CN111881939A - Shared single-vehicle parking area layout method based on clustering algorithm - Google Patents
Shared single-vehicle parking area layout method based on clustering algorithm Download PDFInfo
- Publication number
- CN111881939A CN111881939A CN202010590509.1A CN202010590509A CN111881939A CN 111881939 A CN111881939 A CN 111881939A CN 202010590509 A CN202010590509 A CN 202010590509A CN 111881939 A CN111881939 A CN 111881939A
- Authority
- CN
- China
- Prior art keywords
- clustering
- parking area
- parking
- data
- shared
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Traffic Control Systems (AREA)
Abstract
A shared single-vehicle parking area layout method based on a clustering algorithm comprises the following steps: s1, obtaining historical position data of the shared bicycle; s2, carrying out coordinate conversion on the shared bicycle position data; s3, initializing clustering parameters of a DBSCAN algorithm and carrying out primary clustering; s4, adopting a k-means clustering algorithm to divide the oversize classes; s5, calculating evaluation indexes and checking traversal conditions of clustering parameters; s6, providing the optimal shared bicycle parking area position and capacity; and S7, judging the stability of the layout effect of the parking area. The method can effectively relieve the unreasonable layout of the shared single-vehicle parking areas, more pertinently lays the parking areas, improves the standardized management level of the shared single-vehicle to a certain extent, gives consideration to the factors of position information in different time periods, the service radius of the shared single-vehicle parking areas and the like to perform the layout of the parking areas, and can comprehensively plan the parking requirements in the whole time period and the walking distance of a user.
Description
Technical Field
The invention relates to the field of shared single vehicles of urban traffic, in particular to a method for arranging parking areas of the shared single vehicles based on a clustering algorithm.
Background
As an emerging mode of transportation, shared vehicles are becoming increasingly popular worldwide. Each bicycle in the shared bicycle system is equipped with a Global Positioning System (GPS) and can be rented by scanning a two-dimensional code. The user can park the rented shared bicycle on a bicycle frame or on the roadside. This provides an alternative mode of short-haul travel for the residents and solves the "last mile" problem of docking subway stations. However, these conveniences also present many problems, such as excess shared bikes, unreasonable parking, and so forth. Shared bicycles which are parked and laid randomly obstruct the running space of pedestrians and motor vehicles. This presents a significant challenge to governments and shared-bicycle operators.
Governments around the world are beginning to regulate parking of shared vehicles and control the overall fleet size of shared vehicles. The government forces operators to set up shared single-car parking areas in subway stations, bus stations and residential areas. However, the effect of parking areas in most cities in china is not ideal, mainly because parking areas do not match the real parking requirements. Therefore, it is necessary to adopt scientific methods to help government-related units and operators to properly share the single-car parking area.
Currently, most shared bicycle services use a cell phone application to rent the bicycle and pay the associated fees. The application may provide the user with a real-time location of nearby available shared bikes. The real-time static position data of the shared bicycle can just reflect the dynamic parking requirement of the shared bicycle. Therefore, the method provides a shared bicycle parking area layout method based on a clustering algorithm according to the real-time position data of the shared bicycle.
