CN111899059A - Navigation driver revenue management dynamic pricing method based on block chain - Google Patents
Navigation driver revenue management dynamic pricing method based on block chain Download PDFInfo
- Publication number
- CN111899059A CN111899059A CN202010808770.4A CN202010808770A CN111899059A CN 111899059 A CN111899059 A CN 111899059A CN 202010808770 A CN202010808770 A CN 202010808770A CN 111899059 A CN111899059 A CN 111899059A
- Authority
- CN
- China
- Prior art keywords
- data
- model
- cabin
- passenger
- block chain
- 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
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000004458 analytical method Methods 0.000 claims abstract description 20
- 238000013135 deep learning Methods 0.000 claims abstract description 13
- 230000006399 behavior Effects 0.000 claims description 33
- 238000004422 calculation algorithm Methods 0.000 claims description 25
- 238000012549 training Methods 0.000 claims description 19
- 230000007246 mechanism Effects 0.000 claims description 15
- 238000005457 optimization Methods 0.000 claims description 11
- 230000008859 change Effects 0.000 claims description 10
- 230000000694 effects Effects 0.000 claims description 7
- 238000011156 evaluation Methods 0.000 claims description 7
- 238000013528 artificial neural network Methods 0.000 claims description 6
- 238000004140 cleaning Methods 0.000 claims description 6
- 238000007405 data analysis Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 6
- 238000009826 distribution Methods 0.000 claims description 5
- 230000010006 flight Effects 0.000 claims description 4
- 230000035945 sensitivity Effects 0.000 claims description 4
- 230000003321 amplification Effects 0.000 claims description 3
- 238000010835 comparative analysis Methods 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 238000010219 correlation analysis Methods 0.000 claims description 3
- 238000004836 empirical method Methods 0.000 claims description 3
- 238000011985 exploratory data analysis Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 235000012054 meals Nutrition 0.000 claims description 3
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000007637 random forest analysis Methods 0.000 claims description 3
- 230000003068 static effect Effects 0.000 claims description 3
- 238000012706 support-vector machine Methods 0.000 claims description 3
- 238000013075 data extraction Methods 0.000 abstract description 3
- 238000007726 management method Methods 0.000 description 14
- 238000005516 engineering process Methods 0.000 description 4
- 238000010276 construction Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000006467 substitution reaction Methods 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/27—Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/64—Protecting data integrity, e.g. using checksums, certificates or signatures
-
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0206—Price or cost determination based on market factors
-
- 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
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- General Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Bioethics (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Computer Hardware Design (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Tourism & Hospitality (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a block chain-based navigation driver revenue management dynamic pricing method, which comprises the following steps of: s1, constructing a big data platform based on the block chain; s2, constructing a cabin price prediction model by using the big data platform, and predicting the cabin price; s3, taking the cabin price prediction result as input data, and constructing a dynamic pricing model; s4, building a personalized product recommendation model based on deep learning by combining passenger characteristic information provided by the passenger portrait; and S5, optimizing and evaluating the personalized product recommendation model to obtain a yield management decision. According to the invention, the block chain and the big data platform are fused, and a protected data source is provided, so that the data extraction becomes safe and reliable, and the prediction precision of the cabin price is improved; in addition, based on deep learning, through passenger portrait and demand statistics analysis customer demand, realize the accurate capture of target customer crowd's income, satisfy the decision-making needs of actual airline and airport and policy.
Description
Technical Field
The invention relates to the technical field of block chains, in particular to a block chain-based navigation department revenue management dynamic pricing method.
Background
The income management is a process that an airline company selectively accepts passengers of various types to maximize income, is a computer management system integrating manpower and technology, and can estimate demand probability distribution curves of different fares and different slots of each flight through a flight income maximization decision model so as to determine stock control and discount fares and maximize the income.
The key of dynamic pricing lies in maximizing revenue of an airline company through a pricing strategy and determining the optimal time of price change by using a proper method, but most of research is concentrated on revenue management of inventory allocation at present, but the revenue management methods based on price decision are relatively few, and the traditional cabin control model has the defects of limitation on applicability of multiple fare levels and the like because the behavior selected by passengers is not considered, and in addition, the domestic revenue management system has certain defects on data storage and data utilization, and a safer mode is needed for data storage.
Disclosure of Invention
In order to solve the problems, the invention provides a block chain-based navigation driver revenue management dynamic pricing method.
