CN115879737A - Shared bicycle station site selection method based on density and access degree balanced clustering - Google Patents
Shared bicycle station site selection method based on density and access degree balanced clustering Download PDFInfo
- Publication number
- CN115879737A CN115879737A CN202310022588.XA CN202310022588A CN115879737A CN 115879737 A CN115879737 A CN 115879737A CN 202310022588 A CN202310022588 A CN 202310022588A CN 115879737 A CN115879737 A CN 115879737A
- Authority
- CN
- China
- Prior art keywords
- grid
- density
- clustering
- shared
- site
- 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
Images
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention discloses a shared bicycle station site selection method based on density and access degree balance clustering, wherein an access balance coefficient is introduced, and a candidate area of a shared bicycle station is clustered through a composite clustering algorithm of the density and the balance coefficient; the method comprises the steps of obtaining a GPS data set of a single vehicle as a sample point data set, improving and clustering the sample point data set by combining the characteristics of a Clique grid clustering algorithm, obtaining a plurality of shared site candidate addresses, optimizing each shared site candidate address, and determining the optimal shared site address by combining POI matching in the area. The complex attribute condition is formally defined by using a Boolean expression, and then the clustering result of the shared single-vehicle station under the complex attribute condition is given based on the density and the threshold value. The method has the advantages of high efficiency, high accuracy, light weight and flexibility, can be used for carrying out data mining on mass user travel OD data, analyzing a hotspot gathering area of the order form of the single vehicle user, and providing good early-stage data preparation for the single vehicle station.
Description
Technical Field
The invention relates to the field of data mining analysis, in particular to a shared bicycle station site selection method based on density and access degree balanced clustering
Background
In the first and second stages of the development of public bicycles, because the bicycles are provided with piles and need to be parked at fixed positions, the parking behaviors of users are greatly restrained, and the traffic or management is not influenced. The shared bicycle is an emerging public bicycle sharing service, is dominated by commercial operating companies and depends on the development of the Internet. It supports intelligence to sweep sign indicating number unblock, does not have fixed parking stake, and the flexibility is strong, and use density is big. The mode of 'taking and using at any time and stopping and walking at any time' is adopted, the mobile operation is flexible, and the selectable distance of a user is 1-3 kilometers. The method can be used as a connection scheme of a traditional traffic mode, the popularization of the shared bicycle shows the flexibility and convenience of the shared bicycle, and the problem of the last kilometer in a city is well solved.
Due to the fact that the Chinese market is large in user quantity and high in daily use frequency, the shared bicycle has the most active use market in the world, has better expectation on the consumption market of the shared bicycle, and shows great advantages in application of the shared bicycle. The sharing bicycle system provides a low-carbon and environment-friendly travel mode for urban residents. However, since there is a certain randomness in the usage of the shared bicycle by the user, different areas often show a phenomenon that the number of the bicycles is unbalanced. The high-demand area for bicycle renting has no bicycle, and the high-demand area for returning the bicycle has no more space. This condition is known as the tidal phenomenon of a shared bicycle. This phenomenon is more severe during morning and evening peak hours. The parking of shared vehicles is too discrete, which is undoubtedly a challenge for the shared vehicle companies, increasing their costs of daily management. For users, the problem of no adjacent vehicles or difficulty in finding vehicles exists in the peak period of vehicle utilization, so that the two problems can be flexibly solved by arranging the parking station. This approach, also known as the electronic fence for the shared bicycle, can be used for parking and access to the shared bicycle.
At present, K-means and DBSAN are used as common traffic node clustering modes in markets and researches, and a grid clustering mode called Clique also appears, wherein the clustering mode is a grid clustering mode based on density. The site candidates sharing the bicycle are also often subjected to site selection planning in a clustering manner.
The traditional clustering of shared sites for sharing a single vehicle is mostly based on density to perform clustering, and actual life application scenes are ignored. For example, considering the space-time factor, the shared bicycle presents a certain morning and evening peak tide phenomenon, and the number of the shared bicycle presents different spatial distribution in different time periods, so that the shared bicycle can be used as a cluster with a certain limitation. The station setting of the shared bicycle can consider inflow and outflow of the area, and the inflow and outflow can be used as a clustering condition to enable the vehicle taking number set by the station to be stabilized in a balanced state, so that vehicle searching and vehicle management are facilitated. In order to solve the problems, the invention provides a shared bicycle station site selection method based on density and access degree balance clustering.
