Civil aviation logistics data exchange method
By establishing an intelligent routing model and automatic correction mechanism in the civil aviation logistics data exchange method, and dynamically adjusting the data exchange path and format, the problem of inefficient data exchange caused by fixed data processing mode in the prior art is solved, and more efficient and flexible data exchange is achieved.
Patent Information
- Application Number
- CN202510679198.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-26
- Publication Date
- 2025-06-27
- Estimated Expiration
- 2045-05-26
AI Technical Summary
In the prior art, the data processing process mode is fixed, which is difficult to adapt to the processing needs of different data types, resulting in inefficient data exchange.
By providing a civil aviation logistics data exchange method, it includes receiving data to be exchanged, establishing an intelligent routing model, selecting the data exchange path and ideal switching area, using the automatic correction mechanism to complete verification of incomplete data information, forming a preprocessed data set, and converting the data into a target data set through the data transcoding engine.
It realizes dynamic adjustment of data exchange mode, improves data exchange efficiency, ensures the accuracy and completeness of address information, and uses aviation semantic network technology to interoperate data in different formats to improve data availability and value.
Smart Images

Figure CN120223612A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of data processing, and particularly to a civil aviation logistics data exchange method. Background Art
[0002] In the field of civil aviation logistics, there is a temporary data communication interconnection path established between multiple data terminal devices (DTEs) to achieve cargo tracking, management, and optimization. The purpose of data exchange is not only to obtain standardized logistics information, such as general data like the flight number, takeoff and landing time, weight, and volume of goods, which can be easily read, written, added, deleted, etc. under a general system architecture. However, with the complexity and diversification of logistics operations, more and more non-general data has emerged, such as cargo codes unique to specific airlines, handling requirements for special goods, and cargo photos or schematic diagrams edited by different graphic applications. Therefore, in the field of civil aviation logistics, there is an urgent need for an efficient and flexible data exchange method that can automatically identify and process various general and non-general data to ensure the accurate transmission and timely processing of logistics information, thereby improving the operation efficiency of the entire logistics link and customer satisfaction.
[0003] The Chinese invention patent with the application number 202311287788.4 provides a data exchange method and platform, which obtains the header information of the data to be exchanged, identifies user requirements, selects a data exchange area and the corresponding relevant application program. Each data exchange area generates a basic identification file and compares it with the data to be exchanged to obtain a first basic identification file, and determines the exchange object of the data to be exchanged according to the first basic identification file.
[0004] However, in the prior art, the data processing flow pattern is fixed and it is difficult to adapt to the processing requirements of different data types. Especially during the data processing process, the collaborative work between each exchange area depends on the comparison of basic identification files, resulting in low data exchange efficiency. Summary of the Invention
[0005] By providing a civil aviation logistics data exchange method, the present application solves the problem of low data exchange efficiency caused by the fixed data processing mode in the prior art, and achieves the technical effect of dynamically adjusting the data exchange mode and improving the data exchange efficiency.
[0006] The present application provides a civil aviation logistics data exchange method, and the method includes: S100: Receive the data to be exchanged, establish an intelligent routing model, select a data exchange path and an ideal exchange area according to the information of the data to be exchanged and the historical trust chain, and perform complement verification on the incomplete information of the data to be exchanged through an automatic correction mechanism to form a preprocessed data set; S200: Establish a data transcoding engine to receive the preprocessed data set and convert the preprocessed data set into a target data set; specifically including: identifying the load condition of the current ideal exchange area, determining the final exchange area, and converting the data information to be exchanged into target data; using aviation semantic web technology to further standardize the remaining data in the preprocessed data set to form standard remaining data; encapsulating the target data and the standard remaining data into a target data set; S300: Receive the target data set and transmit it to the next transmission node according to the data exchange path.
