A flight travel recommendation system and method

Abstract

The application discloses a kind of flight travel recommendation system and method, comprising: obtaining the travel demand information of user;According to the travel demand information of user, obtain the candidate flight set containing several candidate flights, based on the geographical position of departure place and the airport corresponding to each candidate flight, at least one kind of feasible potential travel mode is identified and determined;Collect and fuse the dynamic influence parameter related to each potential travel mode, special auxiliary data and the static geographic information from departure place to airport, to evaluate the potential travel mode corresponding to each candidate flight, obtain the evaluation result of each potential travel mode;The comprehensive recommendation value of each candidate flight is generated in combination with the flight attribute data of each candidate flight and the evaluation result, and the flight recommendation scheme is output according to the comprehensive recommendation value.The scheme recommended by the application can more accurately fit the real demand and value orientation of user.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of traffic travel, and particularly relates to a flight travel recommendation system and method. BACKGROUND

[0002] With the popularity of air travel and the development of Internet technology, flight query and booking services have become an important part of public travel planning. At present, the flight query systems or platforms on the market mainly rely on traditional lists or tables to show users the basic information such as flight schedules, ticket prices and cabin classes provided by ticket vendors. Users usually need to manually compare the advantages and disadvantages of different flights in terms of price, time, transfer times, etc. on the basis of these information, combined with personal experience, to make travel decisions.

[0003] However, the prior art solution has the following disadvantages in actual application: the information is scattered in different platforms, and the user needs to repeatedly switch to obtain flight, punctuality rate, weather and other data, which is cumbersome to operate; the interaction mode is single, and the list form is mainly used, lacking visual presentation and intelligent recommendation based on user preferences and real-time data; more importantly, the existing solution only focuses on the "airport to airport" flight segment, and does not include the ground connection mode from the actual departure location to the airport in the overall evaluation, resulting in an incomplete and inaccurate recommended travel plan. SUMMARY

[0004] To solve the technical problems in the background art, the present application proposes a flight travel recommendation system and method.

[0005] The flight travel recommendation method proposed by the present application comprises:

[0006] S1, obtaining travel demand information of a user, the travel demand information comprising a departure location, a destination and a travel date;

[0007] S2, obtaining a candidate flight set comprising a plurality of candidate flights according to the user travel demand information, identifying and determining at least one feasible potential travel mode based on the geographical position of the departure location and the airport corresponding to each candidate flight;

[0008] S3, collecting and fusing dynamic influence parameters, special auxiliary data related to each potential travel mode, and static geographical information from the departure location to the airport, to evaluate the potential travel mode corresponding to each candidate flight, and obtain the evaluation result of each potential travel mode;

[0009] S4, generating a comprehensive recommendation value of each candidate flight in combination with the flight attribute data of each candidate flight and the evaluation result, and outputting a flight recommendation plan according to the comprehensive recommendation value.

[0010] Preferably, in S1, the obtaining of the travel demand information of the user specifically comprises: receiving a geographic point selection operation of the user on a departure location and a destination location through a map interactive interface, and generating initial travel demand information containing the departure location and the destination location; receiving a travel date input by the user on the map interactive interface, and merging the initial travel demand information to form complete travel demand information.

[0011] Preferably, S2 specifically comprises: performing format standardization processing on the travel demand information to generate structured request data; calling a ticket service interface based on the structured request data to obtain a corresponding candidate flight set; calling a map service interface or a traffic planning service in combination with user departure location information for a geographic location of a departure airport corresponding to each candidate flight in the candidate flight set to obtain multiple potential travel modes from the departure location to the airport; the potential travel modes include but are not limited to self-driving, online car hailing, taxi, bus, and subway.

[0012] Preferably, S3 specifically comprises: for each potential travel mode, collecting and fusing dynamic influence parameters, static geographic information, and special auxiliary data to form a multi-dimensional feature vector of the potential travel mode, wherein the dynamic influence parameters are current and predicted traffic information obtained by calling a real-time traffic data interface and a weather data interface, the static geographic information is path information from the departure location to the airport obtained by a map service interface, and the special auxiliary data is additional parameters obtained according to the type of the travel mode; according to a preset priority configuration, evaluating feature components representing efficiency, cost, convenience, and reliability dimensions in the multi-dimensional feature vector; based on an importance relationship defined by the priority configuration, comprehensively evaluating the evaluation results of each dimension to generate a final evaluation result of each potential travel mode.

[0013] Preferably, the preset priority configuration can be dynamically adjusted according to the travel preference data of the user, specifically comprising: obtaining the travel preference data of the user; analyzing the travel preference data to extract preference parameters for quantitatively representing the degree of attention of the user on efficiency, cost, convenience, and reliability dimensions; based on the preference parameters, generating a group of correction instructions for adjusting the importance relationship of each dimension; and updating the importance relationship of each dimension defined in the priority configuration according to the correction instructions.

[0014] Preferably, the travel preference data is derived from at least one of the following ways: configuration information actively submitted by the user through a system interface or default configuration information generated by analyzing historical orders and query records of the user.

[0015] Preferably, S4 specifically comprises:

[0016] S41, for each candidate flight in the candidate flight set, obtain its flight attribute data and associated weather data, wherein the flight attribute data at least includes ticket price, total journey time, number of transfers, historical punctuality rate and seat availability, and the associated weather data at least includes weather forecast information of the departure airport and the destination airport within a preset time period before and after the scheduled takeoff time of the flight;

[0017] S42, based on the obtained flight attribute data and associated weather data, comprehensively considering the economy, reliability and experience dimensions, the flight attribute comprehensive score of the candidate flight is calculated;

[0018] S43, obtain the evaluation result of all potential travel modes corresponding to the candidate flight;

[0019] S44, overall analysis is performed on the flight attribute comprehensive score and the evaluation result, and the best matching relationship between the flight and the ground connection mode before flight is judged according to the preset decision logic, and a comprehensive recommendation value representing the overall advantages and disadvantages of the flight and its connected travel mode is generated accordingly;

[0020] S45, according to the comprehensive recommendation value of all candidate flights, the top ranked scheme is selected and added with a highlight display mark and output as a flight recommendation scheme.

[0021] Preferably, the calculation of the flight attribute comprehensive score can be dynamically adjusted according to the personal flight preference parameters of the user, specifically:

[0022] Obtain the personal flight preference parameters of the user; analyze the personal flight preference parameters to extract personalized tendency information representing the user's preferences in the economy, reliability and experience dimensions; adjust the comprehensive consideration of the flight attribute data and associated weather data in the economy, reliability and experience dimensions according to the personalized tendency information; and calculate the flight attribute comprehensive score that integrates the user's personalized tendency based on the adjusted comprehensive consideration.

[0023] Preferably, it further comprises S5, which is specifically: obtaining ticketing platform booking interface information corresponding to the flight recommendation scheme; generating and displaying a user interface containing an interactive booking control; in response to the triggering operation of the interactive booking control, calling the corresponding ticketing platform booking interface and jumping to the ticket purchase page.

[0024] The application also provides a flight travel recommendation system, comprising:

[0025] A demand obtaining interaction module is used to receive the departure place, destination and travel date input by the user through an interactive map;

[0026] a flight connection scheme generation module configured to obtain a candidate flight set according to the demand and identify at least one potential travel mode for each candidate flight to a departure airport corresponding to the candidate flight;

[0027] a connection scheme evaluation module configured to, for each potential travel mode, fuse multi-source data to form feature information, perform multi-dimensional evaluation based on a preset priority configuration and fuse the results, and output an evaluation result of each potential travel mode;

[0028] a comprehensive recommendation generation module configured to calculate a comprehensive score of each flight attribute based on flight attribute data, associated meteorological data and user preference data, analyze and calculate based on a preset decision logic in combination with the evaluation result, generate a comprehensive recommendation value of each flight, and output a flight recommendation scheme;

[0029] a display output module configured to visually display the flight recommendation scheme and provide a jump interface to a ticketing platform.

[0030] In the present application, by collecting, fusing and calculating data dispersed in multiple platforms, and through intelligent sorting and visual presentation, users can quickly choose from a small number of selected and high-confidence recommendation schemes in a single interface, simplifying user operations and greatly shortening decision-making time. Through map interaction design, users can intuitively select the departure location and destination on the map, and the system renders the route in real time, changing the abstract interaction mode of traditional lists, reducing the operation difficulty, and providing a more intuitive user experience. By creatively including various potential travel modes (such as self-driving and subway) from the actual departure location of the user to the airport in the evaluation system, and dynamically injecting user preference-related data into the core evaluation process, the recommended scheme can more accurately meet the real needs and value orientation of the user, providing a customized service experience for "thousands of people with thousands of faces". BRIEF DESCRIPTION OF DRAWINGS

[0031] Figure 1 A flowchart of a flight travel recommendation method according to the present application. DETAILED DESCRIPTION

[0032] REFERENCE Figure 1 The flight travel recommendation method according to the present application includes the following steps:

[0033] S1, obtain the travel demand information of the user, the travel demand information including the departure location, the destination and the travel date.

[0034] In this step, the system presents an interactive map to the user, who specifies the origin and destination by clicking, long-pressing, or dragging on the map. The system captures these two geographic coordinate points (or regions) and converts them into available location identifiers (such as city names or airport codes), generating initial trip demand information containing the origin and destination. This greatly improves the intuitiveness and convenience of the operation, especially for users who are not familiar with airport names or want to plan their trip from a macro geographic perspective.

