CN112418730A - Construction method of response index estimation model of transportation system - Google Patents
Construction method of response index estimation model of transportation system Download PDFInfo
- Publication number
- CN112418730A CN112418730A CN202011463862.XA CN202011463862A CN112418730A CN 112418730 A CN112418730 A CN 112418730A CN 202011463862 A CN202011463862 A CN 202011463862A CN 112418730 A CN112418730 A CN 112418730A
- Authority
- CN
- China
- Prior art keywords
- response index
- data
- transportation system
- model
- estimation model
- 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
- 230000004044 response Effects 0.000 title claims abstract description 226
- 238000010276 construction Methods 0.000 title claims abstract description 34
- 238000012549 training Methods 0.000 claims abstract description 67
- 238000012360 testing method Methods 0.000 claims abstract description 30
- 238000010801 machine learning Methods 0.000 claims abstract description 12
- 238000000034 method Methods 0.000 claims description 56
- 239000013598 vector Substances 0.000 claims description 8
- 239000000470 constituent Substances 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 230000010006 flight Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 8
- 239000011159 matrix material Substances 0.000 description 7
- 230000007613 environmental effect Effects 0.000 description 5
- 238000004140 cleaning Methods 0.000 description 3
- 230000004927 fusion Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Software Systems (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Mathematical Physics (AREA)
- Operations Research (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Medical Informatics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Quality & Reliability (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a construction method of a response index estimation model of a transportation system, which comprises the following steps: acquiring historical operation data of a transportation system, and constructing a data sample set according to the historical operation data; constructing a response index estimation model based on a machine learning algorithm according to preset estimation requirements and attribute data of a transportation system; extracting training samples from the data sample set, inputting the training samples into a response index estimation model, and performing model training on the response index estimation model; extracting test samples from the data sample set, inputting the test samples into a response index estimation model after model training, and obtaining corresponding estimation results; and determining a target response index estimation model according to the estimation result. The reliability of the obtained response index estimation model is improved, and a foundation is laid for improving the accuracy of the estimation result of the response index of the transportation system.
Description
Technical Field
The application relates to the technical field of artificial intelligence, in particular to a construction method of a response index estimation model of a transportation system.
Background
With the increasing transportation demand of people, various transportation industries, such as the air transportation industry, etc., have been developed rapidly. However, the air transportation is affected by factors such as environment, the accuracy of the operation data such as the arrival time in the flight transportation process cannot be guaranteed, and the arrival time of each flight cannot be effectively estimated, so that the estimation of each operation data in the air transportation process becomes a key point of research.
In the prior art, the arrival time of a flight is usually estimated according to the departure time of the flight, the transportation distance and the environmental data.
However, the current air transportation system is a system in which a plurality of flights are coupled with each other, and a certain correlation exists between the flights. If the arrival time of the flight is estimated based only on the departure time of the flight, the transportation distance, and the environmental data, the reliability of the obtained estimation result is relatively low. Therefore, a response index estimation model of the transportation system, which can accurately estimate the arrival time of each flight and other system response indexes, is urgently needed, and has important significance for improving the accuracy of the estimation result of the response index estimation.
Disclosure of Invention
The application provides a construction method of a response index estimation model of a transportation system, which aims to overcome the defects that the arrival time of flights and the accuracy of other system response indexes obtained in the prior art are low and the like.
The first aspect of the present application provides a method for constructing a response index estimation model of a transportation system, including:
acquiring historical operation data of a transportation system, and constructing a data sample set according to the historical operation data; wherein the historical operating data at least comprises a planned departure time, an actual departure time, a planned arrival time and an actual arrival time of each transport object in the transport system;
constructing a response index estimation model based on a machine learning algorithm according to preset estimation requirements and attribute data of the transportation system;
extracting training samples from the data sample set, inputting the training samples into the response index estimation model, and performing model training on the response index estimation model;
extracting test samples from the data sample set, inputting the test samples into a response index estimation model after model training, and obtaining corresponding estimation results;
and determining a target response index estimation model according to the estimation result.
Optionally, the determining a target response indicator prediction model according to the prediction result includes:
determining the performance index of the current response index estimation model according to the estimation result;
judging whether the performance index of the current response index estimation model reaches a preset performance index threshold value or not;
and when the performance index of the current response index prediction model reaches the performance index threshold value, determining that the current response index prediction model is the target response index prediction model.
Optionally, the method further includes:
and returning to the step of extracting training samples from the data sample set, inputting the training samples into the response index estimation model and carrying out model training on the response index estimation model when the performance index of the current response index estimation model does not reach the performance index threshold value.