The invention adopts the following technical scheme:
a navigation driver revenue management dynamic pricing method based on a block chain comprises the following steps:
s1, constructing a big data platform based on the block chain;
s2, constructing a cabin price prediction model by using the big data platform, and predicting the cabin price;
s3, taking the cabin price prediction result as input data, and constructing a dynamic pricing model;
s4, building a personalized product recommendation model based on deep learning by combining passenger characteristic information provided by the passenger portrait;
and S5, optimizing and evaluating the personalized product recommendation model to obtain a yield management decision.
Further, the big data platform based on the block chain comprises a block chain consisting of a data layer, a network layer, a consensus layer, an application layer, a contract layer and an incentive layer, wherein the data layer comprises a chain structure, a timestamp, asymmetric encryption, a hash function, an aviation sales data block and an aviation passenger information block, the network layer comprises a P2P network, a propagation mechanism and a verification mechanism, the consensus layer comprises a dynamic data consensus algorithm and a static data consensus algorithm, the application layer comprises an individual user, a government department and an enterprise user, the contract layer comprises a script code, an algorithm mechanism and an intelligent contract, and the incentive layer comprises a resource providing mechanism and a resource adjusting mechanism.
Further, the specific steps of constructing the cabin price prediction model are as follows:
s21, analyzing and processing the air ticket data: extracting relevant data for constructing a cabin price prediction model from the flight basic information table and the historical data of the flight fare information table; through exploratory analysis, the distribution condition and the importance of passengers on labels such as comfort degree, basic attribute, time sequence characteristic and other additional attribute data are explored; extracting main characteristics possibly influencing the pricing of the fare of the airplane by carrying out preliminary data cleaning and correlation analysis on the original data, and classifying the main characteristics into comfort degree, traffic attributes or time characteristics;
s22, improving the prediction algorithm: combining five models of random forests, support vector machines, gradient lifting trees, artificial neural networks and deep learning into a strong learner to carry out comprehensive learning and judgment; the data set of model training is divided into a training set and a verification set, and the training and the tuning of the model are carried out on the training set; the model is analyzed and calculated by adopting a gradient lifting tree algorithm; the index of evaluation isR mapping goodness of fit of model2And the absolute value of the deviation of all individual observations from the arithmetic mean;
s23, implementation of the cabin price prediction model: importing training set data into a model for training, and adjusting corresponding parameters of an algorithm to achieve the optimal parameters; diagnosing the trained model by using the evaluation indexes, and judging the fitting state of the trained model; carrying out further optimization on the diagnosed model, diagnosing the optimized new model again, and repeatedly iterating and continuously approaching to achieve the optimal state;
s24, price prediction is carried out by utilizing the built cabin price prediction model, the prediction result is stored in a big data platform, the model effect is evaluated through the business indexes of passenger behaviors or enterprise profits and the operation indexes of online operation speed, resource consumption degree and stability of the model, the business indexes of the passenger behaviors comprise high evaluation rate, the business indexes of the enterprise profits comprise profit, high probability and passenger source amplification, the online operation speed of the model is time complexity, and the resource consumption degree is space complexity.
Further, the building of the dynamic pricing model specifically includes:
s31, preprocessing data: extracting a prediction result of the cabin price prediction model from a big data platform as input data, wherein the input data comprises four types: TCN data, INV data, flight information data of the co-flying company and other basic data, and the data cleaning is carried out on the input data, and the non-limiting processing is carried out on the historical booking data;
s32, prediction: selecting a prediction model with the best effect in the current period from the cabin price prediction models, extracting historical cabin or ticket outlet people flow statistical data, estimating the whole market demand scale by adopting an empirical method and a joint estimation method, performing prediction correction on data loss, correcting the prediction data provided by a cabin price prediction module, performing price optimization by combining passenger behavior analysis, and obtaining a passenger sensitivity behavior analysis result through passenger portrait and demand statistics;
s33, solving the dynamic pricing model: the optimal strategy of the control cabin is actively controlled by utilizing an optimal solution algorithm, and meanwhile, manual intervention measures are taken, wherein the manual intervention comprises the consideration of suboptimal targets and the control adjustment of rules,
s34, outputting the result: and obtaining an output result by the dynamic pricing model, wherein the output result comprises a cabin position control cabin instruction and an analysis chart, the cabin position control cabin instruction is used for cabin position control, cabin position opening quantity change and cabin position nesting change, the analysis chart comprises a data analysis chart and a flight early warning chart, the data analysis chart provides a sale price curve for the navigation department, and the flight early warning chart provides seat booking and capacity change warning for the navigation department.
