Civil aviation passenger data portrait method and system, electronic equipment and storage medium

Abstract

The invention provides a civil aviation passenger data portraying method and system, electronic equipment and a storage medium, and the method comprises the steps: obtaining civil aviation passenger demand data and airport activity data, and forming a passenger behavior and environment data set; extracting time characteristics of key behaviors of civil aviation passengers based on the passenger behaviors and the environment data set, and generating time sequence behavior dependence characteristics; generating a similar behavior data set based on the time sequence behavior dependence characteristics to identify key behavior modes of civil aviation passengers, and constructing a group behavior mode set; and setting a real-time data flow interface based on the group behavior mode set to obtain a dynamically updated passenger portrait. Therefore, a civil aviation passenger personalized service scheme is conveniently generated, dynamic data analysis is realized, the flexibility and real-time performance during passenger data processing are improved, dynamic service adjustment and timely response to passenger demands are facilitated, and the individuation and satisfaction of the service are improved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of civil aviation passenger profiling, and in particular to a civil aviation passenger data profiling method, system, electronic device and storage medium. Background Art

[0002] Passenger profiling technology uses data analysis methods to extract valuable information from large amounts of passenger data to build detailed portraits of individual or group passengers, which can help airlines and travel service providers conduct more accurate market positioning, service personalization and operational optimization.

[0003] The civil aviation passenger data profiling method is a specific application of passenger profiling technology in the civil aviation field. It uses a large amount of data collected from civil aviation passengers and builds passenger behavior and preference models through statistical and analytical techniques to help airlines better understand their customer base, optimize service provision, improve passenger satisfaction, and increase revenue.

[0004] However, current civil aviation passenger data profiling technology usually relies on static data analysis and lacks flexibility and real-time performance when processing passenger data. It is insufficient in dynamically adjusting services and responding to passenger needs in a timely manner, resulting in services that may be out of sync with passengers' current expectations, affecting the personalization and satisfaction of services. Summary of the invention

[0005] To solve the above problems, the present disclosure provides a civil aviation passenger data profiling method, system, electronic device and storage medium. By accurately matching the current needs of passengers, deep preference analysis can reveal subtle changes in passenger choices, enabling airlines to provide more refined flight options based on passengers' purchasing behavior, enhance the accuracy of market positioning, improve the personalization of services and the flexibility of operations, and help improve passenger satisfaction and airline profits.

[0006] A first aspect of the present disclosure provides a civil aviation passenger data profiling method, comprising: acquiring civil aviation passenger demand data and airport activity data, and forming a passenger behavior and environment data set; extracting time characteristics of key behaviors of civil aviation passengers based on the passenger behavior and environment data set, and generating temporal behavior dependency features; generating a similar behavior data set based on the temporal behavior dependency features to identify key behavior patterns of civil aviation passengers and construct a group behavior pattern set; and setting a real-time data stream interface based on the group behavior pattern set to obtain a dynamically updated passenger portrait.

[0007] This setting combines passenger needs with airport activities and finds the time characteristics of passenger key behaviors, so as to build a set of group behavior patterns and obtain dynamically updated passenger portraits. This helps to generate personalized service plans for civil aviation passengers after analyzing the attributes of target flights based on the passenger portraits. It also enables dynamic data analysis, improves flexibility and real-time performance in processing passenger data, and helps to dynamically adjust services and respond to passenger needs in a timely manner, thereby improving service personalization and satisfaction.

[0008] In some embodiments, the obtaining of civil aviation passenger demand data and airport activity data and forming a passenger behavior and environment data set includes: obtaining civil aviation passengers' flight selection information, ticket purchase time and airport activity data in real time based on an application programming interface, and generating a travel data set; collecting current weather information and flight update status based on the travel data set, and generating an enhanced travel environment data set; performing data cleaning and preprocessing based on the enhanced travel environment data set to obtain a passenger behavior and environment data set.

[0009] Such a setting helps to collect passengers' needs and collect passengers' behavior and environmental data based on airport activities and weather conditions, making the data collected from passengers more real-time and dynamic.

[0010] In some embodiments, the extracting of time characteristics of key behaviors of civil aviation passengers based on the passenger behavior and environmental data set and generating time series behavior dependency characteristics includes: filtering data records with time tags based on the passenger behavior and environmental data set and generating a time series data set; acquiring key behaviors of civil aviation passengers at different time points based on the time series data set and generating a key behavior time characteristic data set; analyzing passenger behavior periodicity and trends based on the key behavior time characteristic data set to obtain time series behavior dependency characteristics.

[0011] This setting collects the key behaviors of flight passengers at different time points, so as to analyze the periodicity and trend of passenger behavior, and helps predict the future activity trends of passengers.

