CN112365062A - Method and system for mining implicit interactive features and recommending flights of civil aviation passengers - Google Patents
Method and system for mining implicit interactive features and recommending flights of civil aviation passengers Download PDFInfo
- Publication number
- CN112365062A CN112365062A CN202011271428.1A CN202011271428A CN112365062A CN 112365062 A CN112365062 A CN 112365062A CN 202011271428 A CN202011271428 A CN 202011271428A CN 112365062 A CN112365062 A CN 112365062A
- Authority
- CN
- China
- Prior art keywords
- flight
- passenger
- modeling
- feature
- mining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000002452 interceptive effect Effects 0.000 title claims abstract description 61
- 238000005065 mining Methods 0.000 title claims abstract description 47
- 238000000034 method Methods 0.000 title claims abstract description 41
- 230000010006 flight Effects 0.000 title claims abstract description 22
- 238000013528 artificial neural network Methods 0.000 claims abstract description 32
- 210000002569 neuron Anatomy 0.000 claims abstract description 7
- 238000012545 processing Methods 0.000 claims abstract description 6
- 238000012549 training Methods 0.000 claims abstract description 6
- 230000004927 fusion Effects 0.000 claims description 12
- 238000000547 structure data Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 4
- 238000005457 optimization Methods 0.000 claims description 3
- 238000012512 characterization method Methods 0.000 description 13
- 230000003993 interaction Effects 0.000 description 8
- 239000011159 matrix material Substances 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000005295 random walk Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Educational Administration (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a system for mining implicit interactive characteristics and recommending flights of civil aviation passengers, belonging to the technical field of civil aviation data processing and characterized by comprising the following steps of: step one, fine-grained modeling and establishing a grading rule; step two, GNN implicit interactive feature mining modeling, including passenger feature modeling, project feature modeling and flight score prediction; thirdly, optimizing the model by adopting a batch training method and an RMSprop method according to data acquired by civil aviation; step four, determining the weight and the offset of the neural network neurons; step five, predicting the score of the passenger non-interactive item by using the model; and step six, calculating flight comprehensive scores of the recommendable flight pool to generate a recommendation list. According to the method, the flight recommendation model is mined by constructing the civil aviation passenger implicit interactive characteristics based on the graph neural network, the passenger implicit interactive characteristics and the implicit interactive characteristics of the flight are fully mined, and the flight recommendation accuracy is improved.
Description
Technical Field
The invention belongs to the technical field of civil aviation data processing, and particularly relates to a method and a system for mining an implicit interactive characteristic of a civil aviation passenger and recommending a flight.
Background
With the improvement of living standard of people, the outgoing of airplanes is more and more common, and a large amount of interactive data lays a foundation for personalized recommendation. Emerging travel tools such as high-speed maglev trains are produced in the flood of scientific and technological development, and impact is brought to the income of airlines. The arrival of 5G provides more convenience for passengers to select aviation products on the Internet, but the information which is too rich also brings happiness trouble to the passengers, namely information overload. Potential features in the interactive data are mined, the preference of the passengers is refined, more detailed personalized service can be provided for the passengers, and therefore the business benefit of the airline company is improved. In the field of civil aviation, the personalized recommendation system can help passengers to complete information screening, so that time is saved, and passenger experience is improved. In recent years, personalized recommendation systems have been applied in the field of civil aviation. The personalized recommendation field of civil aviation comprises additional service recommendation, seat recommendation, airline recommendation and the like. The field of flight recommendation is not concerned by researchers, but the method has great potential value in the field of civil aviation by fully utilizing mass data in the big data era to provide flight recommendation service for passengers. In recent years, a neural network based on a graph structure is rapidly developed, a frame for learning a graph structure embedded representation is called a graph neural network, interaction among passenger commodities and evaluation of the commodities by passengers are typical graph structure data in a recommendation system, and a plurality of researchers recently solve the problems in the recommendation field by utilizing the advantages of the graph neural network and achieve good effects. PinSsage provides node information in a random walk neural network learning graph, GraphRec integrates social relations of graph structures to realize personalized recommendation, and NGCF learns high-level node information through high-level ranking to improve recommendation accuracy. Although the models have good effects on processing graph structure data, the text provides a new fine-grained implicit interactive feature mining model in consideration of the particularity of the field of civil aviation flight recommendation, and the establishment of the flight recommendation model based on the graph neural network and mined by the implicit interactive features of civil aviation passengers still faces challenges. (1) Considering the civil aviation field, flight numbers are generally fixed, and the registration sequence is not concerned. For passengers, flight attributes such as airline, departure time, discount fares, and main space are more of concern. (2) Aviation data does not have explicit grading (3) model framework building of implicit information extraction and fusion. Aiming at the problems, flight fine-grained modeling is adopted for flights, a scoring rule is designed, a flight recommendation model based on the graph neural network and civil aviation passenger implicit interactive feature mining is constructed, implicit interactive features between passengers and fine-grained attributes are mined, potential representations of the passengers and fine-grained flight attribute items are enriched, scoring accuracy of the passengers on non-interactive items is improved, and finally, flight recommendation is generated by integrating fine-grained attribute scoring, and accuracy of personalized recommendation is improved.
