Construction method, device and equipment of unmanned aerial vehicle technical data and storage medium

Abstract

The invention discloses an unmanned aerial vehicle technical data construction method and device, equipment and a storage medium, and relates to the technical field of computers, and the method comprises the steps: extracting target cognitive behavior data of unmanned aerial vehicle aviation support personnel in a task execution process, so as to construct a target triple, and building a cognitive process model through employing a target BERT model; clustering knowledge elements used and maintained by the unmanned aerial vehicle to obtain a knowledge hierarchical framework, extracting unstructured data in the field of the unmanned aerial vehicle, and constructing a target knowledge model by using a knowledge graph technology; determining a cognitive vector of each stage in the cognitive process model; and determining a matching relationship between the cognitive process and the knowledge based on the similarity between the knowledge vector corresponding to the target knowledge model and the cognitive vector, and constructing technical data of the unmanned aerial vehicle in combination with the cognitive process model and the target knowledge model. Cognitive characteristics and knowledge requirements of a user in different stages are considered while the integrity of unmanned aerial vehicle technical data construction is ensured.

Description

A method, apparatus, device, and storage medium for constructing technical data for unmanned aerial vehicles (UAVs). Technical Field

[0001] This invention relates to the field of computer technology, and in particular to a method, apparatus, device, and storage medium for constructing technical data for unmanned aerial vehicles (UAVs). Background Technology

[0002] Technical documentation for medium and large-sized reconnaissance and strike UAVs serves as a crucial basis for air and ground crews in equipment use and maintenance. Traditional technical documentation architectures are typically divided according to functional modules or system components, lacking consideration for user cognitive processes and knowledge acquisition patterns. This results in insufficient overall effectiveness and guidance of the technical documentation, failing to meet actual user needs. Existing technologies employ a task-flow-based approach to technical documentation construction. This method divides technical documentation according to the user's task execution process, such as pre-flight checks, in-flight operations, and post-landing maintenance. While this approach considers user scenarios to some extent, it still suffers from a lack of consideration for user cognitive processes, a simplistic knowledge presentation style, and difficulties in updating and maintaining the documentation, impacting user learning efficiency and user experience.

[0003] As can be seen from the above, how to ensure the integrity of the construction of UAV technical data while taking into account the cognitive characteristics and knowledge needs of users at different stages is an urgent problem to be solved. Summary of the Invention

[0004] In view of this, the purpose of this invention is to provide a method, apparatus, device, and storage medium for constructing UAV technical data, which can ensure the integrity of the UAV technical data construction while taking into account the cognitive characteristics and knowledge needs of users at different stages. The specific solution is as follows: Firstly, this application provides a method for constructing UAV technical data, comprising: extracting target cognitive behavior data of UAV aviation support personnel during mission execution to obtain entities; constructing target triples based on the relationships between the entities; determining a comprehensive vector based on the target triples and using a target BERT model; the UAV aviation support personnel include UAV aircrew and UAV ground crew; establishing a bidirectional reasoning logic based on the target cognitive behavior data of the UAV aviation support personnel and the comprehensive vector; and using the bidirectional reasoning logic to establish a cognitive process model including a perception stage, a understanding stage, a memory stage, and an application stage; clustering the knowledge elements of UAV use and maintenance based on the job responsibilities corresponding to the UAV aviation support personnel to obtain knowledge levels. The framework extracts tacit knowledge from unstructured data in the UAV field. Based on the knowledge hierarchy framework and the tacit knowledge, a relational network is constructed using knowledge graph technology. A target knowledge model is established by combining incremental learning algorithms and a preset knowledge update interface. Each stage in the cognitive process model is described in natural language to obtain a corresponding descriptive language. Based on the descriptive language, the cognitive vectors of each stage are determined using the Word2Vec model and TF-IDF technology. The similarity between the knowledge vectors corresponding to the target knowledge model and the cognitive vectors is determined, and a corresponding similarity matrix is ​​constructed based on the similarity. The similarity matrix is ​​used to determine the matching relationship between the cognitive process and the knowledge. Technical information for UAVs is constructed based on the cognitive process model, the target knowledge model, and the matching relationship.

[0005] Optionally, the step of extracting target cognitive behavior data of UAV aviation support personnel during mission execution to obtain entities, constructing target triples based on the relationships between the entities, and determining a comprehensive vector based on the target triples and a target BERT model includes: collecting raw cognitive behavior data of UAV aviation support personnel during mission execution; preprocessing the raw cognitive behavior data to obtain target cognitive behavior data; extracting the cognitive behavior data to obtain entities; defining the relationships between the entities; constructing target triples based on the entities and the relationships; converting the target triples into natural language; encoding each natural language segment using a Sentence-BERT model to obtain language vectors; and performing average pooling on the language vectors to obtain a comprehensive vector.

[0006] Optionally, the step of establishing a bidirectional reasoning logic based on the target cognitive behavior data of the UAV aviation support personnel and the integrated vector, and using the bidirectional reasoning logic to establish a cognitive process model including the perception stage, understanding stage, memory stage, and application stage, includes: determining the behavioral decision data in the target cognitive behavior data of the UAV aviation support personnel; constructing a bidirectional reasoning logic including forward reasoning and backward reasoning based on the behavioral decision data and the integrated vector; and constructing a cognitive process model including the perception stage, understanding stage, memory stage, and application stage based on the bidirectional reasoning logic.

[0007] Optionally, the step of clustering knowledge elements related to UAV use and maintenance based on the job responsibilities of the UAV aviation support personnel to obtain a knowledge hierarchy framework, and extracting unstructured data in the UAV field to obtain tacit knowledge, includes: clustering knowledge elements related to UAV use and maintenance based on the job responsibilities and task execution requirements of the UAV aviation support personnel using a hierarchical clustering algorithm to obtain a knowledge hierarchy framework; and extracting unstructured data in the UAV field using natural language processing technology to obtain tacit knowledge.