Disclosure of Invention
Aiming at the problems, the invention provides a shared single-car parking area layout method based on a clustering algorithm, which can effectively relieve the unreasonable layout of the shared single-car parking areas, more specifically lay the parking areas, and improve the standardized management level of the shared single-car to a certain extent, and gives consideration to the factors of position information in different time periods, the service radius of the shared single-car parking areas and the like to perform the layout of the parking areas, so that the parking requirements and the walking distance of a user in the whole time period can be comprehensively planned, and the invention provides the shared single-car parking area layout method based on the clustering algorithm, which comprises the following steps:
s1, obtaining historical position data of the shared bicycle;
in the step S1, historical position data of all shared vehicles in the urban area is acquired every T hours, and accumulated for 14 days; the first 7-day data is a training set, and the second 7-day data is a verification set; the historical position data of the shared single vehicles comprises the number n and the longitude of each vehicleLatitude lambda and acquisition time t;
s2, carrying out coordinate conversion on the shared bicycle position data;
the coordinates in the step S2 are converted into cluster data, and the longitude in S1 is converted into cluster dataConverting the latitude lambda data into UTM coordinate data (E, N), wherein the converted data is a clustering database;
s3, initializing clustering parameters of a DBSCAN algorithm and carrying out primary clustering;
the step S3 specifically includes the following steps:
s31, initializing parameters EPS and minPts of the DBSCAN clustering model, and selecting the EPS and the minPts from the optional set Z without putting back; the optional set Z is formed by any two-by-two combination of EPS in the range of { x |0< x <60, x in the range of N } and minPts in the range of { x |0< x <30, x in the range of N };
s32, aiming at the coordinate data (E, N) in the clustering database of the step S2, adopting the parameter values in the step S31 to perform DBSCAN clustering, and marking each group of coordinates as a first-class number or noise according to a clustering result;
s4, adopting a k-means clustering algorithm to divide the oversize classes;
the step S4 specifically includes extracting the non-noise data clustered in the step S32, and performing k-means clustering on the data with the same class number of the first class, where an initial value of k is set to 1; if the distance from the generated clustering center to each data point in the class is smaller than a critical value R1, the class does not need to be subdivided, and the serial number of the secondary class is the same as that of the primary class; otherwise, adjusting the k value to be k +1, and re-performing k-means clustering until the distance from the clustering center in each subclass to each data point in the subclass is smaller than a critical value R1, wherein the second-class number is the first-class number plus the subclass number;
s5, calculating evaluation indexes and checking traversal conditions of clustering parameters;
the step S5 specifically includes the following steps:
s51, evaluation index calculation: the evaluation indexes comprise three indexes, namely coverage rate, total parking area number and parking area average bicycle number, and the three indexes are functions related to clustering parameters EPS and minPts;
s52, testing the traversal condition of the clustering parameters: if the current optional cluster set Z is an empty set, the traversal of the cluster parameters is complete, and the step S6 is carried out; otherwise, returning to the step S3 for continuing;
s6, providing the optimal shared bicycle parking area position and capacity;
step S6, calculating and selecting an optimal clustering result according to an optimization problem, wherein the decision variables are EPS and minPts; the optimal shared bicycle parking area is a clustering center corresponding to the optimal solution, and the parking area capacity is the number of bicycles in the category corresponding to the clustering center;
s7, judging the stability of the layout effect of the parking area;
the stability of the layout effect of the parking areas in the step S7 is determined by the shortest crossing neighboring distance CNND of the training scheme and the verification scheme, and when the CNND is less than or equal to the critical value R2, the positions and the capacities of the parking areas in the step S6 are output through stability verification, and all calculation steps are ended; when the CDDN is greater than the threshold value R2, the data acquisition time interval T is decreased without passing the stability check, that is, the data acquisition frequency is increased to half of the original frequency, and the process returns to step S1 to acquire data again.
As a further improvement of the present invention, in S51, the three evaluation indexes, the coverage rate, the total parking area number and the average number of bicycles in the parking area, are specifically calculated as follows:
Total number of parking zones NP (EPS, minPts) ═ Cluster (EPS, minPts) | (2)
Wherein, | Noise (EPS, minPts) | is the number of the shared vehicles identified as Noise when the DBSCAN is clustered, | D | is the total number of the shared vehicles, | Cluster (EPS, minPts) | is the number of all the classes formed after k-means clustering.
As a further improvement of the present invention, the optimization problem in S6 is specifically calculated as follows;
wherein, the CoverageminMNB for minimum acceptable coverageminAverage number of cycles for minimum parking area, NPmaxThe maximum parking area setting number w1, w2 and w3 are weights of 0-1.
As a further improvement of the present invention, the CNND calculation formula in step S7 is as follows:
wherein n isAiFor the parking capacity of the i-th bicycle parking area in the training scheme, nBiTo verify the parking capacity of the ith bicycle parking area in the solution, dAiThe shortest distance from the ith parking area in the training scheme to any parking area in the verification scheme; dBiFor the ith stop in the verification schemeThe shortest distance from the parking area to any parking area in the training scheme; m isAAnd mBThe number of the parking areas planned in the training scheme and the verification scheme is respectively.
As a further improvement of the present invention, the training scheme and the verification scheme in step S7 are respectively calculated from the training set and the verification set in step S1.
Has the advantages that: compared with the prior art, the invention has the following beneficial effects:
1) the method can effectively relieve the unreasonable layout of the shared bicycle parking areas, more pertinently lay the parking areas, effectively solve the problems of disordered parking and disordered layout of the shared bicycle, block traffic and the like, improve the standardized management level of the shared bicycle to a certain extent, greatly improve the utilization efficiency and urban appearance of the shared bicycle, and maximally reduce the negative influence on the city while meeting the traveling of residents.
2) The method disclosed by the invention is more scientific and reasonable in parking area arrangement based on historical shared bicycle positions. The positions of the shared bicycles are dynamically changed, the difference between the position information of a peak and a peak, and between a working day and a weekend is obvious, and the parking demands of the whole time period can be comprehensively planned by considering the real-time position information of different time periods to perform parking area planning.
3) The method of the invention adopts the clustering center as the parking area position, and gives consideration to the available parking space. The cluster centers are often areas where the shared vehicles are parked most, while areas with more shared vehicles typically have space defined by parking areas.
4) The method considers the service radius of the shared single-vehicle parking area, and is more in line with the travel behaviors of users. Research shows that the user of the shared bicycle only wants to select a parking area, namely a service radius, within a range of 30-40 m away from the destination.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Detailed Description
The invention is described in further detail below with reference to the following detailed description and accompanying drawings:
the invention provides a method for arranging shared single-car parking areas based on a clustering algorithm, which can effectively relieve the unreasonable arrangement of the shared single-car parking areas, arrange the parking areas more specifically, improve the standardized management level of the shared single-car to a certain extent, and arrange the parking areas by taking account of factors such as position information of different time periods, service radius of the shared single-car parking areas and the like, so that the parking requirements of the whole time period and the walking distance of a user can be comprehensively arranged.
As shown in fig. 1, the shared single-vehicle parking area layout method based on the clustering algorithm provided by the invention comprises the following steps: s1, obtaining historical position data of the shared bicycle; s2, carrying out coordinate conversion on the shared bicycle position data;
s3, initializing clustering parameters of a DBSCAN algorithm and carrying out primary clustering; s4, adopting a k-means clustering algorithm to divide the oversize classes;
s5, calculating evaluation indexes and checking traversal conditions of clustering parameters; s6, providing the optimal shared bicycle parking area position and capacity;
and S7, judging the stability of the layout effect of the parking area. The specific implementation process is detailed below.
S1, obtaining the historical position data of the shared bicycle: as shown in table 1, the historical location data of all the shared vehicles in the urban area is acquired once every T hours (1 hour in the example), and the collection is accumulated for 14 days (06 days 00:00: 00:00 in 05 month and 2018 and 19 days 23:00:00 in 05 month and 2018); the first 7-day data is a training set (06, 00: 00-05, 2018, 12, 23, 00), and the second 7-day data is a verification set (13, 00, 2018, 05, 19, 23, 00); the historical position data of the shared single vehicles comprises the number n and the longitude of each vehicleLatitude λ, acquisition time t.