Disclosure of Invention
As a re-extension of an emerging urban traffic network, the shared bicycle well solves the problem of the last kilometer of an urban traffic system, and as a connection scheme of a traditional traffic mode, the popularization of the shared bicycle shows the flexibility and convenience of the shared bicycle. However, due to the characteristic of being too flexible, the cost of manpower and material resources consumed during vehicle recovery and maintenance is very high, traffic silting caused by irregular parking of the vehicles is also caused, and the road traffic travel is influenced. Therefore, a shared single-vehicle station can be established at the roadside, and management of single-vehicle enterprises and convenience in traveling and vehicle searching of users are facilitated. Planning and designing sharing bicycle recommends the parking point and has important research meaning in the use and the management of sharing bicycle, not only helps enterprise rational planning and construction fence, still can improve sharing bicycle availability and utilization ratio, alleviates sharing bicycle's morning and evening tides phenomenon, improves green trip proportion. The arrangement of the stations is favorable for guiding and standardizing the parking behaviors of users, avoids the phenomena of influencing city appearance and city appearance, such as disordered parking, disordered placement, occupation of other road resources and the like, is favorable for reducing the operation cost of the shared single-vehicle enterprises, and improves the service quality and social benefits. The rescheduling of the shared bicycle is beneficial to relieving the phenomena of difficult vehicle utilization and silting caused by unreasonable distribution of the shared bicycle.
With the rapid development of urban roads and transportation systems, the release of single vehicles in a shared single vehicle system is increasingly expanded, and meanwhile, the development of the shared single vehicle system is also influenced and limited by various factors, such as limited number of shared single vehicles and unstable parking geographic positions, so that the development of the existing shared single vehicle system is already subjected to bottlenecks, and the market attraction of the shared single vehicle system is gradually weakened and reduced. In particular, the optimization problem of the shared bicycle space and the unbalance problem caused by the peak passenger flow tide phenomenon are increasingly remarkable. In addition, whether the selection of the position of a single vehicle release point in the system is reasonable or not, how to establish the release amount among different stations, an effective space configuration model is not obtained at present, and the study on the travel characteristics and space optimization configuration of the shared single vehicle has important significance for solving the problem of imbalance caused by mismatching of the spatial travel behaviors of residents and the spatial configuration of the single vehicle.
The technical scheme adopted by the invention is that a shared bicycle station site selection method based on density and access degree balanced clustering is provided, an access balance coefficient is introduced, and candidate areas of stations of shared bicycles are clustered through a composite clustering algorithm of the density and the balance coefficient; the shared sites are set through matching of different priorities of the POI sites, the problem that shared bicycles occupy urban traffic roads randomly in urban traffic is solved, and the management pressure of an urban traffic network is relieved. The method comprises the steps of obtaining a GPS data set of a single vehicle as a sample point data set, improving and clustering the sample point data set by combining the characteristics of a Clique grid clustering algorithm, obtaining a plurality of shared site candidate addresses, optimizing each shared site candidate address, and determining the optimal shared site address by combining POI matching in the area.
Clique grid clustering is only aimed at density clustering, but shared bicycles are influenced by space-time factors and the taking frequency more, and the fact that the bicycle entering a certain area and leaving the certain area within one day is guaranteed to be stabilized at a certain balance threshold value by considering the balance value coefficient of the entrance and exit degree of the bicycle entering the certain area and leaving the certain area is not taken as the clustering condition, which means that the supply and demand of the area are stabilized within a range.