[0008] Optionally, the step of constructing an association network based on the knowledge hierarchy framework and the tacit knowledge using knowledge graph technology, and establishing a target knowledge model by combining incremental learning algorithms and preset knowledge update interfaces, includes: integrating the tacit knowledge and the explicit knowledge in the knowledge elements to obtain integrated knowledge; filling the integrated knowledge into the knowledge hierarchy framework to obtain target knowledge; constructing an association network in the form of triples based on the target knowledge using knowledge graph technology; and establishing a target knowledge model containing a knowledge layer, a skill layer, and a problem-solving layer based on the association network using incremental learning algorithms and preset knowledge update interfaces.

[0009] Optionally, the step of describing each stage in the cognitive process model using natural language to obtain a corresponding descriptive language, and determining the cognitive vector of each stage based on the descriptive language using a Word2Vec model and TF-IDF technology, includes: describing each stage in the cognitive process model using natural language to obtain a corresponding descriptive language; converting each word in the descriptive language into a word vector using a Word2Vec model, and weighting the word vectors using TF-IDF technology to obtain a weighted word vector; and performing average pooling on the weighted word vectors to obtain the cognitive vector of each stage.

[0010] Optionally, determining the similarity between the knowledge vector corresponding to the target knowledge model and the cognitive vector, and constructing a corresponding similarity matrix based on the similarity, to determine the matching relationship between the cognitive process and knowledge using the similarity matrix, and constructing technical data for the UAV based on the cognitive process model, the target knowledge model, and the matching relationship, includes: converting the target knowledge model into knowledge vectors based on preset rules, determining the cosine similarity between the knowledge vectors and the cognitive vectors, and constructing a corresponding similarity matrix based on the cosine similarity; the knowledge vectors and the cognitive vectors have the same dimension; using the similarity matrix to determine the correspondence between each stage in the cognitive process model and each level in the target knowledge model, and determining the matching relationship between the cognitive process and knowledge based on the correspondence; constructing technical data for the UAV based on the cognitive process model, the target knowledge model, and the matching relationship; the technical data includes the type and composition of the technical data, the chapter structure and content composition, and the encoding system; obtaining feedback results from the user terminal regarding the technical data, and updating the technical data based on the feedback results.

[0011] Secondly, this application provides an apparatus for constructing UAV technical data, comprising: a comprehensive vector determination module, used to extract target cognitive behavior data of UAV aviation support personnel during mission execution to obtain entities, construct target triples based on the relationships between the entities, and determine a comprehensive vector based on the target triples and using a target BERT model; the UAV aviation support personnel include UAV aircrew and UAV ground crew; a cognitive model building module, used to establish bidirectional reasoning logic based on the target cognitive behavior data of the UAV aviation support personnel and the comprehensive vector, and use the bidirectional reasoning logic to establish a cognitive process model including a perception stage, a comprehension stage, a memory stage, and an application stage; and a knowledge model building module, used to cluster knowledge elements of UAV use and maintenance based on the job responsibilities corresponding to the UAV aviation support personnel to obtain a knowledge layer. The sub-framework extracts unstructured data from the UAV domain to obtain tacit knowledge. Based on the knowledge hierarchy framework and the tacit knowledge, it constructs an association network using knowledge graph technology and establishes a target knowledge model by combining incremental learning algorithms and preset knowledge update interfaces. The cognitive vector determination module describes each stage of the cognitive process model in natural language to obtain a corresponding descriptive language. Based on the descriptive language, it determines the cognitive vector for each stage using the Word2Vec model and TF-IDF technology. The technical data construction module determines the similarity between the knowledge vector corresponding to the target knowledge model and the cognitive vector, constructs a similarity matrix based on the similarity, and uses the similarity matrix to determine the matching relationship between the cognitive process and knowledge. Based on the cognitive process model, the target knowledge model, and the matching relationship, it constructs technical data for the UAV.

[0012] Thirdly, this application provides an electronic device, including: a memory for storing a computer program; and a processor for executing the computer program to implement the aforementioned method for constructing UAV technical data.

[0013] Fourthly, this application provides a computer-readable storage medium for storing a computer program, wherein the computer program, when executed by a processor, implements the aforementioned method for constructing UAV technical data.

[0014] This application extracts target cognitive behavior data of UAV aviation support personnel during mission execution to obtain various entities. Based on the relationships between these entities, target triples are constructed. A comprehensive vector is determined based on these target triples and a target BERT model. The UAV aviation support personnel include UAV aircrew and UAV ground crew. A bidirectional reasoning logic is established based on the target cognitive behavior data of the UAV aviation support personnel and the comprehensive vector. This bidirectional reasoning logic is then used to establish a cognitive process model including perception, understanding, memory, and application stages. Based on the job responsibilities corresponding to the UAV aviation support personnel, knowledge elements related to UAV use and maintenance are clustered to obtain a knowledge hierarchy framework. This framework is then used to process unstructured data in the UAV domain. The process involves extracting implicit knowledge, constructing an association network based on the knowledge hierarchy framework and the implicit knowledge using knowledge graph technology, and establishing a target knowledge model by combining incremental learning algorithms and a preset knowledge update interface. Each stage of the cognitive process model is described in natural language to obtain a corresponding descriptive language. Based on the descriptive language, the cognitive vectors for each stage are determined using the Word2Vec model and TF-IDF technology. The similarity between the knowledge vectors corresponding to the target knowledge model and the cognitive vectors is determined, and a corresponding similarity matrix is ​​constructed based on the similarity. This similarity matrix is ​​used to determine the matching relationship between the cognitive process and the knowledge. Finally, technical information about the UAV is constructed based on the cognitive process model, the target knowledge model, and the matching relationship.

