CN111539778B - Dynamic pricing method and system for directional pushing - Google Patents
Dynamic pricing method and system for directional pushing Download PDFInfo
- Publication number
- CN111539778B CN111539778B CN202010462049.4A CN202010462049A CN111539778B CN 111539778 B CN111539778 B CN 111539778B CN 202010462049 A CN202010462049 A CN 202010462049A CN 111539778 B CN111539778 B CN 111539778B
- Authority
- CN
- China
- Prior art keywords
- client
- information
- dynamic pricing
- historical
- achievement rate
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 34
- 230000010006 flight Effects 0.000 claims abstract description 49
- 238000012806 monitoring device Methods 0.000 claims abstract description 13
- 238000012549 training Methods 0.000 claims description 16
- 239000002245 particle Substances 0.000 claims description 13
- 241000273930 Brevoortia tyrannus Species 0.000 description 10
- 230000009286 beneficial effect Effects 0.000 description 6
- 230000006399 behavior Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000006872 improvement Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000001737 promoting effect Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 210000001503 joint Anatomy 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
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
- G06Q30/0206—Price or cost determination based on market factors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- 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
- G06Q10/02—Reservations, e.g. for tickets, services or events
-
- 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
- G06Q30/0283—Price estimation or determination
-
- 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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0611—Request for offers or quotes
-
- G06Q50/40—
Abstract
The application discloses a dynamic pricing method and a system for directional pushing, and relates to the field of airline income analysis. The method comprises the following steps: the method comprises the steps that a flight seat monitoring device obtains residual seat information of a plurality of flights of a route to be profit optimized, an air operation background computing device obtains a target client according to a client query record of the route, a client dynamic pricing model trained through information of historical bargain clients outputs dynamic pricing results of residual seats according to the input residual seat information and the information of the target client, an air operation front-end device pushes the dynamic pricing results to the target client respectively, the dynamic pricing model predicts overall operation conditions of flights in real time according to the residual seat requirements of the flights, dynamic quotations are carried out for different passengers, the bargain of the passengers is improved, and accurate profit management is achieved.
Description
Technical Field
The application relates to the field of route income analysis, in particular to a dynamic pricing method and a system for directional pushing.
Background
With the gradual improvement of living standard of people, more and more people select aircraft as travel traffic modes. Often, before traveling, the passengers choose to reserve air tickets in advance, and different airlines can also give corresponding air ticket price schemes for different time periods so that the passengers choose traveling time. For airlines, an effective ticket price management scheme is formulated, which is beneficial to improving the passenger rate of flights and the overall benefit of the flights.
The current air ticket price management scheme adopted by the airline company is based on seat control, and the purpose of controlling the air ticket income is achieved by controlling the seat numbers of different seats. For the price of a certain specified airline company assigned complete cabin, different discount ticket prices are set according to the distance from the departure time, and different passengers are combined to sell tickets with different prices.
However, the conventional airline ticket price management scheme only carries out pricing based on the consideration of the airline end, belongs to a passive pricing process, is not in butt joint with the demand of clients, and greatly reduces the yield of unstable client groups, so that the overall income of the airline is reduced.
Disclosure of Invention
The application aims to solve the technical problem of providing a dynamic pricing method and a system for directional pushing aiming at the defects of the prior art.
The technical scheme for solving the technical problems is as follows:
a dynamic pricing method for directed pushing, comprising:
s1, a flight seat monitoring device obtains residual seat information of a plurality of flights of a route of which profit is to be optimized;
s2, the air operation background computing device obtains a target client according to the client query record of the air route;
s3, outputting dynamic pricing results of the residual seats according to the input residual seat information and the target client information through a client dynamic pricing model trained by the information of the historical bargain clients;
and S4, the front-end device of the air operation pushes the dynamic pricing results to the target clients respectively.
The beneficial effects of the application are as follows: according to the scheme, through a client dynamic pricing model trained by information of historical bargain clients, dynamic pricing results of the target clients are output according to the input residual seat information and the target clients, and then the dynamic pricing results are respectively pushed to the target clients, the dynamic pricing model predicts the overall operation condition of flights in real time according to the residual seat requirements of the flights, dynamically offers different passengers, improves the traffic of the passengers, and realizes accurate revenue management.
The method accords with the concept of differentiated accurate marketing in the NDC standard, carries out directional quotation aiming at different clients, improves the seat achievement rate, carries out directional accurate marketing on potential unstable client groups, improves the service quality of the clients, and simultaneously increases the utilization rate of the rest seats to improve the profit of flights.
