CN116503086A - Method, system and medium for processing freight rate data of airline ticket based on machine learning - Google Patents
Method, system and medium for processing freight rate data of airline ticket based on machine learning Download PDFInfo
- Publication number
- CN116503086A CN116503086A CN202310490403.8A CN202310490403A CN116503086A CN 116503086 A CN116503086 A CN 116503086A CN 202310490403 A CN202310490403 A CN 202310490403A CN 116503086 A CN116503086 A CN 116503086A
- Authority
- CN
- China
- Prior art keywords
- freight rate
- air ticket
- rate data
- data
- ticket freight
- 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
- 238000010801 machine learning Methods 0.000 title claims abstract description 55
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000012545 processing Methods 0.000 title claims abstract description 29
- 230000008859 change Effects 0.000 claims abstract description 75
- 239000002245 particle Substances 0.000 claims description 32
- 238000012549 training Methods 0.000 claims description 19
- 238000005457 optimization Methods 0.000 claims description 17
- 230000006399 behavior Effects 0.000 claims description 14
- 238000012360 testing method Methods 0.000 claims description 14
- 230000007246 mechanism Effects 0.000 claims description 13
- 238000012216 screening Methods 0.000 claims description 13
- 238000012300 Sequence Analysis Methods 0.000 claims description 12
- 230000003993 interaction Effects 0.000 claims description 12
- 239000011159 matrix material Substances 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 10
- 238000013528 artificial neural network Methods 0.000 claims description 8
- 238000013500 data storage Methods 0.000 claims description 8
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 238000007418 data mining Methods 0.000 claims description 6
- 238000012546 transfer Methods 0.000 claims description 6
- 210000002569 neuron Anatomy 0.000 claims description 5
- 230000002776 aggregation Effects 0.000 claims description 4
- 238000004220 aggregation Methods 0.000 claims description 4
- 238000013527 convolutional neural network Methods 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 4
- 238000003672 processing method Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 abstract description 7
- 230000004913 activation Effects 0.000 description 4
- 238000007726 management method Methods 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 230000001364 causal effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000000513 principal component analysis Methods 0.000 description 2
- 238000007637 random forest analysis Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
- 238000006467 substitution reaction 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/042—Knowledge-based neural networks; Logical representations of neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a machine learning-based method, a machine learning-based system and a machine learning-based medium for processing freight rate data of airline tickets, wherein the machine learning-based method comprises the following steps: acquiring historical air ticket freight rate data, and extracting time sequence change sequences of air ticket freight rates of all air routes; acquiring update periods and update frequencies of historical air ticket freight rates according to the time sequence change sequence, acquiring access amounts of each route in each update period based on a big data means, and associating the access amounts with the time sequence change sequence; constructing an air ticket freight rate data updating model based on machine learning, acquiring multi-source air ticket freight rate data, acquiring next updating time of the air ticket freight rate data and predicted air ticket freight rate through the air ticket freight rate data updating model, and storing data; and calling the air ticket freight rate data in the stored data based on the time stamp searched by the user, and returning the output result to the user side. The invention carries out the data processor through the air ticket freight rate data, obtains reasonable price prediction, and improves the price accuracy and success rate in the process of purchasing the travel products by the user.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a method, a system and a medium for processing waybill freight rate data based on machine learning.
Background
With the vigorous development of civil aviation industry in China, more and more passengers select airplanes as travel tools. The passenger traffic volume of airlines is rapidly increasing, and meanwhile, the generated airline ticket freight rate data is also increasing explosively, so that the data processing of the airline ticket freight rate data is challenged. The long-term data accumulation ensures that the airline ticket freight rate data has more data dimension and larger data volume. Dynamic pricing, one of the main technologies for revenue management, is an important means for airlines to adjust the price of tickets for different supply levels in order to obtain maximum revenue, and has been widely used in the sales of airline tickets in recent years.
Currently, most travel service providers earn profits by selling airline tickets and additionally taking a commission on the basis of the tickets, and many travel companies attempt to make more profits by adjusting the commission based on their own industry experience. However, since the ticket demands and the behavior patterns of users are very complex in the real world, there are many disadvantages in price adjustment decision-making methods such as expert experience and the like, which are accurate in risk assessment, and an efficient and reasonable airline ticket price management system is needed. Therefore, in the management of the airline ticket freight rate, how to process the data related to the airline ticket freight rate by using machine learning, extract the correlation characteristics and perform periodic intelligent judgment so as to improve the price accuracy and success rate in the process of purchasing the travel product by the user is an urgent problem which cannot be solved.
Disclosure of Invention
In order to solve the technical problems, the invention provides a method, a system and a medium for processing the freight rate data of an airline ticket based on machine learning.
The first aspect of the invention provides a machine learning-based method for processing freight rate data of airline tickets, which comprises the following steps:
acquiring historical air ticket freight rate data, dividing the historical air ticket freight rate data into different data sets according to the airline information, and carrying out time sequence analysis on the different data sets to acquire time sequence change sequences of the air ticket freight rates of all the airlines;
acquiring update periods and update frequencies of historical air ticket freight rates according to the time sequence change sequence, acquiring access amounts of each route in each update period based on a big data means, and associating the access amounts with the time sequence change sequence to acquire a characteristic sample data set;
constructing an air ticket freight rate data updating model based on machine learning, training by utilizing the characteristic sample data set, and outputting the trained air ticket freight rate data updating model after the test reaches the standard;
acquiring multi-source air ticket freight rate data, screening the multi-source air ticket freight rate data according to a preset parameterized reference, acquiring next update time of the air ticket freight rate data through an air ticket freight rate data update model, acquiring predicted air ticket freight rate based on the next update time, and setting a data tag for data storage;
And calling the air ticket freight rate data in the stored data based on the time stamp searched by the user, and returning the output result to the user side.
