CN111178628B - Luggage arrival time prediction method and device - Google Patents

Luggage arrival time prediction method and device Download PDF

Info

Publication number
CN111178628B
CN111178628B CN201911395473.5A CN201911395473A CN111178628B CN 111178628 B CN111178628 B CN 111178628B CN 201911395473 A CN201911395473 A CN 201911395473A CN 111178628 B CN111178628 B CN 111178628B
Authority
CN
China
Prior art keywords
flight
information
baggage
sample
time
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201911395473.5A
Other languages
Chinese (zh)
Other versions
CN111178628A (en
Inventor
李德龙
李洪飞
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.)
Shenyang Ne Cares Co ltd
Original Assignee
Shenyang Ne Cares 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 Shenyang Ne Cares Co ltd filed Critical Shenyang Ne Cares Co ltd
Priority to CN201911395473.5A priority Critical patent/CN111178628B/en
Publication of CN111178628A publication Critical patent/CN111178628A/en
Application granted granted Critical
Publication of CN111178628B publication Critical patent/CN111178628B/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
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/40—Business processes related to the transportation industry

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Software Systems (AREA)
  • Economics (AREA)
  • Evolutionary Computation (AREA)
  • Computational Linguistics (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Biophysics (AREA)
  • Mathematical Physics (AREA)
  • Biomedical Technology (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Strategic Management (AREA)
  • Data Mining & Analysis (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Game Theory and Decision Science (AREA)
  • Development Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Primary Health Care (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application discloses a luggage arrival time prediction method and device, which are characterized in that the related information of a flight where a target luggage is located is collected, wherein the related information at least comprises the located flight data and the leading flight information corresponding to the located flight; predicting to obtain the predicted time information of the target baggage reaching the target baggage turntable according to the associated information of the flight and a pre-established time prediction model; pushing the estimated time information to a target passenger corresponding to the target baggage. According to the application, the time prediction model can be obtained through multidimensional data according to the combined modeling of the current flight information and the preface flight information, so that the information quantity learned by the time prediction model is larger, the characterization capability is stronger, and the time prediction result is more accurate. Thereby reducing the residence time of the passengers at the baggage extraction point and improving the experience effect of the passengers.

