CN112651546A - Bus route optimization method and system - Google Patents
Bus route optimization method and system Download PDFInfo
- Publication number
- CN112651546A CN112651546A CN202011440130.9A CN202011440130A CN112651546A CN 112651546 A CN112651546 A CN 112651546A CN 202011440130 A CN202011440130 A CN 202011440130A CN 112651546 A CN112651546 A CN 112651546A
- Authority
- CN
- China
- Prior art keywords
- residence
- point
- determining
- preset
- residence point
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000005457 optimization Methods 0.000 title claims abstract description 25
- 238000003066 decision tree Methods 0.000 claims abstract description 50
- 238000004458 analytical method Methods 0.000 claims abstract description 12
- 238000012546 transfer Methods 0.000 claims description 14
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 239000003550 marker Substances 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 5
- 238000010801 machine learning Methods 0.000 abstract description 4
- 239000002699 waste material Substances 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000011144 upstream manufacturing Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 238000013138 pruning Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013461 design Methods 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
- 238000005070 sampling Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Abstract
The application provides a bus route optimization method and a system, wherein the method comprises the following steps: determining a plurality of residence points along a road and attribute data of each residence point; and generating a feature mark of the residence point according to the attribute data of the residence point based on the judging conditions of each level from the root node to the minimum leaf node in the decision tree model, and determining whether the residence point is the preferred bus stop or not according to the feature mark of the residence point. This application is based on real-time pedestrian location data and is carried out the analysis to circuit and website information, the trip law of analysis urban crowd, based on big data and machine learning (decision tree model), according to the analysis result, carry out reasonable increase and decrease to the bus stop, the website position carries out appropriate adjustment, the conclusion that reachs has very strong effect, bus stop to on each circuit is optimized, the setting that makes the bus stop in city reaches optimal effect, confirm that urban crowd goes out the journey smoothly, the waste of public resource has been avoided simultaneously.
Description
Technical Field
The application relates to the technical field of machine learning, in particular to a bus route optimization method and system.
Background
The main design principles of the traditional bus line include: the method comprises the following steps of opening a line along the main passenger flow direction, giving priority to high-flow direct passenger flow, enabling the average passenger flow of a line to be not lower than the lowest opening standard, enabling the average full load rate to be as high as possible, enabling the passenger flow of the line to be as balanced as possible and the like, wherein the judgment standards of a first point and a second point are based on statistical analysis of historical passenger flow data to obtain a prediction conclusion, and the third point to the fifth point are standards which are required to be met after the construction of the bus line is completed.
In the prior art, when a bus route is built, a bus route scheme is obtained by analyzing past historical data, so that the customized bus route is poor in timeliness and does not necessarily meet current traffic laws of people.
Therefore, it is desirable to provide a method, an apparatus, a device, an electronic device, and a medium for optimizing a bus route, which are highly time-efficient and meet current traffic regulations of people.
Disclosure of Invention
The application aims to provide a bus route optimization method and system.
The application provides a bus route optimization method in a first aspect, including:
determining a plurality of stagnation points along a road and attribute data of each stagnation point;
and generating a feature mark of the residence point according to the attribute data of the residence point based on the judging conditions of each level from the root node to the minimum leaf node in the decision tree model, and determining whether the residence point is the preferred bus stop or not according to the feature mark of the residence point.
In some embodiments of the present application, the determining a plurality of stagnation points along the roadway comprises:
dividing a city area into a plurality of continuous geographic grids, and determining characteristic data of each geographic grid, wherein the characteristic data comprises: density, transfer amount, coverage and imbalance coefficients;
based on a clustering algorithm, carrying out clustering analysis on the plurality of geographic grids according to the characteristic data to obtain a plurality of geographic grids with characteristic data meeting a preset index as the residence points; the preset indexes comprise that the intensity is greater than the preset intensity, the transfer amount is greater than the preset transfer amount, the coverage is greater than the preset coverage, and the unbalance coefficient is greater than the preset constant.
In some embodiments of the present application, the determining a plurality of stagnation points along the roadway further comprises:
if the plurality of resident points meeting the preset index have adjacent resident points, comparing the feature data of the two adjacent resident points one by one, and determining whether to remove one of the two adjacent resident points from the resident point set according to the comparison result.
In some embodiments of the present application, the attribute data of the dwell point includes: the number of residents, the residence time, the road information in the preset range of the residence point and the residence peak time.
