CN114005100B - Road side parking space classification method based on cluster analysis - Google Patents
Road side parking space classification method based on cluster analysis Download PDFInfo
- Publication number
- CN114005100B CN114005100B CN202110674918.4A CN202110674918A CN114005100B CN 114005100 B CN114005100 B CN 114005100B CN 202110674918 A CN202110674918 A CN 202110674918A CN 114005100 B CN114005100 B CN 114005100B
- Authority
- CN
- China
- Prior art keywords
- time
- parking space
- parking
- utilization rate
- orders
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/75—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/7867—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/231—Hierarchical techniques, i.e. dividing or merging pattern sets so as to obtain a dendrogram
-
- 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
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- Databases & Information Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Library & Information Science (AREA)
- Traffic Control Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a road side parking space classification method based on cluster analysis, which is used for extracting the time of entering a vehicle and the time of leaving the vehicle of all orders in a given time period according to parking order data aiming at a parking space to be researched, and calculating the parking duration according to the time of entering the vehicle. And carrying out abnormal value processing and vacancy data repair on the vehicle entering and exiting time and the duration time of the extracted order, and calculating the parking space utilization rate at one-hour intervals according to the vehicle entering and exiting time and the duration time to generate a utilization rate time sequence. And dividing the time sequence into different time periods by using an aggregation hierarchical clustering algorithm according to all the time sequences of the berth utilization rates, and calculating the berth utilization rate in the time periods. And finally, classifying the berths by using a fuzzy C-means clustering algorithm by taking the utilization rate in different time periods as a characteristic. The method can provide powerful support for urban parking management, avoid blindly expanding the existing parking spaces, and promote the scientific and modernized process of urban traffic management.
Description
Technical Field
The invention belongs to the technical field of intelligent transportation, and particularly relates to a roadside parking space classification processing method based on cluster analysis.
Background
At present, main energy of intelligent parking is concentrated on automatic charging, parking guidance and reverse vehicle finding are concerned partially, parking management is optimized through the technologies and functions, and user experience is improved. However, technologies covered by intelligent parking are far more than the technologies, the parking rules of users are known through data driving, the use attributes of the parking spaces are classified, the operation effect is evaluated, category-oriented differentiated parking management strategies are formulated, if the parking is carried out in time, parking spaces are reasonably planned according to the information, and the intelligent parking management system is of great importance for improving the foresight of dynamic management policies.
Disclosure of Invention
The invention provides a road side parking space classification method based on cluster analysis, aiming at the problem of reasonably planning motor vehicle parking spaces under the existing limited road side parking resources.
The invention provides a roadside parking space classification method based on cluster analysis, which comprises the following steps:
screening out berths provided with high-order videos, video piles or geomagnetism according to roadside parking order data, and taking the berths as classification targets;
step (2) screening effective orders according to status fields in the orders, cleaning order data, reducing the data, extracting vehicle entering time, vehicle leaving time and duration time, and performing abnormal value processing and vacancy data repair according to the extracted order vehicle entering and leaving time and duration time;
step (3) calculating the parking utilization rate at one-hour intervals based on one monthly history parking data to generate a utilization rate time sequence of the parking;
step (4) according to all the parking space utilization rate time sequences, comprehensively considering a plurality of parking data inter-cluster similarity calculation methods, using a cluster hierarchical clustering algorithm to subdivide the time sequences into a plurality of different time periods, and calculating the parking space utilization rate in the plurality of different time periods;
and (5) determining the clustering number of the berths by using an elbow method and classifying the berths by using a fuzzy C-means clustering algorithm by taking the utilization rates in the different time periods as characteristics.
Further, effective orders are screened out according to the status fields in the orders in the step (2), the orders with the duration of less than 1 minute are considered to be mixed in non-parking behaviors caused by high sensitivity of the detection equipment, and the orders cannot reflect the use condition of the parking space, so that the orders are deleted; deleting orders with the departure time being less than the departure time, which are regarded as abnormal orders; orders with a duration greater than 2 days are given a deletion.
Further, the describing the parking space utilization rate in a small time in the step (3) specifically includes: based on the parking order data, defining a parking space utilization:
wherein u is ij The berth utilization rate of the berth i in the jth natural hour is shown, i represents different berths, j represents different acquisition times, i is 1,2, …, and M, j is 0,2, …, 23; t is ijkl The duration of the ith order on the kth date of the berth i in the jth natural hour, K represents different dates, L represents different orders K equal to 1,2, … K, L equal to 1,2, …, L; k represents the number of days and M represents the number of berths.
