CN110837928A - Method and device for predicting security check time - Google Patents
Method and device for predicting security check time Download PDFInfo
- Publication number
- CN110837928A CN110837928A CN201911070494.XA CN201911070494A CN110837928A CN 110837928 A CN110837928 A CN 110837928A CN 201911070494 A CN201911070494 A CN 201911070494A CN 110837928 A CN110837928 A CN 110837928A
- Authority
- CN
- China
- Prior art keywords
- time
- security check
- data
- prediction
- security
- 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
- 238000000034 method Methods 0.000 title claims abstract description 72
- 238000012549 training Methods 0.000 claims abstract description 86
- 238000007781 pre-processing Methods 0.000 claims abstract description 21
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 20
- 238000007689 inspection Methods 0.000 claims description 140
- 238000012795 verification Methods 0.000 claims description 35
- 238000012360 testing method Methods 0.000 claims description 29
- 238000012545 processing Methods 0.000 claims description 26
- 238000012544 monitoring process Methods 0.000 claims description 21
- 238000010606 normalization Methods 0.000 claims description 15
- 238000005070 sampling Methods 0.000 claims description 9
- 238000010276 construction Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 5
- 238000005457 optimization Methods 0.000 claims description 3
- 238000010200 validation analysis Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 6
- 230000010006 flight Effects 0.000 description 6
- 238000001514 detection method Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000005034 decoration Methods 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000002759 z-score normalization 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
- G06Q10/04—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
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/53—Recognition of crowd images, e.g. recognition of crowd congestion
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- General Business, Economics & Management (AREA)
- Software Systems (AREA)
- Marketing (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Development Economics (AREA)
- Computational Linguistics (AREA)
- Primary Health Care (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Computer Security & Cryptography (AREA)
- Operations Research (AREA)
- Multimedia (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method and a device for predicting security check time, wherein the method comprises the following steps: acquiring security check time of a newly arrived passenger and airport historical data in a preset time period; preprocessing the security check time of the newly arrived passenger and the airport historical data to obtain time interval data; and predicting the security check time in a pre-constructed prediction model based on the time interval data to obtain the security check prediction time at the current moment. It can be seen that, in the embodiment of the invention, the prediction time of the security check at the current moment can be predicted by the prediction model generated based on the LSTM algorithm model and the sample time data training, so that the prediction of the security check time is realized, and the security check port can be allocated based on the predicted prediction time of the security check at the current moment, so that the travel satisfaction of passengers is improved and the labor cost is reduced.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a method and a device for predicting security check time.
Background
At present, for the security inspection process of an airport, a security inspection manager usually observes the number of people who queue in each security inspection queue at present, manually coordinates the number of people in each security inspection queue or opens a corresponding number of security inspection ports as appropriate.
However, this method has a certain hysteresis in terms of relieving the security queue, which has affected the travel satisfaction of passengers, and secondly, this method is based on manual observation and coordination, and requires a large number of security managers to stand by, thereby causing waste of manpower.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method and an apparatus for predicting security check time, so as to predict the security check time, and arrange a security check port in advance based on the predicted security check time, thereby improving the travel satisfaction of passengers and reducing the labor cost.
In order to achieve the above purpose, the embodiments of the present invention provide the following technical solutions:
the embodiment of the invention discloses a method for predicting security check time on one hand, which comprises the following steps:
acquiring security check time of a newly arrived passenger and airport historical data in a preset time period, wherein the airport historical data at least comprise security check related data, passenger related data and predicted influence data, the predicted influence data refer to related data influencing a prediction result, and the security check time comprises security check waiting time and security check clearance time;
preprocessing the security check time of the newly arrived passenger and the airport historical data to obtain time interval data;
and predicting the security check time in a pre-constructed prediction model based on the time interval data to obtain the security check prediction time at the current moment, wherein the pre-constructed prediction model is constructed based on an LSTM algorithm model.
Optionally, the process of acquiring the security check time of the new arriving passenger includes:
obtaining the current time T0The number n of the opened security inspection ports;
obtaining security check monitoring image data, and determining current time T based on the security check monitoring image data0The number of people in a security queue at a security inspection port is m;
calculating the current time T based on the open number n of the security inspection openings and the number m of the security inspection queue people0The average queue number P in the security check area;
according to the average number of people in the queue P and the average handling time T of the security inspectionave_dealCalculating the security check time t of the newly arrived passenger0The security inspection time of the newly arrived passenger
Wherein, the average handling time T of the security inspectionave_dealThe passenger security check passing time is divided by the number of the security check clearance persons,
waiting time for new arriving passenger queue, PTave_dealFor the total time of security check of P passengers outside the security check port,
for the current time T0The remaining security check transaction time of the passenger who entered the security check operating area through ticket checking.
Optionally, the preprocessing the security check time of the newly arrived passenger and the airport historical data to obtain time interval data includes:
extracting feature data of different feature types in the security check time of the new arriving passenger and the airport historical data based on the feature types, wherein the feature types comprise security check state features, passenger flow volume features and prediction influence features;
carrying out null filling and normalization processing on the characteristic data to obtain processed characteristic data;
and dividing the processed characteristic data based on preset equal intervals according to the time sequence to obtain time interval data corresponding to each characteristic data.
Optionally, the process of constructing the prediction model in advance includes:
acquiring sample data, wherein the sample data comprises airport historical data in a sampling time period and security check time of a newly arrived passenger;
extracting sample feature data of different feature types in the sample data based on the feature types, wherein the feature types comprise security inspection state features, passenger flow volume features and prediction influence features;
carrying out null filling and normalization processing on the sample characteristic data to obtain processed sample characteristic data;
dividing the processed sample characteristic data based on preset equal intervals according to a time sequence to obtain sample time interval data corresponding to each characteristic data;
dividing the sample time interval data into a training set, a verification set and a test set based on a preset proportion;
and determining an initial LSTM network model, training the LSTM network model based on the training set, the verification set and the test set until the obtained prediction deviation value is within a preset range, and determining the LSTM network model obtained by current training as a prediction model.
