Multi-source data processing method, device, equipment and program product

Abstract

The embodiment of the invention provides a multi-source data processing method and device, equipment and a program product. The method comprises the steps that at least one piece of original data of a target flight is acquired from at least one information channel; based on the accuracy of the information channel corresponding to each piece of original data and a preset channel authority value, determining the data source confidence of each piece of original data; the content of each piece of original data is analyzed, the attribute confidence coefficient of each piece of original data is determined based on the content analysis result, and the attribute confidence coefficient comprises at least one of the identification confidence coefficient, the logic confidence coefficient and the updating confidence coefficient; determining the data item confidence coefficient of each piece of original data based on the attribute confidence coefficient of each piece of original data and the data source confidence coefficient; and sorting the data item confidence of the original data, so as to determine the original data with the highest data item confidence as the target data of the target flight.

Description

A multi-source data processing method, apparatus, equipment, and program product Technical Field

[0001] This application relates to the field of civil aviation information processing technology, specifically to a multi-source data processing method, apparatus, equipment, and program product. Background Technology

[0002] In the operation and management of civil aviation airports, flight manifests (including passenger, cargo, and baggage load balance data) are core foundational information for airport operations, directly supporting airport decision-making and execution across multiple dimensions, including passenger service, safety assurance, operational efficiency, financial settlement, and long-term planning. Currently, the most authoritative and complete manifest data in China's civil aviation industry is centrally stored in a core system. However, for airports, obtaining manifest data directly, stably, and in real-time from this core system faces numerous limitations and difficulties. This "desirable but unattainable" status quo of accessing the core data source forces airports to rely on various indirect and heterogeneous methods to obtain manifest data in actual operations, leading to a series of technical problems related to data inaccuracy. Improving the accuracy of the acquired data has become an urgent technical issue to be addressed. Summary of the Invention

[0003] The purpose of this application is to provide a multi-source data processing method, apparatus, device, and program product. The specific technical solution adopted is as follows: In a first aspect, embodiments of this application provide a multi-source data processing method, the method comprising: obtaining at least one original data of a target flight from at least one information channel; determining the data source confidence of each original data based on the accuracy of the information channel corresponding to each original data and a preset channel authority value; analyzing the content of each original data and determining the attribute confidence of each original data based on the content analysis results, wherein the attribute confidence includes at least one of the following: identification confidence, logical confidence, and update confidence; determining the data item confidence of each original data based on the attribute confidence and the data source confidence; and sorting the data item confidence of the original data to determine the original data with the highest data item confidence as the target data of the target flight.

[0004] Secondly, a multi-source data processing apparatus is provided, the apparatus comprising: an acquisition module for acquiring at least one original data of a target flight from at least one information channel; a first determination module for determining the data source confidence of each original data based on the accuracy of the information channel corresponding to each original data and a preset channel authority value; a second determination module for analyzing the content of each original data and determining the attribute confidence of each original data based on the content analysis results, wherein the attribute confidence includes at least one of the following: identification confidence, logical confidence, and update confidence; a second determination module for determining the data item confidence of each original data based on the attribute confidence and the data source confidence; and a sorting module for sorting the data item confidence of the original data to determine the original data with the highest data item confidence as the target data of the target flight.

[0005] Thirdly, an electronic device is provided, including a memory and a processor, the memory storing a computer program executable on the processor, the processor executing the computer program causing the electronic device to perform the methods described above.

[0006] Fourthly, a computer program product is provided, comprising: computer program code, which, when run on a computer, causes the electronic device to perform the above-described method.

[0007] Fifthly, a computer-readable storage medium is provided that stores computer program code, which, when executed on a computer, causes the computer to perform the methods described above.

[0008] This application offers the following advantages: it does not rely on any single data source, but rather utilizes an intelligent algorithm to fully leverage the value of all available data sources, ultimately outputting a unique, optimal, and highly reliable data version. This not only solves the data source problem but also achieves the effect of automatically and efficiently determining the optimal data from multiple sources. Attached Figure Description

[0009] To more clearly illustrate the technical solutions and advantages in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0010] Figure 1 is a flowchart illustrating a multi-source data processing method provided in an embodiment of this application; Figure 2 is a flowchart illustrating a multi-source data fusion method based on intelligent confidence assessment provided in an embodiment of this application; Figure 3 is a schematic diagram illustrating a multi-source data processing device provided in an embodiment of this application; Figure 4 is a structural schematic diagram illustrating a computer block device provided in an embodiment of this application. Detailed Implementation

[0011] To further illustrate the technical means and effects adopted by this application to achieve the intended inventive purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a multi-source data processing method proposed in this application. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined from any suitable form.

[0012] In the description of the embodiments of this application, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. The "and / or" in the text is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the embodiments of this application, "multiple" means two or more.

[0013] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature.

[0014] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains.

[0015] This application provides a multi-source data processing method, as shown in Figure 1, which can be implemented through the following steps: Step S110: Obtain at least one original data of the target flight from at least one information channel; In the operation and management of civil aviation airports, the flight manifest (original) data (including passenger, cargo, baggage and other load balance data) is the core basic information of airport operation, which directly supports the airport's decision-making and execution in multiple dimensions such as passenger service, security, operational efficiency, financial settlement and long-term planning.

[0016] The specific type of information channel (such as airline websites, air traffic control systems, third-party platforms, social media, etc.) allows for the establishment of standardized interfaces to acquire raw data. In some embodiments, the differences in data formats between different channels (such as JSON, XML, unstructured text) can be addressed by pre-processing data cleaning and structuring.

[0017] For example, information channels include at least one of the following: domestic flight information system A, international airline emails / messages B, airline system C, Aircraft Communications Addressing and Reporting System (ACARS), the authority's sharing platform, third-party data interfaces, etc.

[0018] During implementation, raw data for the same target flight can be obtained through different information channels. For example, the transportation data for flight 001 can be obtained simultaneously from both the airline's C system and the domestic flight information A system.

[0019] Step S120: Based on the accuracy of the information channel corresponding to each of the original data and the preset channel authority value, determine the data source confidence of each of the original data. Here, the accuracy can be verified by comparing historical data (e.g., if 95% of the data from a certain channel in the past 1000 times is consistent with the official data, then the accuracy is 95%). The authority value can be comprehensively scored based on the official attributes of the channel (e.g., the authority value of the certification platform is higher), the data update frequency (e.g., the authority value of real-time pushed data is higher than that of manually entered data), industry reputation, and other dimensions.

[0020] For example, the authority value of the manifest data interface provided by the airline is 1.0; the authority value of the mail delivery data provided by the airline is 0.9; the authority value of the OCR recognition result of the flight information service is 0.8; the authority value of the delivery data interface provided by the ACARS system is 0.7; the authority value of the OCR recognition result of the flight information service is 0.6; the authority value of the data shared with the Civil Aviation Administration of China is 0.5; and the authority value of the third-party data interface is 0.4.

[0021] During implementation, the confidence level of the data source can be determined by combining the accuracy of the information channel corresponding to the original data and the preset authority value of the channel. The confidence level of the data source can characterize the credibility of the data source.

[0022] Step S130: Analyze the content of each of the original data, and determine the attribute confidence of each of the original data based on the content analysis results. The attribute confidence includes at least one of the following: identification confidence, logical confidence, and update confidence. Here, the identification confidence can be determined by verifying the legality of the data field through NLP or rule engine (such as whether the flight number conforms to the encoding rules and whether the date format is valid). Alternatively, the identification confidence can be determined by using the identification confidence of Optical Character Recognition (OCR).

[0023] Logical confidence level can be used to construct a business rule base to validate data logic (such as departure time earlier than arrival time, reasonableness of stopover airports and routes, matching degree of flight time and distance, and whether the number of passengers conforms to logic), and determine the logical confidence level based on this validated data logic. For example, logical validation is performed on data values ​​to check whether the number of passengers is within the maximum passenger capacity of the aircraft type, is a non-negative integer and less than 999; whether the cargo and mail weight is within the aircraft's load capacity, etc.; whether the passenger capacity of passenger aircraft is greater than 0, and the passenger capacity of cargo aircraft is 0, etc. The default value is 1.0, and it decreases by 0.5 for each failed validation until the value of the item is 0.

[0024] Update confidence: The timeliness weight is calculated based on the difference between the data collection time and the current time (e.g., the weight of real-time data within 5 minutes is higher than that of historical data 1 hour ago), or the update confidence is determined based on the difference between the latest received data value and the previously received data value.

[0025] In some embodiments, the confidence level of each data item in each raw data may be determined based on at least one of the following: identification confidence level, logical confidence level, and update confidence level, and data source confidence level.

[0026] In some embodiments, the confidence level of each data item in each raw data may be determined based on at least two of the following: identification confidence level, logical confidence level, and update confidence level, and data source confidence level.

[0027] The confidence level of each data item in the original data can be determined based on the identification confidence level, logical confidence level, update confidence level, and data source confidence level of each original data.

[0028] Step S140: Determine the data item confidence level of each of the original data items based on the attribute confidence level and the data source confidence level. Here, in data processing and quality assessment, determining the data item confidence level of the original data is a key step to ensure data reliability and usability. The data item confidence level typically reflects the accuracy and reliability of the data item, and can be derived by comprehensively considering the attribute confidence level and the data source confidence level of the original data.

[0029] During implementation, the confidence level of a data item can be a simple addition or multiplication of the confidence level of the attribute and the confidence level of the data source, or it can be considered comprehensively depending on the specific circumstances.

[0030] In some embodiments, a weighted average or weighted sum may be used, where weights can be allocated based on factors such as the importance or reliability of the attribute or data source.

[0031] For example, a weighting coefficient can be set, and the attribute confidence and data source confidence can be weighted and summed according to the coefficient to obtain the data item confidence.

[0032] Step S150: Sort the confidence scores of the data items in the original data, and determine the original data with the highest confidence scores as the target data for the target flight.

[0033] During implementation, each piece of raw data can be identified and sorted based on the confidence level of the data item, so as to determine the raw data with the highest confidence level of the data item as the target data.

[0034] In some embodiments, a multi-level sorting strategy can be established: first, data items are sorted in descending order of confidence level; if data items have the same confidence level, the authority value or update timestamp of the data source is further compared. When finally outputting the target data, a confidence score and a description of the data source can be included to support subsequent auditing and error correction.

[0035] In this embodiment, instead of relying on any single data source, a smart algorithm is used to fully utilize the value of all available data sources, ultimately outputting a unique, optimal, and highly reliable data version. This not only solves the data source problem but also achieves the effect of automatically and efficiently determining the optimal data from multiple sources.

[0036] In some embodiments, the above step S120, "determining the data source confidence of each original data based on the accuracy of the information channel corresponding to each original data and the preset channel authority value," can be achieved through the following steps: Step 121, determining the accuracy of the information channel based on the correct data volume and the total data volume of the information channel; here, the accuracy, i.e., the historical accuracy (Accuracy_Historical), can characterize the correct proportion of data sources obtained in the past. For example, the historical accuracy can be obtained based on the correct proportion of valid data in the data source within the past 90 natural days, calculated by the following formula (1): Accuracy_Historical = (correct data volume in valid data / total valid data volume) × 100% (1); where valid data refers to "the number of flights that can effectively identify relevant manifests," and correct data refers to "the number of flights that have been manually confirmed to have accurate data."

[0037] In some embodiments, a data collection window can be set, for example, a time window (such as the past 30 days) or an event window (such as the most recent 1000 data interactions), the correct amount of data from the statistical information channel (the amount consistent with official data / cross-validation data), and the total amount of data.

[0038] Example: A third-party platform provides 500 flight data entries within 30 days, of which 475 are consistent with the data on the airline's official website. Then the accuracy rate = 475 / 500 = 95%.

[0039] Step 122: Obtain the preset channel authority value based on the identification information of the information channel. During implementation, the channel authority value, i.e., the data source authority (Weight_Authority), can be an inherent authority weight assigned to the information channel corresponding to different data sources. The preset authority value database can be associated with the unique identifier of the information channel (such as API key, domain name, organization code). The authority value can be comprehensively scored based on the following dimensions: Official attributes: High scores (e.g., 0.8-1.0) are given to authoritative channels such as airline official websites, air traffic control systems, and International Air Transport Association (IATA) certification platforms, while lower scores (e.g., 0.3-0.6) are given to third-party data interfaces and social media; Data update frequency: Real-time pushed data (e.g., updated every minute) has a higher authority value than manually entered data (e.g., updated daily); Industry reputation and compliance: Evaluation through historical cooperation and compliance certification assessments; Data coverage: Coverage of flight numbers, route network breadth, etc.