Optionally, the constructing a data sample set according to the historical operating data includes:
extracting historical operating data from the historical operating data according to a preset time period, and determining the historical operating data in the preset time period as a data sample;
converting the data samples into data samples in a vector form according to the data types corresponding to the historical operating data in the data samples;
and constructing the data sample set according to the data samples in the form of the vectors.
Optionally, before constructing the data sample set according to the historical operating data, the method further includes:
and performing data preprocessing on the historical operating data according to the data quality of the historical operating data and the constituent elements of each historical operating data.
In a second aspect, the present application provides a method for estimating response indicators of a transportation system, including:
acquiring current transportation information; the current transportation information comprises attribute data of a current transportation system and current operation data of each transportation object in the current transportation system.
And inputting the current transportation information into the target response index estimation model constructed by the data estimation model construction methods according to the first aspect and the first aspect to generate estimation results corresponding to each transportation object.
The third aspect of the present application provides a device for constructing a response index estimation model of a transportation system, including:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring historical operation data of a transportation system and constructing a data sample set according to the historical operation data; wherein the historical operating data at least comprises a planned departure time, an actual departure time, a planned arrival time and an actual arrival time of each transport object in the transport system;
the model construction module is used for constructing a response index estimation model based on a machine learning algorithm according to preset estimation requirements and attribute data of the transportation system;
the training module is used for extracting training samples from the data sample set, inputting the training samples into the response index estimation model and carrying out model training on the response index estimation model;
the test module is used for extracting test samples from the data sample set, inputting the test samples into a response index estimation model after model training, and obtaining corresponding estimation results; the estimation result at least comprises an actual departure time and an actual arrival time;
and the determining module is used for determining a target response index estimation model according to the estimation result.
Optionally, the determining module is specifically configured to:
determining the performance index of the current response index estimation model according to the estimation result;
judging whether the performance index of the current response index estimation model reaches a preset performance index threshold value or not;
and when the performance index of the current response index prediction model reaches the performance index threshold value, determining that the current response index prediction model is the target response index prediction model.
Optionally, the determining module is further configured to:
and returning to the step of extracting training samples from the data sample set, inputting the training samples into the response index estimation model and carrying out model training on the response index estimation model when the performance index of the current response index estimation model does not reach the performance index threshold value.
Optionally, the first obtaining module is specifically configured to:
extracting historical operating data from the historical operating data according to a preset time period, and determining the historical operating data in the preset time period as a data sample;
converting the data samples into data samples in a vector form according to the data types corresponding to the historical operating data in the data samples;
and constructing the data sample set according to the data samples in the form of the vectors.
Optionally, the obtaining module is further configured to:
and performing data preprocessing on the historical operating data according to the data quality of the historical operating data and the constituent elements of each historical operating data.
A fourth aspect of the present application provides a response index estimation device for a transportation system, including:
the second acquisition module is used for acquiring the current transportation information; the current transportation information comprises attribute data of a current transportation system and current operation data of each transportation object in the current transportation system.
And the estimation module is used for inputting the current transportation information into the target response index estimation model constructed by the construction device of the data estimation model in the third aspect and the third aspect, so as to generate the estimation result corresponding to each transportation object.
A fifth aspect of the present application provides an electronic device, comprising: at least one processor and memory;
the memory stores computer-executable instructions;
the at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the method for constructing the response indicator prediction model of the transportation system according to the first aspect and the various possible designs of the first aspect or the method for predicting the response indicator of the transportation system according to the second aspect and the various possible designs of the second aspect.
A sixth aspect of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored, and when a processor executes the computer-executable instructions, a method for constructing a response index estimation model of a transportation system according to the first aspect and various possible designs of the first aspect or a method for estimating a response index of a transportation system according to the second aspect and various possible designs of the second aspect is implemented.
This application technical scheme has following advantage:
according to the construction method of the response index estimation model of the transportation system, historical operation data of the transportation system are obtained, and a data sample set is constructed according to the historical operation data; the historical operation data at least comprises planned departure time, actual departure time, planned arrival time and actual arrival time of each transport object in the transport system; constructing a response index estimation model based on a machine learning algorithm according to preset estimation requirements and attribute data of a transportation system; extracting training samples from the data sample set, inputting the training samples into a response index estimation model, and performing model training on the response index estimation model; extracting test samples from the data sample set, inputting the test samples into a response index estimation model after model training, and obtaining corresponding estimation results; and determining a target response index estimation model according to the estimation result. According to the construction method of the response index estimation model of the transportation system, the response index estimation model is constructed according to the applied attribute information of the transportation system and the historical operation data of a plurality of transportation objects in the transportation system, so that the reliability of the obtained response index estimation model is improved, and a foundation is laid for improving the accuracy of the estimation result of the response index of the transportation system.