In the scheme, historical air ticket freight rate data are divided into different data sets according to the airline information, time sequence analysis is carried out on the different data sets, and time sequence change sequences of the air ticket freight rates of all the airlines are obtained, specifically:
extracting keyword information in historical air ticket freight rate data, determining departure city information and destination city information according to the keyword information, extracting route information, and setting classification labels based on the route information;
classifying the historical air ticket freight rate data according to the classification labels, obtaining air ticket freight rate data sets under different classification labels, and marking the corresponding air ticket freight rate data according to holiday information and common day information;
and carrying out time sequence analysis on the air ticket freight rate data under different marks, obtaining the change time stamp and the change difference of the air ticket freight rate, generating time sequence change sequences of each route, and obtaining the update period and the update frequency of the historical air ticket freight rate.
In the scheme, an air ticket freight rate data updating model is built based on machine learning, the feature sample data set is utilized for training, and after the test reaches the standard, the trained air ticket freight rate data updating model is output, specifically:
Acquiring the inquiry quantity of each route information in the air ticket booking related website based on a big data means, setting a heterogeneous information retrieval tag according to destination information of the route information, and acquiring a retrieval time step according to each updating period to acquire the inquiry quantity of the heterogeneous information;
setting conversion coefficients and the query quantity of heterogeneous information to be combined, matching the combined data with the query quantity of each route information to obtain final access quantity in each updating period, correlating the final access quantity with a time sequence change sequence, obtaining correlation characteristics of the access quantity and the updating period, and constructing a characteristic sample data set;
constructing an air ticket freight rate data updating model based on an LSTM network optimized by a particle swarm algorithm, setting particles according to the number of hidden layer neurons in the LSTM network, the learning rate and the maximum iteration number, initializing particle parameters, and setting initial positions and speeds;
setting a fitness function according to the mean square error, carrying out particle position optimization according to the continuous updating of individual particle optimization and global optimization, and determining parameters of an LSTM network according to the optimal particle position;
and dividing the characteristic sample data set into a training set and a testing set according to a preset proportion, and outputting an air ticket freight rate data updating model with accuracy meeting a preset standard after iterative training.
In this scheme, obtain the next updated time of air ticket fortune price data through air ticket fortune price data update model, specifically do:
screening the multi-source air ticket freight rate data to obtain target air ticket freight rate data, extracting the route information, time information and bin position information of the target air ticket freight rate data, and obtaining a time sequence change sequence and an access quantity change sequence in the past preset time as input of an air ticket freight rate data updating model;
introducing a self-attention mechanism into an air ticket freight rate data updating model, constructing a self-attention layer, taking hidden layer state outputs of different time steps as input of the self-attention layer, and calculating self-attention weight;
and representing the importance of each time step to the predicted target through the self-attention weight, and outputting the next updating time of the target air ticket freight rate data according to iterative calculation.
In the scheme, the predicted air ticket freight rate is obtained based on the next updating time, and the data tag is set for data storage, specifically:
according to the time sequence change sequence and the access volume change sequence of the historical air ticket freight rate of each route, acquiring influence factors of the air ticket freight rate through data mining, and screening the influence factors to acquire an influence factor set which influences the target air ticket freight rate in a preset time period in the past;
Constructing an air ticket freight rate prediction network based on a time convolution neural network, taking the acquired next updating time as target prediction time, matching the influencing factors in the influencing factor set with a time sequence change sequence of the target air ticket freight rate in the past preset time, and carrying out normalization processing;
and importing the normalized data into an air ticket freight rate prediction network, obtaining a predicted air ticket freight rate of target prediction time, and storing the next update time and the predicted air ticket freight rate after setting a data label.
In the scheme, the air ticket freight rate data in the stored data is called based on the time stamp searched by the user, and the output result is returned to the user side, specifically:
acquiring historical behavior data of a user, acquiring interaction information of the user and an air ticket project node in a preset time step according to the historical behavior data, and generating a bipartite graph structure for the air ticket project through the interaction information;
acquiring basic information, leg information and advanced ticket buying time information of a user as additional features of nodes in the two-part graph structure;
learning and representing the two-part graph structure based on a graph convolution neural network to obtain initial vector representations of a user and an air ticket project, splicing the initial vector representations of the user and the air ticket project, and constructing an adjacent matrix;
The characteristic transfer between nodes is carried out based on the adjacency matrix through a message transfer mechanism and a neighbor aggregation mechanism of the graph convolutional neural network, the characteristics of neighbor nodes are learned, and the embedded representation of the user nodes is updated;
in addition, acquiring air ticket items interacted by each time stamp of a user in a preset time step, splicing corresponding two graph structures, constructing a meta path in the preset time step, and matching the meta path with the user;
obtaining similarity between users by calculating the mean square distance of nodes on a meta-path between the users, taking the similarity as attention weight, and utilizing a graph attention structure to aggregate the embedded representation of the user nodes to output final user preference characteristics;
and acquiring corresponding air ticket freight rate data according to the search information of the user, analyzing freight rate change trend of the air ticket according to the acquired next updating time and predicted air ticket freight rate according to the preference characteristics of the user, and returning the queried information and freight rate change trend to the user side.