Optionally, the determining an initial LSTM network model, training the LSTM network model based on the training set, the verification set, and the test set until the obtained prediction deviation value is within a preset range, and determining the currently trained LSTM network model as a prediction model includes:
configuring initial network parameters of an initial LSTM network model based on the determined LSTM network model algorithm;
training the initial network parameters on the training set;
optimizing the network parameters trained by the training set on the verification set by adopting a k-fold cross verification method to obtain optimized network parameters, and constructing an optimized LSTM network model based on the optimized network parameters;
predicting the sample time interval data in the test set in the optimized LSTM network model to obtain security check prediction time;
calculating a difference value between the safety inspection prediction time and the sample safety inspection prediction time to obtain a prediction deviation value;
if the prediction deviation value is within the preset range, determining the currently optimized LSTM network model as a prediction model;
and if the prediction deviation value is out of the prediction range, training the optimized LSTM network model on the basis of the training set, the verification set and the test set.
In another aspect, an embodiment of the present invention discloses a device for predicting security inspection time, including:
the system comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring the security check time of a new passenger and airport historical data in a preset time period, the airport historical data at least comprises security check related data, passenger related data and prediction influence data, the prediction influence data refers to related data influencing a prediction result, and the security check time comprises security check waiting time and security check clearance time;
the preprocessing unit is used for preprocessing the security check time of the newly arrived passenger and the airport historical data to obtain time interval data;
and the prediction unit is used for predicting the security check time based on the time interval data in a pre-constructed prediction model to obtain the security check prediction time of the current moment, and the pre-constructed prediction model is constructed based on an LSTM algorithm model.
Optionally, the obtaining unit for obtaining the security check time of the new passenger specifically includes:
a first obtaining module for obtaining the current time T0The open number n of the security inspection ports is used for acquiring security inspection monitoring image data, and the current time T is determined based on the security inspection monitoring image data0The number m of security check queues at the security check port is calculated, and the current time T is calculated based on the security check port opening data n and the number m of security check queues0The average queue number P in the security check area;
a first calculation module for calculating the average queue number P and the average handling time T of the security inspectionave_dealCalculating the security check time t of the newly arrived passenger0The security inspection time of the newly arrived passenger
Wherein, the average handling time T of the security inspectionave_dealThe passenger security check passing time is divided by the number of the security check clearance persons,
waiting time for new arriving passenger queue, PTave_dealFor the total time of security check of P passengers outside the security check port,
for the current time T0The remaining security check transaction time of the passenger who entered the security check operating area through ticket checking.
Optionally, the preprocessing unit includes:
the first extraction module is used for extracting the new passenger security check time and the feature data of different feature types in the airport historical data based on the feature types, wherein the feature types comprise security check state features, passenger flow volume features and prediction influence features;
the first processing module is used for carrying out null filling and normalization processing on the characteristic data to obtain processed characteristic data;
and the first dividing module is used for dividing the processed characteristic data based on preset equal intervals according to the time sequence to obtain time interval data corresponding to each characteristic data.
Optionally, a pre-construction unit;
the pre-construction unit comprises:
the second acquisition module is used for acquiring sample data, wherein the sample data comprises airport historical data in a sampling time period and the security check time of a newly arrived passenger;
the second extraction module is used for extracting sample characteristic data of different characteristic types in the sample data based on the characteristic types, wherein the characteristic types comprise security check state characteristics, passenger flow characteristics and prediction influence characteristics;
the second processing module is used for carrying out null filling and normalization processing on the sample characteristic data to obtain processed sample characteristic data;
the second dividing module is used for dividing the processed sample characteristic data based on preset equal intervals according to a time sequence to obtain sample time interval data corresponding to each characteristic data, and dividing the sample time interval data into a training set, a verification set and a test set based on a preset proportion;
and the training module is used for determining an initial LSTM network model, training the LSTM network model based on the training set, the verification set and the test set until the obtained prediction deviation value is within a preset range, and determining the LSTM network model obtained by current training as a prediction model.
Optionally, the training module includes:
the configuration submodule is used for configuring initial network parameters of the initial LSTM network model based on the determined LSTM network model algorithm;
a training sub-module for training the initial network parameters on the training set;
the optimization module is used for optimizing the network parameters trained by the training set on the verification set by adopting a k-fold cross verification method to obtain optimized network parameters, and constructing an optimized LSTM network model based on the optimized network parameters;
the prediction module is used for predicting the sample time interval data in the test set in the optimized LSTM network model to obtain the security check prediction time;
and the second calculation module is used for calculating a difference value between the safety inspection prediction time and the sample safety inspection prediction time to obtain a prediction deviation value, determining the currently optimized LSTM network model as the prediction model if the prediction deviation value is within a preset range, and continuing training the optimized LSTM network model based on the training set, the verification set and the test set if the prediction deviation value is outside the prediction range.
Based on the method and the device for predicting the security check time provided by the embodiment of the invention, the method comprises the following steps: acquiring security check time of a newly arrived passenger and airport historical data in a preset time period; preprocessing the security check time of the newly arrived passenger and the airport historical data to obtain time interval data; and predicting the security check time in a pre-constructed prediction model based on the time interval data to obtain the security check prediction time at the current moment. It can be seen that, in the embodiment of the invention, the prediction time of the security check at the current moment can be predicted by the prediction model generated based on the LSTM algorithm model and the sample time data training, so that the prediction of the security check time is realized, and the security check port can be allocated based on the predicted prediction time of the security check at the current moment, so that the travel satisfaction of passengers is improved and the labor cost is reduced.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a schematic flowchart of a method for predicting a security inspection time according to an embodiment of the present invention;
fig. 2 is a schematic flow chart illustrating the process of determining time interval data according to an embodiment of the present invention;
fig. 3 is a block diagram of a device for predicting security inspection time according to an embodiment of the present invention;
fig. 4 is a block diagram of a device for predicting security inspection time according to an embodiment of the present invention;
fig. 5 is a block diagram of a device for predicting security inspection time according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the 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 invention.
In this application, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
It can be known from the background art that in the existing airport security inspection process, security inspection managers are often adopted to observe the number of queuing people of each current security inspection queue, manually coordinate the number of security inspection queues or open corresponding number of security inspection ports as appropriate, but this mode has a certain hysteresis in relieving the security inspection queues, which has affected the traveling satisfaction of passengers, and secondly, this mode needs a large number of security inspection managers to stand by on the basis of manual observation and coordination, thereby causing the waste of manpower.
Therefore, the embodiment of the invention provides a method and a device for predicting the security check time, which can predict the security check prediction time at the current moment through a prediction model generated based on an LSTM algorithm model and sample data training, thereby realizing the prediction of the security check time, and allocating a security check port based on the predicted security check prediction time at the current moment, thereby improving the travel satisfaction of passengers and reducing the labor cost.
In the embodiment of the invention, the new passenger can be a domestic passenger or an international passenger, which can be set according to the situation, and the application is not limited.
Referring to fig. 1, a schematic flowchart of a method for predicting a security inspection time according to an embodiment of the present invention is shown, where the method includes:
step S101: and acquiring the security check time of the newly arrived passenger and the airport historical data in a preset time period.
In step S101, the airport historical data at least includes security inspection related data, passenger related data, and prediction influence data, the prediction influence data refers to related data influencing the prediction result, and the security inspection time includes security inspection waiting time and security inspection clearance time.
In the process of implementing step S101 specifically, security check waiting data and security check clearance time of a new passenger are acquired, and security check related data, passenger related data and predicted impact data within a preset time period are extracted from the database.
It should be noted that the predicted impact data at least includes flight data, and/or date data, and/or weather data; the passenger related data comprises passenger flow data and/or passenger check-in data; the security relevant data comprises security time and security monitoring image data.
In a specific implementation, the process of acquiring the security inspection waiting data and the security inspection clearance time of the newly arrived passenger comprises the following steps:
step S11: obtaining the current time T0The number n of the opened security inspection ports.
In step S11, n is an integer of 1 or more.
In the process of implementing step S11, the current time T is obtained from the database0The number n of the opened security inspection ports.
Step S12: obtaining security check monitoring image data, and determining current time T based on the security check monitoring image data0The number of people in the security inspection queue at the security inspection port is m.
In step S12, m is an integer of 1 or more.
In step S12, the time T in the database is called0The monitoring image data in front of the security inspection area is determined at the moment T through an image detection technology based on the security inspection monitoring image data0The number of people in the security inspection queue at the security inspection port is m.
It should be noted that the image detection technology may be RGB (Red Green Blue ), infrared image detection technology, AI (Artificial Intelligence) image detection technology, or other technologies capable of identifying a human body in an image, and the application is not limited thereto.
Step S13: calculating the current time T based on the open number n of the security inspection openings and the number m of the security inspection queue people0The average number of people in the queue P in the security check area.
It should be noted that, theoretically, the number of people in the security check queue per security check port is equivalent, and in the embodiment of the present invention, it is allowed that there is a case where the number of people in the security check queue is inconsistent.
In the process of specifically implementing the step S13, based on the number m of the security check queues obtained in the step S11 and the number n of the security check openings obtained in the step S12, the current time T is calculated and obtained through the formula (1)0The average number of people in the queue P in the security check area. Formula (1):
wherein m is the number of people in the security inspection queue, and n is the number of open security inspection openings.
Step S14: according to the average number of people in queue P and the average handling time T of security inspectionave_dealCalculating the security check time t of the newly arrived passenger0。
In step S14, the security check time of the new arriving passenger includes a security check waiting time and a security check clearance time.
Calculating the security check time t of the newly arrived passenger based on the formula (2)0。
Wherein the content of the first and second substances,waiting time for the new arriving passenger queue, namely waiting time for security check.
PTave_dealFor the total time of security check of P passengers outside the security check port,
for the current time T0The remaining security check transaction time of the passenger who entered the security check operating area through ticket checking.
Wherein, Tave_dealAverage handling time for security inspection, Tave_dealAnd the security check handling time of the newly arrived passenger queue, namely the security check clearance time.
Is calculated by formula (3)Calculating average handling time T of security checkave_deal。
Formula (3):
wherein a is the number of people passing the customs clearance for security inspection, and the accumulated passing time b is the product of the number of security inspection mouths and the total security inspection time of the number of people at each security inspection mouth.
For better explanation of the newly arriving traveler' S security check time t shown in the above-mentioned steps S11 to S140The calculation process of (2) is explained below.
Such as: obtaining the current No. 10/8 month and the time T from the database0When the number of the current security inspection openings is 15, acquiring 8 current security inspection openings from the database; calling the time T in the database0Monitoring image data in front of a security check area, wherein the number of the human images in the monitoring image data in front of the security check area is 200 when the monitoring image data is detected by an AI image detection technology for 15 hours; based on that the number m of people in the security check queue is 200 and the current number n of the opened security check openings is 8, determining that the ratio of the number m of people in the security check queue to the current number n of the opened security check openings is 25, and determining the current T0The number P of the average queue people in the security inspection area at any moment is 25; the accumulated passenger security inspection passing time of the previous 12 hours in the database is 19 hours, the security inspection clearance number is 576, the accumulated passenger security inspection passing time is 19 hours, and the security inspection clearance number is 576 to obtain the average security inspection handling time Tave_dealIs 2 minutes; substituting the data into formula (2) for calculation, and obtaining the security check time t of the new passenger as shown in formula (4)0Was 53 minutes.