Further, the plurality of inter-cluster similarity calculation methods in the step (4) include a "center of gravity method", a "variance method", and a "shortest distance method"; the method for calculating the berthage utilization rate in the multiple different time periods comprises the following steps of dividing a time sequence into n time periods j ', j' ═ 1,2, …, n by using an aggregation hierarchical clustering algorithm, wherein n is the number of the divided multiple different time periods:
wherein u is ij′ And dividing the time sequence of the parking space i into a plurality of different time periods to obtain the parking space utilization rate, wherein len (j ') is the number of hours contained in the time period j'.
By adopting the technical scheme, the invention has the following beneficial effects:
1. and large-scale traffic investigation is not needed, so that a large amount of manpower and time are saved. As long as the parking lot is provided with electronic equipment such as high-level videos, video piles, geomagnetism and the like, the operation efficiency of the researched parking lot can be extracted for a user to recognize, analyze and judge.
2. With some methods in data mining, credible and potentially useful information hidden in incomplete, noisy and fuzzy order data is extracted from a large volume of the order data. Under the background of the existing limited parking lot resources, the parking lot data are analyzed and evaluated through a series of correct data mining processes, and positive effects can be generated on intelligent parking planning and practice, so that the aims of avoiding blindly expanding the existing parking lot and saving the economic cost are fulfilled.
3. The parking management method of data planning, data decision and data management is established, and the urban parking planning and management level is comprehensively improved. The system has universality in various urban parking systems. In order to bring limited road resources and parking resources into play with maximized social benefits, the invention carries out differential treatment on different types of parking requirements obtained by classification, for example, aiming at the problem of traffic jam caused by a road section with higher parking utilization rate in a peak period, the invention can be set as a 'time-limited-period' parking position, and can properly delete parking positions with low utilization rate. In a word, the parking problem is comprehensively improved, parking space monitoring can not be realized only by newly added parking facilities through parking data, and classified application and targeted treatment are performed on different types of parking spaces, so that the direction of fine management of the parking spaces is in the process.
Drawings
FIG. 1 is a schematic process diagram of a roadside parking space classification method based on clustering;
FIG. 2 is a diagram showing the results of a hierarchical clustering algorithm based on a gravity center method;
FIG. 3 is a schematic diagram of a hierarchical clustering algorithm result based on a variance method;
FIG. 4 is a diagram illustrating a result of a hierarchical clustering algorithm based on a shortest distance method;
FIG. 5 is a diagram illustrating a result of selecting cluster numbers based on the elbow method.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
According to the embodiment of the invention, the roadside parking space classification method based on cluster analysis is provided, firstly, the roadside parking space to be researched needs to be determined, then, the parking space utilization condition is analyzed according to the parking order data fed back in real time, and the parking space is classified according to the parking space utilization condition. The method specifically comprises the following steps:
screening out berths provided with high-order videos, video piles or geomagnetism according to roadside parking order data, and taking the berths as classification targets;
step (2) screening effective orders according to status fields in the orders, cleaning order data, reducing the data, extracting vehicle entering time, vehicle exiting time and duration, and performing abnormal value processing and vacancy data repair according to the extracted vehicle entering and exiting time and duration of the orders;
step (3) calculating the parking utilization rate at one-hour intervals based on one monthly history parking data to generate a utilization rate time sequence of the parking;
step (4) according to all parking space utilization rate time sequences, comprehensively considering three parking data inter-cluster similarity calculation methods of a gravity center method, a variance method and a shortest distance method, dividing the time sequences into different time periods by using a clustering hierarchy algorithm, and calculating the parking space utilization rate in the time periods;
and (5) determining the clustering number of the berths by using an elbow method and classifying the berths by using a fuzzy C-means clustering algorithm by taking the utilization rate in different time periods as a characteristic.
Further, in the roadside parking space classification method based on cluster analysis, in the step (2), valid orders are screened out according to the status fields in the orders, roadside parking data are automatically acquired by hardware, and loss, incompleteness and data errors are inevitable. Orders with duration less than 1 minute can be considered as mixing of non-parking behaviors caused by high sensitivity of detection equipment, and the orders cannot reflect the use condition of the parking space, so that the orders are deleted. And deleting the orders with the departure time less than the departure time, which are considered as abnormal orders. Some personnel can occupy the parking stall for a long time, lead to the parking stall utilization ratio to be high, and this other action can not reflect the in service behavior of parking stall, consequently gives the deletion to the order that duration is greater than 2 days.