The second aspect of the invention also provides a machine learning-based airline ticket freight rate data processing system, which comprises: the system comprises a memory and a processor, wherein the memory comprises a machine learning-based airline ticket freight rate data processing method program, and the machine learning-based airline ticket freight rate data processing method program realizes the following steps when being executed by the processor:
Acquiring historical air ticket freight rate data, dividing the historical air ticket freight rate data into different data sets according to the airline information, and carrying out time sequence analysis on the different data sets to acquire time sequence change sequences of the air ticket freight rates of all the airlines;
acquiring update periods and update frequencies of historical air ticket freight rates according to the time sequence change sequence, acquiring access amounts of each route in each update period based on a big data means, and associating the access amounts with the time sequence change sequence to acquire a characteristic sample data set;
constructing an air ticket freight rate data updating model based on machine learning, training by utilizing the characteristic sample data set, and outputting the trained air ticket freight rate data updating model after the test reaches the standard;
acquiring multi-source air ticket freight rate data, screening the multi-source air ticket freight rate data according to a preset parameterized reference, acquiring next update time of the air ticket freight rate data through an air ticket freight rate data update model, acquiring predicted air ticket freight rate based on the next update time, and setting a data tag for data storage;
and calling the air ticket freight rate data in the stored data based on the time stamp searched by the user, and returning the output result to the user side.
The third aspect of the present invention also provides a computer readable storage medium, including a machine learning-based airline ticket freight rate data processing method program, where the machine learning-based airline ticket freight rate data processing method program is executed by a processor to implement the steps of the machine learning-based airline ticket freight rate data processing method according to any one of the above.
The invention discloses a machine learning-based method, a machine learning-based system and a machine learning-based medium for processing freight rate data of airline tickets, wherein the machine learning-based method comprises the following steps: acquiring historical air ticket freight rate data, and extracting time sequence change sequences of air ticket freight rates of all air routes; acquiring update periods and update frequencies of historical air ticket freight rates according to the time sequence change sequence, acquiring access amounts of each route in each update period based on a big data means, and associating the access amounts with the time sequence change sequence; constructing an air ticket freight rate data updating model based on machine learning, acquiring multi-source air ticket freight rate data, acquiring next updating time of the air ticket freight rate data and predicted air ticket freight rate through the air ticket freight rate data updating model, and storing data; and calling the air ticket freight rate data in the stored data based on the time stamp searched by the user, and returning the output result to the user side. The invention carries out the data processor through the air ticket freight rate data, obtains reasonable price prediction, and improves the price accuracy and success rate in the process of purchasing the travel products by the user.
Drawings
FIG. 1 shows a flow chart of a machine learning based method of processing airline ticket freight rate data in accordance with the present invention;
FIG. 2 is a flow chart of a method of the present invention for obtaining next update time of air ticket fare data;
FIG. 3 illustrates a flow chart of a method of the present invention for invoking air ticket freight rate data in stored data based on a user's searched time stamp;
FIG. 4 shows a block diagram of a machine learning based airline ticket fare data processing system of the present invention.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, in the case of no conflict, the embodiments of the present application and the features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those described herein, and therefore the scope of the present invention is not limited to the specific embodiments disclosed below.
FIG. 1 shows a flow chart of a machine learning based method of processing airline ticket freight rate data according to the present invention.
As shown in fig. 1, a first aspect of the present invention provides a method for processing freight rate data of airline tickets based on machine learning, including:
s102, acquiring historical air ticket freight rate data, dividing the historical air ticket freight rate data into different data sets according to the airline information, and carrying out time sequence analysis on the different data sets to acquire time sequence change sequences of the air ticket freight rates of all the airlines;
S104, acquiring update periods and update frequencies of historical air ticket freight rates according to the time sequence change sequence, acquiring access amounts of each route in each update period based on a big data means, and associating the access amounts with the time sequence change sequence to acquire a characteristic sample data set;
s106, constructing an air ticket freight rate data updating model based on machine learning, training by utilizing the characteristic sample data set, and outputting the trained air ticket freight rate data updating model after the test reaches the standard;
s108, acquiring multi-source air ticket freight rate data, screening the multi-source air ticket freight rate data according to a preset parameterized reference, acquiring next update time of the air ticket freight rate data through an air ticket freight rate data update model, acquiring predicted air ticket freight rate based on the next update time, and setting a data tag for data storage;
s110, calling the air ticket freight rate data in the stored data based on the time stamp searched by the user, and returning the output result to the user side.
The method comprises the steps of extracting keyword information in historical air ticket freight rate data, determining departure city information and destination city information according to the keyword information, extracting route information, and setting classification labels based on the route information; classifying the historical air ticket freight rate data according to the classification labels, obtaining air ticket freight rate data sets under different classification labels, and marking the corresponding air ticket freight rate data according to holiday information and common day information; and carrying out time sequence analysis on the air ticket freight rate data under different marks, obtaining the change time stamp and the change difference of the air ticket freight rate, generating time sequence change sequences of each route, and obtaining the update period and the update frequency of the historical air ticket freight rate.
Fig. 2 shows a flow chart of a method of the present invention for obtaining next update time of air ticket fare data.
According to the embodiment of the invention, the next update time of the air ticket freight rate data is obtained through the air ticket freight rate data update model, and specifically comprises the following steps:
s202, screening multi-source air ticket freight rate data to obtain target air ticket freight rate data, extracting route information, time information and bin position information of the target air ticket freight rate data, and obtaining a time sequence change sequence and an access quantity change sequence in the past preset time as input of an air ticket freight rate data update model;
s204, introducing a self-attention mechanism into the air ticket freight rate data updating model, constructing a self-attention layer, outputting hidden layer states with different time steps as input of the self-attention layer, and calculating self-attention weight;
s206, representing the importance of each time step to the predicted target through the self-attention weight, and outputting the next updating time of the target air ticket freight rate data according to iterative calculation.
The importance of each time step to the prediction target is characterized by the self-attention weight, and the calculation formula of the self-attention weight is as followsWherein (1)>Attention score representing hidden layer state at time step t, tanh represents activation function, W c V c Representing self-attention layer parameters, b c Representing the bias, T represents the matrix transpose.
