CN117522501A - Informationized labeling method and system for user air ticket order management - Google Patents

Informationized labeling method and system for user air ticket order management Download PDF

Info

Publication number
CN117522501A
CN117522501A CN202311086737.5A CN202311086737A CN117522501A CN 117522501 A CN117522501 A CN 117522501A CN 202311086737 A CN202311086737 A CN 202311086737A CN 117522501 A CN117522501 A CN 117522501A
Authority
CN
China
Prior art keywords
user
neural network
network module
linear node
travel
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.)
Granted
Application number
CN202311086737.5A
Other languages
Chinese (zh)
Other versions
CN117522501B (en
Inventor
邵玲
廖伟山
花钰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangdong Meiya Business Travel Technology Co ltd
Original Assignee
Guangdong Meiya Business Travel Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangdong Meiya Business Travel Technology Co ltd filed Critical Guangdong Meiya Business Travel Technology Co ltd
Priority to CN202311086737.5A priority Critical patent/CN117522501B/en
Publication of CN117522501A publication Critical patent/CN117522501A/en
Application granted granted Critical
Publication of CN117522501B publication Critical patent/CN117522501B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0633—Lists, e.g. purchase orders, compilation or processing
    • G06Q30/0635—Processing of requisition or of purchase orders
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/29—Geographical information databases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • 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
    • 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
    • G06N3/045—Combinations of 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
    • G06N3/0464—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
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Software Systems (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Mathematical Physics (AREA)
  • Biomedical Technology (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Databases & Information Systems (AREA)
  • Finance (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Remote Sensing (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention relates to an informationized label method and system for user ticket order management, which monitor and acquire order data constructed by a user based on a preset neural network module; calling departure place information and destination information carried in the order data at the same time, and generating a linear node path through linear node processing of the neural network module; monitoring a travel signal fed back by a user in a cloud database through the linear node path; labeling each travel signal fed back by a user on a linear node path, judging whether the linear node path is labeled completely, if not, determining that the travel of the user is not finished, and continuously monitoring; if yes, the user journey is determined to be ended, and a linear node path is marked correspondingly on a map sub-database pre-stored under the user ID; the method and the system improve order processing efficiency, track real-time travel, simplify user experience, improve order accuracy and provide personalized services.

