inspection task end time text, and inspection interval text can be extracted by parsing the unmanned aerial vehicle inspection instruction text to be processed. This parsing can be performed based on preset rules, such as setting rules to extract data associated with the inspection task start time as the inspection task start time text, extract data associated with the inspection task end time as the inspection task end time text, and the remaining unextracted text is summarized as the inspection interval text associated with the inspection interval. To distinguish between the inspection task start time and the inspection task end time, the difference can be calculated after converting both into the same unit.

[0061] In step S3, inspection task parameters are extracted from the inspection interval text according to the user's language habit characteristics. The inspection task parameters include interval type, interval unit, interval quantity and deadline.

[0062] Specifically, interval types include periodic intervals and fixed dates. Periodic intervals specify the interval at which inspections are performed. For periodic intervals, the drone's inspection time is not specified; it only defines a time interval within which the drone must complete the inspection. Therefore, for a periodic interval, the deadline is "null." The interval unit corresponds to the number of intervals. For example, in "Perform an inspection every 4 months," "every 4 months" indicates periodicity and specifies a specific date for the inspection, so the interval type is "periodic." "4 months" indicates a number of "4" intervals, and the unit corresponding to the interval number is "month." For another example, in "Perform an inspection on the 25th of every month," "the 25th of every month" indicates periodicity but specifies a specific time, i.e., the inspection is performed on the 25th of every month. Therefore, the interval type is "fixed date," and the deadline is the 25th. "Monthly" indicates a number of "1" interval, and the unit corresponding to the interval number is "month."

[0063] In a preferred embodiment, the outputting of inspection task parameters based on the user's language habit characteristics and the inspection interval text includes: determining the user's habitual interval type description form, habitual interval unit description form, habitual interval quantity description form, and habitual deadline description form based on the user's language habit characteristics; extracting information from the inspection interval text based on the user's habitual interval type description form, habitual interval unit description form, habitual interval quantity description form, and habitual deadline description form, and outputting the inspection task parameters.

[0064] Specifically, the user's usual description form of the interval type, usual description form of the interval unit, usual description form of the interval quantity, and usual description form of the deadline are determined based on the user's language habit characteristics. For example, the usual description form of the interval type is "every XX" to express the interval type, the usual description form of the interval unit is "month", the usual description form of the interval quantity is "Arabic numerals before the 'interval unit'", and the usual description form of the deadline is "Arabic numerals after the 'interval unit'". Applying this to "perform an inspection every 4 months" yields the interval type "periodic interval", the interval unit "month", the interval quantity "4", and the deadline "nul l"; applying this to "perform an inspection on the 25th of each month" yields the interval type "fixed date", the interval unit "month", the interval quantity "1", and the deadline "25".

[0065] In step S4, the inspection task start time is extracted from the inspection task start time text, and the inspection task end time is extracted from the inspection task end time text. For example, the inspection task start time extracted from "January 1, 2023" is 2023-01-01, and the inspection task end time extracted from "December 31, 2024" is 2024-01-01.

[0066] In step S5, an inspection list corresponding to the unprocessed drone inspection instruction text is generated based on the extracted inspection task start time, inspection task end time, and inspection task parameters. The inspection list typically includes several inspection subtasks, with the start time of the first inspection subtask corresponding to the inspection task start time, and the end time of the last inspection subtask corresponding to the inspection task end time.

[0067] In a preferred embodiment, the inspection task list is generated based on the inspection task parameters, the inspection task start time and the inspection task end time, including: when the interval type is a periodic interval, the inspection span is determined based on the interval unit and the number of intervals, and the inspection task list is generated based on the inspection span, the inspection task start time and the inspection task end time; when the interval type is a fixed date, several inspection time nodes are determined based on the interval unit, the number of intervals and the deadline, and the inspection task list is generated based on the several inspection time nodes, the inspection task start time and the inspection task end time.

