Traffic flow prediction method, device, equipment, medium and computer program product

Abstract

The invention provides a traffic flow prediction method, device and equipment, a medium and a computer program product. The method comprises the following steps: collecting vehicle operation information based on historical train arrival and departure reports; the vehicle operation information comprises goods categories, starting stations, arrival stations, passing stations and arrival and departure time of each passing station; performing statistical calculation based on the vehicle operation information, and constructing a trajectory table; each piece of trajectory data of the trajectory table comprises a cargo category, a starting station, a final arrival station, a home station, a next station, the average residence time of the home station, the average interval operation time from the home station to the next station, and the probability; and on the basis of the starting station, the current station, the end arrival station, the cargo category and the trajectory table of the to-be-predicted vehicle, predicting the operation of the to-be-predicted vehicle to obtain a prediction result. According to the invention, through the constructed trajectory table, on the basis of the current station and the current time of the vehicle, the future running path and the arrival-departure time sequence of the vehicle are circularly predicted, and a more accurate traffic flow prediction scheme is provided.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic flow prediction, and in particular to a traffic flow prediction method, device, equipment, medium and computer program product. Background Art

[0002] The traffic in the road network passes through each section continuously and unbalancedly to reach each station. When the number of vehicles exceeds the capacity limit of the station and section, congestion will occur. By establishing a more accurate traffic forecasting method and predicting the bottleneck of the road network capacity in advance, data support can be provided for the formulation of effective traffic adjustment measures. Summary of the invention

[0003] The present invention provides a traffic flow prediction method, device, equipment, medium and computer program product, which are used to solve the defect of inaccurate prediction in the existing traffic flow prediction technology and realize accurate traffic flow prediction.

[0004] The present invention provides a traffic flow prediction method, comprising the following steps: Collecting vehicle operation information based on historical train arrival and departure reports; the vehicle operation information includes cargo category, departure station, final destination station, transit stations, and arrival and departure time of each transit station; Perform statistical calculations based on the vehicle operation information to construct a trajectory table; each trajectory data in the trajectory table includes cargo category, departure station, final station, current station, next station, average stay time at current station, average interval running time from current station to next station, and probability; Based on the departure station, current station, final station, cargo category and the trajectory table of the vehicle to be predicted, the operation of the vehicle to be predicted is predicted to obtain a prediction result.

[0005] According to a vehicle flow prediction method provided by the present invention, the operation of the vehicle to be predicted is predicted based on the departure station, current station, destination station, cargo category and the trajectory table to obtain the prediction result, which includes: Obtain the departure station, final destination station and cargo category of the vehicle to be predicted; Obtaining the current time and the current station of the vehicle to be predicted; In the case that the current station is not the final station of the vehicle to be predicted, based on the departure station, current station, final station, cargo category and the trajectory table of the vehicle to be predicted, the next station of the current station, the stay time of the current station and the interval running time from the current station to the next station are determined; The departure time of the current station is calculated as the sum of the current time and the stay time of the current station, and the arrival time of the next station is calculated as the sum of the departure time of the current station and the interval running time; Add the next station of the current station to the predicted path station set, add the stay time of the current station and the interval running time to the predicted running time sequence; add the departure time of the current station and the arrival time of the next station to the predicted arrival and departure time sequence; The next station of the current station is taken as the current station, the arrival time of the next station is taken as the current time, and the step of obtaining the current time and the current station of the vehicle to be predicted is returned to until the current station is the final destination of the vehicle to be predicted, and the vehicle prediction route and the vehicle prediction arrival and departure time series are obtained.

[0006] According to a vehicle flow prediction method provided by the present invention, the method of determining the next station of the current station, the stay time of the current station, and the interval running time from the current station to the next station based on the departure station, the current station, the final station, the cargo category and the trajectory table of the vehicle to be predicted includes: Determine the next station with the maximum probability of the current station in the trajectory table as the next station of the current station; Based on the trajectory table, determining the average stay time of the current station as the stay time of the current station; Based on the trajectory table, the average interval running time from the current station to the next station is determined as the interval running time from the current station to the next station.

[0007] According to a vehicle flow prediction method provided by the present invention, based on the departure station, current station, final station, cargo category and trajectory table of the vehicle to be predicted, the operation of the vehicle to be predicted is predicted to obtain a prediction result, and then the method includes: Receiving arrival or departure information of the vehicle to be predicted; the arrival or departure information includes a station and the arrival or departure time of the station; In the case where the station is the final destination, the vehicle predicted route and the vehicle predicted arrival and departure time series are the prediction results; In the case where the station is not the final station, determining whether the station is in the predicted path station set; In the case where the station is in the predicted path station set, the predicted arrival and departure time series is updated based on the arrival or departure time of the station and the predicted operation time series.

[0008] According to a vehicle flow prediction method provided by the present invention, when the station is not the final destination station, determining whether the station is in the set of stations on the predicted path, then comprising: When the station is not in the predicted route station set, the station is taken as the current station of the vehicle to be predicted, and the arrival or departure time of the station is taken as the current time. The predicted route station set, the predicted operation time series and the predicted arrival and departure time series are reset, and the step of obtaining the current time and the current station of the vehicle to be predicted is returned.

[0009] According to a vehicle flow prediction method provided by the present invention, the statistical calculation based on the vehicle operation information to construct a trajectory table includes: Based on the abnormal data elimination algorithm, the abnormal data elimination operation is performed on the arrival and departure times in the vehicle operation information, and the average stay time at the station, the average interval running time from the station to the next station, and the probability contained in the trajectory table are calculated; the abnormal data elimination algorithm includes a clustering algorithm.

[0010] The present invention also provides a vehicle flow prediction device, comprising the following modules: The vehicle operation information collection module is used to collect vehicle operation information based on historical train arrival and departure reports; the vehicle operation information includes cargo category, departure station, final arrival station, transit station, and arrival and departure time of each transit station; A trajectory table construction module is used to perform statistical calculations based on the vehicle operation information to construct a trajectory table; each trajectory data in the trajectory table includes cargo category, departure station, final station, current station, next station, average stay time at current station, average interval running time from current station to its next station, and probability; The traffic flow prediction module is used to predict the operation of the vehicle to be predicted based on the departure station, current station, final station, cargo category and the trajectory table of the vehicle to be predicted to obtain a prediction result.

[0011] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, any of the above-mentioned traffic flow prediction methods is implemented.

[0012] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the vehicle flow prediction method as described above is implemented.

[0013] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements any of the above-mentioned traffic flow prediction methods.

[0014] The traffic flow prediction method, device, equipment, medium and computer program product provided by the present invention construct a trajectory table containing path and time information based on historical train arrival and departure reports. When predicting traffic flow, the current station of the vehicle is determined, and the stations that the vehicle may pass through are determined in the trajectory table containing path and time information to form a predicted vehicle route, and the arrival and departure times of the stations passed by the vehicle, the stay time at each station, and the interval running time between stations are determined to form a predicted vehicle arrival and departure time series and a predicted running time series. During the operation of the vehicle, the predicted vehicle route and the predicted vehicle arrival and departure time series are cyclically updated. The present invention provides a more accurate traffic flow prediction solution by constructing a trajectory table to cyclically predict the future running route and arrival and departure time series of the vehicle based on the current station and current time of the vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 This is one of the flow charts of the vehicle flow prediction method provided by the present invention.

[0017] Figure 2 This is the second flow chart of the traffic flow prediction method provided by the present invention.

[0018] Figure 3 This is the third flow chart of the traffic flow prediction method provided by the present invention.

[0019] Figure 4 This is the fourth flow chart of the traffic flow prediction method provided by the present invention.

[0020] Figure 5 It is a structural schematic diagram of the vehicle flow prediction device provided by the present invention.

[0021] Figure 6 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] Combine the following Figure 1-Figure 6 The vehicle flow prediction method, device, equipment, medium and computer program product of the present invention are described.

[0024] Figure 1 It is one of the flow charts of the traffic flow prediction method provided by the present invention, such as Figure 1 As shown, the method includes the following: Step 100: Collect vehicle operation information based on historical train arrival and departure reports; the vehicle operation information includes cargo category, departure station, final destination station, transit stations, and arrival and departure time of each transit station; Train arrival and departure reports refer to reports submitted by stations or vehicles when a train arrives at or leaves a station. Train arrival reports include information such as the station of arrival, arrival time, car number, vehicle model, the departure and destination stations of the train marshaling vehicles, and cargo categories; train departure reports include information such as the departure station, departure time, car number, vehicle model, the departure and destination stations of the train marshaling vehicles, and cargo categories. By collecting a certain number of train arrival and departure reports in history and associating all train arrival and departure reports of the vehicle's departure station, destination station, and transit stations, vehicle operation information is obtained. The vehicle operation information includes cargo categories, departure stations, destination stations, transit stations, and the arrival and departure time of each transit station.

[0025] Step 200: Perform statistical calculations based on the vehicle operation information to construct a trajectory table; each trajectory data in the trajectory table includes cargo category, departure station, final station, current station, next station, average stay time at current station, average interval running time from current station to next station, and probability; Based on the vehicle operation information obtained from the above analysis of the historical train arrival and departure reports, the vehicle operation information is statistically calculated to construct a trajectory table. The trajectory table contains a certain amount of trajectory data, where each trajectory data includes the cargo category, the departure station, the final station, the current station, the next station (of this station), the average stay time at this station, the average interval running time from this station to its next station, and the probability of the trajectory occurring in the historical data.

[0026] Step 300: Based on the departure station, current station, destination station, cargo category and the trajectory table of the vehicle to be predicted, the operation of the vehicle to be predicted is predicted to obtain a prediction result.

[0027] Obtain information such as the departure station, current station, final station, and cargo category of the vehicle to be predicted. Based on the trajectory table, predict the next station (of the current station) and its corresponding running time (including the stay time at the current station and the interval running time from the current station to the next station). Through cyclic judgment, predict future stations after the current station, and finally obtain the future running path of the vehicle and the arrival and departure time series, thereby realizing accurate prediction of traffic flow.

[0028] Based on the historical train arrival and departure reports, a trajectory table containing path and time information is constructed. When predicting traffic flow, the current station of the vehicle is determined, and the stations that the vehicle may pass through are determined in the trajectory table containing path and time information to form the predicted vehicle path. In addition, the arrival and departure times of the stations passed by the vehicle, the stay time at each station, and the interval running time between stations are determined to form the predicted vehicle arrival and departure time series and the predicted running time series. During the operation of the vehicle, the predicted vehicle path and the predicted vehicle arrival and departure time series are cyclically updated to finally obtain the traffic flow prediction result. The present invention provides a more accurate traffic flow prediction solution by constructing a trajectory table to cyclically predict the future running path and arrival and departure time series of the vehicle based on the current station and current time of the vehicle.

[0029] In one embodiment, the traffic flow prediction method provided in the embodiment of the present application may further include: Step 210: Based on an abnormal data elimination algorithm, an abnormal data elimination operation is performed on the arrival and departure times in the vehicle operation information, and the average stay time at the station, the average interval running time from the station to the next station, and the probability contained in the trajectory table are calculated; the abnormal data elimination algorithm includes a clustering algorithm.

[0030] Since the historical train arrival and departure reports are reported when the vehicle arrives or leaves the station, there may be abnormal data in them. The abnormal data may be the length of time the vehicle stays at the station, or the interval running time between adjacent stations. The cause of the data abnormality may be the vehicle scheduling problem at the station, or the maintenance problem of the interval line, or it may be a rare accident problem. In short, the occurrence of these abnormal situations will lead to abnormal data, which is reflected in the abnormally large station stay time and the interval running time between adjacent stations. Therefore, the abnormal data removal algorithm (such as clustering algorithm and discrete algorithm, etc.) is used to remove the abnormal data of the arrival and departure time in the vehicle operation information, and then the vehicle operation information after removing the abnormal data is calculated to obtain the average stay time at this station, the average interval running time from this station to its next station, and the probability contained in the trajectory table.

[0031] This embodiment eliminates the influence of abnormal data on the accurate calculation of time data and probability data through an abnormal data elimination algorithm.

[0032] Figure 2 FIG. 2 is a flow chart of the vehicle flow prediction method provided by the present invention. Figure 2 As shown, the method may also include: Step 310: Obtain the departure station, destination station and cargo category of the vehicle to be predicted; Step 320, obtaining the current time and the current station of the vehicle to be predicted; Step 330: if the current station is not the final station of the vehicle to be predicted, determine the next station of the current station, the stay time of the current station, and the interval running time from the current station to the next station based on the departure station, current station, final station, cargo category and the trajectory table of the vehicle to be predicted; Step 340: Calculate the departure time of the current station as the sum of the current time and the stay time of the current station, and the arrival time of the next station as the sum of the departure time of the current station and the interval running time; Step 350: add the next station of the current station to the predicted path station set, add the stay time of the current station and the interval running time to the predicted running time sequence; add the departure time of the current station and the arrival time of the next station to the predicted arrival and departure time sequence; Step 360: take the next station of the current station as the current station, take the arrival time of the next station as the current time, and return to the step of obtaining the current time and the current station of the vehicle to be predicted, until the current station is the final destination of the vehicle to be predicted, and obtain the vehicle predicted route and vehicle predicted arrival and departure time series.

[0033] The vehicle to be predicted in this embodiment is the vehicle ; The departure station of the vehicle to be predicted is The final destination of the vehicle to be predicted is ; The current time is , the current station is .exist In the case of, according to the trajectory table, determine the next station with the highest probability of the current station ,Will Add to the predicted route station collection In Then the historical average stay time of vehicles at the current station is taken as the The duration of stay , thereby predicting the departure time of the current station , then, the dwell time Add to forecast run time series (empty at initialization), that is , the departure time of the current station Add to forecast to send time series In .

[0034] Will , determine the vehicle Arrive at the next stop Time , is the current moment Add interval The running time between ,Right now , current station To its next stop The running time between The historical average running time of the vehicle in this interval can be taken. Then Add to forecast run time series In ,Will Add to forecast to send time series In Then ; , continue the above cycle. Finally, the current station is the final destination of the vehicle to be predicted ( ), the traffic flow prediction result is output, that is, the vehicle prediction path And predict the time series .

[0035] This embodiment provides a more accurate traffic flow prediction solution by cyclically predicting the vehicle's future running path and arrival and departure time sequence based on the vehicle's current station and current time.

[0036] Figure 3 FIG. 3 is a flow chart of the vehicle flow prediction method provided by the present invention. Figure 3 As shown, the method may also include: Step 331: Determine the next station with the highest probability of the current station in the trajectory table as the next station of the current station; Step 332: Based on the trajectory table, determine the average stay time of the current station as the stay time of the current station; Step 333: Based on the trajectory table, determine the average interval running time from the current station to the next station as the interval running time from the current station to the next station.

[0037] In the above embodiment, the basis for determining the next station of the current station can be based on probability, that is, the next station with the highest probability of determining the current station is the next station of the current station; the basis for determining the stay time of the current station can be based on average value calculation, that is, the historical average stay time of the current station is determined as the stay time of the current station; the basis for determining the interval running time from the current station to its next station can also be based on average value calculation, that is, the historical average interval running time from the current station to its next station is the interval running time from the current station to its next station. The traffic flow prediction method provided in this application retains other calculation methods for calculating the next station, the stay time of the current station, and the interval running time from the current station to its next station through the data contained in the trajectory table.

[0038] This embodiment analyzes and calculates the trajectory table to accurately determine the next station of the current station, the stay time at the current station, and the interval running time from the current station to the next station.

[0039] Figure 4 FIG. 4 is a flow chart of the vehicle flow prediction method provided by the present invention. Figure 4 As shown, the method may also include: Step 400: receiving the arrival or departure information of the vehicle to be predicted; the arrival or departure information includes the station and the arrival or departure time of the station; Step 500: When the station is the final destination station, the predicted vehicle route and the predicted vehicle arrival and departure time series are the prediction results; Step 600: if the station is not the final destination station, determine whether the station is in the predicted path station set; Step 700: When the station is in the predicted path station set, update the predicted arrival and departure time series based on the arrival or departure time of the station and the predicted operation time series.

[0040] The vehicle flow prediction method provided in the embodiment of the present application may further include: Step 800: When the station is not in the predicted route station set, take the station as the current station of the vehicle to be predicted, and the arrival or departure time of the station as the current time, reset the predicted route station set, the predicted operation time series and the predicted arrival and departure time series, and return to the step of obtaining the current time and the current station of the vehicle to be predicted.

[0041] After the predicted vehicle route and the predicted vehicle arrival and departure time series are obtained, during the actual operation of the predicted vehicle, the arrival or departure information reported by the station where the predicted vehicle passes is received. The arrival or departure information includes the station and the arrival or departure time of the station. Then the station is judged and the station is reported. If it is not the final destination of the vehicle to be predicted, determine the station Whether to meet at the predicted route station If the station Meet at the predicted route station , then based on the predicted vehicle at the station Arrival or departure time , in the forecasting run time series Based on this, update the forecast to the time series.

[0042] At the reporting station If it is the final destination of the vehicle to be predicted, it means that the vehicle to be predicted has arrived at the final destination and the prediction is terminated.

[0043] At the station If it is not in the predicted path station set, the predicted path station set obtained by the above prediction is explained Wrong, change the station As the current station of the vehicle to be predicted, , and returns the execution steps of the above loop prediction.

[0044] This embodiment updates the above-obtained prediction result through the arrival and departure report of the train to be predicted, thereby achieving the real-time and accuracy of the traffic flow prediction.

[0045] The traffic flow prediction device provided by the present invention is described below. The traffic flow prediction device described below and the traffic flow prediction method described above can be referenced to each other.

[0046] Please refer to Figure 5 The present invention also provides a vehicle flow prediction device, comprising: The vehicle operation information collection module 501 is used to collect vehicle operation information based on historical train arrival and departure reports; the vehicle operation information includes cargo category, departure station, final arrival station, transit stations, and arrival and departure time of each transit station; The trajectory table construction module 502 is used to perform statistical calculations based on the vehicle operation information to construct a trajectory table; each trajectory data in the trajectory table includes cargo category, departure station, final station, current station, next station, average stay time at current station, average interval running time from current station to its next station, and probability; The traffic flow prediction module 503 is used to predict the operation of the vehicle to be predicted based on the departure station, current station, final station, cargo category and the trajectory table of the vehicle to be predicted to obtain a prediction result.

[0047] Optionally, the traffic flow prediction module includes: A first acquisition unit is used to acquire the departure station, the final destination station and the cargo category of the vehicle to be predicted; A second acquisition unit, used to acquire the current time and the current station of the vehicle to be predicted; A first determining unit is used to determine the next station of the current station, the stay time of the current station, and the interval running time from the current station to the next station based on the departure station, the current station, the final station, the cargo category and the track table of the vehicle to be predicted, when the current station is not the final station of the vehicle to be predicted; A time calculation unit, used to calculate the departure time of the current station as the sum of the current time and the stay time of the current station, and the arrival time of the next station as the sum of the departure time of the current station and the interval running time; A data set adding unit, used to add the next station of the current station to the predicted path station set, add the stay time of the current station and the interval running time to the predicted running time sequence; add the departure time of the current station and the arrival time of the next station to the predicted arrival and departure time sequence; A cyclic prediction unit is used to take the next station of the current station as the current station, take the arrival time of the next station as the current time, and return to the step of obtaining the current time and the current station of the vehicle to be predicted, until the current station is the final arrival station of the vehicle to be predicted, and obtain the vehicle prediction route and the vehicle prediction arrival and departure time series.

[0048] Optionally, the first determining unit includes: A next station determination unit, configured to determine the next station with the highest probability of the current station in the trajectory table as the next station of the current station; a dwell time determination unit, configured to determine, based on the trajectory table, an average dwell time of the current station as the dwell time of the current station; The interval running time determining unit is used to determine, based on the trajectory table, the average interval running time from the current station to the next station as the interval running time from the current station to the next station.

[0049] Optionally, the vehicle flow prediction device further includes: An arrival or departure information receiving module, used to receive the arrival or departure information of the vehicle to be predicted; the arrival or departure information includes a station and the arrival or departure time of the station; A prediction result determination module, for determining, when the station is the final destination station, the predicted vehicle path and the predicted vehicle arrival and departure time series as the prediction result; A station determination module, used for determining whether the station is in the predicted path station set when the station is not the final destination station; The predicted arrival and departure time series updating module is used to update the predicted arrival and departure time series based on the arrival or departure time of the station and the predicted operation time series when the station is in the predicted path station set.

[0050] Optionally, the vehicle flow prediction device further includes: A cyclic prediction module is used to, when the station is not in the predicted route station set, take the station as the current station of the vehicle to be predicted, and the arrival or departure time of the station as the current time, reset the predicted route station set, the predicted operation time series and the predicted arrival and departure time series, and return to the step of obtaining the current time and the current station of the vehicle to be predicted.

[0051] Optionally, the trajectory table construction module includes: The abnormal data elimination unit is used to perform abnormal data elimination operations on the arrival and departure times in the vehicle operation information based on the abnormal data elimination algorithm, and calculate the average stay time at the station, the average interval running time from the station to the next station, and the probability contained in the trajectory table; the abnormal data elimination algorithm includes a clustering algorithm.

[0052] Figure 6 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 6 As shown, the electronic device may include: a processor 610, a communication interface 620, a memory 630 and a communication bus 640, wherein the processor 610, the communication interface 620 and the memory 630 communicate with each other through the communication bus 640. The processor 610 may call the logic instructions in the memory 630 to execute the vehicle flow prediction method, which includes: collecting vehicle operation information based on historical train arrival and departure reports; the vehicle operation information includes cargo category, departure station, terminal station, passing station, and arrival and departure time of each passing station; performing statistical calculation based on the vehicle operation information to construct a trajectory table; each trajectory data in the trajectory table includes cargo category, departure station, terminal station, current station, next station, average stay time at this station, average interval running time from this station to its next station, and probability; based on the departure station, current station, terminal station, cargo category and the trajectory table of the vehicle to be predicted, predicting the operation of the vehicle to be predicted to obtain a prediction result.

[0053] In addition, the logic instructions in the above-mentioned memory 630 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0054] On the other hand, the present invention also provides a computer program product, which includes a computer program, and the computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the traffic prediction method provided by the above methods, and the method includes: collecting vehicle operation information based on historical train arrival and departure reports; the vehicle operation information includes cargo category, departure station, destination station, transit station, and arrival and departure time of each transit station; performing statistical calculations based on the vehicle operation information to construct a trajectory table; each trajectory data in the trajectory table includes cargo category, departure station, destination station, current station, next station, average stay time at this station, average interval running time from this station to its next station, and probability; based on the departure station, current station, destination station, cargo category and the trajectory table of the vehicle to be predicted, the operation of the vehicle to be predicted is predicted to obtain a prediction result.

[0055] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the traffic prediction method provided by the above-mentioned methods, the method comprising: collecting vehicle operation information based on historical train arrival and departure reports; the vehicle operation information includes cargo category, departure station, destination station, transit station, and arrival and departure time of each transit station; performing statistical calculations based on the vehicle operation information to construct a trajectory table; each trajectory data in the trajectory table includes cargo category, departure station, destination station, current station, next station, average stay time at this station, average interval running time from this station to its next station, and probability; based on the departure station, current station, destination station, cargo category and the trajectory table of the vehicle to be predicted, predicting the operation of the vehicle to be predicted to obtain a prediction result.

[0056] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0057] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0058] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A traffic flow prediction method, characterized in that: include: Collect vehicle operation information based on historical train arrival and departure reports; The vehicle operation information includes the cargo category, the departure station, the final destination station, the transit stations, and the departure and arrival time of each transit station; Perform statistical calculations based on the vehicle operation information to construct a trajectory table; each trajectory data in the trajectory table includes cargo category, departure station, final station, current station, next station, average stay time at current station, average interval running time from current station to next station, and probability; Based on the departure station, current station, final station, cargo category and the trajectory table of the vehicle to be predicted, the operation of the vehicle to be predicted is predicted to obtain a prediction result.

2. The traffic flow prediction method according to claim 1, characterized in that: The step of predicting the operation of the vehicle to be predicted based on the departure station, current station, final station, cargo category and the trajectory table of the vehicle to be predicted to obtain a prediction result includes: Obtain the departure station, final destination station and cargo category of the vehicle to be predicted; Obtaining the current time and the current station of the vehicle to be predicted; In the case that the current station is not the final station of the vehicle to be predicted, based on the departure station, current station, final station, cargo category and the trajectory table of the vehicle to be predicted, the next station of the current station, the stay time of the current station and the interval running time from the current station to the next station are determined; The departure time of the current station is calculated as the sum of the current time and the stay time of the current station, and the arrival time of the next station is calculated as the sum of the departure time of the current station and the interval running time; Add the next station of the current station to the predicted path station set, add the stay time of the current station and the interval running time to the predicted running time sequence; add the departure time of the current station and the arrival time of the next station to the predicted arrival and departure time sequence; The next station of the current station is taken as the current station, the arrival time of the next station is taken as the current time, and the step of obtaining the current time and the current station of the vehicle to be predicted is returned to until the current station is the final destination of the vehicle to be predicted, and the vehicle prediction route and the vehicle prediction arrival and departure time series are obtained.

3. The traffic flow prediction method according to claim 2, characterized in that: The step of determining the next station of the current station, the stay time of the current station, and the interval running time from the current station to the next station based on the departure station, the current station, the final station, the cargo category, and the trajectory table of the vehicle to be predicted includes: Determine the next station with the maximum probability of the current station in the trajectory table as the next station of the current station; Based on the trajectory table, determining the average stay time of the current station as the stay time of the current station; Based on the trajectory table, the average interval running time from the current station to the next station is determined as the interval running time from the current station to the next station.

4. The traffic flow prediction method according to claim 2, characterized in that: The method predicts the operation of the vehicle to be predicted based on the departure station, current station, final station, cargo category and the trajectory table of the vehicle to be predicted to obtain a prediction result, and then includes: Receiving arrival or departure information of the vehicle to be predicted; the arrival or departure information includes a station and the arrival or departure time of the station; In the case where the station is the final destination, the vehicle predicted route and the vehicle predicted arrival and departure time series are the prediction results; In the case where the station is not the final station, determining whether the station is in the predicted path station set; In the case where the station is in the predicted path station set, the predicted arrival and departure time series is updated based on the arrival or departure time of the station and the predicted operation time series.

5. The method for predicting traffic flow according to claim 4, characterized in that: In the case where the station is not the final station, determining whether the station is in the predicted path station set, then comprising: When the station is not in the predicted route station set, the station is taken as the current station of the vehicle to be predicted, and the arrival or departure time of the station is taken as the current time. The predicted route station set, the predicted operation time series and the predicted arrival and departure time series are reset, and the step of obtaining the current time and the current station of the vehicle to be predicted is returned.

6. The traffic flow prediction method according to claim 1, characterized in that: The performing statistical calculation based on the vehicle operation information to construct a trajectory table includes: Based on the abnormal data elimination algorithm, the abnormal data elimination operation is performed on the arrival and departure times in the vehicle operation information, and the average stay time at the station, the average interval running time from the station to the next station, and the probability contained in the trajectory table are calculated; the abnormal data elimination algorithm includes a clustering algorithm.

7. A vehicle flow prediction device, characterized in that: include: The vehicle operation information collection module is used to collect vehicle operation information based on historical train arrival and departure reports; The vehicle operation information includes the cargo category, the departure station, the final destination station, the transit stations, and the departure and arrival time of each transit station; A trajectory table construction module is used to perform statistical calculations based on the vehicle operation information to construct a trajectory table; each trajectory data in the trajectory table includes cargo category, departure station, final station, current station, next station, average stay time at current station, average interval running time from current station to its next station, and probability; The traffic flow prediction module is used to predict the operation of the vehicle to be predicted based on the departure station, current station, final station, cargo category and the trajectory table of the vehicle to be predicted to obtain a prediction result.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the traffic flow prediction method according to any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the traffic flow prediction method according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the traffic flow prediction method according to any one of claims 1 to 6 is implemented.

Images