[0015] As can be seen from the above, this application converts the thinking, judgment, and decision-making behaviors of UAV aviation support personnel during mission execution into triples, and encodes them into a unified-dimensional comprehensive vector using a target BERT model. Based on the comprehensive vector and cognitive behavior data, a bidirectional reasoning logic is formed to construct a cognitive model covering perception, understanding, memory, and application, aligning the technical information content with the thought process. Then, knowledge elements are clustered based on job responsibilities to form a multi-level knowledge framework, and an association network is constructed using unstructured data. A target knowledge model is established using incremental learning algorithms and a pre-defined knowledge update interface. The natural language descriptions in the cognitive model are converted into weighted cognitive vectors, and the similarity between the cognitive vectors and knowledge vectors is determined. In this way, based on similarity and combined with the cognitive process model and the target knowledge model, a technical information architecture that conforms to the user's cognitive patterns is obtained, helping users quickly locate the information they need, improving learning efficiency, and reducing training costs. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0017] Figure 1 is a flowchart of a method for constructing UAV technical data disclosed in this application; Figure 2 is a schematic diagram of a task coding disclosed in this application; Figure 3 is a schematic diagram of a task code classification disclosed in this application; Figure 4 is a schematic diagram of a page group number coding classification disclosed in this application; Figure 5 is a schematic diagram of a technical data update disclosed in this application; Figure 6 is a flowchart of a specific method for constructing UAV technical data disclosed in this application; Figure 7 is a schematic diagram of a device for constructing UAV technical data disclosed in this application; Figure 8 is a structural diagram of an electronic device disclosed in this application. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] Currently, traditional technical documentation architectures are typically divided according to functional modules or system components, lacking consideration for user cognitive processes and knowledge acquisition patterns. This results in insufficient overall effectiveness and guidance of technical documentation, making it difficult to meet users' actual needs. Therefore, this application provides a method for constructing UAV technical documentation. Based on similarity and combined with a cognitive process model and the target knowledge model, a technical documentation architecture that conforms to user cognitive patterns is obtained. This helps users quickly locate the information they need, improves learning efficiency, and reduces training costs.

[0020] Referring to Figure 1, this embodiment of the invention discloses a method for constructing UAV technical data, including: step S11, extracting target cognitive behavior data of UAV aviation support personnel during mission execution to obtain each entity, constructing target triples based on the correlation between the entities, and determining a comprehensive vector based on the target triples and using a target BERT model; the UAV aviation support personnel include UAV aircrew and UAV ground crew.

[0021] In this embodiment, cognitive behavior data of UAV aviation support personnel are collected throughout the entire process of performing flight missions, equipment maintenance, and fault handling to obtain target cognitive behavior data. The target cognitive behavior data is preprocessed and knowledge is extracted to obtain various entities, including flight parameter data, system components, fault diagnosis results, and fault reports. The relationships between these entities are defined, such as which systems / components correspond to which flight parameter data, which abnormal phenomena correspond to which flight parameter data, which faults can be diagnosed by flight parameter abnormalities, and the methods for handling abnormal situations seen by aviation support personnel. Then, triples are constructed based on the subject entities, relationships, and object entities. Triples are the smallest logical units for the structured expression of knowledge graphs.

[0022] It is understandable that after obtaining the triples, each triple is converted into a natural language sentence, i.e. The Sentence-BERT model (an improved BERT-based model; BERT (Bidirectional Encoder Representations from Transformers)) is used to encode each natural language sentence to obtain language vectors, and the corresponding formula is as follows: ;in, The language vector; The Sentence-BERT model; The natural language sentence; The language vector is defined as a d-dimensional real vector. Then, average pooling is performed on the language vector to obtain the composite vector, as shown in the following formula: ;in, The composite vector; The language vector; The total number of the natural language sentences.

[0023] Specifically, the step of extracting target cognitive behavior data of UAV aviation support personnel during mission execution to obtain entities, constructing target triples based on the relationships between the entities, and determining a comprehensive vector based on the target triples and a target BERT model includes: collecting raw cognitive behavior data of UAV aviation support personnel during mission execution; preprocessing the raw cognitive behavior data to obtain target cognitive behavior data; extracting the cognitive behavior data to obtain entities; defining the relationships between the entities; constructing target triples based on the entities and the relationships; converting the target triples into natural language; encoding each natural language segment using a Sentence-BERT model to obtain language vectors; and performing average pooling on the language vectors to obtain a comprehensive vector.

[0024] Step S12: Based on the target cognitive behavior data of the UAV aviation support personnel and the integrated vector, establish a two-way reasoning logic, and use the two-way reasoning logic to establish a cognitive process model including the perception stage, understanding stage, memory stage, and application stage.

[0025] In this embodiment, the target cognitive behavior data is extracted to obtain behavioral decision data, namely the decision-making process and judgment logic data of the UAV aviation support personnel when performing tasks; and combined with the comprehensive vector, a forward / backward chain bidirectional reasoning logic is established to construct a cognitive process model including the perception stage, understanding stage, memory stage, and application stage; the cognitive process model forms a traceable decision path through the semantic expression capability of knowledge graph, including key stages such as fault identification, fault analysis, and fault troubleshooting.

[0026] Specifically, the step of establishing a bidirectional reasoning logic based on the target cognitive behavior data of the UAV aviation support personnel and the comprehensive vector, and using the bidirectional reasoning logic to establish a cognitive process model including the perception stage, understanding stage, memory stage, and application stage, includes: determining the behavioral decision data in the target cognitive behavior data of the UAV aviation support personnel; constructing a bidirectional reasoning logic including forward reasoning and backward reasoning based on the behavioral decision data and the comprehensive vector; and constructing a cognitive process model including the perception stage, understanding stage, memory stage, and application stage based on the bidirectional reasoning logic.

[0027] Step S13: Based on the job responsibilities of the UAV aviation support personnel, cluster the knowledge elements of UAV use and maintenance to obtain a knowledge hierarchy framework. Extract unstructured data in the UAV field to obtain implicit knowledge. Based on the knowledge hierarchy framework and the implicit knowledge, construct an association network using knowledge graph technology, and establish a target knowledge model by combining incremental learning algorithms and preset knowledge update interfaces.