[0068] Specifically, when the interval type in the inspection task parameters is a periodic interval, the inspection span is determined based on the interval unit and the number of intervals. The inspection task start time is then used as the start time of the first inspection subtask in the inspection task list, and the time node after one inspection span is used as the end time of the first inspection subtask. In addition, to avoid overlap between time nodes, the end time of the first inspection subtask can be reduced by 1 second, and the time node of the original end time of the first inspection subtask is used as the start time node of the next inspection subtask. This process is repeated until the end time of the optimal inspection subtask is equal to or greater than the inspection task end time. The division of each inspection subtask in the inspection task list is completed, and each inspection subtask is numbered according to the division order to obtain the inspection task list.

[0069] For example, the inspection task list generated based on the text "Inspection every four months from January 1, 2023 to December 31, 2023" is as follows:

[0070]

[0071]

[0072] When the interval type in the inspection task parameters is fixed date, several inspection time nodes are determined based on the interval unit, interval number, and deadline. Then, an inspection task list is generated based on the several inspection time nodes, the inspection task start time, and the inspection task end time.

[0073] For example, the inspection task list generated based on the text "Inspection once on the 25th of each month from January 1, 2023 to April 1, 2023" is as follows:

[0074] Serial number Start time End Time 1 2023-01-25 00:00:00 2023-01-25 23:59:59 2 2023-02-25 00:00:00 2023-02-25 23:59:59 3 2023-03-25 00:00:00 2023-03-25 23:59:59

[0075] Preferably, after the inspection task list is generated, it can be fed back to the user through the human-computer interaction interface, and then the user can check whether the inspection task list is generated accurately. If it is accurate, after confirmation, an inspection instruction is generated according to the inspection task list to the corresponding drone, so that the drone can perform the inspection task according to the inspection task list.

[0076] Based on the above method embodiments, the present invention provides corresponding device embodiments.

[0077] like Figure 2 As shown, an embodiment of the present invention provides a device for generating a patrol inspection task list of a UAV, comprising: a data acquisition module, a user analysis module and a patrol inspection task list generation module;

[0078] The data acquisition module is used to obtain the unmanned aerial vehicle inspection instruction text to be processed, the user's identity information, and the unmanned aerial vehicle inspection instruction text input by the user last time; wherein the unmanned aerial vehicle inspection instruction text to be processed includes: the inspection task start time text, the inspection task end time text, and the inspection interval text;

[0079] The user analysis module is configured to input the user identity information and the drone inspection instruction text input by the user last time into a user habit analysis model, so that the user habit analysis model outputs the user's language habit characteristics;

[0080] The inspection task list generation module is used to parse the unmanned aerial vehicle inspection instruction text to be processed to obtain the inspection task start time text, the inspection task end time text and the inspection interval text; output the inspection task parameters according to the user's language habit characteristics and the inspection interval text; wherein the inspection task parameters include: interval type, interval unit, interval number and deadline; determine the inspection task start time and the inspection task end time according to the inspection task start time text and the inspection task end time text; generate the inspection task list according to the inspection task parameters, the inspection task start time and the inspection task end time.

[0081] In a preferred embodiment, it further includes a user habit analysis model building module;

[0082] The user habit analysis model building module is used to obtain a number of sample users and a number of historical input samples of each sample user; wherein each historical input sample includes the language habit characteristics of the sample user's previous historical input sample, the sample user's identity information and the sample user's previous historical input sample;

[0083] For each sample user, generate an initial user habit analysis sub-model for the current sample user based on the user identity information of the current sample user;

[0084] The user habit analysis sub-model is generated by training the sample user identity information and the sample user's previous historical input sample as input to the initial user habit analysis sub-model and outputting the language habit features of the sample user's previous historical input sample until the initial user habit analysis sub-model converges.

[0085] Construct a user habit analysis model based on each user habit analysis sub-model.

[0086] In a preferred embodiment, the interval type includes a periodic interval and a fixed date. When the interval type is a periodic interval, the deadline is empty.