According to the response index estimation method of the transportation system, the current transportation information is obtained; the current transportation information comprises attribute data of a current transportation system and current operation data of each transportation object in the current transportation system; and inputting the current transportation information into the target response index estimation model constructed by the construction method of the response index estimation model of the transportation system to generate an estimation result corresponding to each transportation object. According to the response index estimation method for the transportation system, the estimation result corresponding to each transportation object in the current transportation system is determined according to the current transportation information by utilizing the target response index estimation model established by integrating the attribute information of the applied transportation system and the historical operation data of the transportation objects in the transportation system, so that the accuracy of the estimation result is improved, and a foundation is laid for improving the management efficiency of the transportation system.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art according to these drawings.
Fig. 1 is a schematic structural diagram of a transportation system on which an embodiment of the present application is based;
fig. 2 is a schematic flowchart of a method for constructing a response index estimation model of a transportation system according to an embodiment of the present disclosure;
fig. 3 is a schematic flowchart of a response index estimation method of a transportation system according to an embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of a device for constructing a response index prediction model of a transportation system according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of a response indicator estimation device of a transportation system according to an embodiment of the present disclosure;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
With the above figures, there are shown specific embodiments of the present application, which will be described in more detail below. These drawings and written description are not intended to limit the scope of the disclosed concepts in any way, but rather to illustrate the concepts of the disclosure to those skilled in the art by reference to specific embodiments.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Furthermore, the terms "first", "second", etc. are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. In the description of the following examples, "plurality" means two or more unless specifically limited otherwise.
In the prior art, the arrival time of a flight is usually estimated according to the departure time of the flight, the transportation distance and the environmental data. However, the current air transportation system is a system in which a plurality of flights are coupled with each other, and a certain correlation exists between the flights. If the operation data such as the arrival time of the flight is estimated only based on the departure time of the flight, the transportation distance and the environmental data, the reliability of the obtained estimation result is relatively low.
In order to solve the above problems, the method for constructing the response index estimation model of the transportation system provided by the embodiment of the application acquires historical operation data of the transportation system, and constructs a data sample set according to the historical operation data; the historical operation data at least comprises planned departure time, actual departure time, planned arrival time and actual arrival time of each transport object in the transport system; constructing a response index estimation model based on a machine learning algorithm according to preset estimation requirements and attribute data of a transportation system; extracting training samples from the data sample set, inputting the training samples into a response index estimation model, and performing model training on the response index estimation model; extracting test samples from the data sample set, inputting the test samples into a response index estimation model after model training, and obtaining corresponding estimation results; and determining a target response index estimation model according to the estimation result. According to the construction method of the response index estimation model of the transportation system, the response index estimation model is constructed according to the applied attribute information of the transportation system and the historical operation data of a plurality of transportation objects in the transportation system, so that the reliability of the obtained response index estimation model is improved, and a foundation is laid for improving the accuracy of the estimation result of the response index of the transportation system.
Furthermore, according to the response index estimation method of the transportation system, the current transportation information is obtained; the current transportation information comprises attribute data of a current transportation system and current operation data of each transportation object in the current transportation system; and inputting the current transportation information into the target response index estimation model constructed by the construction method of the response index estimation model of the transportation system to generate an estimation result corresponding to each transportation object. According to the response index estimation method for the transportation system, the estimation result corresponding to each transportation object in the current transportation system is determined according to the current transportation information by utilizing the target response index estimation model established by integrating the attribute information of the applied transportation system and the historical operation data of the transportation objects in the transportation system, so that the accuracy of the estimation result is improved, and a foundation is laid for improving the management efficiency of the transportation system.
The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments. Embodiments of the present invention will be described below with reference to the accompanying drawings.
First, the structure of a transportation system on which the present application is based will be explained:
the construction method of the response index estimation model of the transportation system is suitable for constructing the response index estimation model capable of estimating the index response condition of each transportation object in the transportation system; the method for estimating the response index of the transportation system is suitable for estimating the index response condition of each transportation object in the transportation system. As shown in fig. 1, the schematic structural diagram of a transportation system based on the embodiment of the present application mainly includes a plurality of transportation objects, a database for storing historical operation data, a construction device for constructing a response index estimation model of the transportation system for a response index estimation model, and a response index estimation device for a transportation system for response index estimation. Specifically, during the operation process of each transport object, the generated operation data are stored to a database in real time, a construction device of a response index estimation model of the transport system constructs a response index estimation model according to historical operation data stored in the database and attribute information of the transport system, and the response index estimation device of the transport system estimates the index response condition corresponding to each transport object in the current transport system by using the response index estimation model constructed by the construction device of the response index estimation model of the transport system to obtain a corresponding estimation result.