Acquiring the query quantity of each route information in the air ticket booking related website based on a big data means, setting a heterogeneous information retrieval tag according to destination information of the route information, acquiring a retrieval time step according to each updating period, and acquiring the query quantity of the heterogeneous information, wherein the heterogeneous information can be acquired through hotel booking information, travel searching information and the like of a travel service provider; setting a conversion coefficient and combining the query quantity of heterogeneous information, matching the combined data with the query quantity of each route information, and obtaining the final access quantity in each updating period, wherein the conversion coefficient is set by the ratio of aviation passenger flow quantity to total passenger flow quantity in a certain city history contemporaneous period; and (3) associating the final access quantity with the time sequence change sequence, acquiring the association characteristic of the access quantity and the updating period, and constructing a characteristic sample data set.
Constructing an air ticket freight rate data updating model based on an LSTM network optimized by a particle swarm algorithm, setting particles according to the number of hidden layer neurons in the LSTM network, the learning rate and the maximum iteration number, initializing particle parameters including the maximum iteration number, population scale, acceleration coefficient, inertia weight and the like of the particle swarm algorithm, and setting initial positions and speeds; determining a network structure of an LSTM network, setting an adaptability function according to the mean square error of an actual value and a predicted value, carrying out position optimization of particles according to the individual optimization and the global optimization of the particles which are continuously updated, stopping the optimization process when the optimal position is obtained by replacement, and determining parameters of the LSTM network according to the optimal position of the particles; and dividing the characteristic sample data set into a training set and a testing set according to a preset proportion, and outputting an air ticket freight rate data updating model with accuracy meeting a preset standard after iterative training.
The method is characterized in that the influence factors of the air ticket freight rate are obtained through data mining according to the time sequence change sequence and the access volume change sequence of the air ticket freight rate of each route history, the data mining can be realized by using a big data means, the influence factors of the air ticket freight rate are obtained through methods such as literature and related data retrieval, expert experience summarization and the like, the influence factors generally comprise flight self factors, holiday factors, week factors and the like, and the influence factors are screened through methods such as random forest or principal component analysis and the like to obtain an influence factor set influencing the target air ticket freight rate in a past preset time period; an air ticket freight rate prediction network is constructed based on a time convolution neural network, the air ticket freight rate prediction network is formed by combining an expansion convolution network residual error which is formed by merging 3 causal convolutions with a convolution network of 1 multiplied by 1 convolution kernel, and a final prediction result is finally output through a 1-layer full-connection layer;
the acquired next updating time is used as target prediction time, the influencing factors in the influencing factor set are matched with a time sequence change sequence within the past preset time of the target air ticket freight rate, and normalization processing is carried out; and importing the normalized data into an air ticket freight rate prediction network, obtaining a predicted air ticket freight rate of target prediction time, and storing the next update time and the predicted air ticket freight rate after setting a data label.
FIG. 3 illustrates a flow chart of a method of the present invention for invoking air ticket fare data in stored data based on a user's search time stamp.
According to the embodiment of the invention, the air ticket freight rate data in the stored data is called based on the time stamp searched by the user, and the output result is returned to the user side, specifically:
s302, acquiring historical behavior data of a user, acquiring interaction information of the user and an air ticket project node in a preset time step according to the historical behavior data, and generating a bipartite graph structure for the air ticket project through the interaction information;
s304, acquiring basic information, leg information and advanced ticket buying time information of a user as additional features of nodes in the two-part graph structure;
s306, learning and representing the two-part graph structure based on a graph convolution neural network to obtain initial vector representations of a user and an air ticket project, splicing the initial vector representations of the user and the air ticket project, and constructing an adjacent matrix;
s308, through a message transmission mechanism and a neighbor aggregation mechanism of the graph convolutional neural network, feature transmission between nodes is carried out based on an adjacency matrix, features of neighbor nodes are learned, and embedded representation of user nodes is updated;
S310, additionally, obtaining air ticket items interacted by each time stamp of a user in a preset time step, splicing corresponding two graph structures, constructing a meta path in the preset time step, and matching the meta path with the user;
s312, obtaining similarity between users by calculating the mean square distance of nodes on a meta-path between the users, taking the similarity as attention weight, and utilizing a graph attention structure to aggregate the embedded representation of the user nodes to output final user preference characteristics;
s314, acquiring corresponding air ticket freight rate data according to the search information of the user, analyzing freight rate change trend of the air ticket according to the preference characteristics of the user and combining the acquired next updating time and predicted air ticket freight rate, and returning the queried information and freight rate change trend to the user side.
By the way, use is made ofThe graph attention structure aggregates the embedded representations of the user nodes to output final user preference characteristics, and the specific formulas of the user preference characteristics are as follows: wherein f u Representing a preference feature of user u, σ represents a nonlinear activation function, W s Representing a shared structure matrix, h v Embedded representation representing other user v-nodes, alpha uv Representing attention weight,/->Representing the set of neighbor nodes for user u.
And when the target user searches the air ticket, acquiring the time difference between the time stamp searched by the target user and the departure time of the target air ticket, acquiring the next updating time of the target air ticket and the predicted air ticket freight rate, and analyzing freight rate change trend of the air ticket freight rate in the time difference according to the prediction of a plurality of time steps.