Further, the TCN data includes flight booking data including historical data for estimating market demand and real-time data for performing a comparably comparative analysis; the INV data comprises bay data comprising historical data for estimating market demand and real-time data for supporting subsequent algorithm decisions; the flight information data of the co-flight company and other basic data mainly describe basic information related to flights, including flight numbers, moments, machine types, real-time freight rates and flight basic cabin freight rate tables, and the INV data are further processed to generate passenger seat rate data and output to be a flight passenger seat rate growth curve for airline revenue assessment of a navigation department.
Further, the personalized product recommendation model is modeled by combining passenger characteristic information provided by the passenger portrait, deep learning modeling is performed by adopting a deep cyclic neural network and a convolutional network during modeling, and finally a commodity recommendation list is generated.
Further, the passenger portrait is a customer portrait of an airline passenger, and comprises demographic attributes, ticket buying behaviors, check-in behaviors and boarding behaviors, wherein the demographic attributes comprise the sex, age, source of the passenger, occupation and cultural degree of the customer; the ticket buying behavior comprises a ticket buying advance, a ticket buying channel and a ticket refunding and changing condition; the check-in behavior comprises a check-in mode; the boarding behaviors include a boarding period, a boarding moment, a boarding seat, a boarding cabin space, and meal preferences.
After adopting the technical scheme, compared with the background technology, the invention has the following advantages:
the navigation driver profit management dynamic pricing method solves the data security problem by utilizing a decentralized bottom database which is a block chain technology, fuses a block chain and a large data platform, provides a protected data source, ensures that data extraction becomes safe and reliable, and improves the prediction precision of the cabin price; help model implementation optimization while maintaining data privacy and security; a multi-dimensional and multi-angle analysis is provided by a revenue system considering various service scenes, so that the statistical analysis is conveniently carried out on the result, the personnel are assisted to make the next-stage plan, and the previous complex manual operation is reduced; in addition, based on deep learning, through passenger portrait and demand statistics analysis customer demand, realize the accurate capture of target customer crowd's income, satisfy the decision-making needs of actual airline and airport and policy.
Drawings
FIG. 1 is a flow chart of the operation of the present invention;
FIG. 2 is a block chain based basic architecture diagram of a large data platform;
FIG. 3 is a diagram of a dynamic pricing model.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Examples
As shown in fig. 1, a block chain-based airline driver revenue management dynamic pricing method includes the following steps:
s1, constructing a big data platform based on the block chain;
s2, constructing a cabin price prediction model by using the big data platform, and predicting the cabin price;
s3, taking the cabin price prediction result as input data, and constructing a dynamic pricing model;
s4, building a personalized product recommendation model based on deep learning by combining passenger characteristic information provided by the passenger portrait;
and S5, optimizing and evaluating the personalized product recommendation model to obtain a yield management decision.
As shown in fig. 2, the big data platform based on the block chain comprises a block chain consisting of a data layer, a network layer, a consensus layer, an application layer, a contract layer and an incentive layer, wherein the data layer comprises a chain structure, a timestamp, asymmetric encryption, a hash function, an aviation sales data block and an aviation passenger information block, the network layer comprises a P2P network, a propagation mechanism and a verification mechanism, the consensus layer comprises a dynamic data consensus algorithm and a static data consensus algorithm, the application layer comprises an individual user, a government department and an enterprise user, the contract layer comprises a script code, an algorithm mechanism and an intelligent contract, and the incentive layer comprises a resource providing mechanism and a resource adjusting mechanism.
The big information data such as the airline flights has the characteristics of multiple scenes, large data volume, complex structure and difficulty in collection and integration. For the model construction driven by big data, no matter the algorithm development in the early stage or the optimization iteration in the later stage, the model construction needs to be completed through a large amount of data collection and training. Under the condition that modeling needs to be carried out by combining different trip scene data, a big data architecture for guaranteeing safety and privacy is needed. The blockchain is used as a decentralized bottom database to solve the safety problem: it will enable information security techniques to be consolidated and enhanced from this, which has never been done before, helping to achieve optimization of all models.