The embodiment of the application provides a construction method of a response index estimation model of a transportation system, which is used for constructing the response index estimation model capable of estimating the index response condition of each transportation object in the transportation system. The execution subject of the embodiment of the application is an electronic device, such as a server, a desktop computer, a notebook computer, a tablet computer, and other electronic devices that can be used to construct the response index estimation model.
As shown in fig. 2, a schematic flow chart of a method for constructing a response index estimation model of a transportation system according to an embodiment of the present application is provided, where the method includes:
The historical operating data at least comprises planned departure time, actual departure time, planned arrival time and actual arrival time of each transport object in the transport system.
Further, when the response index estimation model provided by the embodiment of the application is applied to the field of air transportation, a plurality of key node time information exists in the operation process of a flight. For example: the time of closing the cabin door, the time of removing the wheel gear, the time of taking off (departure), the time of landing (arrival), the time of getting on the wheel gear, the time of opening the cabin door and the like. Therefore, in order to further improve the reliability of the constructed response index estimation model, on the basis of the above embodiment, the historical operating data may further include a planned gear-removing time, an actual gear-removing time, a planned gear-loading time, an actual gear-loading time, a planned cabin door opening time, an actual cabin door opening time, a planned cabin door closing time, an actual cabin door closing time, and the like of each transportation object.
It should be explained that the response index estimation model provided in the embodiment of the present application may be applied to the fields of rail transportation and the like in addition to the field of air transportation, and the embodiment of the present application is mainly described by taking the application to the field of air transportation as an example, and the embodiment of the present application is not limited in specific application field.
It should be explained that the attribute data of the transportation system may include airport attribute data, attribute data of each transportation object, and lane attribute data and environment data corresponding to each transportation object. Wherein, the airport attribute data can comprise airport throughput, airport scale, airport type, primary and secondary coordination airports, and the like; the attribute data of each transportation object can comprise front and back-order flights, flight execution airplane types and the like; the airline attribute data may include airline busyness, etc.; environmental data may include airport wind speed, visibility, and regional meteorological conditions, among others.
Specifically, a response index estimation model may be constructed by using common machine learning algorithms such as CNN, DNN, and LSTM, and a relevant operator may select a corresponding machine learning algorithm according to an actual situation, which is not limited in the embodiment of the present application.
Specifically, in order to improve the reliability of the response index prediction model, a large number of training samples may be extracted from the data sample set, so as to perform sufficient model training on the response index prediction model. The unit of extraction of the training samples may be days, for example, a data sample corresponding to historical operating data of the previous 200 days in the data sample set is extracted as the training sample.
The estimated result may include an estimated actual departure time and an estimated actual arrival time.
It should be explained that the estimation result mainly includes the index response condition of each transportation object in the transportation system. The response index not only can include the estimated actual departure time, the actual arrival time and other time information of each transport object, but also can include the estimated departure flight normal rate, the estimated departure flight average delay time, the estimated arrival flight normal rate, the estimated arrival flight average delay time and other information reflecting the overall index response condition of the transport system.
It should be further explained that, in order to improve the testing efficiency, the number of test samples may be less than the number of training samples.
For example, if the preset estimation requirement is to estimate the actual departure time and the actual arrival time of each transportation object in the transportation system, the accuracy and other related performances of the current response index estimation model can be judged according to the actual departure time and the actual arrival time corresponding to each test sample and the actual departure time and the actual arrival time corresponding to each test sample in the estimation result output by the response index estimation model, so as to determine the target response index estimation model.
Specifically, in an embodiment, the performance index of the current response index prediction model may be determined according to the prediction result; judging whether the performance index of the current response index estimation model reaches a preset performance index threshold value or not; and when the performance index of the current response index estimation model reaches the performance index threshold value, determining the current response index estimation model as a target response index estimation model.
It should be explained that the performance index may be determined according to model indexes such as accuracy, generalization capability, and calculation efficiency of the model, and the specific calculation manner may be determined by referring to the prior art and combining with the actual situation, which is not limited in the embodiment of the present application.
On the contrary, when the performance index of the current response index estimation model does not reach the performance index threshold, returning to the step of extracting the training samples from the data sample set, inputting the training samples into the response index estimation model, and performing model training on the response index estimation model.
Specifically, a new training sample is selected from the data sample set, and model training is performed on the current response index estimation model again.