Disclosure of Invention
Technical problem
The invention aims to solve the technical problem of fully mining potential interaction characteristics between passenger flights for realizing personalized and accurate recommendation of the flights. By constructing a civil aviation passenger implicit interactive feature mining flight recommendation model based on a graph neural network, passenger implicit interactive features and implicit interactive features of flights are fully mined, and the flight recommendation accuracy is improved. Firstly, introducing flight fine-grained modeling and designing a scoring rule on the basis of a civil aviation flight recommendation field ontology; then, mining implicit interactive features between passengers and fine-grained attributes by adopting a graph neural network and embedding the implicit interactive features into an entity to obtain potential representations of effective passenger and fine-grained flight attribute items; and finally, integrating fine-grained attribute scores to obtain flight recommendation, and generating a more accurate recommendation list.
Technical scheme
The invention aims to provide a civil aviation passenger implicit interactive feature mining and flight recommendation method, which comprises the following steps:
step one, fine-grained modeling and establishing a grading rule;
step two, GNN implicit interactive feature mining modeling, including passenger feature modeling, project feature modeling and flight score prediction;
thirdly, optimizing the model by adopting a batch training method and an RMSprop method according to data acquired by civil aviation;
step four, determining the weight and the offset of the neural network neurons;
step five, predicting the score of the passenger non-interactive item by using the model;
and step six, calculating flight comprehensive scores of the recommendable flight pool to generate a recommendation list.
Preferably, the flight selection of the passengers is based on flight attributes, the flight attributes comprise airlines, takeoff time, ticket price discount and main space, and the fine granularity is divided according to attribute characteristics during fine granularity modeling; wherein the airline's edge flights are to be removed; uniformly dividing takeoff time and ticket price discount areas; and setting the main cabin according to the standard divided by the airline company.
Preferably, the graph neural network implicit feature mining potential feature extraction method is a neural network built based on graph structure data, wherein the passenger feature modeling comprises potential interactive feature fusion and passenger feature fusion.
The second purpose of the invention is to provide a civil aviation passenger implicit interactive feature mining and flight recommendation system, which comprises:
the modeling module is used for modeling in a fine granularity mode and establishing a grading rule;
the method comprises the following steps of (1) a feature mining module and GNN implicit interactive feature mining modeling, wherein the feature mining modeling comprises passenger feature modeling, project feature modeling and flight score prediction;
the optimization module adopts a batch training method and an RMSprop method to optimize the model according to data acquired by civil aviation;
the parameter determination module is used for determining the weight and the offset of the neural network neurons;
the prediction module is used for predicting the score of the passenger non-interactive item;
and the generation module calculates the flight comprehensive score of the recommendable flight pool and generates a recommendation list.
Preferably, the flight selection of the passengers is based on flight attributes, the flight attributes comprise airlines, takeoff time, ticket price discount and main space, and the fine granularity is divided according to attribute characteristics during fine granularity modeling; wherein the airline's edge flights are to be removed; uniformly dividing takeoff time and ticket price discount areas; and setting the main cabin according to the standard divided by the airline company.
Preferably, the graph neural network implicit feature mining potential feature extraction method is a neural network built based on graph structure data, wherein the passenger feature modeling comprises potential interactive feature fusion and passenger feature fusion.