TABLE 1 shared bicycle historical location data (snippets)
S2, carrying out coordinate conversion on the shared bicycle position data: longitude in S1Converting the latitude lambda data into UTM coordinate data (E, N), wherein the converted data is a clustering database shown in a table 2; coordinate transformation methods are described in wikipedia:
https://en.wikipedia.org/wiki/Universal_Transverse_Mercator_coordinate_system。
TABLE 2 after coordinate transformation of the shared bicycle position data (intercept segment)
S3, initializing clustering parameters of the DBSCAN algorithm and carrying out primary clustering: initializing parameters EPS and minPts of the DBSCAN clustering model, wherein the EPS and the minPts are selected from the optional set Z without being replaced; the optional set Z is formed by any two-by-two combination of EPS in the range of { x |0< x <60, x in the range of N } and minPts in the range of { x |0< x <30, x in the range of N }; aiming at the coordinate data (E, N) in the clustering database in the step S2, the parameter values in the step S31 are adopted to perform DBSCAN clustering, each group of coordinates are marked as a first-class number or noise according to a clustering result, and the DBSCAN clustering method refers to Baidu encyclopedic:
https://baike.baidu.com/item/DBSCAN/4864716?fr=aladdin
TABLE 3 shared bicycle position data DBSCAN clustered result (intercepted segment)
S4, adopting a k-means clustering algorithm to divide the oversize classes: extracting the non-noise data after the last step of clustering, and carrying out k-means clustering on the data with the same class number of the first class, wherein the initial value of k is set to be 1; if the distance from the generated clustering center to each data point in the class is smaller than a critical value R1, the class does not need to be subdivided, and the serial number of the secondary class is the same as that of the primary class; otherwise, adjusting the k value to be k +1, and re-performing k-means clustering until the distance from the clustering center in each subclass to each data point in the subclass is smaller than a critical value R1 (set to be 300m in the example), wherein the second-class number is the first-class number + the subclass number; the k-means clustering method is described in Baidu encyclopedia
https://baike.baidu.com/item/K%E5%9D%87%E5%80%BC%E8%81%9A%E7%B1%BB%E7%AE%97%E6%B3%95/15779627
TABLE 4 shared bicycle position data k-means clustering partitioning oversize results (snippets)
S5, evaluation index calculation and clustering parameter traversal condition inspection: (1) and (3) evaluation index calculation: the evaluation indexes comprise three indexes, namely coverage rate, total parking area number and parking area average bicycle number, the three indexes are functions related to clustering parameters EPS and minPts, and the specific calculation formula is as follows:
Total number of parking zones NP (EPS, minPts) ═ Cluster (EPS, minPts) | (2)
Wherein, | Noise (EPS, minPts) | is the number of the shared vehicles identified as Noise when the DBSCAN is clustered, | D | is the total number of the shared vehicles, | Cluster (EPS, minPts) | is the number of all the classes formed after k-means clustering.
In this example, | Noise (EPS, minPts) | 3574, | D | 25471, | Cluster (EPS, minPts) | 1587 when EPS ═ 28, minPts |, 15, whereby Coverage (EPS, minPts) | (25471-3574)/25471 |, NP (EPS, minPts) | 1587, MNB (EPS, minPts) | 13.80 were calculated
(2) And (3) inspecting the traversal condition of the clustering parameters: if the current optional cluster set Z is an empty set, the traversal of the cluster parameters is complete, and the step S6 is carried out; otherwise, the process returns to step S3 to continue.
In this example, EPS belongs to { x |0< x <60, x belongs to N }, and there are 59 values; minPts belongs to { x |0< x <30, x belongs to N }, and 29 values exist; therefore, after the loop 59 × 29 is completed 1711 times, the optional set Z becomes an empty set, and the process proceeds to step S6.
S6, providing the optimal shared single-vehicle parking area position and capacity: selecting an optimal clustering result according to the following optimization problem, wherein the decision variables are EPS and minPts; the optimal shared bicycle parking area is a clustering center corresponding to the optimal solution, and the parking area capacity is the number of bicycles in the category corresponding to the clustering center.
Wherein, the CoverageminMNB for minimum acceptable coverageminAverage number of cycles for minimum parking area, NPmaxThe maximum parking area setting number w1, w2 and w3 are weights of 0-1.
In this example, Coverage is setmin=75%,MNBmin=10,NPmax=2000,w1=0.9,w2=0.099,w30.001. The optimum solution is obtained when EPS is 28 and minPts is 12, when a total of 1423 parking zones are formed.