On the basis of the above embodiment, since the historical operating data is divided into a plurality of data types, which mainly include data types such as character strings and numerical values, as an implementable manner for improving the model training efficiency, on the basis of the above embodiment, in an embodiment, the constructing a data sample set according to the historical operating data includes: extracting historical operating data from the historical operating data according to a preset time period, and determining the historical operating data in the preset time period as a data sample; converting the data samples into vector-form data samples according to the data types corresponding to the historical operating data in the data samples; and constructing a data sample set according to the data samples in the vector form.
For example, for the time data, all the time is differentiated from the current day 00:00:00, and the obtained time difference value is taken as a corresponding time data coding value in units of minutes. For example, if the takeoff time is "02: 30: 00", the converted numerical code value is 150. For the character string data, regular encoding or one-hot-only encoding is adopted for encoding, for example, for weather data, { clear day ═ 1, cloudy day ═ 2, light/medium rain ═ 3, heavy/heavy rain ═ 4, snow day ═ 5} and the like may be set to convert the character string data into numerical data. And carrying out MinMax normalization processing on the encoded data, namely normalizing the numerical values to be in a range of [0,1] in an equal proportion by taking the maximum value and the minimum value of the parameter as boundaries.
The vector-form data sample mainly includes an input matrix and an output matrix, for example, the vector-form data sample is (X, Y), where X is the input matrix of the model and Y is the output matrix or the output vector of the model. Taking 1 day as a sampling period (preset time period), slicing and grouping all flight data according to the day as a period, and generating a group of (X, Y) data samples each day, wherein X is a matrix of m × n dimensions, and m represents the number of flights, namely m different flights exist in one day; n represents input parameters related to the flight, such as planned departure time, planned arrival time, and the like; y is a matrix of p x q, where p is the number of sets of parameters to be output, such as p flights, p airports, etc.; q is the number of parameters included in each group of output, such as the actual departure time and the actual arrival time of a flight, and the information that can be included in a specific output matrix can be determined according to preset estimation requirements, that is, according to the construction condition of the constructed response index estimation model. Further, each (X, Y) data sample may be divided into a training sample (X1, Y1) and a test sample (X2, Y2), and the ratio of the training sample to the test sample may be adjusted according to the model learning condition.
Further, in an embodiment, in order to further improve the model training efficiency, before the data sample set is constructed according to the historical operating data, the historical operating data may be subjected to data preprocessing according to the data quality of the historical operating data and the constituent elements of each historical operating data.
It should be explained that the data preprocessing mainly includes data cleaning, data fusion and the like, and specifically, the data cleaning may be performed according to the data quality of the historical operating data, and the data fusion may be performed according to the constituent elements of each historical operating data. The specific data preprocessing mode can be determined according to the actual situation of the obtained historical operating data.
For example, the data cleaning method provided by the embodiment of the present application is as follows, for historical operating data with missing values, deleting the data record, or performing interpolation to complete the data record; deleting repeated data records for repeated historical operating data; for historical running data with wrong time sequence, whether the time sequence is wrong or not can be judged by calculating the time difference of two moments and judging whether the time difference exceeds a preset reasonable range, and if the time difference is wrong, the data record is deleted; for historical operation data of data errors, screening can be carried out by setting data detection rules, and data records are revised or deleted. The data fusion mode can be set according to actual conditions, taking the air transportation field as an example, if the constituent elements of the historical operation data of the transportation system in the air transportation field are flight information such as date, flight number, departure airport, landing airport and the like, the data related to the flight can be integrated into a data record by taking the date + flight number + departure airport + landing airport as a flight identification ID, so that the management efficiency of the historical operation data is improved.
According to the construction method of the response index estimation model of the transportation system, historical operation data of the transportation system are obtained, and a data sample set is constructed according to the historical operation data; the historical operation data at least comprises planned departure time, actual departure time, planned arrival time and actual arrival time of each transport object in the transport system; constructing a response index estimation model based on a machine learning algorithm according to preset estimation requirements and attribute data of a transportation system; extracting training samples from the data sample set, inputting the training samples into a response index estimation model, and performing model training on the response index estimation model; extracting test samples from the data sample set, inputting the test samples into a response index estimation model after model training, and obtaining corresponding estimation results; and determining a target response index estimation model according to the estimation result. According to the construction method of the response index estimation model of the transportation system, the response index estimation model is constructed according to the applied attribute information of the transportation system and the historical operation data of a plurality of transportation objects in the transportation system, so that the reliability of the obtained response index estimation model is improved, and a foundation is laid for improving the accuracy of the estimation result of the response index of the transportation system. And in addition, auxiliary decision information is provided for improving flight operation efficiency, finding operation short boards, managing flight time, optimizing flight time and the like.