[0007] Further, the data information to be exchanged includes data type, source, and data exchange requirements. The data exchange requirements refer to the data format to be converted, recipient information, and data transmission conditions. The source refers to the address information of the uploader and the recipient; the data exchange path refers to the sequence of all transmission nodes and connections that the data passes through from the starting point to the target point. The transmission node refers to each entity in the data exchange path; the preprocessed data set includes the complemented data information to be exchanged, the data exchange path, and the ideal exchange area; the historical trust chain is obtained through analysis by the enterprise trust chain database and the trust chain evaluation module.
[0008] Further, the enterprise trust chain database includes the historical sent data, recipient feedback data, and data quality evaluation data of each enterprise; the trust chain evaluation module scores the trust level of each data exchange path according to the evaluation effect of historical data transmission, and selects the data exchange path with the highest trust level score as the historical trust chain.
[0009] Further, the automatic correction mechanism includes address verification and address completion. The address verification verifies the address information in the data information to be exchanged according to all known valid addresses and returns the result; the address completion fills in the incomplete address information through a filling method for valid but partially incomplete address information, and performs secondary verification on the completed address.
[0010] Further, the intelligent routing model uses common exchange paths as basic data and uses a deep neural network as the basic model for training; among them, all completed data exchange path information is collected from the historical data exchange records, and for each collected data exchange path, the occurrence frequency is counted; a frequency base and a frequency threshold are preset. The frequency threshold is the product of the frequency base and the total number of data exchange paths; the paths with occurrence frequencies exceeding the frequency threshold are regarded as common exchange paths.
[0011] Further, in step S100, when selecting a data exchange path, it further includes: based on the historical trust chain as the basic data, establishing a data source archive, combining the current data information to be exchanged, evaluating the comprehensive situation of each data exchange path in the data source archive in real time, and at the same time, generating an exchange path priority queue according to the enterprise's historical data exchange path and demand characteristics, establishing a path conflict detection mechanism, monitoring the usage of each path in real time, and dynamically adjusting the data exchange task.
[0012] Further, the data source archive takes the enterprise as the starting point and the historical data exchange path as the development line, recording each enterprise's historical data exchange path, exchange area, historical transmission nodes, and related performance indicators. The performance indicators include usage time, transmission speed, and security.
[0013] Further, the comprehensive situation includes the real-time load, historical performance, security index, and estimated timeliness of the data exchange path. The estimated timeliness refers to the total time used for each data exchange path, the time used for each transmission node respectively, and the transmission success rate.
[0014] Further, in step S200, establishing a data transcoding engine further includes establishing a dynamic adaptation model for identifying unknown data types, setting a feedback loop, setting conversion rules according to the identification results, and using the conversion rules to update the dynamic adaptation model; further analyzing the hierarchical structure, field types, and relationships of unknown data types, as well as repetition patterns, sequences, and association rules, and parsing the data structure content to extract key structure information; formulating rules for converting unknown data types into standard formats according to the analysis results; and updating the aviation data semantic network.
[0015] Further, the dynamic adaptation model is constructed based on the random forest algorithm. The parsing of the data structure content is performed using natural language processing technology to extract key structure information; the update of the aviation data semantic network integrates the information of unknown data types into the aviation data semantic network. The specific steps are as follows: representing the information of the new data type using the Resource Description Framework, constructing RDF triples to describe the entities, attributes, and relationships in the data; adding the RDF information to the aviation data semantic network, updating the ontology and vocabulary in the network to include relevant concepts of the new data type; using semantic reasoning tools to check the consistency of the updated semantic network.
[0016] One or more technical solutions provided in this application have at least the following technical effects or advantages: By selecting common and efficient data exchange paths through an intelligent routing model, the latency and error rate of data transmission are reduced, achieving the effect of improving the overall data exchange efficiency; an automatic correction mechanism is established to achieve address verification and completion, ensuring the accuracy and integrity of address information, and achieving the effect of quickly solving basic information problems and improving data processing efficiency; a data transcoding engine is established and the aviation semantic web technology is used to standardize the data, enabling interoperability of different formats of data, and achieving the effect of improving data availability and value. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] Figure 1 FIG. is a schematic diagram of the overall process of a civil aviation logistics data exchange method in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS
[0018] To facilitate the understanding of the present invention, the present application will be described more comprehensively with reference to the relevant drawings; the drawings show preferred embodiments of the present invention, however, the present invention may be implemented in many different forms and is not limited to the embodiments described herein; on the contrary, these embodiments are provided to make the disclosure of the present invention more thorough and comprehensive.