Further, in the roadside parking space classification method based on cluster analysis, the step (3) of depicting the parking space utilization rate in a small time specifically includes: based on the parking order data, defining a parking space utilization:
wherein u is ij The berth utilization rate of the berth i in the jth natural hour is shown, i represents different berths, j represents different acquisition times, i is 1,2, …, and M, j is 1,2, …, 24; t is ijkl The duration of the ith order on the kth date of the berth i in the jth natural hour, K represents different dates, L represents different orders K equal to 1,2, … K, L equal to 1,2, …, L; k represents the number of days.
Further, in the roadside parking space classification method based on cluster analysis, the time period considered in the step (4) is divided, after the utilization rate is divided by taking hours as a unit, the fields describing one parking space have 24 dimensions, high-dimensional data are adopted for classification, more system resources can be consumed, and the travel behaviors of human beings have obvious tidal characteristics, so that the time period can be divided into morning, afternoon, evening, night and the like, the expression capability of characteristics is improved, the training complexity is reduced, and meanwhile, the sensory cognition of the human beings is facilitated.
Unsupervised clustering algorithms are more suitable due to the lack of a priori knowledge. Because of the time period division, the number of the initial clusters is 24, and the number is small. And the aggregation hierarchical clustering algorithm assumes that each sample point is an independent cluster, then finds out clusters with higher similarity in each iteration of the operation of the algorithm for combination, and the process is repeated continuously until the preset number of clusters or only one cluster is reached, and the generated dendrogram records the sequence of cluster aggregation and splitting, including the information of the whole algorithm process, so that the aggregation hierarchical clustering algorithm is selected for time period division.
The aggregation hierarchical clustering algorithm is performed based on inter-cluster similarity, and results obtained by comprehensively considering three inter-cluster similarity calculation methods of a gravity center method, a variance method and a shortest distance method are shown in fig. 2, fig. 3 and fig. 4.
If the time period is divided into 4 types, the three methods are divided into: 7:00:00-8:59:59, 9:00:00-17:59:59, 18:00:00-20:59:59, 21:00:00-6:59:59, which can be defined as morning peak, daytime, evening peak, and night.
Considering the results of the three methods comprehensively, if the time period is divided into 4 types, the three methods are all divided into: 7:00:00-8:59:59,9:00:00-17:59:59, 18:00:00-20:59:59, 21:00:00-6:59:59. May be defined as morning peak, daytime, evening peak, night. After dividing into 4 time periods, calculating the berth utilization rate in each time period, wherein the calculation formula specifically comprises the following steps:
wherein u is ij′ And dividing the time period for the time sequence of the berth i to obtain the berth utilization rate. len (j ') is the number of hours included in the time period j ', and j ' is 1,2,3, 4.
Further, the roadside parking space classification method based on cluster analysis, the step (5) considers the berthage classification algorithm, in most cases, the berthages in the data set cannot be divided into obviously separated clusters, and the assignment of a berthage to a specific cluster is hard and hard, and sometimes possibly wrong, so that the concept of fuzzy mathematics and fuzzy logic is used for describing the relationship between objects and clusters by using the 'membership'.
Setting the sample set to be classified as X ═ X 1 ,X 2 ,…,X n }∈R n*q N is the number of elements in the sample set, q is the characteristic space dimension, the sample set X is divided into c types, and the membership degree matrix of n samples belonging to c types is recorded as U ═ m ij ] cn Wherein m is ij Denotes the jth sample X j Degree of membership, m, belonging to the ith class ij The following constraints are satisfied:
the cost function (also called sum of squared errors) of the clustering algorithm is:
wherein k is called fuzzy weighting index, also called smooth exposition parameter, controlling the fuzzy degree of the membership matrix U, C i At the center of the i cluster. C i And u ij The calculation formula of (a) is as follows:
the dataset X, the number of cluster categories c, and the fuzzy weighting index k are known, as determined by minimizing J m Solving the optimal membership matrix U and the clustering center C by adopting an iterative algorithm i ,1≤i≤c。
Further, the roadside parking space classification method based on cluster analysis comprises the step (5) of considering the algorithm of the number of the berth clusters, considering the selection of the cluster number and the determination of the elbow method, wherein the elbow method generally defines a cost function J of the clustering algorithm by comparing the sum of distances from each point to a central point, namely the sum of squares of errors m . As the cluster number c increases, the sample division becomes finer, the aggregation degree of each cluster gradually increases, and then J m And naturally becomes smaller. When c is smaller than the true cluster number, J increases the degree of aggregation per cluster to a large extent due to the increase in c m The decrease in c is large, and when c reaches the true cluster number, the return on the degree of aggregation obtained by increasing c is rapidly smaller, so J m Is suddenly reduced and then becomes gentle as the value of c continues to increase, i.e., J m The relationship between c and c is the shape of an elbow, and the corresponding c value of the elbow is the real clustering number of the data, and the result is shown in FIG. 5.