The embodiment of the application provides a response index estimation method of a transportation system, which is used for estimating the index response condition of each transportation object in the transportation system. The execution subject of the embodiment of the present application is an electronic device, such as a server, a desktop computer, a notebook computer, a tablet computer, and other electronic devices that can be used for response index estimation.
As shown in fig. 3, a schematic flow chart of a method for estimating a response index of a transportation system according to an embodiment of the present application is shown, where the method includes:
The current transportation information comprises attribute data of the current transportation system and current operation data of each transportation object in the current transportation system.
It should be explained that the current operation data may include preset operation data such as a planned departure time and a planned arrival time.
The method for estimating response index of a transportation system provided in this embodiment is specifically a use method of a target response index estimation model constructed by the method for constructing a response index estimation model of a transportation system provided in the above embodiment, and the specific response index estimation method is not described herein again.
According to the response index estimation method of the transportation system, the current transportation information is obtained; the current transportation information comprises attribute data of a current transportation system and current operation data of each transportation object in the current transportation system; and inputting the current transportation information into the target response index estimation model constructed by the construction method of the response index model of the transportation system to generate an estimation result corresponding to each transportation object. According to the response index estimation method for the transportation system, the estimation result corresponding to each transportation object in the current transportation system is determined according to the current transportation information by utilizing the target response index estimation model established by integrating the attribute information of the applied transportation system and the historical operation data of the transportation objects in the transportation system, so that the accuracy of the estimation result is improved, and a foundation is laid for improving the management efficiency of the transportation system.
The embodiment of the application provides a device for constructing a response index estimation model of a transportation system, which is used for executing the method for constructing the response index estimation model of the transportation system provided by the embodiment.
Fig. 4 is a schematic structural diagram of a device for constructing a response index estimation model of a transportation system according to an embodiment of the present disclosure. The constructing device 40 of the response index estimation model of the transportation system comprises a first obtaining module 401, a model constructing module 402, a training module 403, a testing module 404 and a determining module 405.
The first acquisition module is used for acquiring historical operation data of the transportation system and constructing a data sample set according to the historical operation data; the historical operation data at least comprises planned departure time, actual departure time, planned arrival time and actual arrival time of each transport object in the transport system; the model construction module is used for constructing a response index estimation model based on a machine learning algorithm according to preset estimation requirements and attribute data of the transportation system; the training module is used for extracting training samples from the data sample set, inputting the training samples into the response index estimation model and carrying out model training on the response index estimation model; the test module is used for extracting test samples from the data sample set, inputting the test samples into the response index estimation model after model training, and obtaining corresponding estimation results; and the determining module is used for determining the target response index estimation model according to the estimation result.
With regard to the construction apparatus of the response index estimation model of the transportation system in this embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment of the construction method of the response index estimation model of the transportation system, and will not be described in detail here.
The device for constructing the response index estimation model of the transportation system provided by the embodiment of the application is used for executing the method for constructing the response index estimation model of the transportation system provided by the embodiment, and the implementation manner and the principle are the same, and are not repeated.
The embodiment of the application provides a response index estimation device of a transportation system, which is used for executing the response index estimation method of the transportation system provided by the embodiment.
Fig. 5 is a schematic structural diagram of a response indicator estimation device of a transportation system according to an embodiment of the present disclosure. The response index estimation device 50 of the transportation system includes a second obtaining module 501 and an estimation module 502.
The second acquisition module is used for acquiring current transportation information, wherein the current transportation information comprises attribute data of a current transportation system and current operation data of each transportation object in the current transportation system; the estimation module is configured to input the current transportation information into the target response index estimation model constructed by the data estimation model construction device provided in the embodiment, so as to generate an estimation result corresponding to each transportation object.
The response index estimation device of the transportation system in this embodiment is specifically an application device of the target response index estimation model constructed by the data estimation model construction device provided in the above embodiment.
The response index estimation device of the transportation system provided by the embodiment of the application is used for executing the response index estimation method of the transportation system provided by the embodiment, and the implementation manner and the principle are the same, and are not repeated.
The embodiment of the application provides an electronic device, which is used for executing the construction method of the response index estimation model of the transportation system or the response index estimation method of the transportation system provided by the embodiment.
Fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application. The electronic device 60 includes: at least one processor 61 and memory 62;
the memory stores computer-executable instructions; the at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the method for constructing the response index prediction model of the transportation system or the method for predicting the response index of the transportation system provided in the above embodiment.
The electronic device provided in the embodiment of the present application is configured to execute the method for constructing the response index estimation model of the transportation system or the method for estimating the response index of the transportation system provided in the embodiment, and the implementation manner and the principle thereof are the same and are not described again.