Description

Luggage arrival time prediction method and device
Technical Field
The application relates to the technical field of information processing, in particular to a luggage arrival time prediction method and device applied to a civil aviation airport.
Background
With the development of the aviation field, more and more passengers choose to take the aircraft for traveling. When a passenger takes an airplane, the passenger usually carries personal baggage, and the passenger checks in baggage before boarding. After the passenger arrives at the destination airport, the passenger may arrive at the terminal before the baggage, which may be transported to the designated baggage carousel via a unified check-in procedure. The existing airport passengers generally intelligently inquire the position of the luggage turnplate and the number of the luggage turnplate corresponding to the flight, and cannot obtain the time for the luggage to reach the luggage turnplate, so that the passengers can only stay near the luggage turnplate for a long time to wait. The residence time of the passengers at the baggage retrieval point is increased, so that the passenger experience is poor.
Disclosure of Invention
Aiming at the problems, the application provides a method and a device for predicting the arrival time of the baggage, which reduce the residence time of passengers at a baggage extraction point and improve the experience effect of the passengers.
In order to achieve the above object, the present application provides the following technical solutions:
a method of baggage arrival time prediction, the method comprising
Collecting the associated information of the flight where the target luggage is located, wherein the associated information at least comprises the located flight data and the leading flight information corresponding to the located flight;
predicting to obtain the predicted time information of the target baggage reaching the target baggage turntable according to the associated information of the flight and a pre-established time prediction model;
pushing the estimated time information to a target passenger corresponding to the target baggage.
Optionally, the method further comprises:
obtaining sample information, wherein the sample information represents data information associated with the baggage arrival time in all current flight arrival time periods;
determining a label of each sample of the sample information, wherein the label is the time of a row matched with each sample to reach a luggage turntable;
and performing model training according to the sample information and the labels of each sample of the sample information to obtain a time prediction model.
Optionally, the determining the label of each sample point of the sample information includes:
and collecting the time of the baggage corresponding to each sample to the tray of the baggage through the radio frequency identification device.
Optionally, the obtaining sample information includes:
acquiring characteristic data of the current flight;
acquiring leading flight data on the same time sequence as the current flight;
generating single sample information according to the characteristic data of the current flight and the preamble aviation data corresponding to the current flight;
and combining the plurality of pieces of sample information to obtain sample information.
Optionally, the characteristic data of the current flight includes one or more of the following data:
the flight departure time characteristics, the actual arrival time period of the flight, the arrival time period of the flight schedule, the flight delay time period, the flight model number, the number of baggage carried by the flight aircraft, the arrival weather characteristics, the arrival temperature characteristics, the number of airplane stop positions of the flight aircraft, the number of baggage turntables corresponding to the flight, and the information of the stop positions of the flight and the distance between the baggage turntables.
Optionally, the model training is performed according to the sample information and the label of each sample of the sample information to obtain a time prediction model, which includes:
extracting features of the sample information, and carrying out feature representation on the extracted features to obtain target feature information;
and training the target characteristic information and the labels of each sample through an LSTM model to obtain a time prediction model.
A baggage arrival time prediction device, the device comprising:
the information acquisition unit is used for acquiring the associated information of the flight where the target luggage is located, wherein the associated information at least comprises the located flight data and the leading flight information corresponding to the located flight;
the prediction unit is used for predicting and obtaining the predicted time information of the target luggage reaching the target luggage turntable according to the associated information of the flight and a pre-established time prediction model;
and the pushing unit is used for pushing the estimated time information to the target passenger corresponding to the target luggage.
Optionally, the apparatus further comprises:
the system comprises a sample acquisition unit, a baggage arrival time detection unit and a baggage arrival time detection unit, wherein the sample acquisition unit is used for acquiring sample information, and the sample information represents data information associated with the baggage arrival time in all current flight arrival time periods;
a label determining unit, configured to determine a label of each sample of the sample information, where the label is a time when a line matched with each sample arrives at a luggage carousel;
and the model training unit is used for carrying out model training according to the sample information and the labels of each sample of the sample information to obtain a time prediction model.
Optionally, the tag determination unit includes:
collecting the time of the baggage corresponding to each sample to the tray of the baggage through the radio frequency identification device;
the sample acquisition unit includes:
the first acquisition subunit is used for acquiring the characteristic data of the current flight;
a second acquiring subunit, configured to acquire leading flight data in the same time sequence as the current flight;
the generation subunit is used for generating single sample information according to the characteristic data of the current flight and the preamble aviation data corresponding to the current flight;
a combining subunit, configured to combine a plurality of pieces of sample information to obtain sample information;
the characteristic data of the current flight includes one or more of the following data:
