CN104574965B - A kind of urban transportation hot spot region based on magnanimity traffic flow data division methods - Google Patents
A kind of urban transportation hot spot region based on magnanimity traffic flow data division methods Download PDFInfo
- Publication number
- CN104574965B CN104574965B CN201510014926.0A CN201510014926A CN104574965B CN 104574965 B CN104574965 B CN 104574965B CN 201510014926 A CN201510014926 A CN 201510014926A CN 104574965 B CN104574965 B CN 104574965B
- Authority
- CN
- China
- Prior art keywords
- car
- document
- word
- topic
- corpus
- 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
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/338—Presentation of query results
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of urban transportation hot spot region based on magnanimity traffic flow data division methods.nullWhat first each airfield equipment bayonet socket was obtained by the present invention crosses the transmission of car information data to central database,Obtain each car and crossed car record document by what the bayonet socket numbering of process formed within certain time period,Then according to LDA subject distillation model,Car information data of being made a slip of the tongue by card is converted into required corpus document form and models it,Then Gibbs Sampling algorithm is utilized,Words all in corpus document are carried out theme stochastical sampling until restraining,Finally take several the highest bayonet sockets of probability in each theme and represent certain traffic hot spot region,The traffic hot spot region that the present invention is formed by the traffic route rule of all vehicles in can finding different time sections,Thus urban traffic blocking situation provides analysis foundation in solving different time sections for vehicle supervision department,For urban planning authority's roading、Build and reference is provided.
Description
Technical field
The invention belongs to data mining technology field, be specifically related to a kind of city based on magnanimity traffic flow data
City's traffic hot spot region partitioning method.
Background technology
Along with sustained and rapid development of economy, vehicle guaranteeding organic quantity rapidly increases the traffic problems brought to city
Day by day highlighting, congested in traffic, wagon flow freely, greatly not have impact on people's trip speed, and then reduces life
Produce and work efficiency.At present, City Traffic Monitor System comparatively perfect, each arterial highway and crossing are designed with bayonet socket
Real-time Collection crosses car data.By the car data of crossing gathered in analysis city traffic monitoring system, thus send out
The traffic route of existing vehicle, utilizes the traffic route can be with the bayonet socket frequently occurred hidden between digging vehicle simultaneously.
With this hiding information for dividing the foundation of urban transportation hot spot region, and calculate its heavy traffic index, permissible
There is provided for vehicle supervision department and formulate the reference of traffic administration scheme, provide for roading department and formulate road
The reference etc. of planning, finally provides help for solution traffic problems.
The traffic route of research vehicle, often it appeared that many vehicles have similar driving region.Such as,
Hangzhou, Zhejiang province city working day early, evening peak, have substantial amounts of car and travel on urban district and connect with Binjiang District and do
Road, river-spanning bridge must be these vehicle cluster the urban transportation hot spot region of process;Weekend, trip
Must there be each big arterial highway towards scenic spot, the West Lake urban transportation hot spot region.Above-mentioned urban transportation hot spot region
Principal character can be summarized as: the different vehicle of a group at close time point through series of identical bayonet socket,
And region is just made up of these bayonet sockets, the vehicle fleet through these bayonet sockets is designated as this urban transportation hot spot region
Heavy traffic index.Find that the urban transportation hot spot region in the different time sections of city divides and calculates it and hands over
Logical busy index, can be that vehicle supervision department provides the effective means of blocking up of alleviating to provide help.
Summary of the invention
The present invention is directed to the deficiencies in the prior art, it is provided that a kind of urban area based on magnanimity traffic flow data
Division methods.
The central scope of technical solution of the present invention is: utilizes in natural language processing and forms from word and document
The thought extracting theme in corpus solves the problem that urban transportation hot spot region divides;By in a period of time,
Traffic surveillance and control system (monitor, gather, deposit city main trunk road and the system of crossing real-time traffic situation)
In all car datas composition corpus of crossing, wherein to form this car institute at the record that each bayonet socket occurs right for each car
The document answered, and these bayonet sockets numbering is as the word in document, and extract wherein implicit often with
Time the bayonet socket numbering set that occurs as the theme correspondence urban transportation hot spot region of corpus;
The inventive method comprises the following steps:
Step (1). the car information data of crossing obtained by each airfield equipment bayonet socket sends to central database, mistake
Car information data includes license plate number, excessively car time, crosses car direction and cross car bayonet socket numbering;
Step (2). according to LDA (Latent Dirichlet Allocation) subject distillation model, obtain certain
Set in the time period all cards in central database to make a slip of the tongue car information data, be translated into required corpus
It is also modeled by form, particularly as follows:
Obtain city all bayonet sockets numbering and form dictionary as word, from central database, take certain set the time period
In all cards make a slip of the tongue car information data, then obtain each car from which and compiled by the bayonet socket of process within this time period
Number composition cross car record document, then by all vehicles cross car record document merge formed corpus document,
Add up each car in this corpus document and, at the probability of occurrence of each bayonet socket, save it in a license plate number-card
In the probability matrix of mouth, each unit of this matrix represents the probability that certain car occurs at certain bayonet socket;
If total N number of bayonet socket, the most N number of word, it is designated as: wordj, j=0,1 ..., (N-1), certain set in the time period
The car occurred has M, i.e. M piece document is designated as: doci, i=0,1 ..., (M-1), can by all car information datas excessively
To obtain corpus document, every a line record one car bayonet socket of process within this time period of this corpus document
Numbered sequence, adds up number of times and every that in corpus document, in dictionary corresponding to every document, each word occurs
The total words of document, is designated as respectively: ai,j、dwSumi, and by being calculated document-word probability matrix,
It is designated as: Mdoc-word, this matrix M row altogether, N row, the i-th corresponding i-th car of row jth row of matrix is when this
Between in section through the probability of jth bayonet socket, computational methods are:
Corpus document is carried out LDA theme modeling, it is assumed that urban transportation hot spot region number is K, i.e. K
Individual theme, is designated as: topick, k=0,1 ..., (K-1), according to LDA model, it is assumed that document and master in corpus document
Topic meets the Di Li Cray distribution with α and β as Study first respectively, then in corpus, every document is with every
The generation process of individual theme meets respectivelyWithMultinomial distribution, the then distribution of document-theme and master in corpus
The distribution of topic-word can be expressed as doc-topic probability matrix, topic-word probability matrix, is designated as:
Mdoc-topic、Mtopic-word, final Mtopic-wordIt is the model result of LDA;
Step (3). utilize Gibbs Sampling algorithm, words all in corpus are carried out theme and adopts at random
Sample is until Gibbs Sampling convergence obtains Mtopic-word, Mtopic-wordRow k represent all of wordj(i.e.
Bayonet socket is numbered) at this topickUnder probability distribution, take each topickC the word that middle probability is the highestj(i.e.
Bayonet socket is numbered) represent certain traffic hot spot region (c is determined) by the size in required division traffic hot spot region;
Step (4). the total mistake corresponding to bayonet socket numbering set in the traffic hot spot region that statistic procedure (3) obtains
Car amount is designated as the heavy traffic index in this traffic hot spot region.
A kind of urban transportation hot spot region based on magnanimity traffic flow data provided by the present invention division methods by
One group of functional module composition, they include: cross car information data acquisition module, cross car information data convert and
LDA theme MBM, Gibbs Sampling theme sampling module and the heavy traffic in traffic hot spot region
Index for Calculation module.
Cross car information data acquisition module and obtain the car information data excessively of each airfield equipment bayonet socket Real-time Collection,
Including car license plate number, spend the car time, cross car direction and cross car bayonet socket numbering, and preserve to central database.
Cross car information data convert and LDA theme MBM with cross car information data as initial data, by it
It is converted into the form needed for LDA theme models and completes modeling, with Mtopic-wordFor modeling result.
Gibbs Sampling theme sampling module is on the basis of LDA theme models, to Mtopic-wordIn every
One wordjUse Gibbs Sampling algorithm to carry out theme sampling until convergence, obtain each topickInstitute
Corresponding bayonet socket numbering set.
The heavy traffic Index for Calculation module in traffic hot spot region mainly adds up each topickCorresponding bayonet socket
The car total amount of crossing of the corresponding bayonet socket of numbering set is designated as this topickThe heavy traffic in the traffic hot spot region represented
Index.
The invention have the benefit that
The present invention utilizes the magnanimity of City Traffic Monitor System collection to cross car information data, finds different time sections
The region characteristic that the traffic route rule of interior all vehicles is formed, as the foundation dividing hot spot region, city.
In this result can solve different time sections for vehicle supervision department, urban traffic blocking situation provides analysis foundation,
For urban planning authority's roading, building offer reference, driving to go on a journey for resident provides induction.
The present invention, on the basis of urban transportation hot spot region divides, can add up each urban transportation hot spot region
Busy index.This busy index can reflect city focus regional traffic active degree to a certain extent.
Accompanying drawing explanation
Fig. 1 dictionary schematic diagram;
Fig. 2 corpus document schematic diagram;
Fig. 3 license plate number-bayonet socket numbering probability matrix (i.e. document-word frequencies matrix) schematic diagram.
Detailed description of the invention
Below in conjunction with accompanying drawing, the invention will be further described.
Step (1). the car information data of crossing obtained by each airfield equipment bayonet socket sends to central database, mistake
Car information data includes: license plate number, cross the car time, cross car direction and cross car bayonet socket numbering.
Step (2). according to LDA (Latent Dirichlet Allocation) subject distillation model, obtain certain
Set in the time period all cards in central database to make a slip of the tongue car information data, be translated into required corpus
It is also modeled by form, particularly as follows:
Obtain city all bayonet sockets numbering and form dictionary (seeing Fig. 1) as word, take from central database
Certain all card set in time period is made a slip of the tongue car information data, then obtains each car from which within this time period
Being numbered the car record document of crossing formed by the bayonet socket of process (is document doc represented by i-th cari, in document
The bayonet socket number table of the n-th process is shown as word wordi,s, s=0,1 ..., (ni-1), niIt it is the card of i-th car process
Mouth numbering number, wordi,s∈{wordj| j=0,1 ..., (N-1) }), then by the car record document excessively of all vehicles
Merge and form corpus document (seeing Fig. 2), add up each car going out at each bayonet socket in this corpus document
Existing probability, saves it in the probability matrix of a license plate number-bayonet socket, and each unit of this matrix represents certain
The probability that car occurs at certain bayonet socket.
If total N number of bayonet socket, the most N number of word, it is designated as: wordj, j=0,1 ..., (N-1), certain sets the time period
The car of interior appearance has M, i.e. M piece document, is designated as: doci, i=0,1 ..., (M-1), all cross car Information Number
According to obtaining corpus document, one car of every a line record of this corpus document passed through within this time period
Bayonet socket numbered sequence, statistics corpus document obtains the probability square of license plate number-bayonet socket (i.e. document-word)
Battle array, is designated as: Mdoc-word(seeing Fig. 3, this matrix M row altogether, N row, the i-th row jth row of matrix are right
Answering i-th car through the probability of jth bayonet socket within this time period, the probability sum of the every a line of matrix is 1).
Corpus document is carried out LDA theme modeling, it is assumed that urban transportation hot spot region number is K, i.e. K
Individual theme, is designated as: topick, k=0,1 ..., (K-1), according to LDA model, it is assumed that in corpus document document and
Theme meets the Di Li Cray distribution with α and β as Study first respectively, then in corpus every document and
The generation process of each theme meets respectivelyWithMultinomial distribution, then in corpus the distribution of document-theme and
The distribution of theme-word can be expressed as doc-topic probability matrix, topic-word probability matrix, is designated as:
Mdoc-topic、Mtopic-word, final Mtopic-wordIt is the model result of LDA.
Step (3). utilize Gibbs Sampling algorithm, words all in corpus are carried out theme random
Sampling is until Gibbs Sampling convergence obtains Mtopic-word, Mtopic-wordRow k represent all of wordj
(i.e. bayonet socket numbering) is at this topickUnder probability distribution, take each topickC the word that middle probability is the highestj
(i.e. bayonet socket numbering) represents certain traffic hot spot region, and (c is by the size in required division traffic hot spot region certainly
Fixed), concrete steps:
(1) random initializtion: to each word word in every document in corpusj, compose one randomly
Topic numbering k, i.e. this word correspondence topick, add up each topic in every documentkCorresponding word number
And each word word of dictionary corresponding to corpus documentjBelong to different topickNumber be separately recorded in
SMnmk、SMnktIn matrix.SMnmkMatrix M row altogether, K row, wherein the i-th row kth row record i-th
In document, belong to the word number of kth theme;SMnktMatrix altogether K row, N row, wherein row k the
J row record word j represents the number of times that theme k occurs.And add up the total words of every document in corpus
With the total words of each theme, it is separately recorded in MnmkSum、MnktSumIn matrix, MnmkSumMatrix M row altogether
1 row, the i-th row the 1st row record i-th document subject matter sum, MnktSumMatrix K row 1 altogether arranges, K
Total words corresponding to row the 1st row record kth theme.
(2) multiple scanning corpus document, every document dociEach word word corresponding injTopic compile
Number k, obtains φ [k] [j], ζ [i] [k] according to Gibbs Sampling formula: (α, β are empirically worth setting), with KValue uses multinomial
The method of sampling, resampling dociMiddle wordjTopic numbering, by sampling result update SMnmk、SMnkt、
MnmkSumAnd MnktSumMatrix.
(3) sampling process n time of (2) is repeated until Gibbs Sampling restrains (n is empirically worth setting).
(4) M is calculatednmk、MnktIn every value, computational methods are: MnktI.e. the result of model, takes MnktCorresponding to every a line c maximum
wordjAs this row topickThe bayonet socket numbering set represented.
Step (4). the total mistake corresponding to bayonet socket numbering set in the traffic hot spot region that statistic procedure (3) obtains
Che Liang, is designated as the heavy traffic index in this traffic hot spot region.
Claims (1)
1. urban transportation hot spot region based on a magnanimity traffic flow data division methods, it is characterised in that the party
Comprising the concrete steps that of method:
Step (1). the car information data of crossing obtained by each airfield equipment bayonet socket sends to central database, crosses car
Information data includes: license plate number, cross the car time, cross car direction and cross car bayonet socket numbering;
Step (2). according to LDA subject distillation model, obtain certain and set in time period all cards in central database
Make a slip of the tongue car information data, be translated into required corpus form and it is modeled, particularly as follows:
Obtain city all bayonet sockets numbering and form dictionary as word, from central database, take certain set the time period
In all cards make a slip of the tongue car information data, then obtain each car from which and compiled by the bayonet socket of process within this time period
Number composition cross car record document, then by all vehicles cross car record document merge formed corpus document,
Add up each car in this corpus document and, at the probability of occurrence of each bayonet socket, save it in a license plate number-card
In the probability matrix of mouth, each unit of this matrix represents the probability that certain car occurs at certain bayonet socket;
If total N number of bayonet socket, the most N number of word, it is designated as: wordj, j=0,1 ..., (N-1), certain set in the time period
The car occurred has M, i.e. M piece document is designated as: doci, i=0,1 ..., (M-1), can by all car information datas excessively
To obtain corpus document, every a line record one car bayonet socket of process within this time period of this corpus document
Numbered sequence, adds up number of times and every that in corpus document, in dictionary corresponding to every document, each word occurs
The total words of document, is designated as respectively: ai,j、dwSumi;And by being calculated document-word probability matrix,
It is designated as: Mdoc-word, this matrix M row altogether, N row, the i-th corresponding i-th car of row jth row of matrix is when this
Between in section through the probability of jth bayonet socket, this value is:
Corpus document is carried out LDA theme modeling, it is assumed that urban transportation hot spot region number is K, i.e. K
Theme, is designated as: topick, k=0,1 ..., (K-1), according to LDA model, it is assumed that document and theme in corpus document
Meet the Di Li Cray distribution with α and β as Study first respectively, then every document and each master in corpus
The generation process of topic meets respectivelyWithMultinomial distribution, the then distribution of document-theme and theme in corpus-mono-
The distribution of word can be expressed as doc-topic probability matrix, topic-word probability matrix, is designated as: Mdoc-topic、
Mtopic-word, final Mtopic-wordIt is the model result of LDA;
Step (3). utilize Gibbs Sampling algorithm, words all in corpus are carried out theme and adopts at random
Sample is until Gibbs Sampling convergence obtains Mtopic-word, Mtopic-wordRow k represent all of wordj?
This topickUnder probability distribution, take each topickC the word that middle probability is the highestjRepresent certain traffic hot spot district
Territory, c is determined by the size in required division traffic hot spot region;
Step (4). the total car excessively corresponding to the bayonet socket numbering set in the traffic hot spot region that statistic procedure (3) obtains
Amount is designated as the heavy traffic index in this traffic hot spot region.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510014926.0A CN104574965B (en) | 2015-01-11 | 2015-01-11 | A kind of urban transportation hot spot region based on magnanimity traffic flow data division methods |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510014926.0A CN104574965B (en) | 2015-01-11 | 2015-01-11 | A kind of urban transportation hot spot region based on magnanimity traffic flow data division methods |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104574965A CN104574965A (en) | 2015-04-29 |
CN104574965B true CN104574965B (en) | 2017-01-04 |
Family
ID=53090908
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510014926.0A Active CN104574965B (en) | 2015-01-11 | 2015-01-11 | A kind of urban transportation hot spot region based on magnanimity traffic flow data division methods |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104574965B (en) |
Families Citing this family (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106611499A (en) * | 2015-10-21 | 2017-05-03 | 北京计算机技术及应用研究所 | Method of detecting vehicle hotspot path |
CN105809967A (en) * | 2016-05-25 | 2016-07-27 | 浙江宇视科技有限公司 | Traffic flow displaying method and device |
CN106095976B (en) * | 2016-06-20 | 2019-09-24 | 杭州电子科技大学 | A kind of interest Dimensional level extracting method based on microblog data for supporting OLAP to apply |
CN107862862B (en) * | 2016-09-22 | 2020-11-20 | 杭州海康威视数字技术股份有限公司 | Vehicle behavior analysis method and device |
CN106709595A (en) * | 2016-11-24 | 2017-05-24 | 北京交通大学 | Accident delay time prediction method and system based on unformatted information |
CN111126713B (en) * | 2019-12-31 | 2023-05-09 | 方正国际软件(北京)有限公司 | Space-time hot spot prediction method and device based on bayonet data and controller |
CN111932873B (en) * | 2020-07-21 | 2022-10-04 | 重庆交通大学 | Real-time traffic early warning management and control method and system for mountain city hot spot area |
CN112950932B (en) * | 2021-01-26 | 2023-05-02 | 阿里巴巴集团控股有限公司 | Method and device for merging regional units and electronic equipment |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120041953A1 (en) * | 2010-08-16 | 2012-02-16 | Microsoft Corporation | Text mining of microblogs using latent topic labels |
KR101448550B1 (en) * | 2012-11-21 | 2014-10-13 | 서울대학교산학협력단 | Apparatus and Method for Traffic Classificaiton |
KR101481253B1 (en) * | 2013-03-14 | 2015-01-13 | 한국과학기술원 | Method and system for providing summery of text document using word cloud |
CN103544841B (en) * | 2013-10-22 | 2015-10-21 | 银江股份有限公司 | Transportation Controlled Area Dynamic Division method |
CN103678277A (en) * | 2013-12-04 | 2014-03-26 | 东软集团股份有限公司 | Theme-vocabulary distribution establishing method and system based on document segmenting |
CN104050298B (en) * | 2014-07-04 | 2017-09-26 | 成都品果科技有限公司 | A kind of subscriber segmentation method based on LDA topic model algorithms |
CN104156350B (en) * | 2014-08-04 | 2018-03-06 | 苏州大学 | Text semantic meaning extraction method based on thin division MapReduce |
-
2015
- 2015-01-11 CN CN201510014926.0A patent/CN104574965B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN104574965A (en) | 2015-04-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104574965B (en) | A kind of urban transportation hot spot region based on magnanimity traffic flow data division methods | |
Garcia-López et al. | Suburbanization and highways in Spain when the Romans and the Bourbons still shape its cities | |
Wu et al. | Land use dynamics, built-up land expansion patterns, and driving forces analysis of the fast-growing Hangzhou metropolitan area, eastern China (1978–2008) | |
CN103236086B (en) | One takes the contextual multiple dimensioned DEM modeling method of the earth's surface hydrology into account | |
CN101807224B (en) | Mesoscopic-microcosmic integrated traffic simulation vehicle flow loading method | |
CN103593430A (en) | Clustering method based on mobile object spatiotemporal information trajectory subsections | |
CN105183841A (en) | Recommendation method in combination with frequent item set and deep learning under big data environment | |
CN102610092A (en) | Urban road speed predication method based on RBF (radial basis function) neural network | |
CN101853573A (en) | City expressway short-time traffic information predicting system and method | |
CN105095993A (en) | System and method for predicting passenger flow volume of railway stations | |
CN105975582B (en) | RFID data based on Spark generates the method and system of travelling OD matrix | |
Guo | Application of entropy weight method in the evaluation of the road capacity of open area | |
CN106447109B (en) | A kind of community policy patrol path optimization's design method based on deep learning algorithm | |
Lu et al. | Analyzing the evolution of rare events via social media data and k-means clustering algorithm | |
CN103914981A (en) | Method for predicting confliction between pedestrians and left-turn vehicles at plane intersection | |
CN103325010A (en) | Overall city height control partition method based on comprehensive divisor evaluation | |
Huang et al. | Spatiotemporal evolution of land transportation networks and accessibility in inland mountainous areas 1917–2017: A case study of Southwest China | |
CN108882152A (en) | A kind of privacy of user guard method reported based on Path selection | |
Schechla | The right to the city: Cairo | |
Mohamad et al. | Street network design, pattern and characteristics for Malaysian local town | |
CN106096910A (en) | A kind of architecture design method based on information activities | |
Papa et al. | Characteristics of Sprawl in the Naples Metropolitan Area. Indications for Controlling and Monitoring Urban Transformations | |
Wójcik-Leń et al. | The share of land belonging to non-resident owners in a village intersected by a motorway-case study | |
CN109034530A (en) | A kind of piping lane planing method based on neural network algorithm | |
Su et al. | A multi-source data based analysis framework for urban greenway safety |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20150429 Assignee: Hangzhou Cheng Road Polytron Technologies Inc Assignor: Hangzhou Electronic Science and Technology Univ Contract record no.: 2019330000034 Denomination of invention: City traffic hot spot region partition method based on massive traffic flow data Granted publication date: 20170104 License type: Common License Record date: 20190319 |
|
EE01 | Entry into force of recordation of patent licensing contract |