The embodiment of the application provides a computer-readable storage medium, wherein a computer execution instruction is stored in the computer-readable storage medium, and when a processor executes the computer execution instruction, the method for constructing the response index estimation model of the transportation system or the method for estimating the response index of the transportation system, which are provided by the foregoing embodiments, is implemented.
The storage medium including the computer-executable instructions of the embodiment of the present application may be used to store the computer-executable instructions of the method for constructing the response index estimation model of the transportation system or the method for estimating the response index of the transportation system provided in the foregoing embodiments, and the implementation manner and the principle thereof are the same and are not described again.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present application.
Claims (10)
1. A construction method of a response index estimation model of a transportation system is characterized by comprising the following steps:
acquiring historical operation data of a transportation system, and constructing a data sample set according to the historical operation data; wherein the historical operating data at least comprises a planned departure time, an actual departure time, a planned arrival time and an actual arrival time of each transport object in the transport system;
constructing a response index estimation model based on a machine learning algorithm according to preset estimation requirements and attribute data of the transportation system;
extracting training samples from the data sample set, inputting the training samples into the response index estimation model, and performing model training on the response index estimation model;
extracting test samples from the data sample set, inputting the test samples into a response index estimation model after model training, and obtaining corresponding estimation results;
and determining a target response index estimation model according to the estimation result.
2. The method for constructing the response index prediction model of the transportation system according to claim 1, wherein the determining the target response index prediction model according to the prediction result comprises:
determining the performance index of the current response index estimation model according to the estimation result;
judging whether the performance index of the current response index estimation model reaches a preset performance index threshold value or not;
and when the performance index of the current response index prediction model reaches the performance index threshold value, determining that the current response index prediction model is the target response index prediction model.
3. The method for constructing the response index estimation model of the transportation system as claimed in claim 2, further comprising:
and returning to the step of extracting training samples from the data sample set, inputting the training samples into the response index estimation model and carrying out model training on the response index estimation model when the performance index of the current response index estimation model does not reach the performance index threshold value.
4. The method for constructing the response index prediction model of the transportation system according to claim 1, wherein the constructing a data sample set according to the historical operating data comprises:
extracting historical operating data from the historical operating data according to a preset time period, and determining the historical operating data in the preset time period as a data sample;
converting the data samples into data samples in a vector form according to the data types corresponding to the historical operating data in the data samples;
and constructing the data sample set according to the data samples in the form of the vectors.
5. The method of constructing a response indicator prediction model for a transportation system of claim 4, wherein prior to constructing a data sample set from the historical operating data, the method further comprises:
and performing data preprocessing on the historical operating data according to the data quality of the historical operating data and the constituent elements of each historical operating data.
6. A response index estimation method of a transportation system is characterized by comprising the following steps:
acquiring current transportation information; the current transportation information comprises attribute data of a current transportation system and current operation data of each transportation object in the current transportation system;
inputting the current transportation information into a target response index estimation model constructed by the construction method of the response index estimation model of the transportation system according to any one of claims 1 to 5 to generate an estimation result corresponding to each transportation object.
7. A construction device of a response index estimation model of a transportation system is characterized by comprising the following steps:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring historical operation data of a transportation system and constructing a data sample set according to the historical operation data; wherein the historical operating data at least comprises a planned departure time, an actual departure time, a planned arrival time and an actual arrival time of each transport object in the transport system;
the model construction module is used for constructing a response index estimation model based on a machine learning algorithm according to preset estimation requirements and attribute data of the transportation system;
the training module is used for extracting training samples from the data sample set, inputting the training samples into the response index estimation model and carrying out model training on the response index estimation model;
the test module is used for extracting test samples from the data sample set, inputting the test samples into a response index estimation model after model training, and obtaining corresponding estimation results;
and the determining module is used for determining a target response index estimation model according to the estimation result.
8. A response index estimation device of a transportation system is characterized by comprising:
the second acquisition module is used for acquiring current transportation information, wherein the current transportation information comprises attribute data of a current transportation system and current operation data of each transportation object in the current transportation system;
the estimation module is used for inputting the current transportation information into the target response index estimation model constructed by the construction device of the response index estimation model of the transportation system as claimed in claim 7 so as to generate the estimation result corresponding to each transportation object.
9. An electronic device, comprising: at least one processor and memory;
the memory stores computer-executable instructions;
the at least one processor executing the computer-executable instructions stored in the memory causes the at least one processor to perform the method for constructing a response indicator prediction model of a transportation system according to any one of claims 1-5 or to perform the method for predicting a response indicator of a transportation system according to claim 6.