In some embodiments of the present application, the generating a feature label of the dwell point according to the attribute data of the dwell point based on the determination condition of each level from the root node to the minimum leaf node in the decision tree model includes:
determining whether the number of residents at the residence point is greater than a first preset number and/or a second preset number, wherein the first preset number is greater than the second preset number;
if the number of the resident persons is larger than the first preset number, determining that the first characteristic mark of the resident point is preferred, and stopping node splitting by the decision tree model;
if the number of the resident persons is smaller than or equal to the first preset number and larger than the second preset number, determining that the first characteristic mark of the resident point is a candidate;
and if the number of the resident persons is less than or equal to the second preset number, generating a first characteristic mark of the resident point as a non-preferred area, and stopping node splitting by the decision tree model.
In some embodiments of the present application, the determining that the first feature of the dwell point is a candidate further comprises:
determining whether the residence time of the residence point is less than a first preset time and/or a second preset time, wherein the first preset time is less than the second preset time;
if the residence time of the residence point is less than the first preset time, determining that the second characteristic mark of the residence point is preferred, and stopping node splitting by the decision tree model;
if the number of residents at the residence point is greater than or equal to the first preset time length and less than the second preset time length, determining that the second feature mark of the residence point is a candidate;
and if the residence time of the residence point is longer than the second preset time, determining that the second characteristic mark of the residence point is a non-preferred area, and stopping node splitting by the decision tree model.
In some embodiments of the present application, after determining that the second feature of the dwell point is a candidate, the method further comprises:
determining the number of roads within a preset distance range from the residence point, and determining a third feature marker of the residence point as one of preference, candidate and non-preference according to the number of the roads;
determining a dwell peak hour for the dwell point, determining a fourth feature label for the dwell point as one of preferred, candidate, and non-preferred based on the dwell peak hour.
In some embodiments of the present application, the determining whether the parking spot is a preferred bus stop according to the feature tag of the parking spot includes:
determining that the preferred residence point of the first characteristic mark and/or the second characteristic mark is a preferred area of a bus stop;
determining the dwell point of which the first characteristic mark and the second characteristic mark are both candidates as a preferred area of the bus station;
and when one of the first characteristic mark and the second characteristic mark of the residence point is a candidate, determining whether the residence point is a preferred bus stop according to the third characteristic mark and the fourth characteristic mark of the residence point.
A second aspect of the present application provides a bus route optimization system, comprising:
the residence point determining module is used for determining a plurality of residence points along the road and determining the attribute data of each residence point;
and the decision tree module is used for generating a feature label of the residence point according to the attribute data of the residence point based on the judgment condition of each level from the root node to the minimum leaf node in the decision tree model, and determining whether the residence point is the preferred bus stop or not according to the feature label of the residence point.
In some embodiments of the present application, the dwell point determination module comprises:
the system comprises a ground dividing unit, a data processing unit and a data processing unit, wherein the ground dividing unit is used for dividing an urban area into a plurality of continuous geographic grids and determining characteristic data of each geographic grid, and the characteristic data comprises: density, transfer amount, coverage and imbalance coefficients;
and the clustering unit is used for carrying out clustering analysis on the plurality of geographic grids according to the characteristic data to obtain the residence points of which the characteristic data meets the preset indexes.
Compared with the prior art, the method and the system for optimizing the bus routes have the advantages that the route and stop information is analyzed according to the real-time pedestrian positioning data, the travel rule of urban people is analyzed, the bus stops are increased and decreased reasonably based on big data and machine learning (decision tree model) according to the analysis result, the stop positions are adjusted appropriately, the obtained conclusion has strong effectiveness, the bus stops on all the routes are optimized, the setting of the bus stops in the city achieves the optimal effect, the smooth travel of the urban people is confirmed, and meanwhile the waste of public resources is avoided.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the application. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
FIG. 1 illustrates a flow chart of a method of bus route optimization provided by some embodiments of the present application;
FIG. 2 illustrates another flow chart of a method of bus route optimization provided by some embodiments of the present application;
FIG. 3 illustrates a decision diagram of a decision tree model of a method of bus route optimization provided by some embodiments of the present application;
fig. 4 illustrates a block diagram of a bus route optimization system provided by some embodiments of the present application.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
It is to be noted that, unless otherwise specified, technical or scientific terms used herein shall have the ordinary meaning as understood by those skilled in the art to which this application belongs.