The specific steps of constructing the cabin price prediction model are as follows:
s21, analyzing and processing the air ticket data: extracting relevant data for constructing a cabin price prediction model from the flight basic information table and the historical data of the flight fare information table; through exploratory analysis, the distribution condition and the importance of passengers on labels such as comfort degree, basic attribute, time sequence characteristic and other additional attribute data are explored; extracting main characteristics possibly influencing the pricing of the fare of the airplane by carrying out preliminary data cleaning and correlation analysis on the original data, and classifying the main characteristics into comfort degree, traffic attributes or time characteristics;
s22, improving the prediction algorithm: combining five models of random forests, support vector machines, gradient lifting trees, artificial neural networks and deep learning into a strong learner to carry out comprehensive learning and judgment; the data set of model training is divided into a training set and a verification set, and the training and the tuning of the model are carried out on the training set; the model is analyzed and calculated by adopting a gradient lifting tree algorithm; the index evaluated is R reflecting the goodness of fit of the model2And the absolute value of the deviation of all individual observations from the arithmetic mean;
s23, implementation of the cabin price prediction model: importing training set data into a model for training, and adjusting corresponding parameters of an algorithm to achieve the optimal parameters; diagnosing the trained model by using the evaluation indexes, and judging the fitting state of the trained model; carrying out further optimization on the diagnosed model, diagnosing the optimized new model again, and repeatedly iterating and continuously approaching to achieve the optimal state;
s24, price prediction is carried out by utilizing the built cabin price prediction model, the prediction result is stored in a big data platform, the model effect is evaluated through the business indexes of passenger behaviors or enterprise profits and the operation indexes of online operation speed, resource consumption degree and stability of the model, the business indexes of the passenger behaviors comprise high evaluation rate, the business indexes of the enterprise profits comprise profit, high probability and passenger source amplification, the online operation speed of the model is time complexity, and the resource consumption degree is space complexity.
The method predicts the specific price of the air ticket of the given air route at one month or a plurality of time points in the future, and has great positive promotion effect on grasping the market trend of the airline company and adjusting the strategy in time. The air ticket price prediction research has special complexity, which is reflected in the volatility: frequently fluctuating along with time evolution, leading hidden factors (remaining seat number of flight, sales condition and the like), diversity: the prices of different flight routes exhibit a high diversity even at the same point in time, and the distribution and the law followed of the ticket prices as time-sensitive data also vary over time. Therefore, when a cabin price prediction model is constructed, the prediction calculation is improved, and various models are combined into a strong learner by utilizing the idea of integrated learning to carry out comprehensive learning and judgment, so that the accuracy of the model is improved.
As shown in fig. 3, the building of the dynamic pricing model specifically includes:
s31, preprocessing data: extracting a prediction result of the cabin price prediction model from a big data platform as input data, wherein the input data comprises four types: TCN data, INV data, flight information data of the co-flying company and other basic data, and the data cleaning is carried out on the input data, and the non-limiting processing is carried out on the historical booking data;
s32, prediction: selecting a prediction model with the best effect in the current period from the cabin price prediction models, extracting historical cabin or ticket outlet people flow statistical data, estimating the whole market demand scale by adopting an empirical method and a joint estimation method, performing prediction correction on data loss, correcting the prediction data provided by a cabin price prediction module, performing price optimization by combining passenger behavior analysis, and obtaining a passenger sensitivity behavior analysis result through passenger portrait and demand statistics;
s33, solving the dynamic pricing model: the optimal strategy of the control cabin is actively controlled by utilizing an optimal solution algorithm, and meanwhile, manual intervention measures are taken, wherein the manual intervention comprises the consideration of suboptimal targets and the control adjustment of rules,
s34, outputting the result: and obtaining an output result by the dynamic pricing model, wherein the output result comprises a cabin position control cabin instruction and an analysis chart, the cabin position control cabin instruction is used for cabin position control, cabin position opening quantity change and cabin position nesting change, the analysis chart comprises a data analysis chart and a flight early warning chart, the data analysis chart provides a sale price curve for the navigation department, and the flight early warning chart provides seat booking and capacity change warning for the navigation department.
In the dynamic pricing model, price optimization is carried out by combining passenger behavior analysis, behavior analysis results such as passenger sensitivity and the like are obtained through analysis of passenger portraits, flexible manual intervention measures are taken, suboptimal objectives are considered, control and adjustment of rules are achieved, intelligent cabin control is achieved, output results are obtained through the dynamic pricing model, flight quantity of a navigation department in a long time span is managed systematically, real-time price information is provided for the navigation department, a price list and an opening instruction file are generated, and the real-time price information is uploaded to a background for the navigation department to sell in the market.