10. A computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and when the processor executes the method for constructing the response indicator prediction model of the transportation system according to any one of claims 1 to 5, or executes the method for predicting the response indicator of the transportation system according to claim 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011463862.XA CN112418730A (en) | 2020-12-11 | 2020-12-11 | Construction method of response index estimation model of transportation system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011463862.XA CN112418730A (en) | 2020-12-11 | 2020-12-11 | Construction method of response index estimation model of transportation system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112418730A true CN112418730A (en) | 2021-02-26 |
Family
ID=74776136
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011463862.XA Pending CN112418730A (en) | 2020-12-11 | 2020-12-11 | Construction method of response index estimation model of transportation system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112418730A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115759386A (en) * | 2022-11-11 | 2023-03-07 | 中国民航科学技术研究院 | Method and device for predicting flight-taking result of civil aviation flight and electronic equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109492334A (en) * | 2018-12-11 | 2019-03-19 | 青岛心中有数科技有限公司 | Delayed method for establishing model, prediction technique and device |
| CN111160612A (en) * | 2019-12-03 | 2020-05-15 | 南京航空航天大学 | Off-site flight delay analysis and prediction method based on weather influence |
| CN111401601A (en) * | 2019-12-23 | 2020-07-10 | 南京航空航天大学 | Flight take-off and landing time prediction method facing delay propagation |
-
2020
- 2020-12-11 CN CN202011463862.XA patent/CN112418730A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109492334A (en) * | 2018-12-11 | 2019-03-19 | 青岛心中有数科技有限公司 | Delayed method for establishing model, prediction technique and device |
| CN111160612A (en) * | 2019-12-03 | 2020-05-15 | 南京航空航天大学 | Off-site flight delay analysis and prediction method based on weather influence |
| CN111401601A (en) * | 2019-12-23 | 2020-07-10 | 南京航空航天大学 | Flight take-off and landing time prediction method facing delay propagation |
Non-Patent Citations (1)
| Title |
|---|
| 张文学等: "《大数据挖掘技术及其在医药领域的应用》", 30 September 2020, 燕山大学出版社, pages: 23 - 26 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115759386A (en) * | 2022-11-11 | 2023-03-07 | 中国民航科学技术研究院 | Method and device for predicting flight-taking result of civil aviation flight and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ma et al. | A hybrid CNN-LSTM model for aircraft 4D trajectory prediction | |
| CN113361578B (en) | Training method and device for image processing model, electronic equipment and storage medium | |
| CN113658214B (en) | Trajectory prediction method, collision detection method, apparatus, electronic device, and medium | |
| CN114816909A (en) | Real-time log detection early warning method and system based on machine learning | |
| CN112862171B (en) | Flight arrival time prediction method based on space-time neural network | |
| CN115220133B (en) | Rainfall prediction method, device and equipment for multiple meteorological elements and storage medium | |
| CN113341919B (en) | Computing system fault prediction method based on time sequence data length optimization | |
| CN114428828A (en) | Method and device for digging new road based on driving track and electronic equipment | |
| CN116910633B (en) | Power grid fault prediction method based on multi-modal knowledge mixed reasoning | |
| CN114648676A (en) | Point cloud processing model training and point cloud instance segmentation method and device | |
| CN114647985A (en) | Training method of frontal crossing prediction model and frontal crossing prediction method | |
| CN113657814A (en) | Aviation network risk prediction method and risk grade evaluation method | |
| CN116468186A (en) | Flight delay time prediction method, electronic equipment and storage medium | |
| CN115659244A (en) | Fault prediction method, device and storage medium | |
| CN116362430A (en) | Flight delay prediction method and system based on online increment MHHA-SRU | |
| CN116021981A (en) | Method, device, equipment and storage medium for predicting ice coating faults of power distribution network line | |
| CN112418730A (en) | Construction method of response index estimation model of transportation system | |
| CN114594532A (en) | Method and device for predicting cold weather, electronic equipment and computer readable medium | |
| CN112883236A (en) | Map updating method, map updating device, electronic equipment and storage medium | |
| CN115563888B (en) | Spacecraft residual life prediction method, system, electronic equipment and medium | |
| CN112529416A (en) | Construction method of operation efficiency estimation model of transportation system | |
| CN114611753A (en) | Flight airplane trajectory data prediction system and method | |
| Zhang et al. | Runway visual range prediction based on ensemble learning | |
| CN113872794B (en) | IT operation and maintenance platform system based on cloud resource support and operation and maintenance method thereof | |
| CN114445395B (en) | Distribution line tree obstacle intelligent positioning method and device based on Internet and big data |
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 |