The clustering algorithm in the invention relates to a process, and provides a group community search algorithm based on complex attribute conditions of access balance and density composition. The complex attribute condition is formally defined by using a Boolean expression, and then the clustering result of the shared single-vehicle station under the complex attribute condition is given based on the density and the threshold value. On the basis of Clique algorithm, a density threshold value is passed in advance, a boundary grid is judged by using the density threshold value of the boundary grid to improve the cluster boundary precision, the grid clustering algorithm directly projects a data object into a grid space according to a given grid step length, the grid density and a balance value are calculated, if the grid density and the balance value are greater than the given density threshold value, the grid is determined to be a dense grid and a balanced grid, the current cluster is added, the grid is searched until all adjacent grids are non-dense grids and non-balanced grids, and the cycle is ended; the above operations are repeated until all clusters are found.
The scheme provided by the invention has high efficiency and accuracy, can provide an effective solution for sharing the travel demand of the single vehicle under the condition of large data volume of a super-large city, carries out data mining on mass user travel OD data, analyzes to obtain a hotspot gathering area of a single vehicle user order, provides good early-stage data preparation for a single vehicle station, and has the characteristics of light weight and flexibility.
Drawings
FIG. 1 is an overall scheme architecture diagram.
FIG. 2 is a schematic diagram of data preprocessing.
Fig. 3 is a structural diagram of a clustering algorithm.
Fig. 4 is a block diagram of the addressing algorithm.
Detailed Description
The technical scheme of the invention will be clearly and specifically described below with reference to the accompanying drawings in the embodiment of the invention.
The core solution of the technology of the invention is a method for improving shared bicycle station site selection based on CLIQUE grid clustering, which is realized by the following steps: preprocessing GPS data of a single vehicle locking and unlocking order, determining a travel track of a passenger according to the preprocessed data, and obtaining a longitude and latitude set of a discrete destination to which the passenger goes; clustering longitude and latitude sets of discrete end points to which passengers go, obtaining gathering areas where orders of the passengers start and end by adopting an improved BLA-CLIQUE clustering method in the process of density clustering, further carrying out iterative processing on clustering results of the gathering areas where the orders of the passengers start and end to obtain the gathering areas to which the passengers go after the iterative processing, namely clustering results, matching POI points according to preset rules aiming at the clustering results, and finally determining the required candidate stations of the shared bicycle.
Predefining: 1) Grid cell: DS = D 1 ，D 2 ，D 3 ，...，D n Is an n-dimensional data set, subspace D i Is expanded to be equal to the maximum subspace D max And D is i According to the grid step length g s Is divided into m equal intervals to divide D i Into m disjoint rectangular cells, i.e. grid cells g. 2) Dense unit: given a density threshold θ d When DS is projected onto the number of data objects in the range g, x > θ d When g is dense unit gd; for non-dense units
And vice versa. 3) A balancing unit: given a threshold value of equilibrium theta b When DS is projected onto the number of data objects in the range g, x > θ d When g is the balancing unit g b (ii) a For unbalanced cells
And vice versa. 4) Boundary grid: given a threshold value ε ->
g≠g b And &>
g b E { contiguous lattice of g } if g > θ, then g is the boundary grid.
The preprocessing method comprises the steps of carrying out sample denoising and processing on order data of a shared bicycle, removing data with obvious deviation and errors in positioning, cutting the order data, only keeping GPS longitude and latitude data of unlocking and locking, and generating a new csv file.
After preprocessing, defining a density threshold value and a balance coefficient, obtaining a sample point data set, dividing a city into a plurality of grids with equal length and width according to the grid granularity which can be defined by user, and marking the grid unit as an unaccessed state; randomly selecting an unaccessed sample grid from the grid cell set, and marking the sample grid as an accessed state; judging whether the selected grid cell meets the conditions that the grid cell is greater than a density threshold and greater than a balance coefficient threshold; if yes, marking the grid unit as a grid meeting the condition; if not, no processing is performed firstly; in the iteration, when the grid meets the condition, a grid around the grid is searched, and whether the selected grid unit belongs to other clusters is judged; if yes, marking the grid unit as an accessed state; if not, merging the sample data of the peripheral grids into the two grids, recalculating the density and the entrance and exit degree balance coefficient of the merged grid, and judging whether the density and threshold conditions are met. If yes, the clusters are combined into one cluster, and if not, no processing is carried out. After the whole city grid unit is iterated, a plurality of clusters can be obtained. The grid granularity, the density threshold value and the balance coefficient can be customized to adapt to different clustering conditions, for example, the number of shared vehicles in the clustered urban grid area cannot be smaller than a certain threshold value, the inflow and outflow stability of the vehicles in the grid area is larger than a certain threshold value, and the vehicles in the area can be used as a station candidate area when representing the frequent use of the vehicles in the area; the following is a detailed description of the use of the BLA-CLIQUE clustering algorithm:
1) Dividing the sample set into grid units with self-defined sizes according to the longitude and latitude of a city, wherein each grid unit is the same in size, and marking all the grid units as unaccessed grids;
2) Randomly selecting a cell as a cluster with the number of 0, and marking the cell as accessed 'visited';
3) Traversing the peripheral grid of the cluster by taking the cluster as a center, judging whether the peripheral grid is accessed or not, if the peripheral grid is accessed, judging that the peripheral grid is gathered in other clusters, not processing, if the peripheral grid is not accessed, combining the peripheral grid with the previous cluster to recalculate the density and balance threshold, and if the density is greater than the density threshold and the balance coefficient is greater than the balance coefficient threshold, adding the peripheral grid into the cluster and marking the cluster as accessed 'visited', and if the density is not met, not processing;
4) And sequentially iterating and traversing, and finally clustering to obtain a cluster set which is the area of the candidate site.
The specific method for determining the required shared bicycle candidate sites by matching the POI sites according to the preset rules aiming at the clustering results is as follows: 1) Setting a building, a residential district, a hotel, a supermarket and a subway station in the area as a first priority, a second priority, a third priority and a fourth priority respectively; 2) And acquiring the coordinates of the central point of each cluster according to the clustered result. The method comprises the following specific steps: the MapGis software can be used for respectively connecting longitude and latitude points of all sample data in each cluster to construct a corresponding spatial region, and then extracting and outputting coordinates of a central point; 3) For the central point coordinates with the number corresponding to the cluster number obtained in the step 2), firstly, carrying out site matching of POI (i.e. interest points) on the area within the set range, if a stop site meeting the requirements is selected, if POI of the first level and the second level exists, outputting the final result, and if no suitable site is matched, further expanding the matching range for matching; if the sites with the first priority and the second priority are not matched, the POI sites with the third priority and the POI sites with the fourth priority are considered for matching; 4) Obtaining a candidate site corresponding to each cluster by a method of dynamically matching POI; 5) And finally, considering the consumption ability of passengers and the preference of travel willingness comprehensively, and setting a trial operation site as a shared single-vehicle site.
Compared with the prior art, the invention has the advantages that: according to the method for selecting the shared single vehicle candidate station, not only is the common density used as a clustering condition, but also the vehicle use condition during clustering is considered, the data dimension is greatly reduced, the purpose of jointly measuring the two conditions in the clustering process can be realized, and the accuracy and pertinence of a clustering result are finally improved. The invention improves the native CLIQUE grid clustering algorithm based on the clustering algorithm of BLA-CLIQUE, and increases the data magnitude of clustering calculation. Finally, through POI site matching of a specific rule, candidate site selection scenes with different requirements can be met, the result convergence is fast, and meanwhile, the accuracy is high. It should be understood that although the specification describes embodiments, not every embodiment includes only a single embodiment, and such description is for clarity purposes only, and it will be understood by those skilled in the art that the specification as a whole may be read as a whole and that the embodiments may be practiced in various combinations as will be understood by those skilled in the art.
The above-listed detailed description is only a specific description of possible embodiments of the present invention, and they are not intended to limit the scope of the present invention, and all equivalent embodiments or modifications made without departing from the technical spirit of the present invention should be included in the scope of the present invention.
Claims (6)
1. A shared bicycle station site selection method based on density and access degree balance clustering is characterized in that an access balance coefficient is introduced, and candidate areas of stations of shared bicycles are clustered through a composite clustering algorithm of the density and the balance coefficient; establishing shared sites through matching of different priorities of POI sites, obtaining a GPS data set of a single vehicle as a sample point data set, improving by combining the characteristics of a Clique grid clustering algorithm, clustering the sample point data set, obtaining a plurality of shared site candidate addresses, optimizing each shared site candidate address, and determining the optimal shared site address by combining POI matching in the area;
formally defining a complex attribute condition by using a Boolean expression, and then giving a clustering result of the shared single-vehicle station under the complex attribute condition based on the density and a threshold value; based on the Clique algorithm, a density threshold value is passed in advance, and a boundary grid is judged by using the density threshold value of the boundary grid so as to improve the cluster boundary precision, the grid clustering algorithm directly projects a data object into a grid space according to a given grid step length, the grid density and a balance value are calculated, if the grid density and the balance value are greater than the given density threshold value, the grid is determined to be dense and balanced, the current cluster is added, the grid is searched until all adjacent grids are non-dense and non-balanced, and the circulation is ended; the above operations are repeated until all clusters are found.
2. The shared bicycle site location method based on density and access balance clustering of claim 1, characterized in that GPS data of a bicycle locking and unlocking order is preprocessed, a travel track of a passenger is determined according to the preprocessed data, and a longitude and latitude set of a discrete destination to which the passenger goes is obtained; clustering longitude and latitude sets of discrete end points to which passengers go, obtaining gathering areas where orders of the passengers start and end by adopting an improved BLA-CLIQUE clustering method in the process of density clustering, then performing iterative processing on clustering results of the gathering areas where the orders of the passengers start and end to obtain the gathering areas to which the passengers go after the iterative processing, namely clustering results, matching POI points according to preset rules aiming at the clustering results, and finally determining the required shared bicycle candidate stations.
3. The method for locating the shared bicycle stations based on the density and entrance-exit degree balance clustering as claimed in claim 1, wherein the following are predefined: 1) Grid cell: DS = D 1 ，D 2 ，D 3 ，...，D n Is an n-dimensional data set, subspace D i Is extended to be equal to the maximum subspace D max And D is i Is divided into m equal intervals according to the grid step size gs, thereby dividing D i Dividing the grid into m disjoint rectangular units, namely grid units g; 2) Dense unit: given a density threshold θ d When DS is projected onto the number of data objects in the range g, x > θ d When g is dense unit gd; for non-dense units
And vice versa; 3) A balancing unit: given a threshold value of equilibrium theta b When DS is projected onto the number of data objects in the range g, x > θ b G is the balancing unit gb; for unbalanced cells
Vice versa; 4) Boundary grid: given a threshold value ε ->
g≠g b And &>
g b E { contiguous lattice of g } if g θ, then g is the boundary grid.
4. The method as claimed in claim 1, wherein the preprocessing method comprises the steps of de-noising and processing samples of order data of the shared bicycle, removing data with obvious offset and errors in positioning, clipping the order data, only keeping GPS longitude and latitude data for unlocking and locking, and generating a new csv file.
5. The method for locating the shared bicycle sites based on the density and access degree balance clustering of claim 1, wherein after preprocessing, a density threshold value and a balance coefficient are defined, a sample point data set is obtained, a city is divided into a plurality of grids with equal length and width according to the self-defined grid granularity, and the grid unit is marked to be in an unaccessed state; randomly selecting an unaccessed sample grid from the grid cell set, and marking the sample grid as an accessed state; judging whether the selected grid cell meets the conditions that the grid cell is greater than a density threshold and greater than a balance coefficient threshold; if yes, marking the grid unit as a grid meeting the condition; if not, no processing is firstly carried out; in the iteration, when the grid meets the condition, a grid around the grid is searched, and whether the selected grid unit belongs to other clusters is judged; if yes, marking the grid unit as an accessed state; if not, merging the sample data of the peripheral grids into the two grids, recalculating the density and the entrance and exit degree balance coefficient of the merged grid, and judging whether the density and threshold conditions are met; if yes, combining the clusters into a cluster, and if not, not processing; obtaining a plurality of clusters after iterating the whole city grid unit; the grid granularity, the density threshold value and the balance coefficient are customized to adapt to different clustering conditions.
6. The method for shared bicycle site location based on density and in-out balanced clustering of claim 2, wherein the BLA-CLIQUE clustering algorithm is described in detail as follows:
1) Dividing the sample set into grid units with self-defined sizes according to the longitude and latitude of a city, wherein each grid unit is the same in size, and marking all the grid units as unaccessed grids;
2) Randomly selecting a cell as a cluster with the number of 0, and marking the cell as accessed 'visited';
3) Traversing the peripheral grid of the cluster by taking the cluster as a center, judging whether the peripheral grid is accessed, if the peripheral grid is accessed, judging that the peripheral grid is gathered in other clusters, not processing the peripheral grid, if the peripheral grid is not accessed, merging the peripheral grid and the previous clusters to recalculate the density and balance threshold, and if the density is greater than the density threshold and the balance coefficient is greater than the balance coefficient threshold, adding the peripheral grid into the cluster and marking the peripheral grid as accessed 'visited' and not processing the peripheral grid if the density is not greater than the density threshold and the balance coefficient is greater than the balance coefficient threshold;
4) Sequentially iterating and traversing, and finally clustering to obtain a cluster set which is the area of the candidate site;
the specific method for determining the required shared bicycle candidate site by matching the POI site according to the preset rule aiming at the clustering result is as follows: 1) Setting a building, a residential district, a hotel, a supermarket and a subway station in the region as a first priority, a second priority, a third priority and a fourth priority respectively; 2) Acquiring the central point coordinate of each cluster according to the clustered result; the method comprises the following specific steps: respectively connecting longitude and latitude points of all sample data in each cluster by using MapGis software to construct a corresponding spatial region, and then extracting and outputting coordinates of a central point; 3) Carrying out POI site matching on the area within the set range by the central point coordinates with the number corresponding to the cluster number obtained in the step 2), outputting a final result if a stop site meeting the requirements is selected, and if no suitable site is matched, further expanding the matching range for matching; if the sites with the first priority and the second priority are not matched, the POI sites with the third priority and the POI sites with the fourth priority are considered for matching; 4) Obtaining a candidate site corresponding to each cluster by a method of dynamically matching POI; 5) And finally, comprehensively considering the consumption capacity of passengers and the preference of travel willingness, and setting a trial operation site as a shared single-vehicle site.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310022588.XA CN115879737A (en) | 2023-01-08 | 2023-01-08 | Shared bicycle station site selection method based on density and access degree balanced clustering |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310022588.XA CN115879737A (en) | 2023-01-08 | 2023-01-08 | Shared bicycle station site selection method based on density and access degree balanced clustering |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115879737A true CN115879737A (en) | 2023-03-31 |
Family
ID=85758276
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310022588.XA Pending CN115879737A (en) | 2023-01-08 | 2023-01-08 | Shared bicycle station site selection method based on density and access degree balanced clustering |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115879737A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116503098A (en) * | 2023-06-27 | 2023-07-28 | 北京阿帕科蓝科技有限公司 | Mining method, mining device, computer equipment and storage medium for shared vehicle station |
| CN116611678A (en) * | 2023-07-21 | 2023-08-18 | 北京阿帕科蓝科技有限公司 | Data processing method, device, computer equipment and storage medium |
| CN116703132A (en) * | 2023-08-08 | 2023-09-05 | 北京阿帕科蓝科技有限公司 | Management method and device for dynamic scheduling of shared vehicles and computer equipment |
| CN116798234A (en) * | 2023-08-28 | 2023-09-22 | 北京阿帕科蓝科技有限公司 | Method, device, computer equipment and storage medium for determining station parameter information |
| CN117454436A (en) * | 2023-12-22 | 2024-01-26 | 北京天润基业科技发展股份有限公司 | Data alignment method and system based on multiplication group and electronic equipment |