According to the embodiment of the invention, a personalized database is constructed according to the personal preference characteristics of the user, specifically:
acquiring interaction behaviors of a target user in an air ticket booking website to construct a personalized data set, and carrying out preference analysis according to the interaction behavior data in preset time to acquire preference characteristics of the target user in the current preset time;
when the target user performs the air ticket searching process, performing air ticket recommendation on the target user according to the preference characteristics, and performing key annotation on air ticket information according to the searching behaviors of the target user, and monitoring the air ticket with the key annotation;
in the monitoring process, acquiring an update period and update frequency of the air ticket freight rate, judging a price trend, and outputting optimal purchase time based on the preference characteristics of a target user;
and acquiring the interaction behavior of the target user in real time, updating the personalized database, updating the corresponding preference characteristics, and deleting the personalized data of the target object when the timestamp corresponding to the interaction behavior of the target user exceeds a preset storage time threshold.
The user preference includes a preference departure time, a predetermined advance time, a predetermined price feature, a travel location feature, and the like of the user.
FIG. 4 shows a block diagram of a machine learning based airline ticket fare data processing system of the present invention.
The second aspect of the present invention also provides a machine learning based airline ticket fare data processing system 4, the system comprising: the memory 41 and the processor 42, wherein the memory comprises a machine learning-based airline ticket freight rate data processing method program, and the machine learning-based airline ticket freight rate data processing method program realizes the following steps when being executed by the processor:
acquiring historical air ticket freight rate data, dividing the historical air ticket freight rate data into different data sets according to the airline information, and carrying out time sequence analysis on the different data sets to acquire time sequence change sequences of the air ticket freight rates of all the airlines;
acquiring update periods and update frequencies of historical air ticket freight rates according to the time sequence change sequence, acquiring access amounts of each route in each update period based on a big data means, and associating the access amounts with the time sequence change sequence to acquire a characteristic sample data set;
Constructing an air ticket freight rate data updating model based on machine learning, training by utilizing the characteristic sample data set, and outputting the trained air ticket freight rate data updating model after the test reaches the standard;
acquiring multi-source air ticket freight rate data, screening the multi-source air ticket freight rate data according to a preset parameterized reference, acquiring next update time of the air ticket freight rate data through an air ticket freight rate data update model, acquiring predicted air ticket freight rate based on the next update time, and setting a data tag for data storage;
and calling the air ticket freight rate data in the stored data based on the time stamp searched by the user, and returning the output result to the user side.
The method comprises the steps of extracting keyword information in historical air ticket freight rate data, determining departure city information and destination city information according to the keyword information, extracting route information, and setting classification labels based on the route information; classifying the historical air ticket freight rate data according to the classification labels, obtaining air ticket freight rate data sets under different classification labels, and marking the corresponding air ticket freight rate data according to holiday information and common day information; and carrying out time sequence analysis on the air ticket freight rate data under different marks, obtaining the change time stamp and the change difference of the air ticket freight rate, generating time sequence change sequences of each route, and obtaining the update period and the update frequency of the historical air ticket freight rate.
According to the embodiment of the invention, the next update time of the air ticket freight rate data is obtained through the air ticket freight rate data update model, and specifically comprises the following steps:
screening the multi-source air ticket freight rate data to obtain target air ticket freight rate data, extracting the route information, time information and bin position information of the target air ticket freight rate data, and obtaining a time sequence change sequence and an access quantity change sequence in the past preset time as input of an air ticket freight rate data updating model;
introducing a self-attention mechanism into an air ticket freight rate data updating model, constructing a self-attention layer, taking hidden layer state outputs of different time steps as input of the self-attention layer, and calculating self-attention weight;
and representing the importance of each time step to the predicted target through the self-attention weight, and outputting the next updating time of the target air ticket freight rate data according to iterative calculation.
The importance of each time step to the prediction target is characterized by the self-attention weight, and the calculation formula of the self-attention weight is as followsWherein (1)>Attention score representing hidden layer state at time step tTanh represents an activation function, W c V c Representing self-attention layer parameters, b c Representing the bias, T represents the matrix transpose.
Acquiring the query quantity of each route information in the air ticket booking related website based on a big data means, setting a heterogeneous information retrieval tag according to destination information of the route information, acquiring a retrieval time step according to each updating period, and acquiring the query quantity of the heterogeneous information, wherein the heterogeneous information can be acquired through hotel booking information, travel searching information and the like of a travel service provider; setting a conversion coefficient and combining the query quantity of heterogeneous information, matching the combined data with the query quantity of each route information, and obtaining the final access quantity in each updating period, wherein the conversion coefficient is set by the ratio of aviation passenger flow quantity to total passenger flow quantity in a certain city history contemporaneous period; and (3) associating the final access quantity with the time sequence change sequence, acquiring the association characteristic of the access quantity and the updating period, and constructing a characteristic sample data set.
Constructing an air ticket freight rate data updating model based on an LSTM network optimized by a particle swarm algorithm, setting particles according to the number of hidden layer neurons in the LSTM network, the learning rate and the maximum iteration number, initializing particle parameters including the maximum iteration number, population scale, acceleration coefficient, inertia weight and the like of the particle swarm algorithm, and setting initial positions and speeds; determining a network structure of an LSTM network, setting an adaptability function according to the mean square error of an actual value and a predicted value, carrying out position optimization of particles according to the individual optimization and the global optimization of the particles which are continuously updated, stopping the optimization process when the optimal position is obtained by replacement, and determining parameters of the LSTM network according to the optimal position of the particles; and dividing the characteristic sample data set into a training set and a testing set according to a preset proportion, and outputting an air ticket freight rate data updating model with accuracy meeting a preset standard after iterative training.
The method is characterized in that the influence factors of the air ticket freight rate are obtained through data mining according to the time sequence change sequence and the access volume change sequence of the air ticket freight rate of each route history, the data mining can be realized by using a big data means, the influence factors of the air ticket freight rate are obtained through methods such as literature and related data retrieval, expert experience summarization and the like, the influence factors generally comprise flight self factors, holiday factors, week factors and the like, and the influence factors are screened through methods such as random forest or principal component analysis and the like to obtain an influence factor set influencing the target air ticket freight rate in a past preset time period; an air ticket freight rate prediction network is constructed based on a time convolution neural network, the air ticket freight rate prediction network is formed by combining an expansion convolution network residual error which is formed by merging 3 causal convolutions with a convolution network of 1 multiplied by 1 convolution kernel, and a final prediction result is finally output through a 1-layer full-connection layer;
the acquired next updating time is used as target prediction time, the influencing factors in the influencing factor set are matched with a time sequence change sequence within the past preset time of the target air ticket freight rate, and normalization processing is carried out; and importing the normalized data into an air ticket freight rate prediction network, obtaining a predicted air ticket freight rate of target prediction time, and storing the next update time and the predicted air ticket freight rate after setting a data label.
According to the embodiment of the invention, the air ticket freight rate data in the stored data is called based on the time stamp searched by the user, and the output result is returned to the user side, specifically:
acquiring historical behavior data of a user, acquiring interaction information of the user and an air ticket project node in a preset time step according to the historical behavior data, and generating a bipartite graph structure for the air ticket project through the interaction information;
acquiring basic information, leg information and advanced ticket buying time information of a user as additional features of nodes in the two-part graph structure;
learning and representing the two-part graph structure based on a graph convolution neural network to obtain initial vector representations of a user and an air ticket project, splicing the initial vector representations of the user and the air ticket project, and constructing an adjacent matrix;
the characteristic transfer between nodes is carried out based on the adjacency matrix through a message transfer mechanism and a neighbor aggregation mechanism of the graph convolutional neural network, the characteristics of neighbor nodes are learned, and the embedded representation of the user nodes is updated;
in addition, acquiring air ticket items interacted by each time stamp of a user in a preset time step, splicing corresponding two graph structures, constructing a meta path in the preset time step, and matching the meta path with the user;
Obtaining similarity between users by calculating the mean square distance of nodes on a meta-path between the users, taking the similarity as attention weight, and utilizing a graph attention structure to aggregate the embedded representation of the user nodes to output final user preference characteristics;
and acquiring corresponding air ticket freight rate data according to the search information of the user, analyzing freight rate change trend of the air ticket according to the acquired next updating time and predicted air ticket freight rate according to the preference characteristics of the user, and returning the queried information and freight rate change trend to the user side.
It should be noted that, the embedded representation of the user node is aggregated by using the graph attention structure to output the final user preference feature, and the specific formula of the user preference feature is as follows: wherein f u Representing a preference feature of user u, σ represents a nonlinear activation function, W s Representing a shared structure matrix, h v Embedded representation representing other user v-nodes, alpha uv Representing attention weight,/->Representing the set of neighbor nodes for user u.
And when the target user searches the air ticket, acquiring the time difference between the time stamp searched by the target user and the departure time of the target air ticket, acquiring the next updating time of the target air ticket and the predicted air ticket freight rate, and analyzing freight rate change trend of the air ticket freight rate in the time difference according to the prediction of a plurality of time steps.
The third aspect of the present invention also provides a computer readable storage medium, including a machine learning-based airline ticket freight rate data processing method program, where the machine learning-based airline ticket freight rate data processing method program is executed by a processor to implement the steps of the machine learning-based airline ticket freight rate data processing method according to any one of the above.
In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.
The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units; can be located in one place or distributed to a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present invention may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or an optical disk, or the like, which can store program codes.
Alternatively, the above-described integrated units of the present invention may be stored in a computer-readable storage medium if implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within 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 (10)
1. The machine learning-based method for processing the freight rate data of the airline ticket is characterized by comprising the following steps of:
acquiring historical air ticket freight rate data, dividing the historical air ticket freight rate data into different data sets according to the airline information, and carrying out time sequence analysis on the different data sets to acquire time sequence change sequences of the air ticket freight rates of all the airlines;
acquiring update periods and update frequencies of historical air ticket freight rates according to the time sequence change sequence, acquiring access amounts of each route in each update period based on a big data means, and associating the access amounts with the time sequence change sequence to acquire a characteristic sample data set;
constructing an air ticket freight rate data updating model based on machine learning, training by utilizing the characteristic sample data set, and outputting the trained air ticket freight rate data updating model after the test reaches the standard;
acquiring multi-source air ticket freight rate data, screening the multi-source air ticket freight rate data according to a preset parameterized reference, acquiring next update time of the air ticket freight rate data through an air ticket freight rate data update model, acquiring predicted air ticket freight rate based on the next update time, and setting a data tag for data storage;
and calling the air ticket freight rate data in the stored data based on the time stamp searched by the user, and returning the output result to the user side.
2. The machine learning-based method for processing the freight rate data of the airline ticket according to claim 1, wherein the historical freight rate data of the airline ticket is divided into different data sets according to the airline information, and the time sequence analysis is carried out on the different data sets to obtain the time sequence change sequence of freight rates of the airline ticket, specifically:
extracting keyword information in historical air ticket freight rate data, determining departure city information and destination city information according to the keyword information, extracting route information, and setting classification labels based on the route information;
classifying the historical air ticket freight rate data according to the classification labels, obtaining air ticket freight rate data sets under different classification labels, and marking the corresponding air ticket freight rate data according to holiday information and common day information;
and carrying out time sequence analysis on the air ticket freight rate data under different marks, obtaining the change time stamp and the change difference of the air ticket freight rate, generating time sequence change sequences of each route, and obtaining the update period and the update frequency of the historical air ticket freight rate.