Description

Informationized labeling method and system for user air ticket order management
Technical Field
The invention relates to the technical field of data processing, in particular to an informationized label method and system for user ticket order management.
Background
With the development of the aviation industry and the increase in global travel, ticket order management has become a critical challenge. Conventional order management methods often face complex order data and cumbersome information processing. This complexity results in inefficiency and error rate of order processing and inconvenience to the user.
In order to improve the problem of ticket order management, some related techniques have emerged. These techniques include big data analysis, cloud computing, artificial intelligence, and neural networks. Big data analysis can be used to process vast amounts of order information from which valuable information and trends are found. Cloud computing may provide a reliable and secure environment for storing and processing order data. Artificial intelligence and neural networks can then improve the intelligence and accuracy of order processing by learning and analyzing historical order data.
However, while the related art is helpful in improving ticket order management, there are some technical drawbacks. The conventional method still requires a lot of manpower and manual operations, which are prone to errors and delays. In addition, in some cases, conventional methods cannot update order status in real time, thereby causing unnecessary confusion to the user. In addition, the complexity and variety of processing order data is also a challenge that the prior art needs to address.
Disclosure of Invention
The invention mainly aims to provide an informationized label method and an informationized label system for user air ticket order management, so that order processing efficiency is improved, real-time travel tracking is realized, user experience is simplified, order accuracy is improved, and personalized service is provided.
In order to achieve the above object, the present invention provides an information-based labeling method for user ticket order management, comprising the steps of:
based on a preset neural network module, monitoring and acquiring order data constructed by a user;
calling departure place information and destination information carried in the order data at the same time, and generating a linear node path through linear node processing of the neural network module;
monitoring a travel signal fed back by a user in a cloud database through the linear node path;
labeling each travel signal fed back by a user on a linear node path, judging whether the linear node path is labeled completely, if not, determining that the travel of the user is not finished, and continuously monitoring;
if yes, the user journey is judged to be ended, and the linear node paths are marked correspondingly on the map sub-database pre-stored under the user ID.
Further, the step of training the neural network module includes:
selecting a CNN convolutional neural network module and an RNN convolutional neural network module;
selecting historical order data from a preset database to extract characteristics of the historical order data to obtain a first training set and a second training set, and a first verification set and a second verification set; extracting a time relation and a space relation in historical order data by using a CNN convolutional neural network module as the first training set; extracting evolution relations and word sense relations in the historical order data through an RNN (RNN recurrent neural network) module to serve as the second training set, wherein the first verification set and the second verification set are actual data in the historical order data respectively and are used for verifying the first training set and the second training set in a one-to-one correspondence mode;
at one moment, the CNN convolutional neural network module performs regional characteristic calibration on the first training set obtained by extraction, wherein the regional characteristic calibration comprises a spatial relationship used for calibrating a departure place and a destination in the first training set and a time relationship used for calibrating a travel date in the first training set;
at one moment, the RNN circulating neural network module performs sequential feature calibration on the extracted second training set, wherein the sequential feature calibration comprises a word meaning relation for calibrating the evolution relation between the seat number and the flight information in the second training set and calibrating the user name in the second training set;
in an embedding layer of the neural network module, converting discrete spatial relationships, time relationships, evolution relationships and word sense relationships into continuous training vectors;
adding the first verification set to a first output layer of a CNN convolutional neural network module, adding the second verification set to a second output layer of an RNN convolutional neural network module, and performing feature fusion on the first verification set and the second verification set based on the historical order data to further drive the first output layer and the second output layer to be fused to form an output layer of the neural network module;
and outputting the training linear node path corresponding to the training vector in the output layer of the neural network module, optimizing the verification set fused on the output layer based on the training linear node path passing through the output layer of the neural network module, and optimizing the whole neural network module by back propagation based on the optimization of the training set.
Further, based on a preset neural network module, the step of monitoring and acquiring order data constructed by a user comprises the following steps:
monitoring payment factors on a cloud database by adopting an input layer of the neural network module; wherein, the payment factor is a payment success signal generated when the user creates an air ticket order;
if the payment factor is monitored, acquiring order data associated with the payment factor by using an input layer of the neural network module;
and if the payment factor is not monitored, the input layer of the neural network module withdraws order data associated with the payment factor.