the flight departure time characteristics, the actual arrival time period of the flight, the arrival time period of the flight schedule, the flight delay time period, the flight model number, the number of baggage carried by the flight aircraft, the arrival weather characteristics, the arrival temperature characteristics, the number of airplane stop positions of the flight aircraft, the number of baggage turntables corresponding to the flight, and the information of the stop positions of the flight and the distance between the baggage turntables.
Optionally, the model training unit includes:
the characteristic extraction subunit is used for extracting the characteristics of the sample information and representing the extracted characteristics to obtain target characteristic information;
and the training subunit is used for training the target characteristic information and the labels of each sample through the LSTM model to obtain a time prediction model.
Compared with the prior art, the application provides a baggage arrival time prediction method and device, which are characterized in that the related information of a flight where a target baggage is located is collected, wherein the related information at least comprises the located flight data and the preamble flight information corresponding to the located flight; predicting to obtain the predicted time information of the target baggage reaching the target baggage turntable according to the associated information of the flight and a pre-established time prediction model; pushing the estimated time information to a target passenger corresponding to the target baggage. According to the application, the time prediction model can be obtained through multidimensional data according to the combined modeling of the current flight information and the preface flight information, so that the information quantity learned by the time prediction model is larger, the characterization capability is stronger, and the time prediction result is more accurate. Thereby reducing the residence time of the passengers at the baggage extraction point and improving the experience effect of the passengers.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present application, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of a baggage arrival time prediction method according to an embodiment of the present application;
fig. 2 is a schematic diagram of data segmentation according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of a baggage arrival time prediction apparatus according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The terms first and second and the like in the description and in the claims and in the above-described figures are used for distinguishing between different objects and not necessarily for describing a sequential or chronological order. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to the listed steps or elements but may include steps or elements not expressly listed.
In an embodiment of the application, a baggage arrival time prediction method is provided, and the method is applied to a civil aviation airport, wherein baggage arrival refers to the arrival of baggage at a baggage tray or a designated baggage picking point. Referring to fig. 1, the method may include:
s101, collecting the associated information of the flight where the target baggage is located.
The associated information at least comprises the located flight data and leading flight information corresponding to the located flight. The information collected in the embodiment of the application not only comprises the data information of the flight where the current target baggage is located, but also comprises M leading flight sets which possibly affect the arrival time of the current flight baggage in time sequence.
S102, predicting and obtaining the predicted time information of the target baggage reaching the target baggage carousel according to the associated information of the flight and a pre-created time prediction model.
The time prediction model is created in advance by sample information and has the function of predicting the time when the target baggage arrives at the target baggage carousel. Correspondingly, in the embodiment of the application, a method for creating a model is also provided, and the method further comprises the following steps:
obtaining sample information, wherein the sample information represents data information associated with the baggage arrival time in all current flight arrival time periods;
determining a label of each sample of the sample information, wherein the label is the time of a row matched with each sample to reach a luggage turntable;
and performing model training according to the sample information and the labels of each sample of the sample information to obtain a time prediction model.
Specifically, the time for the baggage corresponding to each sample to reach the baggage tray may be collected by the rfid device. The process of obtaining sample information is: acquiring characteristic data of the current flight; acquiring leading flight data on the same time sequence as the current flight; generating single sample information according to the characteristic data of the current flight and the preamble aviation data corresponding to the current flight; and combining the plurality of pieces of sample information to obtain sample information. The characteristic data of the current flight includes one or more of the following data: the flight departure time characteristics, the actual arrival time period of the flight, the arrival time period of the flight schedule, the flight delay time period, the flight model number, the number of baggage carried by the flight aircraft, the arrival weather characteristics, the arrival temperature characteristics, the number of airplane stop positions of the flight aircraft, the number of baggage turntables corresponding to the flight, and the information of the stop positions of the flight and the distance between the baggage turntables.
Specifically, training data is acquired in the training process, and all flight related information (including all data information related to the arrival time of the baggage in all the current flight arrival time periods) in the whole day is acquired by using a real-time civil aviation service system. The time when the baggage carried by the specific flight arrives at the baggage carousel on the same day is recorded by the hardware based on RFID, and the time is taken as result prediction data in the model training process. And constructing a time prediction model based on all the leading flight data of the current flight and combining the corresponding dimension data of the current flight. And using an LSTM algorithm, using the influence factor set of the current flight on the arrival time of the baggage, combining the influence factor set of the current M leading flights as single training data, and using the expected arrival time of the baggage of the current flight as tag data to perform model training. And predicting the arrival time of the current flight plum by using the current flight related data and combining all the preface flight data.