[0028] In this embodiment, based on the job responsibilities and task execution requirements of the UAV aviation support personnel, a hierarchical clustering algorithm is used to cluster and classify the knowledge elements related to UAV use and maintenance to obtain a knowledge hierarchy framework. This knowledge hierarchy framework corresponds to the core dimensions of the target knowledge model. Natural Language Processing (NLP) is used to extract tacit knowledge from unstructured data in the UAV domain. The unstructured text includes fault reports and maintenance work orders. Specifically, the process of clustering the knowledge elements related to UAV use and maintenance based on the job responsibilities of the UAV aviation support personnel to obtain a knowledge hierarchy framework, and extracting tacit knowledge from unstructured data in the UAV domain, includes: clustering the knowledge elements related to UAV use and maintenance based on the job responsibilities and task execution requirements of the UAV aviation support personnel using a hierarchical clustering algorithm to obtain a knowledge hierarchy framework; and extracting tacit knowledge from unstructured data in the UAV domain using natural language processing.

[0029] It is understood that after obtaining the tacit knowledge, explicit knowledge of UAV use and maintenance is acquired, including direct knowledge from operation manuals and system principle manuals. The explicit and tacit knowledge are integrated to obtain integrated knowledge, which is then filled into the knowledge hierarchy framework to obtain target knowledge. Based on the target knowledge, a knowledge graph topology network is constructed using knowledge graph technology, and a triplet-based knowledge association mapping mechanism is established. Combined with incremental learning algorithms and preset knowledge update interfaces, a target knowledge model is built, including a basic knowledge layer, a professional skills layer, and a problem-solving layer. The basic knowledge layer covers fundamental cognitive elements such as flight system principles and flight performance limitations. The professional skills layer integrates practical skills elements such as fault diagnosis methodologies, emergency response procedures, and maintenance operation specifications. The problem-solving outcome layer includes decision support capabilities and dynamic response capabilities in complex situations.

[0030] Specifically, the step of constructing a relational network based on the knowledge hierarchy framework and the tacit knowledge using knowledge graph technology, and establishing a target knowledge model by combining incremental learning algorithms and preset knowledge update interfaces, includes: integrating the tacit knowledge and the explicit knowledge in the knowledge elements to obtain integrated knowledge; filling the integrated knowledge into the knowledge hierarchy framework to obtain target knowledge; constructing a relational network in the form of triples based on the target knowledge using knowledge graph technology; and establishing a target knowledge model containing a knowledge layer, a skill layer, and a problem-solving layer based on the relational network using incremental learning algorithms and preset knowledge update interfaces.

[0031] Step S14: Describe each stage in the cognitive process model using natural language to obtain the corresponding descriptive language. Based on the descriptive language, determine the cognitive vector of each stage using the Word2Vec model (a related model for generating word vectors) and TF-IDF (Term Frequency-Inverse Document Frequency, i.e., a weighting technique).

[0032] In this embodiment, each stage in the cognitive process model is described using natural language. Let the cognitive process have k stages, then denoted as a set. Each stage Described by a natural language To define, this description is by It consists of 10 words, that is, the corresponding descriptive language is 10 words. The Word2Vec model is used to convert each word in the description language into a word vector, and the corresponding formula is as follows: ;in, Embedding is the operation of converting words into vectors; Let w be a word vector, that is, a d-dimensional numerical vector corresponding to a word w. For the language description, collect the word vectors corresponding to all valid words to form a word vector set, and the corresponding formula is as follows: ;in, The word vector corresponding to word w; The description language is defined here. Then, the arithmetic mean method is used to aggregate all word vectors in the word vector set into a global vector, which is obtained through average pooling, as shown in the following formula: ;in, The set of word vectors; The word vector is denoted as .

[0033] Furthermore, to highlight key terms in the description language, TF-IDF technology is introduced to weight the word vectors. Specifically, a corresponding corpus is constructed based on the description language at each stage. The TF-IDF weights corresponding to each word in the description language include term frequency and inverse document frequency, and the formulas corresponding to the TF-IDF weights are as follows: ;in, The term frequency represents the frequency of word w in the descriptive language. Frequency of occurrence in; Let be the inverse document frequency, where For the corpus The number of descriptive language documents containing the word 'w'; This represents the total number of stages in the cognitive process. The word vectors are weighted using the TF-IDF weights to obtain weighted word vectors, and then average pooling is performed on these weighted word vectors to obtain the cognitive vectors for each stage. The formula corresponding to each cognitive vector is as follows: ;in, The TF-IDF weights; Word vectors; The description language; The corpus in question.

[0034] Specifically, the step of describing each stage in the cognitive process model using natural language to obtain a corresponding descriptive language, and determining the cognitive vector for each stage based on the descriptive language using the Word2Vec model and TF-IDF technology, includes: describing each stage in the cognitive process model using natural language to obtain a corresponding descriptive language; converting each word in the descriptive language into word vectors using the Word2Vec model, and weighting the word vectors using TF-IDF technology to obtain weighted word vectors; and performing average pooling on the weighted word vectors to obtain the cognitive vector for each stage.

[0035] Step S15: Determine the similarity between the knowledge vector corresponding to the target knowledge model and the cognitive vector, and construct a corresponding similarity matrix based on the similarity, so as to use the similarity matrix to determine the matching relationship between the cognitive process and knowledge, and construct the technical information of the UAV based on the cognitive process model, the target knowledge model and the matching relationship.

[0036] In this embodiment, the cosine similarity algorithm is used to determine the cosine similarity between the knowledge vectors and the cognitive vectors corresponding to each level of the target knowledge model. The corresponding formula is as follows: ;in, The knowledge vector The modulus length; The cognitive vector The modulus length is determined. A corresponding similarity matrix is ​​constructed based on the cosine similarity. Each element in the similarity matrix represents the matching relationship between the cognitive process and knowledge. A dynamic knowledge chain is formed by analyzing the knowledge content and presentation methods required at different cognitive stages. For example, in the fault identification stage, knowledge such as the principles of the UAV system and common fault phenomena is required; in the fault analysis stage, knowledge such as fault diagnosis methods and case analysis is required; and in the fault troubleshooting stage, knowledge such as maintenance operation steps and precautions is required. The three stages are progressive, with the output of the former becoming the input of the latter, and the troubleshooting results are fed back to the analysis and identification stage, forming a closed loop of verification and optimization to obtain a dynamic knowledge chain. Technical data for the UAV is constructed based on the cognitive process model, the target knowledge model, and the matching relationship.