Further, the method further comprises the steps of dividing the rest seat information into different bilges, setting different grades according to the different bilges, and confirming corresponding preferential proportions according to the grades;
the step S3 specifically comprises the following steps: and outputting a dynamic pricing result of the target client according to the input residual seat information and the target client through a client dynamic pricing model trained by the information of the historical bargain client and by combining the cabin class and the preferential proportion of the seat.
The beneficial effects of adopting the further scheme are as follows: the scheme includes that the rest seat information is divided into different bilges, different grades are set according to the different bilges, and corresponding preferential proportions are confirmed according to the grades; different bunkers have different preferential proportions, the prices of the high price bin and the low price bin are distinguished, for example, two clients under the same condition respectively select the high price bin and the low price bin, but the preferential proportions are still different, so that the traffic of seats is ensured, meanwhile, the profit of the high price bin is not damaged, and the overall profit of flights is improved.
The other technical scheme for solving the technical problems is as follows:
a dynamic pricing system for directed pushing, comprising: the system comprises a flight seat monitoring device, an air operation background computing device, a client dynamic pricing model and an air operation front-end device;
the flight seat monitoring device is used for obtaining the rest seat information of a plurality of flights of the route of which profit is to be optimized;
the aviation operation background computing device is used for acquiring a target client according to the client query record of the air route;
the client dynamic pricing model is used for outputting dynamic pricing results of the residual seats according to the input residual seat information and the target client information;
the front end device for the air operation is used for pushing the dynamic pricing results to the target clients respectively.
The beneficial effect of this scheme is: according to the scheme, through a client dynamic pricing model trained by information of historical bargain clients, dynamic pricing results of the target clients are output according to the input residual seat information and the target clients, and then the dynamic pricing results are respectively pushed to the target clients, the dynamic pricing model predicts the overall operation condition of flights in real time according to the residual seat requirements of the flights, dynamically offers different passengers, improves the traffic of the passengers, and realizes accurate revenue management.
The method accords with the concept of differentiated accurate marketing in the NDC standard, carries out directional quotation aiming at different clients, improves the seat achievement rate, carries out directional accurate marketing on potential unstable client groups, improves the service quality of the clients, and simultaneously increases the utilization rate of the rest seats to improve the profit of flights.
Further, the vehicle seat system comprises a vehicle seat grading module, a vehicle seat grading module and a vehicle seat grading module, wherein the vehicle seat grading module is used for dividing the rest seat information into different vehicle seats, setting different grades according to the different vehicle seats and confirming corresponding preferential proportions according to the grades;
the client dynamic pricing model is specifically used for outputting the dynamic pricing result of the target client according to the input residual seat information and the target client after the client dynamic pricing model is trained through the information of the historical bargain client and by combining the seat level and the preferential proportion.
The beneficial effects of adopting the further scheme are as follows: the scheme includes that the rest seat information is divided into different bilges, different grades are set according to the different bilges, and corresponding preferential proportions are confirmed according to the grades; different bunkers have different preferential proportions, the prices of the high price bin and the low price bin are distinguished, for example, two clients under the same condition respectively select the high price bin and the low price bin, but the preferential proportions are still different, so that the traffic of seats is ensured, meanwhile, the profit of the high price bin is not damaged, and the overall profit of flights is improved.
Additional aspects of the application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the application.
Drawings
FIG. 1 is a schematic flow diagram of a dynamic pricing method for directional pushing according to an embodiment of the present application;
FIG. 2 is a network frame diagram of a dynamic pricing system for targeted pushing provided by other embodiments of the present application;
fig. 3 is a block diagram of a dynamic pricing system for directional pushing according to an embodiment of the application.
Detailed Description
The principles and features of the present application are described below with reference to the drawings, the illustrated embodiments are provided for illustration only and are not intended to limit the scope of the present application.
As shown in fig. 1, a dynamic pricing method for directional pushing according to an embodiment of the present application includes:
s1, the flight seat monitoring device 11 obtains the rest seat information of a plurality of flights of a route with profit to be optimized;
specific embodiments for acquiring the remaining seat information of the flight may be: the flight seat monitoring device 11 is used as a server device at the back end of the platform and is used for real-time polling and scanning front-end ticketing equipment, such as an online webpage end, an offline unmanned ticketing machine or ticketing window equipment, and the like, real-time confirming the ticket refund, the ticket sale and the remaining ticket as tickets, connecting with a client dynamic pricing model, and sending acquired information of a plurality of flight remaining seats of the air route to the client dynamic pricing model.
As shown in fig. 2, the flight seat monitoring device transmits the plurality of flight remaining seat information of the route obtained by polling and scanning the front-end ticketing equipment to the client dynamic pricing model; and the air operation background computing device sends the information of the target client obtained by calculation to a client dynamic pricing model, calculates to obtain the pricing of the residual seat information according to the residual seat information and the client dynamic pricing model after training of the target client, sends the pricing result to the air operation front-end device, and pushes the pricing result to the client through the air operation front-end device.