[0012] In some embodiments, the generating of a similar behavior data set based on the temporal behavior dependency feature to identify key behavior patterns of civil aviation passengers and constructing a group behavior pattern set includes: analyzing the time and behavior differences between data points in the key behavior time feature data set based on the temporal behavior dependency feature, and generating a similar behavior data set after grouping; obtaining the start and end time points of the behavior based on the similar behavior data set, and generating a key behavior pattern set; constructing a behavior pattern description for each group based on the key behavior pattern set to obtain a group behavior pattern set.

[0013] Such a setting helps to obtain the start and end time points of the behavior based on the time and behavior differences between data points to construct the behavior pattern of each group, identify the key behavior patterns of passengers, and then facilitate the construction of a group behavior pattern set to collect the passenger behavior pattern sets and enhance the diversity of civil aviation passenger behavior patterns.

[0014] In some embodiments, the analyzing the time and behavior differences of data points based on the temporal behavior dependency feature and generating a similar behavior data set includes: the time and behavior difference analysis formula,

[0015]

[0016] Calculate the comprehensive difference Δd between data points ij , where Δt ij =|t i -t j | represents the time difference, Δf ij =|f i -f j | represents the behavior frequency difference, τ is the time scaling parameter, φ is the behavior frequency scaling parameter, α and β are weight coefficients, γ and λ are the time decay coefficient and decay rate respectively.

[0017] Such a setting helps to analyze the time and behavior differences of passengers, filter out similar behaviors, and then generate a similar behavior data set.

[0018] In some embodiments, setting a real-time data stream interface based on the group behavior pattern set to obtain a dynamically updated passenger profile includes: setting a real-time data stream interface based on the group behavior pattern set to obtain new flight reservations and service evaluation events to generate a real-time behavior matching data set; comparing each service evaluation event with an existing passenger profile based on the real-time behavior matching data set to generate a passenger profile update data set; integrating all updated passenger profile information based on the passenger portrait update data set to obtain a dynamically updated passenger profile.

[0019] With this arrangement, it is possible to monitor new flight reservations and service evaluation events of civil aviation passengers, update the passenger portrait set through real-time feedback, and obtain dynamically updated passenger portraits, so as to facilitate real-time updating of passenger portraits, which helps to understand the latest needs and trends of passengers.

[0020] In some embodiments, the analyzing the target flight attributes based on the passenger portrait to generate a personalized service plan for civil aviation passengers includes: after analyzing the target flight attributes based on the passenger portrait, matching the characteristics of each flight with the passenger preferences to generate a flight attribute analysis data set; identifying the passenger's preferences for the target flight attributes based on the flight attribute analysis data set, and generating a civil aviation passenger service optimization suggestion set; integrating flight services and passenger preferences based on the passenger service optimization suggestion set to obtain a personalized service plan for civil aviation passengers.

[0021] With such settings, flight preference association rules are applied to conduct in-depth analysis of target flight attributes, optimize civil aviation passenger service plans, and generate personalized service plans for civil aviation passengers, which helps to improve the personalization of services and passenger satisfaction.

[0022] A second aspect of the present disclosure provides a civil aviation passenger data profiling system, the system comprising: a collection module for acquiring civil aviation passenger demand data and airport activity data, and forming a passenger behavior and environment data set; a prediction module for extracting time characteristics of key behaviors of civil aviation passengers based on the passenger behavior and environment data set, and generating temporal behavior dependency features; an identification module for generating a similar behavior data set based on the temporal behavior dependency features to identify key behavior patterns of civil aviation passengers and construct a group behavior pattern set; an update module for setting a real-time data stream interface based on the group behavior pattern set to obtain a dynamically updated passenger portrait.

[0023] Such a setting significantly improves the response speed to changes in passenger demand through the integration of real-time data streams and the updating of dynamic passenger portraits. The integrated real-time flight booking information and service evaluation enable airlines to adjust services in real time to accurately match passengers' current needs. Deep preference analysis can reveal subtle changes in passenger choices, improve the flexibility and real-time performance of passenger data processing, help dynamically adjust services and respond to passenger needs in a timely manner, and help improve service personalization and satisfaction.

[0024] A third aspect of the present disclosure provides an electronic device, comprising: a memory for storing a computer program; and a processor for implementing the civil aviation passenger data profiling method as described in the first aspect when executing the computer program.

[0025] The technical effects brought about by any possible implementation of the third aspect can refer to the technical effects brought about by the above-mentioned first aspect, and will not be repeated here.

[0026] A fourth aspect of the present disclosure provides a computer storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the civil aviation passenger data profiling method as described in the first aspect is implemented.

[0027] The technical effects brought about by any possible implementation of the fourth aspect can refer to the technical effects brought about by the above-mentioned first aspect, and will not be repeated here.