-
2023
- 2023-01-08 CN CN202310022588.XA patent/CN115879737A/en active Pending
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116503098A (en) * | 2023-06-27 | 2023-07-28 | 北京阿帕科蓝科技有限公司 | Mining method, mining device, computer equipment and storage medium for shared vehicle station |
| CN116503098B (en) * | 2023-06-27 | 2023-11-14 | 北京阿帕科蓝科技有限公司 | Mining method, mining device, computer equipment and storage medium for shared vehicle station |
| CN116611678A (en) * | 2023-07-21 | 2023-08-18 | 北京阿帕科蓝科技有限公司 | Data processing method, device, computer equipment and storage medium |
| CN116611678B (en) * | 2023-07-21 | 2023-12-01 | 北京阿帕科蓝科技有限公司 | Data processing method, device, computer equipment and storage medium |
| CN116703132A (en) * | 2023-08-08 | 2023-09-05 | 北京阿帕科蓝科技有限公司 | Management method and device for dynamic scheduling of shared vehicles and computer equipment |
| CN116703132B (en) * | 2023-08-08 | 2023-12-12 | 北京阿帕科蓝科技有限公司 | Management method and device for dynamic scheduling of shared vehicles and computer equipment |
| CN116798234A (en) * | 2023-08-28 | 2023-09-22 | 北京阿帕科蓝科技有限公司 | Method, device, computer equipment and storage medium for determining station parameter information |
| CN116798234B (en) * | 2023-08-28 | 2024-01-26 | 北京阿帕科蓝科技有限公司 | Method, device, computer equipment and storage medium for determining station parameter information |
| CN117454436A (en) * | 2023-12-22 | 2024-01-26 | 北京天润基业科技发展股份有限公司 | Data alignment method and system based on multiplication group and electronic equipment |
| CN117454436B (en) * | 2023-12-22 | 2024-02-27 | 北京天润基业科技发展股份有限公司 | Data alignment method and system based on multiplication group and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115879737A (en) | Shared bicycle station site selection method based on density and access degree balanced clustering | |
| CN108596202B (en) | Method for calculating personal commuting time based on mobile terminal GPS positioning data | |
| CN108629974B (en) | Traffic operation index establishing method considering urban road traffic network characteristics | |
| CN107316098B (en) | Automobile leasing point addressing method based on user behavior analysis | |
| CN105844362B (en) | Urban traffic comprehensive trip decision-making device | |
| CN107133700A (en) | Mobile phone signaling data road network method based on R* tree indexes | |
| Wagner et al. | Smart city planning-developing an urban charging infrastructure for electric vehicles | |
| WO2023050955A1 (en) | Urban functional zone identification method based on function mixing degree and ensemble learning | |
| CN110728305A (en) | Taxi passenger-carrying hot spot region mining method based on grid information entropy clustering algorithm | |
| CN109189949A (en) | A kind of population distribution calculation method | |
| Zagorskas | GIS-based modelling and estimation of land use mix in urban environment | |
| CN115860520B (en) | Method for evaluating dynamic and static space-time reachability of high-speed rail hub and urban public transportation | |
| CN111507879A (en) | Urban space structure identification method | |
| CN116542709A (en) | Electric vehicle charging station planning analysis method based on traffic situation awareness | |
| CN115131966A (en) | Road network key node identification method considering intersection operation characteristics | |
| Bao et al. | Spatiotemporal clustering analysis of shared electric vehicles based on trajectory data for sustainable urban governance | |
| Schoier et al. | Individual movements and geographical data mining. Clustering algorithms for highlighting hotspots in personal navigation routes | |
| CN111310340B (en) | Urban area interaction abnormal relation identification method and equipment based on human movement | |
| CN108304470A (en) | A kind of city underground paths planning method based on ArcGIS | |
| CN108805336B (en) | Method and device for selecting shared tower based on power grid geographic information system | |
| Chen et al. | Detecting urban commercial patterns using a latent semantic information model: A case study of spatial-temporal evolution in Guangzhou, China | |
| Kong et al. | Charging pile siting recommendations via the fusion of points of interest and vehicle trajectories | |
| CN114238533A (en) | User commuting path planning method and device, computer equipment and storage medium | |
| CN112380460B (en) | Shortest path query method and system based on approximate algorithm | |
| Liu et al. | Toward identifying the urban community structure from population flow and public services distribution |
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 |