[0037] Specifically, determining the similarity between the knowledge vector corresponding to the target knowledge model and the cognitive vector, and constructing a corresponding similarity matrix based on the similarity, to determine the matching relationship between the cognitive process and knowledge using the similarity matrix, and constructing technical data for the UAV based on the cognitive process model, the target knowledge model, and the matching relationship, includes: converting the target knowledge model into knowledge vectors based on preset rules, determining the cosine similarity between the knowledge vectors and the cognitive vectors, and constructing a corresponding similarity matrix based on the cosine similarity; the knowledge vectors and the cognitive vectors have the same dimension; using the similarity matrix to determine the correspondence between each stage in the cognitive process model and each level in the target knowledge model, and determining the matching relationship between the cognitive process and knowledge based on the correspondence; constructing technical data for the UAV based on the cognitive process model, the target knowledge model, and the matching relationship; the technical data includes the type and composition of the technical data, the chapter structure and content composition, and the encoding system; obtaining feedback results from the user terminal regarding the technical data, and updating the technical data based on the feedback results.

[0038] It is understood that the UAV in this solution can be a medium-to-large reconnaissance and strike UAV. In one specific implementation, the technical data for the medium-to-large reconnaissance and strike UAV includes operation manuals (operator manuals and checklists), maintenance plan manuals (three-stage flight inspection, weekly inspection and storage), maintenance procedure manuals (airborne platform and ground station), troubleshooting and principle manuals (fault isolation, circuit diagrams), illustrated manuals (airborne platform and ground station), and maintenance procedure manuals (structural repair manual). The technical documentation includes the following chapters and content: Operator Manual: An introduction to the UAV system, performance data, interface and operation instructions for each workstation, system usage limitations, and normal and emergency operating procedures; Operator Checklist: The operator checklist provides normal and emergency procedures for each workstation to facilitate accurate operation and checks during each flight phase. The checklist content should be consistent with the normal and emergency procedures in the operator manual to maintain consistency; Work Card: The work card mainly provides maintenance opportunities and work items for each flight phase, weekly, special, conditional, calibration, and storage phases, along with the required maintenance procedures; Maintenance Personnel Checklist: The maintenance personnel checklist presents the inspection items for each flight phase in a tabular format; Maintenance Procedure Manual: The airborne system and ground station operation and maintenance manuals must introduce the various UAV systems and major airborne equipment (including their functions, main technical requirements, composition, working principles, and maintenance operations).

[0039] In addition, the chapter structure and content may also include: Fault Isolation Manual: providing necessary technical data for identifying and analyzing faults in various UAV systems, and providing troubleshooting methods and procedures; Circuit Diagram Manual: providing circuit diagrams and piping diagrams for various UAV systems; Structural Repair Manual: providing descriptions and repair information for the main and secondary structures of the UAV, permissible damage, repair requirements, repair procedures, and inspection and acceptance standards; List of Parts with Life Expirations: providing the first overhaul period, service life, and flight hours of parts with life expirations; Illustrated Parts Catalog: providing layout diagrams of various UAV systems and subsystems, illustrated diagrams of the installation of each finished product, a list of finished products, and a list of standard parts.

[0040] In this embodiment, the coding system in the technical documentation uses a six-digit, three-segment standard system to represent systems, subsystems, and components. The program class sets applicable task codes, each consisting of six parts, detailed in Figure 2. The first, second, and third parts are ATA (Advanced Technology Attachment) numbers, used to identify specific equipment. The fourth part can use numbers to define the maintenance functions to be performed. The fifth part, for tasks and subtasks identical to the first four parts, can be used to create unique codes for all tasks, with task numbers ranging from 801 to 999. The sixth part can consist of three letters or numbers, used to distinguish configurations, methods, technologies, etc. Figure 3 is a schematic diagram of a task code classification. Additionally, the technical documentation is page-numbered, with the corresponding page group number coding classification shown in Figure 4. Then, based on the cognitive characteristics and task requirements of the user (e.g., UAV ground crew), the target imaging method corresponding to the technical documentation is determined, and methods such as combining text and graphics, video demonstrations, and 3D animations are applied to improve user learning efficiency and experience.

[0041] It is understandable that the IETM (Interactive Electronic Technical Manual) of the UAV system is developed based on user feedback regarding the technical data and technological developments to ensure the accuracy and timeliness of the technical data. Figure 5 is a schematic diagram of technical data updates provided in this embodiment. Feedback issues from users during actual use of the technical data are obtained and categorized, such as operation, troubleshooting, and maintenance, to obtain a corresponding problem list. The target cognitive stage corresponding to each feedback issue in the problem list is analyzed to determine whether the knowledge supply of the technical data at the target cognitive stage matches user needs. Based on the judgment results, internal technical problems or external inquiries are answered, and the technical data is modified and a corresponding technical coordination order is issued to obtain the modified technical data. Regarding changes in the technical status of the UAV system itself, the matching degree between the changed user needs and the cognitive stage is analyzed, and the technical data is modified based on the obtained matching results to obtain the modified technical data. These technical status changes include technology upgrades, new fault discoveries, and the application of new maintenance methods. Then, it is determined whether the modified technical data will affect the use and maintenance of the UAV. If it will, a temporary change order is issued to notify relevant personnel to perform operations according to the temporary change order before the technical data is updated in order to avoid risks. The technical data change and temporary operation requirements are sent to the user terminal to ensure information synchronization. If it will not have an impact, the updated data content, technical status changes, user feedback processing results, and other information are regularly reported to the relevant parties.