The TCN data comprises flight booking data comprising historical data for estimating market demand and real-time data for performing a comparably comparative analysis; the INV data comprises bay data comprising historical data for estimating market demand and real-time data for supporting subsequent algorithm decisions; the flight information data of the co-flight company and other basic data mainly describe basic information related to flights, including flight numbers, moments, machine types, real-time freight rates and flight basic cabin freight rate tables, and the INV data are further processed to generate passenger seat rate data and output to be a flight passenger seat rate growth curve for airline revenue assessment of a navigation department.
The personalized product recommendation model is modeled by combining passenger characteristic information provided by the passenger portrait, deep learning modeling is carried out by adopting a deep circulation neural network and a convolution network during modeling, and finally a commodity recommendation list is generated.
The passenger portrait is a customer portrait of an aviation passenger, and comprises demographic attributes, ticket buying behaviors, check-in behaviors and airplane riding behaviors, wherein the demographic attributes comprise sex, age, passenger source, occupation and cultural degree of the customer; the ticket buying behavior comprises a ticket buying advance, a ticket buying channel and a ticket refunding and changing condition; the check-in behavior comprises a check-in mode; the boarding behaviors include a boarding period, a boarding moment, a boarding seat, a boarding cabin space, and meal preferences.
The aviation department revenue management dynamic pricing method of the embodiment solves the data security problem by utilizing a decentralized bottom database, namely a block chain technology, and fuses a block chain and a large data platform to provide a protected data source, so that data extraction becomes safe and reliable, and the prediction precision of the cabin price is improved; help model implementation optimization while maintaining data privacy and security; a multi-dimensional and multi-angle analysis is provided by a revenue system considering various service scenes, so that the statistical analysis is conveniently carried out on the result, the personnel are assisted to make the next-stage plan, and the previous complex manual operation is reduced; in addition, based on deep learning, through passenger portrait and demand statistics analysis customer demand, realize the accurate capture of target customer crowd's income, satisfy the decision-making needs of actual airline and airport and policy.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (7)
1. A navigation department revenue management dynamic pricing method based on a block chain is characterized in that: the method comprises the following steps:
s1, constructing a big data platform based on the block chain;
s2, constructing a cabin price prediction model by using the big data platform, and predicting the cabin price;
s3, taking the cabin price prediction result as input data, and constructing a dynamic pricing model;
s4, building a personalized product recommendation model based on deep learning by combining passenger characteristic information provided by the passenger portrait;
and S5, optimizing and evaluating the personalized product recommendation model to obtain a yield management decision.
2. The block chain-based airline department revenue management dynamic pricing method of claim 1, wherein: the big data platform based on the block chain comprises a block chain consisting of a data layer, a network layer, a consensus layer, an application layer, a contract layer and an incentive layer, wherein the data layer comprises a chain structure, a timestamp, asymmetric encryption, a hash function, an aviation sales data block and an aviation passenger information block, the network layer comprises a P2P network, a propagation mechanism and a verification mechanism, the consensus layer comprises a dynamic data consensus algorithm and a static data consensus algorithm, the application layer comprises an individual user, a government department and an enterprise user, the contract layer comprises a script code, an algorithm mechanism and an intelligent contract, and the incentive layer comprises a resource providing mechanism and a resource adjusting mechanism.
3. The block chain-based airline department revenue management dynamic pricing method of claim 1, wherein: the specific steps of constructing the cabin price prediction model are as follows:
s21, analyzing and processing the air ticket data: extracting relevant data for constructing a cabin price prediction model from the flight basic information table and the historical data of the flight fare information table; through exploratory analysis, the distribution condition and the importance of passengers on labels such as comfort degree, basic attribute, time sequence characteristic and other additional attribute data are explored; extracting main characteristics possibly influencing the pricing of the fare of the airplane by carrying out preliminary data cleaning and correlation analysis on the original data, and classifying the main characteristics into comfort degree, traffic attributes or time characteristics;
s22, improving the prediction algorithm: combining five models of random forests, support vector machines, gradient lifting trees, artificial neural networks and deep learning into a strong learner to carry out comprehensive learning and judgment; the data set of model training is divided into a training set and a verification set, and the training and the tuning of the model are carried out on the training set; the model is analyzed and calculated by adopting a gradient lifting tree algorithm; the index evaluated is R reflecting the goodness of fit of the model2And the absolute value of the deviation of all individual observations from the arithmetic mean;
s23, implementation of the cabin price prediction model: importing training set data into a model for training, and adjusting corresponding parameters of an algorithm to achieve the optimal parameters; diagnosing the trained model by using the evaluation indexes, and judging the fitting state of the trained model; carrying out further optimization on the diagnosed model, diagnosing the optimized new model again, and repeatedly iterating and continuously approaching to achieve the optimal state;
s24, price prediction is carried out by utilizing the built cabin price prediction model, the prediction result is stored in a big data platform, the model effect is evaluated through the business indexes of passenger behaviors or enterprise profits and the operation indexes of online operation speed, resource consumption degree and stability of the model, the business indexes of the passenger behaviors comprise high evaluation rate, the business indexes of the enterprise profits comprise profit, high probability and passenger source amplification, the online operation speed of the model is time complexity, and the resource consumption degree is space complexity.