Formula (4):
it should be noted that the specific data and examples mentioned above are only for illustrative purposes.
Step S102: and preprocessing the newly arrived passenger security check time and airport historical data to obtain time interval data.
In the process of implementing step S102, the waiting time of security check of the newly arrived passenger is determined according to the time sequence
And security inspection clearance time Tave_dealAnd preprocessing the data related to security inspection, the data related to passengers and the data of predicted influence data in a preset time period to obtain time interval data.
Step S103: and predicting the security check time in a pre-constructed prediction model based on the time interval data to obtain the security check prediction time at the current moment.
In step S103, the pre-constructed prediction model is constructed based on the LSTM algorithm model.
It should be noted that the LSTM algorithm model includes an output layer, long-short term memory LSTM units and an output layer.
It should be noted that the sample time interval data is obtained by preprocessing sample data.
It should be noted that the pre-construction process of the prediction model includes the following steps:
step S21: and acquiring sample data.
In step S21, the sample data includes airport history data and the newly arrived passenger' S security check time within the sampling time period.
It should be noted that the airport historical data at least includes security inspection related data, passenger related data and prediction influence data, the prediction influence data refers to related data influencing the prediction result, and the security inspection time includes security inspection waiting time and security inspection clearance time.
In the process of implementing step S21 specifically, security inspection related data, passenger related data and predicted impact data of the passenger in the sampling time period, and security inspection waiting data and security inspection clearance time of the newly arrived passenger are acquired.
It should be noted that the predicted impact data at least includes flight data, and/or date data, and/or weather data; the passenger related data comprises passenger flow data and/or passenger check-in data; the security relevant data comprises security time and security monitoring image data.
Step S22: and extracting sample feature data of different feature types in the sample data based on the feature types.
In step S22, the feature types include a security check status feature, a passenger traffic volume feature, and a prediction influence feature.
In the process of specifically implementing step S22, based on the security check status feature, the passenger flow volume feature, and the prediction influence feature, feature data of the security check status feature type, feature data of the passenger flow volume feature type, and feature data of the prediction influence feature type in the sample data are extracted from the database.
It should be noted that the security inspection state features include security inspection time, security inspection monitoring image data and other features that affect the security inspection time; the passenger flow characteristics comprise the characteristics of affecting the number of passengers going out, such as the number of flights in the check-in state, the number of flights in the boarding state, the number of passengers in the check-in state, the number of passengers in the security check state and the like; the predicted influence characteristics comprise whether the system is on weekends, whether the system is on holidays, weather conditions, the number of departure domestic flights in x hours in the future, the number of domestic passenger flows in x hours in the future and the like, and the system can be set according to actual conditions and is not limited in the application.
The check-in state refers to a state in which a check-in is checked in.
Step S23: and carrying out null filling and normalization processing on the sample characteristic data to obtain the processed sample characteristic data.
It should be noted that the null filling is processing performed to avoid the abnormal feature data caused by the loss of the feature data, and the null filling is performed by a filling method such as fixed value filling, mean value filling, or random forest form algorithm filling, which can be set according to the actual situation, and the application is not limited.
It should be noted that, in order to summarize the statistical distribution of the unified feature data and avoid the feature data having different evaluation indexes, thereby affecting the accuracy of feature data processing, the normalization processing method is usually performed on the feature data by a dispersion normalization method or a Z-score normalization method, and the method can be set according to the actual situation, and the application is not limited.
Step S24: and according to the time sequence, dividing the processed sample characteristic data based on a preset equal interval to obtain sample time interval data corresponding to each characteristic data.
In the process of specifically implementing step S24, the feature data of the security check status feature type, the feature data of the passenger traffic volume feature type, and the feature data of the predicted impact feature type after null filling and normalization processing are divided according to the time sequence to obtain time interval data corresponding to each feature data, where the preset equal time interval may be set to 10 minutes.
Step S25: the sample time interval data is divided into a training set, a validation set and a test set based on a preset proportion.
It should be noted that the preset ratio can be set to 8:1:1, which can be set according to practical situations, and the application is not limited.
Step S26: determining an initial LSTM network model, training the LSTM network model based on a training set, a verification set and a test set until an obtained prediction deviation value is within a preset range, and determining the LSTM network model obtained by current training as a prediction model.
Optionally, based on the above-described pre-construction process of the prediction model, determining an initial LSTM network model in step S26, training the LSTM network model based on the training set, the verification set, and the test set until the obtained prediction deviation value is within a preset range, and determining the currently trained LSTM network model as the prediction model, including the following steps:
step S31: initial network parameters of the initial LSTM network model are configured based on the determined LSTM network model algorithm.
It should be noted that the initial network parameters include parameters for LSTM network model training, such as iteration number, learning rate, and number of times of training samples each time, and the application is not limited thereto.
Step S32: initial network parameters are trained on a training set.
In the process of implementing step S32, the initial network parameters are trained based on the sample data in the training set.
The initial network parameters include, but are not limited to, the number of iterations, learning rate, number of times each training sample, etc.
Step S33: and optimizing the network parameters trained by the training set on the verification set by adopting a k-fold cross verification method to obtain the optimized network parameters, and constructing an optimized LSTM network model based on the optimized network parameters.
In the specific implementation process of step S33, based on the sample data in the validation set, the network parameters trained by the training set are divided into k shares by a k-fold cross validation method. And training an LSTM network model based on the training data in the verification set by using the network parameters trained by 1 part of the training set as verification data and training the LSTM network model by using the other k-1 parts of the training set as training data, obtaining first prediction data by using the verification data to train the LSTM network model for prediction, and repeating the cross verification for k times, wherein k can be set to be 10.
The network parameters trained by each training set need to be verified once, the average value of k times of forecast data is taken, namely the optimized network parameters, so that the generalization error can be reduced, and an optimized LSTM network model is constructed based on the optimized network parameters.