[0042] As can be seen from the above, this application converts the thinking, judgment, and decision-making behaviors of UAV aviation support personnel during mission execution into triples, and encodes them into a unified-dimensional comprehensive vector using a target BERT model. Based on the comprehensive vector and cognitive behavior data, a bidirectional reasoning logic is formed to construct a cognitive model covering perception, understanding, memory, and application, aligning the technical information content with the thought process. Then, knowledge elements are clustered based on job responsibilities to form a multi-level knowledge framework, and an association network is constructed using unstructured data. A target knowledge model is established using incremental learning algorithms and a pre-defined knowledge update interface. The natural language descriptions in the cognitive model are converted into weighted cognitive vectors, and the similarity between the cognitive vectors and knowledge vectors is determined. In this way, based on similarity and combined with the cognitive process model and the target knowledge model, a technical information architecture that conforms to the user's cognitive patterns is obtained, helping users quickly locate the information they need, improving learning efficiency, and reducing training costs.

[0043] As can be seen from the above embodiments, this application forms a technical data architecture that conforms to the user's cognitive laws based on the cognitive process model and the target knowledge model. Therefore, the process of forming a technical data architecture that conforms to the user's cognitive laws based on the cognitive process model and the target knowledge model is described.

[0044] Referring to Figure 6, this embodiment of the invention discloses a specific method for constructing UAV technical data, including: In this embodiment, a cognitive process model is first constructed, the research objectives are determined, and cognitive behavior data of UAV aviation support personnel during mission execution is collected through field research, communication, and observation. The cognitive behavior data is preprocessed and classified to obtain the entities and the relationships between them. Target triples are constructed based on the entities and the relationships. The target triples are converted into natural language, and the natural language is encoded and averaged to obtain a comprehensive vector. Behavioral decision data is extracted from the cognitive behavior data, and a forward / backward chain bidirectional reasoning logic is established in conjunction with the comprehensive vector to construct an initial cognitive process model including a perception stage, a understanding stage, a memory stage, and an application stage. The initial cognitive process model is verified, and if the verification is successful, the corresponding cognitive process model is output.

[0045] Understandably, the construction objective of the target knowledge model (i.e., the deep capability knowledge model) is determined. Based on the job responsibility system and task execution requirements corresponding to the UAV aviation support personnel, a hierarchical clustering algorithm is used to cluster and classify the knowledge elements of UAV use and maintenance to obtain a knowledge hierarchy framework. Based on the implicit knowledge corresponding to unstructured data in the UAV field, and combined with the knowledge hierarchy framework, the target knowledge is obtained. The target knowledge is used to construct a topological network of the knowledge graph, and a knowledge association mapping mechanism in the form of triples is established. An initial knowledge model containing a basic knowledge layer, a professional skills layer, and a problem-solving layer is built by combining an incremental learning algorithm and a preset knowledge update interface. The initial knowledge model is verified. If the verification is successful, the corresponding target knowledge model is output; if the verification fails, the initial knowledge model is optimized until the target conditions are met to obtain the target knowledge model.

[0046] Furthermore, based on the natural language descriptions corresponding to each stage in the cognitive process model, corresponding cognitive vectors are determined. Based on the similarity between the cognitive vectors and the knowledge vectors corresponding to the target knowledge model, the matching relationship between the cognitive process and knowledge is determined. By combining the cognitive process model and the target knowledge model, technical data of the UAV can be constructed. Feedback results from the user on the technical data can be obtained, and the technical data can be updated based on the feedback results.

[0047] As can be seen from the above, this application constructs triples based on the cognitive behavior data of UAV aviation support personnel during mission execution. Using the comprehensive vector determined by these triples and combined with the cognitive behavior data, a bidirectional reasoning logic is formed to construct a cognitive model encompassing perception, understanding, memory, and application. Then, knowledge elements are clustered based on job responsibilities to form a multi-level knowledge framework, and an association network is constructed using unstructured data to establish a target knowledge model. In this way, based on the similarity between the cognitive vectors in the cognitive model and the knowledge vectors in the target knowledge model, and combined with the cognitive process model and the target knowledge model, a technical data architecture is constructed to meet personalized user needs, enhance user experience, and reduce training costs.

[0048] Accordingly, referring to Figure 7, this application also provides a device for constructing UAV technical data, including: a comprehensive vector determination module 11, used to extract target cognitive behavior data of UAV aviation support personnel during mission execution to obtain various entities, construct target triples based on the correlation between the entities, and determine a comprehensive vector based on the target triples and using a target BERT model; the UAV aviation support personnel include UAV aircrew and UAV ground crew; a cognitive model establishment module 12, used to establish bidirectional reasoning logic based on the target cognitive behavior data of the UAV aviation support personnel and the comprehensive vector, and use the bidirectional reasoning logic to establish a cognitive process model including a perception stage, a understanding stage, a memory stage, and an application stage; and a knowledge model establishment module 13, used to cluster the knowledge elements of UAV use and maintenance based on the job responsibilities corresponding to the UAV aviation support personnel, in order to A knowledge hierarchy framework is obtained, and unstructured data in the UAV field is extracted to obtain tacit knowledge. Based on the knowledge hierarchy framework and the tacit knowledge, an association network is constructed using knowledge graph technology, and a target knowledge model is established by combining incremental learning algorithms and preset knowledge update interfaces. A cognitive vector determination module 14 is used to describe each stage in the cognitive process model in natural language to obtain a corresponding descriptive language. Based on the descriptive language, the cognitive vector of each stage is determined using the Word2Vec model and TF-IDF technology. A technical data construction module 15 is used to determine the similarity between the knowledge vector corresponding to the target knowledge model and the cognitive vector, and construct a corresponding similarity matrix based on the similarity to determine the matching relationship between the cognitive process and knowledge. Technical data of the UAV is constructed based on the cognitive process model, the target knowledge model, and the matching relationship.

[0049] In some specific embodiments, the comprehensive vector determination module 11 may specifically include: a behavior data preprocessing unit, used to collect raw cognitive behavior data of UAV aviation support personnel during mission execution, and preprocess the raw cognitive behavior data to obtain target cognitive behavior data; a triplet construction unit, used to extract the cognitive behavior data to obtain each entity, define the association relationship between each entity, and construct target triplets based on each entity and the association relationship; and a language encoding unit, used to convert the target triplets into natural language, and encode each natural language using the Sentence-BERT model to obtain language vectors, and perform average pooling on the language vectors to obtain a comprehensive vector.