4. The block chain-based airline department revenue management dynamic pricing method of claim 1, wherein: the method for constructing the dynamic pricing model specifically comprises the following steps:
s31, preprocessing data: extracting a prediction result of the cabin price prediction model from a big data platform as input data, wherein the input data comprises four types: TCN data, INV data, flight information data of the co-flying company and other basic data, and the data cleaning is carried out on the input data, and the non-limiting processing is carried out on the historical booking data;
s32, prediction: selecting a prediction model with the best effect in the current period from the cabin price prediction models, extracting historical cabin or ticket outlet people flow statistical data, estimating the whole market demand scale by adopting an empirical method and a joint estimation method, performing prediction correction on data loss, correcting the prediction data provided by a cabin price prediction module, performing price optimization by combining passenger behavior analysis, and obtaining a passenger sensitivity behavior analysis result through passenger portrait and demand statistics;
s33, solving the dynamic pricing model: the optimal strategy of the control cabin is actively controlled by utilizing an optimal solution algorithm, and meanwhile, manual intervention measures are taken, wherein the manual intervention comprises the consideration of suboptimal targets and the control adjustment of rules,
s34, outputting the result: and obtaining an output result by the dynamic pricing model, wherein the output result comprises a cabin position control cabin instruction and an analysis chart, the cabin position control cabin instruction is used for cabin position control, cabin position opening quantity change and cabin position nesting change, the analysis chart comprises a data analysis chart and a flight early warning chart, the data analysis chart provides a sale price curve for the navigation department, and the flight early warning chart provides seat booking and capacity change warning for the navigation department.
5. The block chain-based airline department revenue management dynamic pricing method of claim 4, wherein: the TCN data comprises flight booking data comprising historical data for estimating market demand and real-time data for performing a comparably comparative analysis; the INV data comprises bay data comprising historical data for estimating market demand and real-time data for supporting subsequent algorithm decisions; the flight information data of the co-flight company and other basic data mainly describe basic information related to flights, including flight numbers, moments, machine types, real-time freight rates and flight basic cabin freight rate tables, and the INV data are further processed to generate passenger seat rate data and output to be a flight passenger seat rate growth curve for airline revenue assessment of a navigation department.
6. The block chain-based airline department revenue management dynamic pricing method of claim 1, wherein: the personalized product recommendation model is modeled by combining passenger characteristic information provided by the passenger portrait, deep learning modeling is carried out by adopting a deep circulation neural network and a convolution network during modeling, and finally a commodity recommendation list is generated.
