Passenger portrait generation method and device in aviation field and storage medium

Abstract

The invention discloses a passenger portrait generation method and device in the aviation field and a storage medium. The method relates to the technical field of data information processing, and comprises the following steps: determining information of a target passenger, the target passenger being a passenger whose passenger portrait is to be generated in the aviation field; label matching is carried out in a label library according to the information of the target passenger, at least one preset label corresponding to the target passenger is determined, and the labels defined in the label library are labels which are obtained based on data in a database in the aviation field and a data mining technology and are used for describing passenger characteristics; determining a target label from the at least one preset label according to a preset rule; and generating a passenger portrait of the target passenger according to the target label. Through the method and the device, the problem of relatively low accuracy of the customer portrait generated by adopting a mode of directly collecting the related label of the passenger in the related technology is solved.

Description

Technical Field

[0001] The present application relates to the field of data information processing technology, and in particular to a method, device and storage medium for generating passenger portraits in the aviation field. Background Art

[0002] Against the backdrop of the rapid development of information technology and big data technology, companies are increasingly pursuing the refinement and personalization of product design to meet the market's growing personalized needs. As one of the service-oriented industries, the aviation industry is gradually shifting from traditional basic brand ticket sales to more precise and personalized services. At present, most airlines adopt a basic brand ticket sales model, whose core product is only a single ticket, lacking in-depth insight into and satisfaction of passengers' personalized needs. In order to stand out in the fierce market competition and improve passenger loyalty and satisfaction, airlines urgently need to conduct in-depth analysis of passenger preferences, build accurate customer portraits, and then provide customized product recommendations and services to achieve the goal of accurately recommending personalized services.

[0003] However, in the existing technology, the aviation industry has encountered a series of challenges in generating customer portraits. The most prominent one is that the existing technology directly collects passenger-related tags, which is too static and one-sided, and cannot capture the dynamic changes and complex needs of passenger behavior. Such tags are usually limited to basic information of passengers, such as gender, age, occupation, etc., as well as some explicit behavioral data, such as ticket purchase frequency, frequent flight routes, etc., but fail to deeply explore the multi-dimensional characteristics of passengers such as implicit needs, travel motivations, and consumption tendencies. This customer portrait construction method based on direct collection of tags lacks in-depth analysis and real-time update mechanisms, which often leads to a significant reduction in the accuracy of customer portraits and cannot truly reflect the diverse preferences and behavior patterns of passengers.

[0004] Currently, no effective solution has been proposed to address the problem of low accuracy of customer portraits generated by directly collecting relevant tags of passengers in related technologies. Summary of the invention

[0005] The main purpose of the present application is to provide a method, device and storage medium for generating passenger portraits in the aviation field, so as to solve the problem of low accuracy of customer portraits generated by directly collecting relevant tags of passengers in related technologies.

[0006] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a method for generating a passenger portrait in the aviation field is provided. The method comprises: determining the information of a target passenger, wherein the target passenger is a passenger in the aviation field whose passenger portrait is to be generated; performing label matching in a label library according to the information of the target passenger, and determining at least one preset label corresponding to the target passenger, wherein the label defined in the label library is a label for describing passenger characteristics obtained based on data in a database in the aviation field and data mining technology; determining a target label from at least one preset label according to a preset rule; and generating a passenger portrait of the target passenger according to the target label.

[0007] Furthermore, before performing tag matching in the tag library based on the information of the target passenger, it also includes: determining the data source of the aviation field database; cleaning and integrating the data in the data source to obtain the database data; defining basic class tags based on the database data and tag rules and classification standards, wherein the basic class tags at least include a basic class tag name, a basic class tag description, and a basic class tag matching rule.

[0008] Furthermore, before performing tag matching in the tag library based on the information of the target passenger, it also includes: identifying a passenger group that meets the first preset condition based on a pre-screening rule and a basic class tag, wherein the pre-screening rule specifies a specific value and range of the basic class tag related to the business requirement; integrating and analyzing the data information of the passenger group to obtain analysis data; defining a business class tag based on the analysis data and the business requirement, wherein the business class tag includes at least a business class tag name, a business class tag description, and a business class tag matching rule.

[0009] Furthermore, before performing label matching in the label library based on the information of the target passenger, it also includes: dividing the data in the database into training data and verification data; using the training data to train the machine learning algorithm to obtain a training model; evaluating the performance of the training model based on the verification data to obtain an evaluation result; adjusting the training model based on the evaluation result until the second preset condition is met to obtain a target model; based on the basic class labels and business class labels, applying the target model to the data in the database to generate mining class labels, wherein the mining class labels at least include a mining class label name, a mining class label description, and a mining class label matching rule; and constructing a label library based on the basic class labels, the business class labels, and the mining class labels.

[0010] Furthermore, performing label matching in a label library based on the information of the target passenger to determine at least one preset label corresponding to the target passenger includes: preprocessing the information of the target passenger to obtain preprocessed data information; extracting passenger features in the preprocessed data information, wherein the passenger features are features related to the labels in the label library; and determining at least one preset label corresponding to the target passenger based on the passenger features and label matching rules in the label library.

[0011] Furthermore, determining a target tag from at least one preset tag according to a preset rule includes: identifying compatible preset tags and incompatible preset tags in at least one preset tag; if there is an incompatible preset tag in at least one preset tag, calculating a first score on each scoring dimension for each incompatible preset tag according to the scoring rules corresponding to each scoring dimension within multiple scoring dimensions; performing weighted summation on the first scores on each scoring dimension to determine a first comprehensive score for each incompatible preset tag; and taking the predicted tag and the compatible preset tag with the highest first comprehensive score as the target tag.

[0012] Furthermore, after determining the target tag from at least one preset tag according to preset rules, the method also includes: calculating a second score on each scoring dimension for each target tag according to the scoring rules corresponding to each scoring dimension within multiple scoring dimensions; performing weighted summation of the second scores on each scoring dimension to determine a second comprehensive score for each target tag; determining a weight of each target tag based on the second comprehensive score of each target tag; and generating a traveler portrait of the target traveler based on the target tag and the weight of each target tag.

[0013] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a device for generating a passenger portrait in the aviation field is provided. The device comprises: a first determination unit, used to determine the information of a target passenger, wherein the target passenger is a passenger in the aviation field whose passenger portrait is to be generated; a second determination unit, used to match labels in a label library according to the information of the target passenger, and determine at least one preset label corresponding to the target passenger, wherein the labels defined in the label library are labels for describing passenger characteristics obtained based on data in a database in the aviation field and data mining technology; a third determination unit, used to determine a target label from at least one preset label according to a preset rule; and a first generation unit, used to generate a passenger portrait of the target passenger according to the target label.

[0014] Furthermore, the device also includes: a fourth determination unit, used to determine the data source of the aviation field database before performing label matching in the label library based on the information of the target passenger; a cleaning and integration unit, used to clean and integrate the data in the data source to obtain the database data; a first definition unit, used to define the basic class label based on the database data and label rules and classification standards, wherein the basic class label at least includes a basic class label name, a basic class label description, and a basic class label matching rule.

[0015] Furthermore, the device also includes: a first identification unit, which is used to identify a passenger group that meets the first preset condition based on pre-screening rules and basic class tags before performing tag matching in the tag library according to the information of the target passenger, wherein the pre-screening rules specify the specific values ​​and ranges of the basic class tags related to the business needs; an integration and analysis unit, which is used to integrate and analyze the data information of the passenger group to obtain analysis data; a second definition unit, which is used to define business class tags based on the analysis data and business needs, wherein the business class tags at least include business class tag names, business class tag descriptions, and business class tag matching rules.