[0028] Compared with the prior art, the present invention has the following advantages:

[0029] 1. The integration of real-time data streams and the updating of dynamic passenger profiles significantly improve the response speed to changes in passenger demand;

[0030] 2. Comprehensive real-time flight booking information and service evaluations enable airlines to adjust services in real time to accurately match passengers' current needs. Deep preference analysis can reveal subtle changes in passenger choices, providing airlines with an effective tool to optimize services and enhance passenger satisfaction.

[0031] 3. By building flight preference association rules, airlines can provide more refined flight options based on passengers' purchasing behavior, enhance the accuracy of market positioning, improve the personalization of services and operational flexibility, and help improve passenger loyalty and company profits.

[0032] Other features and advantages of the present disclosure will be described in the following description, and partly become apparent from the description, or be understood by implementing the present disclosure. The purpose and other advantages of the present disclosure can be realized and obtained by the structures pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0034] Figure 1 A flow chart of a civil aviation passenger data profiling method provided in an embodiment of the present disclosure;

[0035] Figure 2 A flowchart of the steps for obtaining a passenger behavior and environment data set provided in an embodiment of the present disclosure;

[0036] Figure 3 A flowchart of the steps for obtaining the timing behavior dependency feature provided by the embodiment of the present disclosure;

[0037] Figure 4 A flowchart of steps for obtaining a group behavior pattern set provided in an embodiment of the present disclosure;

[0038] Figure 5A flowchart of the acquisition steps for dynamically updating a passenger portrait provided in an embodiment of the present disclosure;

[0039] Figure 6 A flowchart of steps for obtaining a personalized service plan for civil aviation passengers provided in an embodiment of the present disclosure;

[0040] Figure 7 A structural block diagram of a civil aviation passenger data profiling system provided in an embodiment of the present disclosure;

[0041] Figure 8 The present invention provides an electronic device structure frame. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0043] The purpose of passenger profiling technology is to identify passenger behavior patterns, preferences and needs. By analyzing passengers' historical behavior data, such as ticket purchase records, itinerary selection, service preferences, etc., a detailed passenger profile can be generated. For example, by analyzing passengers' travel patterns and purchasing behaviors, airlines can provide more customized flight options and value-added services, such as priority boarding and customized meals. In addition, it can also be used for risk management and security strategies, such as predicting security risks by analyzing passenger behavior.

[0044] Existing passenger profiling technologies usually rely on static data analysis, lack flexibility and real-time performance when processing passenger data, and are insufficient in dynamically adjusting services and responding to passenger needs in a timely manner, resulting in services that may be out of sync with passengers' current expectations. Static profiling technology is difficult to accurately capture immediate changes in passenger preferences, affecting the personalization and satisfaction of services. For example, in the handling of passenger complaints and service evaluations, due to the lack of a real-time feedback mechanism, airlines may fail to improve services in a timely manner, reducing the overall customer experience and loyalty. In addition, the limitations of static analysis models in predicting future passenger behavior make it impossible to effectively identify new market opportunities or respond to changes in the competitive environment, which in turn affects revenue and market share.

[0045] To this end, the present disclosure provides a civil aviation passenger data profiling method, which has a feedback mechanism for handling passenger complaints and service evaluations, so that airlines can improve services in a timely manner and enhance the overall customer experience and loyalty. In addition, it can also predict the future behavior of passengers, effectively identify new market opportunities or respond to changes in the competitive environment, thereby increasing revenue and market share. Figure 1 As shown, Figure 1 A flow chart of a civil aviation passenger data profiling method provided in an embodiment of the present disclosure, the method comprising the following steps:

[0046] S100. Acquire civil aviation passenger demand data and airport activity data, and form a passenger behavior and environment data set.

[0047] In this embodiment, demand data can be understood as the collection of civil aviation passenger flight selection, ticket purchase time and airport activity data, and the airport activity data includes the departure and destination weather and flight update status. In other words, the passenger behavior and environment data set includes flight selection data, ticket purchase time data, airport activity records, weather information and flight status.

[0048] In some embodiments, see Figure 2 , Figure 2 The flowchart of the steps for obtaining the passenger behavior and environment data set provided in the embodiment of the present disclosure, step S100 may include S101 to S103, as follows:

[0049] S101. Acquire flight selection information, ticket purchase time, and airport activity data of civil aviation passengers in real time based on an application programming interface, and generate an air travel data set.

[0050] In this embodiment, the flight selection information, ticket purchase time and airport activity data of civil aviation passengers are collected, and through cooperation with airlines and airports, the API interface (Application Programming Interface) is used to obtain data in real time, organize the data into a structured format, and generate an air travel data set.