In an embodiment, the flight seat monitoring device 11 gathers the remaining seats of the route for which profit is to be optimized, divides the remaining seat information into different bunkers, sets different grades according to the different bunkers, confirms the corresponding preferential proportion according to the grades, and makes seat quotes of different preferential proportions according to the different bunkers. For example, a dynamic pricing model, when the same user inquires the prices of different bunkers, the offers output by the model are different from the preferential discount of the corresponding original price bunkers, and the preferential degree is confirmed according to the bunkers grade; if the existing primary bunk, secondary bunk and tertiary bunk are adopted, the corresponding bunk full price seat price is as follows: 5000. 4000 and 2000, corresponding preferential proportions of 95 folds, 85 folds and 7 folds; the first customer (the condition of the client is consistent) selects the price of the three cabins to be 5000 x 95%, 4000 x 85% and 2000 x 70% respectively, so even one customer corresponds to different classes of cabins, the preferential proportion is different, thereby ensuring the profit of the high price cabin and the achievement rate of the whole cabin.
S2, the air operation background computing device 12 obtains a target client according to the client query record of the air route;
the implementation of obtaining the target client may be: the air-service background computing device 12 is configured to collect customer query records of the passenger for the air line, for example, the customer queries a record of the air line on a web side or an APP side of an air-service platform, or locates the query record of the air line by querying promotional information such as a special fare ticket, wherein the query record mainly collects personal information and query content of the customer, and can query and obtain historical trip information corresponding to the personal information of the customer, for example, historical trip selected flights, fare information of purchasing tickets, trip time and other historical order information according to the collected personal information of the customer. The air-service background computing device 12 is connected with the client dynamic pricing model, and transmits the acquired client query record information to the client dynamic pricing model.
In an embodiment, S2 specifically includes: the air operation background computing device 12 obtains query content and historical travel information corresponding to each client according to the client query records of the air route;
calculating the virtual achievement rate of each client through a particle swarm algorithm and the acquired inquiry content and history travel information, and taking the client corresponding to the virtual achievement rate higher than the preset virtual achievement rate threshold of the air route as a target client, wherein the virtual achievement rate is used for indicating the probability of the client purchasing the flight seat of the air route.
Parameters of a virtual achievement rate threshold for an airline are set in the airline's background computing device 12, where the virtual achievement rate represents a probability that the customer purchases a flight seat for the airline based on the collected customer's personal information, historical trip information, and query content, where the virtual achievement rate threshold may be determined based on target customer data for the airline's needs in combination with remaining seats.
Specific embodiments for calculating the virtual achievement rate may be: the air-service background computing device 12 computes a virtual achievement rate of each client by a particle swarm algorithm based on the client query record of the air route and the history travel information and query content of each client corresponding to the query record, and takes the client corresponding to the virtual achievement rate higher than the virtual achievement rate threshold as the target client.
Through simple behaviors of individual particles, namely historical transaction behaviors of each customer and query contents, information interaction in groups is associated, wherein the groups are the customers who have historical transactions on the route and the customers who query the route information, parameters of PSO are adjusted to balance global detection and local mining capacity of an algorithm, for example, the Shi and Eberhart introduce inertial weights to speed items of the PSO algorithm, linear (or nonlinear) dynamic adjustment is carried out on the inertial weights according to iteration processes and particle flight conditions so as to balance searching global and convergence speeds, actual adjustment can be selected according to data mining depth, individual behaviors are connected with group behaviors through a particle swarm algorithm, and the customers who are most likely to achieve transactions in users who query the route are obtained, wherein the particle swarm algorithm belongs to the prior art, and detailed calculation process is not repeated here.
According to the scheme, parameters of a virtual achievement rate threshold are set firstly, then, according to customer query records of a route and historical travel information of each customer, the virtual achievement rate of each customer is obtained through a particle swarm algorithm, the customers higher than the virtual achievement rate threshold are used as target customers, among a plurality of login customers, the customers are selected at will to push, the achievement rate tends to be very low, and in addition, preferential quotation is pushed to a large number of customers, profits are damaged, and then, the system processing data pressure is increased, and accurate high-quality target customers are obtained through calculation of the particle swarm algorithm, so that the achievement rate is effectively improved, and the total profits are ensured.
S3, outputting dynamic pricing results of the residual seats according to the input residual seat information and the target client information through a client dynamic pricing model 13 trained by the information of the historical bargain clients;
in one embodiment, the customer dynamic pricing model 13 is built based on the time of departure from the route, historical sales prices for the route, contemporaneous sales prices for the route, reservation rates for all flights on the route, and customer information.