And S103, pushing the estimated time information to a target passenger corresponding to the target baggage.
For example, the baggage arrival time of the current flight is pushed to the passenger in advance through various modes such as an electronic screen, a mobile phone short message or an app message.
The application provides a luggage arrival time prediction method, which is characterized in that the related information of a flight where a target luggage is located is collected, wherein the related information at least comprises the located flight data and the leading flight information corresponding to the located flight; predicting to obtain the predicted time information of the target baggage reaching the target baggage turntable according to the associated information of the flight and a pre-established time prediction model; pushing the estimated time information to a target passenger corresponding to the target baggage. According to the application, the time prediction model can be obtained through multidimensional data according to the combined modeling of the current flight information and the preface flight information, so that the information quantity learned by the time prediction model is larger, the characterization capability is stronger, and the time prediction result is more accurate. Thereby reducing the residence time of the passengers at the baggage extraction point and improving the experience effect of the passengers.
The time prediction model created by the present application will be described in detail.
First, it is necessary to determine characteristic information affecting the arrival time of the baggage. It mainly includes two dimensions, one is each item of characteristic data related to the current flight, and the other is M preface flight sets which can influence the arrival time of the current flight baggage in time sequence.
The characteristic data related to the current flight includes: whether it is holiday (the day), the flight actual arrival time period, the planned arrival time period, the flight delay time period, the carrier aircraft model, the number of carrier aircraft baggage pieces, the weather when the aircraft arrives (the day), the temperature when the aircraft arrives (the current time period), the carrier aircraft stand number, the baggage picking point carousel number, the stand and baggage carousel distance.
The characteristic data related to the leading flight includes: the day is distinguished by the number of the baggage turntables, and all flight information sets and all flight related data feature sets of the day served on each baggage turntable (see description of the feature data related to the current flight, which is not repeated here).
For example: the flight number CA1234 [ whether or not it is holiday (the day), the flight actual arrival time period, the planned arrival time period, the flight delay time period, the carrier model, the carrier luggage number, the weather when the aircraft arrives (the day), the temperature when the aircraft arrives (the current time period), the carrier stand number, the luggage pick-up point carousel number, the distance between the stand and the luggage carousel ], the flight number CA6181 [ whether or not it is holiday, the flight actual arrival time, the estimated arrival time, the carrier model, the carrier luggage number, the weather when the aircraft arrives, the temperature when the aircraft arrives, the aircraft parking space number, the luggage pick-up carousel number, the stand-to-luggage carousel distance ]. M were counted.
And a single training data generation rule takes the luggage turntable as a main key to acquire the relevant characteristic data of all historical flights of the current luggage turntable.
Assuming that the current baggage carousel produces relevant baggage feature records of N flights altogether, starting with the first piece of data, using M as the data segmentation window size, the N flight records are subjected to mobile segmentation using a step size t. Referring to fig. 2, a schematic diagram of data slicing is shown in the embodiment of the present application. By using the method, all the historical data are segmented, and training data are generated. Each square in fig. 2 represents one flight data (characteristic data that the current flight is related to has a possible impact on the arrival time of the baggage) that arrives on the current baggage carousel.
The luggage separation plate is used, the current luggage separation plate is used for representing a flight number mark loaded by the current conveyor belt, reminding a user to pick up luggage, and meanwhile, the luggage separation plate is internally provided with an RFID electronic tag. The baggage carousel exits are provided with RFID readers that record the arrival time of baggage (arrival at the baggage carousel entrance) for a particular flight as all baggage carousels output. The method is used for predicting target predicted values for model training.
Constructing derivative variables may be variable factors that affect the arrival time of the baggage.
Whether the holiday is the holiday or not, the holiday of the whole year is preset. For example, when day 0 is used to represent a holiday, and day 1 is used to represent a holiday, the weight may be set for the holiday information on the day, such as a weight of 0.4 on a common weekend, a weight of 0.7 on eleven, and a weight of 0.8 on a weekend.
Actual arrival time period of flight: the actual arrival time of the flight is mapped to three periods of morning, daytime and nighttime. Morning (5:01-9:00), daytime (9:01-20:00), night (20:01-5:00).
The flight schedule arrival period is the same as the "actual arrival period of the flight".
Flight delay duration, aircraft delay duration = aircraft actual arrival actual-aircraft planned arrival time (units: minutes). The result is a numerical value type, and the numerical value type is used for unified processing.
Carrier model, encoded representation using One-Hot type vectors.
The baggage amount of the aircraft is carried, and the baggage consignment system can acquire the information of the current baggage amount of the aircraft. The representation is transformed using a numerical type variable.
The weather when the aircraft arrives can acquire the partial data through a weather forecast query interface. Including "sunny", "rainy", "heavy", "rainy", "snowy", "typhoon" and the like describe weather fields. The carrier model is represented by an One-Hot vector form.
The temperature of the aircraft at the time of arrival, the data sources are as above, and are represented by numerical type variable transformation.
The carrier aircraft parking space number, available in the airport data system, is encoded using One-Hot type vectors.
The baggage picking point carousel numbers, the baggage consignment system obtains, and uses One-Hot type vectors for coded representation.