[0035] After determining the geographic location of the origin, the user usually needs to input or select the travel date (one-way date or round-trip date) in the map interface or associated controls. The system receives this date information and combines it with the initial trip demand information generated in the previous step to form a complete trip demand information that can be processed in subsequent steps.

[0036] By using intuitive spatial point selection instead of abstract code input, the system reduces the user's threshold for use while ensuring the accuracy and machine readability of the obtained "origin, destination, and travel date" information, which helps improve user experience and decision-making efficiency.

[0037] S2, according to the user's trip demand information, obtain a candidate flight set containing several candidate flights, and based on the geographic location of the origin and the airport corresponding to each candidate flight, identify and determine at least one feasible potential travel mode.

[0038] The specific process is as follows:

[0039] First, demand standardization and structuring: the system performs format standardization on the complete trip demand information obtained in step S1. This includes standardizing the geographic location code, date format, and possible additional preference filtering conditions, and converting them into an internally recognizable structured request data.

[0040] Next, flight information acquisition: the system calls one or more ticketing interfaces based on the above structured request data. These interfaces can access publicly available airline direct sales systems, global distribution systems, or online travel agency inventories. The interface returns a candidate flight set that meets the user's origin, destination, and date, with each flight entry containing at least flight number, departure and arrival airport, and time.

[0041] Finally, generate flight-associated pre-flight ground transfer solutions: for each candidate flight in the candidate flight set, the system performs the following sub-steps to realize the bundling analysis of flights and pre-flight ground transportation, and the analysis process is as follows:

[0042] (1) Positioning analysis: according to the departure airport code of the candidate flight, obtain its accurate geographic location.

[0043] (2) Connection mode discovery: combined with the specific departure information provided by the user, call the map service interface or professional traffic planning service. Based on the spatial relationship between the two points, the real-time traffic network data, the system automatically calculates and obtains multiple potential travel modes from the user's departure place to the specific departure airport.

[0044] (3) Mode enumeration: these potential travel modes are a collection of multiple transportation modes, typically including but not limited to: self-driving, online car-hailing, taxi, bus, subway. The system aims to exhaust all feasible connection options at this stage to provide a basis for subsequent quantitative evaluation.

[0045] S3, collect and fuse dynamic influence parameters, special auxiliary data related to each potential travel mode, and static geographic information from the departure place to the airport to evaluate the potential travel modes corresponding to each candidate flight, and obtain the evaluation results of each potential travel mode.

[0046] The specific process of this step includes the following steps:

[0047] Step one, build a multi-dimensional feature vector: for each potential travel mode identified (such as self-driving, subway), the system performs multi-source data fusion:

[0048] (1) Collect dynamic influence parameters: obtain current and predicted traffic information (including congestion level, estimated travel time) by calling real-time traffic data interfaces and weather data interfaces on the web, which integrates weather influence factors and time characteristics (such as morning and evening peak hours);

[0049] Collect static geographic information: obtain the path distance from the departure place to the airport, the geographic location information of the key nodes (such as highway entrances, transportation hubs) and public transportation stations (bus stops, subway stations) through the map service interface on the web;

[0050] Collect special auxiliary data: obtain additional parameters according to the type of travel mode, which is different for different travel modes, such as: if it is a self-driving mode: call the parking lot data interface on the web to obtain the real-time vacancy number of parking lots around the target airport, parking fees, and the distance from the parking lot to the terminal; The collection of this additional parameter can help users judge whether it is convenient to park, the related parking fees, and the possible time needed to reach the terminal from the parking point when using self-driving mode, so as to help users judge whether to use this mode to go to the airport; If it is a bus or subway mode: calculate the walking distance and estimated walking time from the departure place to the nearest bus stop or subway station, and obtain the real-time arrival interval and operation schedule of the line, the collection of this additional parameter can help users judge the time needed to use the subway or bus to go to the airport.

[0051] (2) Align all collected data with the current assessed origin-airport route and the user's planned travel time window as a benchmark. For example, map weather forecast data to the geographic area of ​​the route and the planned travel time to ensure that all data reflects the same spatiotemporal scenario.

[0052] (3) Extract quantitative features from real-time / predictive data: For example, extract “estimated travel time (minutes)” and “congestion delay index (0-1)” from traffic data; extract “weather impact coefficient” (mapped to a numerical value based on precipitation, visibility, etc.) from weather data.

[0053] Extract invariant or slowly changing features from geographic data: for example, "total path distance (km)," "number of transfers required," and "walking distance from the origin to the subway station (m)."

[0054] Extract specific features based on the mode of travel: for example, extract "parking fee (yuan)" for "driving" mode; extract "waiting time for the next bus (minutes)" for "subway" mode; and extract "current dynamic premium rate" for "ride-hailing" mode.

