Heterogeneous multi-source data association analysis method, equipment and medium

Abstract

The invention relates to the technical field of data processing, and discloses a heterogeneous multi-source data association analysis method and device and a medium, and the method comprises the steps: carrying out the adaptive conversion of heterogeneous multi-source data of an airport operation system, and obtaining a standard data set; associating and binding the data records of the same flight number in the standard data set to obtain a preliminary association relationship of the data records so as to construct a time domain association network; performing deep semantic association analysis on the time domain association network to obtain a deep association knowledge graph; traversing semantic edges in the deep association knowledge graph, identifying a dependency conflict relationship on a critical path, evaluating a comprehensive index reflecting the overall operation situation of the airport, and generating a comprehensive situation evaluation report; performing collaborative coupling analysis on the comprehensive situation assessment report and the deep association knowledge graph to obtain an optimal scheduling recommendation scheme; according to the method, the association analysis efficiency based on the heterogeneous multi-source data can be improved.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method, device and medium for heterogeneous multi-source data correlation analysis. Background Technology

[0002] In airport operations, heterogeneous, multi-source data originates from different business operations and multiple dimensions, exhibiting significant differences in data formats and transmission standards. Existing technologies struggle to efficiently integrate and uniformly adapt this data, resulting in the inability to fully explore the correlations between data points and to form a complete operational data view. This inefficiency in data integration undermines the reliable foundation for subsequent data-driven analysis, making it difficult to accurately reflect the actual situation of airport operations.

[0003] Existing technologies, when processing correlation analysis of airport operational data, lack a deep integration of temporal characteristics and business logic, making it difficult to construct a comprehensive correlation network and thus unable to effectively identify dependency conflicts in the operational process. This results in a lack of scientific basis for the comprehensive assessment of airport operational status, discrepancies between indicator assessment results and actual operational conditions, and an inability to provide effective support for operational optimization. Ultimately, this leads to a lack of targeted adjustments to airport operational scheduling, making it difficult to substantially improve operational efficiency and service quality. Summary of the Invention

[0004] This invention provides a method, device, and medium for heterogeneous multi-source data correlation analysis to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides a heterogeneous multi-source data correlation analysis method, comprising: S1. Collect raw data sets of different businesses in the airport operation system under different dimensions to obtain heterogeneous multi-source data of the airport operation system; S2. Based on preset data conversion rules, the heterogeneous multi-source data is adaptively converted to obtain the standard data set of the airport operation system; S3. Based on the timestamp information of the standard data set, associate and bind data records with the same flight number to obtain the preliminary association relationship of the data records, and construct the time-domain association network of the standard data set according to the preliminary association relationship; S4. Perform deep semantic association analysis on the time-domain association network to obtain a deep association knowledge graph of the airport operation system; S5. Traverse the semantic edges in the deep association knowledge graph, identify the dependency conflict relationships on the critical path, and based on the dependency conflict relationships, evaluate the comprehensive indicators reflecting the overall operation status of the airport, and generate a comprehensive status assessment report of the airport operation system. S6. Perform a collaborative coupling analysis on the indicator status in the comprehensive situation assessment report and the topology of the deep association knowledge graph to obtain the optimized scheduling recommendation scheme of the airport operation system.

[0006] In a preferred embodiment, the collection of raw data sets from different business operations within the airport operation system across different dimensions yields heterogeneous, multi-source data for the airport operation system, including: Based on the business architecture of the airport operation system, the core functions of the airport operation system are filtered to obtain the core business list of the airport operation system. Based on the core business list, determine the data output types of the core businesses in the airport operation system in different dimensions; According to the transmission format specifications of the airport operation system, the core business list and the data output type are encoded and encapsulated to obtain the data acquisition instructions of the airport operation system; The data acquisition command is transmitted to the airport operation system to generate the original data set of the airport operation system; The original dataset is integrated in multiple dimensions to obtain heterogeneous multi-source data for the airport operation system.

[0007] In a preferred embodiment, the adaptive transformation of the heterogeneous multi-source data according to preset data transformation rules to obtain the standard data set of the airport operation system includes: The data items in the heterogeneous multi-source data are parsed to obtain the source format type of the data items; Based on the target format type of the heterogeneous multi-source data, the source format type is mapped to a preset data conversion rule to obtain the conversion template of the data item; Based on the field mapping relationship in the conversion template, the data items are format-converted to obtain the intermediate data set of the heterogeneous multi-source data; By removing abnormal data records from the intermediate data set, the standard data set of the airport operation system is obtained.

[0008] In a preferred embodiment, the step of associating and binding data records with the same flight number based on the timestamp information of the standard data set to obtain a preliminary association relationship of the data records, and constructing a time-domain association network of the standard data set based on the preliminary association relationship, includes: Parse the timestamp information in the standard dataset to obtain the flight number identifier of the standard dataset; Based on the timestamp information of the airport operation system, determine the time window division rules for the standard data set; According to the time window division rules, within the preset time window, data records with the same flight number identifier in the standard data set are grouped and classified, and an internal association index is established for the classified data record group. Using the flight number identifier as nodes and the internal association index as edges, a time-domain association network of the standard data set is constructed.

[0009] In a preferred embodiment, the step of performing deep semantic association analysis on the temporal association network to obtain a deep association knowledge graph of the airport operation system includes: Based on the full-process business logic requirements of the airport operation system, the business logic constraints and data matching standards of the airport operation system are integrated into an airport business rule base. The nodes and bound data records in the time-domain association network are traversed and scanned to obtain the core business attribute features of the data records. Based on the logical constraints in the airport business rule base and combined with the core business attribute features, the business logic relationships between the data records are identified. Using the business logic relationships as semantic edges, the semantic edges are added to the temporal association network to obtain the multi-dimensional association network of the airport operation system; The temporal and semantic association edges in the multi-dimensional association network are topologically reconstructed to obtain a deep association knowledge graph of the airport operation system.

[0010] In a preferred embodiment, the process of traversing the semantic edges in the deep association knowledge graph, identifying dependency conflicts on critical paths, and evaluating comprehensive indicators reflecting the overall operational status of the airport based on these dependency conflicts, thereby generating a comprehensive status assessment report of the airport's operational system, includes: Based on the core objectives of the airport operation system, key business paths that affect flight punctuality, operational efficiency, and service quality are selected from the entire business chain of the airport business rule base. The semantic edges in the key business path and the deep association knowledge graph are subjected to fit detection in order to identify the dependency conflict relationship in the deep association knowledge graph. Based on the aforementioned dependency conflict relationships, the conflict triggering nodes, conflict propagation paths, and conflict impact levels in the deep association knowledge graph are identified, and a conflict evaluation matrix for the deep association knowledge graph is constructed. Based on the comprehensive assessment requirements of the airport operation status in the airport operation system, the smoothness of operation, resource utilization rate and abnormal response efficiency in the airport business rule base are obtained to determine the comprehensive indicators of the airport operation system. Perform a correlation mapping operation on the comprehensive index and the conflict assessment matrix to obtain the actual state value of the comprehensive index; By integrating the actual state values ​​of the comprehensive indicators and the dependency and conflict relationships, a comprehensive situation assessment report of the airport operation system is obtained.

[0011] In a preferred embodiment, the formula for calculating the actual state value is as follows: ; In the formula, Indicates the first The actual state value of each comprehensive indicator The first one, determined by the comprehensive assessment requirements. The basic weights of each comprehensive indicator This indicates the weight of the impact of the key business path. This indicates the number of conflict-triggered nodes corresponding to the aforementioned dependency conflict relationship. This represents the influence hierarchy parameter in the conflict assessment matrix. This indicates the preset conflict impact attenuation coefficient. This represents the average length of the conflict propagation path.

[0012] In a preferred embodiment, the step of performing a synergistic coupling analysis of the indicator states in the comprehensive situation assessment report and the topological structure of the deep-association knowledge graph to obtain an optimized scheduling recommendation scheme for the airport operation system includes: Based on the actual status values ​​in the comprehensive situation assessment report, and combined with the historical normal indicator statistical range of the airport operation system, the comprehensive indicators that exceed the historical normal indicator statistical range are analyzed in a targeted manner to obtain the set of abnormal influencing factors of the comprehensive indicators. Based on the set of abnormal influencing factors, the corresponding nodes, temporal association edges, and semantic association edges in the deep association knowledge graph are matched to obtain the bottleneck nodes and inefficient association paths of the comprehensive index. Based on the resource scheduling optimization principles of the airport operation system, a preliminary optimization scheme is formulated to adapt to the inefficient associated paths of the bottleneck nodes. The preliminary optimization scheme was simulated and verified to obtain the verification results of the preliminary optimization scheme; Based on the verification results, the preliminary optimization scheme is adjusted accordingly to obtain the recommended optimized scheduling scheme for the airport operation system.

[0013] Compared with the prior art, the present invention has the following beneficial effects: 1. This invention achieves adaptive standardization of heterogeneous data from multiple services and dimensions at airports by pre-setting conversion rules, constructs a time-domain association network by combining timestamps and flight numbers, and then integrates business logic to generate a deep association knowledge graph. This efficiently integrates scattered data and fully explores potential associations, solving the problems of inefficient data integration and incomplete association mining in traditional methods.

[0014] 2. This invention identifies critical path dependency conflicts, evaluates comprehensive operational status indicators using quantitative formulas, generates accurate evaluation reports, and then uses collaborative coupling analysis to locate bottleneck nodes and inefficient paths, formulates targeted optimization scheduling plans, provides a scientific basis for airport operation adjustments, and effectively improves operational efficiency, flight punctuality rate, and service quality. Attached Figure Description

[0015] Figure 1 This is a flowchart illustrating a heterogeneous multi-source data correlation analysis method provided in Embodiment 1 of the present invention; Figure 2 This is a schematic diagram of the composition structure of the device for implementing the heterogeneous multi-source data correlation analysis method provided in Embodiment 2 of the present invention.

[0016] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0017] To enable those skilled in the art to better understand the technical solutions of this disclosure, and to fully understand and implement the process of how this disclosure applies technical means to solve technical problems and achieve corresponding technical effects, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, not all embodiments. The embodiments of this disclosure and the various features within them can be combined with each other without conflict, and the resulting technical solutions are all within the protection scope of this disclosure. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without creative effort should fall within the protection scope of this disclosure.

[0018] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0019] Example 1 Reference Figure 1The diagram shown is a flowchart illustrating a heterogeneous multi-source data association analysis method according to Embodiment 1 of the present invention. In this embodiment, the heterogeneous multi-source data association analysis method includes: S1. Collect raw data sets of different businesses in the airport operation system under different dimensions to obtain heterogeneous multi-source data of the airport operation system; In this embodiment of the invention, the collection of raw data sets from different businesses within the airport operation system under different dimensions yields heterogeneous multi-source data of the airport operation system, including: Based on the business architecture of the airport operation system, the core functions of the airport operation system are filtered to obtain the core business list of the airport operation system. Based on the core business list, determine the data output types of the core businesses in the airport operation system in different dimensions; According to the transmission format specifications of the airport operation system, the core business list and the data output type are encoded and encapsulated to obtain the data acquisition instructions of the airport operation system; The data acquisition command is transmitted to the airport operation system to generate the original data set of the airport operation system; The original dataset is integrated in multiple dimensions to obtain heterogeneous multi-source data for the airport operation system.

[0020] Based on the core application scenarios of airport operations, the direct operational attributes of each business link are sorted out, and auxiliary business links such as office logistics that do not directly support airport operations are eliminated. For businesses that directly affect airport operational efficiency, such as flight support, passenger services, airfield management, security control, and resource scheduling, the core execution actions and service objectives of each business are clarified, and all businesses that conform to the core operational positioning are summarized to obtain the core business list of the airport operation system.

[0021] For each core business in the core business list, four dimensions are defined: business execution status, resource usage, service recipient feedback, and environmental adaptation conditions. The specific data forms generated by each core business under the four dimensions are sorted out one by one, clarifying the specific content and business orientation of the output data of each business under the corresponding dimension. The corresponding data forms of all core businesses in different dimensions are summarized to determine the data output types of the core businesses in the airport operation system in different dimensions.

[0022] Referring to the established transmission format specifications of the airport operation system, the specifications clearly define the field arrangement order of data content, the exclusive identification rules corresponding to the business, and the hierarchical structure of data encapsulation. Each business in the core business list is assigned a corresponding exclusive business identifier. Then, the data output types of different dimensions of each business are filled into the corresponding hierarchical structure according to the field arrangement order required by the specifications. Following the encapsulation process set by the specifications, the business identifier and the corresponding data output type are integrated into a unified instruction structure. The core business list and the data output type are encoded and encapsulated to obtain the data acquisition instructions of the airport operation system.

[0023] Relying on the business transmission links built within the airport operation system, the encoded and encapsulated data collection instructions are sent one by one to the execution terminals of the corresponding core business. After receiving the corresponding instructions, each execution terminal retrieves the real-time operation data and historical accumulated data generated during its own business execution, and completes the data extraction work according to the requirements of the instructions. All the data extracted by the execution terminals are aggregated to the central data receiving node of the airport operation system to generate the original data set of the airport operation system.