Step S34: and predicting the sample time interval data in the test set in the optimized LSTM network model to obtain the security check prediction time.
In the specific implementation process of step S34, based on the sample data in the test set, the sample time interval data is predicted based on the sample data in the test set in the optimized LSTM network model, so as to obtain the security inspection prediction time.
Step S35: and calculating the difference value between the safety inspection prediction time and the sample safety inspection prediction time to obtain a prediction deviation value.
Step S36: and if the prediction deviation value is within the preset range, determining the currently optimized LSTM network model as a prediction model.
Step S37: and if the prediction deviation value is out of the prediction range, training the optimized LSTM network model on the basis of the training set, the verification set and the test set.
In the embodiment of the invention, the security check time of a newly arrived passenger and the airport historical data in a preset time period are acquired; preprocessing the security check time of the newly arrived passenger and the airport historical data to obtain time interval data; and predicting the security check time in a pre-constructed prediction model based on the time interval data to obtain the security check prediction time at the current moment. It can be seen that in the scheme, the prediction model generated by training based on the LSTM algorithm model and the sample time data can predict the security inspection prediction time at the current moment, so that the prediction of the security inspection time is realized, and a security inspection port can be allocated based on the predicted security inspection prediction time at the current moment, so that the travel satisfaction of passengers is improved, and the labor cost is reduced.
Based on the method for predicting the security check time shown in fig. 1, in the process of performing step S102 to pre-process the security check time of the new passenger and the airport historical data to obtain time interval data, as shown in fig. 2, the method includes the following steps:
step S201: and extracting feature data of different feature types in the security check time of the new passenger and airport historical data based on the feature types.
In step S201, the feature types include a security check status feature, a passenger flow volume feature, and a prediction influence feature.
In the process of implementing step S201 specifically, feature data of different feature types in airport historical data and feature data of security check time of new passengers are extracted from the database based on the security check state feature, the passenger flow volume feature and the prediction influence feature.
It should be noted that the security inspection state features include security inspection time, security inspection monitoring image data and other features that affect the security inspection time; the passenger flow characteristics comprise the characteristics of affecting the number of passengers going out, such as the number of flights in the check-in state, the number of flights in the boarding state, the number of passengers in the check-in state, the number of passengers in the security check state and the like; the predicted influence characteristics comprise whether the system is on weekends, whether the system is on holidays, weather conditions, the number of departure domestic flights in x hours in the future, the number of domestic passenger flows in x hours in the future and the like, and the system can be set according to actual conditions and is not limited in the application.
The check-in state refers to a state in which a check-in is checked in.
It should be noted that the specific implementation process of step S201 is the same as the specific implementation process of step S22, and reference may be made to each other.
Step S202: and carrying out null filling and normalization processing on the characteristic data to obtain the processed characteristic data.
It should be noted that the specific implementation procedure of step S202 is the same as the specific implementation procedure of step S23, and it can be referred to each other.
Step S203: and according to the time sequence, dividing the processed characteristic data based on a preset equal interval to obtain time interval data corresponding to each characteristic data.
In the process of specifically implementing step S203, feature data of different feature types in the historical data in the sampling time period are acquired, feature data of the security check time of the new passenger are extracted, and the processed feature data are divided based on preset equal intervals according to the time sequence to obtain time interval data corresponding to each feature data, for example, the preset equal intervals may be set to 10 minutes.
It should be noted that the sampling time period may be 7 days, which may be set according to practical situations, and the application is not limited thereto.
It should be noted that the specific implementation process of step S203 is the same as the specific implementation process of step S24, and reference may be made to each other.
In the embodiment of the invention, the characteristic data are processed to determine the time interval data corresponding to each characteristic data, so that the time interval data corresponding to each characteristic data can be predicted based on the prediction model, the security check time can be predicted, and a security check port can be arranged based on the predicted security check predicted time at the current moment, thereby improving the travel satisfaction of passengers and reducing the labor cost.
Corresponding to the method for predicting the security check time disclosed in the embodiment of the present invention, the embodiment of the present invention further discloses a schematic structural diagram of a device for predicting the security check time, as shown in fig. 3, where the device for predicting the security check time includes:
an obtaining unit 301, configured to obtain security check time of a new passenger and airport history data in a preset time period.
It should be noted that the airport historical data at least includes security inspection related data, passenger related data and prediction influence data, the prediction influence data refers to related data influencing the prediction result, and the security inspection time includes security inspection waiting time and security inspection clearance time.
And the preprocessing unit 302 is used for preprocessing the security check time of the newly arrived passenger and the airport historical data to obtain time interval data.
The prediction unit 303 is configured to predict the security check time based on the time interval data in a pre-constructed prediction model, so as to obtain the security check prediction time at the current time.
It should be noted that the pre-constructed prediction model is constructed based on the LSTM algorithm model.
It should be noted that, the specific principle and the implementation process of each unit in the apparatus for predicting security inspection time disclosed in the above embodiment of the present invention are the same as the method for predicting security inspection time shown in the above embodiment of the present invention, and reference may be made to corresponding parts in the method for predicting security inspection time disclosed in the above embodiment of the present invention, which are not described herein again.
In the embodiment of the invention, an acquisition unit acquires the security check time of a newly arrived passenger and airport historical data in a preset time period; preprocessing the security check time of the newly arrived passenger and the airport historical data by a preprocessing unit to obtain time interval data; and then, the prediction unit predicts the security check time in a pre-constructed prediction model based on the time interval data to obtain the security check prediction time at the current moment. It can be seen that, in the embodiment of the present invention, the prediction model generated by training based on the LSTM algorithm model and the sample time data can predict the security inspection prediction time at the current time corresponding to the current time interval data, so as to predict the security inspection time, and the security inspection portal can be deployed based on the predicted security inspection prediction time at the current time, so as to improve the traveling satisfaction of the passenger and reduce the labor cost.