S7, judging the stability of the layout effect of the parking area: the stability of the layout effect of the parking area is determined by the shortest crossing adjacent distance CNND of the training scheme and the verification scheme, when the CNND is less than or equal to a critical value R2, the position and the capacity of the parking area in the step S6 are output through stability verification, and all calculation steps are finished; when CNND is greater than the critical value R2, decreasing the data acquisition time interval T (i.e., increasing the data acquisition frequency) to half of the original value without passing through the stability test, and returning to step S1 to acquire data again;
the CNND calculation formula is as follows:
wherein n isAiFor the parking capacity of the i-th bicycle parking area in the training scheme, nBiTo verify the parking capacity of the ith bicycle parking area in the solution, dAiThe shortest distance from the ith parking area in the training scheme to any parking area in the verification scheme; dBiThe shortest distance from the ith parking area in the verification scheme to any parking area in the training scheme; m isAAnd mBThe number of the parking areas planned in the training scheme and the verification scheme is respectively. The training scheme and the verification scheme are calculated from the training set and the verification set in step S1, respectively.
In this example, at a data acquisition frequency of T ═ 1 hour, the CNND calculation result was 5m, and R2 was set to 20 m. Therefore, CNND < R2, satisfying the parking space layout effect stability requirement, outputs the parking space position and the parking space capacity in step S6 as shown in table 5.
TABLE 5 parking area location and parking area Capacity (snippets) generated at the end
The above description is only a preferred embodiment of the present invention, and is not intended to limit the present invention in any way, but any modifications or equivalent variations made according to the technical spirit of the present invention are within the scope of the present invention as claimed.
Claims (5)
1. A shared single-vehicle parking area layout method based on a clustering algorithm is characterized by comprising the following steps:
s1, obtaining historical position data of the shared bicycle;
in the step S1, historical position data of all shared vehicles in the urban area is acquired every T hours, and accumulated for 14 days; the first 7-day data is a training set, and the second 7-day data is a verification set; sharing listThe historical position data of the vehicles comprises the number n and the longitude of each vehicleLatitude lambda and acquisition time t;
s2, carrying out coordinate conversion on the shared bicycle position data;
the coordinates in the step S2 are converted into cluster data, and the longitude in S1 is converted into cluster dataConverting the latitude lambda data into UTM coordinate data (E, N), wherein the converted data is a clustering database;
s3, initializing clustering parameters of a DBSCAN algorithm and carrying out primary clustering;
the step S3 specifically includes the following steps:
s31, initializing parameters EPS and minPts of the DBSCAN clustering model, and selecting the EPS and the minPts from the optional set Z without putting back; the optional set Z is formed by any two-by-two combination of EPS in the range of { x |0< x <60, x in the range of N } and minPts in the range of { x |0< x <30, x in the range of N };
s32, aiming at the coordinate data (E, N) in the clustering database of the step S2, adopting the parameter values in the step S31 to perform DBSCAN clustering, and marking each group of coordinates as a first-class number or noise according to a clustering result;
s4, adopting a k-means clustering algorithm to divide the oversize classes;
the step S4 specifically includes extracting the non-noise data clustered in the step S32, and performing k-means clustering on the data with the same class number of the first class, where an initial value of k is set to 1; if the distance from the generated clustering center to each data point in the class is smaller than a critical value R1, the class does not need to be subdivided, and the serial number of the secondary class is the same as that of the primary class; otherwise, adjusting the k value to be k +1, and re-performing k-means clustering until the distance from the clustering center in each subclass to each data point in the subclass is smaller than a critical value R1, wherein the second-class number is the first-class number plus the subclass number;
s5, calculating evaluation indexes and checking traversal conditions of clustering parameters;
the step S5 specifically includes the following steps:
s51, evaluation index calculation: the evaluation indexes comprise three indexes, namely coverage rate, total parking area number and parking area average bicycle number, and the three indexes are functions related to clustering parameters EPS and minPts;
s52, testing the traversal condition of the clustering parameters: if the current optional cluster set Z is an empty set, the traversal of the cluster parameters is complete, and the step S6 is carried out; otherwise, returning to the step S3 for continuing;
s6, providing the optimal shared bicycle parking area position and capacity;
step S6, calculating and selecting an optimal clustering result according to an optimization problem, wherein the decision variables are EPS and minPts; the optimal shared bicycle parking area is a clustering center corresponding to the optimal solution, and the parking area capacity is the number of bicycles in the category corresponding to the clustering center;
s7, judging the stability of the layout effect of the parking area;
the stability of the layout effect of the parking areas in the step S7 is determined by the shortest crossing neighboring distance CNND of the training scheme and the verification scheme, and when the CNND is less than or equal to the critical value R2, the positions and the capacities of the parking areas in the step S6 are output through stability verification, and all calculation steps are ended; when the CDDN is greater than the threshold value R2, the data acquisition time interval T is decreased without passing the stability check, that is, the data acquisition frequency is increased to half of the original frequency, and the process returns to step S1 to acquire data again.
2. The method for arranging the shared single-vehicle parking areas based on the clustering algorithm is characterized in that three evaluation indexes, namely the coverage rate, the total parking area number and the average bicycle number of the parking areas in S51 are provided, and the specific calculation formula is as follows:
Total number of parking zones NP (EPS, minPts) ═ Cluster (EPS, minPts) | (2)
Wherein, | Noise (EPS, minPts) | is the number of the shared vehicles identified as Noise when the DBSCAN is clustered, | D | is the total number of the shared vehicles, | Cluster (EPS, minPts) | is the number of all the classes formed after k-means clustering.
3. The method for arranging the shared single-vehicle parking areas based on the clustering algorithm is characterized in that the optimization problem in the step S6 is specifically calculated as follows;
wherein, the CoverageminMNB for minimum acceptable coverageminAverage number of cycles for minimum parking area, NPmaxThe maximum parking area setting number w1, w2 and w3 are weights of 0-1.
4. The method for arranging the shared single-vehicle parking areas based on the clustering algorithm as claimed in claim 1, wherein the CNND calculation formula in the step S7 is as follows:
wherein n isAiFor the parking capacity of the i-th bicycle parking area in the training scheme, nBiTo verify the parking capacity of the ith bicycle parking area in the solution, dAiThe shortest distance from the ith parking area in the training scheme to any parking area in the verification scheme; dBiThe shortest distance from the ith parking area in the verification scheme to any parking area in the training scheme; m isAAnd mBPlanning in training scheme and verification scheme respectivelyThe number of parking areas.
5. The method for arranging the shared single-vehicle parking areas based on the clustering algorithm as claimed in claim 1, wherein the training scheme and the verification scheme in the step S7 are respectively calculated from the training set and the verification set in the step S1.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010590509.1A CN111881939B (en) | 2020-06-24 | 2020-06-24 | Shared single-vehicle parking area layout method based on clustering algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010590509.1A CN111881939B (en) | 2020-06-24 | 2020-06-24 | Shared single-vehicle parking area layout method based on clustering algorithm |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111881939A true CN111881939A (en) | 2020-11-03 |
CN111881939B CN111881939B (en) | 2021-03-09 |
Family
ID=73158109
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010590509.1A Active CN111881939B (en) | 2020-06-24 | 2020-06-24 | Shared single-vehicle parking area layout method based on clustering algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111881939B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112185014A (en) * | 2020-04-07 | 2021-01-05 | 江苏智途科技股份有限公司 | Method for judging rationality of parking points of shared bicycle |
CN113240898A (en) * | 2021-04-30 | 2021-08-10 | 云上青海大数据产业有限公司 | Big data information acquisition method and system |
CN113453154A (en) * | 2021-07-26 | 2021-09-28 | 刘养明 | Related art for shared bicycle parking management |
CN117853714A (en) * | 2024-03-06 | 2024-04-09 | 北京阿帕科蓝科技有限公司 | Parking area generation method, device, computer equipment and storage medium |
Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP3040909A1 (en) * | 2015-01-05 | 2016-07-06 | Delphi Technologies, Inc. | Method of providing an envelope with respect to a cluster |
CN107045673A (en) * | 2017-03-31 | 2017-08-15 | 杭州电子科技大学 | Public bicycles changes in flow rate amount Forecasting Methodology based on heap Model Fusion |