The distance between the stand and the luggage turntable is represented by the luggage car entrance position of the airport terminal. The distance between the stand and the luggage turntable is actually used for representing the distance from the stand to the freight port of each terminal building, the part of data can be directly inquired and obtained in the knowledge graph of airport information, and the data sources are the data which are arranged and recorded when the airport is used for making indoor navigation. Conversion is performed using a numerical type transform.
The numerical type variable transformation represents normalization processing using min-max: scaling the range of values to (0, 1) and not changing the data distribution; the algorithm is a linear transformation of the original data, so that the result falls into the [0,1] interval, and the conversion function is as follows:
x＝(x-min)/(max-min)
max is the maximum value of the sample data, and min is the minimum value of the sample data.
Empirical constant values are used in place of max and min in the numerical variable conversion process of this patent. The 30-day historical similar data was used, with the two-sided boundary values within the 95% confidence interval as the maximum and minimum values, respectively. And taking out all similar data in 30 days, obtaining the mean value and the variance of the similar data, and obtaining the data range by using the mean value and the variance and a 95% confidence interval.
The basic idea of One-Hot is to use One-Hot type vector for coding representation: each value of the discrete feature is regarded as a state, if N different values exist in the feature, we can abstract the feature into N different states, and one-hot encoding ensures that each value only makes one state be in an "active state", that is, only one state bit value in the N states is 1, and other state bits are all 0. Such as the total 5 (D) airport all aircraft models, including 717, 737, 747, 757, 767, can be identified using 5 (D) dimensional data, such as 717 being represented by 10000 and 737 being represented by 010000.
In the embodiment of the application, to predict the arrival time of the passenger baggage at the baggage carousel, the current arrival time of the baggage is influenced by various characteristic factors of the environment where the current flight is located, and the influence of the arrival time of the baggage at the preceding flight is received, and the whole process is sequentially executed in the time dimension, and in the process, predicting the arrival time of the baggage at a certain flight can be understood as a typical prediction process based on time sequence. The model predicts using LSTM algorithm.
The LSTM model structure includes 1 input layer (the input dimension is determined by the flight-related baggage feature data dimension), 1 fully connected output layer.
The loss function (loss function) uses Mean Square Error (MSE), the optimization algorithm (Optimizer) uses adam, the batch size (batch_size) is set to 64, the learning rate is set to 0.001, dropout is set to 0.2, and the model weight is updated by using a random gradient descent method. After super-parameter optimization, the model is applied to a test set, and if the predicted deviation value is within the required range, the model is stored.
And acquiring data of the current flight subjected to feature engineering processing and processed data of M flights of the current flight preamble, inputting a prediction model, and predicting the luggage carousel time of the current flight when the luggage arrives at the luggage extraction point.
In the embodiment of the application, the LSTM deep learning framework is used for predicting the time sequence, compared with the traditional machine learning algorithm, the accuracy of the prediction is higher, the robustness and the fault tolerance to noise nerves are stronger, and the LSTM dynamic neural network is more suitable for predicting the time sequence than the static neural network BP network. And the method applies various feature information related to the current flight and historical feature information of the lead flight to carry out combined modeling, the information amount used in the modeling process is larger, and the characterization capability of the model is stronger. Using lstm and setting the step size to 1 greatly increases the number of training data samples. The application of the time window of M leading flights to manufacture test data increases the number of training samples on one hand, improves the training efficiency on the other hand, avoids using the whole data of one day for training, and has the advantages that the time is not divided by the day, and the data representation is continuous in the time dimension (for example, the luggage arrival time of flights with 1:10 minutes in the morning is predicted, and the data in a certain time window of the previous day can be used for prediction). By using supervised learning, the training data sample library can be continuously enriched by using real data after the system is online, the existing model can be continuously adjusted and optimized, and the model prediction capability can be improved. The embodiment of the application acquires the tag data, extracts the tag data by using the luggage segmentation cards with RFID, uniformly records the part of the data by using the system, has accurate identification, does not have shielding problem (the image identification of the digital cards is firstly carried out), has large effective identification space, has low maintenance cost during trial, is automatically completed in the whole process, and minimizes manual intervention.
The LSTM deep learning framework is described below.
LSTM will change memory in a very accurate manner, applying specialized learning mechanisms to remember, update, and focus on information. This helps track information over a longer period of time. In a cyclic neural network (RNN) model and a forward and backward propagation algorithm, since the RNN also has the problem of gradient disappearance, long-sequence data is difficult to process, and the RNN is improved to obtain a special case LSTM (Long Short-Term Memory) of the RNN, which can avoid gradient disappearance of the conventional RNN. The internal structure of the LSTM model at the time t of each sequence index position is as follows: in addition to the hidden state h (t) h (t) as the RNN, another hidden state is propagated forward at each sequence index position t. This hidden State is generally referred to as the Cell State (Cell State), denoted C (t) C (t). In addition to cellular status, LSTM is also known as Gate structure (Gate). The gates of the LSTM at each sequence index position t generally include a forget gate, an input gate, and an output gate.
The forgetting gate, input gate and output gate of LSTM and cell state are specifically described below.
The forgetting gate (forget gate) is, as the name implies, controlling whether to forget, i.e. in LSTM, controlling with a certain probability whether to forget the hidden cell state of the upper layer. The hidden state h (t-1) h (t-1) of the last sequence and the sequence data x (t) x (t) are input by the forgetting gate substructure, and the output f (t) f (t) of the forgetting gate is obtained through an activation function, generally sigmoid. Since the output f (t) f (t) of sigmoid is between [0,1], the output f { (t) } here represents the probability of forgetting the state of the upper layer of hidden cells. The mathematical expression is:
f(t)＝σ(Wfh(t-1)+Ufx(t)+bf)f(t)＝σ(Wfh(t-1)+Ufx(t)+bf)
where Wf, uf, bfWf, uf, bf are coefficients and biases of linear relationship, similar to those in RNN. Sigma is sigmoid the function is activated.
The input gate (input gate) is responsible for handling the input of the current sequence position, and consists of two parts, the first part uses a sigmoid activation function, the output is i (t) i (t), the second part uses a tanh activation function, the output is a (t) a (t), and the results of the two parts are multiplied and then updated. The mathematical expression is:
i(t)＝σ(Wih(t-1)+Uix(t)+bi)i(t)＝σ(Wih(t-1)+Uix(t)+bi)
a(t)＝tanh(Wah(t-1)+Uax(t)+ba)a(t)＝tanh(Wah(t-1)+Uax(t)+ba)
where Wi, ui, bi, wa, ua, ba are coefficients and biases of linear relationship, similar to those in RNN. Sigma is sigmoid the function is activated.
Cell status of LSTM. The results of both the forgotten gate and the input gate will be applied to the cell state C (t) C (t). How C (t) C (t) is derived from the cell state C (t-1) C (t-1) is described below.
The cell state C (t) C (t) consists of two parts, the first part is the product of C (t-1) C (t-1) and the forgetting gate output f (t) f (t), and the second part is the product of i (t) i (t) and a (t) a (t) of the input gate, namely:
c (t) =C (t-1) f (t) +i (t) ++a (t) C (t) =C (t-1) the ratio of ". Sup.f (t) +i (t) ++a (t) where". Sup.i.is Hadamard product and used in DNN.
The output structures are as follows:
the updating of the hidden state h (t) h (t) consists of two parts, the first part is o (t) o (t), which is obtained by the hidden state h (t-1) h (t-1) of the previous sequence and the present sequence data x (t) x (t), and the activating function sigmoid, and the second part consists of the hidden state C (t) C (t) and the tanh activating function, namely:
o(t)＝σ(Woh(t-1)+Uox(t)+bo)o(t)＝σ(Woh(t-1)+Uox(t)+bo)
h(t)＝o(t)⊙tanh(C(t))h(t)＝o(t)⊙tanh(C(t))
in an embodiment of the present application, there is provided a baggage arrival time prediction apparatus, referring to fig. 3, the apparatus including:
an information collection unit 10, configured to collect association information of a flight on which a target baggage is located, where the association information includes at least the located flight data and leading flight information corresponding to the located flight;
a prediction unit 20, configured to predict and obtain predicted time information that the target baggage reaches the target baggage carousel according to the associated information of the flight and a pre-created time prediction model;
and a pushing unit 30, configured to push the estimated time information to a target passenger corresponding to the target baggage.
On the basis of the above embodiment, the apparatus further includes:
the system comprises a sample acquisition unit, a baggage arrival time detection unit and a baggage arrival time detection unit, wherein the sample acquisition unit is used for acquiring sample information, and the sample information represents data information associated with the baggage arrival time in all current flight arrival time periods;
a label determining unit, configured to determine a label of each sample of the sample information, where the label is a time when a line matched with each sample arrives at a luggage carousel;
and the model training unit is used for carrying out model training according to the sample information and the labels of each sample of the sample information to obtain a time prediction model.
On the basis of the above embodiment, the tag determination unit includes:
collecting the time of the baggage corresponding to each sample to the tray of the baggage through the radio frequency identification device;
the sample acquisition unit includes:
the first acquisition subunit is used for acquiring the characteristic data of the current flight;
a second acquiring subunit, configured to acquire leading flight data in the same time sequence as the current flight;
the generation subunit is used for generating single sample information according to the characteristic data of the current flight and the preamble aviation data corresponding to the current flight;
a combining subunit, configured to combine a plurality of pieces of sample information to obtain sample information;
the characteristic data of the current flight includes one or more of the following data:
the flight departure time characteristics, the actual arrival time period of the flight, the arrival time period of the flight schedule, the flight delay time period, the flight model number, the number of baggage carried by the flight aircraft, the arrival weather characteristics, the arrival temperature characteristics, the number of airplane stop positions of the flight aircraft, the number of baggage turntables corresponding to the flight, and the information of the stop positions of the flight and the distance between the baggage turntables.
On the basis of the above embodiment, the model training unit includes:
the characteristic extraction subunit is used for extracting the characteristics of the sample information and representing the extracted characteristics to obtain target characteristic information;
and the training subunit is used for training the target characteristic information and the labels of each sample through the LSTM model to obtain a time prediction model.
The application provides a baggage arrival time prediction device, which is characterized in that the related information of a flight where a target baggage is located is collected, wherein the related information at least comprises the located flight data and the leading flight information corresponding to the located flight; predicting to obtain the predicted time information of the target baggage reaching the target baggage turntable according to the associated information of the flight and a pre-established time prediction model; pushing the estimated time information to a target passenger corresponding to the target baggage. According to the application, the time prediction model can be obtained through multidimensional data according to the combined modeling of the current flight information and the preface flight information, so that the information quantity learned by the time prediction model is larger, the characterization capability is stronger, and the time prediction result is more accurate. Thereby reducing the residence time of the passengers at the baggage extraction point and improving the experience effect of the passengers.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (7)