[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs; the terms used in the description of the present invention in this specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention; the term "and / or" used herein includes any and all combinations of one or more of the related listed items.
[0020] Embodiment 1: As Figure 1 shown, a civil aviation logistics data exchange method, the method comprising: S100: Receive data to be exchanged, establish an intelligent routing model, select a data exchange path and an ideal exchange area according to the data information to be exchanged and the historical trust chain, and perform complement verification on the incomplete data information to be exchanged through an automatic correction mechanism to form a preprocessed data set; In some embodiments, the data to be exchanged comes from the exchange object. In civil aviation logistics, it generally originates from the transmission path of cargo transportation and each transmission node. The data exchange path refers to the sequence of all transmission nodes and connections that the data passes through from the starting point to the target point. The transmission node refers to each entity or system in the data exchange path. For example, in civil aviation data exchange, the data transmission path from the shipper to the freight forwarder, then to the cargo station, and finally to the airline is a data exchange path. In this application, it mainly focuses on the goods starting from the airline and reaching the destination of the shipper. In different embodiments, the selected starting point and ending point are not the same. This embodiment only describes one of the transmission methods. In the data exchange path, entities such as the shipper, freight forwarder, cargo station, and airline are all transmission nodes in the path. Data needs to be received and transmitted on each transmission path, sharing data with the downstream and returning data and related data status to the upstream. A corresponding data interface needs to be set at each transmission node, defining a clear data receiving interface and supporting the reception of multiple data formats. When receiving data, first, security verification of the received data is required, including authentication of the data uploader, data integrity verification, and security check. Regarding the data processing direction, data verification and data security check are well-known technical means in the art, and this application does not make specific limitations.
[0021] In some embodiments, the intelligent routing model is trained using a common switching path as the basic data and a deep neural network as the basic model. Among them, all completed data exchange path information is collected from the historical data exchange records, including the starting node, target node, and all intermediate nodes of each exchange. For each collected data exchange path, its occurrence frequency (i.e., the number of occurrences) is counted. A frequency base and a frequency threshold are preset. The frequency threshold is the product of the frequency base and the total number of data exchange paths. The paths with occurrence frequencies exceeding the frequency threshold are regarded as common switching paths. To ensure the timeliness of the intelligent routing model, all data exchange paths within a certain period of time need to be obtained, and the specific time period is set according to the actual situation. Therefore, the total number of data exchange paths is not fixed. For example, within the set data time limit, there are a total of 1000 paths, and the set frequency base is 10%. Then the frequency threshold is 100 times, and the paths with occurrence frequencies exceeding 100 times are regarded as common switching paths. The common switching paths are extracted from all paths as the basic data of the intelligent routing model. Each data exchange path is encoded into a format suitable for the input of a deep neural network by representing nodes as vectors (e.g., using one-hot encoding or embedding vectors) and representing the path as a sequence of node vectors. A training dataset is created, where each sample is a path encoding and its corresponding target node. A recurrent neural network is selected as the network architecture, including the input layer, hidden layer, and output layer of the network. The input layer should be able to accept the path encoding as input; the hidden layer is responsible for learning the feature representation of the path; the output layer should be able to predict the next node or the target node; the model is trained using the training dataset. During the training process, the network will adjust its weights through the backpropagation algorithm to minimize the prediction error (such as cross-entropy loss), and an optimization algorithm is used to update the weights of the network.
[0022] In some embodiments, for the data to be exchanged that has passed the data security check, the intelligent routing model is used to initially identify the information of the data to be exchanged. The information of the data to be exchanged includes the data type, source, and data exchange requirements. The data exchange requirements refer to the data format to be converted, recipient information, and data transmission conditions. The source refers to the address information of the uploader and the recipient. In specific applications, different goods transportation has different conditions. To ensure user satisfaction, the necessary conditions for goods transportation must be met. The preprocessed data set includes the complemented information of the data to be exchanged, the data exchange path, and the ideal exchange area; the preprocessed data set includes the complemented information of the data to be exchanged, the data exchange path, and the ideal exchange area; the historical trust chain is obtained through the analysis of the enterprise trust chain database and the trust chain evaluation module. The enterprise trust chain database includes the historical sent data, recipient feedback data, and data quality evaluation data of each enterprise; the trust chain evaluation module scores the trust level of each data exchange path according to the evaluation effect of historical data transmission, and selects the data exchange path with the highest trust level score as the historical trust chain.
[0023] In some embodiments, according to the information of the data to be exchanged and the historical trust chain, the current information of the data to be exchanged, the current several candidate data exchange paths, and exchange areas are further evaluated. The evaluation indicators include but are not limited to the real-time load conditions of the data exchange path and exchange area, the security of data transmission, and the timeliness of data transmission, etc. According to the real-time comparison of different data exchange paths and exchange areas, and comparing with the comprehensive evaluation effect of the historical trust chain, the optimal data exchange path and ideal exchange area are selected. When selecting an exchange area, each exchange area generates a pretest file format according to the information of the data to be exchanged. The pretest file format is a brief verification file used to verify whether it meets the data exchange requirements of the data to be exchanged, and a compliance degree is generated. The exchange area with the highest compliance degree is selected as the ideal exchange area. In some embodiments, if there is a difference between the selected ideal exchange area and the selected data exchange path, the data exchange path where the ideal exchange area is located is preferably selected to ensure the standard degree of data transmission.
[0024] In some embodiments, the automatic correction mechanism includes address verification and address completion. The address verification verifies the address information in the data information to be exchanged according to all known valid addresses and returns a result. All currently known valid addresses are pre-stored to form a list of valid addresses. After obtaining the data information to be exchanged, the address information in the data information to be exchanged is verified one by one according to the known list of valid addresses. If the address in the data information to be exchanged is found in the list of valid addresses, the verification passes. If it is not in the list of valid addresses, it is further verified whether it conforms to a predetermined address pattern, that is, the address format pattern used by enterprises. If it conforms to the predetermined address pattern, the verification passes and the address information in the data information to be exchanged is added to the list of valid addresses; if it is not in the list of valid addresses and does not conform to the predetermined fixed pattern, the verification fails and it is transmitted back to the uploader for verification. The address completion is to complete the address information that is valid but partially incomplete through a filling method, and perform secondary verification on the completed address. The address completion is for the address information that has passed the verification but has incomplete information content. The filling method refers to string matching, pattern recognition, or using a machine learning algorithm model for completion. For example, the sequence-to-sequence model in the machine learning algorithm model is used for completion. The specific steps are as follows: Generate through historical data input by users, public address databases, or synthetic data, and collect a data set containing the corresponding relationship between complete addresses and incomplete addresses. Segment the addresses, encode the segmented addresses, prepare the training set, validation set, and test set to ensure reasonable data distribution. Select an encoder-decoder architecture, where the encoder processes the input incomplete address and the decoder generates the complete address. Define hyperparameters such as the number of layers, hidden units, and embedding dimensions of the encoder and decoder. The setting of hyperparameters needs to be adjusted according to the data information and actual requirements, and no specific restrictions are made here. When processing long sequences, an attention mechanism needs to be added to improve the model performance. Select cross-entropy loss to measure the difference between the model prediction and the real address, select the corresponding optimizer to update the model weights, train the model using the preprocessed data set, and minimize the loss function by iteratively optimizing the model parameters. Monitor the loss during the training process and the performance on the validation set to prevent overfitting. Deploy the trained model into the automatic correction mechanism to ensure that the model can efficiently process real-time requests, implement an interface that allows the address information in the data exchange request to be passed to the model for completion. When a request containing an incomplete address is received, use the model to generate possible complete addresses. Select the best completion result according to the confidence of the model. Perform address verification on the completed address again. If the verification passes, subsequent operations can be carried out.
[0025] S200: Establish a data transcoding engine to receive the preprocessed data set and convert the preprocessed data set into a target data set. Specifically, it includes: identifying the load condition of the current ideal exchange area, determining the final exchange area, and converting the data information to be exchanged into target data; using the aviation semantic web technology to further standardize the remaining data in the preprocessed data set to form standard remaining data; encapsulating the target data and the standard remaining data into a target data set. In some embodiments, the data transcoding engine contains several exchange areas. The exchange area is a standard area for converting different data formats, which is divided according to the conversion between different formats. The data transcoding engine can identify and distinguish different exchange areas, determine whether to use the ideal exchange area according to the load condition of the ideal exchange area, realize real-time monitoring of the exchange area status, including data processing speed, error rate, resource usage, etc., dynamically allocate processing resources to ensure efficient processing, and achieve load balancing among multiple exchange areas to avoid a certain exchange area becoming a bottleneck and affecting the overall data exchange efficiency. The aviation semantic web technology is an application of the semantic web technology in the aviation field. The semantic web technology enables computers to understand and process data by adding explicit semantic information to the data, thereby realizing data interoperability. RDF (Resource Description Framework) and OWL (Web Ontology Language) are two important components of the semantic web technology. RDF is used to describe resources and their attributes, providing a standardized way to represent data. Based on RDF, OWL provides richer vocabulary and logical rules for describing the relationships and attributes between resources, supporting more complex queries and inferences. Map the non-standard format data to the corresponding elements in the RDF or OWL model, use URI (Uniform Resource Identifier) to assign unique identifiers to each entity and attribute in the data, construct the corresponding ontology according to the knowledge and requirements of the aviation field. The ontology defines the entities, attributes and their relationships in the data, and instantiates the cleaned and mapped data into specific instances in the ontology, including assigning an instance identifier to each entity in the data and filling in the corresponding attribute values and relationships; use the logical rules provided by ontology languages such as OWL to reason about the data and verify the converted data to ensure compliance with the specifications and standards of semantic web technologies such as RDF and OWL. The standardization process ensures the consistency and interoperability of the data. S300: Receive the target data set and transmit it to the next transmission node according to the data exchange path.
[0026] In some embodiments, after receiving the target data set, the intelligent routing model determines the address and transmission protocol of the next transmission node according to the data exchange path, and uses an appropriate communication protocol to transmit the target data set to the next node.
[0027] The technical solutions in the embodiments of the present application have at least the following technical effects or advantages: In the present application, a common and efficient data exchange path is selected through an intelligent routing model, reducing data transmission latency and error rate, and achieving the effect of improving the overall data exchange efficiency; an automatic correction mechanism is established to implement address verification and completion, ensuring the accuracy and integrity of address information, and achieving the effect of quickly solving basic information problems and improving data processing efficiency; a data transcoding engine is established and the aviation semantic web technology is used to standardize the data, enabling interoperability of different formats of data, and achieving the effect of improving data availability and value.
[0028] Embodiment 2: In Embodiment 1, an intelligent routing model and a data transcoding engine are established to select a suitable data exchange path and exchange area for data exchange, further improving the data exchange efficiency. This embodiment makes further improvements on the basis of the above embodiment.
[0029] In step S100, when selecting a data exchange path, it further includes: establishing a data source archive based on the historical trust chain for the basic data, combining the current data information to be exchanged, and evaluating the comprehensive situation of each data exchange path in the data source archive in real time. At the same time, according to the historical data exchange path and demand characteristics of the enterprise, a priority queue of exchange paths is generated, a path conflict detection mechanism is established, the usage of each path is monitored in real time, and the data exchange task is dynamically adjusted.