[0016] Furthermore, the device also includes: a classification unit, which is used to divide the data in the database into training data and verification data before performing label matching in the label library based on the information of the target passenger; a training unit, which is used to train the machine learning algorithm using the training data to obtain a training model; an evaluation unit, which is used to evaluate the performance of the training model based on the verification data to obtain an evaluation result; an adjustment unit, which is used to adjust the training model based on the evaluation result until a second preset condition is met to obtain a target model; a third definition unit, which is used to apply the target model to the data in the database based on basic class labels and business class labels to generate mining class labels, wherein the mining class labels at least include a mining class label name, a mining class label description, and a mining class label matching rule; a construction unit, which is used to construct a label library based on the basic class labels, business class labels, and mining class labels.

[0017] Furthermore, the second confirmation unit includes: a preprocessing unit, used to preprocess the information of the target passenger to obtain preprocessed data information; an extraction unit, used to extract passenger characteristics in the preprocessed data information, wherein the passenger characteristics are characteristics related to the tags in the tag library; a matching unit, used to determine at least one preset tag corresponding to the target passenger based on the passenger characteristics and the tag matching rules in the tag library.

[0018] Furthermore, the third determination unit includes: a second identification unit, used to identify compatible preset tags and incompatible preset tags in at least one preset tag; a first calculation unit, used to calculate the first score on each scoring dimension for each incompatible preset tag according to the scoring rules corresponding to each scoring dimension within multiple scoring dimensions if there is an incompatible preset tag in at least one preset tag; a first weighted summation unit, used to weighted sum the first scores on each scoring dimension to determine the first comprehensive score of each incompatible preset tag; and a fifth determination unit, used to take the predicted tag and the compatible preset tag with the highest first comprehensive score as the target tag.

[0019] Furthermore, the device also includes: a second calculation unit, which is used to calculate the second score on each scoring dimension for each target tag according to the scoring rules corresponding to each scoring dimension after determining the target tag from at least one preset tag according to the preset rules; a second weighted summation unit, which is used to weighted sum the second scores on each scoring dimension to determine the second comprehensive score of each target tag; a sixth determination unit, which is used to determine the weight of each target tag according to the second comprehensive score of each target tag; and a second generation unit, which is used to generate a passenger portrait of the target passenger based on the target tag and the weight of each target tag.

[0020] According to another aspect of the present application, a computer-readable storage medium is provided, the computer-readable storage medium including a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute any method for generating a passenger portrait in the aviation field.

[0021] According to another aspect of the present application, an electronic device is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include a method for executing any method of generating a passenger portrait in the aviation field.

[0022] According to another aspect of the present application, a computer program product is provided, comprising computer instructions, which, when executed by a processor, implement the steps of any one of the above-mentioned methods for generating a passenger portrait in the aviation field.

[0023] In an embodiment of the present application, by determining the information of the target passenger, wherein the target passenger is a passenger in the aviation field whose passenger portrait is to be generated; performing label matching in the label library based on the information of the target passenger, determining at least one preset label corresponding to the target passenger, wherein the label defined in the label library is a label for describing passenger characteristics obtained based on data in a database in the aviation field and data mining technology; determining the target label from at least one preset label according to preset rules; generating a passenger portrait of the target passenger based on the target label, the problem of low accuracy of customer portraits generated by directly collecting relevant labels of passengers in the related technology is solved. In the present application, by determining the information of the target passenger in the aviation field, matching the information of the target passenger with the labels in the label library, matching to obtain at least one preset label corresponding to the target passenger, determining the target label from at least one preset label according to preset rules, and generating a passenger portrait of the target passenger based on the target label, thereby achieving the technical effect of improving the accuracy of passenger portraits generated in the aviation field. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0025] Figure 1 A hardware structure block diagram of a computer terminal for implementing a method for generating a passenger portrait in the aviation field is shown;

[0026] Figure 2 is a flow chart of a method for generating a passenger portrait in the aviation field provided in an embodiment of the present application;

[0027] Figure 3 This is a flowchart of defining a basic class label according to an embodiment of the present application;

[0028] Figure 4 This is a flowchart of defining a service class label according to an embodiment of the present application;

[0029] Figure 5 This is a flowchart of generating mining class labels according to an embodiment of the present application;

[0030] Figure 6 is a flowchart of label matching provided according to an embodiment of the present application;

[0031] Figure 7 is a flowchart for determining a target tag according to an embodiment of the present application;

[0032] Figure 8 This is a flow chart of generating a customer portrait according to an embodiment of the present application;

[0033] Fig. 9 is a schematic diagram of a method for generating a passenger portrait in the aviation field provided according to an embodiment of the present application;

[0034] Fig.10 is a schematic diagram of a device for generating a passenger portrait in the aviation field according to an embodiment of the present application;

[0035] Fig.11 It is a structural block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0036] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0037] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0038] It should be noted that the relevant information (including but not limited to passenger equipment information, passenger personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in this application are all information and data authorized by passengers or fully authorized by all parties. For example, an interface is set up between this system and relevant passengers or institutions. Before obtaining relevant information, it is necessary to send an acquisition request to the aforementioned passengers or institutions through the interface, and obtain relevant information after receiving the consent information fed back by the aforementioned passengers or institutions.

[0039] Example 1

[0040] According to an embodiment of the present application, a method embodiment for generating a passenger portrait in the aviation field is also provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0041] The method embodiment provided in the first embodiment of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 The hardware structure block diagram of a computer terminal (or mobile device) for implementing a method for generating a passenger portrait in the aviation field is shown. Figure 1As shown, the computer terminal 10 (or mobile device) may include one or more (102a, 102b, ..., 102n are used to illustrate) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0042] It should be noted that the one or more processors 102 and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 10 (or mobile device). As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0043] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the method for generating passenger portraits in the aviation field in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, the method for generating passenger portraits in the aviation field mentioned above is realized. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0044] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0045] The display may be, for example, a touch screen liquid crystal display (LCD) that enables the passenger to interact with the passenger interface of the computer terminal 10 (or mobile device).

[0046] Under the above operating environment, this application provides Figure 2 The method for generating passenger portraits in the aviation field is shown. Figure 2 It is a flowchart of a method for generating passenger portraits in the aviation field according to Example 1 of the present application.

[0047] Step S201, determining the information of the target passenger, wherein the target passenger is a passenger in the aviation field for whom a passenger portrait is to be generated.

[0048] Optionally, the target passenger's information may include the target passenger's basic information (such as name, age, gender), ticket purchase history, frequent flight routes, search history, membership level, consumption behavior, etc. For example, passenger A's information includes basic information, which is the personal information filled in when registering for the airline's membership service, including passenger A's name, age "30 years old", and gender "male". Passenger A's information includes ticket purchase history: by querying the airline's sales records, it is found that passenger A has purchased a total of 15 tickets in the past year, of which 10 are domestic flights and 5 are international flights. In these trips, passenger A prefers business class, especially on international flights, and the ticket purchase time is mostly concentrated in the morning on weekdays. Ticket purchase history helps to understand the passenger's travel frequency, cabin preference and ticket purchase habits. Passenger A's information includes frequent flight routes: in passenger A's ticket purchase history, it is identified that passenger A's most frequently flown routes are from Beijing to Shanghai and from Beijing to New York. Frequent flight route information helps airlines provide discounts and services for specific routes. Passenger A's information includes search history analysis: Passenger A recently searched for flight information from Beijing to New York, and paid special attention to the departure and arrival times of the flights, hoping to travel during the day so as to better arrange work and rest. Passenger A's information also includes membership level and consumption behavior: Passenger A's membership level is a gold card member. In addition to buying tickets, Passenger A also often purchases airport lounge access and selects the airline's hotel reservation service. The above target passenger information will be used in the subsequent tag matching process to further refine the target passenger's passenger portrait and support airlines in providing customized services.

[0049] Optionally, a DatacategorySet model can be defined to represent a defined set of data categories. The model contains multiple Datacategory structures, each Datacategory represents a data category. As the amount of collected data continues to accumulate, the model will continue to expand. Each category has a standard data format specification, and the data is standardized according to the specification. The processed standardized data is persistently stored to form a database.