[0040] Step 123: Weight the accuracy rate and the channel authority value to obtain the data source confidence of the original data.

[0041] Here, the formula (2) for calculating the overall confidence of the data source is as follows: Confidence_Source=α×Accuracy_Historical+β×Weight_Authority (2); where Accuracy_Historical represents the accuracy rate; Weight_Authority represents the channel authority value. The coefficients α and β satisfy α+β=1, and the default values ​​and ranges are optimized as follows: α∈[0.5, 0.7], default 0.6; β∈[0.3, 0.5], default 0.4.

[0042] In some embodiments, a data quality feedback channel can be established, allowing users or the system to mark erroneous data and reverse-optimize the accuracy and authority value calculation model.

[0043] In this embodiment, a full-link confidence assessment can be achieved by referencing the accuracy of historical data and the authority of information channels, ensuring that target flight data can be filtered based on data sources, which not only meets business needs but also has interpretability and adaptability.

[0044] In some embodiments, this application also provides a method for adjusting the weight value corresponding to the accuracy rate and the weight value corresponding to the channel authority value, which can be implemented through the following steps: Step 124: When it is determined that the accuracy rate is greater than the accuracy rate threshold, increase the weight value corresponding to the accuracy rate and decrease the weight value corresponding to the channel authority value; In some embodiments, dynamic adjustment triggering conditions can be set in the following scenarios: Scenario 1: If Accuracy_Historical ≥ 95%, α is increased to 0.7 and β is decreased to 0.3.

[0045] When the accuracy rate of an information channel is greater than or equal to a preset threshold (such as 95%), the system determines that the information channel has "excellent historical performance" and enters the "accuracy priority mode".

[0046] Adjustment logic: Increase the weight of accuracy (e.g., from 60% to 70%) to strengthen trust in high-frequency, high-precision channels; simultaneously reduce the weight of channel authority value (e.g., from 30% to 20%) to avoid excessively high authority value masking short-term accuracy fluctuations.

[0047] Business scenario adaptation: Suitable for scenarios with high real-time requirements and sensitive data accuracy (such as flight delay warnings and emergency dispatch), in which case "historical accuracy" is more valuable for decision-making than "inherent authority".

[0048] Step 125: If the channel authority value matches the preset authority threshold, increase the weight value corresponding to the channel authority value and decrease the weight value corresponding to the accuracy rate.

[0049] In some embodiments, the triggering conditions can be dynamically adjusted in the following scenarios: Scenario 2: If Weight_Authority=1.0, β is increased to 0.5 and α is decreased to 0.5.

[0050] When the channel authority value is greater than or equal to the preset authority threshold (e.g., 0.8), the system determines that the channel has "high inherent credibility" and enters the "authority value priority mode".

[0051] Adjustment logic: Increase the weight of authority value (e.g., from 40% to 50%) to strengthen long-term trust in official / authoritative channels; simultaneously reduce the weight of accuracy (e.g., from 60% to 50%) to avoid misjudging the value of channels due to short-term data fluctuations (e.g., system failures causing a temporary drop in accuracy).

[0052] Business scenario adaptation: Applicable to regular queries and long-term data accumulation scenarios (such as flight schedule queries and historical data analysis). In this case, the long-term characteristics of the channel, such as "official attributes" and "compliance", are more meaningful.

[0053] In some embodiments, the adjustment of weights can follow a gradual principle (e.g., each adjustment does not exceed 5%) to avoid system instability caused by sudden weight changes. For example, when the accuracy weight increases from 60% to 70%, it needs to be adjusted in 2 to 3 steps, with each adjustment increasing by 3 to 5 percentage points.

[0054] You can set weight boundaries (such as accuracy weight range of 40%-70%, authority value weight range of 20%-50%) to ensure that the adjusted weights are still within a reasonable range.

[0055] In some embodiments, a feedback loop can be established, allowing users or the system to provide feedback on the effects of weight adjustments (such as whether the data quality has improved after the adjustment), thereby optimizing the threshold setting and adjustment strategy in reverse.

[0056] In this embodiment, an upgrade from static weights to dynamic adaptive weights is implemented, enabling the data source confidence assessment to be automatically optimized based on channel performance and business needs, thereby improving the accuracy and robustness of flight data filtering.

[0057] In some embodiments, step S130 above, "analyzing the content of each of the original data and determining the attribute confidence of each of the original data based on the content analysis results, wherein the attribute confidence includes at least one of the following: recognition confidence, logical confidence, and update confidence," can be implemented by the following method: Step 131, if it is determined that the original data is obtained based on optical character recognition (OCR), the recognition confidence of the OCR is determined as the recognition confidence of the original data; here, the recognition confidence is the intrinsic quality score of the data item (Score_DataItem). For example, the Score_DataItem of OCR-recognized data directly adopts the recognition confidence score provided by the OCR engine (e.g., 0.92); the default value for non-OCR data source data items is 1.0.

[0058] For example, if the OCR recognition confidence score for the flight number characters "CA123" is 0.95, it means that the engine's recognition of this character is highly reliable. Therefore, 0.95 is determined as the recognition confidence score.

[0059] Step 132: Perform logical verification on the original data to determine the logical confidence level based on the verification results. Here, the logical confidence level (Score_Logic) can characterize the logical rationality and perform logical verification on the data values. For example, whether the number of passengers is within the maximum passenger capacity of the aircraft type, is a non-negative integer and less than 999; whether the cargo and mail weight is within the aircraft's load capacity, etc.; whether the passenger capacity of the passenger aircraft is greater than 0, and the passenger capacity of the cargo aircraft is 0, etc. The default value is 1.0, and it decreases by 0.5 for each failed verification until the value of that item is 0.

[0060] In some embodiments, time logic can be used for judgment, such as takeoff time being less than arrival time; stopover time being greater than 0 and less than total flight time; values ​​that do not conform to the logic are set to 0, and values ​​that conform to the logic are set to 1.

[0061] In some embodiments, spatial logic can be used for judgment, such as the stopover airport must be on the flight path between the departure airport and the arrival airport; the flight distance and flight time must be within the speed range of the aircraft type (e.g., a narrow-body aircraft takes about 1.5 hours to fly 800 kilometers); if the logic is not valid, it is set to 0, and if the logic is valid, it is set to 1.