[0055] (4) Data cleaning and normalization

[0056] First, handle missing values ​​and outliers (such as unreasonable negative time or extremely high cost).

[0057] Next, feature values ​​with different dimensions and ranges are mapped to a unified numerical interval (such as [0, 1] or conforming to a standard normal distribution) through methods such as linear scaling (e.g., Min-Max) and Z-score normalization. This is a key step in achieving comparability of features with different dimensions and enabling subsequent rule-based judgments. For example, both "cost (0-200 yuan)" and "time (0-120 minutes)" are normalized to the interval [0,1].

[0058] (5) Based on the preset evaluation dimensions (efficiency, cost, convenience, reliability), select the key features that best represent the dimension from all extracted and processed features. For example, features of the "efficiency" dimension may include "normalized estimated time" and "congestion delay index".

[0059] Then, the selected feature values ​​are arranged sequentially according to a fixed dimensional order and assembled into a one-dimensional array, i.e., a multi-dimensional feature vector.

[0060] The above data was cleaned, normalized, and merged to form a multidimensional feature vector representing the full-scale status of this potential mode of transportation.

[0061] Step Two: Quantitative Evaluation Based on Priority Configuration

[0062] The system initializes a default priority configuration, which explicitly sets the relative importance of four core dimensions—efficiency (e.g., time), cost (e.g., expenses), convenience (e.g., walking distance), and reliability (e.g., delay risk)—in the overall assessment in the form of rules. For example, the default configuration might assign a higher base weight to "efficiency" and "reliability," while setting "cost" and "convenience" to medium.

[0063] Specifically, the system has a built-in hierarchical rule base, which contains the following two core rule categories:

[0064] (1) Dimensional filtering rules: Define the basic criteria for "qualified" and "unqualified" for each evaluation dimension (efficiency, cost, convenience, reliability). Each rule acts independently on a specific component of the multidimensional feature vector.

[0065] For example:

[0066] In the efficiency dimension, if the estimated travel time is greater than the baseline time threshold, it is marked as "inefficiency unacceptable"; if the travel time fluctuation range is greater than the acceptable fluctuation threshold, it is marked as "low time reliability".

[0067] In the cost dimension, if the estimated total cost exceeds the budget threshold, it is marked as "cost overrun".

[0068] In the reliability dimension, if the current weather warning level is greater than or equal to the severe weather threshold, it is marked as "high-risk weather"; if the current traffic congestion index is greater than the severe congestion threshold, it is marked as "high delay risk".

[0069] (2) Comprehensive decision-making rules: These rules define how to make a final evaluation based on the results of dimensional filtering. These rules clarify the priority relationships between different dimensions.

[0070] Rule A (Safety / Reliability Veto): If there is "High-Risk Weather" or "High Delay Risk", the final evaluation result will be "Not Recommended".

[0071] Rule B (Cost and Efficiency Trade-off): If it is marked as "Cost Exceeds Limits" but not "Inefficiency Fails", the final evaluation result is "Average" (unless the user explicitly indicates a preferred cost).

[0072] Rule C (Efficiency First): If marked as "Inefficiency Unsatisfactory" and Rule A is not triggered, the final evaluation result is "Not Recommended".

[0073] Rule D (Convenience Supplement): If there are no negative markers and the number of transfers is 0, the final evaluation result is "Strongly Recommended";

[0074] Rule E (default pass): If none of the above rules are triggered, the final evaluation result is "recommended".

[0075] In this embodiment, user preference data directly influences the execution logic of the rule base, enabling personalized evaluation. The system obtains user preference data through two methods: first, an explicit method, which directly receives configuration information submitted by the user in the map interaction interface (such as setting "lowest cost" as the priority option), which is more suitable for users logging in for the first time; second, an implicit method, which analyzes the user's historical orders and query records to intelligently generate default configurations representing their long-term behavioral tendencies (such as frequently selecting early morning flights to infer that the user is a "time-sensitive" user), which is more suitable for users with multiple flight experiences and multiple uses of this system. This design also enables the system to learn and adapt, and can automatically update the default configuration information.

[0076] It is worth noting that the aforementioned "user historical orders and query records" are sourced with user authorization.

[0077] This step is based on the aforementioned dimensional filtering rules and comprehensive decision-making rules. The specific operation process is as follows:

[0078] (1) The system generates modification instructions to enable or disable some comprehensive adjudication rules based on the parsed user preference parameters.

[0079] For example, when the system determines that a user is "extremely cost-sensitive", rule C (efficiency first) is disabled, and the conclusion of rule B (cost-efficiency trade-off) is significantly strengthened. Even if the efficiency is not up to standard, as long as the cost is extremely low, the user may still receive a "recommended" rating.

[0080] (2) Dynamically adjust rule thresholds: Various thresholds in the dimension filtering rules (such as “baseline time threshold” and “budget threshold”) are set in a personalized manner based on user preference data.

[0081] For example, for "time-sensitive" users, the system will automatically generate a correction instruction—lowering the "baseline time threshold" for the efficiency dimension, making it easier for the same travel time to trigger the "inefficiency failure" flag, thus making them more likely to be screened out in subsequent decisions.

[0082] (3) Adjusting the order of rule execution: The order of application of the comprehensive adjudication rules can be adjusted according to the preferences in the amendment instructions. For example, for "convenience-first" users, the execution order of adjudication rules on convenience (such as rule D) can be advanced.

[0083] The assessment process for each potential mode of transportation to be evaluated in S3 is explained below, combining the above two steps:

[0084] ①Feature extraction and input: The multi-dimensional feature vector formed by fusion is converted into "fact" data that can be recognized by the rule engine.

[0085] ② Execute dimension filtering rules: The rule engine traverses all dimension filtering rules, matches the input facts, and outputs a set of "tags" (such as "cost exceeded" or "high delay risk").

[0086] ③ Load personalized rule set: Based on the current user's preference data, load a comprehensive adjudication rule set that matches the user's preferences and has been adjusted in terms of status and parameters from the rule base.

[0087] ④ Execute comprehensive judgment: The rule engine reasons on the "tag" set generated in step ② based on the loaded rule set. Rules are triggered in sequence until a definite final evaluation result is generated (such as "strongly recommended", "recommended", "neutral", "not recommended").

[0088] ⑤ Result Quantification Mapping (Optional): To facilitate subsequent comprehensive calculation with flight ratings, the system can internally map the qualitative evaluation results (such as "Strongly Recommended") output by the rules to a score within a standardized numerical range.

[0089] The core of this evaluation process lies in transforming "priority configuration" into a configurable and adjustable rule system. By acquiring user preference data, the activation status, judgment thresholds, and execution logic of the rules within this system are dynamically modified. This allows the same rule engine to execute drastically different evaluation strategies for different users, achieving highly transparent and interpretable personalized evaluations that are entirely based on business logic and do not rely on numerical weights. This ensures that recommendation results better match users' actual needs and values, providing a customized service experience tailored to each individual.

[0090] S4. Combine the flight attribute data of each candidate flight with the evaluation results to generate a comprehensive recommendation value for each candidate flight, and output a flight recommendation scheme based on the comprehensive recommendation value.

[0091] The specific process for this step is as follows:

[0092] First, the calculation of the comprehensive score of flight attributes: For each candidate flight, the system obtains its flight attribute data in real time (such as ticket price, total travel time, number of transfers, historical on-time rate, seat availability) and related meteorological data (weather forecasts for the take-off and landing airports before and after the scheduled flight time).

[0093] Based on the above data, the system performs quantitative calculations on three preset dimensions: economy (mainly related to ticket price and total duration), reliability (mainly related to on-time performance, number of transfers and weather impact), and experience (mainly related to service evaluation and seat availability), generating preliminary sub-scores for each dimension.

[0094] Simultaneously, the system automatically retrieves and analyzes the user's personal flight preference parameters (such as "price sensitive," "extremely averse to layovers," and "preference for specific airlines") from their historical flight records. For first-time flyers, these parameters can be manually entered through the interactive interface. These parameters are not simply filtered but are used to dynamically adjust the way the three dimensions are considered in the final overall assessment. For example, for "extremely price-sensitive" users, the system will significantly increase the weight of the economy dimension in the overall assessment, and even tolerate a slight decrease in reliability to some extent. Ultimately, a personalized flight attribute comprehensive score is calculated for each candidate flight, integrating objective data and the user's subjective preferences.

[0095] Next, a comprehensive recommendation value is generated: For each candidate flight, the generated personalized flight attribute comprehensive score is analyzed in conjunction with the evaluation results of all potential ground transportation modes associated with the flight's departure airport. The system performs in-depth analysis based on a preset decision logic. This decision logic defines the complex matching and mutual exclusion relationships between flight attributes and ground transportation modes. For example:

[0096] (1) Complementary reinforcement logic: If a flight has a high score, but the only feasible ground connection method is rated as "high delay risk", the decision-making logic may determine that the overall plan has shortcomings, thereby lowering its comprehensive recommendation value.

[0097] (2) Bottleneck Arbitration Logic: If a flight has a medium rating, but there is a connection method that is rated as "efficient and low cost" (such as direct subway access), the decision logic may determine that "the advantages of the ground segment significantly make up for the shortcomings of the air segment", thereby increasing its overall recommendation value.