[0030] In some embodiments, a detailed profile is established for each enterprise participating in data exchange in the data source repository, including but not limited to enterprise ID, data type, data format, data update frequency, historical data exchange records, etc. Starting from the enterprise and taking the historical data exchange path as the development line, the historical data exchange path, exchange area, historical transmission nodes and related performance indicators of each enterprise are recorded. The performance indicators include usage time, transmission speed, security, etc.; monitoring tools are deployed on each data exchange path to collect the status information of each transmission node in real time, including node load, response time, network latency, etc., and these data are summarized and analyzed regularly (such as every hour or every day) to update the node status database. The comprehensive situation of each data exchange path in the data source repository is evaluated in real time. The comprehensive situation includes the real-time load, historical performance, security indicators and estimated timeliness of the data exchange path. The estimated timeliness refers to the total time of each data exchange path, the respective time of each transmission node and the transmission success rate; at the same time, according to the historical data exchange path and demand characteristics of the enterprise, the demand characteristics refer to the special needs of each enterprise, such as selecting a transmission node and necessary timeliness, etc.; an exchange path priority queue is generated. Combining the method for further evaluating the current data information to be exchanged and the current several candidate data exchange paths and exchange areas according to the data information to be exchanged and the historical trust chain in the above embodiments, the generated exchange path priority queue is further screened, and at the same time, a path conflict detection mechanism is used for each exchange path to avoid congestion caused by multiple data exchange tasks using the same path at the same time. The usage load and time of the transmission nodes of each transmission path are monitored and estimated, the usage situation of each path is monitored in real time, and the data exchange tasks are dynamically adjusted, so as to obtain the optimal data exchange path.
[0031] In some embodiments, when statistically analyzing historical data, key indicators such as the total time of each data exchange path, the respective time of each node, and the transmission success rate need to be recorded. The statistical data is deeply analyzed regularly (such as every month or every quarter) to identify performance bottlenecks and potential optimization points. According to the statistical results, targeted optimization strategies are formulated, and the optimization strategies are fed back to the data source management profile as an important reference for future selection of data exchange paths and exchange areas. According to the above steps, the data source management mechanism and the data exchange path optimization scheme are gradually implemented, and the scheme is continuously optimized according to the monitoring results and the feedback of the enterprise to improve the efficiency and security of data exchange.
[0032] The technical solutions in the embodiments of the present application at least have the following technical effects or advantages: This application ensures that data can be transmitted quickly and efficiently along the optimal path by real-time evaluating the path performance and dynamically adjusting the data exchange tasks; comprehensively considers the security indicators of the path to ensure the security of data during transmission; flexibly selects the data exchange path according to the special needs and real-time situation of the enterprise to meet diverse data exchange requirements; and avoids resource congestion and waste and improves the utilization rate of transmission nodes through path conflict detection and load monitoring.
[0033] Embodiment 3: In the above embodiment, a data source archive is established to generate a priority queue for exchange paths, a path conflict detection mechanism is established, and the data exchange tasks are dynamically adjusted, further reducing the actual time used for data exchange. This embodiment makes further improvements on the basis of the above embodiment.
[0034] In step S200, establishing a data transcoding engine further includes establishing a dynamic adaptation model for identifying unknown data types, setting a feedback loop, setting conversion rules according to the identification results, and using the conversion rules to update the dynamic adaptation model; further analyzing the hierarchical structure, field types and relationships of unknown data types, as well as repetition patterns, sequences and association rules, and parsing the data structure content to extract key structure information; formulating rules for converting unknown data types into standard formats according to the analysis results; and updating the aviation data semantic network.
