CN114912854B - Subway train operation adjusting method and device, electronic equipment and storage medium - Google Patents
Subway train operation adjusting method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN114912854B CN114912854B CN202210839166.7A CN202210839166A CN114912854B CN 114912854 B CN114912854 B CN 114912854B CN 202210839166 A CN202210839166 A CN 202210839166A CN 114912854 B CN114912854 B CN 114912854B
- Authority
- CN
- China
- Prior art keywords
- passenger flow
- information
- target
- time period
- historical
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000013528 artificial neural network Methods 0.000 claims abstract description 54
- 230000008859 change Effects 0.000 claims abstract description 52
- 230000004044 response Effects 0.000 claims abstract description 34
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 14
- 238000003064 k means clustering Methods 0.000 claims abstract description 12
- 238000012549 training Methods 0.000 claims description 67
- 238000004590 computer program Methods 0.000 claims description 15
- 230000000694 effects Effects 0.000 claims description 15
- 230000006870 function Effects 0.000 claims description 11
- 238000007781 pre-processing Methods 0.000 claims description 11
- 238000010276 construction Methods 0.000 claims description 8
- 238000007689 inspection Methods 0.000 claims description 6
- 238000012360 testing method Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000002146 bilateral effect Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L27/00—Central railway traffic control systems; Trackside control; Communication systems specially adapted therefor
- B61L27/10—Operations, e.g. scheduling or time tables
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06314—Calendaring for a resource
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Evolutionary Biology (AREA)
- General Business, Economics & Management (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Quality & Reliability (AREA)
- General Health & Medical Sciences (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Mechanical Engineering (AREA)
- Primary Health Care (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Train Traffic Observation, Control, And Security (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a subway train operation adjusting method, a device, electronic equipment and a storage medium, and relates to the technical field of rail transit, wherein the method comprises the following steps: determining passenger flow related data of the target site in the target time period according to the passenger flow information of the target site in the adjacent time of the target time period, the historical contemporaneous passenger flow information and the social environment influence information of the target site in the target time period; inputting the passenger flow related data of the target station in the target time period into a trained back propagation neural network, and outputting the predicted passenger flow information of the target station in the target time period; and classifying the predicted passenger flow information and the social environment influence information based on a passenger flow change response case library and a K-means clustering algorithm to obtain a train operation adjusting scheme of the target station in the target time period.
Description
Technical Field
The invention relates to the technical field of rail transit, in particular to a subway train operation adjusting method and device, electronic equipment and a storage medium.
Background
In recent years, with the great advance of the construction of transportation infrastructure, the construction of urban rail transit enters a rapid development stage, and as an important component of an urban public transport system, the subway becomes one of the preferred transportation modes for urban residents to go out by virtue of the advantages of large transportation quantity, high speed and high efficiency. However, with the large-scale subway network construction, the increase of subway passenger capacity and the influence of various emergencies, the phenomenon of short-time passenger flow mutation becomes a key problem to be solved urgently by the subway operation department, and the core of the problem lies in that the staff cannot accurately sense the passenger flow change and respond in time.
Therefore, how to better sense the change of passenger flow and adjust the operation of the subway train becomes an urgent problem to be solved in the industry.
Disclosure of Invention
The invention provides a subway train operation adjusting method, a subway train operation adjusting device, electronic equipment and a storage medium, which are used for solving the defect that the subway train operation adjustment is difficult to effectively sense passenger flow change in the prior art.
The invention provides a subway train operation adjusting method, which comprises the following steps:
determining passenger flow related data of a target site in a target time period according to passenger flow information of the target site in adjacent time of the target time period, historical contemporaneous passenger flow information and social environment influence information of the target site in the target time period, wherein the social environment influence information comprises: holiday information, large-scale event information, weather information, and emergency information;
inputting the passenger flow related data of the target station in the target time period into a trained back propagation neural network, and outputting the predicted passenger flow information of the target station in the target time period;
classifying the predicted passenger flow information and the social environment influence information based on a passenger flow change response case base and a K-means clustering algorithm to obtain a train operation adjustment scheme of a target station in a target time period, wherein each passenger flow change response case of the target station in the passenger flow change response case base comprises historical social environment influence information, historical passenger flow data and a historical train operation adjustment scheme.