[0062] In some embodiments, format logic can be used for judgment. For example, flight numbers, airport codes, and date formats must conform to international standards, such as the IATA three-letter code and the International Civil Aviation Organization (ICAO) four-letter code. Formats that do not conform to the logic are set to 0, and those that do conform are set to 1.

[0063] Step 133: Determine the update confidence level based on the deviation between the original data and the corresponding historical data.

[0064] During implementation, the data values ​​can be compared to determine the update confidence score (Score_Update). If the latest received data value differs from the previously received data value, the latest data item value will receive a bonus.

[0065] For example, the Score_Update value range can be set to [0.7, 1.0]. If this is the first time the data item is retrieved: 0.7 points are awarded; if the deviation between the latest data value and the previous data value is ≤3%: add 0.2 points, for a total of 0.9 points; if the deviation is >3% but ≤10%: add 0.1 points, for a total of 0.8 points; if the deviation in passenger numbers is <3: add 0.3 points, for a total of 1.0 points.

[0066] In this embodiment, the above-described implementation method determines the identification confidence level, logical confidence level, and update confidence level, forming a dynamic and adaptive confidence assessment system that effectively supports the needs of flight data filtering. This not only improves the accuracy and robustness of data filtering but also enhances the system's maintainability and user trust through interpretability and feedback loops.

[0067] In some embodiments, the step S140 above, "determining the data item confidence of each original data based on the attribute confidence of each original data and the data source confidence", can be implemented by the following process: weighting and summing the data source confidence, the identification confidence, the logical confidence, and the update confidence to obtain the data item confidence of the original data.

[0068] Here, the formula for calculating the confidence of a data item (3) is as follows: Confidence_Item=ω1×Confidence_Source+ω2×Score_DataItem+ω3×Score_Logic+ω4×Score_Update (3); where the coefficient (weight parameter) ω1+ω2+ω3+ω4=1, the default value and range optimization can be set as follows: ω1∈[0.4, 0.6], default 0.5; ω2∈[0.2, 0.3], default 0.25; ω3∈[0.1, 0.15]; ω4∈[0.05, 0.15], default 0.13.

[0069] In this embodiment, the data item confidence level of the original data can be obtained by weighted summing of the data source confidence level, identification confidence level, logical confidence level, and update confidence level. This data item confidence level can effectively characterize whether the corresponding original data is accurate and valid, providing an effective criterion for data filtering.

[0070] In some embodiments, this application provides a method for adjusting data source confidence, identification confidence, logical confidence, and updating confidence, which can be implemented through the following steps: Step 141, determining that the data source confidence is less than a data source confidence threshold; here, the data source confidence threshold can be set according to actual needs. For example, the data source confidence threshold can be set to 0.6.

[0071] Step 142: Decrease the weight value of the data source confidence and increase the weight value of at least one of the following attribute confidences: the identification confidence, the logical confidence, and the update confidence.

[0072] During implementation, the following weight adjustment rules can be set: if Confidence_Source < 0.6 (low confidence of the data source), then in the above formula (1), ω1 is adjusted down to 0.4, ω2 is adjusted up to 0.3, ω3 is adjusted up to 0.15, and ω4 is adjusted up to 0.15.

[0073] In some embodiments, the weight of the data source can be reduced proportionally or by a fixed value (e.g., from 40% to 20%) to reduce the impact of unreliable information channels on the final decision.

[0074] Attribute confidence weight enhancement: Simultaneously increase the weight of at least one of the following: recognition confidence, logical confidence, and update confidence. The adjustment range can be based on business priority (e.g., prioritizing recognition confidence in OCR scenarios) or historical performance (e.g., prioritizing the increase of weight for attributes with high historical accuracy).

[0075] Weight boundary control: The adjusted weights should be set within a reasonable range (e.g., data source weight ≥ 10%, total attribute confidence ≤ 90%) to avoid extreme weights that could lead to system instability.

[0076] In this embodiment, an upgrade from static weights to dynamic adaptive weights is implemented, enabling the data confidence assessment system to automatically optimize based on fluctuations in data source reliability and business needs, thereby improving the accuracy and robustness of flight data filtering. This mechanism not only enhances the system's adaptability but also improves its maintainability and user trust through feedback loops and interpretable design.

[0077] In some embodiments, the target data includes the transport volume of at least one segment corresponding to the target flight; this application embodiment also provides a method for determining the air transport volume of the target airport corresponding to the target flight, which can be implemented through the following steps: Step S160, determine at least one of the following flight parameters of the target flight: multi-segment flight, transit flight, diverted flight, arrival / departure direction, passenger aircraft attribute, cargo aircraft attribute; Here, based on the fused baseline manifest data, combined with the flight plan, a set of business rule engines (such as multi-segment flight, transit flight, diverted flight, arrival / departure direction, passenger / cargo aircraft, etc.) can be used to intelligently associate and calculate the air transport volume related to the airport.

[0078] During implementation, at least one of the following flight parameters can be obtained first: multi-segment flights, transit flights, diverted flights, arrival / departure directions, passenger aircraft type, and cargo aircraft type. Among them, multi-segment flights refer to flights with two or more segments in the flight plan (such as Beijing-Shanghai-Guangzhou), which is different from single-segment point-to-point flights.

[0079] A transit flight is a flight that needs to stop at a certain airport on its planned route for technical inspection, refueling, or passenger boarding and alighting (such as an international flight stopping at a domestic hub airport).

[0080] A diverted flight is a flight that is unable to reach its destination airport as planned due to weather, mechanical failure, air traffic control, or other reasons and needs to make a temporary landing at an alternative airport.

[0081] The direction of arrival and departure refers to the direction of takeoff and landing of a flight relative to the airport ("arrival" means the arrival airport, and "departure" means the departure airport).

[0082] The passenger aircraft attribute refers to the type of aircraft used for the flight mission, which is a passenger aircraft. Passenger capacity usually needs to be verified.

[0083] Cargo aircraft attributes refer to the type of aircraft used for the flight mission, which usually requires verification of cargo capacity and cargo type (such as dangerous goods labeling).

[0084] Step S170: Determine the air traffic volume of the target airport corresponding to the target flight based on at least one of the flight parameters and the traffic volume of at least one of the flight segments.