[0098] (3) Risk avoidance logic: For early morning flights, the decision-making logic will more rigorously examine the "reliability" evaluation of the connection method. An unreliable connection method will lead to a significant reduction in the overall recommendation value of the early morning flight.

[0099] The above decision-making logic can be designed to output a comprehensive recommendation value that represents the overall advantages and disadvantages of the "flight + connection" combination. This value quantifies the expected experience of the complete travel plan from the user's actual departure point to their final destination.

[0100] Finally, the system sorts the comprehensive recommendation values ​​calculated for all candidate flights and automatically selects the top-ranked options as the optimal solution set. These options are highlighted with labels such as "Smart First Recommendation" and "Best Connection" and are then output to the user as the final flight recommendation.

[0101] This invention effectively avoids the decision-making pitfalls of "flights being on time but missed" or "flights being cheap but connections being expensive and cumbersome" by incorporating the reliability and time cost of pre-flight ground connections into the overall evaluation, ensuring that the recommended "door-to-door" solution is more realistic and has overall superiority.

[0102] S5. Obtain the ticketing platform booking interface information corresponding to the flight recommendation scheme; generate and display a user interface containing interactive booking controls; in response to the trigger operation of the interactive booking controls, call the corresponding ticketing platform booking interface and jump to the ticket purchase page.

[0103] The specific process for this step is as follows:

[0104] Once the system generates and filters the final flight recommendations according to step S4, it immediately parses and associates each recommendation with its corresponding ticketing platform booking interface information. This information is not a simple webpage link, but a structured calling credential, typically including: the target ticketing platform's application programming interface address, a session identifier or price code uniquely identifying the query or cabin class price on the target platform, and necessary authentication parameters (such as encrypted partner tokens). This information has been pre-extracted and encapsulated from the ticketing interface's metadata or response during the data aggregation phase (corresponding to the system's data aggregation module), and is bound to the flight data as supplementary information when generating the recommendation.

[0105] Meanwhile, during the system output process, the interface rendering engine dynamically generates and embeds interactive booking controls (e.g., the "Book Now" or "View Details" buttons at the bottom of each recommended plan card). The generation logic of these controls is as follows: ① State binding: Each control is internally and logically strongly associated with the booking interface information of the ticketing platform corresponding to its recommended plan; ② Context awareness: The visual style of the controls (such as color and text) may be dynamically adjusted according to the attributes of the recommended plan (such as whether it is "Smart Recommendation") or the user's membership status to improve the guidance effect.

[0106] Finally, the system uses front-end interaction logic to monitor user actions (such as clicks and touches) on the aforementioned "interactive booking control." Once triggered, the system executes a secure call process. It extracts the interface information bound to the control and organizes it into an interface call request that conforms to the target ticketing platform's specifications. Crucially, this request passes an identifier containing complete context information such as specific flight selection, cabin class, and price to the target platform, ensuring that the user sees a booking page completely consistent with the recommended plan, rather than a blank page requiring a new search. After a successful call, the system guides the user to the corresponding ticketing page on the target ticketing platform based on the response.

[0107] The present invention also provides a flight travel recommendation system, including a demand acquisition and interaction module, a flight connection plan generation module, a connection plan evaluation module, a comprehensive recommendation generation module, and a display and output module.

[0108] The demand acquisition interaction module includes a map interaction unit, a geographic point capture unit, and a structured encapsulation unit. The map interaction unit is responsible for loading and rendering a map interface with geographic information visualization capabilities and providing basic interactive functions such as zooming and dragging. The geographic point capture unit listens for and responds to user point selection, drawing, or search operations on the map interaction interface, parsing user actions into precise geographic location coordinates. The structured encapsulation unit receives location information from the interaction unit and parameters such as the travel date entered by the user, integrates, verifies, and encapsulates them into a machine-readable structured travel demand object.

[0109] The flight connection scheme generation module has an interface scheduling unit, a data parsing and processing unit, and a connection scheme identification unit. The interface scheduling unit is used to coordinate and call external ticketing data interfaces according to structured travel needs, and request and receive the raw data of the candidate flight set. The data parsing and processing unit is used to clean and parse the acquired raw flight data, extract key attributes (such as flight number, departure and arrival airports, and time), and convert them into an internal unified data format. The connection scheme identification unit is used to automatically discover and list all feasible ground transportation connection methods for each candidate flight's departure airport, combined with the user's actual departure coordinates, by calling map or transportation planning service interfaces, forming an initial association pair between flights and connection methods.

[0110] The connection scheme evaluation module comprises a multi-source data fusion unit, a feature extraction unit, an evaluation unit, and a personalized rule adjustment unit. The multi-source data fusion unit collects real-time traffic conditions, static route information, and mode-specific parameters in parallel for each discovered potential travel mode, performing time and space alignment and fusion processing. The feature extraction unit extracts quantitative features reflecting efficiency, cost, convenience, and reliability from the fused data and constructs them into standardized multi-dimensional feature vectors. The evaluation unit embeds a configurable rule engine that loads preset priority configurations (represented by a business rule set), uses the feature vectors as input facts, performs rule reasoning, and outputs qualitative evaluation results for each travel mode. The personalized rule adjustment unit dynamically adjusts the activation status, threshold parameters, or execution priority of relevant rules in the rule engine based on the acquired user travel preference data, achieving personalized adaptation of the evaluation criteria.

[0111] The comprehensive recommendation generation module comprises a multi-dimensional flight scoring unit, a collaborative analysis unit, a comprehensive recommendation value calculation unit, and a scheme generation unit. The multi-dimensional flight scoring unit acquires flight attribute data and associated meteorological data for each candidate flight, and, considering user preferences, quantitatively scores them across multiple dimensions such as economy, reliability, and user experience, ultimately merging them into a personalized comprehensive flight attribute score. The collaborative analysis unit receives the comprehensive flight attribute score and the corresponding ground connection scheme evaluation result set. This unit incorporates pre-set collaborative decision-making logic (such as complementary reinforcement, bottleneck arbitration, and risk avoidance) to perform integrated analysis of the "flight-connection" combination, evaluating its overall merits. The comprehensive recommendation value calculation unit calculates a unified comprehensive recommendation value for each candidate flight (and its associated best or typical connection scheme) based on the results of the collaborative decision-making analysis, and sorts all candidate schemes in descending order according to this value, forming a ranked list. The scheme generation unit selects the top-ranked schemes from the ranked list, adds recommendation tags to them, and assembles them into the final flight recommendation scheme list.

[0112] The display output module includes a visualization rendering unit, an interface binding unit, and a response and redirection unit. The visualization rendering unit is used to visualize the final flight recommendation list in a user-friendly format (such as cards or lists), highlighting recommendation icons and key information. The interface binding unit is used to dynamically generate interactive controls such as "Book" or "View Details" for each recommendation and securely bind these controls to the specific booking interface information of the corresponding ticketing platform. The response and redirection unit is used to listen for user trigger events on the interactive controls. Once triggered, it extracts and calls the bound ticketing interface, carrying complete context information (such as flight selection and price code), and seamlessly guides the user to the corresponding ticketing page of the partner ticketing platform.

[0113] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A method for recommending flight travel, characterized in that, include: S1. Obtain the user's travel demand information, which includes the departure point, destination, and travel date; S2. Obtain a set of candidate flights containing several candidate flights based on user travel demand information, and identify and determine at least one feasible potential travel mode based on the geographical location of the departure point and the airport corresponding to each candidate flight. S3. Collect and integrate dynamic impact parameters, specific ancillary data, and static geographic information from departure point to airport related to each potential travel mode to evaluate the potential travel modes corresponding to each candidate flight and obtain the evaluation results of each potential travel mode. S4. Combine the flight attribute data of each candidate flight with the evaluation results to generate a comprehensive recommendation value for each candidate flight, and output a flight recommendation scheme based on the comprehensive recommendation value; S2 specifically involves: standardizing the format of travel demand information to generate structured request data; based on the structured request data, calling the ticketing interface to obtain the corresponding candidate flight set; and, based on the geographical location of the departure airport corresponding to each candidate flight in the candidate flight set, combining the user's departure location information, calling the map service interface or traffic planning service to obtain multiple potential travel modes from the departure location to the airport; the potential travel modes include, but are not limited to: driving, ride-hailing, taxi, bus, and subway. S3 specifically involves: for each potential travel mode, collecting and fusing dynamic impact parameters, static geographic information, and specific ancillary data to form a multi-dimensional feature vector for that potential travel mode. The dynamic impact parameters are current and predicted road condition information obtained by calling real-time traffic data interfaces and weather data interfaces; the static geographic information is path information from the departure point to the airport obtained through a map service interface; and the specific ancillary data are additional parameters obtained based on the travel mode type. Based on a preset priority configuration, the feature components representing efficiency, cost, convenience, and reliability dimensions in the multi-dimensional feature vector are evaluated. Based on the importance relationships defined by the priority configuration, and by combining the evaluation results of various dimensions, a final evaluation result is generated for each potential travel mode.

2. The flight travel recommendation method according to claim 1, characterized in that, In S1, obtaining the user's travel demand information specifically involves: receiving the user's geographical selection of the departure point and destination through the map interaction interface, generating initial travel demand information containing the departure point and destination; receiving the travel date entered by the user on the map interaction interface, merging it with the initial travel demand information to form complete travel demand information.