It should be noted that, determining a certain route A at an airline company, where the route has a plurality of flights, and the flight a has determined departure time Ta, subdividing according to the ticket purchasing date of the passengers and the different ticket purchasing grades to generate a multi-level cabin and a multi-level fare system, optimizing according to the information in the income management database, and determining the acceptable number of seats and corresponding contemporaneous sales price of each grade of each flight;
in an airline company's revenue management system, a model is predicted by combining historical data through historical seat booking numbers and corresponding historical sales prices in a revenue management database, and market demands are presumed by using the model for seat booking of the airlines, so that the reservation rate of all flights on the airlines is determined; the model calculates the preset rate according to the historical sales information and the quarter booking fluctuation rate after being combined with weighting.
The method comprises the steps that the situation of booking flights in sales is timely obtained from a booking system, historical sales data and planned sales targets of the situation are compared, ticket price discounts are determined by marketing management personnel of an airline company in combination with prediction information of a prediction subsystem, the airline company can flexibly allocate the bilges, and the bilges with less requirements and low reservation speed are subjected to price reduction treatment or bilge transfer, so that the optimization of the scheduled rate of flights is realized;
basic variables of the customer dynamic pricing model: determining acceptable booking numbers and corresponding contemporaneous sales prices of each level according to the time from take-off; determining the reservation rate of all flights on the route according to the historical seat reservation number and the corresponding historical sales price; and adjusting the seat information behind the cabin.
Important influencing variables output by the client dynamic pricing model: the target clients and the system fare correspond to the achievement rate.
In an embodiment, in the dynamic pricing model, the route a, the departure time of a flight a of the route is Ta, the number of acceptable seats of each level of the flight a is 50, the corresponding price for selling is 5000 yuan, after being distributed by an airline manager, the number of seats of three levels of the flight is adjusted to be 20, 50 and 80, the optimal preset rate of the flight is determined to be 75%, that is, the rest seats to be profit-optimized are 25% of the seats of the flight, 5 seats, 12 seats and 20 seats of the three levels are respectively determined, and the optimal price of the flight corresponding to the target customer in different levels is determined according to the target customer, the time difference T of the preset time of the customer and the Ta and the achievement rate of the price after the original price is folded.
Wherein the model after training outputs the optimal price, in an embodiment, for example, in an embodiment, the historical trip information of the client a includes information of a plurality of different airlines, wherein the airlines 1 are our target airlines, namely, there are remaining seats, and belong to airlines with profit to be optimized, in the trip of the airlines 1, the client a takes 50 times, and the taking price has three grades of one grade respectively: 4000. and (2) second-stage: 6000 and three stages: 10000, wherein the primary riding times are 10 times, the secondary riding times are 40 times, and the tertiary riding times are 10 times, and the primary price riding probability is as follows: 10/50 x 100%, the second-order price riding probability is: the 40/50 x 100% and three-level price ride probabilities are: 10/50 x 100%, it can be seen that for lane 1, the secondary price achievement rate is highest, the trained model will price the customer based on the secondary price as the optimal price for lane 1, and in combination with the discount corresponding to the predetermined time, as a reference, this optimal price reference indicates that if the existing remaining target is a seat with no secondary price, the seat price closest to the secondary price will be the pricing result finally output by the model.
According to the scheme, a model is built according to the distance take-off time, the historical sales price of the air route, the contemporaneous sales price of the air route, the reservation rate of all flights on the air route and the client information, so that the client dynamic pricing can combine various influencing factors, the accuracy of directional pricing is improved, and the arrival rate of the seats of the flights is improved.
Wherein, the client information includes: personal information of the customer, historical travel information, and historical purchase seat information.
The dynamic pricing model fully mines the actual demands of the clients through the personal information, the historical travel information and the historical purchase seat information of the clients, and offers are made according to the actual demands of the clients, so that the offer results more accord with the concept of accurate marketing, and the improvement of flight earnings is facilitated.
In a certain embodiment, training the client dynamic pricing model 13 based on historical trip information of the client and ticket price information corresponding to the trip, and outputting ticket price information corresponding to flights with an achievement rate not less than a preset achievement rate, so as to obtain the trained client dynamic pricing model 13 for completing training, wherein the flights represent flight information of the airlines corresponding to the historical trip; if the achievement rate is less than the preset achievement rate, training is continued. The preset achievement rate can be determined according to profit standards of flights, different achievement rates can be obtained according to historical information by different pricing, different profit values can be obtained for different prices, and the proper preset achievement rate can be determined according to different profit standards of different seasons.
It should be noted that, the achievement rate refers to the relationship between the historical journey of the client and the corresponding fare, the same route journey, which price has the highest purchase probability, each route is calculated to have a plurality of exact actual probability values, and the trained model determines the most reasonable price according to the condition that the probability value is the largest and the preset achievement rate is satisfied. For example, in one embodiment, the historical trip information of the customer a includes information of a plurality of different airlines, wherein the airlines 1 are our target airlines, i.e. there are remaining seats, and are airlines belonging to profit to be optimized, and in the trip of the airlines 1, the customer a takes 50 times, and the take price has three levels of one level respectively: 4000. and (2) second-stage: 6000 and three stages: 10000, wherein the primary riding times are 10 times, the secondary riding times are 40 times, and the tertiary riding times are 10 times, and the primary price riding probability is as follows: 10/50 x 100%, the second-order price riding probability is: the 40/50 x 100% and three-level price ride probabilities are: 10/50 x 100%, it can be seen that for lane 1, the secondary price achievement rate is highest, and the trained model will price the customer based on the secondary price as the optimal price reference for lane 1, which represents the final output pricing result of the model with the seat price closest to the secondary price if the existing remaining targets are seats with no secondary price.
According to the scheme, based on historical travel information of the client and ticket price information corresponding to the travel, the client dynamic pricing model 13 is trained, ticket price information corresponding to flights with the achievement rate not smaller than the preset achievement rate is output, the model is trained through historical achievement data of the user, the trained model can output the price with the highest flight purchase rate according to the flight information and the user information, and the quotation of the client through the trained model is reasonable and the achievement rate is highest.
Preferably, the rest seat information is divided into different bilges, different grades are set according to the different bilges, and corresponding preferential proportions are confirmed according to the grades;
s3 specifically comprises: and outputting the dynamic pricing result of the target client according to the input residual seat information and the target client through the client dynamic pricing model 13 trained by the information of the historical bargain client and by combining the cabin class and the preferential proportion of the seat.
The method comprises the steps of dividing the rest seat information into different bilges, setting different grades according to the different bilges, and confirming corresponding preferential proportions according to the grades; different bunkers have different preferential proportions, the prices of the high price bin and the low price bin are distinguished, two clients under the same condition respectively select the high price bin and the low price bin, but the preferential proportions are still different, so that the traffic of seats is ensured, meanwhile, the profit of the high price bin is not damaged, and the overall profit of flights is improved.
S4, the air operation front-end device 14 pushes the dynamic pricing results to target clients respectively. The pushing mode can be that the client sends out in a bouncing window mode when inquiring the platform, or directly displays the bouncing window in the inquiring result of the client, or sends out the pricing result in a short message mode; the pushing mode can be confirmed according to the inquiry records of the clients, for example, when the clients directly inquire the information of a certain route, the pricing results can be directly displayed in the inquiry results by inputting the exact route information; if the customer is located on the route in other travel information or promotional discount information, the route may be sent to the customer in a pop-up window or text message.
According to the scheme, the dynamic pricing model 13 of the clients is trained through information of historical bargain clients, dynamic pricing results of the target clients are output according to the input residual seat information and the target clients, then the dynamic pricing results are respectively pushed to the target clients, the dynamic pricing model predicts the overall operation condition of flights in real time according to the residual seat requirements of the flights, dynamic quotations are carried out for different passengers, the bargain of the passengers is improved, and accurate revenue management is achieved.
The concept of differentiated accurate marketing in NDC (New Distribution Capability) standard is met, the targeted quotation is carried out for different clients, the seat achievement rate is improved, the targeted accurate marketing is carried out for the potentially unstable client group, the client service quality is improved, and meanwhile, the utilization rate of the rest seats is increased, and the flight profit is improved.
In one embodiment, as shown in FIG. 3, a dynamic pricing system for targeted pushing, the system comprising: a flight seat monitoring device 11, an air operation background computing device 12, a client dynamic pricing model 13 and an air operation front-end device 14;
the flight seat monitoring device 11 is used for obtaining the rest seat information of a plurality of flights of the route of which profit is to be optimized;
the air operation background computing device 12 is used for acquiring a target client according to the client query record of the air route;
the client dynamic pricing model 13 is used for outputting dynamic pricing results of the remaining seats according to the input remaining seat information and the target client;
the air-operation front-end device 14 is configured to push dynamic pricing results to target clients by the air-operation front-end device 14.