[0085] Multi-segment flights: calculated by summing the traffic volume of each segment.

[0086] If the flight is an ABC multi-segment inbound flight, and the airport is C, then the following formula (4) is used to calculate the transport volume: Inbound transport volume of the airport = [AC] direct flight transport volume + [BC] segment calculated transport volume (4); where, the [AC] direct flight transport volume represents the direct flight transport volume from airport A to airport C. For example, if the passenger flight is Beijing-Zhengzhou-Fuzhou, then the [AC] direct flight transport volume represents the number of passengers flying directly from Beijing to Fuzhou.

[0087] The calculated transport volume for segment [BC] can be calculated using the following formula (5): Calculated transport volume for segment [BC] = Total actual transport volume for [BC] - Transport volume for direct flights in [AC] (5); where, for example, the total actual transport volume for [BC] can be the actual transport volume of passengers from Zhengzhou to Fuzhou, including the number of passengers boarding in Zhengzhou and the number of passengers flying directly from Beijing to Fuzhou (transport volume for direct flights in [AC]); then, the calculated transport volume for segment [BC] can be obtained from the number of passengers boarding in Zhengzhou to Fuzhou. In the implementation process, since the transport volume of different segments can be charged in segments, multi-segment flights need to calculate the transport volume of different segments.

[0088] If a flight is a multi-segment outbound flight of ABC, and the local airport is A, the transport volume can be calculated using the following formula (6): Local outbound transport volume = [AB] transport volume + [AC] direct flight transport volume (6); where, [AB] transport volume refers to the transport volume from airport A to airport B; [AC] direct flight transport volume refers to the transport volume from airport A to airport C.

[0089] Transit flights: Only the cargo loading / unloading and passenger loading / unloading volume during transit at this airport is calculated. The formula is: For ABC transit flights, the airport is B. The following formula (7) can be used to calculate: Airport transport volume = [AB] airport inbound transport volume + [AC] direct flight transport volume (i.e., airport transit transport volume) + [BC] airport outbound transport volume (7); where, [BC] airport outbound transport volume = [BC] total actual transport volume - [AC] direct flight transport volume; Diverted flights: After diversion, there is no passenger transfer or cargo transfer, and the airport transport volume is counted as 0; Passenger and cargo aircraft distinction: Passenger aircraft only count passenger volume, and cargo aircraft only count cargo volume; Passenger and cargo mixed aircraft need to count passenger volume and cargo volume separately.

[0090] Results and Applications: Outputs final, unified, high-quality manifest data and generates accurate local air traffic volume statistics reports for airport production command, resource allocation, and business analysis.

[0091] In this embodiment, based on the obtained high-quality fused data, a "business volume calculation module" intelligently calculates the accurate transportation volume relevant to the actual situation at the airport based on flight attributes (such as multiple flight segments or transit points). In this way, instead of relying on any single perfect data source, a set of intelligent algorithms fully utilizes the value of all available data sources while suppressing their noise, thus not only solving the data source problem but also achieving in-depth mining of data into business value.

[0092] In the operation and management of civil aviation airports, flight manifests (including passenger, cargo, and baggage load balance data) are the core foundational information for airport operations, directly supporting airport decision-making and execution across multiple dimensions, including passenger service, safety assurance, operational efficiency, financial settlement, and long-term planning. Currently, the most authoritative and complete manifest data in the domestic civil aviation industry is centrally stored in System A. However, for airports, obtaining manifest data directly, stably, and in real-time from this core system faces numerous limitations and difficulties. This "desirable but unattainable" status quo of accessing the core data source forces airports to rely on various indirect and heterogeneous methods to obtain manifest data in actual operations, leading to a series of new technical problems: 1. Fragmented and unreliable data acquisition methods: ① Printed OCR recognition: To obtain data from System A, airports often need to first print the manifest as a paper or electronic image, and then convert it using optical character recognition technology. This method is not only inefficient, but the OCR recognition results are also affected by print quality, image clarity, and layout changes, resulting in inherent risks of misidentification and omission, and the accuracy of the data cannot be guaranteed.

[0093] ② International Airlines B Emails / Messages: For some international airlines B, their manifest data may be sent via email. The real-time nature of this method cannot be guaranteed, the formats vary widely, requiring significant manual intervention or customized parsing, making automated processing difficult.

[0094] ③Airline C System: Some airlines have their own manifest data interface, but their data interfaces and protocols are different, making integration with the airport's existing system highly complex and costly to maintain.

[0095] Other data sources: Some data can also be obtained through the relevant manifest data interface of the Civil Aviation Administration's sharing platform, but there are problems such as the inability to accurately obtain relevant data for multiple flight segments and transit flights; there is also some relevant data that can be obtained through commercial channels, but the data interfaces and protocols are different, which makes the integration with the airport's existing systems highly complex and the maintenance costs high.

[0096] 2. "Data Silos" and the Accuracy Dilemma: Each of the aforementioned alternative data sources constitutes a "data silo." They may provide some accurate data, but they differ significantly in format, content, and timeliness. When different sources provide inconsistent information on key data for the same flight (such as load factor and passenger numbers), the system lacks an automatic and reliable mechanism to determine which data should be used, often requiring manual verification, which is inefficient and prone to errors.

[0097] 3. Incomplete data coverage: Due to the lack of a stable and reliable single primary data source, any interruption of an alternative link (such as printer failure, email delay, or interface change) will directly lead to the loss of flight manifest data, making it difficult for the airport to obtain a complete and unified view of flight support, which seriously affects operational efficiency and safety.

[0098] In summary, this application aims to solve the core technical problem arising under the above background: how to overcome the technical difficulties of narrow data coverage, low accuracy and poor consistency caused by the limitation of direct access to core manifest data sources, which forces reliance on multiple heterogeneous, scattered and unreliable indirect data sources; and on this basis, to achieve accurate and automated statistics on the relevant air traffic volume of the airport based on manifest data.

[0099] To address this issue, Figure 2 is a flowchart illustrating a multi-source data fusion method based on intelligent confidence assessment, as provided in this application embodiment. As shown in Figure 2, the method can be implemented through the following steps: Step S210, multi-channel data acquisition; during implementation, the manifest information of the target flight is obtained in parallel from multiple indirect data sources, including but not limited to: OCR recognition results of the Load Distribution Message (LDM) printed out by System A, message data from the body or attachment of emails from airlines, data interfaces of airline manifests, data interfaces of shared manifests from the Civil Aviation Administration, and data interfaces provided by other external data vendors.

[0100] Step S220: Heterogeneous data standardization; During implementation, raw data from different channels with different formats can be mapped to a unified data model through interface parsing or message parsing, and key data items such as structured planned execution date, flight number, aircraft number, flight segment information, and the number of passengers and cargo / mail baggage weight corresponding to the flight segment can be extracted.

[0101] Step S230: Confidence Assessment and Weighted Fusion; During implementation, a confidence weight can be dynamically or statically assigned to each data item from each data source. This weight is calculated based on the historical accuracy of the data source, the characteristics of the data itself (such as image quality scores during OCR recognition), and the timeliness of the data. Subsequently, a weight-based fusion algorithm is used to calculate the optimal estimate for each data item. When conflicts arise between data sources, the system automatically arbitrates based on the confidence weights, generating a set of highly reliable "benchmark manifest data."

[0102] Confidence assessment is divided into two levels: the data source level and the data item level.

[0103] 1. Data source confidence assessment: The core assessment dimensions include historical accuracy (Accuracy_Historical) and data authority (Weight_Authority). Among them, historical accuracy can represent the correct percentage of data sources obtained in the past. For example, historical accuracy can be obtained based on the correct percentage of valid data in the past 90 natural days of the data source, and is calculated by the following formula (1): Accuracy_Historical = (Amount of correct data in valid data / Total amount of valid data) × 100% (1); where valid data refers to "the number of flights that can effectively identify relevant manifests", and correct data refers to "the number of flights that have been manually confirmed to have accurate data".

[0104] Data source authority can be assigned an inherent authority weight to different data sources. For example, the authority value of the airline's manifest data interface is 1.0; the authority value of the mail delivery data provided by the airline is 0.9; the authority value of the OCR recognition result of the flight information service is 0.8; the authority value of the delivery data interface provided by the Aircraft Communications Addressing and Reporting System (ACARS) is 0.7; the authority value of the flight information service's manifest OCR recognition result is 0.6; the authority value of the Civil Aviation Administration of China (CAAC) interface data is 0.5; and the authority value of third-party data interfaces is 0.4.

[0105] The formula for calculating the overall confidence level of the data source (2) is as follows: Confidence_Source=α×Accuracy_Historical+β×Weight_Authority (2); where the coefficients α and β satisfy α+β=1, and the default values ​​and ranges are optimized as follows: α∈[0.5, 0.7], default 0.6; β∈[0.3, 0.5], default 0.4; In some embodiments, the triggering conditions can be dynamically adjusted in the following scenarios: Scenario 1: If Accuracy_Historical≥95%, α is increased to 0.7 and β is decreased to 0.3; Scenario 2: If Weight_Authority=1.0, β is increased to 0.5 and α is decreased to 0.5.

[0106] 2. Data Item Confidence Assessment: The core assessment dimensions include at least one of the following: intrinsic quality score (Score_DataItem), logical reasonableness (Score_Logic), and data update (Score_Update). For example, the intrinsic quality score (recognition confidence) of OCR-recognized data directly uses the recognition confidence score provided by the OCR engine (e.g., 0.92); for data items from non-OCR sources, the default value is 1.0.

[0107] Logical Reasonableness (Logical Confidence): Performs logical checks on data values, such as whether the number of passengers is within the maximum passenger capacity of the aircraft type, is a non-negative integer and less than 999; whether the weight of cargo and mail is within the aircraft's load capacity, etc.; whether the passenger capacity of passenger aircraft is greater than 0, and the passenger capacity of cargo aircraft is 0, etc. The default value is 1.0, and it decreases by 0.5 for each failed check, until the value of this item is 0.

[0108] Data Update (Update Confidence): This function compares and judges data values. If the latest received data value differs from the previously received data value, the latest data item will receive a bonus. For example, the Score_Update value range can be set to [0.7, 1.0]. If this is the first time the data item is retrieved: 0.7 points are awarded; if the deviation between the latest and previous data values ​​is ≤3%: 0.2 points are added, resulting in 0.9 points; if the deviation is >3% but ≤10%: 0.1 points are added, resulting in 0.8 points; if the passenger number deviation is <3: 0.3 points are added, resulting in 1.0 point.

[0109] Here, the formula for calculating the confidence of a data item (3) is as follows: Confidence_Item=ω1×Confidence_Source+ω2×Score_DataItem+ω3×Score_Logic+ω4×Score_Update (3); where the coefficient (weight parameter) ω1+ω2+ω3+ω4=1, the default value and range optimization can be set as follows: ω1∈[0.4, 0.6], default 0.5; ω2∈[0.2, 0.3], default 0.25; ω3∈[0.1, 0.15]; ω4∈[0.05, 0.15], default 0.13.

[0110] In some embodiments, the following weight adjustment rules can be set: if Confidence_Source < 0.6 (low confidence of the data source), then ω1 is adjusted down to 0.4, ω2 is adjusted up to 0.3, ω3 is adjusted up to 0.15, and ω4 is adjusted up to 0.15.

[0111] During implementation, the system records data items for each flight. When the overall confidence level of newly acquired data items is higher than that of existing data items in the system, the system is updated, and the corresponding update basis is recorded.

[0112] Step S240: Calculation of local transport volume.

[0113] During implementation, based on the integrated baseline manifest data and combined with flight schedules, a set of business rule engines (such as multi-segment flights, transit flights, diverted flights, arrival / departure directions, passenger / cargo aircraft, etc.) can intelligently correlate and calculate the air traffic volume related to the airport. The specific calculation rules and correlation logic of the rule engine are as follows: Multi-segment flights: calculated by accumulating the traffic volume of each segment.

[0114] If the flight is an ABC multi-segment inbound flight, and the airport is C, then the following formula (4) is used to calculate the transport volume: Inbound transport volume of the airport = [AC] direct flight transport volume + [BC] segment calculated transport volume (4); where, the [AC] direct flight transport volume represents the direct flight transport volume from airport A to airport C. For example, if the passenger flight is Beijing-Zhengzhou-Fuzhou, then the [AC] direct flight transport volume represents the number of passengers flying directly from Beijing to Fuzhou.

[0115] The calculated transport volume for segment [BC] can be calculated using the following formula (5): Calculated transport volume for segment [BC] = Total actual transport volume for [BC] - Transport volume for direct flights in [AC] (5); where, for example, the total actual transport volume for [BC] can be the actual transport volume of passengers from Zhengzhou to Fuzhou, including the number of passengers boarding in Zhengzhou and the number of passengers flying directly from Beijing to Fuzhou (transport volume for direct flights in [AC]); then, the calculated transport volume for segment [BC] can be obtained from the number of passengers boarding in Zhengzhou to Fuzhou. In the implementation process, since the transport volume of different segments can be charged in segments, multi-segment flights need to calculate the transport volume of different segments.

[0116] If a flight is a multi-segment outbound flight of ABC, and the local airport is A, the transport volume can be calculated using the following formula (6): Local outbound transport volume = [AB] transport volume + [AC] direct flight transport volume (6); where, [AB] transport volume refers to the transport volume from airport A to airport B; [AC] direct flight transport volume refers to the transport volume from airport A to airport C.

[0117] Transit flights: Only the cargo loading / unloading and passenger loading / unloading volume during transit at this airport is calculated. The formula is: For ABC transit flights, the airport is B. The following formula (7) can be used to calculate: Airport transport volume = [AB] airport inbound transport volume + [AC] direct flight transport volume (i.e., airport transit transport volume) + [BC] airport outbound transport volume (7); where, [BC] airport outbound transport volume = [BC] total actual transport volume - [AC] direct flight transport volume; Diverted flights: After diversion, there is no passenger transfer or cargo transfer, and the airport transport volume is counted as 0; Passenger and cargo aircraft distinction: Passenger aircraft only count passenger volume, and cargo aircraft only count cargo volume; Passenger and cargo mixed aircraft need to count passenger volume and cargo volume separately.

[0118] Results and Applications: Outputs final, unified, high-quality manifest data and generates accurate local air traffic volume statistics reports for airport production command, resource allocation, and business analysis.

[0119] The transportation volume calculation method provided in this application introduces a core intelligent layer of "confidence assessment and fusion." The system has a built-in set of rules or models that dynamically assign a "confidence score" to each data item from different sources, and performs weighted fusion and automatic conflict resolution based on this score, ultimately outputting a unique, optimal, and highly reliable data version. Based on the obtained high-quality fused data, a "business volume calculation module" intelligently calculates the accurate transportation volume relevant to the actual situation at the airport based on flight attributes (such as multi-segment or transit). In this way, instead of relying on any single perfect data source, it fully utilizes the value of all available data sources and suppresses their noise through an intelligent algorithm, not only solving the data source problem but also achieving deep mining of data into business value. It not only outputs more reliable data but also derives new knowledge with direct business value (such as "actual number of departing passengers at the airport"), realizing an elevation from data to decision-making.

[0120] This application provides a multi-source data processing device. Referring to Figure 3, the system 300 includes: an acquisition module 310, used to acquire at least one original data of a target flight from at least one information channel; a first determination module 320, used to determine the data source confidence of each original data based on the accuracy of the information channel corresponding to each original data and a preset channel authority value; a second determination module 330, used to analyze the content of each original data and determine the attribute confidence of each original data based on the content analysis results, wherein the attribute confidence includes at least one of the following: identification confidence, logical confidence, and update confidence; a second determination module 340, used to determine the data item confidence of each original data based on the attribute confidence and the data source confidence; and a sorting module 350, used to sort the data item confidence of the original data to determine the original data with the highest data item confidence as the target data of the target flight.

[0121] In some embodiments, the first determining module 320 includes a first determining submodule, an acquiring submodule, and a weighted summation submodule, wherein the first determining submodule is used to determine the accuracy of the information channel based on the correct data volume and the total data volume of the information channel; the acquiring submodule is used to acquire the preset channel authority value based on the identification information of the information channel; and the weighted summation submodule is used to perform a weighted summation of the accuracy and the channel authority value to obtain the data source confidence of the original data.

[0122] In some embodiments, the first determining module 320 further includes a first adjustment submodule and a second adjustment submodule, wherein the first adjustment submodule is used to determine that when the accuracy rate is greater than an accuracy rate threshold, increase the weight value corresponding to the accuracy rate and decrease the weight value corresponding to the channel authority value; the second adjustment submodule is used to determine that when the channel authority value matches a preset authority threshold, increase the weight value corresponding to the channel authority value and decrease the weight value corresponding to the accuracy rate.

[0123] In some embodiments, the second determining module 330 includes a second determining submodule, a third determining submodule, and a fourth determining submodule. The second determining submodule is used to determine the recognition confidence level of the original data as the recognition confidence level of the original data when the original data is obtained based on Optical Character Recognition (OCR). The third determining submodule is used to perform logical verification on the original data to determine the logical confidence level based on the verification result. The fourth determining submodule is used to determine the updated confidence level based on the deviation between the original data and the corresponding historical data.

[0124] In some embodiments, the third determining module 340 is further configured to perform a weighted summation of the data source confidence, the identification confidence, the logical confidence, and the update confidence to obtain the data item confidence of the original data.

[0125] In some embodiments, the third determining module 340 includes a fifth determining submodule and a third adjusting submodule, wherein the fifth determining submodule is used to determine that the confidence level of the data source is less than the confidence level threshold of the data source; the third adjusting submodule is used to reduce the weight value of the confidence level of the data source, while increasing the weight value of at least one of the following attribute confidence levels: the identification confidence level, the logical confidence level, and the update confidence level.

[0126] In some embodiments, the target data includes the traffic volume of at least one segment corresponding to the target flight; the apparatus further includes a fourth determining module and a fifth determining module, wherein the fourth determining module is used to determine at least one of the following flight parameters of the target flight: multi-segment flight, transit flight, diverted flight, arrival / departure direction, passenger aircraft attribute, and cargo aircraft attribute; the fifth determining module is used to determine the air traffic volume of the target airport corresponding to the target flight based on at least one of the flight parameters and the traffic volume of at least one segment.

[0127] Figure 4 is a schematic diagram of the structure of a computer block device provided in an embodiment of this application. As exemplarily shown in Figure 4, the computer block device 400 includes: a memory 401, a processor 402, and a computer program 403 stored in the memory 401 and running on the processor 402, wherein when the processor 402 executes the computer program 403, the computer block device can perform any of the multi-source data processing methods described above.

[0128] Furthermore, this application also protects a control block device, which may include a memory and a processor. The memory stores executable program code, and the processor is used to call and execute the executable program code to perform a multi-source data processing method provided in this application. This application can divide the control block device into functional modules based on the above method examples. For example, each module may correspond to a specific function, or two or more functions may be integrated into a single processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this application is illustrative and only represents a logical functional division; other division methods may exist in actual implementation. It should also be noted that all relevant content of each step involved in the above method embodiments can be referenced to the functional description of the corresponding functional module, and will not be repeated here. It should be understood that the control block device provided in this application is used to execute the above-described multi-source data processing method, and therefore can achieve the same effect as the above-described implementation method. When using integrated units, the control block device may include a processing module and a storage module. When the control block device is applied to a block device, the processing module can be used to control and manage the actions of the block device. The storage module can be used to support block devices in executing mutual program code, etc. The processing module can be a processor or controller, which can implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. The processor can also be a combination of functions that implement computing capabilities, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and microprocessors, etc., and the storage module can be a memory.

[0129] Furthermore, the control block device provided in the embodiments of this application may specifically be a chip, component, or module. The chip may include a connected processor and a memory; wherein, the memory is used to store instructions, and when the processor calls and executes the instructions, the chip can execute a multi-source data processing method provided in the above embodiments. The embodiments of this application also provide a computer-readable storage medium storing computer program code. When the computer program code is run on a computer, it causes the computer to execute the aforementioned method steps to implement a multi-source data processing method provided in the above embodiments.

[0130] This application also provides a computer program product. When the computer program product is run on a computer, it causes the computer to perform the above-mentioned related steps to implement the multi-source data processing method provided in the above embodiments. The control block device, computer-readable storage medium, computer program product, or chip provided in this application are all used to execute the corresponding methods provided above. Therefore, the beneficial effects they achieve can be referred to in the beneficial effects of the corresponding methods provided above, and will not be repeated here. Through the description of the above embodiments, those skilled in the art can understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the control block device can be divided into different functional modules to complete all or part of the functions described above. In the embodiments provided in this application, it should be understood that the disclosed control block device and method can be implemented in other ways. For example, the control block device embodiments described above are merely illustrative. For example, the division of modules or units is only a logical functional division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another control block device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, control block device or unit, and can be electrical, mechanical or other forms.

[0131] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some embodiments, multiple task processing and parallel processing are possible or may be advantageous. The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. The above content is only a specific implementation of this application, but the protection scope of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the protection scope of this application.

Claims

1. A multi-source data processing method, characterized in that, The method includes: obtaining at least one piece of raw data for a target flight from at least one information channel; determining the data source confidence of each piece of raw data based on the accuracy of the information channel corresponding to each piece of raw data and a preset channel authority value; analyzing the content of each piece of raw data and determining the attribute confidence of each piece of raw data based on the content analysis results, wherein the attribute confidence includes at least one of the following: identification confidence, logical confidence, and update confidence; determining the data item confidence of each piece of raw data based on the attribute confidence and the data source confidence; and sorting the data item confidence of the raw data to determine the raw data with the highest data item confidence as the target data for the target flight.

2. The method as described in claim 1, characterized in that, The step of determining the data source confidence of each original data source based on the accuracy of the information channel corresponding to each original data source and a preset channel authority value includes: determining the accuracy of the information channel based on the correct data volume and total data volume of the information channel; obtaining the preset channel authority value based on the identification information of the information channel; and performing a weighted summation of the accuracy and the channel authority value to obtain the data source confidence of the original data source.

3. The method as described in claim 2, characterized in that, The method further includes: when the accuracy rate is greater than an accuracy rate threshold, increasing the weight value corresponding to the accuracy rate while decreasing the weight value corresponding to the channel authority value; when the channel authority value matches a preset authority threshold, increasing the weight value corresponding to the channel authority value while decreasing the weight value corresponding to the accuracy rate.

4. The method as described in claim 1, characterized in that, The step of analyzing the content of each piece of original data and determining the attribute confidence level of each piece of original data based on the content analysis results includes: determining the recognition confidence level of the OCR as the recognition confidence level of the original data when the original data is determined to be obtained based on optical character recognition (OCR); performing logical verification on the original data to determine the logical confidence level based on the verification results; and determining the updated confidence level based on the deviation between the original data and the corresponding historical data.

5. The method as described in claim 1, characterized in that, Determining the data item confidence of each original data based on the attribute confidence of each original data and the data source confidence includes: performing a weighted summation of the data source confidence, the identification confidence, the logical confidence, and the update confidence to obtain the data item confidence of the original data.

6. The method as described in claim 5, characterized in that, The method further includes: determining that the confidence level of the data source is less than the confidence level threshold of the data source; reducing the weight value of the confidence level of the data source, while increasing the weight value of at least one of the following attribute confidence levels: the identification confidence level, the logical confidence level, and the update confidence level.

7. The method according to any one of claims 1 to 6, characterized in that, The target data includes the transport volume of at least one segment corresponding to the target flight; the method further includes: determining at least one of the following flight parameters of the target flight: multi-segment flight, transit flight, diverted flight, arrival / departure direction, passenger aircraft attribute, cargo aircraft attribute; and determining the air transport volume of the target airport corresponding to the target flight based on at least one of the flight parameters and the transport volume of at least one segment.

8. A multi-source data processing device, characterized in that, The method includes: an acquisition module for acquiring at least one piece of raw data of a target flight from at least one information channel; a first determination module for determining the data source confidence of each piece of raw data based on the accuracy of the information channel corresponding to each piece of raw data and a preset channel authority value; a second determination module for analyzing the content of each piece of raw data and determining the attribute confidence of each piece of raw data based on the content analysis results, wherein the attribute confidence includes at least one of the following: identification confidence, logical confidence, and update confidence; a third determination module for determining the data item confidence of each piece of raw data based on the attribute confidence and the data source confidence; and a sorting module for sorting the data item confidence of the raw data to determine the raw data with the highest data item confidence as the target data of the target flight.

9. An electronic device comprising a memory and a processor, the memory storing a computer program executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the multi-source data processing method according to any one of claims 1 to 7.

10. A computer program product, characterized in that, The computer program product includes: computer program code, which, when run on an electronic device, implements the steps of the multi-source data processing method as described in any one of claims 1 to 7.

Images