3. The flight travel recommendation method according to claim 1, characterized in that, The preset priority configuration can be dynamically adjusted according to the user's travel preference data. Specifically, it involves: obtaining the user's travel preference data; parsing the travel preference data; and extracting preference parameters used to quantify the user's level of attention to efficiency, cost, convenience, and reliability. Based on the preference parameters, a set of correction instructions are generated to adjust the importance relationships of each dimension; according to the correction instructions, the importance relationships of each dimension defined in the priority configuration are updated.

4. The flight travel recommendation method according to claim 3, characterized in that, The travel preference data comes from at least one of the following sources: configuration information actively submitted by the user through the system interface or default configuration information generated after analyzing the user's historical orders and query records.

5. The flight travel recommendation method according to claim 1, characterized in that, Specifically, S4 is: S41. For each candidate flight in the candidate flight set, obtain its flight attribute data and associated meteorological data. The flight attribute data includes at least ticket price, total travel time, number of transfers, historical on-time rate and seat availability. The associated meteorological data includes at least weather forecast information of the departure airport and the destination airport within a preset time period before and after the flight's scheduled departure time. S42. Based on the acquired flight attribute data and related meteorological data, and taking into account the dimensions of economy, reliability and experience, the comprehensive score of the flight attributes of the candidate flight is calculated. S43. Obtain the evaluation results of all potential travel modes corresponding to the candidate flight; S44. Perform an overall analysis of the comprehensive score of the flight attributes and the evaluation results, determine the best matching relationship between the flight and the ground connection method before the flight based on the preset decision logic, and generate a comprehensive recommendation value representing the overall advantages and disadvantages of the flight and its connecting travel methods. S45. Sort all candidate flights according to their overall recommendation values, select the top-ranked options, add a highlight mark, and output them as recommended flight options.

6. The flight travel recommendation method according to claim 5, characterized in that, The calculation of the comprehensive flight attribute score can be dynamically adjusted according to the user's personal flight preference parameters, specifically: Obtain the user's personal flight preference parameters; parse the personal flight preference parameters to extract personalized preference information that characterizes the user's preferences in terms of economy, reliability, and experience; and adjust the comprehensive consideration of the flight attribute data and related meteorological data in terms of economy, reliability, and experience based on the personalized preference information. Based on the adjusted comprehensive consideration method, a comprehensive score for flight attributes that incorporates users' personalized preferences is calculated.

7. The flight travel recommendation method according to claim 1, characterized in that, S4 is followed by S5, which specifically involves: obtaining the ticketing platform booking interface information corresponding to the flight recommendation scheme; generating and displaying a user interface containing interactive booking controls; and, in response to a trigger operation on the interactive booking controls, calling the corresponding ticketing platform booking interface and redirecting to the ticket purchase page.

8. A flight travel recommendation system, characterized in that, include: The demand acquisition interaction module is used to receive user input of departure point, destination and travel date through an interactive map; The flight connection solution generation module is used to obtain a set of candidate flights based on the requirements, and identify at least one potential travel mode to the departure airport corresponding to each candidate flight. Specifically, it is used to standardize the format of the travel demand information to generate structured request data; based on the structured request data, it calls the ticketing interface to obtain the corresponding set of candidate flights; based on the geographical location of the departure airport corresponding to each candidate flight in the set of candidate flights, and combined with the user's departure location information, it calls the map service interface or traffic planning service to obtain multiple potential travel modes from the departure location to the airport; the potential travel modes include, but are not limited to: driving, ride-hailing, taxi, bus, and subway. The connection scheme evaluation module is used to integrate multi-source data to form feature information for each potential travel mode, perform multi-dimensional evaluation based on preset priority configuration, and output the evaluation results for each potential travel mode. Specifically, it is used to collect and integrate dynamic impact parameters, static geographic information, and special auxiliary data for each potential travel mode to form a multi-dimensional feature vector for that potential travel mode. The dynamic impact parameters are current and predicted road condition information obtained by calling real-time traffic data interfaces and weather data interfaces. The static geographic information is the route information from the departure point to the airport obtained through a map service interface. The special auxiliary data are additional parameters obtained according to the travel mode type. According to the preset priority configuration, the feature components representing efficiency, cost, convenience, and reliability dimensions in the multi-dimensional feature vector are evaluated. Based on the importance relationship defined by the priority configuration, the evaluation results of each dimension are combined to generate the final evaluation result for each potential travel mode. The comprehensive recommendation generation module is used to calculate the comprehensive score of each flight attribute based on flight attribute data, related meteorological data and user preference data, and to analyze and calculate the evaluation results according to the preset decision logic to generate the comprehensive recommendation value of each flight and output the flight recommendation scheme. The display output module is used to visually present the flight recommendation scheme and provide a redirect interface to the ticketing platform.

Images