[0024] For data from different core business execution terminals in the original dataset, classification and aggregation are carried out according to business dimensions and data output types. Consistency verification is performed on the aggregated data by comparing whether the business identifier and dimension identifier corresponding to the data match each other. Invalid data with mismatched identifiers are removed. Data from different sources and in different forms that have passed the verification are merged according to the preset business association logic. During the fusion process, the original business attributes of each data are fully preserved. After the data fusion processing is completed, the heterogeneous multi-source data of the airport operation system is obtained.

[0025] The beneficial effects are as follows: by clearly defining the core business scope of the airport operation system, clearly delineating the data output types of different dimensions of the core business, completing the encoding and encapsulation of data collection instructions based on established transmission format specifications, issuing instructions through internal transmission links and generating a complete set of raw data, and achieving effective integration of heterogeneous multi-source data through classification, aggregation and consistency verification, the entire data collection and integration process has clear logical guidance and standardized execution standards, enabling accurate extraction of key airport operation data, avoiding interference from invalid data, and the final heterogeneous multi-source data can completely retain the original attributes of each core business, providing accurate and comprehensive data support for subsequent data analysis and operational optimization of the airport operation system.

[0026] S2. Based on preset data conversion rules, the heterogeneous multi-source data is adaptively converted to obtain the standard data set of the airport operation system; In this embodiment of the invention, the step of adaptively transforming the heterogeneous multi-source data according to preset data transformation rules to obtain the standard data set of the airport operation system includes: The data items in the heterogeneous multi-source data are parsed to obtain the source format type of the data items; Based on the target format type of the heterogeneous multi-source data, the source format type is mapped to a preset data conversion rule to obtain the conversion template of the data item; Based on the field mapping relationship in the conversion template, the data items are format-converted to obtain the intermediate data set of the heterogeneous multi-source data; By removing abnormal data records from the intermediate data set, the standard data set of the airport operation system is obtained.

[0027] The content structure and field organization method of each data item in the heterogeneous multi-source data are identified one by one, the content presentation characteristics of each data item are clarified, and the format feature information corresponding to all data items is summarized to obtain the source format type of the data item.

[0028] The target format type of the heterogeneous multi-source data is clearly defined. Preset data conversion rules containing the correspondence between various source formats and target formats are retrieved. The source format type of each identified data item is accurately matched with the source format entries in the data conversion rules. After successful matching, the corresponding field processing method, content adjustment requirements and format integration standards in the rules are extracted. These contents are integrated into the exclusive processing basis for the corresponding data item to obtain the conversion template of the data item.

[0029] According to the field mapping relationship set in the conversion template, the original fields of each data item are matched one-to-one with the target fields. Content in the original fields that does not meet the target format requirements is rectified, the order of the original fields is rearranged, redundant content in the original fields is removed, and all data items that have completed the format adjustment are summarized to obtain the intermediate data set of the heterogeneous multi-source data.

[0030] The criteria for judging abnormal data records are clearly defined. The criteria are data that does not match the core business attributes, data with missing field content, and data that still does not meet the target format requirements after format adjustment. Each data record in the intermediate data set is checked one by one. During the check, the data records are compared with the attribute characteristics of the core business and the standard requirements of the target format. All data records judged as abnormal by the check results are removed from the intermediate data set. Data records that meet the requirements are retained and integrated to obtain the standard data set of the airport operation system.

[0031] The beneficial effects are as follows: by performing format parsing on data items in heterogeneous multi-source data to clarify the source format type, generating corresponding conversion templates by combining the target format type mapping with preset conversion rules, completing data format conversion based on the field mapping relationship of the conversion template to obtain an intermediate data set, and removing abnormal data records in the intermediate data set, the heterogeneous data of the airport operation system achieves format unification and standardization, effectively filtering out invalid data that does not meet the requirements, and the final standard data set has accurate business attributes and consistent format characteristics, providing high-quality and reliable data support for subsequent data analysis, operational decision-making and other related work of the airport operation system.

[0032] S3. Based on the timestamp information of the standard data set, associate and bind data records with the same flight number to obtain the preliminary association relationship of the data records, and construct the time-domain association network of the standard data set according to the preliminary association relationship; In this embodiment of the invention, the step of associating and binding data records with the same flight number based on the timestamp information of the standard data set to obtain a preliminary association relationship of the data records, and constructing a time-domain association network of the standard data set based on the preliminary association relationship, includes: Parse the timestamp information in the standard dataset to obtain the flight number identifier of the standard dataset; Based on the timestamp information of the airport operation system, determine the time window division rules for the standard data set; According to the time window division rules, within the preset time window, data records with the same flight number identifier in the standard data set are grouped and classified, and an internal association index is established for the classified data record group. Using the flight number identifier as nodes and the internal association index as edges, a time-domain association network of the standard data set is constructed.

[0033] Each data record in the standard dataset undergoes complete timestamp extraction and feature identification. The extracted timestamp information includes the specific time of business execution corresponding to the data record. The timestamp information of each extracted data record is precisely compared with the pre-stored flight schedule runtime information in the airport operation system to confirm which flight's schedule runtime range each data record's timestamp falls within. Then, the flight-specific identifier information corresponding to that time period is extracted, and the corresponding flight-specific identifier information is matched for each data record in the standard dataset. The flight-specific identifier information corresponding to all data records is summarized to obtain the flight number identifier of the standard dataset.

[0034] The system retrieves all timestamp information from the airport operation system, covering the entire process of a flight from arrival preparation, taxiing and parking, passenger boarding to departure taxiing. This full set of timestamp information corresponds to each key business link in the flight operation. Combining the sequence and business connection characteristics of each key business link in the flight operation, the complete flight operation cycle is divided into several continuous and non-overlapping sub-time periods. The starting boundary of each sub-time period is defined as the completion timestamp of the previous key business link, and the ending boundary is defined as the completion timestamp of the current key business link. This determines the time window division rules of the standard data set.

[0035] Referring to the established time window division rules, first, the time boundary range of the sub-period corresponding to each preset time window is locked. Then, all data records in the standard data set are traversed one by one to determine whether the timestamp information of the data record is within the sub-period range of the current preset time window. All data records with the same flight number identifier within the preset time window are filtered out. All these filtered data records are integrated and collected into an independent data record group. Then, the specific business links corresponding to each data record in the same data record group are sorted out. According to the execution order of the business links and the business logic relationship, the association points of each data record with other data records in the group are marked. The combination of these marked association points forms the internal association index of the data record group.

[0036] Each flight number identifier in the standard data set is set as an independent network node. The node carries the basic operational attribute information of the corresponding flight. Then, the internal association index of the data record group corresponding to the same flight number identifier within the same preset time window is set as the network edge connecting the corresponding child nodes of each data record under the node. The network edge carries the business association logic attributes between the data records. Then, according to the order of the time windows, the target flight number network node of the previous time window and the same flight number network node of the next time window are connected in an orderly manner through the network edge representing the connection logic of different business links of the flight. This makes the network nodes and network edges corresponding to all time windows interconnected to form an organic whole, thus constructing the temporal association network of the standard data set.

[0037] The beneficial effects are as follows: by parsing the timestamp information of the standard data set, the corresponding flight number identifier is accurately matched; by combining the full timestamp information of the airport operation system, a scientific and reasonable time window division rule is determined; according to the rule, data records with the same flight number identifier are grouped and classified, and an internal association index is established; finally, a time-domain association network of the standard data set is constructed with the flight number identifier as the node and the internal association index as the edge, so that the scattered standard data forms an organic whole with time sequence characteristics and business association logic, clearly presenting the business execution context of the same flight in different time windows, and providing structured and highly correlated data support for flight operation monitoring, business process optimization, and operational decision-making in the airport operation process.

[0038] S4. Perform deep semantic association analysis on the time-domain association network to obtain a deep association knowledge graph of the airport operation system; In this embodiment of the invention, the step of performing deep semantic association analysis on the temporal association network to obtain a deep association knowledge graph of the airport operation system includes: Based on the full-process business logic requirements of the airport operation system, the business logic constraints and data matching standards of the airport operation system are integrated into an airport business rule base. The nodes and bound data records in the time-domain association network are traversed and scanned to obtain the core business attribute features of the data records. Based on the logical constraints in the airport business rule base and combined with the core business attribute features, the business logic relationships between the data records are identified. Using the business logic relationships as semantic edges, the semantic edges are added to the temporal association network to obtain the multi-dimensional association network of the airport operation system; The temporal and semantic association edges in the multi-dimensional association network are topologically reconstructed to obtain a deep association knowledge graph of the airport operation system.

[0039] This paper analyzes the execution requirements of the entire airport operation system, including flight support, passenger services, airfield management, security control, and resource scheduling. It extracts the sequential connection conditions, data interaction requirements, and resource usage restrictions between core businesses as business logic constraints. At the same time, it clarifies the field matching requirements, attribute consistency requirements, and source validity requirements of the data corresponding to each business as data matching standards. The extracted business logic constraints and the clarified data matching standards are systematically integrated to form a complete and logically unified set, which is the airport business rule base.

[0040] Each flight number identifier node in the time-domain association network is accessed one by one, and all data records bound to each node are retrieved. The content of each data record is carefully sorted out, and key contents such as the business execution link, service object scope, resource usage type, and status change result corresponding to the data record are extracted. All the extracted key contents are summarized and organized to obtain the core business attribute characteristics of the data record.

[0041] All preset logical constraints in the airport business rule base are retrieved, and the core business attribute characteristics of each data record are compared with the corresponding logical constraints one by one. It is determined whether the core business attribute characteristics of different data records conform to the business connection relationship, data dependency relationship, and state association relationship set in the rule base. Based on the judgment result, the sequential execution relationship, mutual dependency relationship, and collaborative cooperation relationship between different data records are clarified, and the business logical relationship between the data records is identified.

[0042] Each identified business logic relationship is defined as a semantic edge. The starting and ending points of the semantic edge correspond to two data records with the same logic relationship. The connection direction of the semantic edge is marked according to the direction of the business logic relationship. All marked semantic edges are added to the temporal association network one by one, so that the semantic edges and the temporal association edges in the original network work together to affect the network nodes and data records, thus obtaining the multi-dimensional association network of the airport operation system.

[0043] The distribution, connection status, and connection strength of temporal and semantic related edges in the multi-dimensional related network are analyzed. Edges directly related to core business logic are retained, while redundant edges with duplicate connections or irrelevant to business needs are removed. The connection paths of the edges are adjusted to fit the actual business processes of airport operations, and the connection strength of the edges between key business nodes is strengthened. Through the above series of adjustments and optimizations, the topology of the network structure is reconstructed, resulting in a deep related knowledge graph of the airport operation system.

[0044] The beneficial effects are as follows: by integrating the business logic constraints and data matching standards of the airport operation system to construct an airport business rule base, the nodes and bound data records of the temporal correlation network are traversed and scanned to extract core business attribute features. Combined with the logical constraints of the rule base, the business logic relationships between data records are identified. The business logic relationships are integrated into the temporal correlation network as semantic edges to form a multi-dimensional correlation network. The temporal correlation edges and semantic correlation edges in the network are topologically reconstructed to obtain a deep correlation knowledge graph. This enables airport operation-related data to form a correlation system that combines temporal characteristics and business semantic logic, clearly presenting the internal connections and execution context between various core businesses. This provides comprehensive and accurate knowledge support for the optimization and adjustment of airport operation processes, the early prediction of operational risks, and the scientific formulation of operational decisions.

[0045] S5. Traverse the semantic edges in the deep association knowledge graph, identify the dependency conflict relationships on the critical path, and based on the dependency conflict relationships, evaluate the comprehensive indicators reflecting the overall operation status of the airport, and generate a comprehensive status assessment report of the airport operation system. In this embodiment of the invention, the step of traversing the semantic edges in the deep association knowledge graph, identifying dependency conflict relationships on critical paths, and based on these dependency conflict relationships, evaluating comprehensive indicators reflecting the overall operational status of the airport, and generating a comprehensive status assessment report of the airport operation system, includes: Based on the core objectives of the airport operation system, key business paths that affect flight punctuality, operational efficiency, and service quality are selected from the entire business chain of the airport business rule base. The semantic edges in the key business path and the deep association knowledge graph are subjected to fit detection in order to identify the dependency conflict relationship in the deep association knowledge graph. Based on the aforementioned dependency conflict relationships, the conflict triggering nodes, conflict propagation paths, and conflict impact levels in the deep association knowledge graph are identified, and a conflict evaluation matrix for the deep association knowledge graph is constructed. Based on the comprehensive assessment requirements of the airport operation status in the airport operation system, the smoothness of operation, resource utilization rate and abnormal response efficiency in the airport business rule base are obtained to determine the comprehensive indicators of the airport operation system. Perform a correlation mapping operation on the comprehensive index and the conflict assessment matrix to obtain the actual state value of the comprehensive index; By integrating the actual state values ​​of the comprehensive indicators and the dependency and conflict relationships, a comprehensive situation assessment report of the airport operation system is obtained.

[0046] The formula for calculating the actual state value is as follows: ; In the formula, Indicates the first The actual state value of each comprehensive indicator The first one, determined by the comprehensive assessment requirements. The basic weights of each comprehensive indicator This indicates the weight of the impact of the key business path. This indicates the number of conflict-triggered nodes corresponding to the aforementioned dependency conflict relationship. This represents the influence hierarchy parameter in the conflict assessment matrix. This indicates the preset conflict impact attenuation coefficient. This represents the average length of the conflict propagation path.

[0047] The comprehensive assessment requirement is a comprehensive assessment requirement for the operational status of the airport's operating system. It is obtained by combining the importance of each comprehensive indicator in the assessment of the operational status. The airport operations management team determines the basic weight of each comprehensive indicator by directly assigning values ​​based on the general standards for airport operation assessment in the industry, while matching the airport's operating scale and core business focus. The constraint is that the sum of the basic weights of all comprehensive indicators is a fixed and uniform value, and the threshold range is a value between 0 and 1.

[0048] The critical business path is the business link that affects flight punctuality, operational efficiency, and service quality. It is obtained by statistically analyzing the actual frequency of the critical business path's impact on the corresponding comprehensive indicator in the past three months, and combining the execution ratio of the path in the entire business link. The weight is calculated by the operations analyst. The constraint is that the weight must be positively correlated with the actual impact of the critical business path, the threshold range is between 0 and 1, and it does not exceed the basic weight of the corresponding comprehensive indicator.

[0049] Dependency conflict relationships are business logic conflict relationships identified in the deep association knowledge graph. The acquisition method is to trace the starting business node corresponding to each conflict from these dependency conflict relationships one by one, and count the total number of these starting nodes. The constraint is that this number must correspond one-to-one with the actual identified dependency conflict relationships. Each conflict corresponds to only one conflict triggering node. The threshold range is a positive integer not less than 1, and the maximum does not exceed the total number of nodes in the entire business chain.

[0050] The conflict assessment matrix is ​​a matrix obtained by sorting out dependent conflict relationships. It is obtained by extracting the impact level of the corresponding conflict from the matrix and directly using the level value corresponding to the level as the impact level parameter. The constraint is that the level classification of this parameter must be completely consistent with the business level classification standard in the airport business rule base. The threshold range is a positive integer between 1 and 3, corresponding to different business levels.

[0051] This coefficient is a preset value, obtained by the airport's operations technology team based on the airport's conflict transmission data over the past year, combined with the industry's pattern of conflict impact attenuation along the transmission path. The constraint is that the coefficient must reflect the pattern of conflict impact weakening as the transmission path increases, and the threshold range is a decimal between 0.1 and 0.5.

[0052] The conflict propagation path is obtained from the conflict assessment matrix. The method is to extract all conflict propagation paths from the matrix, count the number of business nodes contained in each path as the path length, and then calculate the arithmetic mean of these lengths. The constraint is that the average length must be calculated based on the actual conflict propagation path and must not include virtual paths. The threshold range is a positive integer not less than 1 and the maximum does not exceed the total number of nodes in the entire business chain.

[0053] This formula is used to calculate the actual state value of the comprehensive indicator. It is obtained by combining the basic weight of the comprehensive indicator, the impact weight of the key business path, and also incorporating the number of conflict triggering nodes corresponding to the dependency conflict relationship, the impact level parameter, as well as the preset conflict impact attenuation coefficient and the average length of the conflict transmission path. The theoretical state of the comprehensive indicator is adjusted to finally obtain the actual state value of the comprehensive indicator that reflects the actual situation of airport operation. The constraints are that the calculation process must strictly follow the value rules of each parameter, the usage of parameters cannot be arbitrarily adjusted, there is no separate threshold range, and the result must be consistent with the actual performance of the comprehensive indicator.

[0054] When the number of conflict-triggered nodes increases or the influence level parameter increases, the corresponding value in the formula will increase, and the actual state value of the comprehensive index will decrease. The constraint is that this trend only holds when the values ​​of other parameters are fixed. The threshold range is when the number of conflict-triggered nodes and the influence level parameter are within their respective thresholds, and the trend is stable.

[0055] When the average length of the conflict propagation path increases, the product of the conflict impact attenuation coefficient and the average length will increase, the value of the corresponding part in the formula will decrease, and the actual state value of the comprehensive index will increase. The constraint is that this trend only holds when the conflict impact attenuation coefficient is within its threshold. The threshold range is when the average length of the conflict propagation path is within its threshold, and this trend is stable.

[0056] When the base weight of the comprehensive indicator or the influence weight of the key business path increases, the actual state value of the comprehensive indicator will increase. The constraint is that this trend only holds when the values ​​of other parameters are fixed. The threshold range is when the base weight and the influence weight are within their respective thresholds, and the trend is stable.

[0057] The core objectives of the airport operation system are clearly defined as improving flight punctuality, optimizing operational efficiency, and enhancing service quality. The system retrieves data from the airport's business rule base, covering the entire process of flight arrival preparation, runway taxiing, jet bridge docking, passenger boarding, baggage handling, and flight departure. For each business link, based on its actual execution process in airport operations, the system evaluates its execution time, resource consumption, and impact on preceding and following business links. This determines the weight of each business link's influence on the three core objectives of flight punctuality, operational efficiency, and service quality. Business links with dominant influence weights that directly determine the achievement of the core objectives are retained, thus identifying the key business paths that affect flight punctuality, operational efficiency, and service quality.

[0058] The complete business logic, including the execution order, resource allocation constraints, and business connection criteria, of the core business processes contained in the critical business path is analyzed. This business logic is then precisely compared with the business logic relationships represented by each semantic edge in the deep association knowledge graph. The focus is on verifying whether the connection direction of the semantic edge is consistent with the execution order of the critical business path, whether the business constraints corresponding to the semantic edge match the resource allocation requirements of the critical business path, and whether the connection relationships reflected by the semantic edge meet the connection criteria of the critical business path. Any discrepancies in logical order, conflicting constraints, or inconsistent connection criteria found during the comparison process are systematically summarized to identify dependency conflicts in the deep association knowledge graph.

[0059] For each identified dependency conflict relationship, the specific business node that first triggered the conflict is located by tracing the associated edges in the deep association knowledge graph. The associated edges extending outward from the conflict triggering node are then used to trace the complete path of the conflict from the triggering node to downstream business nodes and then to related business processes. This path is then used as the conflict propagation path. Combined with the business hierarchy classification standards in the airport business rule base, the scope and severity of the conflict's impact on core business processes, auxiliary business processes, and supporting business processes are analyzed, and the conflict impact level is defined. All conflict triggering nodes, conflict propagation paths, and conflict impact levels corresponding to all dependency conflict relationships are systematically integrated according to a unified sorting dimension to construct the conflict evaluation matrix of the deep association knowledge graph.

[0060] To clarify the comprehensive assessment requirements for airport operation status within the airport operation system, and to fully grasp the real-time operational status of the airport, promptly identify potential operational risks, and provide a basis for operational optimization decisions, the following criteria are retrieved from the airport business rule base: Criteria for judging operational smoothness are retrieved, including the range of connection intervals for each business link, criteria for judging link stagnation, and requirements for identifying business process breakpoints. Criteria for judging resource utilization are also retrieved, including the matching standards between the actual usage time and available time of various resources such as boarding bridges, passenger stairs, and ground staff, and the conditions for judging resource idleness and overload. Criteria for judging abnormal response efficiency are also retrieved, including the time threshold from the occurrence of an abnormal event to the initiation of response, the time requirements for the completion of response measures, and the criteria for judging the elimination of abnormal impacts. These three criteria are then systematically integrated to determine the comprehensive indicators of the airport operation system.

[0061] The three criteria for determining the comprehensive indicator—operational smoothness, resource utilization, and anomaly response efficiency—are mapped to the corresponding conflict impact levels in the conflict assessment matrix. For the operational smoothness criterion, the judgment result of the business connection interval is adjusted according to the impact level of the conflict on the business process connection. For the resource utilization criterion, the judgment result of the resource usage matching degree is adjusted according to the impact level of the conflict on resource allocation. For the anomaly response efficiency criterion, the judgment result of the handling timeliness is adjusted according to the impact level of the conflict on anomaly handling. The status results corresponding to the three adjusted criteria are summarized and integrated to obtain the actual status value of the comprehensive indicator.

[0062] The system integrates the actual state values ​​of comprehensive indicators with the specific performance of airport operation smoothness, resource utilization, and anomaly response efficiency, along with the specific types, locations, and scope of impact of business logic conflicts corresponding to dependency and conflict relationships. This integration is structured in an orderly manner, including an overall overview of airport operation status, detailed analysis of the actual state of comprehensive indicators, a detailed analysis of dependency and conflict relationships, an analysis of the impact mechanism of conflicts on comprehensive indicators, and directions and suggestions for airport operation optimization. This results in a complete and logically clear textual content, leading to a comprehensive situation assessment report of the airport operation system.

[0063] The beneficial effects include: screening key business paths based on the core objectives of airport operations; detecting their compatibility with the semantic edges of the deep-linked knowledge graph; identifying dependency conflicts; sorting out conflict elements to construct an evaluation matrix; determining comprehensive indicators in conjunction with operational needs; obtaining the actual state values ​​of the indicators through correlation mapping; integrating relevant content to generate a comprehensive situation assessment report; accurately locating key operational impact links; and providing precise basis for airport operation optimization and decision-making.

[0064] S6. Perform a collaborative coupling analysis on the indicator status in the comprehensive situation assessment report and the topology of the deep association knowledge graph to obtain the optimized scheduling recommendation scheme of the airport operation system.

[0065] In this embodiment of the invention, the step of performing a synergistic coupling analysis of the indicator states in the comprehensive situation assessment report and the topological structure of the deep-association knowledge graph to obtain an optimized scheduling recommendation scheme for the airport operation system includes: Based on the actual status values ​​in the comprehensive situation assessment report, and combined with the historical normal indicator statistical range of the airport operation system, the comprehensive indicators that exceed the historical normal indicator statistical range are analyzed in a targeted manner to obtain the set of abnormal influencing factors of the comprehensive indicators. Based on the set of abnormal influencing factors, the corresponding nodes, temporal association edges, and semantic association edges in the deep association knowledge graph are matched to obtain the bottleneck nodes and inefficient association paths of the comprehensive index. Based on the resource scheduling optimization principles of the airport operation system, a preliminary optimization scheme is formulated to adapt to the inefficient associated paths of the bottleneck nodes. The preliminary optimization scheme was simulated and verified to obtain the verification results of the preliminary optimization scheme; Based on the verification results, the preliminary optimization scheme is adjusted accordingly to obtain the recommended optimized scheduling scheme for the airport operation system.

[0066] The actual status values ​​of each comprehensive indicator in the comprehensive situation assessment report are retrieved. At the same time, the historical normal indicator statistical range accumulated by the airport operation system during normal operation periods is retrieved. This range is determined based on the sum of the actual values ​​of each comprehensive indicator during the past six months of stable airport operation. The actual status value of each comprehensive indicator is compared with the corresponding historical normal indicator statistical range one by one. Comprehensive indicators whose actual status values ​​exceed the range are screened out. For these comprehensive indicators that exceed the range, in conjunction with the dependency and conflict relationships and conflict assessment matrix content in the comprehensive situation assessment report, the business links, conflict factors and resource allocation that affect the status of the indicator are traced. All the contents that affect the abnormality of the indicator are summarized and organized to obtain the set of abnormal influencing factors of the comprehensive indicator.

[0067] For each influencing factor in the set of abnormal influencing factors, a deep association knowledge graph is retrieved to accurately match the business process corresponding to the influencing factor with the nodes in the knowledge graph. At the same time, the temporal and semantic association edges associated with the node are matched, and the operational status of these nodes and association edges in the knowledge graph is analyzed to locate the business nodes that cause the abnormal comprehensive indicators. These nodes are identified as bottleneck nodes. Meanwhile, the paths formed by the association edges connecting these nodes that have poor business logic connection and inefficient resource flow are identified and these paths are identified as inefficient association paths. All bottleneck nodes and inefficient association paths are summarized to obtain the bottleneck nodes and inefficient association paths of the comprehensive indicators.

[0068] The principles for optimizing resource scheduling in the airport operation system are clearly defined. These principles include prioritizing the resource needs of core business nodes, balancing the occupancy time of various resources, and shortening the connection intervals between business processes. Based on these principles, for each bottleneck node, the corresponding resource allocation quantity and resource arrival sequence are adjusted. For each inefficient connection path, the execution order and connection rules of each business process in the path are optimized. These adjustments and optimizations are integrated according to the sequence of business processes to form specific operational specifications covering bottleneck nodes and inefficient connection paths. A preliminary optimization plan adapted to the bottleneck nodes and inefficient connection paths is then developed.

[0069] The current airport operation system's business execution scenario is reconstructed, including resource allocation, execution sequence, and interrelationships of each business link. The preliminary optimization plan is then applied to this scenario, and at least one complete flight operation cycle is simulated according to the airport's normal operating rhythm. During the simulation, the status changes of various comprehensive indicators, resource usage of bottleneck nodes, and connection efficiency of inefficient paths are continuously recorded. After the simulation, these records are summarized, and the differences in the status of comprehensive indicators before and after the simulation, as well as the improvement of bottleneck nodes and inefficient paths, are compared to obtain the verification results of the preliminary optimization plan.

[0070] The analysis and verification results revealed areas where the overall indicator status did not meet expectations, bottleneck node resource allocation remained unreasonable, and inefficient connection efficiency of inefficient related paths was not sufficiently improved. To address these issues, the resource allocation ratio of bottleneck nodes was adjusted, the connection rules of inefficient related paths were optimized, and the operational specifications in the solution were reviewed again to match the adjusted content. All adjusted content was then integrated to ensure the solution covers all aspects requiring optimization and complies with resource scheduling optimization principles, thus obtaining the recommended optimized scheduling solution for the airport operation system.

[0071] The beneficial effects are as follows: based on the actual state values ​​of the comprehensive situation assessment report and combined with the historical normal indicator statistical range of the airport operation system, the set of abnormal influencing factors of the comprehensive indicators is analyzed in a targeted manner. Then, a deep association knowledge graph is matched to obtain the corresponding bottleneck nodes and inefficient association paths. Based on the resource scheduling optimization principle, an appropriate preliminary optimization plan is formulated. After simulation verification, targeted adjustments are made to obtain the optimized scheduling recommendation plan. The root cause of the abnormal comprehensive indicators is accurately located, and the bottleneck links and inefficient business paths in the operation are clarified. The formulated plan is in line with the actual operation needs of the airport. The optimized scheduling recommendation plan after verification and adjustment has stronger feasibility, effectively helping the airport operation system to optimize resource allocation, improve business process efficiency, and enhance the stability and smoothness of operation.

[0072] Example 2 like Figure 2 As shown, this embodiment also provides a computer device, which may include a processor 10, a memory 11, a communication bus 12 and a communication interface 13, and may also include a computer program stored in the memory 11 and capable of running on the processor 10, such as a heterogeneous multi-source data correlation analysis program.

[0073] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the device, connecting various components of the device through various interfaces and lines. It executes programs or modules stored in the memory 11 (e.g., executing a heterogeneous multi-source data correlation analysis program) and calls data stored in the memory 11 to perform various functions of the device and process data.

[0074] The memory 11 includes at least one type of medium, including flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the device, such as the portable hard drive of the device. In other embodiments, the memory 11 can also be an external storage device of the device, such as a plug-in portable hard drive, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, etc. Furthermore, the memory 11 can include both internal and external storage units of the device. The memory 11 can be used not only to store application software and various types of data installed on the device, such as the code of a heterogeneous multi-source data correlation analysis program, but also to temporarily store data that has been output or will be output.

[0075] The communication bus 12 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. This bus can be divided into an address bus, a data bus, a control bus, etc. The bus is configured to enable communication between the memory 11 and at least one processor 10, etc.

[0076] The communication interface 13 is used for communication between the aforementioned device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, Bluetooth interface, etc.), typically used to establish communication connections between the device and other devices. The user interface may be a display, an input unit (such as a keyboard), or optionally, a standard wired or wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed within the device and to display a visual user interface.

[0077] The figure only shows the device with components. Those skilled in the art will understand that the structure shown in the figure does not constitute a limitation on the device and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0078] For example, although not shown, the device may also include a power supply (such as a battery) to power the various components. Preferably, the power supply can be logically connected to the at least one processor 10 via a power management device, thereby enabling functions such as charging management, discharging management, and power consumption management. The power supply may also include one or more DC or AC power sources, a recharging device, a power fault detection circuit, a power converter or inverter, a power status indicator, or any other components. The device may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0079] It should be understood that the embodiments described are for illustrative purposes only and are not limited to this structure in the scope of the patent application.

[0080] The heterogeneous multi-source data correlation analysis program stored in the memory 11 of the device is a combination of multiple instructions. When run in the processor 10, it can achieve the following: S1. Collect raw data sets of different businesses in the airport operation system under different dimensions to obtain heterogeneous multi-source data of the airport operation system; S2. Based on preset data conversion rules, the heterogeneous multi-source data is adaptively converted to obtain the standard data set of the airport operation system; S3. Based on the timestamp information of the standard data set, associate and bind data records with the same flight number to obtain the preliminary association relationship of the data records, and construct the time-domain association network of the standard data set according to the preliminary association relationship; S4. Perform deep semantic association analysis on the time-domain association network to obtain a deep association knowledge graph of the airport operation system; S5. Traverse the semantic edges in the deep association knowledge graph, identify the dependency conflict relationships on the critical path, and based on the dependency conflict relationships, evaluate the comprehensive indicators reflecting the overall operation status of the airport, and generate a comprehensive status assessment report of the airport operation system. S6. Perform a collaborative coupling analysis on the indicator status in the comprehensive situation assessment report and the topology of the deep association knowledge graph to obtain the optimized scheduling recommendation scheme of the airport operation system.

[0081] Specifically, the specific implementation method of the processor 10 for the above instructions can be referred to the description of the relevant steps in the corresponding embodiment of the accompanying drawings, and will not be repeated here.

[0082] Furthermore, if the modules / units integrated into the device are implemented as software functional units and sold or used as independent products, they can be stored in a medium. The medium can be volatile or non-volatile. For example, the medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0083] In the several embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0084] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0085] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0086] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0087] This application embodiment can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0088] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for correlation analysis of heterogeneous multi-source data, characterized in that, The method includes: S1. Collect raw data sets of different businesses in the airport operation system under different dimensions to obtain heterogeneous multi-source data of the airport operation system; S2. Based on preset data conversion rules, the heterogeneous multi-source data is adaptively converted to obtain the standard data set of the airport operation system; S3. Based on the timestamp information of the standard data set, associate and bind data records with the same flight number to obtain the preliminary association relationship of the data records, and construct the time-domain association network of the standard data set according to the preliminary association relationship; S4. Perform deep semantic association analysis on the time-domain association network to obtain a deep association knowledge graph of the airport operation system; S5. Traverse the semantic edges in the deep association knowledge graph, identify the dependency conflict relationships on the critical path, and based on the dependency conflict relationships, evaluate the comprehensive indicators reflecting the overall operation status of the airport, and generate a comprehensive status assessment report of the airport operation system. S6. Perform a collaborative coupling analysis on the indicator status in the comprehensive situation assessment report and the topology of the deep association knowledge graph to obtain the optimized scheduling recommendation scheme of the airport operation system.

2. The heterogeneous multi-source data correlation analysis method as described in claim 1, characterized in that, The collection of raw data from different business operations within the airport operation system across various dimensions yields heterogeneous, multi-source data for the airport operation system, including: Based on the business architecture of the airport operation system, the core functions of the airport operation system are filtered to obtain the core business list of the airport operation system. Based on the core business list, determine the data output types of the core businesses in the airport operation system in different dimensions; According to the transmission format specifications of the airport operation system, the core business list and the data output type are encoded and encapsulated to obtain the data acquisition instructions of the airport operation system; The data acquisition command is transmitted to the airport operation system to generate the original data set of the airport operation system; The original dataset is integrated in multiple dimensions to obtain heterogeneous multi-source data for the airport operation system.

3. The heterogeneous multi-source data correlation analysis method as described in claim 1, characterized in that, The step of adaptively transforming the heterogeneous multi-source data according to preset data transformation rules to obtain the standard data set of the airport operation system includes: The data items in the heterogeneous multi-source data are parsed to obtain the source format type of the data items; Based on the target format type of the heterogeneous multi-source data, the source format type is mapped to a preset data conversion rule to obtain the conversion template of the data item; Based on the field mapping relationship in the conversion template, the data items are format-converted to obtain the intermediate data set of the heterogeneous multi-source data; By removing abnormal data records from the intermediate data set, the standard data set of the airport operation system is obtained.

4. The heterogeneous multi-source data correlation analysis method as described in claim 1, characterized in that, The process involves associating and binding data records with the same flight number based on the timestamp information of the standard data set to obtain a preliminary association relationship between the data records, and constructing a time-domain association network for the standard data set based on the preliminary association relationship, including: Parse the timestamp information in the standard dataset to obtain the flight number identifier of the standard dataset; Based on the timestamp information of the airport operation system, determine the time window division rules for the standard data set; According to the time window division rules, within the preset time window, data records with the same flight number identifier in the standard data set are grouped and classified, and an internal association index is established for the classified data record group. Using the flight number identifier as nodes and the internal association index as edges, a time-domain association network of the standard data set is constructed.

5. The heterogeneous multi-source data correlation analysis method as described in claim 1, characterized in that, The deep semantic association analysis performed on the temporal association network to obtain the deep association knowledge graph of the airport operation system includes: Based on the full-process business logic requirements of the airport operation system, the business logic constraints and data matching standards of the airport operation system are integrated into an airport business rule base. The nodes and bound data records in the time-domain association network are traversed and scanned to obtain the core business attribute features of the data records. Based on the logical constraints in the airport business rule base and combined with the core business attribute features, the business logic relationships between the data records are identified. Using the business logic relationships as semantic edges, the semantic edges are added to the temporal association network to obtain the multi-dimensional association network of the airport operation system; The temporal and semantic association edges in the multi-dimensional association network are topologically reconstructed to obtain a deep association knowledge graph of the airport operation system.

6. The heterogeneous multi-source data correlation analysis method as described in claim 5, characterized in that, The process involves traversing the semantic edges in the deep association knowledge graph, identifying dependency conflicts on critical paths, and based on these conflicts, evaluating comprehensive indicators reflecting the overall operational status of the airport, generating a comprehensive status assessment report for the airport's operational system, including: Based on the core objectives of the airport operation system, key business paths that affect flight punctuality, operational efficiency, and service quality are selected from the entire business chain of the airport business rule base. The semantic edges in the key business path and the deep association knowledge graph are subjected to fit detection in order to identify the dependency conflict relationship in the deep association knowledge graph. Based on the aforementioned dependency conflict relationships, the conflict triggering nodes, conflict propagation paths, and conflict impact levels in the deep association knowledge graph are identified, and a conflict evaluation matrix for the deep association knowledge graph is constructed. Based on the comprehensive assessment requirements of the airport operation status in the airport operation system, the smoothness of operation, resource utilization rate and abnormal response efficiency in the airport business rule base are obtained to determine the comprehensive indicators of the airport operation system. Perform a correlation mapping operation on the comprehensive index and the conflict assessment matrix to obtain the actual state value of the comprehensive index; By integrating the actual state values ​​of the comprehensive indicators and the dependency and conflict relationships, a comprehensive situation assessment report of the airport operation system is obtained.

7. The heterogeneous multi-source data correlation analysis method as described in claim 6, characterized in that, The formula for calculating the actual state value is as follows: ； In the formula, Indicates the first The actual state value of each comprehensive indicator The first one, determined by the comprehensive assessment requirements. The basic weights of each comprehensive indicator This indicates the weight of the impact of the key business path. This indicates the number of conflict-triggered nodes corresponding to the aforementioned dependency conflict relationship. This represents the influence hierarchy parameter in the conflict assessment matrix. This indicates the preset conflict impact attenuation coefficient. This represents the average length of the conflict propagation path.

8. The heterogeneous multi-source data correlation analysis method as described in claim 1, characterized in that, The method involves performing a synergistic coupling analysis of the indicator states in the comprehensive situation assessment report and the topology of the deep-association knowledge graph to obtain an optimized scheduling recommendation scheme for the airport operation system, including: Based on the actual status values ​​in the comprehensive situation assessment report, and combined with the historical normal indicator statistical range of the airport operation system, the comprehensive indicators that exceed the historical normal indicator statistical range are analyzed in a targeted manner to obtain the set of abnormal influencing factors of the comprehensive indicators. Based on the set of abnormal influencing factors, the corresponding nodes, temporal association edges, and semantic association edges in the deep association knowledge graph are matched to obtain the bottleneck nodes and inefficient association paths of the comprehensive index. Based on the resource scheduling optimization principles of the airport operation system, a preliminary optimization scheme is formulated to adapt to the inefficient associated paths of the bottleneck nodes. The preliminary optimization scheme was simulated and verified to obtain the verification results of the preliminary optimization scheme; Based on the verification results, the preliminary optimization scheme is adjusted accordingly to obtain the recommended optimized scheduling scheme for the airport operation system.

9. An apparatus comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 8.

10. A medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the steps of the method according to any one of claims 1 to 8.

Images