3. The machine learning-based airline ticket freight rate data processing method according to claim 1, wherein an airline ticket freight rate data update model is constructed based on machine learning, training is performed by using the characteristic sample data set, and after the test is up to standard, the trained airline ticket freight rate data update model is output, specifically:
Acquiring the inquiry quantity of each route information in the air ticket booking related website based on a big data means, setting a heterogeneous information retrieval tag according to destination information of the route information, and acquiring a retrieval time step according to each updating period to acquire the inquiry quantity of the heterogeneous information;
setting conversion coefficients and the query quantity of heterogeneous information to be combined, matching the combined data with the query quantity of each route information to obtain final access quantity in each updating period, correlating the final access quantity with a time sequence change sequence, obtaining correlation characteristics of the access quantity and the updating period, and constructing a characteristic sample data set;
constructing an air ticket freight rate data updating model based on an LSTM network optimized by a particle swarm algorithm, setting particles according to the number of hidden layer neurons in the LSTM network, the learning rate and the maximum iteration number, initializing particle parameters, and setting initial positions and speeds;
setting a fitness function according to the mean square error, carrying out particle position optimization according to the continuous updating of individual particle optimization and global optimization, and determining parameters of an LSTM network according to the optimal particle position;
and dividing the characteristic sample data set into a training set and a testing set according to a preset proportion, and outputting an air ticket freight rate data updating model with accuracy meeting a preset standard after iterative training.
4. The machine learning-based method for processing air ticket freight rate data according to claim 1, wherein the next update time of the air ticket freight rate data is obtained through an air ticket freight rate data update model, specifically:
screening the multi-source air ticket freight rate data to obtain target air ticket freight rate data, extracting the route information, time information and bin position information of the target air ticket freight rate data, and obtaining a time sequence change sequence and an access quantity change sequence in the past preset time as input of an air ticket freight rate data updating model;
introducing a self-attention mechanism into an air ticket freight rate data updating model, constructing a self-attention layer, taking hidden layer state outputs of different time steps as input of the self-attention layer, and calculating self-attention weight;
and representing the importance of each time step to the predicted target through the self-attention weight, and outputting the next updating time of the target air ticket freight rate data according to iterative calculation.
5. The machine learning-based method for processing the freight rate data of the airline ticket according to claim 1 or 4, wherein the predicted freight rate of the airline ticket is obtained based on the next update time, and the data tag is set for data storage, specifically:
According to the time sequence change sequence and the access volume change sequence of the historical air ticket freight rate of each route, acquiring influence factors of the air ticket freight rate through data mining, and screening the influence factors to acquire an influence factor set which influences the target air ticket freight rate in a preset time period in the past;
constructing an air ticket freight rate prediction network based on a time convolution neural network, taking the acquired next updating time as target prediction time, matching the influencing factors in the influencing factor set with a time sequence change sequence of the target air ticket freight rate in the past preset time, and carrying out normalization processing;
and importing the normalized data into an air ticket freight rate prediction network, obtaining a predicted air ticket freight rate of target prediction time, and storing the next update time and the predicted air ticket freight rate after setting a data label.
6. The machine learning-based method for processing air ticket freight rate data according to claim 1, wherein the air ticket freight rate data in the stored data is called based on the time stamp searched by the user, and the output result is returned to the user side, specifically:
acquiring historical behavior data of a user, acquiring interaction information of the user and an air ticket project node in a preset time step according to the historical behavior data, and generating a bipartite graph structure for the air ticket project through the interaction information;
Acquiring basic information, leg information and advanced ticket buying time information of a user as additional features of nodes in the two-part graph structure;
learning and representing the two-part graph structure based on a graph convolution neural network to obtain initial vector representations of a user and an air ticket project, splicing the initial vector representations of the user and the air ticket project, and constructing an adjacent matrix;
the characteristic transfer between nodes is carried out based on the adjacency matrix through a message transfer mechanism and a neighbor aggregation mechanism of the graph convolutional neural network, the characteristics of neighbor nodes are learned, and the embedded representation of the user nodes is updated;
in addition, acquiring air ticket items interacted by each time stamp of a user in a preset time step, splicing corresponding two graph structures, constructing a meta path in the preset time step, and matching the meta path with the user;
obtaining similarity between users by calculating the mean square distance of nodes on a meta-path between the users, taking the similarity as attention weight, and utilizing a graph attention structure to aggregate the embedded representation of the user nodes to output final user preference characteristics;
and acquiring corresponding air ticket freight rate data according to the search information of the user, analyzing freight rate change trend of the air ticket according to the acquired next updating time and predicted air ticket freight rate according to the preference characteristics of the user, and returning the queried information and freight rate change trend to the user side.
7. A machine learning-based airline ticket fare data processing system, the system comprising: the system comprises a memory and a processor, wherein the memory comprises a machine learning-based airline ticket freight rate data processing method program, and the machine learning-based airline ticket freight rate data processing method program realizes the following steps when being executed by the processor:
acquiring historical air ticket freight rate data, dividing the historical air ticket freight rate data into different data sets according to the airline information, and carrying out time sequence analysis on the different data sets to acquire time sequence change sequences of the air ticket freight rates of all the airlines;
acquiring update periods and update frequencies of historical air ticket freight rates according to the time sequence change sequence, acquiring access amounts of each route in each update period based on a big data means, and associating the access amounts with the time sequence change sequence to acquire a characteristic sample data set;
constructing an air ticket freight rate data updating model based on machine learning, training by utilizing the characteristic sample data set, and outputting the trained air ticket freight rate data updating model after the test reaches the standard;
acquiring multi-source air ticket freight rate data, screening the multi-source air ticket freight rate data according to a preset parameterized reference, acquiring next update time of the air ticket freight rate data through an air ticket freight rate data update model, acquiring predicted air ticket freight rate based on the next update time, and setting a data tag for data storage;
And calling the air ticket freight rate data in the stored data based on the time stamp searched by the user, and returning the output result to the user side.
