CN112288197A - Intelligent scheduling method and device for station vehicles - Google Patents
Intelligent scheduling method and device for station vehicles Download PDFInfo
- Publication number
- CN112288197A CN112288197A CN202011573567.XA CN202011573567A CN112288197A CN 112288197 A CN112288197 A CN 112288197A CN 202011573567 A CN202011573567 A CN 202011573567A CN 112288197 A CN112288197 A CN 112288197A
- Authority
- CN
- China
- Prior art keywords
- information
- transport capacity
- demand prediction
- capacity demand
- current
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 63
- 230000005540 biological transmission Effects 0.000 claims abstract description 38
- 238000005457 optimization Methods 0.000 claims abstract description 16
- 238000004458 analytical method Methods 0.000 claims abstract description 8
- 238000012549 training Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 10
- 230000000306 recurrent effect Effects 0.000 claims description 10
- 238000003062 neural network model Methods 0.000 claims description 9
- 230000015654 memory Effects 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 4
- 238000011478 gradient descent method Methods 0.000 claims description 3
- 238000010801 machine learning Methods 0.000 abstract description 13
- 238000004422 calculation algorithm Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000002068 genetic effect Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013377 clone selection method Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012248 genetic selection Methods 0.000 description 1
- 238000007689 inspection 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
- 108090000623 proteins and genes Proteins 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000004904 shortening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—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
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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
-
- 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
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Data Mining & Analysis (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a station vehicle intelligent scheduling method and device. Wherein, the method comprises the following steps: acquiring current actual transmission quantity information and attribute information of a current time point; inputting the current actual sending quantity information and the attribute information of the current time point into a transport capacity demand prediction model to obtain a transport capacity demand prediction result within a target time period output by the transport capacity demand prediction model; and determining the current transport capacity scheduling scheme based on the transport capacity demand prediction result and a preset optimization principle. By adopting the intelligent dispatching method for the station vehicles, disclosed by the invention, the transportation capacity demand condition of the passenger station in a future period of time can be predicted based on historical data, current ticket sales condition and the like by using a machine learning analysis method, and a recommended dispatching plan is intelligently generated by combining multi-dimensional reference information, so that the passenger flow prediction precision and efficiency are effectively improved.
Description
Technical Field
The invention relates to the technical field of big data processing, in particular to a method and a device for intelligently scheduling station vehicles. In addition, an electronic device and a non-transitory computer readable storage medium are also related.
Background
In recent years, with the rapid development of internet and computer technology, machine learning has been widely applied to various industries, and navigation positioning devices have also been popularized in every operating passenger car. In the traffic operation process of regional client stations, the operation passenger cars are accurately scheduled in real time and the like, and are closely related to the corresponding different passenger flow change conditions. For example, in holidays, abnormal weather or peak hours, the passenger flow change needs to be ensured to operate orderly and efficiently by measures such as increasing the departure times of the passenger cars, shortening the departure intervals of the trains, increasing managers and the like. Therefore, accurate prediction of daily passenger flow change conditions of each line is very important for realizing effective regulation and control.
At present, the shift scheduling of the traditional passenger station is usually 'blind scheduling', that is, a dispatcher can only obtain relevant information through communication equipment, schedule relevant vehicles according to own experience or expected required transport capacity, and arrange and implement corresponding scheduling plans. However, the system has the problems of large flow and concentrated travel time of people in holidays and the like, and the reaction is delayed, so that the people cannot be accurately arranged. Therefore, how to design a safe, efficient and convenient scheduling scheme generation and recommendation strategy for the scheduling problem in passenger car traffic operation becomes a problem to be solved urgently in the industry at present.
Disclosure of Invention
Therefore, the invention provides a station vehicle intelligent scheduling method and device, which are used for solving the problems that in the prior art, the efficiency and the accuracy of vehicle scheduling in passenger car traffic operation are low, and timely and effective measures cannot be taken for the actual change situation of the current passenger flow.