1. A method of predicting a time of arrival of a baggage, the method comprising:
collecting the associated information of the flight where the target luggage is located, wherein the associated information at least comprises the located flight data and the leading flight information corresponding to the located flight;
predicting to obtain the predicted time information of the target baggage reaching the target baggage turntable according to the associated information of the flight and a pre-established time prediction model; the time prediction module is an LSTM model;
pushing the estimated time information to a target passenger corresponding to the target baggage;
wherein the method further comprises:
obtaining sample information, wherein the sample information represents data information associated with the baggage arrival time in all current flight arrival time periods;
determining a label of each sample of the sample information, wherein the label is the time of a row matched with each sample to reach a luggage turntable;
model training is carried out according to the sample information and the labels of each sample of the sample information, so as to obtain a time prediction model;
the obtaining sample information includes:
acquiring characteristic data of the current flight;
acquiring leading flight data on the same time sequence as the current flight;
generating single sample information according to the characteristic data of the current flight and the preamble aviation data corresponding to the current flight; after acquiring the relevant baggage feature records of a plurality of flights, starting from a first piece of data, using M as the data segmentation window size, and using a step length t to carry out mobile segmentation on the relevant baggage feature records of the plurality of flights to generate single sample information;
and combining the plurality of pieces of sample information to obtain sample information.
2. The method of claim 1, wherein the determining the label for each sample point of the sample information comprises:
and collecting the time of the baggage corresponding to each sample to the tray of the baggage through the radio frequency identification device.
3. The method of claim 1, wherein the characteristic data of the current flight includes one or more of the following:
the flight departure time characteristics, the actual arrival time period of the flight, the arrival time period of the flight schedule, the flight delay time period, the flight model number, the number of baggage carried by the flight aircraft, the arrival weather characteristics, the arrival temperature characteristics, the number of airplane stop positions of the flight aircraft, the number of baggage turntables corresponding to the flight, and the information of the stop positions of the flight and the distance between the baggage turntables.
4. A method according to claim 3, wherein the model training based on the sample information and the labels of each sample of the sample information to obtain a time prediction model comprises:
extracting features of the sample information, and carrying out feature representation on the extracted features to obtain target feature information;
and training the target characteristic information and the labels of each sample through an LSTM model to obtain a time prediction model.
5. A baggage arrival time prediction apparatus, said apparatus comprising:
the information acquisition unit is used for acquiring the associated information of the flight where the target luggage is located, wherein the associated information at least comprises the located flight data and the leading flight information corresponding to the located flight;
the prediction unit is used for predicting and obtaining the predicted time information of the target luggage reaching the target luggage turntable according to the associated information of the flight and a pre-established time prediction model; the time prediction module is an LSTM model;
a pushing unit, configured to push the estimated time information to a target passenger corresponding to the target baggage;
wherein the apparatus further comprises:
the system comprises a sample acquisition unit, a baggage arrival time detection unit and a baggage arrival time detection unit, wherein the sample acquisition unit is used for acquiring sample information, and the sample information represents data information associated with the baggage arrival time in all current flight arrival time periods;
a label determining unit, configured to determine a label of each sample of the sample information, where the label is a time when a line matched with each sample arrives at a luggage carousel;
the model training unit is used for carrying out model training according to the sample information and the labels of each sample of the sample information to obtain a time prediction model;
the sample acquisition unit includes:
the first acquisition subunit is used for acquiring the characteristic data of the current flight;
a second acquiring subunit, configured to acquire leading flight data in the same time sequence as the current flight;
the generation subunit is used for generating single sample information according to the characteristic data of the current flight and the preamble aviation data corresponding to the current flight; after acquiring the relevant baggage feature records of a plurality of flights, starting from a first piece of data, using M as the data segmentation window size, and using a step length t to carry out mobile segmentation on the relevant baggage feature records of the plurality of flights to generate single sample information;
and the combining subunit is used for combining the plurality of pieces of sample information to obtain sample information.
6. The apparatus according to claim 5, wherein the tag determination unit includes:
collecting the time of the baggage corresponding to each sample to the tray of the baggage through the radio frequency identification device;
the characteristic data of the current flight includes one or more of the following data:
the flight departure time characteristics, the actual arrival time period of the flight, the arrival time period of the flight schedule, the flight delay time period, the flight model number, the number of baggage carried by the flight aircraft, the arrival weather characteristics, the arrival temperature characteristics, the number of airplane stop positions of the flight aircraft, the number of baggage turntables corresponding to the flight, and the information of the stop positions of the flight and the distance between the baggage turntables.
7. The apparatus of claim 6, wherein the model training unit comprises:
the characteristic extraction subunit is used for extracting the characteristics of the sample information and representing the extracted characteristics to obtain target characteristic information;
and the training subunit is used for training the target characteristic information and the labels of each sample through the LSTM model to obtain a time prediction model.
CN201911395473.5A 2019-12-30 2019-12-30 Luggage arrival time prediction method and device Active CN111178628B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911395473.5A CN111178628B (en) 2019-12-30 2019-12-30 Luggage arrival time prediction method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911395473.5A CN111178628B (en) 2019-12-30 2019-12-30 Luggage arrival time prediction method and device