[0035] In some embodiments, after receiving the preprocessed data set, the data transcoding engine uses predefined rules or pattern matching techniques to detect the current and data types to be converted. When the received data does not match any known types, the dynamic adaptation mode is triggered and analyzed according to the dynamic adaptation model. The dynamic adaptation model is constructed based on the random forest algorithm. Random Forest is an ensemble learning method that improves the accuracy and stability of the model by constructing multiple decision trees and integrating their prediction results. The specific steps are as follows: Collect historical data containing known data types and a small number of unknown data type samples, process missing values and outliers to ensure data quality, extract or construct meaningful features according to the characteristics of the data types, divide the data set into a training set and a test set with a ratio of 70%:30%; Initialize parameter settings, specifically including the number of decision trees, usually set to 100 or more; The maximum depth of each tree, which can be set to None; The minimum number of samples required to split internal nodes; The minimum number of samples required for leaf nodes; The maximum number of features considered when deciding node splitting, etc. The specific parameter settings can be set and adjusted according to the actual model construction needs. Use the training set for training, optimize the parameters, use the trained model to predict the test set, obtain the prediction results, calculate the accuracy between the prediction results and the actual results, and output a detailed classification report, including indicators such as precision, recall rate, and F1 score. Use cross-validation (such as K-fold cross-validation) to further evaluate the stability and generalization ability of the model. The feedback loop is that when a new data type is identified and processed, collect its processing results and conversion rules, add the new data type and its conversion rules as new samples to the training set, and retrain the dynamic adaptation model regularly or according to the frequency of the appearance of the new data type, and then use the identification processing results and conversion rules of the unknown data type to update the dynamic adaptation model.
[0036] In some embodiments, the parsing of the data structure content is performed by applying natural language processing techniques to extract key structural information such as entities, attributes, and relationships. The updating of the aviation data semantic network integrates information of unknown data types into the aviation data semantic network, and the specific steps are as follows: Represent the information of the new data type using the Resource Description Framework, construct RDF triples to describe the entities, attributes, and relationships in the data; Add the RDF information to the aviation data semantic network, and update the ontology and vocabulary in the network to include concepts related to the new data type; Use a semantic reasoning tool to check the consistency of the updated semantic network. Set conversion rules according to the recognition results, and apply the conversion rules to update the dynamic adaptation model. The conversion rules are formulated based on the recognition results to convert unknown data types into a standard format. Based on the results of structural analysis and content understanding, conversion rules are formulated. The conversion rules clearly specify how to extract information from unknown data types and map it into the standard format. Use a test data set to verify the correctness and effectiveness of the conversion rules, and adjust and optimize the rules according to the verification results.
[0037] The technical solutions in the embodiments of the present application at least have the following technical effects or advantages: The dynamic adaptation model established in the present application can quickly identify and process unknown data types, reducing the processing time and achieving the effect of quickly identifying unknown data types; By analyzing the data structure and content in detail, precise conversion rules are formulated to ensure the accuracy of data conversion, achieving the effect of enhancing the accuracy of data conversion; Integrating the information of unknown data types into the aviation data semantic network enriches the semantic information of the data, facilitating subsequent data analysis and applications.
[0038] The above is only the preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.
Claims
1. A civil aviation logistics data exchange method, characterized in that, The method includes: S100: Receive the data to be exchanged, establish an intelligent routing model, select a data exchange path and an ideal exchange area according to the data information to be exchanged and the historical trust chain, and perform complement verification on the incomplete data information to be exchanged through an automatic correction mechanism to form a preprocessing data set; S200: Establish a data transcoding engine to receive the preprocessing data set and convert the preprocessing data set into a target data set; specifically including: identifying the load condition of the current ideal exchange area, determining the final exchange area, converting the data information to be exchanged into target data; using the aviation semantic network technology to further standardize the remaining data in the preprocessing data set to form standard remaining data; encapsulating the target data and the standard remaining data into a target data set; S300: Receive the target data set and transmit it to the next transmission node according to the data exchange path.
2. The civil aviation logistics data exchange method according to claim 1, characterized in that The data information to be exchanged includes the data type, source, and data exchange requirements. The data exchange requirements refer to the data format to be converted, the recipient information, and the data transmission conditions. The source refers to the address information of the uploader and the recipient; the data exchange path refers to the sequence of all transmission nodes and connections that the data passes through from the starting point to the target point. The transmission node refers to each entity in the data exchange path; the preprocessing data set includes the complemented data information to be exchanged, the data exchange path, and the ideal exchange area; the historical trust chain is obtained through analysis by the enterprise trust chain database and the trust chain evaluation module.