Based on the apparatus for predicting the security check time shown in fig. 3, the obtaining unit 301 for obtaining the security check time of the new passenger specifically includes:
a first obtaining module 3011, configured to obtain the current time T0The open number n of the security inspection ports is used for acquiring security inspection monitoring image data and determining the current time T based on the security inspection monitoring image data0The number m of security check queues at the security check port is calculated based on the number n of open security check ports and the number m of security check queues at the current time T0The average number of people in the queue P in the security check area.
A first calculating module 3012, configured to calculate an average transaction time T according to the average number of people in queue P and the average security inspection time Tave_dealCalculating the security check time t of the newly arrived passenger0The security inspection time of the newly arrived passenger
It should be noted that the average handling time T of the security inspectionave_dealThe passenger security check passing time is divided by the number of the security check clearance persons,waiting time for new arriving passenger queue, PTave_dealFor the total time of security check of P passengers outside the security check port,
for the current time T0The remaining security check transaction time of the passenger who entered the security check operating area through ticket checking.
In the embodiment of the invention, the current security inspection opening number and the current security inspection queue number are determined, so that the current new security inspection time of passengers is determined, the current time interval data is convenient to determine, the security inspection prediction time of the current time corresponding to the current time interval data is predicted according to the prediction model, the security inspection time is predicted, the security inspection openings can be arranged based on the predicted security inspection prediction time of the current time, the travel satisfaction of the passengers is improved, and the labor cost is reduced.
Based on the device for predicting the security check time shown in fig. 3, referring to fig. 4 in conjunction with fig. 3, the preprocessing unit 302 includes:
a first extracting module 3021, configured to extract feature data of different feature types in the security inspection time of the new passenger and the airport historical data based on the feature types.
It should be noted that the feature types include a security check status feature, a passenger flow volume feature, and a prediction influence feature.
The first processing module 3022 is configured to perform null filling and normalization processing on the feature data to obtain processed feature data.
The first dividing module 3033 is configured to divide the processed feature data at preset equal intervals according to the time sequence to obtain time interval data corresponding to each feature data.
In the embodiment of the invention, the characteristic data are processed to determine the time interval data corresponding to each characteristic data, so that the time interval data corresponding to each characteristic data can be predicted based on the prediction model, the security check time can be predicted, and a security check port can be arranged based on the predicted security check predicted time at the current moment, thereby improving the travel satisfaction of passengers and reducing the labor cost.
Based on the device for predicting the security inspection time shown in fig. 3, with reference to fig. 3 and fig. 5, a pre-construction unit 304 may be further provided, where the construction unit 304 includes:
and the second acquisition module is used for acquiring sample data, wherein the sample data comprises airport historical data in a sampling time period and the security check time of a newly arrived passenger.
And the second extraction module is used for extracting sample characteristic data of different characteristic types in the sample data based on the characteristic types, wherein the characteristic types comprise security check state characteristics, passenger flow volume characteristics and prediction influence characteristics.
And the second processing module is used for carrying out null filling and normalization processing on the sample characteristic data to obtain the processed sample characteristic data.
And the second division module is used for dividing the processed sample characteristic data based on preset equal intervals according to the time sequence to obtain sample time interval data corresponding to each characteristic data, and dividing the sample time interval data into a training set, a verification set and a test set based on a preset proportion.
And the training module is used for determining an initial LSTM network model, training the LSTM network model based on the training set, the verification set and the test set until the obtained prediction deviation value is within a preset range, and determining the LSTM network model obtained by current training as a prediction model.
Based on the device for predicting the security check time shown in fig. 5, the training module includes:
and the configuration submodule is used for configuring initial network parameters of the initial LSTM network model based on the determined LSTM network model algorithm.
A training sub-module for training the initial network parameters on the training set.
And the optimization module is used for optimizing the network parameters trained by the training set on the verification set by adopting a k-fold cross verification method to obtain the optimized network parameters, and constructing an optimized LSTM network model based on the optimized network parameters.
And the prediction module is used for predicting the sample time interval data in the test set in the optimized LSTM network model to obtain the security check prediction time.
And the second calculation module is used for calculating a difference value between the safety inspection prediction time and the sample safety inspection prediction time to obtain a prediction deviation value, determining the currently optimized LSTM network model as the prediction model if the prediction deviation value is within a preset range, and continuing training the optimized LSTM network model based on the training set, the verification set and the test set if the prediction deviation value is outside the prediction range.
In the embodiment of the invention, the sample time interval data is determined based on the airport historical data and the security check time of the newly arrived passenger, the prediction of the security check time is realized through the prediction model generated based on the LSTM algorithm model and the sample time data training, and the security check port can be allocated based on the predicted security check prediction time at the current moment, so that the travel satisfaction of the passenger is improved and the labor cost is reduced.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. 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 invention. Thus, the present invention 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.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (10)
1. A method for predicting security inspection time is characterized in that,
acquiring security check time of a newly arrived passenger and airport historical data in a preset time period, wherein the airport historical data at least comprise security check related data, passenger related data and predicted influence data, the predicted influence data refer to related data influencing a prediction result, and the security check time comprises security check waiting time and security check clearance time;
preprocessing the security check time of the newly arrived passenger and the airport historical data to obtain time interval data;
and predicting the security check time in a pre-constructed prediction model based on the time interval data to obtain the security check prediction time at the current moment, wherein the pre-constructed prediction model is constructed based on an LSTM algorithm model.
2. The method of claim 1, wherein the process of obtaining the new passenger's security check time comprises:
obtaining the current time T0The number n of the opened security inspection ports;
obtaining security check monitoring image data, and determining current time T based on the security check monitoring image data0The number of people in a security queue at a security inspection port is m;
calculating the current time T based on the open number n of the security inspection openings and the number m of the security inspection queue people0The average queue number P in the security check area;
according to the average number of people in the queue P and the average handling time T of the security inspectionave_dealCalculating the security check time t of the newly arrived passenger0The security inspection time of the newly arrived passengerWherein, the average handling time T of the security inspectionave_dealThe passenger security check passing time is divided by the number of the security check clearance persons,
waiting time for new arriving passenger queue, PTave_dealFor the total time of security check of P passengers outside the security check port,
for the current time T0The remaining security check transaction time of the passenger who entered the security check operating area through ticket checking.
3. The method of claim 1, wherein preprocessing the incoming passenger's security check time and the airport history data to obtain time interval data comprises:
extracting feature data of different feature types in the security check time of the new arriving passenger and the airport historical data based on the feature types, wherein the feature types comprise security check state features, passenger flow volume features and prediction influence features;
carrying out null filling and normalization processing on the characteristic data to obtain processed characteristic data;
and dividing the processed characteristic data based on preset equal intervals according to the time sequence to obtain time interval data corresponding to each characteristic data.
4. The method of claim 1, wherein the pre-constructing a predictive model comprises:
acquiring sample data, wherein the sample data comprises airport historical data in a sampling time period and security check time of a newly arrived passenger;
extracting sample feature data of different feature types in the sample data based on the feature types, wherein the feature types comprise security inspection state features, passenger flow volume features and prediction influence features;
carrying out null filling and normalization processing on the sample characteristic data to obtain processed sample characteristic data;
dividing the processed sample characteristic data based on preset equal intervals according to a time sequence to obtain sample time interval data corresponding to each characteristic data;
dividing the sample time interval data into a training set, a verification set and a test set based on a preset proportion;
and determining an initial LSTM network model, training the LSTM network model based on the training set, the verification set and the test set until the obtained prediction deviation value is within a preset range, and determining the LSTM network model obtained by current training as a prediction model.
5. The method of claim 4, wherein the determining an initial LSTM network model and training the LSTM network model based on the training set, the validation set and the test set until the obtained prediction deviation value is within a preset range, and the determining a currently trained LSTM network model as a prediction model comprises:
configuring initial network parameters of an initial LSTM network model based on the determined LSTM network model algorithm;
training the initial network parameters on the training set;
optimizing the network parameters trained by the training set on the verification set by adopting a k-fold cross verification method to obtain optimized network parameters, and constructing an optimized LSTM network model based on the optimized network parameters;
predicting the sample time interval data in the test set in the optimized LSTM network model to obtain security check prediction time;
calculating a difference value between the safety inspection prediction time and the sample safety inspection prediction time to obtain a prediction deviation value;
if the prediction deviation value is within the preset range, determining the currently optimized LSTM network model as a prediction model;
and if the prediction deviation value is out of the prediction range, training the optimized LSTM network model on the basis of the training set, the verification set and the test set.
6. An apparatus for predicting a security inspection time, comprising:
the system comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring the security check time of a new passenger and airport historical data in a preset time period, the airport historical data at least comprises security check related data, passenger related data and prediction influence data, the prediction influence data refers to related data influencing a prediction result, and the security check time comprises security check waiting time and security check clearance time;
the preprocessing unit is used for preprocessing the security check time of the newly arrived passenger and the airport historical data to obtain time interval data;
and the prediction unit is used for predicting the security check time based on the time interval data in a pre-constructed prediction model to obtain the security check prediction time of the current moment, and the pre-constructed prediction model is constructed based on an LSTM algorithm model.
7. The apparatus according to claim 6, wherein the obtaining unit for obtaining the security check time of the new passenger specifically comprises:
a first obtaining module for obtaining the current time T0The open number n of the security inspection ports is used for acquiring security inspection monitoring image data, and the current time T is determined based on the security inspection monitoring image data0The number m of security check queues at the security check port is calculated, and the current time T is calculated based on the security check port opening data n and the number m of security check queues0The average queue number P in the security check area;
a first calculation module for calculating the average queue number P and the average handling time T of the security inspectionave_dealCalculating the security check time t of the newly arrived passenger0The security inspection time of the newly arrived passenger
Wherein, the average handling time T of the security inspectionave_dealThe passenger security check passing time is divided by the number of the security check clearance persons,
waiting time for new arriving passenger queue, PTave_dealFor the total time of security check of P passengers outside the security check port,
for the current time T0The remaining security check transaction time of the passenger who entered the security check operating area through ticket checking.
8. The apparatus of claim 6, wherein the pre-processing unit comprises:
the first extraction module is used for extracting the new passenger security check time and the feature data of different feature types in the airport historical data based on the feature types, wherein the feature types comprise security check state features, passenger flow volume features and prediction influence features;
the first processing module is used for carrying out null filling and normalization processing on the characteristic data to obtain processed characteristic data;
and the first dividing module is used for dividing the processed characteristic data based on preset equal intervals according to the time sequence to obtain time interval data corresponding to each characteristic data.
9. The apparatus of claim 6, further comprising: a pre-construction unit;
the pre-construction unit comprises:
the second acquisition module is used for acquiring sample data, wherein the sample data comprises airport historical data in a sampling time period and the security check time of a newly arrived passenger;
the second extraction module is used for extracting sample characteristic data of different characteristic types in the sample data based on the characteristic types, wherein the characteristic types comprise security check state characteristics, passenger flow characteristics and prediction influence characteristics;
the second processing module is used for carrying out null filling and normalization processing on the sample characteristic data to obtain processed sample characteristic data;
the second dividing module is used for dividing the processed sample characteristic data based on preset equal intervals according to a time sequence to obtain sample time interval data corresponding to each characteristic data, and dividing the sample time interval data into a training set, a verification set and a test set based on a preset proportion;
and the training module is used for determining an initial LSTM network model, training the LSTM network model based on the training set, the verification set and the test set until the obtained prediction deviation value is within a preset range, and determining the LSTM network model obtained by current training as a prediction model.
10. The apparatus of claim 9, wherein the training module comprises:
the configuration submodule is used for configuring initial network parameters of the initial LSTM network model based on the determined LSTM network model algorithm;
a training sub-module for training the initial network parameters on the training set;
the optimization module is used for optimizing the network parameters trained by the training set on the verification set by adopting a k-fold cross verification method to obtain optimized network parameters, and constructing an optimized LSTM network model based on the optimized network parameters;
the prediction module is used for predicting the sample time interval data in the test set in the optimized LSTM network model to obtain the security check prediction time;
and the second calculation module is used for calculating a difference value between the safety inspection prediction time and the sample safety inspection prediction time to obtain a prediction deviation value, determining the currently optimized LSTM network model as the prediction model if the prediction deviation value is within a preset range, and continuing training the optimized LSTM network model based on the training set, the verification set and the test set if the prediction deviation value is outside the prediction range.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911070494.XA CN110837928A (en) | 2019-11-05 | 2019-11-05 | Method and device for predicting security check time |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911070494.XA CN110837928A (en) | 2019-11-05 | 2019-11-05 | Method and device for predicting security check time |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110837928A true CN110837928A (en) | 2020-02-25 |
Family
ID=69576113
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911070494.XA Pending CN110837928A (en) | 2019-11-05 | 2019-11-05 | Method and device for predicting security check time |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110837928A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112329974A (en) * | 2020-09-03 | 2021-02-05 | 中国人民公安大学 | LSTM-RNN-based civil aviation security event behavior subject identification and prediction method and system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106096767A (en) * | 2016-06-07 | 2016-11-09 | 中国科学院自动化研究所 | A kind of link travel time prediction method based on LSTM |
| CN106971545A (en) * | 2017-05-16 | 2017-07-21 | 青岛大学 | A kind of bus arrival time Forecasting Methodology |
| CN107704971A (en) * | 2017-10-27 | 2018-02-16 | 中航信移动科技有限公司 | A kind of data processing method and device of real-time estimate airport security number |
| CN108769924A (en) * | 2018-04-28 | 2018-11-06 | 哈尔滨工业大学 | A kind of scenic spot tourist chain type trip service system and method |
| CN109376913A (en) * | 2018-09-30 | 2019-02-22 | 北京市天元网络技术股份有限公司 | The prediction technique and device of precipitation |
-
2019
- 2019-11-05 CN CN201911070494.XA patent/CN110837928A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106096767A (en) * | 2016-06-07 | 2016-11-09 | 中国科学院自动化研究所 | A kind of link travel time prediction method based on LSTM |
| CN106971545A (en) * | 2017-05-16 | 2017-07-21 | 青岛大学 | A kind of bus arrival time Forecasting Methodology |
| CN107704971A (en) * | 2017-10-27 | 2018-02-16 | 中航信移动科技有限公司 | A kind of data processing method and device of real-time estimate airport security number |
| CN108769924A (en) * | 2018-04-28 | 2018-11-06 | 哈尔滨工业大学 | A kind of scenic spot tourist chain type trip service system and method |
| CN109376913A (en) * | 2018-09-30 | 2019-02-22 | 北京市天元网络技术股份有限公司 | The prediction technique and device of precipitation |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112329974A (en) * | 2020-09-03 | 2021-02-05 | 中国人民公安大学 | LSTM-RNN-based civil aviation security event behavior subject identification and prediction method and system |
| CN112329974B (en) * | 2020-09-03 | 2024-02-27 | 中国人民公安大学 | LSTM-RNN-based civil aviation security event behavior subject identification and prediction method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Toqué et al. | Forecasting dynamic public transport origin-destination matrices with long-short term memory recurrent neural networks | |
| CN107086935B (en) | People flow distribution prediction method based on WIFI AP | |
| McLay et al. | Risk-based policies for airport security checkpoint screening | |
| CN111709566A (en) | Bank branch business prediction and scheduling method | |
| CN106022929A (en) | Collision accident loss estimating method and system based on expert system | |
| CN108647743B (en) | Driver safety portrait system | |
| CN111985646B (en) | Service processing method and device | |
| CN104156594B (en) | Dynamic flight station-crossing time estimation method based on Bayes network | |
| CN110992072A (en) | Abnormal order prediction method and system | |
| Choi et al. | Artificial neural network models for airport capacity prediction | |
| CN111210094A (en) | Airport taxi automatic scheduling method and device based on real-time passenger flow prediction | |
| CN110991999A (en) | Method and device for improving law enforcement amount cutting efficiency, computer equipment and storage medium | |
| CN112508305A (en) | Public place entrance pedestrian flow prediction method based on LSTM | |
| CN111192090A (en) | Seat allocation method and device for flight, storage medium and electronic equipment | |
| CN110458325A (en) | A kind of traffic zone passenger flow forecasting and device in short-term | |
| CN110009224A (en) | Suspect's violation probability prediction technique, device, computer equipment and storage medium | |
| CN110837928A (en) | Method and device for predicting security check time | |
| CN115578815A (en) | Access control management method, authentication server, access control system and readable storage medium | |
| CN115359659A (en) | Lane opening and closing configuration method and system | |
| CN110852792A (en) | Big data analysis-based airline value evaluation method and related products | |
| Monmousseau et al. | Predicting passenger flow at Charles de Gaulle airport security checkpoints | |
| CN111080672B (en) | Safety early warning method and device, computing equipment and storage medium | |
| CN114239325B (en) | Airport check-in consignment counter configuration planning method, device, equipment and storage medium | |
| CN111832929B (en) | Dynamic scheduling method and system for airport check-in machine | |
| CN112738066B (en) | Business hall business intelligent distribution system |
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 |