According to the subway train operation adjusting method provided by the invention, before inputting the passenger flow related data of the target time period into the trained back propagation neural network, the method further comprises the following steps:
constructing an initial passenger flow related data sample of the target station, wherein the initial passenger flow related data sample comprises: historical early and late peak-average peak-low peak division data, historical holiday information, historical large-scale activity information, historical weather information and historical emergency data;
and carrying out data preprocessing on the initial passenger flow related data sample to obtain a passenger flow related data sample.
According to the subway train operation adjusting method provided by the invention, after the passenger flow related data sample is obtained, the method further comprises the following steps:
obtaining passenger flow data labels corresponding to the passenger flow related data samples;
and taking the combination of each passenger flow related data sample and the passenger flow data label as a training sample to obtain a plurality of training samples, and training a preset neural network by using the plurality of training samples.
According to the subway train operation adjusting method provided by the invention, the training of the preset neural network by utilizing the plurality of training samples comprises the following steps:
for any training sample, inputting the training sample into the preset neural network, and outputting predicted passenger flow data corresponding to the training sample;
calculating a loss value according to the predicted passenger flow data corresponding to the training sample and the passenger flow data label in the training sample by using a preset loss function;
and if the loss value is smaller than a preset threshold value, finishing training of the preset neural network to obtain a trained back propagation neural network.
According to the subway train operation adjusting method provided by the invention, after the predicted passenger flow information of the target station in the target time period is output, the method further comprises the following steps:
constructing a passenger flow information time sequence of an adjacent time period with the time step of 15min and the sample size of 10 based on the predicted passenger flow information;
analyzing the passenger flow information sequence based on a Mankendel inspection method to obtain passenger flow change trend information of the target site in a target time period;
and generating train operation adjustment prompt information based on the passenger flow change trend information.
The invention also provides a subway train operation adjusting device, which comprises:
the determining module is used for determining passenger flow related data of the target site in the target time period according to passenger flow information of the target site in the adjacent time of the target time period, historical contemporaneous passenger flow information and social environment influence information of the target site in the target time period, wherein the social environment influence information comprises: at least one of holiday information, large event information, weather information, and emergency information;
the output module is used for inputting the passenger flow related data of the target station in the target time period into the trained back propagation neural network and outputting the predicted passenger flow information of the target station in the target time period;
and the adjusting module is used for classifying the predicted passenger flow information and the social environment influence information based on a passenger flow change response case base and a K-means clustering algorithm to obtain a train operation adjusting scheme of the target station in a target time period, wherein each passenger flow change response case of the target station in the passenger flow change response case base comprises historical social environment influence information, historical passenger flow data and a historical train operation adjusting scheme.
According to the subway train operation adjusting device provided by the invention, the device further comprises:
a construction module, configured to construct an initial passenger flow related data sample of the target site, where the initial passenger flow related data sample includes: historical early and late peak-average peak-low peak division data, historical holiday information, historical large-scale activity information, historical weather information and historical emergency data;
and the preprocessing module is used for preprocessing the data of the initial passenger flow related data sample to obtain a passenger flow related data sample.
According to the subway train operation adjusting device provided by the invention, the device further comprises:
the acquisition module is used for acquiring the passenger flow data label corresponding to each passenger flow related data sample;
and the training module is used for taking the combination of each passenger flow related data sample and the passenger flow data label as a training sample, obtaining a plurality of training samples, and training a preset neural network by using the plurality of training samples.
The invention also provides an electronic device, which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein when the processor executes the program, the subway train running adjusting method is realized according to any one of the methods.
The present invention also provides a non-transitory computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a subway train operation adjusting method as any one of the above.
The invention also provides a computer program product, which comprises a computer program, wherein the computer program is used for realizing the subway train operation adjusting method when being executed by a processor.
According to the subway train operation adjusting method, the device, the electronic equipment and the storage medium, passenger flow related data of a target station in a target time period, which are constructed by fully considering influence factors such as morning and evening peaks, holidays, large activities, severe weather, emergencies and the like, the forecast passenger flow information of the target time period is determined through a trained back propagation neural network, the perception and the forecast of passenger flow change can be effectively realized, and a train operation adjusting scheme of the target station in the target time period is determined by further combining a K mean value clustering algorithm according to the forecast passenger flow information.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a subway train operation adjusting method provided in an embodiment of the present application;
FIG. 2 is a schematic diagram of a back propagation neural network according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of a subway train operation adjusting device provided in the embodiment of the present application;
fig. 4 is a schematic structural diagram of an electronic device provided in the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. 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.