8. The machine learning-based airline ticket freight rate data processing system according to claim 7, wherein an airline ticket freight rate data update model is constructed based on machine learning, training is performed by using the characteristic sample data set, and after the test is up to standard, the trained airline ticket freight rate data update model is output, specifically:
acquiring the inquiry quantity of each route information in the air ticket booking related website based on a big data means, setting a heterogeneous information retrieval tag according to destination information of the route information, and acquiring a retrieval time step according to each updating period to acquire the inquiry quantity of the heterogeneous information;
setting conversion coefficients and the query quantity of heterogeneous information to be combined, matching the combined data with the query quantity of each route information to obtain final access quantity in each updating period, correlating the final access quantity with a time sequence change sequence, obtaining correlation characteristics of the access quantity and the updating period, and constructing a characteristic sample data set;
constructing an air ticket freight rate data updating model based on an LSTM network optimized by a particle swarm algorithm, setting particles according to the number of hidden layer neurons in the LSTM network, the learning rate and the maximum iteration number, initializing particle parameters, and setting initial positions and speeds;
Setting a fitness function according to the mean square error, carrying out particle position optimization according to the continuous updating of individual particle optimization and global optimization, and determining parameters of an LSTM network according to the optimal particle position;
and dividing the characteristic sample data set into a training set and a testing set according to a preset proportion, and outputting an air ticket freight rate data updating model with accuracy meeting a preset standard after iterative training.
9. The machine learning-based airline ticket freight rate data processing system according to claim 7, wherein the next update time of the ticket freight rate data is obtained by the ticket freight rate data update model, specifically:
screening the multi-source air ticket freight rate data to obtain target air ticket freight rate data, extracting the route information, time information and bin position information of the target air ticket freight rate data, and obtaining a time sequence change sequence and an access quantity change sequence in the past preset time as input of an air ticket freight rate data updating model;
introducing a self-attention mechanism into an air ticket freight rate data updating model, constructing a self-attention layer, taking hidden layer state outputs of different time steps as input of the self-attention layer, and calculating self-attention weight;
And representing the importance of each time step to the predicted target through the self-attention weight, and outputting the next updating time of the target air ticket freight rate data according to iterative calculation.
10. A computer-readable storage medium, characterized by: the computer readable storage medium includes a machine learning-based airline ticket freight rate data processing method program, which when executed by a processor, implements the machine learning-based airline ticket freight rate data processing method steps of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310490403.8A CN116503086A (en) | 2023-05-04 | 2023-05-04 | Method, system and medium for processing freight rate data of airline ticket based on machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310490403.8A CN116503086A (en) | 2023-05-04 | 2023-05-04 | Method, system and medium for processing freight rate data of airline ticket based on machine learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116503086A true CN116503086A (en) | 2023-07-28 |
Family
ID=87329968
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310490403.8A Pending CN116503086A (en) | 2023-05-04 | 2023-05-04 | Method, system and medium for processing freight rate data of airline ticket based on machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116503086A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117271886A (en) * | 2023-08-25 | 2023-12-22 | 广东美亚旅游科技集团股份有限公司 | Data searching method, system, equipment and medium based on air ticket order management |
-
2023
- 2023-05-04 CN CN202310490403.8A patent/CN116503086A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117271886A (en) * | 2023-08-25 | 2023-12-22 | 广东美亚旅游科技集团股份有限公司 | Data searching method, system, equipment and medium based on air ticket order management |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110163647B (en) | Data processing method and device | |
| VE et al. | Season wise bike sharing demand analysis using random forest algorithm | |
| WO2017190610A1 (en) | Target user orientation method and device, and computer storage medium | |
| CN112632405B (en) | Recommendation method, recommendation device, recommendation equipment and storage medium | |
| CN108885624A (en) | Information recommendation system and method | |
| CN111612499B (en) | Information pushing method and device, storage medium and terminal | |
| CN110852785B (en) | User grading method, device and computer readable storage medium | |
| Vahidi Farashah et al. | An analytics model for TelecoVAS customers’ basket clustering using ensemble learning approach | |
| CN117473431B (en) | Airport data classification and classification method and system based on knowledge graph | |
| US20140250044A1 (en) | Method and system using association rules to form custom lists of cookies | |
| CN116503086A (en) | Method, system and medium for processing freight rate data of airline ticket based on machine learning | |
| Khandokar et al. | A gradient boosting classifier for purchase intention prediction of online shoppers | |
| Singh et al. | Analysis of machine learning techniques for airfare prediction | |
| Dai | A hybrid machine learning-based model for predicting flight delay through aviation big data | |
| Choi et al. | Fake review identification and utility evaluation model using machine learning | |
| Vicenzi et al. | Exploring frequency-based approaches for efficient trajectory classification | |
| Wu et al. | [Retracted] Using the Mathematical Model on Precision Marketing with Online Transaction Data Computing | |
| WO2023051085A1 (en) | Object recognition method and apparatus, device, storage medium and program product | |
| US20230027530A1 (en) | Artificial intelligence (ai) engine assisted creation of production descriptions | |
| CN112926701B (en) | GCN semi-supervision-based classification method, system and equipment for airline passengers | |
| Hamad et al. | Sentiment analysis of restaurant reviews in social media using naïve bayes | |
| TWM573493U (en) | System for predicting conversion probability by visitors' browsing paths | |
| CN114925290A (en) | Self-service user group expansion method and device, computer equipment and storage medium | |
| CN111400567B (en) | AI-based user data processing method, device and system | |
| Parbat et al. | Understanding the customer perception using machine learning while booking flight tickets |
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 |