[0050] Step S202, performing tag matching in a tag library according to the information of the target passenger, and determining at least one preset tag corresponding to the target passenger, wherein the tags defined in the tag library are tags for describing passenger characteristics obtained based on data in an aviation database and data mining technology.

[0051] Optionally, the tag library is a set of tags predefined by the airline to describe passenger characteristics. The tag types can be basic, business, and mining tags, involving basic attributes, travel preferences, and potential behavior patterns of passengers. At this stage, the characteristic information of the target passenger is matched with the tag definitions in the tag library to identify one or more preset tags that match the passenger's characteristics.

[0052] In an optional embodiment, if Figure 3 As shown, before matching tags in the tag library based on the target passenger's information, the following is also included:

[0053] Step S301, determining the data source of the aviation field database.

[0054] Optionally, the above data source can be passenger account information: from the airline's membership registration system, including basic information such as the passenger's name, gender, age, contact information, etc. The data source can be ticket purchase history: obtained from the airline's sales database, recording the passenger's past ticket purchase times, cabin selection, flight type (domestic / international), etc. The data source can be airport business system data: data collected in cooperation with the airport, including passenger boarding records, baggage check-in information, airport consumption, etc. The data source can be third-party retailer data: passenger travel-related consumption records obtained from partners such as hotel booking platforms and car rental service companies. This technical solution is based on comprehensive and diverse data sources. Airlines can generate more accurate and dynamic passenger portraits, and then provide personalized services, reasonably allocate resources, and achieve a deep understanding and satisfaction of passenger needs, thereby maintaining an advantage in the highly competitive aviation market.

[0055] Step S302: clean and integrate the data in the data source to obtain the data in the database.

[0056] Optionally, the methods for cleaning the data in the data source can be data format consistency, data type conversion, consistency check, data standardization, etc. Data format consistency: ensure that the format of data fields is consistent, such as the date format is unified as "YYYY-MM-DD", and unnecessary text descriptions are removed from numeric fields. Data type conversion: convert data to the correct type, such as converting string type values ​​into integer or floating point types, to ensure that the data can be correctly analyzed and processed. Consistency check: check the logical relationship between data fields, for example, the consistency between age and date of birth, to ensure that the logic of the data is correct. Data standardization: convert data fields into a unified unit of measurement or ratio, such as converting income data into thousands / million yuan, to facilitate comparison and analysis of different data.

[0057] Optionally, the data in the data source can be cleaned. Each piece of data can be analyzed for fit from different angles based on the actual business, and a comprehensive fit value can be calculated, and then the data with low fit can be filtered out. Fit analysis is a quantitative assessment of the degree of match between data and business needs, which involves evaluating the fit of the information in the data source to a specific business scenario. The calculation of the fit value can be achieved by defining a series of evaluation indicators and weights. For example, for the ticket purchase history of passenger A, the evaluation indicators can be set: the proximity of the ticket purchase time to the travel time (high weight), the frequency of the flight segments (high weight), the consumption level (medium weight), and the diversity of cabin options (low weight). After calculation, if the information contained in a ticket purchase record of passenger A (such as an abnormally low fare) has a low correlation with his historical behavior and the current business scenario, then this record is excluded from the analysis data.

[0058] Optionally, data in the data source can be integrated to integrate different types of data by formulating unified data formats and specifications, building a model suitable for integrating data, selecting mature data conversion tools, and building a unified data view. By setting standard data validation specifications and audit mechanisms, the data view can be verified and audited to ensure the quality and accuracy of the data, and a database can be established to store and manage data.

[0059] Step S303, defining basic class tags according to the data in the database, tag rules and classification standards, wherein the basic class tags at least include a basic class tag name, a basic class tag description and a basic class tag matching rule.

[0060] Optionally, the above-mentioned labeling rules are a set of specific specifications for creating and applying labels, which specify the logic, conditions and methods of label generation. Labeling rules ensure the consistency and accuracy of labels, and avoid defining labels that are too broad or unclear, which will affect the analysis results. Labeling rules may include the following elements: label generation logic, conditions and thresholds, label update mechanism, etc. Label generation logic: describes how to extract information from raw data to create labels. Conditions and thresholds: set specific conditions for label application, such as age range, thresholds for ticket purchase frequency, etc. Label update mechanism: defines when and how labels are updated to reflect changes in passenger behavior.

[0061] Optionally, the above classification standard is a system for organizing and classifying tags, helping to classify different types of tags together for easy management and application. The classification standard can be set based on dimensions such as passenger attributes, behaviors or needs.

[0062] For example, define the following basic class tags. Basic class tag name: Passengers by age. Basic class tag description: Passengers are classified into specific age groups according to their age to analyze the behaviors and preferences of passengers of different age groups. Basic class tag matching rules: Under 18 years old: youth passengers; 18 to 45 years old: adult passengers; 45 years old and above: middle-aged and elderly passengers. Basic class tag name: Gender. Basic class tag description: Identify the gender of passengers in order to analyze the impact of gender differences on travel behavior. Basic class tag matching rules: Male: marked as "M"; Female: marked as "F".

[0063] In summary, through the above technical solutions, key information is extracted from the data source of the aviation database through labeling rules and classification standards, and converted into basic class labels to better understand and classify passengers. Airlines can combine these basic class labels to optimize service processes and personalized recommendations, thereby improving passenger satisfaction and company profits.

[0064] In an optional embodiment, if Figure 4 As shown, before performing tag matching in the tag library according to the information of the target passenger, the following steps are also included:

[0065] Step S401, identifying a passenger group meeting a first preset condition based on a pre-screening rule and a basic class tag, wherein the pre-screening rule specifies a specific value and range of the basic class tag related to the business requirement.

[0066] Optionally, the above-mentioned pre-screening rules are a series of conditions set by the airline according to its business objectives and strategies, which are used to preliminarily screen passenger data to ensure that the data for subsequent analysis is highly matched with the company's specific operational needs. The pre-screening rules specify the specific values ​​and ranges of basic class tags related to business needs, which can be the specific values ​​and ranges of basic class tags such as the passenger's age, gender, ticket purchase frequency, consumption habits, travel purpose (business or leisure), etc. The above-mentioned first preset condition is the result of the concretization of the pre-screening rules. It is directly based on the conditions and thresholds defined in the pre-screening rules, and is used to determine whether the passenger belongs to a specific business concern group. For example, for a scenario where an airline wants to increase business class sales, the first preset condition may be "business class ticket purchase rate exceeds 50%."

[0067] For example, an airline wants to optimize its sales strategy for business class and high-end services to improve the satisfaction and loyalty of high-spending passengers. In this case, the pre-screening rules can be age: 25 to 55 years old (peak business travel period), gender: unlimited, flight frequency: at least 15 flights in the past year, cabin selection: at least 50% of the tickets purchased are business class or first class, consumption level: the average consumption in terms of air tickets, additional services, airport consumption, etc. is higher than the average level of ordinary passengers. Based on the above pre-screening rules, the first preset condition is: if the passenger meets all of the following conditions, he will be identified as a "high-spending business passenger group". Aged between 25 and 55, at least 15 flights in the past year, the number of business class or first class tickets purchased accounts for more than 50% of the total number of tickets purchased, and the average consumption level of the passenger is 1.5 times higher than the average consumption level of ordinary passengers.

[0068] Step S402, integrating and analyzing the data information of the passenger groups to obtain analysis data.

[0069] For example, in step S401, a passenger group with "business travel preference" has been identified based on basic tags such as "age level" (25-55 years old), "occupation" (corporate employees), "flight frequency" (at least 10 flights per year) and "cabin selection" (business class ticket purchase ratio is higher than 50%). Then, the data information of these passenger groups is integrated and analyzed:

[0070] Data collection: Extracting the ticket purchase history, flight preferences, additional service purchase records, etc. of all passengers marked as "business travel preference" from the database;

[0071] Data preprocessing: Check whether there are missing or abnormal values ​​in the ticket purchase time, flight selection, additional service purchase and other information in the data, and perform necessary cleaning;

[0072] Data integration: Integrate information such as ticket purchase history and flight preferences into a single analytical framework, such as converting ticket purchase time into working days or non-working days, and converting flight selection into business class or non-business class.