3. The civil aviation logistics data exchange method according to claim 2, characterized in that, The enterprise trust chain database includes the historical sent data, recipient feedback data, and data quality evaluation data of each enterprise; the trust chain evaluation module scores the trust degree of each data exchange path according to the evaluation effect of historical data transmission, and selects the data exchange path with the highest trust degree score as the historical trust chain.
4. The civil aviation logistics data exchange method according to claim 1, characterized in that The automatic correction mechanism includes address verification and address complementation. The address verification verifies the address information in the data information to be exchanged according to all known valid addresses and returns the result; the address complementation fills in the incomplete address information that is valid through a filling method and performs secondary verification on the complemented address.
5. The civil aviation logistics data exchange method according to claim 1, characterized in that The intelligent routing model uses common exchange paths as basic data and is trained using a deep neural network as the basic model; among them, collect all the completed data exchange path information from the historical data exchange records, and count the occurrence frequency for each collected data exchange path; preset a frequency base and a frequency threshold, and the frequency threshold is the product of the frequency base and the total number of data exchange paths; regard the path with the occurrence frequency exceeding the frequency threshold as a common exchange path.
6. The civil aviation logistics data exchange method according to claim 1, wherein In the step S100, selecting a data exchange path further includes: establishing a data source archive based on the historical trust chain for the basic data, combining the current data information to be exchanged, evaluating the comprehensive situation of each data exchange path in the data source archive in real time, and at the same time generating an exchange path priority queue according to the historical data exchange path and demand characteristics of the enterprise, establishing a path conflict detection mechanism, monitoring the usage of each path in real time, and dynamically adjusting the data exchange task.
7. The civil aviation logistics data exchange method according to claim 6, wherein, The data source archive takes the enterprise as the starting point and the historical data exchange path as the development line, records the historical data exchange path, exchange area, historical transmission node of each enterprise and related performance indicators, and the performance indicators include usage time, transmission speed, and security.
8. The civil aviation logistics data exchange method according to claim 6, wherein, The comprehensive situation includes the real-time load, historical performance, security index, and estimated timeliness of the data exchange path. The estimated timeliness refers to the total time of each data exchange path, the time of each transmission node respectively, and the transmission success rate.
9. A civil aviation logistics data exchange method as claimed in claim 1, characterized in that, In the step S200, establishing a data transcoding engine further includes establishing a dynamic adaptation model for identifying unknown data types, setting a feedback loop, setting conversion rules according to the identification results, and using the conversion rules to update the dynamic adaptation model; further analyzing the hierarchical structure, field type, and relationship of the unknown data type, as well as the repetition pattern, sequence, and association rules, and parsing the data structure content to extract the key structure information; formulating rules for converting the unknown data type into a standard format according to the analysis results; and updating the aviation data semantic network.
10. A civil aviation logistics data exchange method as claimed in claim 9, characterized in that, The dynamic adaptation model is constructed based on the random forest algorithm. The data structure content is parsed using natural language processing technology to extract the key structure information. Updating the aviation data semantic network integrates the information of the unknown data type into the aviation data semantic network. The specific steps are as follows: representing the information of the new data type using the Resource Description Framework, constructing RDF triples to describe the entities, attributes, and relationships in the data; adding the RDF information to the aviation data semantic network, and updating the ontology and vocabulary in the network to include the relevant concepts of the new data type; Using a semantic reasoning tool to check the consistency of the updated semantic network.
Citation Information
Patent Citations
Intelligent data forwarding and sharing method and system
CN116232724A
Address standardization method and device, equipment and storage medium
CN117112850A
Logistics distribution method and device based on grid map, equipment and storage medium
CN118966957A
Goods transportation integrated logistics management system
CN119624287A
Artificial intelligence-based address standardization method and apparatus, device and storage medium
WO2022100154A1
Cited By
Real-time data exchange anomaly detection method and device based on deep learning
CN120956531A