Further, the step of calling the departure place information and the destination information carried in the order data, and generating a linear node path through linear node processing of the neural network module comprises the following steps:
inputting the order data into an embedded layer of the neural network module for discrete identification; wherein, based on the spatial relationship, the time relationship, the evolution relationship and the word meaning relationship in the order data, at least the departure place information, the destination information and the flight information corresponding to the order data are determined through the discrete identification;
based on the flight information, determining all the route blocking nodes from the departure place information to the destination information, and generating corresponding linear node paths by using all the route blocking nodes;
and outputting the linear node path by using an output layer of the neural network module.
Further, the step of monitoring the travel signal fed back by the user in the cloud database through the linear node path includes:
monitoring all the interface nodes on the linear node path through the cloud database; the monitoring of each of the interface nodes establishes a cloud channel with the cloud database through the interface gate, when a user uses the corresponding certificate to pass through the interface gate, the interface gate generates a travel signal to the cloud database, and the neural network module monitors the travel signal in the cloud database.
Further, the step of labeling each travel signal fed back by the user on the linear node path includes:
and after the travel signals are obtained from the cloud database, marking the corresponding travel signals on the linear node paths one by one.
Further, the step of marking the linear node path corresponding to the map sub-database pre-stored under the user ID includes:
under the condition that the journey of the user is judged to be ended, retrieving the travel date in the order data;
based on the travel dates, arranging the historical travel dates in the map sub-database, and generating an order navigation catalog through the arrangement;
at the same time, generating corresponding travel routes in a map sub-database based on the departure place and the destination of the linear node path;
and packaging the map carrying the travel route and the order navigation directory data, and sending the map and the order navigation directory data to a user ID of the user terminal.
The invention also provides an informationized label system for managing the user air ticket order, which comprises the following steps:
the user unit is used for monitoring and acquiring order data constructed by a user based on a preset neural network module;
the processing unit is used for calling the departure place information and the destination information carried in the order data at the same time, and generating a linear node path through the linear node processing of the neural network module;
the monitoring unit is used for monitoring the travel signal fed back by the user in the cloud database through the linear node path;
the judging unit is used for marking all the travel signals fed back by the user on the linear node paths, judging whether the linear node paths are marked completely or not, if not, judging that the travel of the user is not finished, and continuously monitoring;
and the recording unit is used for determining that the user journey is finished if the user journey is finished so as to mark the linear node path corresponding to the map sub-database pre-stored under the user ID.
The invention also provides computer equipment, which comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the steps of the informationized label method for managing the user ticket order when executing the computer program.
The present invention also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the above described informationized labeling method for customer ticket order management.
The informationized label method and the informationized label system for the user air ticket order management have the following beneficial effects:
the order processing efficiency is improved: through the processing and analysis of the neural network module, a large amount of air ticket order data is automatically and efficiently processed, the time and the manual workload of the traditional manual order processing are greatly reduced, and the order processing efficiency is improved.
Real-time travel tracking: the cloud database and a monitoring mechanism of the user travel signals are adopted to update the travel information of the user in real time, accurately know the state of an order and the latest travel condition, and provide better travel tracking experience.
Order accuracy is improved: through training and feature extraction of the neural network module, the time relationship, the space relationship, the evolution relationship and the word meaning relationship in order data are accurately predicted and marked, the accuracy and the reliability of order processing are improved, and processing errors and misunderstanding are reduced.
Providing personalized services: combining the order data and the travel signals to provide personalized services according to the user demands and preferences, generating corresponding travel routes according to the travel dates and destinations of the user, and providing maps and order navigation catalog data to the user.
Drawings
FIG. 1 is a flow chart of an information labeling method for user ticket order management in accordance with an embodiment of the present invention;
FIG. 2 is a block diagram of an information-based tag system for user ticket order management in accordance with an embodiment of the present invention;
fig. 3 is a block diagram schematically illustrating a structure of a computer device according to an embodiment of the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Referring to fig. 1, a flowchart of an informationized label method for user ticket order management provided by the invention includes the steps of:
s1, monitoring and acquiring order data constructed by a user based on a preset neural network module;
in S1, monitoring a payment factor on a cloud database by adopting an input layer of the neural network module; wherein, the payment factor is a payment success signal generated when the user creates an air ticket order; if the payment factor is monitored, acquiring order data associated with the payment factor by using an input layer of the neural network module; and if the payment factor is not monitored, the input layer of the neural network module withdraws order data associated with the payment factor.