[0050] In some specific embodiments, the cognitive model building module 12 may specifically include: a reasoning logic building unit, used to determine the behavioral decision data in the target cognitive behavior data of the UAV aviation support personnel, and to build a bidirectional reasoning logic including forward reasoning and backward reasoning based on the behavioral decision data and the comprehensive vector; and a cognitive model building unit, used to build a cognitive process model including a perception stage, a comprehension stage, a memory stage, and an application stage based on the bidirectional reasoning logic.

[0051] In some specific embodiments, the knowledge model building module 13 may include: a knowledge element clustering unit, used to cluster knowledge elements related to the use and maintenance of UAVs based on the job responsibilities and task execution requirements of the UAV aviation support personnel and using a hierarchical clustering algorithm to obtain a knowledge hierarchy framework; and a data extraction unit, used to extract unstructured data in the UAV field using natural language processing technology to obtain tacit knowledge.

[0052] In some specific embodiments, the knowledge model building module 13 may specifically include: a knowledge integration unit, used to integrate the implicit knowledge and the explicit knowledge in the knowledge elements to obtain integrated knowledge; an association network construction unit, used to fill the integrated knowledge into the knowledge hierarchy framework to obtain target knowledge, and construct an association network in the form of triples based on the target knowledge and using knowledge graph technology; and a knowledge model building unit, used to build a target knowledge model including a knowledge layer, a skill layer, and a problem-solving layer based on the association network and using an incremental learning algorithm and a preset knowledge update interface.

[0053] In some specific embodiments, the cognitive vector determination module 14 may specifically include: a description language determination unit, used to perform natural language descriptions on each stage in the cognitive process model to obtain corresponding description languages; a word vector weighting unit, used to convert each word in the description language into word vectors using the Word2Vec model, and use TF-IDF technology to weight the word vectors to obtain weighted word vectors; and a vector average pooling unit, used to perform average pooling on the weighted word vectors to obtain the cognitive vectors for each stage.

[0054] In some specific embodiments, the technical data construction module 15 may specifically include: a matrix construction unit, used to convert the target knowledge model into knowledge vectors based on preset rules, determine the cosine similarity between the knowledge vectors and the cognitive vectors, and construct a corresponding similarity matrix based on the cosine similarity; the knowledge vectors and the cognitive vectors have the same dimension; a matching relationship determination unit, used to use the similarity matrix to determine the correspondence between each stage in the cognitive process model and each level in the target knowledge model, and to determine the matching relationship between the cognitive process and knowledge based on the correspondence; a technical data construction unit, used to construct technical data for the UAV based on the cognitive process model, the target knowledge model, and the matching relationship; the technical data includes the type and composition of the technical data, the chapter structure and content composition, and the encoding system; and a technical data updating unit, used to obtain feedback results from the user terminal regarding the technical data, and update the technical data based on the feedback results.

[0055] Furthermore, this application also discloses an electronic device. FIG8 is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content in the figure should not be considered as any limitation on the scope of use of this application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 is used to store a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the method for constructing UAV technical data disclosed in any of the foregoing embodiments. Additionally, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0056] In this embodiment, the power supply 23 is used to provide operating voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol it follows can be any communication protocol applicable to the technical solution of this application, and is not specifically limited here; the input / output interface 25 is used to acquire external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs, and is not specifically limited here.

[0057] In addition, the memory 22, as a carrier for resource storage, can be a read-only memory, random access memory, disk or optical disk, etc. The resources stored thereon can include operating system 221, computer program 222, etc., and the storage method can be temporary storage or permanent storage.

[0058] The operating system 221 is used to manage and control the various hardware devices on the electronic device 20 and the computer program 222, which may be Windows Server, Netware, Unix, Linux, etc. In addition to including a computer program capable of performing the method for constructing UAV technical data executed by the electronic device 20 as disclosed in any of the foregoing embodiments, the computer program 222 may further include computer programs capable of performing other specific tasks.

[0059] Furthermore, this application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the aforementioned method for constructing UAV technical data. Specific steps of this method can be found in the corresponding content disclosed in the foregoing embodiments, and will not be repeated here.

[0060] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section.

[0061] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0062] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0063] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0064] The technical solutions provided in this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for constructing technical data for unmanned aerial vehicles (UAVs), characterized in that, include: This paper extracts target cognitive behavior data of UAV aviation support personnel during mission execution to obtain various entities. Based on the relationships between these entities, target triples are constructed. A comprehensive vector is then determined using the target triples and a target BERT model. The UAV aviation support personnel include both aircrew and ground crew. A bidirectional reasoning logic is established based on the target cognitive behavior data and the comprehensive vector. This logic is then used to build a cognitive process model including perception, understanding, memory, and application stages. Based on the job responsibilities of the UAV aviation support personnel, knowledge elements related to UAV use and maintenance are clustered to obtain a knowledge hierarchy framework. This process is used to extract data from unstructured data in the UAV domain. The process involves: acquiring implicit knowledge; constructing an association network based on the knowledge hierarchy framework and the implicit knowledge using knowledge graph technology; establishing a target knowledge model by combining incremental learning algorithms and a preset knowledge update interface; describing each stage of the cognitive process model using natural language to obtain a corresponding descriptive language; determining the cognitive vector for each stage based on the descriptive language using the Word2Vec model and TF-IDF technology; determining the similarity between the knowledge vector corresponding to the target knowledge model and the cognitive vector; constructing a corresponding similarity matrix based on the similarity; determining the matching relationship between the cognitive process and knowledge using the similarity matrix; and constructing technical data for the UAV based on the cognitive process model, the target knowledge model, and the matching relationship.

