CN113470364A - Bus scheduling method and system based on artificial intelligence and big data - Google Patents
Bus scheduling method and system based on artificial intelligence and big data Download PDFInfo
- Publication number
- CN113470364A CN113470364A CN202111022049.3A CN202111022049A CN113470364A CN 113470364 A CN113470364 A CN 113470364A CN 202111022049 A CN202111022049 A CN 202111022049A CN 113470364 A CN113470364 A CN 113470364A
- Authority
- CN
- China
- Prior art keywords
- bus
- station
- stop
- route
- departure
- 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 33
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 24
- 238000012216 screening Methods 0.000 claims abstract description 9
- 239000000126 substance Substances 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 5
- 238000005516 engineering process Methods 0.000 abstract description 3
- 238000001514 detection method Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 238000006243 chemical reaction Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000002354 daily effect Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/20—Monitoring the location of vehicles belonging to a group, e.g. fleet of vehicles, countable or determined number of vehicles
Landscapes
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- Analytical Chemistry (AREA)
- Marketing (AREA)
- Chemical & Material Sciences (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Primary Health Care (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to the technical field of artificial intelligence and big data, in particular to a bus dispatching method and a system based on artificial intelligence and big data, which comprises the following steps: the target route and all stops on the target route are selected, the time period of the current bus departure to reach each stop is obtained by means of a big data technology, and then the traffic pressure value of each stop is calculated, so that the score of the target route is determined. And matching and screening all stops and all bus routes on the target route, wherein the stops and all bus routes are larger than a set pressure threshold value, so that the alternative route of each stop is obtained, and the score of the target route is updated accordingly. And finally, determining the bus schedule of the current departure time period on the target route. According to the invention, the intelligent dispatching of the bus route is realized, and the accuracy of bus dispatching is improved, so that the traffic pressure of the route stop with a larger traffic pressure value is relieved, and the traffic resources are saved to a certain extent.
Description
Technical Field
The invention relates to the technical field of artificial intelligence and big data, in particular to a bus scheduling method and system based on artificial intelligence and big data.
Background
With the rapid development of the economy of China, the construction of cities is changing day by day and the population of the cities is increasing year by year, more pressure is brought to the traffic system of the cities, and the urban traffic problem becomes one of the key problems in the development of many cities. Compared with private cars, the urban public transport has the advantages of large passenger capacity, less relative investment, less occupied resources, high efficiency and the like, and buses in the urban public transport are transportation means with higher use frequency in daily life of people.
Because the population is concentrated in the city and the urban traffic is relatively congested, the bus is used as a main vehicle in the city and plays an extremely important role in relieving the urban traffic pressure. In order to meet the traveling needs of citizens and improve the traveling efficiency, the bus needs to be scheduled at the time of traffic pressure peak.
At present, bus scheduling is usually a hard index, namely, each bus must complete corresponding target lap number regardless of traffic pressure of a route every day. For example, in rush hours, a certain number of buses are fixedly scheduled to relieve traffic pressure, and if the scheduled buses are not fully utilized, traffic resources are wasted to a certain extent; if the number of dispatched vehicles is small, the traffic pressure cannot be sufficiently relieved. Therefore, the existing mode is not accurate enough, and the scheduling accuracy is poor.
Disclosure of Invention
The invention aims to provide a public transport scheduling method and system based on artificial intelligence and big data, which are used for solving the problem that the conventional public transport scheduling mode is inaccurate.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows: the invention provides a bus scheduling method based on artificial intelligence and big data, which comprises the following steps:
selecting a target route from all bus routes, and acquiring each stop on the target route, the required driving time between any two stops and the number of passengers getting on and off each stop in each time period;
predicting the time period of the current bus departure to each stop and the traffic pressure value at each stop according to the required driving time between any two stops on the target route and the number of people getting on or off the bus at each stop in each time period;
determining a target route score of the bus shift of the current departure according to the predicted traffic pressure value of the bus shift of the current departure at each stop;
if the score of the target route of the current bus departure is larger than a set score threshold, respectively judging whether the traffic pressure value of the current bus departure at each stop is larger than a set pressure threshold, and obtaining each stop of which the target route is larger than the set pressure threshold;
acquiring all bus routes which can be replaced at each stop and are greater than a set pressure threshold according to the predicted time period for the bus which is sent out currently to reach each stop;
updating the traffic pressure values of the current bus departure at the stations which are larger than the set pressure threshold according to the traffic pressure values of all the alternative routes at the corresponding stations which are larger than the set pressure threshold;
and recalculating the target route score of the current bus departure time according to the updated traffic pressure value of the current bus departure time at each stop, and determining the bus dispatching time of the current departure time period on the target route according to the recalculated target route score.
Further, the time period when the current bus departure shift reaches each stop and the traffic pressure value at each stop are predicted, and the specific steps comprise:
calculating the traffic pressure value of the current bus departure at the first stop according to the number of passengers getting on and off the first stop at the current bus departure time period;
predicting the time period of the current bus departure to the next stop according to the time period of the current bus departure to the previous stop, the number of people getting on or off the bus in the time period of the current bus departure to the previous stop, the traffic pressure value of the previous stop and the required driving time from the previous stop to the next stop; predicting the number of passengers getting on and off corresponding to the next stop in the time period according to the predicted time period when the bus which is sent out currently arrives at the next stop; and predicting the traffic pressure value of the next stop according to the traffic pressure value of the current departure bus at the previous stop and the predicted number of passengers getting on and off the next stop in the time period.
Further, the time period for predicting the bus shift of the current departure to reach each stop and the corresponding calculation formula of the traffic pressure value at each stop are as follows:
wherein the content of the first and second substances,is at the firstThe traffic pressure value of each station is set,for the current bus departureTime period of each site is inThe traffic pressure value of each station is set,for the current bus departureThe time period of each station is,is as followsFrom station to stationThe travel time required for each station is,is as followsThe lower-vehicle heat value of each station,is as followsThe heat value of getting-on of the vehicle at each station,=,,is as followsStation in time slotThe corresponding number of the people getting off the bus,is as followsStation in time slotThe corresponding number of the passengers getting on the bus,the number of seats on the bus shift from which the bus is currently dispatched,is as followsThe lower-vehicle heat value of each station,is as followsThe heat value of getting-on of the vehicle at each station,=,,is as followsStation in time slotThe corresponding number of the people getting off the bus,is as followsStation in time slotThe corresponding number of the passengers getting on the bus,the time coefficient of getting on and off the vehicle is,for the length of time of each time segment,presentation pairRounding down is performed.
The pressure value of the previous station is larger, the higher the pressure value of the previous station is, the more crowded the vehicle is, the corresponding time coefficient isThe larger.
Further, the expression of the time coefficient for getting on and off is:
wherein the content of the first and second substances,the time coefficient of getting on and off the vehicle is,is at the firstTraffic pressure values for individual stations.
Further, the step of acquiring all the alternative bus routes of each stop which are greater than the set pressure threshold comprises the following steps:
for the second time greater than the set pressure thresholdA station acquiring the data passing through the firstAll bus routes of each stop, wherein the target routes are not included in all the bus routes;
acquiring the driving time required by any two stops on each bus route in all bus routes and the number of passengers getting on and off each stop in each time period;
predicting the arrival of each bus on each bus route in all bus routes in the first bus shift according to the required driving time between any two stops on each bus route in all bus routes and the number of passengers getting on and off each stop in each time periodTime period of individual site and inTraffic pressure values for individual stations;
determining a preliminary alternative bus route from all bus routes, wherein the preliminary bus route of the preliminary alternative bus route reaches the first bus shiftThe time period of each station and the arrival number of bus shifts of the current departure on the target lineThe time periods of the stations are the same;
calculating the coincidence degree of each bus route in the preliminary planned alternative bus routes and the target route, and screening out the bus routes with the coincidence degree of the target route being greater than a set coincidence degree threshold value from the preliminary planned alternative bus routes;
judging whether the screened coincidence degree is greater than the preset coincidence degree threshold value or notAnd (4) whether the traffic pressure value of each station is greater than a set pressure threshold value or not, and taking the bus route smaller than the set pressure threshold value as a final bus route capable of being replaced.
Further, the step of calculating the contact ratio of each bus route in the preliminary bus routes to the target route comprises the following steps:
on the target line atEach station behind each station is used as a circle center, a circle is drawn by taking a set distance as a radius, and the circle corresponding to each station on the target line is used as the coincidence range of the station;
obtaining each bus route in the preliminary alternative bus routes on the second placeEach station behind each station and judging whether each bus route is on the first stationWhether each station behind each station is positioned in the overlapping range or not is judged, and the position of each bus route is the first positionThe number of all stations located in the overlapping range after the station is taken as the number of the stationThe coincidence degree of the bus route and the target route at each station.
Further, the formula for updating the traffic pressure value of the current bus departure at each stop point which is greater than the set pressure threshold value is as follows:
wherein the content of the first and second substances,is the first after updateThe traffic pressure value of each station is set,is the first before updateThe traffic pressure value of each station is set,is as followsThe number of all alternative bus routes for each stop,is as followsBus route capable of replacing bus stopThe degree of coincidence with the target route,in order to set the pressure threshold value,is as followsBus route capable of replacing bus stopIn the first placeThe traffic pressure value of each station is set,for the current bus departureTime period of each site.
Further, the calculation formula corresponding to the bus dispatching shift of the current departure time period on the target line is determined as follows:
wherein the content of the first and second substances,the number of shifts to be scheduled for the bus,for the score of the recalculated target route,in order to set the pressure threshold value,for the time period when the current bus shift of departure arrives at the first stop,is a pair ofRounding down is performed.
Further, the maximum value of the traffic pressure value of the current bus departure at each stop is used as the target route score of the current bus departure.
The invention also provides a bus dispatching system based on artificial intelligence and big data, which comprises a processor and a memory, wherein the processor is used for processing the instructions stored in the memory so as to realize the bus dispatching method based on artificial intelligence and big data.
The invention has the following beneficial effects:
according to the method, a target route and each stop on the target route are selected from all bus routes, and the traffic pressure value and the target route score of each stop on the target route are obtained according to the running time of any two stops on the target route and the number of passengers getting on and off each stop. And selecting corresponding alternative routes for all the stations with the traffic pressure values larger than the set pressure threshold. And updating the score of the target route according to the information of the alternative route so as to determine the dispatching result of the bus.
When the bus shift of the current departure is sent out, the traffic pressure value of each stop is closely related to the traffic states of all the stops, so the traffic pressure value of the bus shift reaching each stop is predicted by using the number of people getting on or off the bus at each stop in each time period, wherein each stop comprises an initial stop. Meanwhile, the influence condition of the traffic pressure value of the starting station and the replaceable public traffic route of each station with larger traffic pressure value on the traffic pressure value of the station is fully considered, so that more accurate traffic pressure value of each station is obtained, the bus dispatching shift is determined by using the more accurate traffic pressure value, the influence of the replaceable route on the traffic pressure value of each station is fully considered, the dispatching is more accurate, the traffic pressure is effectively relieved, and meanwhile, the waste of traffic resources is also avoided.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart 1 of a bus dispatching method based on artificial intelligence and big data according to the present invention;
fig. 2 is a system flow chart 2 of the bus scheduling method and system based on artificial intelligence and big data of the present invention.
Detailed Description
To further explain the technical means and effects of the present invention adopted to achieve the predetermined objects, the following detailed description of the embodiments, structures, features and effects of the technical solutions according to the present invention will be given with reference to the accompanying drawings and preferred embodiments.
The embodiment provides a public transportation scheduling method based on artificial intelligence and big data, as shown in fig. 1 and 2, the specific steps are as follows:
step (ii) of: and selecting a target route from all bus routes, and acquiring each stop on the target route, the required driving time between any two stops and the number of people getting on or off the bus at each time period at each stop.
The main purpose of the step is to obtain some parameters in advance by using an experimental and statistical method, wherein the parameters are needed to be used in the process of realizing intelligent bus dispatching and comprise: the target route, each station on the target route, the required driving time of any two stations and the number of people getting on or off the bus at each station in each time period. The following describes in detail the method for acquiring the number of people getting on or off the bus at each station in each time slot in the target route, and the specific steps are as follows:
step (ii) of: first, a target bus traveling along a target route is found using a monitoring camera. The monitoring camera acquires an RGB image of each station on the target line, wherein the RGB image refers to an image represented by different proportions of each pixel R (red), G (green) and B (blue) of a color image. The RGB image of each station is converted into the HSV color space, and the HSV color space has a larger effect when used for color segmentation of the designated image, and is more suitable for judging whether the target bus appears in the image.
In the process of converting the RGB image into the HSV color space, the HSV color space model used represents hue (H), saturation sum (S), and lightness (V), and in the RGB image, three components of red (R), green (G), and blue (B) are represented. In the conversion process, the maximum value of the three components is set to be MAX, the minimum value is set to be MIN, and the conversion formula from RGB to HSV is as follows:
as can be seen from the above conversion formula, the hue (H) ranges from 0 degree to 360 degrees, and the saturation (S) and lightness (V) values range from 0 to 1. When in useWhen the color (H) channel is pure gray, no color information exists; when in useWhen the temperature of the water is higher than the set temperature,indicating no color. The component value is artificially set according to the prior knowledge and the scene needs. The conversion formula from RGB to HSV is a well-known formula, and the reasoning process is not described herein again.
After the RGB image of each station is converted into the HSV color space, thresholds of three channels are manually set according to priori knowledge, wherein the thresholds of the three channels refer to the set threshold of H, S, V, and the LED lamp image of the bus can be segmented. The segmented LED light image reflects current bus information, i.e., the number of bus routes along the target route, e.g., 1, 2, 3, B1, B2, S108, S109, etc. And matching the segmented LED image with a template in a database to judge whether the current bus is a target bus, wherein the target bus refers to a bus along a target route. Since template matching is a prior art, it is not described herein in detail.
The purpose of the above steps is to identify the bus of the target route in the image, and a specific implementation manner is given, and those skilled in the art can also adopt other manners when the above purpose is achieved.
Step (ii) of: and then, shielding an irrelevant working condition by using a target detection network CenterNet technology, wherein the irrelevant working condition is to shield the background outside a bus area, so that the influence on the detection of the number of people getting on or off the bus subsequently is avoided. When the target vehicle appears in the monitoring camera, the acquired RGB image is input into the trained target detection network CenterNet to obtain the center coordinates of the bus door enclosure frameAnd length and width dimensions. The RGB image is cut by the enclosing frame, so that the purpose of shielding the number of people getting on or off the bus in a follow-up state under an irrelevant working condition is achieved. The target detection network centret, its training process, and the specific process of identifying a target by using the trained network are well known in the art, and are not described herein.
Step (ii) of: and finally, judging the number of people getting on or off the bus by detecting key points on the heads of the passengers. The steps are as followsInputting the cut picture into human body key point detection network, outputting Heatmap of human body head key pointAnd the function processing obtains the position information of the key point. Detecting the key points of the head by using an optical flow method to obtain the motion information of personnel, and specifying the motion direction to point to the central point of the vehicle door surrounding frameThe person getting on the bus or the person getting off the bus. The human body key point detection network can be an existing openpos network, which is a known technology and is not described herein again.
Summarizing the above stepsAnd carrying out image recognition on each stop of all bus routes by using the monitoring camera, and judging whether the segmented image is a bus along the target route according to the image recognition. Then, background factors that may affect the detection of the number of persons getting on and off need to be excluded. And finally, detecting the specific numerical value of the number of passengers getting on the bus and the specific numerical value of the number of passengers getting off the bus at each station of the target route in any period of time by using the key point information of the heads of the passengers. Thereby, canThe number of passengers getting on or off the bus at each stop in any period of time on all bus routes is detected, a plurality of time periods are set manually, then the number of passengers getting on or off the bus at each stop in each set time period can be determined by utilizing a big data statistics mode, and the determined number of passengers getting on or off the bus at each stop in each time period is stored in a corresponding database.
Step (ii) of: according to the driving time required by any two stops on the target route and the number of people getting on or off the bus at each stop in each time period, the time period when the current bus departure time reaches each stop and the traffic pressure value at each stop are predicted, and the specific steps are as follows:
step (ii) of: and calculating the traffic pressure value of the current bus departure at the starting station according to the number of passengers getting on and off the starting station at the current bus departure time period.
And calculating from the starting station to obtain the traffic pressure value of each station. The starting station is not influenced by other stations, and the departure time periodLower its traffic pressure valueThe difference between the getting-on heat and the getting-off heat of the personnel at the current station is as follows:
wherein the content of the first and second substances,is the traffic pressure value of the starting station,for the time period of departureThe heat of boarding of the passengers at the starting station,=,is a starting stationThe number of the passengers getting on the bus in the time period,the number of seats on the bus,for the time period of departureThe degree of heat of alighting of passengers at the starting station,,is a starting stationThe number of people getting off in the time period,,the length of time of each time segment corresponds to a value as a function of time.
Step (ii) of: according to the time period of the current departure bus to the starting station, the number of people getting on or off the bus in the time period of the current departure bus, the traffic pressure value of the starting station and the required driving time from the starting station to the next station, the time period of the current departure bus to the next station is predicted, and the specific implementation calculation formula is as follows:
wherein the content of the first and second substances,respectively the time periods of the bus arriving at the initial station and the current station, the unit is。The time required for the bus to travel from the initial station to the current station is given in units of。The time taken for passengers to get on or off the bus at the initial station is given by。For the time length of each time segmentHere, the 。In order to round the symbol down,for the getting on and off time coefficient, the corresponding expression is:
wherein the content of the first and second substances,the time coefficient of getting on and off the vehicle is,is at the firstTraffic pressure values for individual stations. The train getting-on and getting-off coefficient reflects the time of the passengers getting on and off the train, is a piecewise function and is directly given by the personnel in the industry according to experience and related to the pressure value of the previous station, the larger the pressure value of the previous station is, the more crowded the train is, the corresponding pressure valueThe larger.
Step (ii) of: predicting the number of passengers getting on and off the next stop in the time period according to the predicted time period when the bus which is sent out currently arrives at the next stop; predicting the traffic pressure value at the next stop according to the traffic pressure value at the previous stop of the current bus departure shift and the predicted number of passengers getting on and off at the next stop in the time period, and realizing the following calculation formula:
for the next stationThe traffic pressure value of (a) is,time period for previous stationThe traffic pressure value of (a) is,for the getting-off heat of the passenger at the latter station,the passenger getting on the bus at the latter station.
Step (ii) of: and predicting the time period of the current bus departure to the next stop according to the time period of the current bus departure to the previous stop, the number of people getting on or off the bus in the time period of the current bus departure to the previous stop, the traffic pressure value of the previous stop and the required driving time from the previous stop to the next stop. Predicting the number of passengers getting on and off the next stop and the traffic pressure value of the previous stop according to the time period for predicting the arrival of the current bus departure at the next stop, and obtaining the traffic pressure value of the next stop, wherein the concrete implementation formula is as follows:
wherein the content of the first and second substances,is at the firstThe traffic pressure value of each station is set,is at the firstThe traffic pressure value of each station is set,is as followsThe lower-vehicle heat value of each station,is as followsThe heat value of getting-on of the vehicle at each station,=,,is as followsStation in time slotThe corresponding number of the people getting off the bus,is as followsStation in time slotThe corresponding number of the passengers getting on the bus,the number of seats on the current bus shift of departure;for the current bus departureThe time period of each station is,for the current bus departureThe time period of each station is,is as followsFrom station to stationThe travel time required for each station is,the time coefficient of getting on and off the vehicle is,is as followsThe lower-vehicle heat value of each station,is as follows-a boarding heating value of 1 station,=,,the number of seats on the bus shift from which the bus is currently dispatched,for the time length of each time segment, is based on the stepsDetermined by the length of time of the artificially set time period),presentation pairRounding down is performed.
Here, the current departure bus shift arrival number is calculated asTime period of each siteThe calculation formula (c) is explained as follows: and according to the time periods of all the stops counted by the big data, dividing the time into different time periods by using the set time length of each time period, thereby judging which time period the current bus departure time is in when the current bus departure time arrives at the next stop.To divide the time length of each time segment, the time to the next station is in which time segment should be rounded down, and the rounding down is to ensure the accuracy of calculating the time segment to the next station. By usingIt can be determined that the time required for the previous station to reach the next station has moved by several time periods.
For example, time periods 5:00-5:30, 5:30-6:00, 6:00-6:30 … … are respectively taken as time period 1, time period 2, and time period 3 … …, whenAnd =30 min. Then the data is stored according to the corresponding number of persons getting on and off the bus in time period 1, time period 2 and time period 3 … …. If the current bus shift arrives the firstThe time period of each station is time period 1, and the time period is calculated=32min, at this timeI.e. only one time period, i.e. time period 2, has to be moved from time period 1. Therefore, the time slot 2 is the arrival of the current bus shiftTime period of each site.
Step (ii) of: and determining the target route score of the bus shift of the current departure according to the predicted traffic pressure value of the bus shift of the current departure at each stop.
Based on the stepsCalculating a target route score of the current bus departure time based on the traffic pressure values of the stations on the target route obtained by the basis, wherein the calculation method of the target route score comprises the following steps:
wherein the content of the first and second substances,the number of the bus stations is the number of the bus stations,as the traffic pressure value of each station,indicating a period of timeAnd scoring the target route when the vehicle is sent.
Step (ii) of: according to the stepsAnd judging the obtained target route score, if the target route score of the current bus departure time is greater than a set score threshold value, respectively judging whether the traffic pressure value of the current bus departure time at each stop is greater than a set pressure threshold value, and obtaining each stop of which the target route is greater than the set pressure threshold value.
The purpose of the step is to obtain the stations with larger traffic pressure values, and form a setSubsequently, will pair the setsThe sites within are analyzed one by one. The specific implementation mode is as follows: the traffic pressure value of each station obtained in the steps is compared with an empirical threshold valueComparing, will be greater than a thresholdSite entry set of. It should be noted that, in the following description,to be an empirical threshold, the implementer may set according to urban traffic needs.
Step (ii) of: and acquiring all alternative bus routes of all stops smaller than a set pressure threshold according to the predicted time period for the bus which is sent out currently to reach each stop.
The purpose of this step is to obtain a collectionAnd the alternative routes of each stop can relieve the traffic pressure value of the target route at the current stop. Mainly, the influence of the alternative route on the traffic pressure value of the station on the target route is considered, the accuracy of the traffic pressure value and the accuracy of bus scheduling are ensured, and the specific implementation method comprises the following steps:
step (ii) of: and screening all bus routes for the first time. First-come-from collectionRandomly selecting a site for analysis, and recording the site as. Then, the passing sites are screened out from the databaseThe bus route does not include the target route. Finally, an alternative route that was preliminary screened for the first time can be obtained.
Step (ii) of: and screening the primary alternative routes screened in the previous step again. Predicting the arrival of each bus on each bus route in all bus routes in the first bus shift according to the required driving time between any two stops on each bus route in all bus routes and the number of passengers getting on and off each stop in each time periodTime period of each site. In order to guarantee the travel time of passengers, the screened routes and the target route must arrive at the stationThe time periods are the same, all the preliminary alternative routes of the same time period are reserved and recorded as an alternative route set。
Step (ii) of: set of alternative routes screened out for the previous stepScreening was performed again. Calculating a set of alternative bus routesThe coincidence degree of each bus route and the target route in the system is collected from the alternative routesAnd screening out the bus route with the coincidence degree with the target route larger than a set coincidence degree threshold value.
The specific screening steps are as follows, the invention considers that when the straight-line distance between two stations is less than a certain valueA time, i.e. a passenger arriving from one station to another in a short time, indicates that the two stations have a certain overlap.The determination of the value is related to the traffic convenience degree of the city, and the implementer sets a proper threshold value according to different cities.
Target route is located at stationAll sites thereafter are recorded as a setSet ofEach bus route is at the stationAll sites thereafter, denoted as aggregate. Taking each station of the target line as a circle center, and taking the numerical value asFor drawing a circle by a radius, the invention takes. And taking the circle corresponding to the station on each target route as the overlapping range of the station, thereby obtaining the overlapping range of each station on the target route. When the collectionIncludes a set within the coincidence range of one stationWhen the station is in, the accumulator is connectedPlus 1, the target bus routeIn thatAfter-site overlap ratioThe calculation formula of (a) is as follows:
wherein the content of the first and second substances,is a routeIn thatThe degree of coincidence after a station is,is an accumulator and is a gas-liquid separator,is a setThe number of stations in (1).Is shown at the stationThe situation that the superposed station exists on the station of the target route on the primary alternative route later can be metStation reservation to obtain a bus route set。
Step (ii) of: judging each bus with the screened contact ratio larger than the set contact ratio threshold valueArrival of each bus shift of the routeAnd (4) whether the traffic pressure value of each station is greater than a set pressure threshold value or not, and taking the bus route smaller than the set pressure threshold value as a final bus route capable of being replaced.
According to collectionsInternal bus route at stationThe traffic pressure value result of the department is set to the screened bus routesThe last screening was performed. According to the stepsMethod (2) computing a setAll bus routes are at the stationAnd (4) setting the traffic pressure value, wherein the result of the traffic pressure value is larger than the set pressure threshold value after the traffic pressure value is cut off, considering that the current bus route is incapable of sharing the traffic pressure of the target route, and reserving the bus route of which the traffic pressure value result is smaller than the set pressure threshold value. So far, the station on the target route can be obtainedThe final set of alternative routes, denoted as set of alternative routes。
Thus, the collection is traversed in the same wayFor each stop, a set of alternative bus routes for each stop is obtained. The alternative routes of each stop provide more selectable routes for passengers to a certain extent, and the traffic pressure of the stop with higher traffic pressure value on the target route is relieved.
Step (ii) of: and updating the traffic pressure values of the current bus departure at the stations larger than the set pressure threshold according to the traffic pressure values of all the alternative routes at the corresponding stations smaller than the set pressure threshold.
When updating the traffic pressure value of each station on the target route, considering that different alternative routes have different influence degrees on the traffic pressure of the target route at the current station, obtaining a more accurate updated traffic pressure value of each station according to the alternative routes, and specifically realizing the following steps:
first, a set is obtainedSet of alternative routes for each site within, here with siteSet of alternative routes ofThe traffic pressure value updating method is described in detail. Then, the known siteAlternative bus route setEach route comprises information of coincidence degree and traffic pressure score and is marked as a substitute routeRespectively the contact ratio and the traffic pressure ofIf the target route is at the stationUpdated traffic pressure valuesThe calculation formula of (2) is as follows:
wherein the content of the first and second substances,for sites after updateThe traffic pressure value of (a) is,for sites before updateThe traffic pressure value of (a) is,as a stationThe number of all of the alternative bus routes,as a stationCan be replaced byThe degree of coincidence with the target route,as a stationAlternative routes toIn the first placeThe traffic pressure value of each station is set,in order to set the pressure threshold value,for the current bus departureTime period of each site. It is explained that, in order to prevent the situation that the number of the alternative routes is too large to generate negative number, whenIt is set to 0.
At the end, the sets are assembled in the same wayAnd updating the traffic pressure value of each station in the system.
Step (ii) of: according to the updated traffic pressure values of the bus shift of the current departure at each stop, recalculating the purpose of the bus shift of the current departureAnd marking the line score. According to the recalculated updated target route score, determining the bus dispatching shift of the current departure time period on the target route, wherein the specific implementation content is as follows:
according to the updated setTaking the maximum value of the updated traffic pressure value as the score of the updated target route. Time period after updateTarget route score ofAnd traffic pressure thresholdComparing to obtain the current time periodScheduling shiftThe calculation formula is as follows:
wherein the content of the first and second substances,the number of shifts to be scheduled for the bus,for the score of the recalculated target route,in order to set the pressure threshold value,for the time period when the current bus shift of departure arrives at the first stop,is a pair ofRounding down is performed.
Thus, according to the above stepsAnd finally, determining a bus dispatching scheme based on artificial intelligence and big data.
The embodiment also provides a bus dispatching system based on artificial intelligence and big data, which comprises a processor and a memory, wherein the processor is used for processing instructions stored in the memory to realize the bus dispatching method based on artificial intelligence and big data, and since the dispatching method is described in detail in the above content, the dispatching method is not described in detail here.
It should be noted that: the precedence order of the above embodiments of the present invention is only for description, and does not represent the merits of the embodiments. And specific embodiments thereof have been described above. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (7)
1. A bus dispatching method based on artificial intelligence and big data is characterized by comprising the following steps:
selecting a target route from all bus routes, and acquiring each stop on the target route, the required driving time between any two stops and the number of passengers getting on and off each stop in each time period;
predicting the time period of the current bus departure to each stop and the traffic pressure value at each stop according to the required driving time between any two stops on the target route and the number of people getting on or off the bus at each stop in each time period;
determining a target route score of the bus shift of the current departure according to the predicted traffic pressure value of the bus shift of the current departure at each stop;
if the target route score of the current bus departure time is larger than a set score threshold, respectively judging whether the traffic pressure value of the current bus departure time at each stop is larger than a set pressure threshold, and obtaining each stop of which the target route is larger than the set pressure threshold;
acquiring all bus routes which can be replaced at each stop and are smaller than a set pressure threshold according to the predicted time period for the bus which is sent out currently to reach each stop;
updating the traffic pressure values of the current bus departure at all the stations smaller than the set pressure threshold according to the traffic pressure values of all the alternative routes at all the stations smaller than the set pressure threshold;
recalculating the target route score of the current bus departure time according to the updated traffic pressure value of the current bus departure time at each stop, and determining the bus dispatching time of the current departure time period on the target route according to the recalculated target route score;
the step of acquiring all the alternative bus routes of all the stations which are greater than the set pressure threshold comprises the following steps:
for the second time greater than the set pressure thresholdA station acquiring the data passing through the firstAll bus routes of each stop, wherein the target routes are not included in all the bus routes;
acquiring the required running time between any two stops on each bus route in all bus routes and the number of passengers getting on and off each stop in each time period;
predicting the arrival of each bus on each bus route in all bus routes in the first bus shift according to the required driving time between any two stops on each bus route in all bus routes and the number of passengers getting on and off each stop in each time periodTime period of individual site and inTraffic pressure values for individual stations;
determining a preliminary alternative bus route from all bus routes, wherein the preliminary bus route of the preliminary alternative bus route reaches the first bus shiftThe time period of each station and the arrival number of bus shifts of the current departure on the target lineThe time periods of the stations are the same;
calculating the coincidence degree of each bus route in the preliminary planned alternative bus routes and the target route, and screening out the bus routes with the coincidence degree of the target route being greater than a set coincidence degree threshold value from the preliminary planned alternative bus routes;
judging whether the screened coincidence degree is greater than the preset coincidence degree threshold value or notWhether the traffic pressure value of each station is larger than a set pressure threshold value or not, and taking the bus route smaller than the set pressure threshold value as a final bus route capable of being replaced;
the step of calculating the contact ratio of each bus route in the preliminary bus routes and the target route comprises the following steps:
on the target line atEach station behind each station is used as a circle center, a circle is drawn by taking a set distance as a radius, and the circle corresponding to each station on the target line is used as the coincidence range of the station;
obtaining each bus route in the preliminary alternative bus routes on the second placeEach station behind each station and judging whether each bus route is on the first stationWhether each station behind each station is positioned in the overlapping range or not is judged, and the position of each bus route is the first positionThe number of all stations located in the overlapping range after the station is taken as the number of the stationThe coincidence degree of the bus route and the target route at each station;
the formula for updating the traffic pressure value of the current bus departure at each stop point which is greater than the set pressure threshold value is as follows:
wherein the content of the first and second substances,is the first after updateThe traffic pressure value of each station is set,is the first before updateThe traffic pressure value of each station is set,is as followsThe number of all alternative bus routes for each stop,is as followsBus route capable of replacing bus stopThe degree of coincidence with the target route,in order to set the pressure threshold value,is as followsBus route capable of replacing bus stopIn the first placeThe traffic pressure value of each station is set,for the current bus departureTime period of each site.
2. The artificial intelligence and big data based bus scheduling method according to claim 1, wherein the step of predicting the time period for the current bus departure shift to reach each stop and the traffic pressure value at each stop comprises:
calculating the traffic pressure value of the current bus departure at the first stop according to the number of passengers getting on and off the first stop at the current bus departure time period;
predicting the time period of the current bus departure to the next stop according to the time period of the current bus departure to the previous stop, the number of people getting on or off the bus in the time period of the current bus departure to the previous stop, the traffic pressure value of the previous stop and the required driving time from the previous stop to the next stop; predicting the number of passengers getting on and off corresponding to the next stop in the time period according to the predicted time period when the bus which is sent out currently arrives at the next stop; and predicting the traffic pressure value of the next stop according to the traffic pressure value of the current departure bus at the previous stop and the predicted number of passengers getting on and off the next stop in the time period.
3. The artificial intelligence and big data based bus scheduling method according to claim 2, wherein the calculation formula corresponding to the time period for predicting the arrival of the bus shift of the current departure at each stop and the traffic pressure value at each stop is as follows:
wherein the content of the first and second substances,is at the firstThe traffic pressure value of each station is set,is at the firstThe traffic pressure value of each station is set,for the current bus departureThe time period of each station is,for the current bus departureThe time period of each station is,is as followsFrom station to stationThe travel time required for each station is,is as followsThe lower-vehicle heat value of each station,is as followsThe heat value of getting-on of the vehicle at each station,=,,is as followsStation in time slotThe corresponding number of the people getting off the bus,is as followsStation in time slotThe corresponding number of the passengers getting on the bus,the number of seats on the bus shift from which the bus is currently dispatched,is as followsThe lower-vehicle heat value of each station,is as followsThe heat value of getting-on of the vehicle at each station,=,,is as followsStation in time slotThe corresponding number of the people getting off the bus,is as followsStation in time slotThe corresponding number of the passengers getting on the bus,the time coefficient of getting on and off the vehicle is,for the length of time of each time segment,presentation pairRounding down is performed.
4. The artificial intelligence and big data based bus scheduling method according to claim 3, wherein the expression of the time coefficient for getting on or off the bus is:
5. The artificial intelligence and big data based bus scheduling method according to claim 1, wherein the calculation formula corresponding to the bus scheduling shift at the current departure time period on the target line is determined as follows:
wherein the content of the first and second substances,the number of shifts to be scheduled for the bus,for the score of the recalculated target route,in order to set the pressure threshold value,for the time period when the current bus shift of departure arrives at the first stop,is a pair ofRounding down is performed.
6. The artificial intelligence and big data based bus scheduling method according to any one of claims 1-3, wherein the maximum value of the traffic pressure values of the current bus departure at each stop is used as the target route score of the current bus departure.
7. An artificial intelligence and big data based bus dispatching system, characterized by comprising a processor and a memory, wherein the processor is used for processing instructions stored in the memory to realize the artificial intelligence and big data based bus dispatching method as claimed in any one of claims 1-6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111022049.3A CN113470364B (en) | 2021-09-01 | 2021-09-01 | Bus scheduling method and system based on artificial intelligence and big data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111022049.3A CN113470364B (en) | 2021-09-01 | 2021-09-01 | Bus scheduling method and system based on artificial intelligence and big data |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113470364A true CN113470364A (en) | 2021-10-01 |
CN113470364B CN113470364B (en) | 2021-11-26 |
Family
ID=77868028
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111022049.3A Active CN113470364B (en) | 2021-09-01 | 2021-09-01 | Bus scheduling method and system based on artificial intelligence and big data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113470364B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113905215A (en) * | 2021-12-07 | 2022-01-07 | 江西佳铭特实业有限公司 | Bus safe driving monitoring system |
CN114241770A (en) * | 2021-12-21 | 2022-03-25 | 杭州图软科技有限公司 | Bus scheduling method and system based on accurate real-time information |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103077605A (en) * | 2012-12-14 | 2013-05-01 | 中国航天系统工程有限公司 | Scheduling method and device for vehicle |
CN106781432A (en) * | 2016-11-16 | 2017-05-31 | 青岛海信网络科技股份有限公司 | A kind of method and device of public traffic vehicles schedule |
CN109859459A (en) * | 2019-02-22 | 2019-06-07 | 北京航空航天大学 | A kind of automatic Pilot bus dispatching optimization method |
CN109886491A (en) * | 2019-02-26 | 2019-06-14 | 北京工业大学 | A kind of routine bus system two stages Optimization Scheduling of magnanimity operation data driving |
CN110245558A (en) * | 2019-05-07 | 2019-09-17 | 平安科技(深圳)有限公司 | Method for dispatching public transport vehicles, device and computer equipment based on recognition of face |
CN111754757A (en) * | 2020-06-24 | 2020-10-09 | 广州公交集团第三公共汽车有限公司 | Bus competition line scheduling method |
-
2021
- 2021-09-01 CN CN202111022049.3A patent/CN113470364B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103077605A (en) * | 2012-12-14 | 2013-05-01 | 中国航天系统工程有限公司 | Scheduling method and device for vehicle |
CN106781432A (en) * | 2016-11-16 | 2017-05-31 | 青岛海信网络科技股份有限公司 | A kind of method and device of public traffic vehicles schedule |
CN109859459A (en) * | 2019-02-22 | 2019-06-07 | 北京航空航天大学 | A kind of automatic Pilot bus dispatching optimization method |
CN109886491A (en) * | 2019-02-26 | 2019-06-14 | 北京工业大学 | A kind of routine bus system two stages Optimization Scheduling of magnanimity operation data driving |
CN110245558A (en) * | 2019-05-07 | 2019-09-17 | 平安科技(深圳)有限公司 | Method for dispatching public transport vehicles, device and computer equipment based on recognition of face |
CN111754757A (en) * | 2020-06-24 | 2020-10-09 | 广州公交集团第三公共汽车有限公司 | Bus competition line scheduling method |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113905215A (en) * | 2021-12-07 | 2022-01-07 | 江西佳铭特实业有限公司 | Bus safe driving monitoring system |
CN114241770A (en) * | 2021-12-21 | 2022-03-25 | 杭州图软科技有限公司 | Bus scheduling method and system based on accurate real-time information |
Also Published As
Publication number | Publication date |
---|---|
CN113470364B (en) | 2021-11-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113470364B (en) | Bus scheduling method and system based on artificial intelligence and big data | |
JP6570731B2 (en) | Method and system for calculating passenger congestion | |
WO2021159865A1 (en) | Data calibration-based bus route prediction method and system | |
CN110493816B (en) | Real-time prediction method for rail transit subway station passenger flow volume | |
CN106197458B (en) | A kind of mobile phone user's trip mode recognition methods based on mobile phone signaling data and navigation route data | |
CN110164152B (en) | Traffic signal lamp control system for single-cross intersection | |
WO2021023310A1 (en) | Method for estimating and presenting passenger flow, system, and computer readable storage medium | |
CN106935027A (en) | A kind of traffic information predicting method and device based on running data | |
CN109085790A (en) | A kind of underground traffic passenger guiding system based on smart city | |
CN107545757B (en) | Urban road flow velocity measuring device and method based on license plate recognition | |
CN108615378A (en) | A kind of traffic light time regulation and control method at two-way multilane zebra stripes crossing | |
CN110298516B (en) | Method and device for splitting overlong bus line based on passenger flow OD data, mobile terminal equipment and server | |
CN108922194A (en) | A kind of dynamic controllable intelligent traffic information prompting system based on big data | |
CN104021605A (en) | Real-time statistics system and method for public transport passenger flow | |
CN110634299B (en) | Urban traffic state fine division and identification method based on multi-source track data | |
CN110675032A (en) | Vehicle scheduling method and device | |
CN105261211B (en) | A kind of bus departure interval transition method under the influence of traffic composite factor | |
CN112016735B (en) | Patrol route planning method and system based on traffic violation hotspot prediction and readable storage medium | |
CN105844229A (en) | Method and system for calculating passenger crowdedness degree | |
Razavi et al. | Smart traffic light scheduling in smart city using image and video processing | |
CN106931981A (en) | A kind of generation method and device of remaining time of navigating | |
CN114419924B (en) | AI application control management system based on wisdom city | |
CN116050581A (en) | Smart city subway driving scheduling optimization method and Internet of things system | |
CN112601187B (en) | Bus frequent passenger prediction method and system based on mobile phone signaling | |
CN108197078B (en) | Method for calculating bus section passenger flow based on bus IC card data |
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 |