The invention provides an intelligent scheduling method for station vehicles, which comprises the following steps: acquiring current actual transmission quantity information and attribute information of a current time point; inputting the current actual sending quantity information and the attribute information of the current time point into a transport capacity demand prediction model to obtain a transport capacity demand prediction result within a target time period output by the transport capacity demand prediction model; the transport capacity demand prediction model is a recurrent neural network model obtained by performing back propagation training by taking historical transmission quantity information of a preset time length and attribute information of corresponding time points as samples and taking actual transport capacity demand prediction results corresponding to the historical transmission quantity information and the attribute information of the corresponding time points as sample labels; and determining the current transport capacity scheduling scheme based on the transport capacity demand prediction result and a preset optimization principle.
Further, the intelligent scheduling method for the station vehicle further comprises the following steps: and generating a corresponding alternative scheduling scheme according to the transport capacity demand prediction result, the personnel driving information, the vehicle operation information and a preset fixed scheduling scheme.
Further, the transport capacity demand prediction model is specifically configured to perform feature extraction on the historical transmission amount information and the attribute information at the corresponding time point to obtain target features, perform transport capacity demand prediction analysis on the current actual transmission amount information and the attribute information at the current time point based on the target features, and output a corresponding transport capacity demand prediction result.
Further, the obtaining of the current actual transmission amount information specifically includes: acquiring current actual sending volume information according to the current actual ticket selling volume information;
the attribute information of the current time point specifically includes: at least one of weather condition information corresponding to the current time point, transport capacity index information of a previous synchronization time point, holiday information, average transport capacity index information in a previous target time period and morning and evening peak change rule characteristic information.
Further, the intelligent scheduling method for the station vehicle further comprises the following steps: the method comprises the steps of collecting real-time position information of a current commercial vehicle, predicting a target commercial vehicle which enters a station and reports the shift within a preset time range according to the real-time position information, bringing the target commercial vehicle into scheduling resources, and determining a corresponding vehicle scheduling resource range.
Further, the intelligent scheduling method for the station vehicle further comprises the following steps: and generating the hot line scheduling information of the current passenger station based on the current actual ticket sales information.
Further, the intelligent scheduling method for the station vehicle further comprises the following steps: and in the model training process, optimizing the transport capacity demand prediction model based on a preset mean square error method or a random gradient descent method.
Correspondingly, the invention also provides an intelligent scheduling device for the station vehicles, which comprises:
the information acquisition unit is used for acquiring the current actual sending quantity information and the attribute information of the current time point;
the transport capacity demand prediction unit is used for inputting the current actual sending quantity information and the attribute information of the current time point into a transport capacity demand prediction model to obtain a transport capacity demand prediction result within a target time period output by the transport capacity demand prediction model;
the transport capacity demand prediction model is a recurrent neural network model obtained by performing back propagation training by taking historical transmission quantity information of a preset time length and attribute information of corresponding time points as samples and taking actual transport capacity demand prediction results corresponding to the historical transmission quantity information and the attribute information of the corresponding time points as sample labels;
and the transport capacity scheduling scheme determining unit is used for determining the current transport capacity scheduling scheme based on the transport capacity demand prediction result and a preset optimization principle.
Further, the station vehicle intelligent scheduling device further includes: and the scheduling scheme determining unit is used for generating a corresponding alternative scheduling scheme according to the transport capacity demand prediction result, the personnel driving information, the vehicle operation information and a preset fixed scheduling scheme.
Further, the transport capacity demand prediction model is specifically configured to perform feature extraction on the historical transmission amount information and the attribute information at the corresponding time point to obtain target features, perform transport capacity demand prediction analysis on the current actual transmission amount information and the attribute information at the current time point based on the target features, and output a corresponding transport capacity demand prediction result.
Further, the obtaining of the current actual transmission amount information specifically includes: acquiring current actual sending volume information according to the current actual ticket selling volume information;
the attribute information of the current time point specifically includes: at least one of weather condition information corresponding to the current time point, transport capacity index information of a previous synchronization time point, holiday information, average transport capacity index information in a previous target time period and morning and evening peak change rule characteristic information.
Further, the station vehicle intelligent scheduling device further includes: and the scheduling resource range determining unit is used for acquiring the real-time position information of the current commercial vehicle, predicting the target commercial vehicle which enters the station and reports the shift within a preset time range according to the real-time position information, bringing the target commercial vehicle into scheduling resources, and determining the corresponding vehicle scheduling resource range.
Further, the station vehicle intelligent scheduling device further includes: and the hot line scheduling unit is used for generating the current hot line scheduling information of the passenger station based on the current actual ticket selling amount information.
Further, the station vehicle intelligent scheduling device further includes: and the model optimization processing unit is used for optimizing the transport capacity demand prediction model based on a preset mean square error method or a random gradient descent method in the model training process.
Correspondingly, the invention also provides an electronic device, comprising: the intelligent scheduling method comprises the following steps of a storage device, a processor and a computer program which are stored on the storage device and can run on the processor, wherein the processor executes the program to realize the steps of the intelligent scheduling method for the station vehicle.
Accordingly, the present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when being executed by a processor, implements the steps of the intelligent scheduling method for station vehicles as described in any one of the above.
According to the intelligent dispatching method for the station vehicles, provided by the invention, the transportation capacity demand condition of the passenger station in a future period of time can be predicted by using a machine learning analysis method, and a recommended dispatching plan is generated intelligently by combining with multi-dimensional reference information, so that the passenger flow prediction precision and efficiency are effectively improved.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed for 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 those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of a station vehicle intelligent scheduling method provided by the present invention;
fig. 2 is a schematic structural diagram of an intelligent scheduling device for a station vehicle provided by the invention;
fig. 3 is a schematic physical structure 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.
The following describes an embodiment of the intelligent station vehicle scheduling method in detail based on the invention. As shown in fig. 1, which is a schematic flow chart of the intelligent scheduling method for station vehicles provided by the present invention, the specific implementation process includes the following steps:
step 101: and acquiring the current actual sending quantity information and the attribute information of the current time point. Wherein the current actual transmission amount information may be determined by a current ticket sales amount of the passenger station. The attribute information of the current time point may specifically include at least one of weather condition information, road condition, transportation capacity index information of previous synchronization time points, holiday information, average transportation capacity index information in previous target time periods, morning and evening peak change rule characteristic information, and the like corresponding to the current time point. In the embodiment of the invention, the current actual sending amount information can be determined according to the current actual ticket selling amount information. Of course, in the specific implementation process, the current actual transmission amount information may also be obtained in other manners, which is not specifically limited herein.
Step 102: and inputting the current actual sending quantity information and the attribute information of the current time point into a transport capacity demand prediction model to obtain a transport capacity demand prediction result within a target time period output by the transport capacity demand prediction model.
The transport capacity demand prediction model is a recurrent neural network model obtained by performing back propagation training by taking historical transmission quantity information of a preset time length and attribute information of corresponding time points as samples and taking actual transport capacity demand prediction results corresponding to the historical transmission quantity information and the attribute information of the corresponding time points as sample labels. The transport capacity demand prediction model is specifically used for carrying out feature extraction on the historical transmission quantity information and the attribute information of the corresponding time point to obtain target features, carrying out transport capacity demand prediction analysis on the current actual transmission quantity information and the attribute information of the current time point based on the target features, and outputting a corresponding transport capacity demand prediction result; or carrying out the transport capacity demand prediction on the sending quantity information to be predicted in a period of time in the future and the attribute information in the period of time in the future, and outputting corresponding transport capacity demand curve data in a target period of time.
In the actual implementation process, firstly, the forecasting demand can be abstracted into a regression problem, namely, the current ticket selling quantity and the future ticket selling quantity are considered; and secondly, carrying out normalization and normalization processing on historical data (such as indicators of the same year, holidays, average last week and the like) of the passenger station for a period of time, analyzing by using a machine learning method based on the processed historical data of the passenger station, predicting a transport capacity demand curve of the passenger station for a period of time in the future through a preset machine learning model, and generating a recommended scheduling plan and a scheduling plan by combining multidimensional information such as current ticket sales volume, weather conditions, vehicle operation conditions, driver working conditions and the like.
Specifically, processed passenger station historical data can be divided into a training set and a testing set, and mean square error or random gradient descent is used as an optimizer to optimize a transport capacity demand prediction model; establishing a machine learning model, and after training the machine learning model by using a training set, evaluating the machine learning model by using a test set to realize model parameter adjustment to obtain a trained machine learning model; and further predicting by using the trained machine learning model, and drawing a transport capacity demand curve graph.
In the embodiment of the invention, the machine learning model is a Long Short-Term Memory network (LSTM) model, and prediction is carried out based on the LSTM model. The LSTM model is different from a traditional neural network architecture, and is a recurrent neural network which uses back propagation time training and overcomes the problem of hour gradient.
Step 103: and determining the current transport capacity scheduling scheme based on the transport capacity demand prediction result and a preset optimization principle.
In the embodiment of the invention, after the current transport capacity scheduling scheme is determined based on the transport capacity demand prediction result and a preset optimization principle, the corresponding transport capacity scheduling scheme is pushed to the target user side for selection of a dispatcher, and the corresponding scheduling task is completed based on the selection information input by the dispatcher. Wherein, the optimization principle can also include but not limited to the following constraints: the total driving time of a driver per day is not more than 8 hours, the safety inspection of the vehicle is passed, the errors of the planned transportation capacity and the predicted transportation capacity are not more than 20%, whether the vehicle can pass at a high speed or not on the day, the principle of maximum transportation capacity, the principle of highest efficiency, the principle of fastest time and the like.
In a specific implementation process, an exhaustive method can be adopted to determine all current capacity scheduling schemes. And the distance information from the passenger station can be calculated according to the GPS positioning information of the vehicle, so that the station entering time and the earliest scheduling time can be calculated and added into the constraint condition of the scheduling scheme. And screening all unreasonable scheduling schemes according to an optimization principle comprising a plurality of constraint conditions, and determining the current capacity scheduling scheme meeting the actual requirement.
In the actual implementation process, the evaluation of the capacity scheduling scheme can be abstracted into a weight scoring problem based on an optimization principle, that is to say: the total score of the capacity scheduling scheme = ∑ capacity scheduling scheme score index item × (weight); wherein the mathematics of the optimization principle are embodied as weights. The specific algorithm of the scoring index items of each capacity scheduling scheme is as follows: capacity score = N ∑ total seat number of vehicles; efficiency score = M capacity/number of vehicles scheduled in a time period; passenger residence time score = L/Σ (time slot forecasted demand capacity-scheduled capacity) time slot duration. The parameter N, M, L is an empirical coefficient, which can be obtained through actual survey and statistics, and is not limited herein. According to the scheme total score, the capacity scheduling scheme display can be taken as a preset item (such as the top 5 items) so as to be selected by scheduling personnel.
In the specific implementation process, the real-time position information of the current operation vehicle can be acquired, the target operation vehicle which enters the station and reports the shift within the preset time range after the prediction is carried out according to the real-time position information, the target operation vehicle is brought into the scheduling resource, the scheduling resource range is expanded, the vehicles which do not enter the station and report the shift are also partially brought into the scheduling resource, and the corresponding vehicle scheduling resource range is determined. In addition, for the convenience of reference of the dispatcher, the hot line scheduling information of the current passenger station can be generated according to the current actual ticket sales information in the embodiment of the invention.
Furthermore, a corresponding alternative scheduling scheme in a later period of time can be generated according to the forecast result of the transport capacity demand, the personnel driving information, the vehicle running information and a preset fixed scheduling scheme in the forecast target time period, so that the manual workload is reduced, and the scheduling work efficiency is improved. The specific implementation process is that the information is analyzed through a genetic algorithm and a clone selection algorithm to generate a corresponding alternative scheduling scheme, and the evolution process of the algorithm is effectively guided through a designed scheduling scheme evaluation method.
In the specific implementation process, the whole system can be calculated by adopting a genetic algorithm, and in order to accelerate the convergence speed of the optimal scheme, the initial population is generated by adopting a priority-based scheduling algorithm. The method comprises the following specific steps: s1 encoding: and forming a two-dimensional matrix by using the states of all vehicles which can participate in the shift arrangement at each station in each time period as genes. S2 calculates the adaptation value: and calculating local scores by using a constraint condition weight calculation method and taking each constraint condition as a local evaluation unit, taking the weighted average value of all the local scores as a global score, specifically setting the weight value to be 1-10, and setting in advance according to the importance of the constraint condition. The constraint conditions include an optimized dimension item, policy regulations, the number of vehicle demands in each time period obtained from the capacity demand prediction curve, and the like, and are not specifically limited herein. S3 mutation and genetic selection: calculating a global score F (G0) of the initial population G0, mutating the initial population according to a preset probability p to generate a next generation population G1, calculating a corresponding global score F (G1), if F (G1) > F (G0), continuously mutating on the basis of a next generation population G1, otherwise, continuously mutating by using the initial population G0. And S4, obtaining a theoretical optimal solution after multiple generations of inheritance. It should be noted that, considering that there may be conflicts in the efficiency and the constraint conditions, the score may be set to reach a preset threshold value, which is regarded as a feasible solution, and a corresponding capacity scheduling scheme is obtained.
By adopting the intelligent dispatching method for the station vehicles, the transportation capacity demand condition of the passenger station in a future period of time can be predicted based on historical data, current ticket sales condition and the like by using a machine learning analysis method, and a recommended dispatching plan is generated intelligently by combining multi-dimensional reference information, so that the precision and the efficiency of passenger flow prediction are effectively improved.
Corresponding to the station vehicle intelligent scheduling method, the invention also provides a station vehicle intelligent scheduling device. Because the embodiment of the device is similar to the method embodiment, the description is relatively simple, and please refer to the description of the method embodiment, and the following embodiment of the station vehicle intelligent dispatching device is only schematic. Fig. 2 is a schematic structural diagram of an intelligent scheduling apparatus for a station vehicle according to the present invention.
The intelligent scheduling device for the station vehicle specifically comprises the following parts:
an information obtaining unit 201, configured to obtain current actual transmission amount information and attribute information of a current time point;
and the transport capacity demand prediction unit 202 is configured to input the current actual sending amount information and the attribute information of the current time point into a transport capacity demand prediction model, and obtain a transport capacity demand prediction result within a target time period output by the transport capacity demand prediction model.
The transport capacity demand prediction model is a recurrent neural network model obtained by performing back propagation training by taking historical transmission quantity information of a preset time length and attribute information of corresponding time points as samples and taking actual transport capacity demand prediction results corresponding to the historical transmission quantity information and the attribute information of the corresponding time points as sample labels;
and the capacity scheduling scheme determining unit 203 is configured to determine a current capacity scheduling scheme based on the capacity demand prediction result and a preset optimization principle.
By adopting the intelligent station vehicle scheduling device, the capacity demand condition of the passenger station in a future period of time can be predicted based on historical data, current ticket sales condition and the like by using a machine learning analysis method, and a recommended scheduling plan is intelligently generated by combining multi-dimensional reference information, so that the passenger flow prediction precision and efficiency are effectively improved.
Corresponding to the station vehicle intelligent scheduling method, the invention also provides electronic equipment. Since the embodiment of the electronic device is similar to the above method embodiment, the description is relatively simple, and please refer to the description of the above method embodiment, and the electronic device described below is only schematic. Fig. 3 is a schematic physical structure diagram of an electronic device according to the present disclosure. The electronic device may include: a processor (processor) 301, a memory (memory) 302, a communication bus 303 and a communication interface 304, wherein the processor 301 and the memory 302 complete communication with each other through the communication bus 303, and communicate with external devices through the communication interface 304. Processor 301 may invoke logic instructions in memory 302 to perform a site vehicle intelligent scheduling method comprising: acquiring current actual transmission quantity information and attribute information of a current time point;
inputting the current actual sending quantity information and the attribute information of the current time point into a transport capacity demand prediction model to obtain a transport capacity demand prediction result within a target time period output by the transport capacity demand prediction model; the transport capacity demand prediction model is a recurrent neural network model obtained by performing back propagation training by taking historical transmission quantity information of a preset time length and attribute information of corresponding time points as samples and taking actual transport capacity demand prediction results corresponding to the historical transmission quantity information and the attribute information of the corresponding time points as sample labels; and determining the current transport capacity scheduling scheme based on the transport capacity demand prediction result and a preset optimization principle.
Furthermore, the logic instructions in the memory 302 may be implemented in software functional units and stored in a computer readable storage medium when sold or used as a stand-alone product. 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 also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, the computer program including program instructions, when the program instructions are executed by a computer, the computer being capable of executing the station vehicle intelligent scheduling method provided by the above-mentioned method embodiments, the method including: acquiring current actual transmission quantity information and attribute information of a current time point; inputting the current actual sending quantity information and the attribute information of the current time point into a transport capacity demand prediction model to obtain a transport capacity demand prediction result within a target time period output by the transport capacity demand prediction model; the transport capacity demand prediction model is a recurrent neural network model obtained by performing back propagation training by taking historical transmission quantity information of a preset time length and attribute information of corresponding time points as samples and taking actual transport capacity demand prediction results corresponding to the historical transmission quantity information and the attribute information of the corresponding time points as sample labels; and determining the current transport capacity scheduling scheme based on the transport capacity demand prediction result and a preset optimization principle.
In yet another aspect, the present invention further 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 station vehicle intelligent scheduling method provided in the foregoing embodiments, the method including: acquiring current actual transmission quantity information and attribute information of a current time point; inputting the current actual sending quantity information and the attribute information of the current time point into a transport capacity demand prediction model to obtain a transport capacity demand prediction result within a target time period output by the transport capacity demand prediction model; the transport capacity demand prediction model is a recurrent neural network model obtained by performing back propagation training by taking historical transmission quantity information of a preset time length and attribute information of corresponding time points as samples and taking actual transport capacity demand prediction results corresponding to the historical transmission quantity information and the attribute information of the corresponding time points as sample labels; and determining the current transport capacity scheduling scheme based on the transport capacity demand prediction result and a preset optimization principle.
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 the present 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 will 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 (10)
1. A station vehicle intelligent scheduling method is characterized by comprising the following steps:
acquiring current actual transmission quantity information and attribute information of a current time point;
inputting the current actual sending quantity information and the attribute information of the current time point into a transport capacity demand prediction model to obtain a transport capacity demand prediction result within a target time period output by the transport capacity demand prediction model;
the transport capacity demand prediction model is a recurrent neural network model obtained by performing back propagation training by taking historical transmission quantity information of a preset time length and attribute information of corresponding time points as samples and taking actual transport capacity demand prediction results corresponding to the historical transmission quantity information and the attribute information of the corresponding time points as sample labels;
and determining the current transport capacity scheduling scheme based on the transport capacity demand prediction result and a preset optimization principle.
2. The intelligent scheduling method of station vehicles according to claim 1,
further comprising: and generating a corresponding alternative scheduling scheme according to the transport capacity demand prediction result, the personnel driving information, the vehicle operation information and a preset fixed scheduling scheme.
3. The intelligent scheduling method of station vehicles according to claim 1,
the transport capacity demand prediction model is specifically used for performing feature extraction on the historical transmission quantity information and the attribute information of the corresponding time point to obtain target features, performing transport capacity demand prediction analysis on the current actual transmission quantity information and the attribute information of the current time point based on the target features, and outputting a corresponding transport capacity demand prediction result.
4. The intelligent scheduling method for the station vehicle according to claim 1, wherein the obtaining of the current actual transmission amount information specifically includes: determining current actual sending volume information according to the current actual ticket selling volume information;
the attribute information of the current time point specifically includes: at least one of weather condition information corresponding to the current time point, transport capacity index information of a previous synchronization time point, holiday information, average transport capacity index information in a previous target time period and morning and evening peak change rule characteristic information.
5. The intelligent scheduling method of station vehicles according to claim 1,
further comprising: the method comprises the steps of collecting real-time position information of a current commercial vehicle, predicting a target commercial vehicle which enters a station and reports the shift within a preset time range according to the real-time position information, bringing the target commercial vehicle into scheduling resources, and determining a corresponding vehicle scheduling resource range.
6. The intelligent scheduling method of station vehicles according to claim 4,
further comprising: and generating the hot line scheduling information of the current passenger station based on the current actual ticket sales information.
7. The intelligent scheduling method of station vehicles according to claim 1,
further comprising: and in the model training process, optimizing the transport capacity demand prediction model based on a preset mean square error method or a random gradient descent method.
8. An intelligent station vehicle scheduling device, comprising:
the information acquisition unit is used for acquiring the current actual sending quantity information and the attribute information of the current time point;
the transport capacity demand prediction unit is used for inputting the current actual sending quantity information and the attribute information of the current time point into a transport capacity demand prediction model to obtain a transport capacity demand prediction result within a target time period output by the transport capacity demand prediction model;
the transport capacity demand prediction model is a recurrent neural network model obtained by performing back propagation training by taking historical transmission quantity information of a preset time length and attribute information of corresponding time points as samples and taking actual transport capacity demand prediction results corresponding to the historical transmission quantity information and the attribute information of the corresponding time points as sample labels;
and the transport capacity scheduling scheme determining unit is used for determining the current transport capacity scheduling scheme based on the transport capacity demand prediction result and a preset optimization principle.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program implements the steps of the intelligent scheduling method for station vehicles according to any one of claims 1-7.
10. A non-transitory computer readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the intelligent scheduling method for station vehicles according to any one of claims 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011573567.XA CN112288197B (en) | 2020-12-28 | 2020-12-28 | Intelligent scheduling method and device for station vehicles |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011573567.XA CN112288197B (en) | 2020-12-28 | 2020-12-28 | Intelligent scheduling method and device for station vehicles |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112288197A true CN112288197A (en) | 2021-01-29 |
CN112288197B CN112288197B (en) | 2021-06-15 |
Family
ID=74426492
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011573567.XA Active CN112288197B (en) | 2020-12-28 | 2020-12-28 | Intelligent scheduling method and device for station vehicles |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112288197B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113421039A (en) * | 2021-05-21 | 2021-09-21 | 浙江大搜车融资租赁有限公司 | Vehicle management method, device and equipment |
CN113447080A (en) * | 2021-07-07 | 2021-09-28 | 广州佰迈起生物科技有限公司 | Temperature and humidity detection processing method and device, server and system |
CN113470206A (en) * | 2021-07-01 | 2021-10-01 | 山东旗帜信息有限公司 | Highway inspection method, device and medium based on vehicle matching |
CN114239906A (en) * | 2021-11-08 | 2022-03-25 | 壹药网科技(上海)股份有限公司 | Human demand prediction method and personnel scheduling system |
CN114254869A (en) * | 2021-11-19 | 2022-03-29 | 深圳云天励飞技术股份有限公司 | Interval vehicle scheduling method and device, computer equipment and storage medium |
CN114912854A (en) * | 2022-07-18 | 2022-08-16 | 通号城市轨道交通技术有限公司 | Subway train operation adjusting method and device, electronic equipment and storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107564270A (en) * | 2017-09-07 | 2018-01-09 | 深圳市蓝泰源信息技术股份有限公司 | A kind of intelligent public transportation dispatching method for running |
CN109034449A (en) * | 2018-06-14 | 2018-12-18 | 华南理工大学 | Short-term bus passenger flow prediction technique based on deep learning and passenger behavior mode |
CN109829649A (en) * | 2019-01-31 | 2019-05-31 | 北京首汽智行科技有限公司 | A kind of vehicle dispatching method |
CN109978040A (en) * | 2019-03-19 | 2019-07-05 | 西南交通大学 | A kind of traffic transport power distribution forecasting method |
CN110796317A (en) * | 2019-12-02 | 2020-02-14 | 武汉理工大学 | Urban taxi scheduling method based on demand prediction |
JP2020166532A (en) * | 2019-03-29 | 2020-10-08 | 株式会社メトロリー | Outing determination system, outing determination method and outing determination program |
-
2020
- 2020-12-28 CN CN202011573567.XA patent/CN112288197B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107564270A (en) * | 2017-09-07 | 2018-01-09 | 深圳市蓝泰源信息技术股份有限公司 | A kind of intelligent public transportation dispatching method for running |
CN109034449A (en) * | 2018-06-14 | 2018-12-18 | 华南理工大学 | Short-term bus passenger flow prediction technique based on deep learning and passenger behavior mode |
CN109829649A (en) * | 2019-01-31 | 2019-05-31 | 北京首汽智行科技有限公司 | A kind of vehicle dispatching method |
CN109978040A (en) * | 2019-03-19 | 2019-07-05 | 西南交通大学 | A kind of traffic transport power distribution forecasting method |
JP2020166532A (en) * | 2019-03-29 | 2020-10-08 | 株式会社メトロリー | Outing determination system, outing determination method and outing determination program |
CN110796317A (en) * | 2019-12-02 | 2020-02-14 | 武汉理工大学 | Urban taxi scheduling method based on demand prediction |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113421039A (en) * | 2021-05-21 | 2021-09-21 | 浙江大搜车融资租赁有限公司 | Vehicle management method, device and equipment |
CN113470206A (en) * | 2021-07-01 | 2021-10-01 | 山东旗帜信息有限公司 | Highway inspection method, device and medium based on vehicle matching |
CN113470206B (en) * | 2021-07-01 | 2023-04-25 | 山东旗帜信息有限公司 | Expressway inspection method, equipment and medium based on vehicle matching |
CN113447080A (en) * | 2021-07-07 | 2021-09-28 | 广州佰迈起生物科技有限公司 | Temperature and humidity detection processing method and device, server and system |
CN114239906A (en) * | 2021-11-08 | 2022-03-25 | 壹药网科技(上海)股份有限公司 | Human demand prediction method and personnel scheduling system |
CN114254869A (en) * | 2021-11-19 | 2022-03-29 | 深圳云天励飞技术股份有限公司 | Interval vehicle scheduling method and device, computer equipment and storage medium |
CN114912854A (en) * | 2022-07-18 | 2022-08-16 | 通号城市轨道交通技术有限公司 | Subway train operation adjusting method and device, electronic equipment and storage medium |
CN114912854B (en) * | 2022-07-18 | 2022-11-29 | 通号城市轨道交通技术有限公司 | Subway train operation adjusting method and device, electronic equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN112288197B (en) | 2021-06-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112288197B (en) | Intelligent scheduling method and device for station vehicles | |
Larsen et al. | Susceptibility of optimal train schedules to stochastic disturbances of process times | |
Ghannadpour et al. | A multi-objective dynamic vehicle routing problem with fuzzy time windows: Model, solution and application | |
CN104464291B (en) | Traffic flow predicting method and system | |
US9020857B2 (en) | Integrated risk management process | |
CN111915254A (en) | Inventory optimization control method and system suitable for automobile after-sales accessories | |
CN109920248B (en) | Bus arrival time prediction method based on GRU neural network | |
CN104504460A (en) | Method and device for predicating user loss of car calling platform | |
US20210192555A1 (en) | Model-based deep reinforcement learning for dynamic pricing in an online ride-hailing platform | |
CN104573877A (en) | Power distribution network equipment demand prediction and quantitative method and system | |
CN116167585A (en) | Data processing method, device, equipment and scheduling system applied to garbage collection | |
CN111415027A (en) | Method and device for constructing component prediction model | |
Mukhitdinov | An imitation model of quality utility services to the population | |
Jamil et al. | Taxi passenger hotspot prediction using automatic ARIMA model | |
CN116432806A (en) | Rolling prediction method and system for flight ground guarantee node time | |
CN104408525A (en) | Quantitative evaluation and control method of job shop scheduling risks | |
Sánchez-Martínez | Running time variability and resource allocation: a data-driven analysis of high-frequency bus operations | |
Martínez-Estupiñan et al. | Improving the performance of headway control tools by using individual driving speed data | |
CN112308618B (en) | Data processing method and device, electronic equipment and storage medium | |
CN114693265A (en) | Supply chain multi-user docking method and system of cloud switching platform | |
Cavone et al. | Efficient resource planning of intermodal terminals under uncertainty | |
CN112308344A (en) | Method and device for predicting reservation value of non-departure flight and electronic equipment | |
CN116757330B (en) | Method, system, equipment and medium for calculating minimum transit time of different stations in same city of railway | |
CN118195280B (en) | Integrated task scheduling method, system and device based on integrated nesting model | |
Vakaliuk et al. | Methodology for Evaluation the Performance Indicators of the Ergatic Information System Functioning. |
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 |