[0051] For example, the flight selection information, ticket purchase time and airport activity data of civil aviation passengers are collected, and the weight coefficients of flight selection information, ticket purchase time and airport activity data are respectively represented by setting parameters α, β, and γ. According to the specific agreement of cooperation with airlines and airports, the API interface is called to obtain data in real time. For each piece of data, the weighted synthesis formula D = αx + βy + γz (where x, y, and z represent the flight selection information, ticket purchase time, and airport activity data collected from the interface, respectively) is executed to ensure that the setting of the weight coefficient can reflect the actual importance of different data types. In this process, the data is organized into a structured format to generate an air travel data set; wherein, the setting of α, β, and γ is dynamically adjusted according to the influence of the data on the passenger's air travel decision, and the specific weight adjustment is based on the impact analysis results of historical data.

[0052] S102: Collect current weather information and flight update status based on the flight travel data set, and generate an enhanced flight travel environment data set.

[0053] In this embodiment, based on the air travel data set, current weather information and flight update status are collected, and weather conditions and flight dynamic update information are added to the air travel data set through the API provided by the meteorological department and the aviation administration bureau to generate an enhanced air travel environment data set.

[0054] For example, through the API provided by the meteorological department and the aviation administration, a formula E=δt+εu is established to integrate weather conditions and flight dynamic update information, where t represents weather condition data, u represents flight update information, and δ and ε are corresponding weight coefficients. The weight is set based on the impact of historical data analysis on the actual flight of passengers, and weather conditions and flight dynamic update information are added to the travel data set to generate an enhanced travel environment data set; wherein, δ and ε are dynamically adjusted to adapt to changes in sensitivity to weather and flight updates in different seasons or different regions.

[0055] S103: Perform data cleaning and preprocessing based on the enhanced air travel environment dataset to obtain a passenger behavior and environment dataset.

[0056] In this embodiment, based on the enhanced air travel environment data set, data cleaning and preprocessing are performed to remove erroneous and duplicate data, standardize the time format and data fields, and obtain the passenger behavior and environment data set.

[0057] Exemplarily, firstly, a data integrity check is performed to identify and remove erroneous data v. The data item v is scored according to its integrity and logical consistency, and a threshold θ is set. If the data item score is lower than θ, it is identified as erroneous data and removed. Secondly, for the standardization of time format and data fields, the formula G(w)=κw+λ is used for conversion, where w represents the original time data, κ and λ are conversion parameters, which are set according to the standard of the target database. The data is standardized through this formula to obtain the passenger behavior and environment data set.

[0058] S200, extracting the temporal characteristics of key behaviors of civil aviation passengers based on the passenger behavior and environment data set, and generating temporal behavior dependency features.

[0059] In this embodiment, based on the passenger behavior and environment data set, the time points of the data set are analyzed, the time characteristics of the key behaviors of civil aviation passengers are extracted, and the future activity trends of passengers are predicted to generate time-series behavior dependency features. The time-series behavior dependency features include time point tags, behavior time series, and passenger future activity prediction results.

[0060] In some embodiments, see Figure 3 , Figure 3 The flowchart of the steps for obtaining the timing behavior dependency feature provided by the embodiment of the present disclosure, step S200 may include S201 to S203, as follows:

[0061] S201. Filter data records with time tags based on the passenger behavior and environment dataset, and generate a time series dataset.

[0062] In this embodiment, the filtered data records with time tags are sorted in chronological order to ensure the continuity of the time series and generate a time series data set.

[0063] For example, based on the passenger behavior and environment dataset, data records with time tags are filtered and sorted by defining a sorting function where t i The time tag representing each piece of data is used to sort the data in chronological order to ensure the continuity of the time series and generate a time-series data set. During this process, the time sorting algorithm will consider the accuracy and completeness of the timestamp to ensure that there is no time dislocation. The timestamp verification mechanism is used to ensure the validity and accuracy of all time tags and eliminate any possible time errors or duplications.

[0064] S202. Acquire key behaviors of civil aviation passengers at different time points based on the time series data set, and generate a key behavior time feature data set.

[0065] In this embodiment, the key behaviors of civil aviation passengers at different time points include the time points of boarding, buying tickets and participating in airport activities. The key time points are then marked to generate a key behavior time feature data set.

[0066] Exemplarily, based on a time series data set, key behaviors of civil aviation passengers at different time points are extracted, including: boarding, ticket purchase, and participation in airport activities, and key time points are marked to generate a key behavior time feature data set; an extraction function T(x) = {x|x is a key time point} is used, where x represents the time point extracted from the data set. This function identifies and extracts the time points of boarding, ticket purchase, and participation in airport activities, and marks these time points for further analysis. At the same time, a weight function W(a, b, c) is defined to adjust the degree of attention to boarding a, ticket purchase b, and activity participation c. The weight reflects the priority of different behaviors. These time points are marked after being processed by the T(x) function and are used for further data set construction.

[0067] S203. Analyze the periodicity and trend of passenger behavior based on the key behavior time feature data set to obtain time series behavior dependency features.

[0068] In this embodiment, based on the key behavior time feature data set, the passenger behavior periodicity and trend are analyzed to predict the passenger's future behavior pattern, and the future activity time is evaluated according to the past behavior time points to obtain the temporal behavior dependency characteristics.

[0069] For example, the future activity time is evaluated based on the past behavior time points to obtain the time series behavior dependency characteristics; through the periodic analysis function P(d) = d period, where d represents the passenger's behavior data, this function analyzes the time periodicity and repetitive patterns in the data to predict future behavior. Trend analysis uses the function Q(d) = αd 近期 +βd 长期 , where α and β are the weights of recent and long-term behaviors. These weights are dynamically adjusted according to the historical trends of . Combining the results of periodic analysis and trend analysis, the weighted formula R = P(d)·Q(d) is used to combine periodicity and trend characteristics to predict future behavior patterns of passengers, optimize the evaluation of future activity time, and ensure the accuracy and practicality of the prediction.

[0070] S300, generating a similar behavior data set based on temporal behavior dependency features to identify key behavior patterns of civil aviation passengers and construct a group behavior pattern set.

[0071] In this embodiment, the temporal behavior dependency feature is used to cluster civil aviation passenger behaviors through data similarity, identify key behavior patterns, and construct a group behavior pattern set. The group behavior pattern set includes behavior clustering categories, key behavior identification results, and behavior pattern similarity analysis results.

[0072] In some embodiments, see Figure 4 , Figure 4 The flowchart of the steps for obtaining the group behavior pattern set provided in the embodiment of the present disclosure, step S300 may include S301 to S303, as follows:

[0073] S301, analyzing the time and behavior differences between data points in a key behavior time feature data set based on temporal behavior dependency features, and generating a similar behavior data set after grouping.

[0074] In this embodiment, based on the temporal behavior dependency features, timestamps and behavior labels in the key behavior time feature data set are extracted, the time and behavior differences between each data point in the key behavior time feature data set are analyzed, and preliminary grouping is performed according to the proximity of time and behavior to generate a similar behavior data set.

[0075] Exemplarily, time and behavior difference analysis, according to the formula:

[0076]

[0077] Calculate the comprehensive difference Δd between data points ij , where Δt ij =|t i -t j | represents the time difference, Δf ij =|f i -f j | represents the behavior frequency difference, τ is the time scaling parameter, φ is the behavior frequency scaling parameter, α and β are weight coefficients, γ and λ are the time decay coefficient and decay rate respectively.

[0078] For example, the execution process: First, calculate the time difference Δt ij and the behavior frequency difference Δf ij Then, the time and frequency are standardized by parameters τ and φ, and the time difference and frequency difference are compared on the same scale. Then, the weight coefficients α and β are used to adjust the influence of the time difference and behavior frequency difference in the total difference Δd. Finally, the exponential decay term is introduced. This item decreases as the time difference increases, thereby reducing the similarity of data points with long time intervals. The values ​​of the α, β, γ and λ coefficients can be adjusted using a data-driven approach by optimizing the silhouette coefficient of the clustering results to ensure the best data grouping effect.

[0079] S302: Acquire the start and end time points of the behavior based on the similar behavior data set, and generate a key behavior pattern set.

[0080] In this embodiment, based on similar behavior data sets, the common behavior patterns of data points in each group are identified, the start and end time points of the behavior are extracted, and the frequency of behavior and participation statistics are combined to mark the frequency of behavior occurrence and generate a key behavior pattern set.

[0081] For example, in the above process, a key behavior extraction algorithm K(t,f)=(t s ,t e ,n), where t s and t e Represent the start and end time points of the behavior, and n represents the number of times the behavior occurs. This algorithm analyzes the behavior timestamps of each group, identifies the commonality and frequency of the behavior patterns, and generates a detailed set of behavior patterns for each group by counting the participation of each behavior.

[0082] S303: construct a behavior pattern description for each group based on the key behavior pattern set to obtain a group behavior pattern set.

[0083] In this embodiment, based on the key behavior pattern set, the data points in each group, that is, the marked behavior data of each group, are integrated to construct a description of each group's behavior pattern, and the behavior pattern of each group is summarized and concluded to obtain a group behavior pattern set.

[0084] For example, using the inductive algorithm I(Y) = group behavior pattern description, where Y represents the data extracted from the key behavior pattern set, the algorithm analyzes and compares the behavior data of different groups to summarize the behavior characteristics and trends of each group. The key to this step is to describe and summarize the behavior patterns of each group in detail to provide a basis for future behavior prediction and resource optimization.