The third invention of the patent aims to provide a computer program for realizing the mining of the implicit interactive characteristics of civil aviation passengers and the flight recommendation method.
The fourth invention of the patent aims to provide an information data processing terminal for realizing the mining of the implicit interactive characteristics of civil aviation passengers and the flight recommendation method.
A fifth object of the present invention is to provide a computer-readable storage medium, comprising instructions which, when run on a computer, cause the computer to perform the above-mentioned civil aviation passenger implicit interactive feature mining and flight recommendation method.
The invention has the advantages and positive effects that:
by adopting the technical scheme, the invention has the following technical effects:
the method adopts the PNR data provided by the Chinese letter to perform fine-grained modeling on the flight booking data, so that personalized accurate recommendation is realized, and the potential interaction characteristics among the passenger flights should be fully mined. The map neural network-based civil aviation passenger implicit interactive feature mining flight recommendation model fully mines passenger implicit interactive features and implicit interactive features of flights, and improves flight recommendation accuracy.
Drawings
FIG. 1 is a flow chart of a preferred embodiment of the present invention;
FIG. 2 is a diagram of potential interaction feature fusion;
FIG. 3 is a diagram of a passenger potential characterization neural network;
FIG. 4 is a graph of a scoring prediction neural network;
FIG. 5 is a passenger-project interaction diagram.
Detailed Description
In order to further understand the contents, features and effects of the present invention, the following embodiments are illustrated and described in detail with reference to the accompanying drawings.
Aiming at the problem of overload of flight information of civil aviation passengers, the method related by the invention introduces flight fine-grained modeling and designs scoring rules on the basis of a civil aviation flight recommendation field ontology; then, mining implicit interactive features between passengers and fine-grained attributes by adopting a graph neural network and embedding the implicit interactive features into an entity to obtain potential representations of effective passenger and fine-grained flight attribute items; and finally, integrating fine-grained attribute scores to obtain flight recommendation, and generating a more accurate recommendation list with interpretability.
Referring to fig. 1 to 5 of the drawings,
a civil aviation passenger implicit interactive feature mining and flight recommendation method comprises the following steps:
the method comprises the following steps: fine-grained modeling and establishing a grading rule. The number of airlines is first counted. The study data is provided by a pilot, and by statistics, there are some airlines and few passengers select their flights, thus filtering out this part of airlines. The number of airlines is finally 20, so only the passenger preferences for these 20 airlines are taken into account. For the takeoff time attribute, 4 hours is taken as a time period herein, and one day is divided into 6 time periods, namely 00: 00-04: 00, 04: 00-08: 00, 08: 00-12: 00, 12: 00-16: 00, 16: 00-20: 00, 20: 00-00: 00, the model mines passenger preferences for 6 time periods. The discount attributes mainly include nine of 3 folds or less, 3 folds, 4 folds, 5 folds, 6 folds, 7 folds, 8 folds, 9 folds and full price. As for the main bay attributes, four types C, F, W and Y are found statistically, so only these four bays need to be modeled. Calculating specific scores according to the attribute ratios, wherein the scoring standards are shown in the table 1:
TABLE 1 Scoring standards
Ratio of a | Scoring |
Over 85 percent | 5 |
65%~85% | 4 |
50%~65% | 3 |
25%~50% | 2 |
Less than 25% | 1 |
For example, traveler A purchased 10 tickets, of which 5 are airlines with ID 110; 3 airlines with ID 129, 1 airline with ID 138; 1 is an airline with an ID of 220. The proportion of 110 airlines is 50%, the passenger A scores 3 points for 110 airlines; if the 129 airlines account for 30%, the passenger A scores 2 for the 129 airlines; 138 airlines account for 10%, passenger a scores 1 for 138 airlines and 1 for 220 airlines. The same method can calculate the grade of the passenger A to the cabin space, discount and travel time. The original flight booking data is processed into the form of < passenger ID, project ID, score >, and the projects studied herein include airline, departure time, discount of fare and main space. The item ID of 1-20 represents 20 airlines; 21-26 represent six travel times; 27-35 represent nine fare discounts; 36-39 represent four bays. And calculating the grade of the passenger for the project according to the grade calculation rule. The form of < passenger ID, item ID, score > is obtained as the initial input data for the model.