[0087] Generating the inspection task list according to the inspection task parameters, the inspection task start time and the inspection task end time includes:

[0088] When the interval type is periodic interval, the inspection span is determined based on the interval unit and the number of intervals, and the inspection task list is generated based on the inspection span, the inspection task start time, and the inspection task end time;

[0089] When the interval type is a fixed date, several inspection time nodes are determined according to the interval unit, interval quantity and deadline, and an inspection task list is generated according to the several inspection time nodes, the inspection task start time and the inspection task end time.

[0090] In a preferred embodiment, the outputting of inspection task parameters according to the user's language habit characteristics and the inspection interval text includes:

[0091] Determining the user's usual interval type description form, usual interval unit description form, usual interval quantity description form, and usual deadline description form according to the user's language habit characteristics;

[0092] The information in the inspection interval text is extracted according to the user's usual interval type description form, usual interval unit description form, usual interval quantity description form and usual deadline description form, and the inspection task parameters are output.

[0093] It should be noted that the device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed across multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment. In addition, in the drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art can understand and implement the present invention without inventive effort.

[0094] Those skilled in the art will clearly understand that for the sake of convenience and brevity, the specific working process of the device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0095] Based on the above method embodiment, the present invention provides a corresponding terminal device embodiment.

[0096] An embodiment of the present invention provides a terminal device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, a method for generating a drone inspection task list as described in any one of the present inventions is implemented.

[0097] The terminal device may be a computing device such as a desktop computer, a notebook computer, a PDA, a cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0098] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, connecting various parts of the entire terminal device using various interfaces and lines.

[0099] The memory can be used to store the computer program, and the processor realizes various functions of the terminal device by running or executing the computer program stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function, etc.; the data storage area can store data created based on the use of the mobile phone, etc. In addition, the memory can include a high-speed random access memory and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0100] Based on the above method embodiment, the present invention provides a corresponding storage medium embodiment.

[0101] An embodiment of the present invention provides a storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute a method for generating a drone inspection task list as described in any one of the present inventions.

[0102] The storage medium is a computer-readable storage medium, and the computer program is stored in the computer-readable storage medium. When the computer program is executed by the processor, the steps of each of the above-mentioned method embodiments can be implemented. The computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunications signal, and a software distribution medium.

[0103] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for generating a UAV inspection task list, characterized in that: include: Obtain the unmanned aerial vehicle inspection instruction text to be processed, the user's identity information, and the unmanned aerial vehicle inspection instruction text last entered by the user; wherein the unmanned aerial vehicle inspection instruction text to be processed includes: inspection task start time text, inspection task end time text, and inspection interval text; Inputting the user identity information and the drone inspection instruction text input by the user last time into the user habit analysis model, so that the user habit analysis model outputs the user's language habit characteristics; Output inspection task parameters according to the user's language habit characteristics and inspection interval text; wherein the inspection task parameters include: interval type, interval unit, interval number and deadline; Determine the inspection task start time and inspection task end time according to the inspection task start time text and inspection task end time text; Generate an inspection task list according to the inspection task parameters, the inspection task start time and the inspection task end time.

2. A method for generating a UAV inspection task list according to claim 1, characterized in that: The construction of the user habit analysis model includes: Obtaining a number of sample users and a number of historical input samples of each sample user; wherein each historical input sample includes the language habit features of the sample user's previous historical input sample, the sample user's identity information, and the sample user's previous historical input sample; For each sample user, generate an initial user habit analysis sub-model for the current sample user based on the user identity information of the current sample user; The user habit analysis sub-model is generated by training the sample user identity information and the sample user's previous historical input sample as input to the initial user habit analysis sub-model and outputting the language habit features of the sample user's previous historical input sample until the initial user habit analysis sub-model converges. Construct a user habit analysis model based on each user habit analysis sub-model.