Publications (2)

Publication Number Publication Date
CN111178628A CN111178628A (en) 2020-05-19
CN111178628B true CN111178628B (en) 2023-09-19

Family

ID=70654298

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911395473.5A Active CN111178628B (en) 2019-12-30 2019-12-30 Luggage arrival time prediction method and device

Country Status (1)

Country Link
CN (1) CN111178628B (en)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112396254A (en) * 2020-12-11 2021-02-23 北京百分点信息科技有限公司 Destination prediction method, destination prediction device, destination prediction medium, and electronic device
CN112836905B (en) * 2021-04-22 2021-08-03 中航信移动科技有限公司 Flight event occurrence time prediction method, device, equipment and storage medium
CN113449915B (en) * 2021-06-28 2023-10-27 中国电子科技集团公司第二十八研究所 Flight delay prediction method based on knowledge graph
CN113835331A (en) * 2021-09-10 2021-12-24 西安悦泰科技有限责任公司 Method for acquiring and displaying passenger baggage extraction pre-waiting time
CN116596168A (en) * 2023-07-17 2023-08-15 四川省机场集团有限公司 Airport luggage information synchronization and prediction method and system
CN116703010B (en) * 2023-08-09 2023-10-31 民航成都信息技术有限公司 Luggage arrival time prediction method and device, electronic equipment and medium

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004046522A (en) * 2002-07-11 2004-02-12 Mitsubishi Electric Corp Aircraft arrival information delivery system, processing server and terminal
CN106778857A (en) * 2016-12-09 2017-05-31 北京首都国际机场股份有限公司 To the method that port flight baggage status are obtained automatically
CN108197081A (en) * 2017-11-03 2018-06-22 上海敬之网络科技有限公司 A kind of data actuarial model method for building up of flight delay danger
CN108388963A (en) * 2018-02-13 2018-08-10 百度在线网络技术（北京）有限公司 Luggage arrival time prediction technique, device, computer equipment and readable medium
CN109448445A (en) * 2018-09-05 2019-03-08 南京航空航天大学 Flight based on shot and long term Memory Neural Networks is delayed grading forewarning system method
CN109791731A (en) * 2017-06-22 2019-05-21 北京嘀嘀无限科技发展有限公司 A kind of method and system for estimating arrival time

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004046522A (en) * 2002-07-11 2004-02-12 Mitsubishi Electric Corp Aircraft arrival information delivery system, processing server and terminal
CN106778857A (en) * 2016-12-09 2017-05-31 北京首都国际机场股份有限公司 To the method that port flight baggage status are obtained automatically
CN109791731A (en) * 2017-06-22 2019-05-21 北京嘀嘀无限科技发展有限公司 A kind of method and system for estimating arrival time
CN108197081A (en) * 2017-11-03 2018-06-22 上海敬之网络科技有限公司 A kind of data actuarial model method for building up of flight delay danger
CN108388963A (en) * 2018-02-13 2018-08-10 百度在线网络技术（北京）有限公司 Luggage arrival time prediction technique, device, computer equipment and readable medium
CN109448445A (en) * 2018-09-05 2019-03-08 南京航空航天大学 Flight based on shot and long term Memory Neural Networks is delayed grading forewarning system method

Also Published As

Publication number Publication date
CN111178628A (en) 2020-05-19

Similar Documents

Publication Publication Date Title
CN111178628B (en) Luggage arrival time prediction method and device
CN111223301B (en) Traffic flow prediction method based on graph attention convolution network
CN109389244B (en) GRU-based multi-factor perception short-term scenic spot visitor number prediction method
CN101414366B (en) Method for forecasting electric power system short-term load based on method for improving uttermost learning machine
CN110570678B (en) Method and device for predicting total travel time of bus from starting point to end point
Chen et al. Uncertainty in urban mobility: Predicting waiting times for shared bicycles and parking lots
CN109583565A (en) Forecasting Flood method based on the long memory network in short-term of attention model
CN109086926B (en) Short-time rail transit passenger flow prediction method based on combined neural network structure
CN111242395B (en) Method and device for constructing prediction model for OD (origin-destination) data
CN113393032B (en) Track circulation prediction method based on resampling
Ballakur et al. Empirical evaluation of gated recurrent neural network architectures in aviation delay prediction
CN113657671B (en) Flight delay prediction method based on ensemble learning
Yu et al. Improved convolutional neural network‐based quantile regression for regional photovoltaic generation probabilistic forecast
Lin et al. Short-term metro passenger flow prediction based on random forest and LSTM
CN112132366A (en) Prediction system for flight clearance rate
Zhang et al. An interpretable station delay prediction model based on graph community neural network and time-series fuzzy decision tree
CN115358491A (en) Subway passenger flow prediction method and system based on CEEMDAN-LSTM
CN114078237A (en) Remote sensing image road change identification method and device
CN116432806A (en) Rolling prediction method and system for flight ground guarantee node time
Xu et al. A taxi dispatch system based on prediction of demand and destination
CN113221472B (en) Passenger flow prediction method based on LSTM
CN110659773A (en) Flight delay prediction method based on deep learning
Agga et al. Short-term load forecasting: based on hybrid CNN-LSTM neural network
Faridai et al. Neural network model for predicting passenger congestion to optimize traffic management for urban public transport
CN113112050A (en) W-BilSTM-based short-time passenger flow prediction method for rail transit

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