Step two: and (4) carrying out GNN implicit interactive feature mining modeling.
(a) And modeling passenger characteristics. Passenger feature modeling requires fusing of the project features that the passenger has interacted with, as shown in fig. 3. The passenger potential characterization integrates a passenger ID embedded characterization, an interacted project ID embedded characterization and a grading embedded characterization of the interacted project ID, and a passenger model is constructed by the following mathematical expressions:
in the formula: e.g. of the typeuPassenger ID embedded token vector, W, b are weights and bias quantities in the neural network, which corresponds to a matrix operation at the matrix element level,is a potential factor vector that incorporates the items that the passenger has interacted with.
(b) And (4) modeling project characteristics. Similar to passenger modeling, the term potential characterization fuses a term ID embedded characterization, an interacted passenger embedded characterization and a grade embedded characterization of a passenger generating an interaction relation to the term, and a characterization formula constructed by a term model is as follows:
in the formula: e.g. of the typejItem ID embedded token vector, W, b weight and bias vector in neural network, matrix operation at matrix element level, Yagg_uIs a passenger potential factor vector fused with the interaction of the project, and the mathematical expression is as follows:
in the formula:is the set of passengers with item j interacted with, βjbIs a weight factor of the item j and the interacted passenger b, which is determined between the item j and the interacted passenger bAre equal and all equal toYjbThe potential characterization vector of passenger b representing the interacted item j and the interaction potential characterization of the potential characterization vector of the score of the passenger for the item. The mathematical representation is as follows:
in the formula:is a matrix splicing operation, and the function g is used for fusing a passenger potential factor ebAnd the evaluation potential factor e of the passenger b on the projectrThe multilayer perceptron of (1).
(c) And (4) score prediction. Fusing passenger potential factors obtained by passenger modeling and project potential factors obtained by project modeling, feeding the fused passenger potential factors and project potential factors into a multilayer perceptron neural network, and finally outputting neurons to obtain score prediction
A civil aviation passenger implicit interactive feature mining and flight recommendation system comprises:
the modeling module is used for modeling in a fine granularity mode and establishing a grading rule;
the method comprises the following steps of (1) a feature mining module and GNN implicit interactive feature mining modeling, wherein the feature mining modeling comprises passenger feature modeling, project feature modeling and flight score prediction;
the optimization module adopts a batch training method and an RMSprop method to optimize the model according to data acquired by civil aviation;
the parameter determination module is used for determining the weight and the offset of the neural network neurons;
the prediction module is used for predicting the score of the passenger non-interactive item;
and the generation module calculates the flight comprehensive score of the recommendable flight pool and generates a recommendation list.
The method comprises the following steps that a passenger selects flights according to flight attributes, wherein the flight attributes comprise an airline company, take-off time, ticket price discount and a main cabin space, and attribute characteristics are divided according to fine granularity during fine-grained modeling; wherein the airline's edge flights are to be removed; uniformly dividing takeoff time and ticket price discount areas; and setting the main cabin according to the standard divided by the airline company.
The latent feature extraction method for hidden feature mining of the graph neural network is a neural network built based on graph structure data, wherein passenger feature modeling comprises latent interactive feature fusion and passenger feature fusion.
A computer program for realizing the mining and flight recommendation method for the civil aviation passenger implicit interactive characteristics is provided.
An information data processing terminal for realizing the mining and flight recommendation method for the implicit interactive characteristics of the civil aviation passengers.
A computer-readable storage medium comprising instructions which, when executed on a computer, cause the computer to perform the above-described method of civil aviation passenger implicit interactive feature mining and flight recommendation.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When used in whole or in part, can be implemented in a computer program product that includes one or more computer instructions. When loaded or executed on a computer, cause the flow or functions according to embodiments of the invention to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, the computer instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center via wire (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL), or wireless (e.g., infrared, wireless, microwave, etc.)). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that includes one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
The above description is only for the preferred embodiment of the present invention, and is not intended to limit the present invention in any way, and all simple modifications, equivalent changes and modifications made to the above embodiment according to the technical spirit of the present invention are within the scope of the technical solution of the present invention.
Claims (9)
1. A civil aviation passenger implicit interactive feature mining and flight recommendation method is characterized by comprising the following steps:
step one, fine-grained modeling and establishing a grading rule;
step two, GNN implicit interactive feature mining modeling, including passenger feature modeling, project feature modeling and flight score prediction;
thirdly, optimizing the model by adopting a batch training method and an RMSprop method according to data acquired by civil aviation;
step four, determining the weight and the offset of the neural network neurons;
step five, predicting the score of the passenger non-interactive item by using the model;
and step six, calculating flight comprehensive scores of the recommendable flight pool to generate a recommendation list.
2. The method for mining the implicit interactive characteristics of the civil aviation passengers and recommending the flights according to claim 1, wherein the selection of the flights by the passengers is based on flight attributes, the flight attributes comprise airlines, takeoff time, discount of fare price and main space, and the attribute characteristics are divided in a fine-grained mode; wherein the airline's edge flights are to be removed; uniformly dividing takeoff time and ticket price discount areas; and setting the main cabin according to the standard divided by the airline company.
3. The method for mining implicit interactive features and recommending flights of civil aviation passengers according to claim 1, characterized in that the method for extracting the implicit features of the graph neural network based on the graph structure data is a neural network built based on graph structure data, wherein the passenger feature modeling comprises potential interactive feature fusion and passenger feature fusion.
4. A civil aviation passenger implicit interactive feature mining and flight recommendation system is characterized by comprising:
the modeling module is used for modeling in a fine granularity mode and establishing a grading rule;
the method comprises the following steps of (1) a feature mining module and GNN implicit interactive feature mining modeling, wherein the feature mining modeling comprises passenger feature modeling, project feature modeling and flight score prediction;
the optimization module adopts a batch training method and an RMSprop method to optimize the model according to data acquired by civil aviation;
the parameter determination module is used for determining the weight and the offset of the neural network neurons;
the prediction module is used for predicting the score of the passenger non-interactive item;
and the generation module calculates the flight comprehensive score of the recommendable flight pool and generates a recommendation list.
5. The system for mining and recommending flights according to implicit interactive features of civil aviation passengers as claimed in claim 4, wherein the selection of flights by passengers is based on flight attributes, the flight attributes include airline, departure time, discount of fare and main space, and are divided in fine granularity according to attribute features during fine granularity modeling; wherein the airline's edge flights are to be removed; uniformly dividing takeoff time and ticket price discount areas; and setting the main cabin according to the standard divided by the airline company.
6. The civil aviation passenger implicit interactive feature mining and flight recommendation system according to claim 4, wherein the graph neural network implicit feature mining potential feature extraction method is a neural network built based on graph structure data, and passenger feature modeling comprises potential interactive feature fusion and passenger feature fusion.
7. A computer program for implementing the method for mining implicit interactive features and recommending flights for civil aviation passengers according to any of claims 1 to 3.
8. An information data processing terminal for implementing the mining and flight recommendation method for the implicit interactive characteristics of civil aviation passengers as claimed in any one of claims 1 to 3.
9. A computer-readable storage medium comprising instructions which, when run on a computer, cause the computer to perform the civil aviation passenger implicit interactive feature mining and flight recommendation method of any one of claims 1 to 3.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011271428.1A CN112365062A (en) | 2020-11-13 | 2020-11-13 | Method and system for mining implicit interactive features and recommending flights of civil aviation passengers |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011271428.1A CN112365062A (en) | 2020-11-13 | 2020-11-13 | Method and system for mining implicit interactive features and recommending flights of civil aviation passengers |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112365062A true CN112365062A (en) | 2021-02-12 |
Family
ID=74515594
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011271428.1A Pending CN112365062A (en) | 2020-11-13 | 2020-11-13 | Method and system for mining implicit interactive features and recommending flights of civil aviation passengers |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112365062A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113590933A (en) * | 2021-06-07 | 2021-11-02 | 海南太美航空股份有限公司 | Flight pushing method and system and electronic equipment |
CN114595518A (en) * | 2022-03-09 | 2022-06-07 | 中国民航大学 | Commercial space flight and civil aviation operation cooperative system based on digital twin |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111429234A (en) * | 2020-04-16 | 2020-07-17 | 电子科技大学中山学院 | Deep learning-based commodity sequence recommendation method |
CN111681067A (en) * | 2020-04-17 | 2020-09-18 | 清华大学 | Long-tail commodity recommendation method and system based on graph attention network |
CN111695965A (en) * | 2020-04-26 | 2020-09-22 | 清华大学 | Product screening method, system and equipment based on graph neural network |
CN111784455A (en) * | 2020-06-30 | 2020-10-16 | 腾讯科技(深圳)有限公司 | Article recommendation method and recommendation equipment |
CN111815415A (en) * | 2020-07-14 | 2020-10-23 | 北京邮电大学 | Commodity recommendation method, system and equipment |
-
2020
- 2020-11-13 CN CN202011271428.1A patent/CN112365062A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111429234A (en) * | 2020-04-16 | 2020-07-17 | 电子科技大学中山学院 | Deep learning-based commodity sequence recommendation method |
CN111681067A (en) * | 2020-04-17 | 2020-09-18 | 清华大学 | Long-tail commodity recommendation method and system based on graph attention network |
CN111695965A (en) * | 2020-04-26 | 2020-09-22 | 清华大学 | Product screening method, system and equipment based on graph neural network |
CN111784455A (en) * | 2020-06-30 | 2020-10-16 | 腾讯科技(深圳)有限公司 | Article recommendation method and recommendation equipment |
CN111815415A (en) * | 2020-07-14 | 2020-10-23 | 北京邮电大学 | Commodity recommendation method, system and equipment |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113590933A (en) * | 2021-06-07 | 2021-11-02 | 海南太美航空股份有限公司 | Flight pushing method and system and electronic equipment |
CN114595518A (en) * | 2022-03-09 | 2022-06-07 | 中国民航大学 | Commercial space flight and civil aviation operation cooperative system based on digital twin |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR101871747B1 (en) | Similarity tendency based user-sightseeing recommendation system and method thereof | |
US11574201B2 (en) | Enhancing evolutionary optimization in uncertain environments by allocating evaluations via multi-armed bandit algorithms | |
US20150242927A1 (en) | Method and system of an online travel website | |
EP3742356A1 (en) | Information processing device, information processing method and program | |
Carlos Martín et al. | Willingness to pay for airline service quality | |
Lawrence et al. | Passenger-based predictive modeling of airline no-show rates | |
Al-Sharif et al. | Automated optimal design methodology of elevator systems using rules and graphical methods (the HARint plane) | |
CN111709810A (en) | Object recommendation method and device based on recommendation model | |
CN112365062A (en) | Method and system for mining implicit interactive features and recommending flights of civil aviation passengers | |
CN108491511A (en) | Data digging method and device, model training method based on diagram data and device | |
CN112507196A (en) | Training method, search ordering method, device and equipment of fusion ordering model | |
Duran et al. | Robust airline scheduling with controllable cruise times and chance constraints | |
Koo et al. | The effect of enhanced international air access on the demand for peripheral tourism destinations: Evidence from air itinerary choice behaviour of Korean visitors to Australia | |
Jiang et al. | Forecast and analysis of aircraft passenger satisfaction based on RF-RFE-LR model | |
Dandapat et al. | An approach for identifying optimal service for rural bus routes | |
Pan et al. | Costly price adjustment and automated pricing: The case of Airbnb | |
CN107784387A (en) | The continuous dynamic prediction method that a kind of microblogging event information is propagated | |
Abdelghany et al. | An integrated reinforced learning and network competition analysis for calibrating airline itinerary choice models with constrained demand | |
CN113672818B (en) | Method and system for acquiring social media user portraits | |
Hjorth et al. | Joint overbooking and seat allocation for fare families | |
Qiang et al. | New boarding strategies for a novel aircraft cabin installed with side-slip seats | |
US7801757B2 (en) | Computer implemented customer value model in airline industry | |
Urban et al. | Mapping causalities of airline dynamics in long-haul air transport markets | |
Gao et al. | Three-stage decision approach of network dynamic pricing and seat inventory control | |
Huang et al. | Two new prediction-driven approaches to discrete choice prediction |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210212 |
|
RJ01 | Rejection of invention patent application after publication |