3. A method for generating a UAV inspection task list according to claim 2, characterized in that: The interval type includes periodic interval and fixed date. When the interval type is periodic interval, the deadline is empty. Generating the inspection task list according to the inspection task parameters, the inspection task start time and the inspection task end time includes: When the interval type is periodic interval, the inspection span is determined based on the interval unit and the number of intervals, and the inspection task list is generated based on the inspection span, the inspection task start time, and the inspection task end time; When the interval type is a fixed date, several inspection time nodes are determined according to the interval unit, interval quantity and deadline, and an inspection task list is generated according to the several inspection time nodes, the inspection task start time and the inspection task end time.

4. A method for generating a UAV inspection task list according to claim 3, characterized in that: Outputting inspection task parameters according to the user's language habit characteristics and inspection interval text includes: Determining the user's usual interval type description form, usual interval unit description form, usual interval quantity description form, and usual deadline description form according to the user's language habit characteristics; The information in the inspection interval text is extracted according to the user's usual interval type description form, usual interval unit description form, usual interval quantity description form and usual deadline description form, and the inspection task parameters are output.

5. A device for generating a UAV inspection task list, characterized in that: include: Data acquisition module, user analysis module and inspection task list generation module; The data acquisition module is used to obtain the unmanned aerial vehicle inspection instruction text to be processed, the user's identity information, and the unmanned aerial vehicle inspection instruction text input by the user last time; wherein the unmanned aerial vehicle inspection instruction text to be processed includes: the inspection task start time text, the inspection task end time text, and the inspection interval text; The user analysis module is configured to input the user identity information and the drone inspection instruction text input by the user last time into a user habit analysis model, so that the user habit analysis model outputs the user's language habit characteristics; The inspection task list generation module is used to output inspection task parameters based on the user's language habit characteristics and the inspection interval text; wherein the inspection task parameters include: interval type, interval unit, interval number and deadline; determine the inspection task start time and inspection task end time based on the inspection task start time text and the inspection task end time text; generate an inspection task list based on the inspection task parameters, the inspection task start time and the inspection task end time.

6. The device for generating a UAV inspection task list according to claim 5, wherein: It also includes a user habit analysis model building module; The user habit analysis model building module is used to obtain a number of sample users and a number of historical input samples of each sample user; wherein each historical input sample includes the language habit characteristics of the sample user's previous historical input sample, the sample user's identity information and the sample user's previous historical input sample; For each sample user, generate an initial user habit analysis sub-model for the current sample user based on the user identity information of the current sample user; The user habit analysis sub-model is generated by training the sample user identity information and the sample user's previous historical input sample as input to the initial user habit analysis sub-model and outputting the language habit features of the sample user's previous historical input sample until the initial user habit analysis sub-model converges. Construct a user habit analysis model based on each user habit analysis sub-model.

7. The device for generating a UAV inspection task list according to claim 6, wherein: The interval type includes periodic interval and fixed date. When the interval type is periodic interval, the deadline is empty. Generating the inspection task list according to the inspection task parameters, the inspection task start time and the inspection task end time includes: When the interval type is periodic interval, the inspection span is determined based on the interval unit and the number of intervals, and the inspection task list is generated based on the inspection span, the inspection task start time, and the inspection task end time; When the interval type is a fixed date, several inspection time nodes are determined according to the interval unit, interval quantity and deadline, and an inspection task list is generated according to the several inspection time nodes, the inspection task start time and the inspection task end time.

8. The device for generating a UAV inspection task list according to claim 7, wherein: Outputting inspection task parameters according to the user's language habit characteristics and inspection interval text includes: Determining the user's usual interval type description form, usual interval unit description form, usual interval quantity description form, and usual deadline description form according to the user's language habit characteristics; The information in the inspection interval text is extracted according to the user's usual interval type description form, usual interval unit description form, usual interval quantity description form and usual deadline description form, and the inspection task parameters are output.

9. A terminal device, characterized in that: The invention comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, a method for generating a drone inspection task list according to any one of claims 1 to 4 is implemented.

10. A storage medium, characterized in that: The storage medium includes a stored computer program, wherein, when the computer program is running, the device where the storage medium is located is controlled to execute the method for generating a drone inspection task list according to any one of claims 1 to 4.

Images