[0085] S400. Setting a real-time data stream interface based on the group behavior pattern set to obtain a dynamically updated passenger portrait.

[0086] In this embodiment, a real-time data stream interface and a group behavior pattern set are used to monitor new flight bookings and service evaluation events of civil aviation passengers, and the passenger portrait set is updated through real-time feedback to obtain a dynamically updated passenger portrait. The dynamically updated passenger portrait includes flight booking update records, service evaluation data, and real-time update content of the portrait to obtain the passenger's deep preference factors and flight preference association rules. The passenger's deep preference factor characteristics include preference change analysis records, influencing factor integration results, and deep factor identification results. The flight preference association rules include passenger purchase behavior patterns, pattern analysis results, and association rule confirmation results.

[0087] In some embodiments, see Figure 5 , Figure 5The flowchart of the acquisition steps of dynamically updating the passenger portrait provided in the embodiment of the present disclosure, step S400 may include S401 to S403, as follows:

[0088] S401. Setting a real-time data stream interface based on a group behavior pattern set to obtain new flight reservation and service evaluation events to generate a real-time behavior matching data set.

[0089] In this embodiment, a real-time data stream interface is set to capture new flight booking and service evaluation events, record the timestamp and key content of each event, match the real-time data with the group behavior pattern set, confirm the validity of the behavior pattern, and generate a real-time behavior matching data set.

[0090] Exemplarily, the timestamp and key content of each event are recorded, and each event e is processed, wherein the parameters included are the timestamp t and the key content c. The implementation steps include a data matching algorithm M(d,B), where d represents a real-time data point and B represents a group behavior pattern set. The algorithm confirms the validity of the behavior pattern by comparing and analyzing the time and content, and generates a real-time behavior matching data set. This process ensures that each new behavior data point can be compared with the existing pattern in real time, and behaviors that deviate from the norm can be identified in a timely manner for further analysis and response.

[0091] S402: Compare each service evaluation event with the existing passenger profile based on the real-time behavior matching data set to generate a passenger profile update data set.

[0092] In this embodiment, based on the real-time behavior matching dataset, content analysis is performed on each captured event to extract key features, including passenger ratings, feedback keywords, and booking details. These features are compared with existing passenger profiles to identify differences and new behavior trends, and existing passenger profile features are updated to generate a passenger profile update dataset.

[0093] For example, based on the real-time behavior matching dataset, content analysis is performed on each captured event to extract key features including passenger ratings, feedback keywords and booking details. An analysis function A(x) is set, where x represents the content of the event, and these contents are converted into feature vectors V(f1, f2, ..., f m ), each f i Represents a feature extracted from an event. By comparing with the existing passenger profile, using the difference analysis function D(V,P), where P represents the existing passenger profile feature set, new trends and significant differences in passenger behavior are identified, the existing passenger profile features are updated, and a passenger profile update data set is generated. This process not only updates the passenger's behavioral characteristics, but also enhances the sensitivity and response speed to changes in passenger behavior.

[0094] S403: Integrate all updated passenger portrait information based on the passenger portrait update data set to obtain a dynamically updated passenger portrait.

[0095] In this embodiment, new features and behavior patterns are integrated into the dynamic profile of the passenger to reflect the latest passenger behavior and feedback, thereby obtaining a dynamically updated passenger profile.

[0096] For example, by integrating the function I(P m ), where P n Indicates all updated passenger profile features, integrates new features and behavior patterns into the passenger's dynamic profile, reflects the latest passenger behavior and feedback, and obtains a dynamically updated passenger profile. The core of this step is to ensure the continuous updating and accuracy of the passenger profile. n ) function effectively integrates new data into the overall profile of passengers, ensuring that each profile reflects the passenger’s latest behavioral characteristics and feedback information, thereby providing more accurate services and personalized experiences.

[0097] S500: Analyze the attributes of the target flight based on the passenger portrait and generate a personalized service plan for civil aviation passengers.

[0098] In this embodiment, passenger portraits are used to conduct in-depth analysis of target flight attributes, optimize civil aviation passenger service plans, and generate personalized civil aviation passenger service plans. The personalized civil aviation passenger service plans include service plan optimization content and personalized service details.

[0099] In some embodiments, see Figure 6 , Figure 6 The flowchart of the steps for obtaining the personalized service plan for civil aviation passengers provided in the embodiment of the present disclosure, step S500 may include S501 to S503, as follows:

[0100] S501. After analyzing the attributes of the target flight based on the passenger portrait, the characteristics of each flight are matched with the passenger preferences to generate a flight attribute analysis data set.