[0073] Data analysis: Use statistical methods, such as frequency distribution and correlation analysis, to understand the ticket purchasing behavior patterns of these business travelers. For example, by analyzing the time of ticket purchase, it is found that they tend to buy tickets on weekdays, and by analyzing flight selection, it is found that they are more inclined to choose business class.

[0074] Step S403, defining a business class tag based on the analysis data and business requirements, wherein the business class tag at least includes a business class tag name, a business class tag description, and a business class tag matching rule.

[0075] For example, through the analysis data of step S402, it is identified that there are behavioral patterns of "weekday ticket purchase preference" and "business class preference" in the business traveler group. Then, the features of "weekday ticket purchase preference" and "business class preference" are extracted from the pattern recognition as the basis for defining business class labels. Based on the above analysis data and business needs, business class labels are defined, for example, business class label name: Weekday business class frequent flyer, business class label description: corporate employees who frequently choose business class travel on weekdays, business class label matching rules: If a passenger has purchased at least 70% of tickets on weekdays in the past year, and the number of business class ticket purchases accounts for 60% of the total number of ticket purchases, then the passenger can be marked as a "weekday business class frequent flyer".

[0076] In summary, through the above technical solutions, airlines will be able to have a deeper understanding of the behavioral preferences of passenger groups, and then define more accurate business category labels to guide the formulation of personalized services to enhance customer satisfaction and improve business efficiency.

[0077] In an optional embodiment, if Figure 5 As shown, before matching tags in the tag library based on the target passenger's information, the following is also included:

[0078] Step S501, dividing the data in the database into training data and verification data.

[0079] Optionally, the data in the database can be divided into two parts: one part is used as training data for training machine learning algorithms; the other part is used as validation data for evaluating the performance of the trained model. The data can be divided according to a certain ratio (such as 70% training and 30% validation) to ensure the representativeness of the training data and validation data and avoid overfitting or underfitting of the model.

[0080] Step S502: Use training data to train the machine learning algorithm to obtain a training model.

[0081] Optionally, the training data is used to train a machine learning algorithm, which could be a decision tree, logistic regression, or neural network, etc. The training process involves the algorithm learning the patterns and features in the passenger data and the relationship between these features and the base class labels and business class labels.

[0082] For example, training data is used to train machine learning algorithms (such as random forests). When training the model, the characteristics of passengers such as flight frequency, cabin selection history, ticket purchase time, and frequent flight routes are taken into account.

[0083] Step S503, evaluating the performance of the training model based on the verification data to obtain an evaluation result.

[0084] Optionally, apply the trained model to validation data to evaluate the model's predictive accuracy and performance. The evaluation results can include metrics such as precision, recall, and F1 score to measure the ability of the trained model to identify specific groups of travelers.

[0085] For example, the performance of the trained model is evaluated using the validation data, and the evaluation results show that the trained model predicts "business economy class alternating users" with an accuracy of 85%, a recall of 70%, and an F1 score of 78%.

[0086] Step S504, adjusting the training model based on the evaluation result until the second preset condition is met to obtain the target model.

[0087] Optionally, the training model is adjusted and optimized according to the evaluation results to improve its prediction performance. The adjustment may involve parameter tuning, feature selection or model selection, etc. The second preset condition may be to reach a specific prediction accuracy threshold, such as 90% accuracy.

[0088] Step S505, based on the basic class tags and the business class tags, apply the target model to the data in the database to generate mining class tags, wherein the mining class tags at least include the mining class tag name, the mining class tag description, and the mining class tag matching rules.

[0089] Optionally, if the target model achieves satisfactory performance, it can be applied to the data of the entire database. Through machine learning algorithms, it can identify undefined, potential behavior patterns or preferences in the data, etc., and generate mining class labels. For example, the target model finds that a certain group of passengers switches between business class and economy class more frequently than the average, thus defining the mining class label "Business-Economy Class Alternating Users". Mining class label name: Business-Economy Class Alternating Users, Mining class label description: There are both business class and economy class ticket purchase records, Mining class label matching rules: In the past year, there were both business class and economy class ticket purchase records, and the proportion of business class ticket purchases was between 30% and 70%.

[0090] Step S506, constructing a tag library based on basic class tags, business class tags and mining class tags.

[0091] Optionally, all basic tags, business tags, and mining tags are integrated into a unified tag library to facilitate subsequent passenger profile analysis and personalized service design. The tag library can contain tag names, tag descriptions, and tag matching rules, as well as statistical information about the tag, such as the number of covered passengers, average behavioral characteristics of passenger groups, and so on.

[0092] In summary, through the above technical solutions, airlines can not only identify passengers with basic and business tags, but also generate mining tags based on the target model. Mining tags are of high value and can better reflect the real situation.

[0093] In an optional embodiment, if Figure 6 As shown, performing tag matching in a tag library according to the target passenger's information and determining at least one preset tag corresponding to the target passenger includes:

[0094] Step S601, preprocessing the target passenger's information to obtain preprocessed data information.

[0095] Optionally, preprocessing is a pre-step for data processing and analysis. The above preprocessing methods can be: data cleaning, data format unification, data conversion, data standardization, etc. For example, it is necessary to match the preset label suitable for the target passenger Mr. Zhao from the label library. First, preprocess Mr. Zhao's information. Extract Mr. Zhao's data from the database, including his age (35 years old), gender (male), occupation (corporate executive), flight records in the past year, etc. After data cleaning, ensure that all field formats are consistent, such as converting age to numeric data and processing the date format in flight records.

[0096] Step S602: extracting passenger features from the preprocessed data information, wherein the passenger features are features related to the tags in the tag library.

[0097] Optionally, passenger feature extraction is to select features related to the tag definition in the tag library from the preprocessed data, and these features will be used for subsequent tag matching. For example, there is a tag called "business traveler", and the passenger features related to this tag can be the average flight frequency, the proportion of weekday ticket purchases, the proportion of business class purchases, etc.

[0098] Step S603: Determine at least one preset tag corresponding to the target passenger based on the passenger characteristics and the tag matching rules in the tag library.

[0099] Optionally, tag matching is the process of determining the preset tag that best matches the target passenger based on the passenger characteristics and the matching rules of each tag in the tag library. The above tag matching rules define how to determine whether a passenger belongs to a specific tag based on the passenger characteristics.

[0100] For example, according to the results of feature extraction, it is found that Mr. Zhao meets two preset labels. Business travelers: defined as passengers with a high proportion of ticket purchases on weekdays (over 70%) and a high proportion of business class purchases (over 60%). Business route frequent flyers: defined as passengers who have frequently (at least 2 times a month on average) flown on specific business routes (such as Beijing-Shanghai, Beijing-Guangzhou) in the past year. Therefore, according to the label matching rules in the label library, Mr. Zhao will be marked with the preset labels of "business traveler" and "business route frequent flyer".

[0101] In summary, through the above technical solutions, airlines can effectively analyze and understand the characteristics of each passenger and provide them with more accurate and personalized services, thereby standing out in the fierce market competition and enhancing passenger satisfaction and loyalty.

[0102] Step S203: determining a target tag from at least one preset tag according to a preset rule.

[0103] Optionally, the above preset rules can be based on the compatibility, priority, historical behavior patterns and other business requirements of the tags. For example, the preset rules are to determine the compatibility of tags. Compatible preset tags refer to those that can be applied to a passenger at the same time, while incompatible tags are logically mutually exclusive or cannot exist at the same time in a specific scenario. Through the preset rules, the most relevant target tags that best reflect the core characteristics of the passenger can be filtered out from the matching preset tags.

[0104] In an optional embodiment, if Figure 7 As shown, determining a target tag from at least one preset tag according to a preset rule includes:

[0105] Step S701: identifying compatible preset tags and incompatible preset tags in at least one preset tag.

[0106] Optionally, identification of compatible and incompatible preset tags is based on the logical relationship between passenger characteristics and tags. Compatible preset tags are tags that can be applied to the same passenger at the same time, while incompatible preset tags are tags that are mutually exclusive and cannot exist at the same time. The logical judgment of incompatible tags can be based on mutually exclusive attributes: check whether the characteristics of the passenger simultaneously meet the logically mutually exclusive or exclusive tag definitions. For example, if a passenger meets the characteristics of frequent weekday ticket purchases and frequent holiday ticket purchases, this may indicate that there is a conflict or overlap between the tag definitions, and further inspection of the logical relationship of the tags is required. For example, the label "business traveler" is usually associated with characteristics such as business class selection and weekday ticket purchases, while "leisure traveler" may be more related to characteristics such as economy class and holiday ticket purchases. If the characteristics of a passenger point to these two completely different modes at the same time, then the two preset tags are logically incompatible.

[0107] Step S702: If there is an incompatible preset tag in at least one preset tag, a first score in each scoring dimension is calculated for each incompatible preset tag according to a scoring rule corresponding to each scoring dimension in multiple scoring dimensions.

[0108] Optionally, when the target passenger is matched by multiple incompatible preset tags, a scoring rule is required to determine which tag is more applicable to the current passenger. The scoring dimension can be an operational behavior dimension, and the operational behavior can be: different behaviors such as passenger browsing, searching, collecting, and placing orders. Different operational behaviors have different importance to passengers. Browsing behavior may be a passenger's initial understanding of various information and options, and is their exploration stage before making a decision. Searching behavior shows the passenger's demand for specific information, indicating that they already have certain goals and directions. Collecting behavior means that the passenger has an interest in certain products or services, which may be a potential choice for future purchases. The ordering behavior is the specific manifestation of the passenger's final decision to purchase, representing their recognition and satisfaction with a certain product or service. The first score corresponding to the operational behavior dimension can be calculated according to the scores of different operational behaviors set in Table 1.

[0109] Table 1

[0110] Operational behavior Points Browse 10 search 20 collect 30 Place an order 40

[0111] Optionally, the scoring dimension can be the operation time dimension. The influence of time on certain behaviors of passengers is gradually weakened. The farther the behavior time is from now, the less significance the behavior has for the current behavior of the passenger. The degree of time weakening can be calculated by the formula:

[0112]

[0113] Among them, I represents the time reduction degree; K represents the time reduction base coefficient; d represents the time reduction degree coefficient; and t represents the time difference between the behavior time and the last behavior time. Under the premise that K and d are constant values, as t increases, I also increases, that is, when the time difference between two behaviors increases, the time reduction degree also increases, and the score of this dimension becomes lower and lower.

[0114] Optionally, the scoring dimension may be an operation frequency dimension. The passenger operation frequency is counted according to a period. The more times a passenger has performed actions with the tag in this period, the greater the impact of the tag on the user, and the higher the score. The first score corresponding to the operation frequency dimension may be calculated according to the scores corresponding to different frequencies set in Table 2.

[0115] Table 2

[0116] Frequency Points 1-5 10 6-10 20 11-30 30 >30 40

[0117] For example, the scoring dimensions are the operation behavior dimension and the operation frequency dimension. The two preset labels of the target passenger Mr. Zhang, "Business Traveler" and "Leisure Traveler", are incompatible preset labels. First, calculate the score of the preset label "Business Traveler". In the operation behavior dimension, there have been 2 orders for business class tickets, so the score in the operation behavior dimension is 80 (40*2); Mr. Zhang's operation frequency for business class tickets in a cycle is 11-30, and the score in the operation frequency dimension is 30. Then calculate the score of the preset label "Leisure Traveler". In the operation behavior dimension, there have been 1 order and 1 collection of economy class tickets, so the score in the operation behavior dimension is 70 (40+30); Mr. Zhang's operation frequency for economy class tickets in a cycle is 6-10, and the score in the operation frequency dimension is 20.

[0118] Step S703: Perform a weighted summation on the first scores of each scoring dimension to determine a first comprehensive score of each incompatible preset tag.

[0119] Optionally, each scoring dimension has its importance, so it is necessary to perform a weighted summation on the first scores of each scoring dimension to obtain a first comprehensive score that is incompatible with the preset label. The weight setting can be based on actual business needs and the priority of passenger behavior. For example, the weighted summation formula can be: Among them, n represents the number of dimensions, k represents the coefficient of the current dimension, and k1+k2+k3+…+k n =1, v represents the score of the current dimension.

[0120] For example, the coefficient of the operation behavior dimension is set to 0.4, and the coefficient of the operation frequency dimension is set to 0.6. Based on the first score of each incompatible preset label calculated in step S702 in each scoring dimension, a weighted sum is performed. The score of "Business Traveler" in the operation behavior dimension is 80, and the score in the operation frequency dimension is 30. The weighted sum score is 80*0.4+30*0.6=50. The score of "Leisure Traveler" in the operation behavior dimension is 70, and the score in the operation frequency dimension is 20. The weighted sum score is 70*0.4+20*0.6=40, so the predicted label with the highest first comprehensive score is "Business Traveler".

[0121] Step S704: Use the predicted tag with the highest first comprehensive score and the compatible preset tag as the target tag.

[0122] For example, "business travelers" having the highest comprehensive score and compatible preset tags are used as target tags.

[0123] In summary, through the above technical solutions, airlines can accurately identify the travel preferences and behavior patterns of target passengers and provide them with personalized services that meet the characteristics of the target tags.

[0124] Step S204: Generate a traveler portrait of the target traveler based on the target tag.

[0125] Optionally, a passenger profile is a document that combines target labels and their weights to provide a detailed description of the passenger's characteristics and behavior predictions. Once the target label is determined, a complete profile representing the passenger's characteristics and preferences can be generated.

[0126] In an optional embodiment, if Figure 8 As shown, after determining the target tag from at least one preset tag according to a preset rule, the method further includes:

[0127] Step S801, calculating a second score in each scoring dimension for each target tag according to the scoring rules corresponding to each scoring dimension in multiple scoring dimensions.

[0128] For example, the target labels of the target passenger Mr. Li are "business travelers", "high-spending travelers" and "domestic and foreign air passengers", and the second scores of the three target labels in the operation behavior dimension and the operation frequency dimension are calculated. The target label "business travelers" has a score of 100 in the operation behavior dimension and a score of 40 in the operation frequency dimension. The target label "high-spending travelers" has a score of 80 in the operation behavior dimension and a score of 30 in the operation frequency dimension. The target label "business travelers" has a score of 40 in the operation behavior dimension and a score of 20 in the operation frequency dimension.

[0129] Step S802: Perform a weighted summation on the second scores of each scoring dimension to determine a second comprehensive score for each target tag.

[0130] For example, using the weighted sum formula: Among them, n represents the number of dimensions, k represents the coefficient of the current dimension, and k1+k2+k3+…+k n =1, v represents the score of the current dimension. Set the coefficient of the operation behavior dimension to 0.8, and the coefficient of the operation frequency dimension to 0.2. The second comprehensive score of "business travelers" is 100*0.8+40*0.2=100. The second comprehensive score of "high-spending travelers" is 80*0.8+30*0.2=70. The second comprehensive score of "domestic and foreign air passengers" is 40*0.8+20*0.2=36.

[0131] Step S803: Determine the weight of each target tag according to the second comprehensive score of each target tag.

[0132] For example, according to the second comprehensive score, the second comprehensive score of the "Business Traveler" label (100) > the second comprehensive score of the "High Spending Traveler" label (70) > the second comprehensive score of the "Domestic and International Airline Passengers" label (36). Therefore, the weight of "Business Traveler" can be 0.45, the weight of "High Spending Traveler" can be 0.35, and the weight of "Domestic and International Airline Passengers" can be 0.2.

[0133] Step S804: Generate a traveler portrait of the target traveler based on the target tag and the weight of each target tag.

[0134] For example, Mr. Li's passenger profile will include the following information: Basic tags: Gender (male), Age (35-45 years old), Occupation (corporate executive). Business tags: "Business travelers" has a weight of 0.45, "High-spending travelers" has a weight of 0.35, and "Domestic and international flight passengers" has a weight of 0.2.

[0135] In summary, through this passenger portrait, the airline can gain a deep understanding of Mr. Li's travel needs and consumption habits. When providing services, it will give priority to convenience recommendations based on the high weight of the "business traveler" label. At the same time, considering the importance of the "high-spending passenger" label, it will also provide luxury services and high-end products. And it will also combine some additional services for foreign flights to ensure that Mr. Li's core needs are met.

[0136] The method for generating a passenger portrait in the aviation field provided in the embodiment of the present application determines the information of the target passenger, wherein the target passenger is the passenger for whom the passenger portrait is to be generated in the aviation field; performs label matching in the label library according to the information of the target passenger, and determines at least one preset label corresponding to the target passenger, wherein the label defined in the label library is a label for describing passenger characteristics obtained based on data in a database in the aviation field and data mining technology; determines the target label from at least one preset label according to preset rules; generates the passenger portrait of the target passenger according to the target label, thereby solving the problem of low accuracy of the customer portrait generated by directly collecting the relevant labels of the passenger in the related technology. In the present application, by determining the information of the target passenger in the aviation field, matching the information of the target passenger with the labels in the label library, matching to obtain at least one preset label corresponding to the target passenger, determining the target label from at least one preset label according to preset rules, and generating the passenger portrait of the target passenger according to the target label, thereby achieving the technical effect of improving the accuracy of the passenger portrait generated in the aviation field.

[0137] For example, Fig. 9 A schematic diagram of a method for generating a passenger portrait in the aviation field according to an embodiment of the present application, comprising the following steps:

[0138] Establish a data warehouse: determine the data source of the aviation database, clean and integrate the data in the data source, and obtain the database data;

[0139] Define basic passenger tags: Define basic tags based on database data, tag rules and classification standards;

[0140] Define passenger business tags: Identify passenger groups that meet the first preset condition based on pre-screening rules and basic class tags, integrate and analyze the data information of passenger groups to obtain analysis data, and define business class tags based on the analysis data and business needs;

[0141] Calculate label data: match the target label of the target passenger based on the label rule, calculate the score of each target label in each scoring dimension according to the scoring rule corresponding to each scoring dimension, perform weighted sum of the scores in each scoring dimension, and determine the comprehensive score of each target label;

[0142] Determine the weight of passenger tags: Determine the weight of each target tag based on its comprehensive score;

[0143] Generate passenger profile: Generate a passenger profile of the target passenger based on the target label and the weight of each target label.

[0144] In summary, the above steps can generate a more accurate passenger portrait, thereby providing more personalized products for target passengers.

[0145] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0146] Example 2

[0147] The embodiment of the present application also provides a device for generating a passenger portrait in the aviation field. It should be noted that the device for generating a passenger portrait in the aviation field in the embodiment of the present application can be used to execute the method for generating a passenger portrait in the aviation field provided in the embodiment of the present application. The device for generating a passenger portrait in the aviation field provided in the embodiment of the present application is introduced below.

[0148] According to an embodiment of the present application, a device for implementing the above-mentioned method for generating a passenger portrait in the aviation field is also provided, such as Fig.10 As shown, the device includes: a first determining unit 1001, a second determining unit 1002, a third determining unit 1003 and a first generating unit 1004.

[0149] Specifically, the first determination unit 1001 is used to determine the information of the target passenger, wherein the target passenger is a passenger in the aviation field for whom a passenger portrait is to be generated; the second determination unit 1002 is used to perform label matching in a label library based on the information of the target passenger, and determine at least one preset label corresponding to the target passenger, wherein the labels defined in the label library are labels for describing passenger characteristics obtained based on data in a database in the aviation field and data mining technology; the third determination unit 1003 is used to determine a target label from at least one preset label according to a preset rule; the first generation unit 1004 is used to generate a passenger portrait of the target passenger based on the target label.

[0150] In summary, the device for generating a passenger portrait in the aviation field provided in the embodiment of the present application determines the information of the target passenger through the first determination unit 1001, wherein the target passenger is a passenger in the aviation field for whom a passenger portrait is to be generated; the second determination unit 1002 performs label matching in the label library based on the information of the target passenger, and determines at least one preset label corresponding to the target passenger, wherein the labels defined in the label library are labels for describing passenger characteristics obtained based on data in a database in the aviation field and data mining technology; the third determination unit 1003 determines the target label from at least one preset label according to preset rules; the first generation unit 1004 generates a passenger portrait of the target passenger based on the target label, thereby solving the problem of low accuracy of customer portraits generated by directly collecting relevant labels of passengers in related technologies in related technologies. In the present application, the information of the target passenger in the aviation field is determined by the first determination unit 1001, the second determination unit 1002 matches the information of the target passenger with the tags in the tag library to obtain at least one preset tag corresponding to the target passenger, the third determination unit 1003 determines the target tag from at least one preset tag according to a preset rule, and the first generation unit 1004 can generate a passenger portrait of the target passenger according to the target tag, thereby achieving a technical effect of improving the accuracy of passenger portraits generated in the aviation field.

[0151] Optionally, the device also includes: a fourth determination unit, used to determine the data source of the aviation field database before performing label matching in the label library based on the information of the target passenger; a cleaning and integration unit, used to clean and integrate the data in the data source to obtain the database data; a first definition unit, used to define the basic class label based on the database data and label rules and classification standards, wherein the basic class label includes at least the basic class label name, the basic class label description, and the basic class label matching rule.

[0152] Optionally, the device also includes: a first identification unit, used to identify a passenger group that meets a first preset condition based on pre-screening rules and basic class labels before performing label matching in a label library according to the information of the target passenger, wherein the pre-screening rules specify specific values ​​and ranges of basic class labels related to business needs; an integration and analysis unit, used to integrate and analyze data information of passenger groups to obtain analysis data; a second definition unit, used to define business class labels based on the analysis data and business needs, wherein the business class labels include at least a business class label name, a business class label description, and a business class label matching rule.

[0153] Optionally, the device also includes: a classification unit, used to divide the data in the database into training data and verification data before performing label matching in the label library based on the information of the target passenger; a training unit, used to train the machine learning algorithm using the training data to obtain a training model; an evaluation unit, used to evaluate the performance of the training model based on the verification data to obtain an evaluation result; an adjustment unit, used to adjust the training model based on the evaluation result until a second preset condition is met to obtain a target model; a third definition unit, used to apply the target model to the data in the database based on basic class labels and business class labels to generate mining class labels, wherein the mining class labels at least include a mining class label name, a mining class label description, and a mining class label matching rule; a construction unit, used to construct a label library based on the basic class labels, business class labels, and mining class labels.

[0154] Optionally, the second confirmation unit 1002 includes: a preprocessing unit, used to preprocess the information of the target passenger to obtain preprocessed data information; an extraction unit, used to extract passenger characteristics from the preprocessed data information, wherein the passenger characteristics are characteristics related to the tags in the tag library; and a matching unit, used to determine at least one preset tag corresponding to the target passenger based on the passenger characteristics and the tag matching rules in the tag library.

[0155] Optionally, the third determination unit 1003 includes: a second identification unit, used to identify compatible preset tags and incompatible preset tags in at least one preset tag; a first calculation unit, used to calculate the first score on each scoring dimension for each incompatible preset tag according to the scoring rules corresponding to each scoring dimension within multiple scoring dimensions if there is an incompatible preset tag in at least one preset tag; a first weighted summation unit, used to weighted sum the first scores on each scoring dimension to determine the first comprehensive score of each incompatible preset tag; and a fifth determination unit, used to select the predicted tag and the compatible preset tag with the highest first comprehensive score as the target tag.