In the implementation of S1:
a preset neural network module: a pre-set neural network module is presented that includes a plurality of layers, nodes, and parameters for processing and analyzing order data. The neural network module adopts different types of modules of a Convolutional Neural Network (CNN) and a cyclic neural network (RNN) so as to adapt to the characteristics and accuracy requirements of order data.
The input layer listens for payment factors: the input layer of the neural network module monitors payment factors on a cloud database; the payment factor refers to a payment success signal generated when the user creates an air ticket order; by monitoring the payment factor, the module can capture the payment state of the user order in real time, thereby triggering the related order data acquisition and processing.
Order data associated with a payment factor: once the input layer of the preset neural network module listens to the payment factor, it automatically acquires order data associated with the payment factor. The module can take the payment factors as input signals and extract order information related to the payment factors from the cloud database.
Order data for unassociated payment factors is withdrawn: if the input layer of the preset neural network module fails to monitor any payment factor, order data which is not related to the payment factor is withdrawn. Only order data of successful payment is captured and processed, so that the accuracy of the data and the effectiveness of processing are improved.
S2, calling the departure place information and the destination information carried in the order data at the same time, and generating a linear node path through linear node processing of the neural network module;
in S2, inputting the order data into an embedded layer of a neural network module for discrete identification; wherein, based on the spatial relationship, the time relationship, the evolution relationship and the word meaning relationship in the order data, at least the departure place information, the destination information and the flight information corresponding to the order data are determined through the discrete identification;
based on the flight information, determining all the route blocking nodes from the departure place information to the destination information, and generating corresponding linear node paths by using all the route blocking nodes;
and outputting the linear node path by using an output layer of the neural network module.
In the implementation of S2:
and (3) discrete identification: the order data is input to the embedded layer of the neural network module for discrete identification. The module can identify spatial relationships, temporal relationships, evolution relationships and word sense relationships in the order data through learning and analysis of the neural network. Through discrete identification, the module can determine departure place information, destination information and flight information corresponding to order data.
The departure place and destination information determination: based on the results of the discrete identification and the flight information in the order data, the module is able to determine all gate paths from the departure information to the destination information, each gate also being referred to as a gate-blocking node during a complete course.
The interface node generates a linear node path: generating a linear node path corresponding to the departure place information and the destination information by the module through the identified interface node; the module orders each of the obstacle nodes between the departure information and the destination information according to the flight information in the order, and forms a linear path from the departure to the destination.
The neural network module outputs a linear node path: all the generated linear node paths are output by the output layer of the module; the module will eventually present the linear node paths to the user in an easy-to-read format so that they can clearly understand the flight path and sequence of the itineraries.
S3, monitoring a travel signal fed back by a user in a cloud database through the linear node path;
in S3, monitoring each of the interference nodes on the linear node path through the cloud database; the monitoring of each of the interface nodes establishes a cloud channel with the cloud database through the interface gate, when a user uses the corresponding certificate to pass through the interface gate, the interface gate generates a travel signal to the cloud database, and the neural network module monitors the travel signal in the cloud database.
In the implementation of S3:
and (3) monitoring a sex node path: the cloud database monitors all the interface nodes on the linear node path; for each airport node, the cloud database establishes a cloud channel between the cloud database and the gate of the obstacle so as to monitor and receive the travel signals related to each obstacle node.
The gate and the cloud channel of the cloud database are in the way: in order to establish information communication, a cloud channel is established between each of the access points and the cloud database. This channel may be used to transmit travel signals generated from the gate of the obstacle to the cloud database. When a user passes airport security check with a corresponding certificate, the gate in the way generates a travel signal and sends the travel signal to a cloud database through a cloud channel.
Monitoring a travel signal: through the established cloud channel, the neural network module can monitor the travel signals in the cloud database; the module receives the travel signals in the cloud database in real time, and updates and tracks the travel information of the user according to the signals.
S4, marking all the travel signals fed back by the user on a linear node path, judging whether the linear node path is marked completely, if not, determining that the travel of the user is not finished, and continuously monitoring;
in S4, after the trip signals are obtained from the cloud database, the corresponding trip signals are marked on the linear node paths one by one.
In the implementation of S4:
marking a travel signal: once the travel signals in the cloud database are monitored, the neural network module marks the travel signals on the linear node paths one by one; and the module associates and marks the corresponding airport nodes in the linear node path according to the information of the journey signal.
Judging whether the test is complete: after labeling the travel signals on the linear node path, the module determines whether the linear node path has been completely labeled with all the travel signals. If any node is not marked, the module will assume that the user's journey has not ended at this time.
Continuously monitoring: if the module judges that the route has unlabeled nodes, namely unfinished routes, the module continues to monitor route signals in the cloud database; the module is ensured to continuously track and update the journey information of the user until the journey of the user is completely ended or cancelled.
And S5, if yes, determining that the user journey is finished, and marking the linear node path correspondingly on a map sub-database pre-stored under the user ID.
In S5, when it is determined that the user has completed the journey, retrieving the travel date in the order data;
based on the travel dates, arranging the historical travel dates in the map sub-database, and generating an order navigation catalog through the arrangement;
at the same time, generating corresponding travel routes in a map sub-database based on the departure place and the destination of the linear node path;
and packaging the map carrying the travel route and the order navigation directory data, and sending the map and the order navigation directory data to a user ID of the user terminal.
In the implementation of S5:
user trip end determination: once the module determines that the user's journey has ended, the next operation will be performed; this determination is based on the module checking in S4 that all travel signals on the linear node path have been marked.
Travel date arrangement and order navigation catalog generation: once the travel date is determined, the module will rank the historical travel dates in the map sub-database; the historical travel date contains travel information for the user. Based on the ranking results, the module will generate an order navigation directory to facilitate the user's search and navigation of his journey.
Travel route generation: meanwhile, according to the departure place and destination information of the linear node path, the module generates corresponding travel routes in the map sub-database. The travel route may be a complete path showing the user's navigation route from the origin to the destination.
Data packing and sending: finally, the module packages the data including the travel routes, the map, and the order navigation directory. This data packet will be sent to the user terminal for viewing and use by the user based on the user's ID.
In one embodiment, the step of training the neural network module includes:
selecting a CNN convolutional neural network module and an RNN convolutional neural network module;
selecting historical order data from a preset database to extract characteristics of the historical order data to obtain a first training set and a second training set, and a first verification set and a second verification set; extracting a time relation and a space relation in historical order data by using a CNN convolutional neural network module as the first training set; extracting evolution relations and word sense relations in the historical order data through an RNN (RNN recurrent neural network) module to serve as the second training set, wherein the first verification set and the second verification set are actual data in the historical order data respectively and are used for verifying the first training set and the second training set in a one-to-one correspondence mode;
at one moment, the CNN convolutional neural network module performs regional characteristic calibration on the first training set obtained by extraction, wherein the regional characteristic calibration comprises a spatial relationship used for calibrating a departure place and a destination in the first training set and a time relationship used for calibrating a travel date in the first training set;
at one moment, the RNN circulating neural network module performs sequential feature calibration on the extracted second training set, wherein the sequential feature calibration comprises a word meaning relation for calibrating the evolution relation between the seat number and the flight information in the second training set and calibrating the user name in the second training set;
in an embedding layer of the neural network module, converting discrete spatial relationships, time relationships, evolution relationships and word sense relationships into continuous training vectors;
adding the first verification set to a first output layer of a CNN convolutional neural network module, adding the second verification set to a second output layer of an RNN convolutional neural network module, and performing feature fusion on the first verification set and the second verification set based on the historical order data to further drive the first output layer and the second output layer to be fused to form an output layer of the neural network module;
and outputting the training linear node path corresponding to the training vector in the output layer of the neural network module, optimizing the verification set fused on the output layer based on the training linear node path passing through the output layer of the neural network module, and optimizing the whole neural network module by back propagation based on the optimization of the training set.
In the specific implementation process:
selecting a CNN convolutional neural network module and an RNN cyclic neural network module: two neural network modules, namely a convolutional neural network module and a cyclic neural network module, are selected to be used; convolutional Neural Networks (CNNs) are commonly used to extract features of image or spatial data, while Recurrent Neural Networks (RNNs) are used to process sequential and time-series data.
Feature extraction and dataset selection: historical order data are selected from a preset database, and feature extraction is carried out on the historical order data to obtain a first training set and a second training set, and a first verification set and a second verification set. The CNN convolutional neural network module is responsible for extracting a time relation and a space relation in the historical order data to serve as a first training set, and the RNN convolutional neural network module extracts an evolution relation and a word meaning relation to serve as a second training set. The first verification set and the second verification set are actual data in the historical order data and are used for verifying results of the first training set and the second training set.
Regional feature calibration and sequential feature calibration: and at one moment, the CNN convolutional neural network module performs regional characteristic calibration on the first training set, wherein the regional characteristic calibration comprises the calibration of the spatial relationship between the departure place and the destination and the time relationship of the travel date. Meanwhile, the RNN cyclic neural network module performs sequential feature calibration on the second training set, wherein the sequential feature calibration comprises calibration of the evolution relationship between the seat number and the flight information and the word meaning relationship of the user name.
Vectorization processing: in the embedded layer of the neural network module, discrete spatial relationships, temporal relationships, evolutionary relationships, and word sense relationships are converted into continuous training vectors so that the neural network can process and learn these features.
Feature fusion and output layer: the first verification set is added to a first output layer of the CNN convolutional neural network module, and the second verification set is added to a second output layer of the RNN convolutional neural network module. And then, performing feature fusion on the first verification set and the second verification set based on the historical order data, and further fusing to form an output layer of the neural network module.
Training and tuning: in the output layer of the neural network module, a training linear node path corresponding to the training vector is output. Based on the historical order data, the whole neural network module is optimized in a back propagation mode so as to optimize the verification set fused on the output layer.
Referring to fig. 2, a block diagram of an informationized tag system for user ticket order management according to the present invention includes:
the user unit 10 is configured to monitor and acquire order data constructed by a user based on a preset neural network module;
the processing unit 20 is configured to invoke the departure place information and the destination information carried in the order data at the same time, and generate a linear node path through linear node processing of the neural network module;
the monitoring unit 30 is configured to monitor, in the cloud database, a travel signal fed back by the user through the linear node path;
the judging unit 40 is configured to label each travel signal fed back by the user on a linear node path, and judge whether the linear node path is labeled completely, if not, it is determined that the travel of the user is not finished, and monitor continuously;
and the recording unit 50 is used for determining that the user journey is finished if the user journey is finished, so as to correspondingly mark the linear node path on a map sub-database pre-stored under the user ID.
In this embodiment, for specific implementation of each unit in the above embodiment of the apparatus, please refer to the description in the above embodiment of the method, and no further description is given here.
Referring to fig. 3, in an embodiment of the present invention, there is further provided a computer device, which may be a server, and an internal structure thereof may be as shown in fig. 3. The computer device includes a processor, a memory, a display screen, an input device, a network interface, and a database connected by a system bus. Wherein the computer is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used to store the corresponding data in this embodiment. The network interface of the computer device is used for communicating with an external terminal through a network connection. Which computer program, when being executed by a processor, carries out the above-mentioned method.
It will be appreciated by those skilled in the art that the architecture shown in fig. 3 is merely a block diagram of a portion of the architecture in connection with the present inventive arrangements and is not intended to limit the computer devices to which the present inventive arrangements are applicable.
An embodiment of the present invention also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the above method. It is understood that the computer readable storage medium in this embodiment may be a volatile readable storage medium or a nonvolatile readable storage medium.
In summary, the order data constructed by the user is monitored and acquired through the neural network module based on the preset; calling departure place information and destination information carried in the order data at the same time, and generating a linear node path through linear node processing of the neural network module; monitoring a travel signal fed back by a user in a cloud database through the linear node path; labeling each travel signal fed back by a user on a linear node path, judging whether the linear node path is labeled completely, if not, determining that the travel of the user is not finished, and continuously monitoring; if yes, the user journey is determined to be ended, and a linear node path is marked correspondingly on a map sub-database pre-stored under the user ID; the method and the system improve order processing efficiency, track real-time travel, simplify user experience, improve order accuracy and provide personalized services.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium provided by the present invention and used in embodiments may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM, among others.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, apparatus, article or method that comprises the element.
The foregoing description is only of the preferred embodiments of the present invention and is not intended to limit the scope of the invention, and all equivalent structures or equivalent processes using the descriptions and drawings of the present invention or direct or indirect application in other related technical fields are included in the scope of the present invention.

Claims (10)

1. An informationized labeling method for user ticket order management is characterized by comprising the following steps:
based on a preset neural network module, monitoring and acquiring order data constructed by a user;
calling departure place information and destination information carried in the order data at the same time, and generating a linear node path through linear node processing of the neural network module;
monitoring a travel signal fed back by a user in a cloud database through the linear node path;
labeling each travel signal fed back by a user on a linear node path, judging whether the linear node path is labeled completely, if not, determining that the travel of the user is not finished, and continuously monitoring;
if yes, the user journey is judged to be ended, and the linear node paths are marked correspondingly on the map sub-database pre-stored under the user ID.
2. The method of informative labeling for ticket order management in a customer according to claim 1, wherein the step of training the neural network module comprises:
selecting a CNN convolutional neural network module and an RNN convolutional neural network module;
selecting historical order data from a preset database to extract characteristics of the historical order data to obtain a first training set and a second training set, and a first verification set and a second verification set; extracting a time relation and a space relation in historical order data by using a CNN convolutional neural network module as the first training set; extracting evolution relations and word sense relations in the historical order data through an RNN (RNN recurrent neural network) module to serve as the second training set, wherein the first verification set and the second verification set are actual data in the historical order data respectively and are used for verifying the first training set and the second training set in a one-to-one correspondence mode;
at one moment, the CNN convolutional neural network module performs regional characteristic calibration on the first training set obtained by extraction, wherein the regional characteristic calibration comprises a spatial relationship used for calibrating a departure place and a destination in the first training set and a time relationship used for calibrating a travel date in the first training set;
at one moment, the RNN circulating neural network module performs sequential feature calibration on the extracted second training set, wherein the sequential feature calibration comprises a word meaning relation for calibrating the evolution relation between the seat number and the flight information in the second training set and calibrating the user name in the second training set;
in an embedding layer of the neural network module, converting discrete spatial relationships, time relationships, evolution relationships and word sense relationships into continuous training vectors;
adding the first verification set to a first output layer of a CNN convolutional neural network module, adding the second verification set to a second output layer of an RNN convolutional neural network module, and performing feature fusion on the first verification set and the second verification set based on the historical order data to further drive the first output layer and the second output layer to be fused to form an output layer of the neural network module;
and outputting the training linear node path corresponding to the training vector in the output layer of the neural network module, optimizing the verification set fused on the output layer based on the training linear node path passing through the output layer of the neural network module, and optimizing the whole neural network module by back propagation based on the optimization of the training set.
3. The method of claim 1, wherein the step of monitoring and acquiring order data constructed by a user based on a preset neural network module comprises:
monitoring payment factors on a cloud database by adopting an input layer of the neural network module; wherein, the payment factor is a payment success signal generated when the user creates an air ticket order;
if the payment factor is monitored, acquiring order data associated with the payment factor by using an input layer of the neural network module;
and if the payment factor is not monitored, the input layer of the neural network module withdraws order data associated with the payment factor.
4. The method of claim 1, wherein the step of calling the departure information and the destination information carried in the order data, and generating a linear node path through linear node processing of the neural network module, comprises the steps of:
inputting the order data into an embedded layer of the neural network module for discrete identification; wherein, based on the spatial relationship, the time relationship, the evolution relationship and the word meaning relationship in the order data, at least the departure place information, the destination information and the flight information corresponding to the order data are determined through the discrete identification;
based on the flight information, determining all the route blocking nodes from the departure place information to the destination information, and generating corresponding linear node paths by using all the route blocking nodes;
and outputting the linear node path by using an output layer of the neural network module.
5. The method for information-based labeling of ticket order management of a user according to claim 4, wherein the step of monitoring the travel signal fed back by the user in the cloud database through the linear node path comprises the steps of:
monitoring all the interface nodes on the linear node path through the cloud database; the monitoring of each of the interface nodes establishes a cloud channel with the cloud database through the interface gate, when a user uses the corresponding certificate to pass through the interface gate, the interface gate generates a travel signal to the cloud database, and the neural network module monitors the travel signal in the cloud database.
6. The method of claim 1, wherein labeling the travel signals fed back by the user on the linear node path comprises:
and after the travel signals are obtained from the cloud database, marking the corresponding travel signals on the linear node paths one by one.
7. The method of claim 1, wherein the step of marking the linear node path on the map sub-database pre-stored under the user ID comprises:
under the condition that the journey of the user is judged to be ended, retrieving the travel date in the order data;
based on the travel dates, arranging the historical travel dates in the map sub-database, and generating an order navigation catalog through the arrangement;
at the same time, generating corresponding travel routes in a map sub-database based on the departure place and the destination of the linear node path;
and packaging the map carrying the travel route and the order navigation directory data, and sending the map and the order navigation directory data to a user ID of the user terminal.
8. An informative label system for customer ticket order management, comprising:
the user unit is used for monitoring and acquiring order data constructed by a user based on a preset neural network module;
the processing unit is used for calling the departure place information and the destination information carried in the order data at the same time, and generating a linear node path through the linear node processing of the neural network module;
the monitoring unit is used for monitoring the travel signal fed back by the user in the cloud database through the linear node path;
the judging unit is used for marking all the travel signals fed back by the user on the linear node paths, judging whether the linear node paths are marked completely or not, if not, judging that the travel of the user is not finished, and continuously monitoring;
and the recording unit is used for determining that the user journey is finished if the user journey is finished so as to mark the linear node path corresponding to the map sub-database pre-stored under the user ID.
9. A computer device comprising a memory and a processor, the memory having stored therein a computer program, characterized in that the processor, when executing the computer program, carries out the steps of the informative labeling method of user ticket order management according to any of claims 1 to 7.
10. A computer readable storage medium having stored thereon a computer program, characterized in that the computer program when executed by a processor implements the steps of the informative labeling method of user ticket order management of any of claims 1 to 7.
CN202311086737.5A 2023-08-28 2023-08-28 Informationized labeling method and system for user air ticket order management Active CN117522501B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311086737.5A CN117522501B (en) 2023-08-28 2023-08-28 Informationized labeling method and system for user air ticket order management