[0101] In this embodiment, based on the flight preference association rules, the target flight attributes are analyzed, including flight duration, seat type, and service level. The target flight attributes are matched with the rules to determine the key passenger groups of the target flight. The characteristics of each flight are matched with passenger preferences to generate a flight attribute analysis data set.

[0102] For example, by applying the rule matching function M(a,R)={r∈R|a meets r}, where a represents the flight attribute and R represents the established flight preference association rule set, the flight characteristics that match the preferences of a specific passenger group are determined. This function compares and analyzes the characteristics of each flight (such as duration, seat type, and service level) with passenger preferences, matches the appropriate passenger group, and generates a flight attribute analysis data set. This data set highlights the correspondence between the key characteristics of each flight and the preferences of specific passengers, providing airlines with a basis for precision marketing and service configuration.

[0103] S502: Identify passengers' preferences for target flight attributes based on the flight attribute analysis data set, and generate a civil aviation passenger service optimization suggestion set.

[0104] In this embodiment, the passenger's preferences for target flight attributes, including preference for legroom or priority boarding service, are used to optimize flight services and generate a set of civil aviation passenger service optimization recommendations.

[0105] For example, using the preference analysis function P(b)=max(preference(b i ), where b represents the flight attribute set, b i It is a single attribute such as legroom or priority boarding. Optimize flight services based on preferences. This analysis evaluates the impact of each attribute on passenger satisfaction, identifies service areas that need to be optimized or enhanced, and generates a set of recommendations for optimizing civil aviation passenger services. The set of recommendations helps airlines adjust their service features to meet the specific needs of passengers, thereby improving passenger experience and satisfaction.

[0106] S503. Integrate flight services and passenger preferences based on the passenger service optimization suggestion set to obtain personalized service plans for civil aviation passengers.

[0107] In this embodiment, after integrating flight services and passenger preferences, service adjustment plans for all flights are formulated to ensure that each service matches the needs of civil aviation passengers and obtain personalized service plans for civil aviation passengers.

[0108] For example, when developing service adjustment plans for all flights, the feasibility, cost-effectiveness and passenger satisfaction improvement potential of each service proposal should be examined. Ensure that each service matches the needs of civil aviation passengers, so as to obtain a personalized service plan for civil aviation passengers. This plan collectively reflects how to better meet the personalized needs of passengers by adjusting existing services, thereby improving passenger loyalty and the market competitiveness of airlines.

[0109] Based on the above method, the embodiment of the present disclosure also provides a civil aviation passenger data profiling system 2000 corresponding to the above method, such as Figure 7 As shown, Figure 7A structural block diagram of a civil aviation passenger data profiling system provided in an embodiment of the present disclosure, the system includes a collection module 201, a prediction module 202, an identification module 203, an update module 204 and an application module 205.

[0110] The acquisition module 201 is used to obtain civil aviation passenger demand data and airport activity data, and form a passenger behavior and environmental data set. The prediction module 202 is used to extract the time characteristics of the key behaviors of civil aviation passengers based on the passenger behavior and environmental data set, and generate temporal behavior dependency features. The identification module 203 is used to generate a similar behavior data set based on the temporal behavior dependency features to identify the key behavior patterns of civil aviation passengers and construct a group behavior pattern set. The update module 204 is used to set a real-time data stream interface based on the group behavior pattern set to obtain a dynamically updated passenger portrait. The application module 205 is used to analyze the attributes of the target flight based on the passenger portrait and generate a personalized service plan for civil aviation passengers.

[0111] This system significantly improves the response speed to changes in passenger demand through the integration of real-time data streams and the updating of dynamic passenger portraits. It integrates real-time flight booking information and service evaluations to enable airlines to adjust services in real time to accurately match passengers' current needs. Deep preference analysis can reveal subtle changes in passenger choices, providing airlines with an effective tool for optimizing services and enhancing passenger satisfaction. By building flight preference association rules, airlines can provide more refined flight options based on passenger purchasing behavior, enhance the accuracy of market positioning, improve the personalization of services and operational flexibility, and help improve passenger loyalty and company profits.

[0112] Based on the same inventive concept as the above disclosed content, the present disclosure also provides an electronic device 3000. Figure 8 As shown, Figure 8 The electronic device 3000 of the embodiment of the present disclosure includes at least one processor 310 and at least one memory 320 electrically connected to each other. The memory 320 is electrically connected to the processor 310, wherein the memory 320 stores instructions executable by the at least one processor 310, and the instructions are executed by the at least one processor 310 so that the at least one processor 310 can execute the method described above.

[0113] It should be noted that the electrical connection between the above-mentioned units does not necessarily mean the connection between lines. An indirect connection method can be applied to the embodiments of the present disclosure as long as the purpose of the present disclosure is achieved.