7. The block chain-based airline department revenue management dynamic pricing method of claim 6, wherein: the passenger portrait is a customer portrait of an aviation passenger, and comprises demographic attributes, ticket buying behaviors, check-in behaviors and airplane riding behaviors, wherein the demographic attributes comprise sex, age, passenger source, occupation and cultural degree of the customer; the ticket buying behavior comprises a ticket buying advance, a ticket buying channel and a ticket refunding and changing condition; the check-in behavior comprises a check-in mode; the boarding behaviors include a boarding period, a boarding moment, a boarding seat, a boarding cabin space, and meal preferences.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010808770.4A CN111899059A (en) | 2020-08-12 | 2020-08-12 | Navigation driver revenue management dynamic pricing method based on block chain |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010808770.4A CN111899059A (en) | 2020-08-12 | 2020-08-12 | Navigation driver revenue management dynamic pricing method based on block chain |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111899059A true CN111899059A (en) | 2020-11-06 |
Family
ID=73229154
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010808770.4A Pending CN111899059A (en) | 2020-08-12 | 2020-08-12 | Navigation driver revenue management dynamic pricing method based on block chain |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111899059A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112598310A (en) * | 2020-12-29 | 2021-04-02 | 北京筹策科技有限公司 | Real-time dynamic distribution method and device for flight space and computer equipment |
CN112907158A (en) * | 2021-05-10 | 2021-06-04 | 北京人人云图信息技术有限公司 | Flight passenger flow generation method and system based on game learning |
CN113033685A (en) * | 2021-04-01 | 2021-06-25 | 安徽理工大学 | Method for portraying and analyzing seat selection willingness of airline passengers for payment |
CN113379443A (en) * | 2021-05-10 | 2021-09-10 | 北京人人云图信息技术有限公司 | Flight flow simulation method and system |
CN113469743A (en) * | 2021-07-01 | 2021-10-01 | 浙江数秦科技有限公司 | Greenhouse planting income prediction system based on block chain |
CN113609142A (en) * | 2021-07-06 | 2021-11-05 | 深圳市飞耶软件有限公司 | Automatic freight rate updating method and storage medium based on OTA platform data delivery |
CN114255074A (en) * | 2021-12-06 | 2022-03-29 | 蚂蚁区块链科技(上海)有限公司 | Block chain based method and system for evaluating product value |
CN115169757A (en) * | 2022-09-07 | 2022-10-11 | 中国民航信息网络股份有限公司 | Passenger cabin-lifting prediction method, passenger cabin-lifting prediction model obtaining method and device |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106030626A (en) * | 2013-12-11 | 2016-10-12 | 天巡有限公司 | Method and system for providing fare availabilities, such as air fare availabilities |
CN107506869A (en) * | 2017-09-05 | 2017-12-22 | 济南浚达信息技术有限公司 | A kind of air ticket day booking number Forecasting Methodology based on Recognition with Recurrent Neural Network |
US20180032924A1 (en) * | 2013-03-08 | 2018-02-01 | Us Airways, Inc. | Unobscuring algorithm |
CN107909383A (en) * | 2017-09-28 | 2018-04-13 | 天津伊翔运达网络科技有限公司 | A kind of Dynamic Pricing method of combination passenger information |
CN108830635A (en) * | 2018-04-26 | 2018-11-16 | 深圳马可孛罗科技有限公司 | A kind of air ticket order dynamic price adjustment method and system |
CN109983490A (en) * | 2016-10-06 | 2019-07-05 | 邓白氏公司 | The Machine learning classifiers and prediction engine that the potential customers of artificial intelligence optimization determine are carried out on winning/losing classification |
CN110233869A (en) * | 2019-04-26 | 2019-09-13 | 平安科技(深圳)有限公司 | Passenger based on block chain seizes the opportunity data sharing method and relevant device |
CN110472760A (en) * | 2019-08-21 | 2019-11-19 | 北京艾摩瑞策科技有限公司 | A kind of air ticket ticket booking data processing method and device on block chain |
CN111539778A (en) * | 2020-05-27 | 2020-08-14 | 海南太美航空股份有限公司 | Dynamic pricing method and system for directional pushing |
-
2020
- 2020-08-12 CN CN202010808770.4A patent/CN111899059A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20180032924A1 (en) * | 2013-03-08 | 2018-02-01 | Us Airways, Inc. | Unobscuring algorithm |
CN106030626A (en) * | 2013-12-11 | 2016-10-12 | 天巡有限公司 | Method and system for providing fare availabilities, such as air fare availabilities |
CN109983490A (en) * | 2016-10-06 | 2019-07-05 | 邓白氏公司 | The Machine learning classifiers and prediction engine that the potential customers of artificial intelligence optimization determine are carried out on winning/losing classification |
CN107506869A (en) * | 2017-09-05 | 2017-12-22 | 济南浚达信息技术有限公司 | A kind of air ticket day booking number Forecasting Methodology based on Recognition with Recurrent Neural Network |
CN107909383A (en) * | 2017-09-28 | 2018-04-13 | 天津伊翔运达网络科技有限公司 | A kind of Dynamic Pricing method of combination passenger information |
CN108830635A (en) * | 2018-04-26 | 2018-11-16 | 深圳马可孛罗科技有限公司 | A kind of air ticket order dynamic price adjustment method and system |
CN110233869A (en) * | 2019-04-26 | 2019-09-13 | 平安科技(深圳)有限公司 | Passenger based on block chain seizes the opportunity data sharing method and relevant device |
CN110472760A (en) * | 2019-08-21 | 2019-11-19 | 北京艾摩瑞策科技有限公司 | A kind of air ticket ticket booking data processing method and device on block chain |
CN111539778A (en) * | 2020-05-27 | 2020-08-14 | 海南太美航空股份有限公司 | Dynamic pricing method and system for directional pushing |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112598310A (en) * | 2020-12-29 | 2021-04-02 | 北京筹策科技有限公司 | Real-time dynamic distribution method and device for flight space and computer equipment |
CN113033685A (en) * | 2021-04-01 | 2021-06-25 | 安徽理工大学 | Method for portraying and analyzing seat selection willingness of airline passengers for payment |
CN112907158A (en) * | 2021-05-10 | 2021-06-04 | 北京人人云图信息技术有限公司 | Flight passenger flow generation method and system based on game learning |
CN112907158B (en) * | 2021-05-10 | 2021-07-23 | 北京人人云图信息技术有限公司 | Flight passenger flow generation method and system based on game learning |
CN113379443A (en) * | 2021-05-10 | 2021-09-10 | 北京人人云图信息技术有限公司 | Flight flow simulation method and system |
CN113379443B (en) * | 2021-05-10 | 2023-10-17 | 北京人人云图信息技术有限公司 | Flight flow simulation method and system |
CN113469743A (en) * | 2021-07-01 | 2021-10-01 | 浙江数秦科技有限公司 | Greenhouse planting income prediction system based on block chain |
CN113469743B (en) * | 2021-07-01 | 2024-02-27 | 浙江数秦科技有限公司 | Greenhouse planting income prediction system based on block chain |
CN113609142A (en) * | 2021-07-06 | 2021-11-05 | 深圳市飞耶软件有限公司 | Automatic freight rate updating method and storage medium based on OTA platform data delivery |
CN113609142B (en) * | 2021-07-06 | 2024-02-20 | 深圳市飞耶软件有限公司 | Automatic freight rate updating method based on OTA platform data delivery and storage medium |
CN114255074A (en) * | 2021-12-06 | 2022-03-29 | 蚂蚁区块链科技(上海)有限公司 | Block chain based method and system for evaluating product value |
CN115169757A (en) * | 2022-09-07 | 2022-10-11 | 中国民航信息网络股份有限公司 | Passenger cabin-lifting prediction method, passenger cabin-lifting prediction model obtaining method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111899059A (en) | Navigation driver revenue management dynamic pricing method based on block chain | |
US11182808B2 (en) | Method and system for attributes based forecasting | |
Cadarso et al. | Integrated airline scheduling: Considering competition effects and the entry of the high speed rail | |
Echaniz et al. | Modelling perceived quality for urban public transport systems using weighted variables and random parameters | |
Di Puglia Pugliese et al. | The last-mile delivery process with trucks and drones under uncertain energy consumption | |
Sakib | Restaurant sales prediction using machine learning | |
CN115358651A (en) | Method, system and computer readable storage medium for automatic replenishment of retail store | |
CN111539778A (en) | Dynamic pricing method and system for directional pushing | |
van der Hagen et al. | Machine learning–based feasibility checks for dynamic time slot management | |
CN112948412A (en) | Flight inventory updating method, system, electronic equipment and storage medium | |
CN111680382A (en) | Grade prediction model training method, grade prediction device and electronic equipment | |
CN110516873B (en) | Optimization method for cabin allocation of airline company | |
CN115619571A (en) | Financing planning method, system and device | |
Ariyawansa et al. | Review on state of art data mining and machine learning techniques for intelligent Airport systems | |
Agarwal et al. | Machine Learning and Natural Language Processing in Supply Chain Management: A Comprehensive Review and Future Research Directions. | |
Vadlamani et al. | Using machine learning to analyze and predict entry patterns of low-cost airlines: a study of Southwest Airlines | |
CN110852792A (en) | Big data analysis-based airline value evaluation method and related products | |
Yoo et al. | Predicting hotel booking cancelation with machine learning techniques | |
CN106779245B (en) | Event-based civil aviation demand prediction method and device | |
CN113269402A (en) | Flight space control method and device and computer equipment | |
Gunjal et al. | Fusing clustering and machine learning techniques for Big-Mart sales predication | |
Ramos-Carrasco et al. | Artificial neural networks to estimate the forecast of tourism demand in Peru | |
CN112308618B (en) | Data processing method and device, electronic equipment and storage medium | |
Ruch et al. | The impact of fleet coordination on taxi operations | |
Güner et al. | Output targeting and capacity utilization for a new-built airport: Analysis for the new airport in Istanbul |
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 |