CN107256017A (en) * | 2017-04-28 | 2017-10-17 | 中国农业大学 | route planning method and system |
CN107292798A (en) * | 2017-06-29 | 2017-10-24 | 国信优易数据有限公司 | A kind of shared bicycle parks determination method and device a little |
CN107704868A (en) * | 2017-08-29 | 2018-02-16 | 重庆邮电大学 | Tenant group clustering method based on Mobile solution usage behavior |
CN108664995A (en) * | 2018-04-18 | 2018-10-16 | 宁波工程学院 | More granularity city public bicycle dispatching methods based on DBScan and system |
CN108764555A (en) * | 2018-05-22 | 2018-11-06 | 浙江大学城市学院 | A kind of shared bicycle based on Hadoop parks a site selecting method |
CN108876136A (en) * | 2018-06-11 | 2018-11-23 | 北京工商大学 | Recommend the attack of terrorism methods of risk assessment of innovatory algorithm based on position |
KR101957343B1 (en) * | 2017-11-03 | 2019-03-12 | 한남대학교 산학협력단 | Method for using vehicles of parking lot as resource of datacenter |
CN109558533A (en) * | 2018-10-29 | 2019-04-02 | 广东奥博信息产业股份有限公司 | A kind of personalization content recommendation method and device based on multiple cluster |
CN109902969A (en) * | 2019-03-13 | 2019-06-18 | 武汉大学 | A kind of shared bicycle release position planing method based on OD data |
CN110751531A (en) * | 2018-11-13 | 2020-02-04 | 北京嘀嘀无限科技发展有限公司 | Track identification method and device and electronic equipment |
CN111121803A (en) * | 2019-11-27 | 2020-05-08 | 北京中交兴路信息科技有限公司 | Method and device for acquiring common stop points of road |
CN111160385A (en) * | 2019-11-27 | 2020-05-15 | 北京中交兴路信息科技有限公司 | Method, device, equipment and storage medium for aggregating mass location points |
-
2020
- 2020-06-24 CN CN202010590509.1A patent/CN111881939B/en active Active
Patent Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP3040909A1 (en) * | 2015-01-05 | 2016-07-06 | Delphi Technologies, Inc. | Method of providing an envelope with respect to a cluster |
CN107045673A (en) * | 2017-03-31 | 2017-08-15 | 杭州电子科技大学 | Public bicycles changes in flow rate amount Forecasting Methodology based on heap Model Fusion |
CN107256017A (en) * | 2017-04-28 | 2017-10-17 | 中国农业大学 | route planning method and system |
CN107292798A (en) * | 2017-06-29 | 2017-10-24 | 国信优易数据有限公司 | A kind of shared bicycle parks determination method and device a little |
CN107704868A (en) * | 2017-08-29 | 2018-02-16 | 重庆邮电大学 | Tenant group clustering method based on Mobile solution usage behavior |
KR101957343B1 (en) * | 2017-11-03 | 2019-03-12 | 한남대학교 산학협력단 | Method for using vehicles of parking lot as resource of datacenter |
CN108664995A (en) * | 2018-04-18 | 2018-10-16 | 宁波工程学院 | More granularity city public bicycle dispatching methods based on DBScan and system |
CN108764555A (en) * | 2018-05-22 | 2018-11-06 | 浙江大学城市学院 | A kind of shared bicycle based on Hadoop parks a site selecting method |
CN108876136A (en) * | 2018-06-11 | 2018-11-23 | 北京工商大学 | Recommend the attack of terrorism methods of risk assessment of innovatory algorithm based on position |
CN109558533A (en) * | 2018-10-29 | 2019-04-02 | 广东奥博信息产业股份有限公司 | A kind of personalization content recommendation method and device based on multiple cluster |
CN110751531A (en) * | 2018-11-13 | 2020-02-04 | 北京嘀嘀无限科技发展有限公司 | Track identification method and device and electronic equipment |
CN109902969A (en) * | 2019-03-13 | 2019-06-18 | 武汉大学 | A kind of shared bicycle release position planing method based on OD data |
CN111121803A (en) * | 2019-11-27 | 2020-05-08 | 北京中交兴路信息科技有限公司 | Method and device for acquiring common stop points of road |
CN111160385A (en) * | 2019-11-27 | 2020-05-15 | 北京中交兴路信息科技有限公司 | Method, device, equipment and storage medium for aggregating mass location points |
Non-Patent Citations (4)
Title |
---|
DE ZHAO 等: "Effect of built environment on shared bicycle reallocation: A case study on Nanjing, China", 《TRANSPORTATION RESEARCH PART A: POLICY AND PRACTICE》 * |
庄夏: "基于DBSCAN和Kmeans的用户地理位置聚类算法研究", 《数字化用户》 * |
王霞 等: "基于混合聚类分析的共享单车停放点位置合理性研究", 《数字技术与应用》 * |
龙拥军 等: "城镇商业活动空间相互作用的测算方法探讨", 《贵州教育学院学报》 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112185014A (en) * | 2020-04-07 | 2021-01-05 | 江苏智途科技股份有限公司 | Method for judging rationality of parking points of shared bicycle |
CN113240898A (en) * | 2021-04-30 | 2021-08-10 | 云上青海大数据产业有限公司 | Big data information acquisition method and system |
CN113240898B (en) * | 2021-04-30 | 2022-11-22 | 云上青海大数据产业有限公司 | Big data information acquisition method |
CN113453154A (en) * | 2021-07-26 | 2021-09-28 | 刘养明 | Related art for shared bicycle parking management |
CN117853714A (en) * | 2024-03-06 | 2024-04-09 | 北京阿帕科蓝科技有限公司 | Parking area generation method, device, computer equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN111881939B (en) | 2021-03-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111881939B (en) | Shared single-vehicle parking area layout method based on clustering algorithm | |
CN108596727B (en) | Management and decision-making method for shared bicycle | |
CN110288212B (en) | Improved MOPSO-based electric taxi newly-built charging station site selection method | |
CN105427594B (en) | A kind of public transport section volume of the flow of passengers acquisition methods and system based on two-way passenger flow of getting on the bus | |
Wang et al. | Parking practices and policies under rapid motorization: The case of China | |
CN107871184A (en) | A kind of site selecting method of the electric automobile charging station of facing area electrically-charging equipment | |
CN103295414A (en) | Bus arrival time forecasting method based on mass historical GPS (global position system) trajectory data | |
CN104166895A (en) | Public bike scheduling area dividing method | |
CN104166897A (en) | Public bike scheduling monitoring method | |
KR20200127842A (en) | Real time shared parking service system | |
Qu et al. | Location optimization for urban taxi stands based on taxi GPS trajectory big data | |
CN104318081A (en) | Method for allocating bicycles at public bicycle rental stations with urgent demand in city | |
CN104240042A (en) | Carbon emission management system based on public bicycle system and accumulating method for carbon emission management system | |
Zhou et al. | Research on resource allocation optimization of smart city based on big data | |
Wang et al. | Multi-objective optimization of customized bus routes based on full operation process | |
Cui et al. | Study on the selection model of staying adjustment bus lines along rail transit | |
CN113393113B (en) | Method and system for tracing parking fee evasion in road based on theoretical credit evaluation of complex network | |
CN110223103A (en) | Taximeter system and its working method based on Beidou integrated navigation | |
CN107229988A (en) | A kind of Optimization Method for Location-Selection of intelligent road side equipment | |
CN108197078A (en) | A kind of method that the public transport section volume of the flow of passengers is calculated based on Based on Bus IC Card Data | |
CN108399736A (en) | A kind of effective vehicle number acquisition methods of district-share bicycle based on service time | |
Jara-Díaz et al. | Optimal pricing and design of station-based bike-sharing systems: A microeconomic model | |
Zhao et al. | Optimization of intensive land use in blocks of Xi’an from the perspective of bicycle travel | |
Li et al. | Flexible Bus Route Setting and Scheduling Optimization Adapted to Spatial-temporal Variation of Passenger Flow. | |
CN108629522B (en) | Public bicycle scheduling method based on cluster analysis |
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 |