2. The method for constructing UAV technical data according to claim 1, characterized in that, The process of extracting target cognitive behavior data of UAV aviation support personnel during mission execution to obtain entities, constructing target triples based on the relationships between the entities, and determining a comprehensive vector based on the target triples and a target BERT model includes: collecting raw cognitive behavior data of UAV aviation support personnel during mission execution; preprocessing the raw cognitive behavior data to obtain target cognitive behavior data; extracting the cognitive behavior data to obtain entities; defining the relationships between the entities; constructing target triples based on the entities and the relationships; converting the target triples into natural language; encoding each natural language segment using a Sentence-BERT model to obtain language vectors; and performing average pooling on the language vectors to obtain a comprehensive vector.

3. The method for constructing UAV technical data according to claim 1, characterized in that, The step of establishing a bidirectional reasoning logic based on the target cognitive behavior data of the UAV aviation support personnel and the comprehensive vector, and using the bidirectional reasoning logic to establish a cognitive process model including the perception stage, understanding stage, memory stage, and application stage, includes: determining the behavioral decision data in the target cognitive behavior data of the UAV aviation support personnel; constructing a bidirectional reasoning logic including forward reasoning and backward reasoning based on the behavioral decision data and the comprehensive vector; and constructing a cognitive process model including the perception stage, understanding stage, memory stage, and application stage based on the bidirectional reasoning logic.

4. The method for constructing UAV technical data according to claim 1, characterized in that, The process involves clustering knowledge elements related to UAV use and maintenance based on the job responsibilities of the UAV aviation support personnel to obtain a knowledge hierarchy framework, and extracting tacit knowledge from unstructured data in the UAV field. This includes: clustering knowledge elements related to UAV use and maintenance based on the job responsibilities and task execution requirements of the UAV aviation support personnel using a hierarchical clustering algorithm to obtain a knowledge hierarchy framework; and extracting tacit knowledge from unstructured data in the UAV field using natural language processing technology.

5. The method for constructing UAV technical data according to claim 1, characterized in that, The process of constructing a relational network based on the knowledge hierarchy framework and the implicit knowledge, and establishing a target knowledge model by combining incremental learning algorithms and preset knowledge update interfaces, includes: integrating the implicit knowledge and explicit knowledge in the knowledge elements to obtain integrated knowledge; filling the integrated knowledge into the knowledge hierarchy framework to obtain target knowledge; constructing a relational network in the form of triples based on the target knowledge and using knowledge graph technology; and establishing a target knowledge model containing a knowledge layer, a skill layer, and a problem-solving layer based on the relational network and using incremental learning algorithms and preset knowledge update interfaces.

6. The method for constructing UAV technical data according to claim 1, characterized in that, The step of describing each stage in the cognitive process model using natural language to obtain a corresponding descriptive language, and determining the cognitive vector for each stage based on the descriptive language using a Word2Vec model and TF-IDF technology, includes: describing each stage in the cognitive process model using natural language to obtain a corresponding descriptive language; converting each word in the descriptive language into word vectors using a Word2Vec model, and weighting the word vectors using TF-IDF technology to obtain weighted word vectors; and performing average pooling on the weighted word vectors to obtain the cognitive vector for each stage.

7. The method for constructing UAV technical data according to any one of claims 1 to 6, characterized in that, The process of determining the similarity between the knowledge vector corresponding to the target knowledge model and the cognitive vector, and constructing a corresponding similarity matrix based on the similarity, to determine the matching relationship between the cognitive process and knowledge using the similarity matrix, and constructing technical data for the UAV based on the cognitive process model, the target knowledge model, and the matching relationship, includes: converting the target knowledge model into knowledge vectors based on preset rules, determining the cosine similarity between the knowledge vectors and the cognitive vectors, and constructing a corresponding similarity matrix based on the cosine similarity; the knowledge vectors and the cognitive vectors have the same dimension; using the similarity matrix to determine the correspondence between each stage in the cognitive process model and each level in the target knowledge model, and determining the matching relationship between the cognitive process and knowledge based on the correspondence; constructing technical data for the UAV based on the cognitive process model, the target knowledge model, and the matching relationship; the technical data includes the type and composition of the technical data, the chapter structure and content composition, and the encoding system; obtaining feedback results from the user terminal regarding the technical data, and updating the technical data based on the feedback results.

8. A device for constructing technical data for unmanned aerial vehicles (UAVs), characterized in that, include: The comprehensive vector determination module extracts target cognitive behavior data of UAV aviation support personnel during mission execution to obtain various entities, constructs target triples based on the relationships between these entities, and determines the comprehensive vector based on the target triples and a target BERT model. The UAV aviation support personnel include UAV aircrew and UAV ground crew. The cognitive model building module establishes bidirectional reasoning logic based on the target cognitive behavior data of the UAV aviation support personnel and the comprehensive vector, and uses this bidirectional reasoning logic to build a cognitive process model including perception, understanding, memory, and application stages. The knowledge model building module clusters knowledge elements related to UAV use and maintenance based on the job responsibilities of the UAV aviation support personnel to obtain a knowledge hierarchy framework, addressing the unstructured aspects of the UAV domain. The system extracts implicit knowledge from data, constructs a relational network based on the knowledge hierarchy framework and implicit knowledge using knowledge graph technology, and establishes a target knowledge model by combining incremental learning algorithms and preset knowledge update interfaces. A cognitive vector determination module describes each stage of the cognitive process model in natural language to obtain a corresponding descriptive language, and determines the cognitive vector for each stage based on the descriptive language using the Word2Vec model and TF-IDF technology. A technical data construction module determines the similarity between the knowledge vector corresponding to the target knowledge model and the cognitive vector, constructs a similarity matrix based on the similarity, uses the similarity matrix to determine the matching relationship between the cognitive process and knowledge, and constructs technical data for the UAV based on the cognitive process model, the target knowledge model, and the matching relationship.

9. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program to implement the method for constructing UAV technical data as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, Used to store computer programs, wherein the computer programs, when executed by a processor, implement the method for constructing UAV technical data as described in any one of claims 1 to 7.

Images