In addition, the terms "first" and "second", etc. are used to distinguish different objects, rather than to describe a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.
The embodiment of the application provides a bus route optimization method, which is exemplarily described below by combining the embodiment and the attached drawings.
As shown in fig. 1 to 3, a bus route optimization method according to the present application may include:
In this step, the attribute data of the stay point is data indicating whether the area is suitable for setting a bus stop, for example, the number of people at the stay point per unit time, the stay time of pedestrians at the stay point, the stay peak time, road information near the stay point, and the like, wherein the attribute data of the stay point is obtained by sampling the travel track of mass pedestrians in the city.
The residence points are the bus stops that may be located in the area, and generally speaking, one bus stop is located in one residence point.
And 102, generating a feature mark of the residence point according to the attribute data of the residence point based on the judgment conditions of each level from the root node to the minimum leaf node in the decision tree model, and determining whether the residence point is the preferred bus stop or not according to the feature mark of the residence point.
It can be understood that the decision book model can be used for classification, and the feature labels of the residence points are obtained based on the judgment conditions of the nodes at each level of the decision tree. A plurality of levels of the decision tree model can be preset from top to bottom, each level has different judgment conditions (the top and the bottom correspond to the sequence of the different judgment conditions), the minimum leaf node refers to the level at the lowest level, specifically, one judgment condition appears on each level of the decision tree model, the judgment result of each residing point on each level determines that the residing point is judged to be the judgment condition of the next level, and as shown in fig. 3, when the number of residing persons at the residing point is greater than the first preset number, the judgment of the next level is not carried out; when the number of the resident people is between the first preset number of people and the second preset number of people, judging the next level; when the number of the resident persons is not more than the second preset number, the judgment of the next level is not carried out.
In this embodiment, the attribute data of the residence point may include: the decision conditions corresponding to the attribute data are respectively located at different node positions of the decision tree model, for example, the decision conditions of the nodes from top to bottom in the decision tree model are respectively the relationship between the number of resident persons and the preset number of persons, the relationship between the residence time and the preset time, the road information in the predetermined range of the residence point and the residence peak time, the attribute data of each residence point is input into the root node of the decision tree model, and the nodes at all levels obtain the feature mark of the residence point according to the judgment conditions of the node. For example, the feature labels that can be obtained according to the judgment condition of the root node of the decision tree include preference, candidate and non-preference.
In this embodiment, the feature marks of the residence points are obtained according to the attribute data of the residence points, and the attribute data can indicate that the residence points are not suitable for setting bus stops. Therefore, whether the residence point is a preferred area or not can be determined according to the feature marks of the residence point, for example, the number of residence people and the residence time are main attribute data, the feature mark of the residence point is judged to be preferred as long as one of the two is close to the preset optimal data, and when the feature mark of the residence point is preferred, the residence point is determined to be the preferred area of the bus stop.
Certainly, when the bus stop is actually set, the simulated bus stop is set in the preferred area, the upstream and downstream link information of the simulated bus stop is determined, and the simulated bus stop with the optimal upstream and downstream link information is selected as the actual bus stop. And calculating the optimal upstream and downstream link information, and according to a reasonable and non-waste principle, utilizing the minimum public resources to enable the urban traffic to achieve the optimal transport capacity.
When the prior art constructs the bus route, through historical data analysis in the past, reach the bus route scheme, compared with the prior art, this application carries out the analysis to circuit and website information according to real-time pedestrian's location data, the travel law of city crowd is analyzed, based on big data and machine learning (decision tree model), according to the analysis result, carry out reasonable increase and decrease to the bus website, the website position carries out appropriate adjustment, the conclusion that reachs has very strong actual effect, optimize the bus website on each circuit, the setting of the bus website in messenger city reaches the optimal effect, confirm that city crowd goes out the journey smoothly, the waste of public resources has been avoided simultaneously.
In some variations of the embodiments of the present application, the determining 101 a plurality of stagnation points along the road may include:
It is understood that the geographic grid: the grid system is obtained by dividing the earth surface space according to certain rules, and is also called a geographic grid, a spatial information grid or a geographic grid. The method comprises the steps that massive positioning data of urban crowds are obtained through operators (such as Baidu maps, Tencent maps and other software operators for obtaining user positions in real time), and characteristic data of each geographic grid are determined according to the positioning data.
Wherein, the intensity refers to the population set in each geographic grid in unit time (such as 1 hour); the transfer amount refers to the number of people change value in each geographic grid in unit time; the coverage degree refers to the number of roads in a preset distance range of each geographic grid; the imbalance coefficient is a proportional constant between the intensity and the overall average passenger flow.
In the step, clustering analysis is carried out on the attribute data of the plurality of geographic grids based on a clustering algorithm, the plurality of geographic grids are divided into two types, one type is the geographic grid meeting the preset index, the other type is the geographic grid not meeting the preset index, and the plurality of geographic grids with the characteristic data meeting the preset index are screened out.
In the step, indexes of the residence points are lower than those of the bus stops normally set, the number of the residence points is far larger than the number of the actual bus stops, and the optimal residence area is obtained through next step of decision tree model training.
Further, step 101, determining a plurality of stagnation points along the road, may further include:
and if the plurality of resident points meeting the preset index have adjacent resident points, comparing the feature data of the two adjacent resident points one by one, and determining whether to eliminate one of the two adjacent resident points from the resident point set according to the comparison result.
In this step, if the feature data of each item of one of the two neighboring resident points is better than the corresponding feature data of the other of the two neighboring resident points, the other of the two neighboring resident points is discarded, i.e., not determined as a resident point. Of course, if the feature data of at least one of the two neighboring anchor points is not better than the corresponding feature data of the other of the two neighboring anchor points, then both of the two neighboring anchor points are determined to be anchor points.
In some variations of the embodiments of the present application, the attribute data of the residence point includes: the number of residents, the residence time, the road information in the preset range of the residence point and the residence peak time.
In this embodiment, the number of residents refers to the number of residents at a residence point in a unit time. When the number of residents in unit time period is larger than the base number of the constructed bus stop, the residence point can be used as an alternative scheme of the bus stop, and if the residence point is used as the bus stop, the capacity saturation condition of the bus stop is detected.
The residence time duration refers to the average residence time duration from the time when the pedestrian enters the residence point to the time when the pedestrian leaves the residence point. The residence time is short when the residence number is large and the residence time is long in a residence place, the residence point is considered, the crowd frequently flows, and the residence point is suitable for being considered as a transit junction of a bus line. When the residence time of the residence place is longer, the residence place is considered to be unsuitable to be used as a transfer point and suitable to be used as a trip destination of part of people.
The road information in the stay point range refers to the number of roads in a predetermined distance range of the stay point. And searching the optimal bus stop position according to the road information in the residence point range.
Peak dwell time refers to a period of time during a day (24 hours) when the number of dwells at a dwell point is greater than a predetermined threshold number of people. The bus departure frequency and the stop stay time can be reasonably arranged according to the stay peak time.
As shown in fig. 3, in some modified embodiments of the embodiment of the present application, the step 102 of generating a feature label of a dwell point according to attribute data of the dwell point based on a determination condition of each level from a root node to a minimum leaf node in the decision tree model may include:
and determining whether the number of the resident people at the resident point is larger than a first preset number and/or a second preset number, wherein the first preset number is larger than the second preset number.
It can be understood that the number of residents is a main influence factor for determining whether the residence point is the preferred bus stop, and therefore whether the number of residents at the residence point is greater than the first preset number and/or the second preset number is used as a judgment condition for the root node of the decision tree.
If the number of residents is larger than a first preset number, determining that the first characteristic mark of the resident point is preferred, and stopping node splitting by the decision tree model.
When the feature marks of the residence points obtained according to the judgment conditions of the root nodes are preferred, the decision tree model stops node splitting, the attribute data representing the number of residents of the residence points can determine that the residence points are preferred regions of the bus stop at the moment, whether other feature data meet preset conditions is not traced, and the residence points are directly placed into a residence point resource pool.
And if the number of the resident persons is less than or equal to a first preset number and greater than a second preset number, determining that the first characteristic mark of the resident point is a candidate.
When the number of residents of the resident point is between a first preset number of people and a second preset number of people, the fact that the first feature mark of the resident point is a candidate is obtained, namely, other feature marks of the main force area are determined according to other attribute data of the resident point to determine whether the resident point is a preferred area, and at the moment, the decision tree model continues to split the next-level node.
And if the number of the residents is less than or equal to a second preset number, generating a first characteristic mark of the resident point as a non-preferred area, and stopping node splitting by the decision tree model.
And the number of the resident persons is less than or equal to the second preset number of persons, the number of the resident persons representing the resident persons at the resident point is very small, and a bus stop does not need to be set at the resident point, so that the decision tree model stops node splitting.
Further, determining that the first feature of the dwell point is a candidate further comprises:
and determining whether the residence time of the residence point is less than a first preset time and/or a second preset time, wherein the first preset time is less than the second preset time.
It can be understood that the length of the residence time is also a main influence factor for determining whether the residence point is the preferred bus stop, so that whether the number of residents at the residence point is greater than the first preset number and/or the second preset number is used as a judgment condition for the next node of the decision tree root node.
And if the residence time of the residence point is less than the first preset time, determining that the second characteristic mark of the residence point is preferred, and stopping the node splitting by the decision tree model.
When the residence time of the residence point is less than a first preset time, representing that the crowd at the residence point frequently flows, the residence point can be determined to be the preferred region for going to the bus stop according to the attribute data, whether other characteristic data meet preset conditions is not traced, and the residence point directly enters a residence point resource pool.
And if the number of the resident people at the resident point is greater than or equal to a first preset time length and less than a second preset time length, determining that the second feature mark of the resident point is a candidate.
When the number of residents of the resident point is between a first preset duration and a second preset duration, the second feature mark of the resident point is obtained to be a candidate, namely, other feature marks of the main force area are determined according to other attribute data of the resident point to determine whether the resident point is a preferred area, and at the moment, the decision tree model continues to split the next-level node.
And if the residence time of the residence point is greater than a second preset time, determining that the second characteristic mark of the residence point is a non-preferred area, and stopping node splitting by the decision tree model.
When the number of residents is larger than or equal to a second preset time, the bus stop does not need to be set at the residence point, and therefore the decision tree model stops node splitting.
Further, after determining that the second feature of the dwell point is a candidate, the method further includes:
determining the number of roads within a preset distance range from the resident point, and determining the third feature mark of the resident point as one of preference, candidate and non-preference according to the number of the roads.
Determining a dwell peak period of the dwell point, determining a fourth feature label of the dwell point as one of preferred, candidate, and non-preferred based on the dwell peak period.
It is understood that how to determine the third feature mark may be set according to specific situations, and is not limited to the figure with more than 2 bars being preferred and 1 bar being not preferred. The peak residence time period is a time period when the number of residents at a residence point is higher than a threshold number of people, for example, 7 o 'clock to 8 o' clock earlier, 6 o 'clock to 7 o' clock later, and there are two peak residence time periods. How to determine the fourth feature flag may be set according to specific situations, and is not limited to the peak period fourth feature flag in fig. 3 being preferred.
In principle, the decision tree model is likely to generate an overfitting phenomenon in the growing process, and the decision tree model is larger and deeper in the growing process, so that the overfitting phenomenon is caused. In order to prevent this, precautionary measures are taken in advance to avoid the tree from growing too much. For example, setting the deepest level (max-depth) of the tree, the threshold value for stopping splitting of the node, etc., or performing pruning operation on the tree after the tree completely grows.
In this embodiment, the pruning operation of the decision tree model is specifically that the number of residents is greater than a first preset number or the residence time of the residence point is less than a first preset time, and then the decision tree model stops node splitting. And if the number of the resident persons is less than or equal to a second preset number or the resident time of the resident points is greater than a second preset time, the decision tree model stops node splitting.
Further, the determining whether the parking spot is the preferred bus stop according to the feature tag of the parking spot in step 102 may include:
determining that the preferred residence point of the first characteristic mark and/or the second characteristic mark is a preferred area of the bus stop;
determining the residence point of which the first characteristic mark and the second characteristic mark are both candidates as a preferred area of the bus station;
and when one of the first characteristic mark and the second characteristic mark of the residence point is a candidate, determining whether the residence point is the preferred bus stop according to the third characteristic mark and the fourth characteristic mark of the residence point.
Of course, the judgment condition of each level of the decision tree model is modified in real time according to specific situations.
It is understood that when one of the first feature mark and the second feature mark of the residence point is a candidate, that is, when it cannot be determined whether the residence point is a preferred bus stop through the first feature mark and the second feature mark of the residence point, it is determined whether the residence point is a preferred area of the bus stop by combining the third feature mark and the fourth feature mark of the residence point. Specifically, the number of the selected bus stops is set to be M in advance, the total number of the first feature mark and/or the second feature mark which are the preferred bus stop plus the candidate bus stops of which the first feature mark and the second feature mark are both the preferred bus stop is N, and N is smaller than M, and at this time, whether the bus stops are the preferred areas is determined by the third feature mark and the fourth feature mark which need to be the bus stops, for example, the bus stops with more resident peaks at the bus stops are selected as the preferred areas of the bus stops, and the bus stops with more roads in the preset distance range of the bus stops are selected as the preferred areas of the bus stops.
Of course, the determined preferred area of the bus stop is compared and analyzed with the actual bus route construction condition, and the bus stop position can be properly increased, decreased and adjusted according to the number of residents at the residence point and road information near the residence point, so that the junction stop can be reasonably set.
The average residence time, the residence peak time, the departure frequency and the residence time of the station in different time intervals are reasonably planned according to the residence peak time of the station information on the optimal line of the algorithm. And by combining the restriction relationship of the factors and the known urban road traffic characteristics, comprehensively analyzing, reasonably adjusting the position of the station, the route trend, the non-average station spacing, the departure frequency, the station residence time and the like, and finally forming a perfect optimization scheme.
As shown in fig. 4, as an implementation of the methods shown in the above diagrams, the present application provides an embodiment of a bus route optimization system, and the embodiment of the system corresponds to the embodiment of the method shown in fig. 4.
A residence point determining module 401, configured to determine multiple residence points along a road, and determine attribute data of each residence point;
and the decision tree module 402 is configured to generate a feature tag of the residence point according to the attribute data of the residence point based on the determination condition of each level from the root node to the minimum leaf node in the decision tree model, and determine whether the residence point is the preferred bus stop according to the feature tag of the residence point.
Further, the dwell point determination module includes:
the ground dividing unit 4011 is configured to divide an urban area into a plurality of continuous geographic grids, and determine feature data of each geographic grid, where the feature data includes: density, transfer amount, coverage and imbalance coefficients;
and the clustering unit 4012 is configured to perform cluster analysis on the multiple geographic grids according to the feature data, and screen out multiple geographic grids with feature data meeting a predetermined index as residence points.
It should be noted that the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Finally, it should be noted that: the above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the present disclosure, and the present disclosure should be construed as being covered by the claims and the specification.
Claims (10)
1. A bus route optimization method is characterized by comprising the following steps:
determining a plurality of stagnation points along a road and attribute data of each stagnation point;
and generating a feature mark of the residence point according to the attribute data of the residence point based on the judging conditions of each level from the root node to the minimum leaf node in the decision tree model, and determining whether the residence point is the preferred bus stop or not according to the feature mark of the residence point.
2. The bus route optimization method of claim 1, wherein the determining a plurality of waypoints along the route comprises:
dividing a city area into a plurality of continuous geographic grids, and determining characteristic data of each geographic grid, wherein the characteristic data comprises: density, transfer amount, coverage and imbalance coefficients;
based on a clustering algorithm, carrying out clustering analysis on the plurality of geographic grids according to the characteristic data to obtain the residence points of which the characteristic data meets a preset index; the preset indexes comprise that the intensity is greater than the preset intensity, the transfer amount is greater than the preset transfer amount, the coverage is greater than the preset coverage, and the unbalance coefficient is greater than the preset constant.
3. The bus route optimization method of claim 2, wherein the determining a plurality of waypoints along the route further comprises:
if the plurality of resident points meeting the preset index have adjacent resident points, comparing the feature data of the two adjacent resident points one by one, and determining whether to remove one of the two adjacent resident points from the resident point set according to the comparison result.
4. The bus route optimization method according to claim 1, wherein the attribute data of the residence point includes: the number of residents, the residence time, the road information in the preset range of the residence point and the residence peak time.
5. The bus route optimization method according to claim 4, wherein the generating the feature labels of the residence points according to the attribute data of the residence points based on the judgment conditions of each level from a root node to a minimum leaf node in the decision tree model comprises:
determining whether the number of residents at the residence point is greater than a first preset number and/or a second preset number, wherein the first preset number is greater than the second preset number;
if the number of the resident persons is larger than the first preset number, determining that the first characteristic mark of the resident point is preferred, and stopping node splitting by the decision tree model;
if the number of the resident persons is smaller than or equal to the first preset number and larger than the second preset number, determining that the first characteristic mark of the resident point is a candidate;
and if the number of the resident persons is less than or equal to the second preset number, generating a first characteristic mark of the resident point as a non-preferred area, and stopping node splitting by the decision tree model.
6. The bus route optimization method according to claim 4, wherein the determining that the first feature of the stagnation point is a candidate further comprises:
determining whether the residence time of the residence point is less than a first preset time and/or a second preset time, wherein the first preset time is less than the second preset time;
if the residence time of the residence point is less than the first preset time, determining that the second characteristic mark of the residence point is preferred, and stopping node splitting by the decision tree model;
if the number of residents at the residence point is greater than or equal to the first preset time length and less than the second preset time length, determining that the second feature mark of the residence point is a candidate;
and if the residence time of the residence point is longer than the second preset time, determining that the second characteristic mark of the residence point is a non-preferred area, and stopping node splitting by the decision tree model.
7. The bus route optimization method according to claim 6, wherein after determining that the second feature of the stagnation point is a candidate, further comprising:
determining the number of roads within a preset distance range from the residence point, and determining a third feature marker of the residence point as one of preference, candidate and non-preference according to the number of the roads;
determining a dwell peak hour for the dwell point, determining a fourth feature label for the dwell point as one of preferred, candidate, and non-preferred based on the dwell peak hour.
8. The bus route optimization method according to claim 7, wherein the determining whether the stop point is a preferred bus stop according to the feature label of the stop point comprises:
determining that the preferred residence point of the first characteristic mark and/or the second characteristic mark is a preferred area of a bus stop;
determining the dwell point of which the first characteristic mark and the second characteristic mark are both candidates as a preferred area of the bus station;
and when one of the first characteristic mark and the second characteristic mark of the residence point is a candidate, determining whether the residence point is a preferred bus stop according to the third characteristic mark and the fourth characteristic mark of the residence point.
9. A bus route optimization system, comprising:
the residence point determining module is used for determining a plurality of residence points along the road and determining the attribute data of each residence point;
and the decision tree module is used for generating a feature label of the residence point according to the attribute data of the residence point based on the judgment condition of each level from the root node to the minimum leaf node in the decision tree model, and determining whether the residence point is the preferred bus stop or not according to the feature label of the residence point.
10. The bus route optimization system of claim 9, wherein the waypoint determination module comprises:
the system comprises a ground dividing unit, a data processing unit and a data processing unit, wherein the ground dividing unit is used for dividing an urban area into a plurality of continuous geographic grids and determining characteristic data of each geographic grid, and the characteristic data comprises: density, transfer amount, coverage and imbalance coefficients;
and the clustering unit is used for carrying out clustering analysis on the plurality of geographic grids according to the characteristic data to obtain the residence points of which the characteristic data meets the preset indexes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011440130.9A CN112651546A (en) | 2020-12-10 | 2020-12-10 | Bus route optimization method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011440130.9A CN112651546A (en) | 2020-12-10 | 2020-12-10 | Bus route optimization method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112651546A true CN112651546A (en) | 2021-04-13 |
Family
ID=75350769
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011440130.9A Pending CN112651546A (en) | 2020-12-10 | 2020-12-10 | Bus route optimization method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112651546A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113361749A (en) * | 2021-05-14 | 2021-09-07 | 北京北大千方科技有限公司 | Bus express route planning method, device, equipment and medium based on principal component analysis |
| CN113627669A (en) * | 2021-08-10 | 2021-11-09 | 中国联合网络通信集团有限公司 | Traffic route optimization processing method, device and equipment |
| CN117593167A (en) * | 2024-01-18 | 2024-02-23 | 山东国建土地房地产评估测绘有限公司 | Intelligent city planning management method and system based on big data |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104376519A (en) * | 2014-10-30 | 2015-02-25 | 中南大学 | Automatic addressing method for newly establishing railway station in mountainous area |
| CN106059816A (en) * | 2016-06-17 | 2016-10-26 | 中联物流（中国）有限公司 | Transfer warehouse site selection method and system |
| CN106570595A (en) * | 2016-11-10 | 2017-04-19 | 深圳市数字城市工程研究中心 | Subway station position selection method and system based on space big data |
| CN111091417A (en) * | 2019-12-12 | 2020-05-01 | 拉扎斯网络科技（上海）有限公司 | Site selection method and device |
| CN111274500A (en) * | 2020-01-15 | 2020-06-12 | 平安医疗健康管理股份有限公司 | Position information recommendation method and device, computer equipment and storage medium |
-
2020
- 2020-12-10 CN CN202011440130.9A patent/CN112651546A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104376519A (en) * | 2014-10-30 | 2015-02-25 | 中南大学 | Automatic addressing method for newly establishing railway station in mountainous area |
| CN106059816A (en) * | 2016-06-17 | 2016-10-26 | 中联物流（中国）有限公司 | Transfer warehouse site selection method and system |
| CN106570595A (en) * | 2016-11-10 | 2017-04-19 | 深圳市数字城市工程研究中心 | Subway station position selection method and system based on space big data |
| CN111091417A (en) * | 2019-12-12 | 2020-05-01 | 拉扎斯网络科技（上海）有限公司 | Site selection method and device |
| CN111274500A (en) * | 2020-01-15 | 2020-06-12 | 平安医疗健康管理股份有限公司 | Position information recommendation method and device, computer equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 张菲菲;许剑辉;解新路;: "GIS空间分析方法在公交站点选址中的应用", 地理空间信息, no. 01, pages 118 - 120 * |
| 杨莉;周志富;: "空间分类在连锁超市选址中的应用研究", 测绘与空间地理信息, no. 05, pages 149 - 151 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113361749A (en) * | 2021-05-14 | 2021-09-07 | 北京北大千方科技有限公司 | Bus express route planning method, device, equipment and medium based on principal component analysis |
| CN113361749B (en) * | 2021-05-14 | 2024-04-16 | 北京北大千方科技有限公司 | Bus rapid transit planning method, device, equipment and medium based on principal component analysis |
| CN113627669A (en) * | 2021-08-10 | 2021-11-09 | 中国联合网络通信集团有限公司 | Traffic route optimization processing method, device and equipment |
| CN113627669B (en) * | 2021-08-10 | 2024-02-20 | 中国联合网络通信集团有限公司 | Traffic route optimization processing method, device and equipment |
| CN117593167A (en) * | 2024-01-18 | 2024-02-23 | 山东国建土地房地产评估测绘有限公司 | Intelligent city planning management method and system based on big data |
| CN117593167B (en) * | 2024-01-18 | 2024-04-12 | 山东国建土地房地产评估测绘有限公司 | Intelligent city planning management method and system based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112651546A (en) | Bus route optimization method and system | |
| EP2630443B1 (en) | Method of determining and validating navigational priority settings utilizing probe data | |
| Weijermars | Analysis of urban traffic patterns using clustering | |
| CN110021161B (en) | Traffic flow direction prediction method and system | |
| Deng et al. | Heterogenous trip distance-based route choice behavior analysis using real-world large-scale taxi trajectory data | |
| Chowdhury et al. | A traffic congestion forecasting model using cmtf and machine learning | |
| Nelson et al. | Bicycle streetscapes: a data driven approach to mapping streets based on bicycle usage | |
| Wang et al. | Road network design in a developing country using mobile phone data: An application to Senegal | |
| CN111008730B (en) | Crowd concentration prediction model construction method and device based on urban space structure | |
| Yao et al. | Trip segmentation and mode detection for human mobility data | |
| Zilske et al. | Building a minimal traffic model from mobile phone data | |
| Naumov et al. | Estimating parameters of demand for trips by public bicycle system using GPS data | |
| Chatterjee et al. | Level of service criteria on Indian multilane highways based on platoon characteristics | |
| CN115186049A (en) | Intelligent bus alternative station site selection method, electronic equipment and storage medium | |
| Liu et al. | Analysis of passenger flow characteristics and their relationship with surrounding urban functional landscape pattern | |
| Si et al. | Data-based sorting algorithm for variable message sign location: Case study of Beijing | |
| Gokasar et al. | Estimation of influence distance of bus stops using bus GPS data and bus stop properties | |
| Dunne et al. | A large scale method for extracting geographical features on bus routes from OpenStreetMap and assessment of their impact on bus speed and reliability | |
| Fan et al. | Optimizing location of variable message signs using GPS probe vehicle data | |
| Esztergár-Kiss et al. | Mobility mapping based on a survey from the city of Berlin | |
| Attili | The demand for public transport: analysis of mobility patterns and bus stops | |
| JP7414502B2 (en) | Information processing device, information processing method and program | |
| Chmiel et al. | Rule system for speed limit determination on national roads in Poland | |
| Huber et al. | Understanding the influence of accident risk and perceived safety on bicycle route choice | |
| Pasindu et al. | Development of a highway performance index for upgrading decision making–Case study for a provincial road network in a developing country |
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 |