[0156] Optionally, the device also includes: a second calculation unit, which is used to calculate the second score on each scoring dimension for each target tag according to the scoring rules corresponding to each scoring dimension after determining the target tag from at least one preset tag according to preset rules; a second weighted summation unit, which is used to weighted sum the second scores on each scoring dimension to determine the second comprehensive score of each target tag; a sixth determination unit, which is used to determine the weight of each target tag based on the second comprehensive score of each target tag; and a second generation unit, which is used to generate a passenger portrait of the target passenger based on the target tag and the weight of each target tag.

[0157] It should be noted that the first determination unit 1001, the second determination unit 1002, the third determination unit 1003 and the first generation unit 1004 described above correspond to steps S201 to S204 in Example 1, and the two modules and the corresponding steps implement the same examples and application scenarios, but are not limited to the contents disclosed in the above-mentioned Example 1. It should be noted that the above-mentioned modules or units may be hardware components or software components stored in a memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n), and the above-mentioned modules may also be part of a device and may be run in the computer terminal 10 provided in Example 1.

[0158] Example 3

[0159] The embodiment of the present application may provide a computer terminal, which may be any computer terminal device in a computer terminal group. Optionally, in this embodiment, the computer terminal may also be replaced by a terminal device such as a mobile terminal or an electronic device.

[0160] Optionally, in this embodiment, the computer terminal may be located in at least one network device among a plurality of network devices of the computer network.

[0161] In this embodiment, the above-mentioned computer terminal can execute the program code of the following steps in the method for generating a passenger portrait in the aviation field: determining the information of the target passenger, wherein the target passenger is a passenger in the aviation field for whom a passenger portrait is to be generated; performing label matching in a label library based on the information of the target passenger, and determining at least one preset label corresponding to the target passenger, wherein the labels defined in the label library are labels for describing passenger characteristics obtained based on data in a database in the aviation field and data mining technology; determining a target label from at least one preset label according to preset rules; and generating a passenger portrait of the target passenger based on the target label.

[0162] Optionally, the above-mentioned computer terminal can execute the program code of the following steps in the method for generating passenger portraits in the aviation field: before performing label matching in the label library based on the information of the target passenger, it also includes: determining the data source of the database in the aviation field; cleaning and integrating the data in the data source to obtain the database data; defining basic class labels based on the database data and label rules and classification standards, wherein the basic class labels at least include a basic class label name, a basic class label description, and a basic class label matching rule.

[0163] Optionally, the above-mentioned computer terminal can execute the program code of the following steps in the method for generating passenger portraits in the aviation field: before performing label matching in the label library based on the information of the target passenger, it also includes: identifying passenger groups that meet the first preset conditions based on pre-screening rules and basic class labels, wherein the pre-screening rules specify specific values ​​and ranges of basic class labels related to business needs; integrating and analyzing data information of passenger groups to obtain analysis data; defining business class labels based on the analysis data and business needs, wherein the business class labels at least include business class label names, business class label descriptions, and business class label matching rules.

[0164] Optionally, the above-mentioned computer terminal can execute the program code of the following steps in the method for generating passenger portraits in the aviation field: before performing label matching in the label library based on the information of the target passenger, it also includes: dividing the data in the database into training data and verification data; using the training data to train the machine learning algorithm to obtain a training model; evaluating the performance of the training model based on the verification data to obtain an evaluation result; adjusting the training model based on the evaluation result until the second preset condition is met to obtain a target model; based on the basic class labels and business class labels, applying the target model to the data in the database to generate mining class labels, wherein the mining class labels at least include a mining class label name, a mining class label description, and a mining class label matching rule; and constructing a label library based on the basic class labels, business class labels, and mining class labels.

[0165] Optionally, the computer terminal may execute the program code of the following steps in the method for generating a passenger portrait in the aviation field: performing label matching in a label library based on the information of the target passenger, and determining at least one preset label corresponding to the target passenger, including: preprocessing the information of the target passenger to obtain preprocessed data information; extracting passenger features in the preprocessed data information, wherein the passenger features are features related to the labels in the label library; and determining at least one preset label corresponding to the target passenger based on the passenger features and label matching rules in the label library.

[0166] Optionally, the above-mentioned computer terminal can execute the program code of the following steps in the method for generating passenger portraits in the aviation field: determining the target tag from at least one preset tag according to preset rules includes: identifying compatible preset tags and incompatible preset tags in at least one preset tag; if there are incompatible preset tags in at least one preset tag, then calculating the first score on each scoring dimension for each incompatible preset tag according to the scoring rules corresponding to each scoring dimension within multiple scoring dimensions; weighted summing the first scores on each scoring dimension to determine the first comprehensive score of each incompatible preset tag; and taking the predicted tag and the compatible preset tag with the highest first comprehensive score as the target tag.

[0167] Optionally, the above-mentioned computer terminal can execute the program code of the following steps in the method for generating a passenger portrait in the aviation field: after determining the target tag from at least one preset tag according to preset rules, the method also includes: calculating the second score on each scoring dimension for each target tag according to the scoring rules corresponding to each scoring dimension within multiple scoring dimensions; weighted summing the second scores on each scoring dimension to determine the second comprehensive score of each target tag; determining the weight of each target tag based on the second comprehensive score of each target tag; and generating a passenger portrait of the target passenger based on the target tag and the weight of each target tag.

[0168] Optionally, Fig.11 is a structural block diagram of an electronic device according to an embodiment of the present application. Fig.11 As shown, the electronic device may include: one or more ( Fig.11 (only one is shown) processor 1102, memory 1104, storage controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.

[0169] Among them, the memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the method and device for generating passenger portraits in the aviation field in the embodiment of the present application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, realizing the above-mentioned method for generating passenger portraits in the aviation field. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0170] The processor can call the information and application programs stored in the memory through the transmission device to execute the above steps in the method for generating passenger portraits in the aviation field.

[0171] By adopting the embodiment of the present application, a scheme for generating passenger portraits in the aviation field is provided. By determining the information of the target passenger, wherein the target passenger is the passenger for whom the passenger portrait is to be generated in the aviation field; performing label matching in the label library according to the information of the target passenger, determining at least one preset label corresponding to the target passenger, wherein the label defined in the label library is a label for describing passenger characteristics obtained based on data in the database of the aviation field and data mining technology; determining the target label from at least one preset label according to preset rules; generating the passenger portrait of the target passenger according to the target label, the problem of low accuracy of the customer portrait generated by directly collecting the relevant labels of the passenger in the related technology is solved. In the present application, by determining the information of the target passenger in the aviation field, matching the information of the target passenger with the labels in the label library, matching to obtain at least one preset label corresponding to the target passenger, determining the target label from at least one preset label according to preset rules, and generating the passenger portrait of the target passenger according to the target label, thereby achieving the technical effect of improving the accuracy of the passenger portrait generated in the aviation field.

[0172] It can be understood by those skilled in the art that Fig.11 The structure shown is for illustration only, and the electronic device may also be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a PDA, a mobile Internet device (Mobile Internet Devices, MID), a PAD, or other terminal devices. Fig.11 The structure of the electronic device is not limited. Fig.11 More or fewer components (such as network interfaces, display devices, etc.) shown in, or having Fig.11 Different configurations are shown.

[0173] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0174] Example 4

[0175] The embodiment of the present application further provides a storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the method for generating passenger portraits in the aviation field provided in the first embodiment.

[0176] Optionally, in this embodiment, the above storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.

[0177] Optionally, in this embodiment, the storage medium is configured to store program codes for executing the following steps: determining information of a target passenger, wherein the target passenger is a passenger in the aviation field for whom a passenger portrait is to be generated; performing tag matching in a tag library based on the information of the target passenger, and determining at least one preset tag corresponding to the target passenger, wherein the tags defined in the tag library are tags for describing passenger characteristics obtained based on data in a database in the aviation field and data mining technology; determining a target tag from at least one preset tag based on preset rules; and generating a passenger portrait of the target passenger based on the target tag.

[0178] Optionally, the storage medium is also configured to store program codes for executing the following steps: before performing label matching in the label library based on the information of the target passenger, it also includes: determining the data source of the aviation field database; cleaning and integrating the data in the data source to obtain the database data; defining basic class labels based on the database data and label rules and classification standards, wherein the basic class labels at least include a basic class label name, a basic class label description, and a basic class label matching rule.

[0179] Optionally, the storage medium is also configured to store program codes for executing the following steps: before performing label matching in the label library based on the information of the target passenger, it also includes: identifying passenger groups that meet the first preset conditions based on pre-screening rules and basic class labels, wherein the pre-screening rules specify specific values ​​and ranges of basic class labels related to business needs; integrating and analyzing data information of passenger groups to obtain analysis data; defining business class labels based on the analysis data and business needs, wherein the business class labels include at least a business class label name, a business class label description, and a business class label matching rule.

[0180] Optionally, the storage medium is also configured to store program codes for executing the following steps: before performing label matching in the label library based on the information of the target passenger, it also includes: dividing the data in the database into training data and verification data; using the training data to train the machine learning algorithm to obtain a training model; evaluating the performance of the training model based on the verification data to obtain an evaluation result; adjusting the training model based on the evaluation result until a second preset condition is met to obtain a target model; based on basic class labels and business class labels, applying the target model to the data in the database to generate mining class labels, wherein the mining class labels at least include a mining class label name, a mining class label description, and a mining class label matching rule; and constructing a label library based on the basic class labels, business class labels, and mining class labels.

[0181] Optionally, the storage medium is also configured to store program code for executing the following steps: performing tag matching in a tag library based on the target passenger's information, and determining at least one preset tag corresponding to the target passenger, including: preprocessing the target passenger's information to obtain preprocessed data information; extracting passenger features in the preprocessed data information, wherein the passenger features are features related to the tags in the tag library; and determining at least one preset tag corresponding to the target passenger based on the passenger features and tag matching rules in the tag library.

[0182] Optionally, the storage medium is also configured to store program code for executing the following steps: determining a target tag from at least one preset tag according to preset rules includes: identifying compatible preset tags and incompatible preset tags in at least one preset tag; if there are incompatible preset tags in at least one preset tag, then calculating the first score on each scoring dimension for each incompatible preset tag within multiple scoring dimensions according to the scoring rules corresponding to each scoring dimension; weightedly summing the first scores on each scoring dimension to determine a first comprehensive score for each incompatible preset tag; and taking the predicted tag and the compatible preset tag with the highest first comprehensive score as the target tag.

[0183] Optionally, the storage medium is also configured to store program code for executing the following steps: after determining the target tag from at least one preset tag according to preset rules, the method also includes: calculating a second score on each scoring dimension for each target tag according to the scoring rules corresponding to each scoring dimension within multiple scoring dimensions; weighted summing the second scores on each scoring dimension to determine a second comprehensive score for each target tag; determining a weight of each target tag based on the second comprehensive score of each target tag; and generating a traveler portrait of the target traveler based on the target tag and the weight of each target tag.

[0184] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing the program steps of the method for generating passenger portraits in the aviation field.

[0185] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0186] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0187] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0188] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0189] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0190] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0191] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for generating passenger portraits in the aviation field, characterized in that: include: Determine information of a target passenger, wherein the target passenger is a passenger in the aviation field for whom a passenger profile is to be generated; Performing tag matching in a tag library according to the information of the target passenger, and determining at least one preset tag corresponding to the target passenger, wherein the tags defined in the tag library are tags used to describe passenger characteristics based on data in an aviation database and data mining technology; Determining a target tag from the at least one preset tag according to a preset rule; A traveler portrait of the target traveler is generated based on the target tag.

2. The method according to claim 1, characterized in that Before performing tag matching in the tag library according to the target passenger's information, the method further includes: Determining the data source of the database in the aviation field; Cleaning and integrating the data in the data source to obtain the data in the database; Based on the data in the database, the label rules and the classification standards, a basic class label is defined, wherein the basic class label at least includes a basic class label name, a basic class label description and a basic class label matching rule.

3. The method according to claim 2, characterized in that Before performing tag matching in the tag library according to the target passenger's information, the method further includes: Identifying a passenger group that meets a first preset condition based on a pre-screening rule and the basic class tag, wherein the pre-screening rule specifies a specific value and range of the basic class tag related to business requirements; Integrate and analyze the data information of the passenger group to obtain analysis data; Based on the analysis data and business requirements, business class tags are defined, wherein the business class tags at least include a business class tag name, a business class tag description, and a business class tag matching rule.

4. The method according to claim 3, characterized in that Before performing tag matching in the tag library according to the target passenger's information, the method further includes: Dividing the data in the database into training data and verification data; Using the training data to train a machine learning algorithm to obtain a training model; Evaluate the performance of the training model based on the verification data to obtain an evaluation result; Adjusting the training model based on the evaluation result until a second preset condition is met to obtain a target model; Based on the basic class labels and the business class labels, applying the target model to the data in the database to generate mining class labels, wherein the mining class labels at least include a mining class label name, a mining class label description, and a mining class label matching rule; The tag library is constructed based on the basic class tags, the business class tags and the mining class tags.

5. The method according to claim 1, characterized in that Performing tag matching in a tag library according to the information of the target passenger to determine at least one preset tag corresponding to the target passenger includes: Preprocessing the information of the target passenger to obtain preprocessed data information; Extracting passenger features from the preprocessed data information, wherein the passenger features are features related to the tags in the tag library; At least one preset tag corresponding to the target passenger is determined based on the passenger characteristics and the tag matching rules in the tag library.

6. The method according to claim 1, characterized in that Determining a target tag from the at least one preset tag according to a preset rule includes: identifying a compatible preset tag and an incompatible preset tag among the at least one preset tag; If there is an incompatible preset tag among the at least one preset tag, then calculating a first score in each scoring dimension for each incompatible preset tag according to a scoring rule corresponding to each scoring dimension in multiple scoring dimensions; Taking a weighted sum of the first scores on each scoring dimension, to determine a first comprehensive score for each incompatible preset tag; The predicted label with the highest first comprehensive score and the compatible preset label are used as the target label.

7. The method according to claim 6, characterized in that After determining the target tag from the at least one preset tag according to a preset rule, the method further includes: Calculating a second score on each scoring dimension for each target tag according to the scoring rules corresponding to each scoring dimension within the multiple scoring dimensions; Performing a weighted summation on the second scores of the respective scoring dimensions to determine a second comprehensive score for each target tag; Determine the weight of each target tag according to the second comprehensive score of each target tag; A traveler profile of the target traveler is generated according to the target tag and the weight of each target tag.

8. A device for generating passenger portraits in the aviation field, characterized in that: include: A first determining unit is used to determine information of a target passenger, wherein the target passenger is a passenger in the aviation field for whom a passenger portrait is to be generated; A second determining unit is configured to perform tag matching in a tag library according to the information of the target passenger, and determine at least one preset tag corresponding to the target passenger, wherein the tags defined in the tag library are tags for describing passenger characteristics obtained based on data in an aviation database and data mining technology; A third determining unit, configured to determine a target tag from the at least one preset tag according to a preset rule; The first generating unit is used to generate a passenger portrait of the target passenger according to the target tag.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored executable program, wherein when the executable program is run, the device where the computer-readable storage medium is located is controlled to execute the method for generating passenger portraits in the aviation field as described in any one of claims 1 to 7.

10. An electronic device, characterized in that: include: A memory storing an executable program; A processor, configured to run the program, wherein the program, when running, executes the method for generating a passenger portrait in the aviation field as described in any one of claims 1 to 7.

11. A computer program product comprising computer instructions, characterized in that: When the computer instructions are executed by the processor, the steps of the method for generating a passenger portrait in the aviation field as described in any one of claims 1 to 7 are implemented.

Images