Fig. 5 is a schematic diagram of a cluster number selection result based on the elbow method, which is a broken line diagram of the cluster error sum of squares varying with the cluster number, and when the cluster number is greater than 5, the error sum of squares drops gently, so that 5 is the true cluster number.
According to the embodiment of the invention, the process of the roadside parking space classification method based on clustering is shown in fig. 1. First, according to roadside parking order data, a berth provided with a high-level video, a video pile or geomagnetism is screened out, and the berths are taken as classification targets. And secondly, extracting the vehicle entering time, the vehicle exiting time and the duration time, and performing abnormal value processing and vacancy data repair aiming at the extracted vehicle entering and exiting time and duration time of the order to generate a utilization rate time sequence of the berth. Then, the time sequence is divided into different time periods by using an aggregation hierarchical clustering algorithm, and the berthage utilization rate in the time period is calculated. And finally, determining the clustering number of the berths by using an elbow method and classifying the berths by using a fuzzy C-means clustering algorithm by taking the utilization rate in different time periods as a characteristic.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will 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 technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (3)
1. A roadside parking space classification method based on cluster analysis is characterized by comprising the following steps:
screening out berths provided with high-order videos, video piles or geomagnetism according to roadside parking order data, and taking the berths as classification targets;
step (2) screening effective orders according to status fields in the orders, cleaning order data, reducing the data, extracting vehicle entering time, vehicle leaving time and duration time, and performing abnormal value processing and vacancy data repair according to the extracted order vehicle entering and leaving time and duration time;
step (3) calculating the parking utilization rate at one-hour intervals based on one monthly history parking data to generate a utilization rate time sequence of the parking; the parking space utilization rate takes the accurate time of the vehicle actually entering the parking space and actually leaving the parking space as a node, and distributes the utilization time of the parking space to each divided time period; the step (3) of depicting the parking space utilization rate in a short time specifically comprises the following steps: based on the parking order data, defining a parking space utilization:
wherein u is ij The parking space utilization rate of the j natural hour for the parking space iI represents different berths, j represents different acquisition times, i is 1,2, …, M, j is 0,2, …, 23; t is ijkl The duration of the ith order on the kth date at the jth natural hour for berth i, K representing different dates, and L representing different orders K being 1,2, … K, L being 1,2, …, L; k represents the number of days, and M represents the number of berths;
step (4) according to all the parking space utilization rate time sequences, comprehensively considering a plurality of parking data inter-cluster similarity calculation methods, using a cluster hierarchical clustering algorithm to subdivide the time sequences into a plurality of different time periods, and calculating the parking space utilization rate in the plurality of different time periods;
and (5) determining the clustering number of the berths by using an elbow method and classifying the berths by using a fuzzy C-means clustering algorithm by taking the utilization rates in the different time periods as characteristics.
2. The method for roadside parking space classification based on cluster analysis as claimed in claim 1, wherein:
screening effective orders according to the status fields in the orders, regarding the orders with the duration less than 1 minute as the orders with the detection equipment with higher sensitivity causing the mixing of non-parking behaviors, and deleting the orders which cannot reflect the use condition of the parking space; deleting orders with the departure time being less than the departure time, which are regarded as abnormal orders; orders with a duration greater than 2 days are given a deletion.