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311086737.5A CN117522501B (en) 2023-08-28 2023-08-28 Informationized labeling method and system for user air ticket order management

Publications (2)

Publication Number Publication Date
CN117522501A true CN117522501A (en) 2024-02-06
CN117522501B CN117522501B (en) 2024-07-23

Family

ID=89742707

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311086737.5A Active CN117522501B (en) 2023-08-28 2023-08-28 Informationized labeling method and system for user air ticket order management

Country Status (1)

Country Link
CN (1) CN117522501B (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20200211217A1 (en) * 2019-01-02 2020-07-02 Fetch Robotics, Inc. System and Method for Robotic Object Detection Using a Convolutional Neural Network
US10783460B1 (en) * 2015-12-15 2020-09-22 Amazon Technologies, Inc. Computer generation of itineraries
WO2021150166A1 (en) * 2020-01-20 2021-07-29 Nanyang Technological University Determining a route between an origin and a destination
CN113298275A (en) * 2020-05-21 2021-08-24 阿里巴巴集团控股有限公司 Travel management method, robot and platform
CN113704379A (en) * 2021-09-10 2021-11-26 瞿萍 Travel itinerary generating method, system and storage medium based on full itinerary

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10783460B1 (en) * 2015-12-15 2020-09-22 Amazon Technologies, Inc. Computer generation of itineraries
US20200211217A1 (en) * 2019-01-02 2020-07-02 Fetch Robotics, Inc. System and Method for Robotic Object Detection Using a Convolutional Neural Network
WO2021150166A1 (en) * 2020-01-20 2021-07-29 Nanyang Technological University Determining a route between an origin and a destination
CN113298275A (en) * 2020-05-21 2021-08-24 阿里巴巴集团控股有限公司 Travel management method, robot and platform
CN113704379A (en) * 2021-09-10 2021-11-26 瞿萍 Travel itinerary generating method, system and storage medium based on full itinerary

Also Published As

Publication number Publication date
CN117522501B (en) 2024-07-23

Similar Documents

Publication Publication Date Title
CN112527630B (en) Test case generation method, device, computer equipment and storage medium
CN110245704B (en) Service processing method and device, storage medium and electronic equipment
CN109934242A (en) Image identification method and device
CN112508078B (en) Image multitasking multi-label recognition method, system, equipment and medium
CN110781818B (en) Video classification method, model training method, device and equipment
US10772035B2 (en) Method and apparatus for generating information
CN115240157B (en) Method, apparatus, device and computer readable medium for persistence of road scene data
CN111626519A (en) Flight arrival time prediction method and device and electronic equipment
CN111178358A (en) Text recognition method and device, computer equipment and storage medium
CN111242167B (en) Distributed image labeling method, device, computer equipment and storage medium
US20230258461A1 (en) Interactive analytical framework for multimodal transportation
CN116964588A (en) Target detection method, target detection model training method and device
CN117522501B (en) Informationized labeling method and system for user air ticket order management
CN115033481A (en) Method and device for automatic test code generation based on browser access and computer equipment
CN113360644B (en) Text model retraining method, device, equipment and storage medium
CN114863201A (en) Training method and device of three-dimensional detection model, computer equipment and storage medium
CN117196322B (en) Intelligent wind control method, intelligent wind control device, computer equipment and storage medium
CN111210634B (en) Intelligent traffic information processing method and device, intelligent traffic system and server
US20210366048A1 (en) Methods and systems for reacting to loss reporting data
WO2023122708A1 (en) Systems and methods of image analysis for automated object location detection and management
CN115952268A (en) Fault solution query method, device and equipment
CN111158812B (en) Interface display method and device based on interface prediction model and computer equipment
CN114663751A (en) Power transmission line defect identification method and system based on incremental learning technology
CN112037202A (en) Method and device for detecting quality of body fluid sample, transportation device, equipment and medium
CN116681263B (en) Electric power data management method and system based on internal model market

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