Fig. 1 is a subway train operation adjusting method provided in an embodiment of the present application, including:
specifically, in the embodiment of the present application, because the passenger flow volume difference of each subway station is large, the subway train operation adjustment analysis needs to be performed according to the specific situation of each target station, so the target station described in the embodiment of the present application may specifically refer to a subway station that needs to perform subway operation adjustment.
The target time described in the embodiment of the present application may be a certain time period that has not occurred in the future, that is, the target time may specifically be a target time that is desired to be predicted.
The adjacent time passenger flow information described in the embodiment of the present application may specifically refer to passenger flow information in a time period adjacent to the target time period, and specifically may be passenger flow information in a time period that is earlier than the target time period and adjacent to the target, for example, the target time period is a time period of 11-00: and (5) passenger flow information in the time period of 00-11.
In some embodiments, since the target time period is a future time period, the adjacent time passenger flow information may refer to the passenger flow information of the current time period.
The historical contemporaneous passenger flow information described in the embodiment of the present application may specifically be the passenger flow information in the historical data, which is also in the target time period, for example, if the target time period is a time period of 11-00.
The social environment influence information described in the embodiment of the present application may specifically refer to factors that may influence the change of subway passenger flow, and specifically may include foreseeable morning and evening peaks, holidays, large events, and the like, and also include unforeseeable severe weather, emergency events, and the like; correspondingly, the social environment influence information in the present application may include holiday information, large event information, weather information, and emergency information.
The passenger flow related data described in the embodiment of the application refers to a data set consisting of passenger flow information at adjacent time, historical contemporaneous passenger flow information and social environment influence information in a target time period.
In the embodiment of the application, the passenger flow can be more accurately predicted by considering various data factors.
specifically, the trained back propagation neural network described in the embodiment of the present application is obtained by training based on a passenger flow related data sample carrying a passenger flow data tag, where the passenger flow data tag marks an actual number of passengers in the passenger flow corresponding to the passenger flow related data sample, and the passenger flow related data sample includes a destination site, historical early and late peak-off-peak division data, historical holiday information, historical large-scale activity information, historical weather information, and historical emergency data.
The trained back propagation neural network in the embodiment of the application can output the predicted passenger flow information of the target time period after the passenger flow related data of the target time period is input.
In the embodiment of the application, the predicted passenger flow information of the target station in the target time period can be effectively predicted through the trained back propagation neural network, and then the train operation adjustment scheme is further determined according to the predicted passenger flow information.
And step 130, classifying the predicted passenger flow information and the social environment influence information based on a passenger flow change response case base and a K-means clustering algorithm to obtain a train operation adjustment scheme of the target station in a target time period, wherein each passenger flow change response case of the target station in the passenger flow change response case base comprises historical social environment influence information, historical passenger flow data and a historical train operation adjustment scheme.
The case base for passenger flow change response described in the embodiment of the present application may be a case base established according to historical data, the case base includes a plurality of passenger flow change response cases, each passenger flow change response case corresponds to a historical event, and the case base includes historical social environment influence information, historical passenger flow data and a historical train operation adjustment scheme, which may specifically cover: historical passenger flow information, historical morning and evening peak-average peak-low peak information, historical holiday information, historical large-scale activity information, historical weather information, historical emergency information, historical dynamic management and control measures, historical station information and historical line information.
The expression form of the passenger flow change response case described in the embodiment of the present application can be shown in table 1 below:
TABLE 1
In the embodiment of the application, after obtaining the predicted passenger flow information and the social environment influence information corresponding to the predicted passenger flow information, the predicted passenger flow information and the social environment influence information can be used as a group of data to be classified, and clustering operation is performed according to the data to be classified and each passenger flow change response case in the passenger flow change response case library, wherein the clustering operation process is as follows:
step 1: initialization
A cluster center;
step 2: calculating the distance between each data and each clustering center, and distributing the distance to the clustering center with the closest distance;
step 3: after the clustering division is finished, the clustering center is recalculated, the Step returns to Step 2, the steps are continuously repeated until an iteration termination condition is reached, the iteration termination condition is that a specified error is reached or the iteration reaches the maximum iteration times, and for the sample
The objective function is as follows, wherein,
is as followskA cluster center;mrepresents a cluster number;
to represent
And
the Euclidean distance is adopted here;
in this application embodiment, through clustering operation of the K-means clustering algorithm, a train operation adjustment scheme of a target station in a target time period can be effectively matched, and the train operation adjustment scheme in this application embodiment may include: train marshalling scheme adjustment, train running density adjustment, train road crossing adjustment and stop scheme adjustment.
In the embodiment of the application, passenger flow related data of a target station in a target time period, which is constructed by fully considering influence factors such as morning and evening peaks, holidays, large-scale activities, severe weather and emergencies, is determined by a trained back propagation neural network, passenger flow change sensing and prediction can be effectively realized, and a train operation adjustment scheme of the target station in the target time period is determined by further combining a K-means clustering algorithm according to the predicted passenger flow information.
Optionally, before the inputting the passenger flow related data of the target time period into the trained back propagation neural network, the method further includes:
constructing an initial passenger flow related data sample of the target site, wherein the initial passenger flow related data sample comprises: historical early and late peak-average peak-low peak division data, historical holiday information, historical large-scale activity information, historical weather information and historical emergency data;
and carrying out data preprocessing on the initial passenger flow related data sample to obtain a passenger flow related data sample.
Specifically, in the embodiment of the application, each initial passenger flow related data sample for constructing the target site is constructed according to the target site corresponding to each time period in the historical data, historical early and late peak-average peak-low peak partition data, historical holiday information, historical large-scale activity information, historical weather information and historical emergency event data.
In the embodiment of the application, after the initial passenger flow related data sample is completed, data preprocessing can be further performed on the initial passenger flow related data sample, a 3 sigma criterion or a single variable boxplot can be used for performing bad value detection to identify outliers, so as to prompt an analyst to correct abnormal values and missing values, or automatically perform mean value correction on abnormal data, so that the passenger flow related data sample after data preprocessing is obtained.
In the embodiment of the application, after the passenger flow related data sample is obtained, a passenger flow data tag is also obtained, wherein the passenger flow data tag refers to actual passenger flow data of a time period corresponding to the passenger flow related data sample.
After the passenger flow related data samples are obtained, the influence weight of each influence factor is set, for example, the weight of the workday peak-to-peak is set to be 0; the weight of the morning and evening peak is 1; the weight of weekends is 0.5, and the weight of non-holidays is 0; the weights of the national day section and the labor section are 1; the weight of other holidays is 0.5; setting the weight of the large campaign to 1; setting the weight of medium/heavy rain and medium/heavy snow to be 1, setting the weight of sunny, cloudy and cloudy to be 0, and setting the weight of other weather to be 0.5; and setting the weight of the emergency event as 1, and finally obtaining a passenger flow related data sample after setting each weight.
In the embodiment of the application, the construction of the initial passenger flow related data sample with multiple influence factors such as historical morning and evening peak-average peak-low peak dividing data, historical holiday information, historical large-scale activity information, historical weather information and historical emergency data can be effectively assisted to the construction of the subsequent back propagation neural network.
Optionally, after obtaining the passenger flow related data sample, the method further includes:
obtaining passenger flow data labels corresponding to the passenger flow related data samples;
and taking the combination of each passenger flow related data sample and the passenger flow data label as a training sample to obtain a plurality of training samples, and training a preset neural network by using the plurality of training samples.
In the embodiment of the application, after the passenger flow related data sample is determined, the actual passenger flow data corresponding to the passenger flow related data sample is also needed, and the actual passenger flow data is used as the passenger flow data label.
And taking the combination of each passenger flow related data sample and the passenger flow data label as a training sample.
In some embodiments, the training sample may be an input feature matrix as shown in table 2 below:
TABLE 2
Fig. 2 is a schematic structural diagram of a back propagation neural network provided in the embodiment of the present application, and as shown in fig. 2, the back propagation neural network includes an input layer, a hidden layer, and an output layer, and in the embodiment of the present application, the back propagation neural network may be designed in advance, and specifically, the back propagation neural network may be designed as follows: number of hidden layers, number of neurons, step length, transfer function, learning function, training function, performance function, and the like.
In this embodiment of the present application, the preset neural network may be a back propagation neural network, and after the back propagation neural network is constructed, a plurality of training samples may be obtained, and the preset neural network is trained through the plurality of training samples.
In the embodiment of the application, the passenger flow data labels corresponding to the passenger flow related data samples are obtained, so that the whole passenger flow related data samples are taken as a training sample, and the passenger flow prediction back propagation neural network can be effectively trained.
Optionally, training a preset neural network by using the plurality of training samples includes:
for any training sample, inputting the training sample into the preset neural network, and outputting predicted passenger flow data corresponding to the training sample;
calculating a loss value according to the predicted passenger flow data corresponding to the training sample and the passenger flow data label in the training sample by using a preset loss function;
and if the loss value is smaller than a preset threshold value, finishing the training of the preset neural network to obtain the trained back propagation neural network.
Specifically, the loss function described in the embodiment of the present application may be Mean Absolute Error (MAE) or Root Mean Square Error (RMSE), and the model structure is continuously adjusted based on the training sample to find the optimal parameters to obtain a satisfactory Error effect, and the final network structure and the selection parameters are determined, thereby completing the model training.
In the embodiment of the application, a training sample is input into the preset neural network, the predicted passenger flow data corresponding to the training sample is output, and then a loss value is calculated according to the predicted passenger flow data corresponding to the training sample and the passenger flow data label in the training sample by using a preset loss function.
In the embodiment of the present application, when the loss value is smaller than the preset threshold, it indicates that the preset neural network has obtained a better training effect, and at this time, the training of the preset neural network is completed, so that the trained back propagation neural network can be obtained, where the preset threshold may be preset.
In the embodiment of the application, the preset neural network is trained according to the training samples, so that the trained back propagation neural network which effectively synthesizes various factors to predict passenger flow can be obtained.
Optionally, after the outputting the predicted passenger flow information of the target station in the target time period, the method further includes:
constructing a passenger flow information time sequence of an adjacent time period with the time step of 15min and the sample size of 10 based on the predicted passenger flow information;
analyzing the passenger flow information sequence based on a Mankendel inspection method to obtain passenger flow change trend information of the target site in a target time period;
and generating train operation adjustment prompt information based on the passenger flow change trend information.
Specifically, in the embodiment of the present application, after obtaining the predicted passenger flow information, a real-time passenger flow information sequence is constructed according to the predicted passenger flow information, and the real-time passenger flow change is determined by using a Mann-Kendall check sequence trend, where the calculation process is as follows:
the original hypothesis defining the M-K test is
：
Are independently and identically distributed
Is optionally assumed to be
：
And
the distribution of (a) is not the same,
alternative hypothesis
Is a bilateral test.
Defining test statisticsSWhen is coming into contact with
When the number of samples in (1) is more than 8, the test statisticSObey normal distribution
In the formula (I), wherein,
a function of the sign is represented by,Sthe representation of the test statistic is shown,
based on test statisticsSCalculating the standard normal statistic of the M-K testZM-K test is bilateral test, at significant level
Then, if
If so, the original hypothesis is rejected
I.e. the real-time passenger flow information sequence develops according to a certain trend, wherein,
which indicates a tendency of rising to the sun,
indicating a downward trend.
By combining with the predicted passenger flow data, the passenger flow increase early warning can be carried out by setting a trend inspection threshold value and a passenger flow prediction threshold value, the passenger flow change is comprehensively analyzed in multiple directions, and the train operation adjustment prompt information is generated.
Wherein,
wherein,
in order to be a function of the sign,
in order to test the statistics of the test,
is the size of the sample to be tested,
is a standard normal statistic.
In the embodiment of the application, the passenger flow information sequence is analyzed by a man-kender inspection method, the change trend of the passenger flow can be effectively further judged, and then train operation adjustment prompt information is effectively generated according to the change trend, so that operators are helped to better perform train operation adjustment.
The following describes the subway train operation adjusting device provided by the present invention, and the subway train operation adjusting device described below and the subway train operation adjusting method described above can be referred to correspondingly.
Fig. 3 is a schematic structural diagram of a subway train operation adjusting device provided in an embodiment of the present application, as shown in fig. 3, including: a determination module 310, an output module 320, and an adjustment module 330;
the determining module 310 is configured to determine passenger flow related data of the target site in the target time period according to passenger flow information of the target site in adjacent time of the target time period, historical contemporaneous passenger flow information, and social environment influence information of the target site in the target time period, where the social environment influence information includes: holiday information, large-scale event information, weather information, and emergency information;
the output module 320 is configured to input the passenger flow related data of the target station in the target time period into the trained back propagation neural network, and output the predicted passenger flow information of the target station in the target time period;
the adjusting module 330 is configured to classify the predicted passenger flow information and the social environment influence information based on a passenger flow change response case library and a K-means clustering algorithm to obtain a train operation adjusting scheme of a target station at a target time interval, where each passenger flow change response case of the target station in the passenger flow change response case library includes historical social environment influence information, historical passenger flow data, and a historical train operation adjusting scheme.
Optionally, the apparatus further comprises:
a construction module, configured to construct an initial passenger flow related data sample of the destination site, where the initial passenger flow related data sample includes: historical early and late peak-average peak-low peak division data, historical holiday information, historical large-scale activity information, historical weather information and historical emergency data;
and the preprocessing module is used for carrying out data preprocessing on the initial passenger flow related data sample to obtain the passenger flow related data sample.
Optionally, the apparatus further comprises:
the acquisition module is used for acquiring a passenger flow data label corresponding to each passenger flow related data sample;
and the training module is used for taking the combination of each passenger flow related data sample and the passenger flow data label as a training sample, obtaining a plurality of training samples and training a preset neural network by using the plurality of training samples.
In the embodiment of the application, passenger flow related data of a target station in a target time period, which is constructed by fully considering influence factors such as morning and evening peaks, holidays, large activities, severe weather, emergencies and the like, is determined through a trained back propagation neural network, passenger flow change perception and prediction can be effectively achieved, and a train operation adjustment scheme of the target station in the target time period is determined according to the predicted passenger flow information by further combining a K mean clustering algorithm.
Fig. 4 is a schematic structural diagram of an electronic device provided in the present invention, and as shown in fig. 4, the electronic device may include: a processor (processor) 410, a communication Interface 420, a memory (memory) 430 and a communication bus 440, wherein the processor 410, the communication Interface 420 and the memory 430 are communicated with each other via the communication bus 440. The processor 410 may invoke logic instructions in the memory 430 to perform a subway train operation adjustment method, the method comprising: determining passenger flow related data of a target site in a target time period according to passenger flow information of the target site in adjacent time of the target time period, historical contemporaneous passenger flow information and social environment influence information of the target site in the target time period, wherein the social environment influence information comprises: holiday information, large-scale event information, weather information, and emergency information; inputting the passenger flow related data of the target station in the target time period into the trained back propagation neural network, and outputting the predicted passenger flow information of the target station in the target time period; and classifying the predicted passenger flow information and the social environment influence information based on a passenger flow change response case library and a K-means clustering algorithm to obtain a train operation adjusting scheme of the target station in a target time period, wherein each passenger flow change response case of the target station in the passenger flow change response case library comprises historical social environment influence information, historical passenger flow data and a historical train operation adjusting scheme.
In addition, the logic instructions in the memory 430 may be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, the present invention further provides a computer program product, where the computer program product includes a computer program, the computer program may be stored on a non-transitory computer readable storage medium, and when the computer program is executed by a processor, a computer is capable of executing the subway train operation adjusting method provided by the above methods, and the method includes: determining passenger flow related data of a target site in a target time period according to passenger flow information of the target site in adjacent time of the target time period, historical contemporaneous passenger flow information and social environment influence information of the target site in the target time period, wherein the social environment influence information comprises: holiday information, large-scale event information, weather information and emergency information; inputting the passenger flow related data of the target station in the target time period into a trained back propagation neural network, and outputting the predicted passenger flow information of the target station in the target time period; classifying the predicted passenger flow information and the social environment influence information based on a passenger flow change response case base and a K-means clustering algorithm to obtain a train operation adjustment scheme of a target station in a target time period, wherein each passenger flow change response case of the target station in the passenger flow change response case base comprises historical social environment influence information, historical passenger flow data and a historical train operation adjustment scheme.
In still another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored, the computer program being implemented by a processor to perform the subway train operation adjusting method provided by the above methods, the method including: determining passenger flow related data of a target site in a target time period according to passenger flow information of the target site in adjacent time of the target time period, historical contemporaneous passenger flow information and social environment influence information of the target site in the target time period, wherein the social environment influence information comprises: holiday information, large-scale event information, weather information and emergency information; inputting the passenger flow related data of the target station in the target time period into the trained back propagation neural network, and outputting the predicted passenger flow information of the target station in the target time period; and classifying the predicted passenger flow information and the social environment influence information based on a passenger flow change response case library and a K-means clustering algorithm to obtain a train operation adjusting scheme of the target station in a target time period, wherein each passenger flow change response case of the target station in the passenger flow change response case library comprises historical social environment influence information, historical passenger flow data and a historical train operation adjusting scheme.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (9)
1. A subway train operation adjusting method is characterized by comprising the following steps:
determining passenger flow related data of a target site in a target time period according to passenger flow information of the target site in adjacent time of the target time period, historical contemporaneous passenger flow information and social environment influence information of the target site in the target time period, wherein the social environment influence information comprises: holiday information, large-scale event information, weather information, and emergency information;
inputting the passenger flow related data of the target station in the target time period into the trained back propagation neural network, and outputting the predicted passenger flow information of the target station in the target time period;
classifying the predicted passenger flow information and the social environment influence information based on a passenger flow change response case library and a K-means clustering algorithm to obtain a train operation adjusting scheme of a target station at a target time period, wherein each passenger flow change response case of the target station in the passenger flow change response case library comprises historical social environment influence information, historical passenger flow data and a historical train operation adjusting scheme;
wherein after the step of outputting the predicted passenger flow information of the target station in the target time period, the method further comprises the following steps:
constructing a passenger flow information sequence based on the predicted passenger flow information;
analyzing the passenger flow information sequence based on a Mankender inspection method to obtain real-time passenger flow change trend information of the target station in a target time period;
generating train operation adjustment prompt information based on the passenger flow change trend information;
wherein the target period is a period of time that has not occurred in the future.
2. The subway train operation adjusting method as claimed in claim 1, wherein before inputting said passenger flow related data of said target time period into said trained back propagation neural network, further comprising:
constructing an initial passenger flow related data sample of the target station, wherein the initial passenger flow related data sample comprises: historical early and late peak-average peak-low peak division data, historical holiday information, historical large-scale activity information, historical weather information and historical emergency data;
and carrying out data preprocessing on the initial passenger flow related data sample to obtain a passenger flow related data sample.
3. A subway train operation adjusting method as claimed in claim 2, further comprising after said obtaining of said passenger flow related data sample:
obtaining passenger flow data labels corresponding to the passenger flow related data samples;
and taking the combination of each passenger flow related data sample and the passenger flow data label as a training sample to obtain a plurality of training samples, and training a preset neural network by using the plurality of training samples.
4. The subway train operation adjusting method according to claim 3, wherein training a preset neural network by using the plurality of training samples comprises:
for any training sample, inputting the training sample to the preset neural network, and outputting the predicted passenger flow data corresponding to the training sample;
calculating a loss value according to the predicted passenger flow data corresponding to the training sample and the passenger flow data label in the training sample by using a preset loss function;
and if the loss value is smaller than a preset threshold value, finishing the training of the preset neural network to obtain the trained back propagation neural network.
5. A subway train operation adjusting device, comprising:
the determining module is used for determining passenger flow related data of the target site in the target time period according to passenger flow information of the target site in the adjacent time of the target time period, historical contemporaneous passenger flow information and social environment influence information of the target site in the target time period, wherein the social environment influence information comprises: holiday information, large-scale event information, weather information and emergency information;
the output module is used for inputting the passenger flow related data of the target station in the target time period into the trained back propagation neural network and outputting the predicted passenger flow information of the target station in the target time period;
the adjusting module is used for classifying the predicted passenger flow information and the social environment influence information based on a passenger flow change response case base and a K-means clustering algorithm to obtain a train operation adjusting scheme of a target station at a target time period, wherein each passenger flow change response case of the target station in the passenger flow change response case base comprises historical social environment influence information, historical passenger flow data and a historical train operation adjusting scheme;
wherein the apparatus is further configured to:
constructing a passenger flow information sequence based on the predicted passenger flow information;
analyzing the passenger flow information sequence based on a Mankendel inspection method to obtain real-time passenger flow change trend information of the target site in a target time period;
wherein the target period is a period of time that has not occurred in the future.
6. The subway train operation adjusting device as claimed in claim 5, wherein said device further comprises:
a construction module, configured to construct an initial passenger flow related data sample of the destination site, where the initial passenger flow related data sample includes: historical early and late peak-average peak-low peak division data, historical holiday information, historical large-scale activity information, historical weather information and historical emergency data;
and the preprocessing module is used for preprocessing the data of the initial passenger flow related data sample to obtain a passenger flow related data sample.
7. The subway train operation adjusting device of claim 6, wherein said device further comprises:
the acquisition module is used for acquiring a passenger flow data label corresponding to each passenger flow related data sample;
and the training module is used for taking the combination of each passenger flow related data sample and the passenger flow data label as a training sample, obtaining a plurality of training samples, and training a preset neural network by using the plurality of training samples.
8. An electronic device comprising a memory, a processor and a computer program stored on the memory and operable on the processor, wherein the processor, when executing the program, implements the subway train operation adjustment method as claimed in any one of claims 1 to 4.
9. A non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the subway train operation adjusting method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210839166.7A CN114912854B (en) | 2022-07-18 | 2022-07-18 | Subway train operation adjusting method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210839166.7A CN114912854B (en) | 2022-07-18 | 2022-07-18 | Subway train operation adjusting method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114912854A CN114912854A (en) | 2022-08-16 |
| CN114912854B true CN114912854B (en) | 2022-11-29 |
Family
ID=82772507
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210839166.7A Active CN114912854B (en) | 2022-07-18 | 2022-07-18 | Subway train operation adjusting method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114912854B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116665798A (en) * | 2023-04-27 | 2023-08-29 | 海南大学 | Air pollution trend early warning method and related device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111444933A (en) * | 2019-11-26 | 2020-07-24 | 北京邮电大学 | Object classification method and device |
| CN111476449A (en) * | 2019-10-09 | 2020-07-31 | 北京交通大学 | Subway station operation period division method based on improved K-means clustering algorithm |
| CN111858672A (en) * | 2020-07-16 | 2020-10-30 | 昆明理工大学 | Improved KNN case reasoning retrieval algorithm |
| CN112288197A (en) * | 2020-12-28 | 2021-01-29 | 盛威时代科技集团有限公司 | Intelligent scheduling method and device for station vehicles |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170068755A1 (en) * | 2015-09-07 | 2017-03-09 | Sap Se | Transportation schedule evaluation |
-
2022
- 2022-07-18 CN CN202210839166.7A patent/CN114912854B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111476449A (en) * | 2019-10-09 | 2020-07-31 | 北京交通大学 | Subway station operation period division method based on improved K-means clustering algorithm |
| CN111444933A (en) * | 2019-11-26 | 2020-07-24 | 北京邮电大学 | Object classification method and device |
| CN111858672A (en) * | 2020-07-16 | 2020-10-30 | 昆明理工大学 | Improved KNN case reasoning retrieval algorithm |
| CN112288197A (en) * | 2020-12-28 | 2021-01-29 | 盛威时代科技集团有限公司 | Intelligent scheduling method and device for station vehicles |
Non-Patent Citations (1)
| Title |
|---|
| "一种改进的基于案例推理的建模算法";万碧君 等;<华东理工大学学报（自然科学版）>;20141031;第40卷(第5期);第107-111页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114912854A (en) | 2022-08-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP2022500769A (en) | Power system heat load prediction method and prediction device | |
| CN109492857A (en) | A kind of distribution network failure risk class prediction technique and device | |
| CN108154244A (en) | The O＆M methods, devices and systems of real estate power equipment | |
| CN111539585B (en) | Random forest-based power customer appeal sensitivity supervision and early warning method | |
| CN111191811A (en) | Cluster load prediction method and device and storage medium | |
| CN104915897B (en) | A kind of computer implemented method of Electric Power Network Planning evaluation assignment | |
| CN116186548B (en) | Power load prediction model training method and power load prediction method | |
| CN114912854B (en) | Subway train operation adjusting method and device, electronic equipment and storage medium | |
| CN110445939A (en) | The prediction technique and device of capacity resource | |
| CN111680712B (en) | Method, device and system for predicting oil temperature of transformer based on similar time in day | |
| CN114648155A (en) | Source analysis method and emergency response system based on weather typing and weather forecast | |
| Wang et al. | Prediction and Analysis of Train Passenger Load Factor of High‐Speed Railway Based on LightGBM Algorithm | |
| CN111415049A (en) | Power failure sensitivity analysis method based on neural network and clustering | |
| Zekić-Sušac et al. | Cluster analysis and artificial neural networks in predicting energy efficiency of public buildings as a cost-saving approach | |
| CN113706291A (en) | Fraud risk prediction method, device, equipment and storage medium | |
| CN115526258A (en) | Power system transient stability evaluation method based on Spearman correlation coefficient feature extraction | |
| CN117674119A (en) | Power grid operation risk assessment method, device, computer equipment and storage medium | |
| Zou et al. | Research on assessment methods for urban public transport development in China | |
| CN113065701B (en) | Intelligent prediction method and device for rail transit passenger flow | |
| WO2021130298A1 (en) | System, apparatus and method for managing energy consumption at a technical installation | |
| CN114463978B (en) | Data monitoring method based on track traffic information processing terminal | |
| CN109800912A (en) | Information determines method and device | |
| CN113011512A (en) | Traffic generation prediction method and system based on RBF neural network model | |
| Siaminamini et al. | Generating a risk profile for car insurance policyholders: A deep learning conceptual model | |
| CN111612302A (en) | Group-level data management method and equipment |
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 |