[0114] Based on the same inventive concept, the present disclosure also provides a computer storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method described above is performed. The storage medium may include: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0115] Although the present disclosure has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure.

Claims

1. A civil aviation passenger data profiling method, characterized in that: The method comprises: Obtain civil aviation passenger demand data and airport activity data, and form a passenger behavior and environment data set; Extracting temporal characteristics of key behaviors of civil aviation passengers based on the passenger behavior and environment dataset, and generating temporal behavior dependency features; Generate a similar behavior data set based on the temporal behavior dependency features to identify key behavior patterns of civil aviation passengers and construct a group behavior pattern set; A real-time data stream interface is set based on the group behavior pattern set to obtain a dynamically updated passenger portrait.

2. The method according to claim 1, characterized in that: The acquisition of civil aviation passenger demand data and airport activity data and the formation of passenger behavior and environment data sets include: Based on the application programming interface, real-time acquisition of civil aviation passengers' flight selection information, ticket purchase time and airport activity data is generated, and an air travel data set is generated; Collecting current weather information and flight update status based on the flight travel data set, and generating an enhanced flight travel environment data set; Data cleaning and preprocessing are performed based on the enhanced air travel environment dataset to obtain a passenger behavior and environment dataset.

3. The method according to claim 1, characterized in that: The extracting of the temporal features of the key behaviors of civil aviation passengers based on the passenger behavior and environment data set and generating temporal behavior dependency features includes: Filtering data records with time tags based on the passenger behavior and environment dataset, and generating a time-series dataset; Acquire key behaviors of civil aviation passengers at different time points based on the time series data set, and generate a key behavior time feature data set; The passenger behavior periodicity and trend are analyzed based on the key behavior time feature data set to obtain the time series behavior dependency features.

4. The method according to claim 1, characterized in that: The generating of similar behavior data sets based on the temporal behavior dependency features to identify key behavior patterns of civil aviation passengers and constructing a group behavior pattern set includes: Analyzing the time and behavior differences between data points in the key behavior time feature data set based on the time series behavior dependency feature, and generating a similar behavior data set after grouping; Acquire the start and end time points of the behavior based on the similar behavior data set, and generate a key behavior pattern set; A behavior pattern description of each group is constructed based on the key behavior pattern set to obtain a group behavior pattern set.

5. The method according to claim 4, characterized in that The method of analyzing the time and behavior differences of data points based on the time series behavior dependency feature and generating a similar behavior data set includes: the time and behavior difference analysis formula, Calculate the comprehensive difference Δd between data points ij , where Δt ij =|t i -t j | represents the time difference, Δf ij =|f i -f j | represents the behavior frequency difference, τ is the time scaling parameter, φ is the behavior frequency scaling parameter, α and β are weight coefficients, γ and λ are the time decay coefficient and decay rate respectively.

6. The method according to claim 1, characterized in that The setting of a real-time data stream interface based on the group behavior pattern set to obtain a dynamically updated passenger portrait comprises: Setting a real-time data stream interface based on the group behavior pattern set to obtain new flight reservation and service evaluation events to generate a real-time behavior matching data set; Comparing each service evaluation event with an existing passenger profile based on the real-time behavior matching data set to generate a passenger profile update data set; All updated passenger portrait information is integrated based on the passenger portrait update data set to obtain a dynamically updated passenger portrait.

7. The method according to claim 1, characterized in that The analyzing the attributes of the target flight based on the passenger portrait to generate a personalized service plan for civil aviation passengers includes: After analyzing the attributes of the target flight based on the passenger portrait, the characteristics of each flight are matched with the passenger preferences to generate a flight attribute analysis data set; Identifying passengers' preferences for target flight attributes based on the flight attribute analysis data set, and generating a set of civil aviation passenger service optimization suggestions; Based on the passenger service optimization suggestion set, flight services and passenger preferences are integrated to obtain a personalized service plan for civil aviation passengers.

8. A civil aviation passenger data profiling system, characterized in that: The system comprises: The collection module is used to obtain civil aviation passenger demand data and airport activity data and form a passenger behavior and environment data set; A prediction module, used to extract the time characteristics of key behaviors of civil aviation passengers based on the passenger behavior and environment data set, and generate time series behavior dependency features; An identification module, used to generate a similar behavior data set based on the temporal behavior dependency features to identify key behavior patterns of civil aviation passengers and construct a group behavior pattern set; An updating module is used to set a real-time data stream interface based on the group behavior pattern set to obtain a dynamically updated passenger portrait.

9. An electronic device, characterized in that: The electronic device comprises: Memory for storing computer programs; A processor, used to implement the civil aviation passenger data profiling method as described in any one of claims 1 to 7 when executing the computer program.

10. A computer storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the civil aviation passenger data profiling method as claimed in any one of claims 1 to 7.

Images