According to the scheme, the dynamic pricing model 13 of the clients is trained through the information of the historical bargain clients, the dynamic pricing results of the target clients are output according to the input residual seat information and the information of the target clients, the dynamic pricing results are respectively pushed to the target clients, the dynamic pricing model predicts the overall operation condition of the flight in real time according to the residual seat requirements of the flight, dynamic quotations are carried out for different passengers, the bargain of the passengers is improved, and accurate profit management is realized.
The method accords with the concept of differentiated accurate marketing in the NDC standard, carries out directional quotation aiming at different clients, improves the seat achievement rate, carries out directional accurate marketing on potential unstable client groups, improves the service quality of the clients, and simultaneously increases the utilization rate of the rest seats to improve the profit of flights.
Preferably, in any of the above embodiments, the air-operation background computing device 12 is specifically configured to obtain a preset virtual achievement rate threshold of the air line;
the air-service background computing device 12 obtains the virtual achievement rate of each client by a particle swarm algorithm based on the client query record of the air route and the history travel information of each client, and uses the client whose virtual achievement rate is higher than the virtual achievement rate threshold value as the target client.
According to the scheme, parameters of a virtual achievement rate threshold are set firstly, then, according to customer query records of a route and historical travel information of each customer, the virtual achievement rate of each customer is obtained through a particle swarm algorithm, the customers higher than the virtual achievement rate threshold are used as target customers, among a plurality of login customers, the customers are selected at will to push, the achievement rate tends to be very low, and in addition, preferential quotation is pushed to a large number of customers, profits are damaged, and then, the system processing data pressure is increased, and accurate high-quality target customers are obtained through calculation of the particle swarm algorithm, so that the achievement rate is effectively improved, and the total profits are ensured.
Preferably, in any of the above embodiments, the method further includes: the model training module is used for training the client dynamic pricing model 13 based on the historical trip information of the client and the ticket price information corresponding to the trip, outputting ticket price information corresponding to the flights with the achievement rate not less than the preset achievement rate, and obtaining the trained client dynamic pricing model 13 for completing the training, wherein the flights represent the flight information of the airlines corresponding to the historical trip; if the achievement rate is less than the preset achievement rate, training is continued.
According to the scheme, based on historical travel information of the client and ticket price information corresponding to the travel, the client dynamic pricing model 13 is trained, ticket price information corresponding to flights with the achievement rate not smaller than the preset achievement rate is output, the model is trained through historical achievement data of the user, the trained model can output the price with the highest flight purchase rate according to the flight information and the user information, and the quotation of the client through the trained model is reasonable and the achievement rate is highest.
Preferably, in any of the above embodiments, the method further includes: the model building module is used for building a client dynamic pricing model 13 according to the distance take-off time, the historical sales price of the airlines, the contemporaneous sales price of the airlines, the reservation rate of all flights on the airlines and client information.
According to the scheme, a model is built according to the distance take-off time, the historical sales price of the air route, the contemporaneous sales price of the air route, the reservation rate of all flights on the air route and the client information, so that the client dynamic pricing can combine various influencing factors, the accuracy of directional pricing is improved, and the arrival rate of the seats of the flights is improved.
Preferably, in any of the above embodiments, the client information includes: personal information of the customer, historical travel information, and historical purchase seat information.
The scheme comprises the following steps of: the personal information, the historical travel information and the historical purchase seat information of the clients enable the dynamic pricing model to fully mine actual demands of the clients, and offer according to the actual demands of the clients, so that offer results are more in line with the concept of accurate marketing, and the method is beneficial to improving flight profits.
Preferably, in any of the above embodiments, the vehicle seat system further includes a bunk classification module, configured to divide the remaining seat information into different bunks, set different grades according to the different bunks, and confirm the corresponding preferential proportion according to the grades;
the client dynamic pricing model is specifically used for outputting the dynamic pricing result of the target client according to the input rest seat information and the target client after the client dynamic pricing model 13 is trained by the information of the historical bargain clients and by combining the cabin class and the preferential proportion of the seat.
The method comprises the steps of dividing the rest seat information into different bilges, setting different grades according to the different bilges, and confirming corresponding preferential proportions according to the grades; different bunkers have different preferential proportions, the prices of the high price bin and the low price bin are distinguished, for example, two clients under the same condition respectively select the high price bin and the low price bin, but the preferential proportions are still different, so that the traffic of seats is ensured, meanwhile, the profit of the high price bin is not damaged, and the overall profit of flights is improved.
It is to be understood that in some embodiments, some or all of the alternatives described in the various embodiments above may be included.
It should be noted that, the foregoing embodiments are product embodiments corresponding to the previous method embodiments, and the description of each optional implementation manner in the product embodiments may refer to the corresponding description in the foregoing method embodiments, which is not repeated herein.
The reader will appreciate that in the description of this specification, a description of the terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
In the several embodiments provided by the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the method embodiments described above are merely illustrative, e.g., the division of steps is merely a logical function division, and there may be additional divisions of actual implementation, e.g., multiple steps may be combined or integrated into another step, or some features may be omitted or not performed.
The above-described method, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present application is essentially or a part contributing to the prior art, or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of the embodiments of the present application. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a Read-only memory (ROM), a random access memory (RAM, randomAccessMemory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The present application is not limited to the above embodiments, and various equivalent modifications and substitutions can be easily made by those skilled in the art within the technical scope of the present application, and these modifications and substitutions are intended to be included in the scope of the present application. Therefore, the protection scope of the application is subject to the protection scope of the claims.
Claims (8)
1. A dynamic pricing method for directed pushing, comprising:
the flight seat monitoring device obtains the rest seat information of a plurality of flights of the route of which profit is to be optimized;
the aviation operation background computing device obtains a target client according to the client query record of the air route;
outputting a dynamic pricing result of the residual seat according to the input residual seat information and the target client information through a client dynamic pricing model trained by the information of the historical bargain client;
the front-end device of the aviation operation pushes the dynamic pricing results to the target clients respectively;
the aviation operation background computing device obtains target clients according to the client query records of the airlines, and the method specifically comprises the following steps:
the aviation operation background computing device obtains query content and historical travel information corresponding to each client according to the client query records of the airlines;
calculating the virtual achievement rate of each client through a particle swarm algorithm and the acquired inquiry content and history travel information, and taking the client corresponding to the virtual achievement rate higher than the preset virtual achievement rate threshold of the air route as a target client, wherein the virtual achievement rate is used for indicating the probability of the client purchasing the flight seat of the air route.
2. A dynamic pricing method for directional pushing according to claim 1, further comprising: training a client dynamic pricing model based on historical travel information and corresponding historical fare information of a historical bargain client, outputting fare information corresponding to flights with an achievement rate not smaller than a preset achievement rate, and obtaining a trained client dynamic pricing model for completing training, wherein the flights represent flight information of airlines corresponding to the historical travel information; if the achievement rate is less than the preset achievement rate, training is continued.
3. A dynamic pricing method for directional pushing according to claim 2, further comprising: the customer dynamic pricing model is established based on the time of departure from distance, historical sales prices for airlines, contemporaneous sales prices for airlines, reservation rates for all flights on the airlines, and customer information.
4. A dynamic pricing method for directed pushing according to claim 3, wherein the customer information comprises: personal information of the customer, historical travel information, and historical purchase seat information.
5. A dynamic pricing system for directed pushing, comprising: the system comprises a flight seat monitoring device, an air operation background computing device, a client dynamic pricing model and an air operation front-end device;
the flight seat monitoring device is used for obtaining the rest seat information of a plurality of flights of the route of which profit is to be optimized;
the aviation operation background computing device is used for acquiring a target client according to the client query record of the air route;
the client dynamic pricing model is used for outputting dynamic pricing results of the residual seats according to the input residual seat information and the target client information;
the front end device of the air operation is used for pushing the dynamic pricing results to the target clients respectively;
the air operation background computing device is specifically used for:
acquiring query content and historical travel information corresponding to each client according to the client query records of the airlines;
calculating the virtual achievement rate of each client through a particle swarm algorithm and the acquired inquiry content and history travel information, and taking the client corresponding to the virtual achievement rate higher than the preset virtual achievement rate threshold of the air route as a target client, wherein the virtual achievement rate is used for indicating the probability of the client purchasing the flight seat of the air route.
6. A dynamic pricing system for directional pushing according to claim 5, further comprising: the model training module is used for training the client dynamic pricing model based on the historical travel information and the corresponding historical fare information of the historical bargain clients, outputting fare information corresponding to flights with the achievement rate not less than the preset achievement rate, and obtaining a trained client dynamic pricing model for completing training, wherein the flights represent flight information of the airlines corresponding to the historical travel information; if the achievement rate is less than the preset achievement rate, training is continued.
7. A dynamic pricing system for directional pushing according to claim 6, further comprising: the model building module is used for building the client dynamic pricing model according to the departure time, the historical sales price of the air route, the contemporaneous sales price of the air route, the reservation rate of all flights on the air route and the client information.
8. A dynamic pricing system for directed pushing according to claim 7, wherein the customer information comprises: personal information of the customer, historical travel information, and historical purchase seat information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010462049.4A CN111539778B (en) | 2020-05-27 | 2020-05-27 | Dynamic pricing method and system for directional pushing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010462049.4A CN111539778B (en) | 2020-05-27 | 2020-05-27 | Dynamic pricing method and system for directional pushing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111539778A CN111539778A (en) | 2020-08-14 |
| CN111539778B true CN111539778B (en) | 2023-11-03 |
Family
ID=71974501
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010462049.4A Active CN111539778B (en) | 2020-05-27 | 2020-05-27 | Dynamic pricing method and system for directional pushing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111539778B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111899059A (en) * | 2020-08-12 | 2020-11-06 | 科技谷（厦门）信息技术有限公司 | Navigation driver revenue management dynamic pricing method based on block chain |
| 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 |
| CN113159888A (en) * | 2021-04-19 | 2021-07-23 | 海南太美航空股份有限公司 | Flight information recommendation method and system and electronic equipment |
| CN113269402B (en) * | 2021-04-28 | 2023-12-26 | 北京筹策科技有限公司 | Flight space control method and device and computer equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102063675A (en) * | 2009-06-03 | 2011-05-18 | 埃森哲环球服务有限公司 | Generation of travel-related offerings |
| WO2011143662A1 (en) * | 2010-05-14 | 2011-11-17 | Farelogix, Inc. | Searching for airline travel based upon seat characteristics |
| 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 |
| CN111028020A (en) * | 2019-12-17 | 2020-04-17 | 上海携程商务有限公司 | Yield management method, system, medium and electronic device for flight bag machine scene |
-
2020
- 2020-05-27 CN CN202010462049.4A patent/CN111539778B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102063675A (en) * | 2009-06-03 | 2011-05-18 | 埃森哲环球服务有限公司 | Generation of travel-related offerings |
| WO2011143662A1 (en) * | 2010-05-14 | 2011-11-17 | Farelogix, Inc. | Searching for airline travel based upon seat characteristics |
| 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 |
| CN111028020A (en) * | 2019-12-17 | 2020-04-17 | 上海携程商务有限公司 | Yield management method, system, medium and electronic device for flight bag machine scene |
Non-Patent Citations (1)
| Title |
|---|
| 机票价格预测的模糊时间序列方法;华逸群 等;《小型微型计算机系统》;第37卷(第11期);第2547-2551页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111539778A (en) | 2020-08-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111539778B (en) | Dynamic pricing method and system for directional pushing | |
| Morrell | Airlines within airlines: An analysis of US network airline responses to Low Cost Carriers | |
| EP2549429A1 (en) | System and method for improving dynamic availability computation | |
| Loh et al. | Airport selection criteria of low-cost carriers: A fuzzy analytical hierarchy process | |
| CN111899059A (en) | Navigation driver revenue management dynamic pricing method based on block chain | |
| CN105354689A (en) | Computer system based civil aviation team management method and system | |
| CN110516873B (en) | Optimization method for cabin allocation of airline company | |
| CN112949926B (en) | Income maximization ticket amount distribution method based on passenger demand re-identification | |
| Chou et al. | Evolutionary bi-level model for optimizing ticket fares and operations profit of Taiwan high-speed rail | |
| Zhao et al. | Dynamic pricing of ancillary services based on passenger choice behavior | |
| Vadlamani et al. | Using machine learning to analyze and predict entry patterns of low-cost airlines: a study of Southwest Airlines | |
| JP2019091389A (en) | Resource arbitration system and resource arbitration apparatus | |
| Miyoshi et al. | Are fuel-efficient aircraft worth investing in for non-Annex country airlines? An empirical analysis of Kenya Airways with an aircraft appraisal cost–benefit analysis model | |
| Oliveira et al. | Vehicle Design Considerations and Operations Optimization for Thin-haul Air Mobility Applications | |
| Chen | Commercial aircraft value evaluation and sensitivity analysis from the perspective of chinese airlines | |
| Rahmat | Evaluate the Service Quality of Local Airline Companies in Libya Using Importance-Satisfaction Analysis | |
| Chemutai et al. | Differentiation strategy and performance of long-distance bus companies in Kenya | |
| CN112907158B (en) | Flight passenger flow generation method and system based on game learning | |
| Yirgu | Long-distance airport choices, and their implications for aviation emissions and price-based environmental policies | |
| Sun et al. | Airline competition: A comprehensive review of recent research | |
| CN117649272A (en) | Dynamic pricing method and system for domestic air ticket products | |
| Competition et al. | Airport monitoring report 2017–18 | |
| Gosling | Aviation system performance measures for state transportation planning | |
| Lindner et al. | The Optimal Size of a Heterogeneous Air Taxi Fleet in Advanced Air Mobility: A Traffic Demand and Flight Scheduling Approach | |
| Kono et al. | Optimizing Multiple Airport Charges with Endogenous Airline Quality Considering the Marginal Cost of Public Funds |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |