CN113469451B - Customized bus route generation method based on heuristic algorithm - Google Patents
Customized bus route generation method based on heuristic algorithm Download PDFInfo
- Publication number
- CN113469451B CN113469451B CN202110812117.XA CN202110812117A CN113469451B CN 113469451 B CN113469451 B CN 113469451B CN 202110812117 A CN202110812117 A CN 202110812117A CN 113469451 B CN113469451 B CN 113469451B
- Authority
- CN
- China
- Prior art keywords
- line
- stations
- new
- steps
- bus
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000005457 optimization Methods 0.000 claims abstract description 12
- 230000008030 elimination Effects 0.000 claims abstract description 11
- 238000003379 elimination reaction Methods 0.000 claims abstract description 11
- 238000006116 polymerization reaction Methods 0.000 claims abstract description 9
- 238000005070 sampling Methods 0.000 claims abstract description 6
- 230000002776 aggregation Effects 0.000 claims description 7
- 238000004220 aggregation Methods 0.000 claims description 7
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 230000003287 optical effect Effects 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 3
- 239000000446 fuel Substances 0.000 claims description 2
- 238000003780 insertion Methods 0.000 claims description 2
- 230000037431 insertion Effects 0.000 claims description 2
- 238000010187 selection method Methods 0.000 claims description 2
- 238000013461 design Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 230000003796 beauty Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000012067 mathematical method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
-
- G06Q50/40—
Abstract
The invention relates to a customized bus route generation method based on a heuristic algorithm, which solves the problems in the prior art and has the technical scheme that: the method comprises the following steps that firstly, the calculated amount is reduced in an OD polymerization mode; sampling a set number of unconnected ODs and generating corresponding travel schemes to finish the initialization of a new line; step three, taking out the currently unattached OD and disturbing the traversing sequence, for each OD, trying to splice all nearby new lines, obtaining the optimal inserting mode, inserting the OD into the new line with the minimum cost, and after traversing all the ODs, completing the generation of the new line; step four: according to OD selection, carrying out line elimination and line optimization, wherein the line elimination and line optimization are carried out in a combined mode; and fifthly, judging whether the current line set meets the requirement, if not, repeating the steps two to four, and obtaining the final line set through iteration.
Description
Technical Field
The invention relates to a customized bus route generation method, in particular to a customized bus route generation method based on a heuristic algorithm.
Background
Custom bus route generation methods belong to the class of vehicle path problems (VRPs), but constraints and implementation are more complex. The problem is similar to the drip carpooling and take-away delivery, and reference is made to the description of the problem in a beauty group intelligent delivery system: "Path planning problem specific to rider, not simple route planning, not the question of which path to go from a to b. This scenario is where a rider has many delivery tasks that have various constraints on how to select an optimal delivery sequence to accomplish all tasks. This is an NP-hard problem, with more than 11 tens of thousands of possible orders when there are 5 orders, 10 task points. In peak time, more than 5 sheets are often carried by a rider, even one rider can receive more than ten sheets at the same time, and the feasible taking and delivering sequence becomes an astronomical number. The difference is that the drip carpool can only accommodate 3-4 people due to the limitation of vehicles; the take-out distribution of the placard is even in extreme cases tens of placards. And in the situation that the single order is not spliced, the single order is directly distributed, the capacity of the bus is enough to be tens of hundreds of people, the solution space of the beauty group assessment 10 sheet is 2.38 x 10 x 15, which is the astronomical number, is only the minimum scale of the bus, and is different from the fixed starting and ending point of the order of the drip/beauty group, and the bus is also required to be matched with a proper bus stop for the user to get on or off.
At present, a great number of methods for solving the vehicle path problem can be basically divided into a precise algorithm and a heuristic algorithm 2. The accurate algorithm is an algorithm capable of solving the optimal solution, and mainly adopts mathematical programming technologies such as linear programming, integer programming, nonlinear programming and the like to describe the quantitative relation of the logistics system so as to solve the optimal decision. However, because a strict mathematical method is introduced, the calculated amount generally increases exponentially with the increase of the problem scale, and thus the problem of exponential explosion cannot be avoided, so that the algorithm can only effectively solve the small-scale deterministic VRP, and generally, the algorithms are designed aiming at a specific problem, and have poor applicability, so that the application range of the algorithm is limited in practice. Since the vehicle path optimization problem is an NP-hard problem, the possibility that efficient and accurate algorithms exist is not great (unless p=np), so finding an approximation algorithm is necessary and realistic, and for this reason, experts are mainly struggling with constructing high quality heuristic algorithms. Heuristic algorithms are improved search algorithms in the state space that evaluate each searched location, get the best location, and then search from this location to the target. In heuristic searches, the valuation of location is important and different valuations may be used with different effects. The existing method is directly used for solving, if the search is fully inspired, the speed is too slow, and because the search frequency of a solution space is too large, the navigation dependence is too heavy (the vehicle navigation speed between two points is slower), if the search is not fully inspired, the line quality is very poor, and the practical applicability is poor. In summary, the disadvantages of the prior art are: the line generation speed is low, the line quality is problematic, the problems such as turning around exist, the satisfaction degree of users is not considered much, and the actual riding will is probably lower.
Disclosure of Invention
Aiming at the problems of low line generation speed, line quality, turning around and the like in the background technology and the problem of low actual riding will due to less consideration of the satisfaction degree of users, the invention provides a customized bus line generation method based on a heuristic algorithm.
The technical scheme adopted for solving the technical problems is as follows: a customized bus route generating method based on heuristic algorithm comprises the following steps after obtaining city OD data,
step one, reducing the calculated amount in an OD polymerization mode;
sampling a set number of unconnected ODs and generating corresponding travel schemes to finish the initialization of a new line;
step three, taking out the ODs which are not connected with each other currently and disturbing the traversing sequence, for each OD, trying to splice all the nearby new lines, obtaining the optimal inserting mode, inserting the OD into the new line with the minimum cost, and after traversing all the ODs, completing the generation of the new line;
step four: according to OD selection, carrying out line elimination and line optimization, wherein the line elimination and line optimization are carried out in a combined mode;
and fifthly, judging whether the current line set meets the requirement, if not, repeating the steps two to four, and obtaining the final line set through iteration.
In the invention, "O" is derived from English ORIGIN, and "D" is derived from English DESTINATION, and refers to DESTINATION of travel, and city OD data belongs to a conventional call in the technical field, and is clear, and the city OD data can be obtained by the prior art. And further optimizing the initial line result to improve the line quality. And quantifying the satisfaction degree of the user, and directly influencing the number of passengers on the line, so that the line result gives consideration to both the passenger feeling and the public transport operation. By utilizing the technical scheme provided by the invention, customized public transportation service can be provided based on travel demands submitted by enterprises, schools, airports, high-speed rail stations and other scenes. Based on city OD data, potential demands are identified, large-flow travel is difficult, and customized bus travel demands are extracted.
Preferably, in said step one, the OD polymerization is carried out in two steps,
the method comprises the steps of a polymerization step I, merging the same OD (optical density) in a Geohash merging requirement mode, converting O and D into Geohash, merging the requirements of the Geohash with the same starting and ending points, merging and compressing the OD with higher frequency into a weighted OD, and reducing the subsequent calculated amount;
and a second aggregation step, calculating all the walking reachable sites with the weight OD, counting the site frequency, and obtaining a site set based on a greedy point selection mode.
Preferably, in the second aggregation step, the greedy point selection method includes a greedy point selection step one, selecting a station with highest frequency, if the frequencies of the stations are the same, selecting a station with a small walking total distance, and subtracting the corresponding frequency from other stations with reachable original OD corresponding to the finally selected station; and step two, repeating the step one of greedy point selection until the frequency of the rest stations is 0.
Preferably, in the aggregation step two, after the setting of the initial site set is completed, the site set needs to be expanded, and all sites adjacent to each site in the initial site set and sites with the same names are supplemented to the initial site set to form the site set for the step two.
Preferably, in the second step, the set number of OD is sampled based on the weighted value of the weighted OD, the reachable sites near O and D are randomly fetched, and the generated new line is a line including only two sites in the initial state.
Preferably, in the third step, the insertion cost is an increased cost of the line, wherein the time-consuming cost is converted into a fee by a driver's time-paid, and the mileage cost is converted into a fee by fuel consumption of the automobile.
Preferably, in the fourth step, the sub-step of line elimination includes: combining the new lines into all generated bus lines, matching all OD requirements with all bus lines, selecting the bus line with the smallest total time consumption by each OD, and carrying out weight conversion according to the OD satisfaction; counting the number of people, time consumption, mileage, cost, benefit and benefit index of the line, and comprehensively screening the line based on the plurality of dimensions.
Preferably, the step of performing weight conversion on the OD satisfaction comprises the steps of calculating satisfaction of time consumption of bus travel through customization based on time consumption of driving and traveling of bus subway.
Preferably, in the fourth step, the line optimization substep includes deleting the station where the person gets on or off, deleting the station with low benefit, sequentially adjusting the stations in each line based on the single-point movement and 2-opt method, and adjusting the stations between lines based on the 2-opt and cross-exchange method.
The invention has the following substantial effects: the invention builds the customized bus route design model and outputs the route scheme on the basis of considering the traveling cost of passengers and the customized bus operation cost, and provides reference for the actual planning and operation of the customized bus. Compared with the research of the existing customized bus route design problem, the method considers the time and space requirements of passengers, designs a heuristic algorithm, can realize large coverage rate of the customized bus demands, has high average boarding rate, and can effectively improve the satisfaction of the passengers and reduce the operation cost of the customized bus.
Drawings
FIG. 1 is a schematic flow chart of the present invention;
FIG. 2 is a schematic diagram of a circuit generation according to the present invention;
fig. 3 is a schematic diagram of a circuit generation according to the present invention.
Detailed Description
The technical scheme of the invention is further specifically described by the following specific examples.
Example 1:
a customized bus route generation method based on heuristic algorithm (see figure 1), after obtaining city OD data, the following steps,
step one, reducing the calculated amount in an OD polymerization mode;
sampling a set number of unconnected ODs and generating corresponding travel schemes to finish the initialization of a new line;
step three, taking out the ODs which are not connected with each other currently and disturbing the traversing sequence, for each OD, trying to splice all the nearby new lines, obtaining the optimal inserting mode, inserting the OD into the new line with the minimum cost, and after traversing all the ODs, completing the generation of the new line;
step four: according to OD selection, carrying out line elimination and line optimization, wherein the line elimination and line optimization are carried out in a combined mode;
and fifthly, judging whether the current line set meets the requirement, if not, repeating the steps two to four, and obtaining the final line set through iteration.
In the invention, "O" is derived from English ORIGIN, and "D" is derived from English DESTINATION, and refers to DESTINATION of travel, and city OD data belongs to a conventional call in the technical field, and is clear, and the city OD data can be obtained by the prior art. And further optimizing the initial line result to improve the line quality. And quantifying the satisfaction degree of the user, and directly influencing the number of passengers on the line, so that the line result gives consideration to both the passenger feeling and the public transport operation. By utilizing the technical scheme provided by the invention, customized public transportation service can be provided based on travel demands submitted by enterprises, schools, airports, high-speed rail stations and other scenes. Based on city OD data, potential demands are identified, large-flow travel is difficult, and customized bus travel demands are extracted.
In the first step, the OD polymerization is divided into two steps,
the method comprises the steps of a polymerization step I, merging the same OD (optical density) in a Geohash merging requirement mode, converting O and D into Geohash, merging the requirements of the Geohash with the same starting and ending points, merging and compressing the OD with higher frequency into a weighted OD, and reducing the subsequent calculated amount;
and a second aggregation step, calculating all the walking reachable sites with the weight OD, counting the site frequency, and obtaining a site set based on a greedy point selection mode. In the second aggregation step, greedy point selection mode comprises greedy point selection step one, selecting a station with highest frequency, if the frequencies of the stations are the same, selecting a station with small walking total distance, and subtracting corresponding frequencies from other stations with reachable original OD corresponding to the finally selected station; and step two, repeating the step one of greedy point selection until the frequency of the rest stations is 0. In the aggregation step II, after the setting of the initial site set is completed, the site set needs to be expanded, and all sites adjacent to each site in the initial site set and sites with the same names are supplemented to the initial site set to form the site set for the step II. The weighted OD in this embodiment refers to an OD with a weighted weight value set, generally refers to the number of people, or may be set manually; the site frequency mainly refers to the accumulated value of the weighted OD, and can be generally understood as the number of times that a person enters and exits the site position in a certain set time period; the total walking distance refers to the walking distance of the station from the actual destination or departure point.
More specifically, first, the same OD merging is performed, O and D are converted into Geohash7 through the Geohash merging requirement, and the requirements of the starting and ending points, which are the same, are merged. The OD with higher frequency can be combined and compressed into one OD with weight (number of people), so that the subsequent calculated amount is reduced. Then, the initial site set is screened, the searching space is greatly reduced based on the frequency greedy site selection, all the walking reachable sites with the right OD (optical density) are calculated, specifically, the boarding site and the alighting site are set within 800 meters, the site frequency is counted, and the site set is obtained based on the greedy site selection mode. Greedy point selection mode: and when the frequencies of the stations are the same, the station with smaller walking total distance is selected, and the corresponding frequencies are subtracted from other stations with reachable original OD corresponding to the station. The above process is repeated until the remaining site frequencies are all 0.
The problem of a large number of turns occurs when the above-mentioned station set actually generates a route, because only one station on one side of the route is included, and no station on the other side of the route is opposite to the traveling station, and thus the station set needs to be expanded. Expanding a site set: all stations in the vicinity of each station. According to the general case, sites within a straight distance of 200 meters are set, as well as sites of the same name, since sites of the same name are generally opposed. The site set obtained by the greedy point selection mode is smaller, so that the solution space can be greatly reduced, the generation of a line is greatly accelerated, and the problem of a large number of turns is avoided by combining the site set expansion method.
In the second step, the set number of OD is sampled based on the weighted value of the weighted OD, the reachable sites near O and D are randomly sampled, and the generated new line is a line containing only two sites in the initial state.
More specifically, based on the weight of the weighted OD, sampling and obtaining a small number of OD, the number of the available sites near O and D can be set to 10, the selected available sites belong to the site set, and the new line initial state is the line only including two sites. Besides the number of OD weight people, other factors, such as higher line indexes finally obtained according to some ODs in previous iteration, are comprehensively considered; in the early iterations, the selected probability of not having a suitable line OD connected is higher than the connected OD.
In the third step, the OD which is not connected with each other currently is taken out and the traversing sequence is disturbed, for each OD, all the nearby new lines are spliced, the optimal inserting mode is obtained, the inserting cost is the increasing cost of the lines, the time-consuming cost is converted into the cost through the firewood of the driver, the mileage cost is converted into the cost through the oil consumption of the automobile, the OD is inserted into the new line with the minimum cost, and after all the OD are traversed, the new line is generated.
In the fourth step, the sub-step of line elimination includes: combining the new lines into all generated bus lines, matching all OD requirements with all bus lines, selecting the bus line with the smallest total time consumption by each OD, and carrying out weight conversion according to the OD satisfaction; counting the number of people, time consumption, mileage, cost, benefit and benefit index of the line, and comprehensively screening the line based on the plurality of dimensions. The step of carrying out weight conversion on the OD satisfaction comprises the steps of taking bus and consuming time and subway and calculating the satisfaction of customizing the time consumed by bus and consuming time based on the OD. In the fourth step, the line optimization substep includes deleting the stations for getting on or off the vehicle without people, deleting the stations with low benefit, sequentially adjusting the stations in each line based on the single-point movement and 2-opt method, and adjusting the stations between lines based on the 2-opt-cross-exchange method. In the present embodiment, the number of passengers is converted based on the satisfaction, for example, the number of weight persons is OD of 2, and the satisfaction is 80%, and then the vehicle is actually 1.6 persons. The benefits described in this embodiment are accumulated as effective transportation distance: the OD distance accumulation of all people on the line, namely benefit/cost, is better as the value is higher, and the minimum total time consumption of each OD selection is the bus line with the minimum sum of walking time consumption and bus time consumption. The final route set in this embodiment may include information such as a station where the route is routed, a route related index, an arrival time of the vehicle at each station, and a time for each user to get on and off the station. Step five, judging whether the current line set meets the requirement, if not, repeating the step two to the step four, and obtaining a final line set through iteration, wherein fig. 2 is a schematic diagram from multiple points to single point, and fig. 3 is a schematic diagram for multiple O multiple D in the method. In the fifth step, judging whether the current line set meets the requirement or not mainly comprises judging whether the total travel duration of the target service crowd is reduced or not, and judging whether the benefit index of the vehicle meets the standard or not, wherein the benefit index is related to the number of people, time consumption, mileage, cost and income of the statistical line.
According to the method, the device and the system, the customized bus route design model is built on the basis of considering the traveling cost of passengers and the customized bus operation cost, and a route scheme is output, so that references are provided for actual planning and operation of customized buses. Compared with the research of the existing customized bus route design problem, the method considers the time and space requirements of passengers, designs a heuristic algorithm, can realize large coverage rate of the customized bus demands, has high average boarding rate, and can effectively improve the satisfaction of the passengers and reduce the operation cost of the customized bus.
The above-described embodiment is only a preferred embodiment of the present invention, and is not limited in any way, and other variations and modifications may be made without departing from the technical aspects set forth in the claims.
Claims (3)
1. A customized bus route generation method based on heuristic algorithm is characterized in that after city OD data are acquired, the method comprises the following steps,
step one, reducing the calculated amount in an OD polymerization mode; in the first step, the OD polymerization is divided into two steps,
the method comprises the steps of firstly, merging the same OD (optical density) in a Geohash merging requirement mode, converting O and D into Geohash, merging the requirements of the same Geohash at the starting and ending points, merging and compressing the OD with higher frequency into an OD with weight, and reducing the subsequent calculated amount;
step two, calculating all the walking reachable sites with the weight OD, counting the site frequency, and obtaining a site set based on a greedy point selection mode;
the greedy point selection method comprises the steps of greedy point selection, namely firstly, selecting a station with highest frequency, if the frequencies of the stations are the same, selecting a station with small walking total distance, and subtracting corresponding frequencies from other stations with reachable original OD corresponding to the finally selected station; step two, greedy point selection, namely repeating the greedy point selection step one until the frequency of the rest stations is 0;
in the aggregation step II, after the setting of the initial site set is completed, the site set needs to be expanded, and all sites adjacent to each site in the initial site set and sites with the same names are supplemented to the initial site set to form a site set for the step II;
sampling a set number of unconnected ODs and generating corresponding travel schemes to finish the initialization of a new line; in the second step, sampling and obtaining set number of OD based on the weight of the weighted OD, randomly taking the reachable sites near O and D, and generating a new line which is a line only comprising two sites in the initial state;
step three, taking out the currently unattached OD and disturbing the traversing sequence, for each OD, trying to splice all nearby new lines, obtaining the optimal inserting mode, inserting the OD into the new line with the minimum cost, and after traversing all the ODs, completing the generation of the new line;
step four: according to OD selection, carrying out line elimination and line optimization, wherein the line elimination and line optimization are carried out in a combined mode;
line elimination includes: combining the new lines into all generated bus lines, matching all OD requirements with all bus lines, selecting the bus line with the smallest total time consumption by each OD, and carrying out weight conversion according to the OD satisfaction; counting the number of people, time consumption, mileage, cost, income and benefit index of the line, and comprehensively screening the line based on the plurality of dimensions;
the line optimization comprises the steps of deleting stations for getting on or off the vehicle without people, deleting stations with low benefit, sequentially adjusting stations in each line based on a single-point movement and 2-opt method, and adjusting stations between lines based on the 2-opt and cross-exchange method;
and fifthly, judging whether the current line set meets the requirement, if not, repeating the steps two to four, and obtaining the final line set through iteration.
2. The method for generating customized bus routes based on heuristic algorithm according to claim 1, wherein in said step three, the insertion cost is the increased cost of the route, wherein the time-consuming cost is converted into a fee by the driver's time-firewood, and the mileage cost is converted into a fee by the fuel consumption of the car.
3. The method for generating customized bus route based on heuristic algorithm according to claim 1, wherein the step of performing weight conversion on the OD satisfaction comprises calculating satisfaction of time consumed by customized bus travel based on time consumed by driving and time consumed by subway travel.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110812117.XA CN113469451B (en) | 2021-07-19 | 2021-07-19 | Customized bus route generation method based on heuristic algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110812117.XA CN113469451B (en) | 2021-07-19 | 2021-07-19 | Customized bus route generation method based on heuristic algorithm |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113469451A CN113469451A (en) | 2021-10-01 |
CN113469451B true CN113469451B (en) | 2024-01-05 |
Family
ID=77881000
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110812117.XA Active CN113469451B (en) | 2021-07-19 | 2021-07-19 | Customized bus route generation method based on heuristic algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113469451B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115577818B (en) * | 2022-12-01 | 2023-04-18 | 武汉好人科技股份有限公司 | Passenger demand response type carpooling scheduling method and system for intelligent bus |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104217086A (en) * | 2014-10-09 | 2014-12-17 | 大连海事大学 | Urban public transport network optimization method |
CN107657330A (en) * | 2017-08-16 | 2018-02-02 | 深圳先进技术研究院 | A kind of candidate's public bus network computational methods, system and electronic equipment |
CN108053062A (en) * | 2017-12-11 | 2018-05-18 | 北京航空航天大学 | A kind of customization public bus network generation method based on multi-source data |
CN109344529A (en) * | 2018-10-22 | 2019-02-15 | 北京航空航天大学 | A kind of customization public bus network design method based on two-phase heuristic algorithm |
CN111815189A (en) * | 2020-07-15 | 2020-10-23 | 同济大学 | Modular bus dispatching system |
CN112289065A (en) * | 2019-12-02 | 2021-01-29 | 南京行者易智能交通科技有限公司 | Customized bus route design method and system based on accurate OD big data |
CN112347596A (en) * | 2020-11-05 | 2021-02-09 | 浙江非线数联科技有限公司 | Urban public transport network optimization method |
CN112381472A (en) * | 2021-01-15 | 2021-02-19 | 深圳市城市交通规划设计研究中心股份有限公司 | Subway connection bus route optimization method and device and storage medium |
CN116187585A (en) * | 2023-04-19 | 2023-05-30 | 杭州数知梦科技有限公司 | Method, device and application for predicting BRT bus route of passenger |
CN116258253A (en) * | 2023-02-07 | 2023-06-13 | 清华大学深圳国际研究生院 | Vehicle OD prediction method based on Bayesian neural network |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP3683742A1 (en) * | 2019-01-18 | 2020-07-22 | Naver Corporation | Method for computing at least one itinerary from a departure location to an arrival location |
-
2021
- 2021-07-19 CN CN202110812117.XA patent/CN113469451B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104217086A (en) * | 2014-10-09 | 2014-12-17 | 大连海事大学 | Urban public transport network optimization method |
CN107657330A (en) * | 2017-08-16 | 2018-02-02 | 深圳先进技术研究院 | A kind of candidate's public bus network computational methods, system and electronic equipment |
CN108053062A (en) * | 2017-12-11 | 2018-05-18 | 北京航空航天大学 | A kind of customization public bus network generation method based on multi-source data |
CN109344529A (en) * | 2018-10-22 | 2019-02-15 | 北京航空航天大学 | A kind of customization public bus network design method based on two-phase heuristic algorithm |
CN112289065A (en) * | 2019-12-02 | 2021-01-29 | 南京行者易智能交通科技有限公司 | Customized bus route design method and system based on accurate OD big data |
CN111815189A (en) * | 2020-07-15 | 2020-10-23 | 同济大学 | Modular bus dispatching system |
CN112347596A (en) * | 2020-11-05 | 2021-02-09 | 浙江非线数联科技有限公司 | Urban public transport network optimization method |
CN112381472A (en) * | 2021-01-15 | 2021-02-19 | 深圳市城市交通规划设计研究中心股份有限公司 | Subway connection bus route optimization method and device and storage medium |
CN116258253A (en) * | 2023-02-07 | 2023-06-13 | 清华大学深圳国际研究生院 | Vehicle OD prediction method based on Bayesian neural network |
CN116187585A (en) * | 2023-04-19 | 2023-05-30 | 杭州数知梦科技有限公司 | Method, device and application for predicting BRT bus route of passenger |
Non-Patent Citations (2)
Title |
---|
城市公交数据大脑建设及应用;王瑞利;;交通与港航(第01期);全文 * |
基于可靠性最短路的实时定制公交线路优化研究;申婵;崔洪军;;交通运输系统工程与信息(第06期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN113469451A (en) | 2021-10-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Al-Kanj et al. | Approximate dynamic programming for planning a ride-hailing system using autonomous fleets of electric vehicles | |
Huang et al. | A two-phase optimization model for the demand-responsive customized bus network design | |
Zhou et al. | Bus arrival time calculation model based on smart card data | |
US9116007B2 (en) | System and method for journey planning, finding K shortest paths through a time/space network | |
Psaraki et al. | Access mode choice for relocated airports: the new Athens International Airport | |
Chen et al. | Customized bus route design with pickup and delivery and time windows: Model, case study and comparative analysis | |
Kato et al. | Comparative analysis of transit assignment: evidence from urban railway system in the Tokyo Metropolitan Area | |
Espinosa-Aranda et al. | High-speed railway scheduling based on user preferences | |
CN104884900A (en) | Travel time information providing apparatus and travel time information providing method | |
Dou et al. | Customized bus service design for uncertain commuting travel demand | |
Kazhaev et al. | Modelling urban route transport network parameters with traffic, demand and infrastructural limitations being considered | |
Hess et al. | Accounting for random taste heterogeneity in airport choice modeling | |
Gomes et al. | Sustainable Demand Responsive Transportation systems in a context of austerity: The case of a Portuguese city | |
Jeong | An optimal approach for a set covering version of the refueling-station location problem and its application to a diffusion model | |
Wu et al. | Predicting peak load of bus routes with supply optimization and scaled Shepard interpolation: A newsvendor model | |
CN116128172A (en) | Air-iron intermodal route generation method, system and equipment and storage medium | |
Li et al. | Taxi service area design: Formulation and analysis | |
CN113469451B (en) | Customized bus route generation method based on heuristic algorithm | |
McCabe et al. | Optimal locations and sizes of layover charging stations for electric buses | |
Yu et al. | Research on high-speed railway freight train organization method considering different transportation product demands | |
CN110347937B (en) | Intelligent passenger searching method for taxi | |
CN110567474B (en) | Taxi real-time tour route recommendation system and method based on big data | |
Bin et al. | An optimization method of multiclass price railway passenger transport ticket allocation under high passenger demand | |
Yang et al. | Trip planning for a mobility-as-a-service system: Integrating metros and shared autonomous vehicles | |
Liu et al. | Forecasting estimated times of arrival of US freight trains |
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 |