3. The cluster analysis-based roadside parking space classification method as claimed in claim 1, wherein: the calculation method of the similarity among the clusters in the step (4) comprises a gravity center method, a variance method and a shortest distance method; the method for calculating the berthage utilization rate in a plurality of different time periods by using the aggregation hierarchical clustering algorithm to divide the time sequence into n time periods j ', j' is 1,2, …, n, wherein n is the number of the divided different time periods, specifically comprises the following steps:
wherein u is ij′ And dividing the time sequence of the parking space i into a plurality of different time periods to obtain the parking space utilization rate, wherein len (j ') is the number of hours contained in the time period j'.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110674918.4A CN114005100B (en) | 2021-06-17 | 2021-06-17 | Road side parking space classification method based on cluster analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110674918.4A CN114005100B (en) | 2021-06-17 | 2021-06-17 | Road side parking space classification method based on cluster analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114005100A CN114005100A (en) | 2022-02-01 |
| CN114005100B true CN114005100B (en) | 2022-09-13 |
Family
ID=79920978
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110674918.4A Active CN114005100B (en) | 2021-06-17 | 2021-06-17 | Road side parking space classification method based on cluster analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114005100B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115394087B (en) * | 2022-10-28 | 2023-04-07 | 苏州大学 | Parking resource supply gap evaluation method |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105489058B (en) * | 2016-01-15 | 2017-12-29 | 成都宜泊信息科技有限公司 | The quantity and the computational methods of idle period of the idle parking stall in parking lot |
| US20200327468A1 (en) * | 2019-04-15 | 2020-10-15 | ParkStash, Inc. | System, Method, and Computer Program Product for Optimizing a Parking Schedule, Increasing Parking Spot Utilization, Parking Lot Enforcement, and Parking Spot Reassignment |
| CN109949606A (en) * | 2019-04-18 | 2019-06-28 | 佛山市百宇行智能科技有限公司 | A kind of big data analysis method of intelligent parking |
-
2021
- 2021-06-17 CN CN202110674918.4A patent/CN114005100B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN114005100A (en) | 2022-02-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020238631A1 (en) | Population type recognition method based on mobile phone signaling data | |
| CN110728842B (en) | Abnormal driving early warning method based on reasonable driving range of vehicles at intersection | |
| Zhang et al. | A framework for passengers demand prediction and recommendation | |
| CN100444210C (en) | Mixed controlling method of single dot signal controlling crossing | |
| CN113096388B (en) | Short-term traffic flow prediction method based on gradient lifting decision tree | |
| CN109376906B (en) | Travel time prediction method and system based on multi-dimensional trajectory and electronic equipment | |
| CN112183605B (en) | Civil aviation control sector classification method based on operation characteristics | |
| CN111190942B (en) | Urban road parking spot overall analysis method based on data mining technology | |
| CN112732905B (en) | Traffic accident analysis, prevention and control method and system based on knowledge graph | |
| CN112001521A (en) | Electric vehicle charging demand prediction method based on multimodal Gaussian distribution fitting | |
| CN114005100B (en) | Road side parking space classification method based on cluster analysis | |
| CN110659774B (en) | Big data method driven parking demand prediction method | |
| CN110490365B (en) | Method for predicting network car booking order quantity based on multi-source data fusion | |
| CN115269758A (en) | Passenger-guidance-oriented road network passenger flow state deduction method and system | |
| Wang et al. | The analysis of electrical vehicles charging behavior based on charging big data | |
| CN112036602A (en) | 5G electric vehicle charging prediction method and system integrating human-computer intelligence | |
| CN110459050B (en) | Short-term bus passenger flow prediction method based on mixed decision tree | |
| CN112052405B (en) | Passenger searching area recommendation method based on driver experience | |
| Wan et al. | DBH-CLUS: A hierarchal clustering method to identify pick-up/drop-off hotspots | |
| CN109859467B (en) | Mining analysis method for environmental impact factors in traffic model | |
| CN117251722A (en) | Intelligent traffic management system based on big data | |
| Attanasi et al. | A hybrid method for real-time short-term predictions of traffic flows in urban areas | |
| CN116205528A (en) | Illegal construction identification method and system based on construction site power data | |
| CN115169630A (en) | Electric vehicle charging load prediction method and device | |
| CN113553350A (en) | Traffic flow partition model for similar evolution mode clustering and dynamic time zone partitioning |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 100616 floor 6, block B, starter building, No. 9, Nanli, Liuliqiao, Fengtai District, Beijing Applicant after: Beijing Intelligent Transportation Development Center (Beijing motor vehicle regulation and management center) Address before: 100616 No.9, Nanli, Liuliqiao, Fengtai District, Beijing Applicant before: BEIJING TRANSPORTATION INFORMATION CENTER |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |