CN102567488A - System and method for mining data of electric vehicle based on cloud computer framework - Google Patents
System and method for mining data of electric vehicle based on cloud computer framework Download PDFInfo
- Publication number
- CN102567488A CN102567488A CN2011104314536A CN201110431453A CN102567488A CN 102567488 A CN102567488 A CN 102567488A CN 2011104314536 A CN2011104314536 A CN 2011104314536A CN 201110431453 A CN201110431453 A CN 201110431453A CN 102567488 A CN102567488 A CN 102567488A
- Authority
- CN
- China
- Prior art keywords
- data
- module
- frequent
- cloud computing
- electric automobile
- 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 first aims to disclose a system for mining data of an electric vehicle based on a cloud computer framework. The system comprises a data acquisition module, a mining system front end module which is connected with the data acquisition module through a third generation (3G) network, and a cloud computer Hadoop cluster module which is connected with the mining system front end module. In the system, the remote monitoring system and the data mining subsystem of the electric vehicle are perfectly combined, so that the real-time service of the remote monitoring system is ensured; and the high storage expandability of a cloud computing platform Hadoop, the high fault tolerance of a computing framework mapreduce and the like are fully used, so that the precision is high. The invention also aims to disclose a method for mining the data of the electric vehicle based on the cloud computer framework. The method is high in applicability, practicability and expandability and short in mining time, a manual system and manual analysis are eliminated by the method, a mining result does not have redundancy, and the development and application of the electric vehicle are ensured.
Description
Technical field
The present invention relates to a kind of digging system and implementation method of electric automobile mass data, be specifically related to a kind of electric automobile data digging system and method for digging based on the cloud computing machine frame.
Background technology
Electric automobile has advantages such as energy-saving and emission-reduction, and development in recent years is rapid.Yet the development of electric automobile also is in " construction period ", from extensively popularizing a segment distance is arranged.Main cause be the electric automobile whole quality particularly the quality of the electronic battery of its most crucial parts that is that all right is ripe.Electronic battery cycle life is short, cost is also more higher relatively, and its adaptability and security all remain to be considered.In addition, the construction of electric automobile infrastructure also fails in time to follow up, and rationally disposes charging station and charging pile, improves the utilization factor of limited urban resource, will promote popularizing and promoting of electric automobile greatly.
At present existing electric automobile long distance control systems, the situation of monitoring electric automobile operation, and these real time datas are carried out statistics and analysis is to find out the reason that electric automobile breaks down, the rule of service data etc.For example, the pure electric automobile long distance control system of Ford's exploitation, the slip-stick artist of Ford has accomplished the improvement of at least 20 place's power battery management system operating strategies according to this monitoring feedack.In addition; Saic Motor Corporation Limited technique center and Tongji University, Shanghai Fuel Battery Automobile Power System Co., Ltd have developed Shanghai Automobile Factory's new-energy automobile long distance control system cooperatively; This system has realized the on-line monitoring of vehicle operating in batches, functions such as the record of the intellectuality processing of fault, the upgrading of vehicle terminal software, data and storage.Above-mentioned supervisory system all adopts the Centralized Monitoring mode.The data volume average out to 82.4kb that electronic according to statistics vapour per minute is uploaded onto the server according to thousand policies in ten cities, will reach 5000 to Beijing's electric automobile in 2012, and 5000 electric automobiles data total amount of uploading onto the server in a year will reach 52T so.Big data volume like this, the mode of Centralized Monitoring all is difficult to bear with handling in data storage, therefore realizes that based on cloud computing similar supervisory system is ten minutes necessity.The electric automobile long distance control system that the Computer Department of the Chinese Academy of Science and the dark Jiang Diandongqichechang of middle section cooperate based on cloud computing; Just adopt increase income framework Hadoop storage and handle the data that electric automobile is uploaded of cloud computing, realized the functions such as real-time monitoring, history playback, fault pre-alarming and processing, data statistic analysis of thousand level electric automobiles.Yet existing supervisory system; No matter be the centralized cloud computing framework that also is based on; All only go to analyze the rule and the reason of electric automobile fault generating, for the improvement of batteries of electric automobile and battery management system can only provide finite information through the statistical condition of manual work definition.Some are hidden among the mass data valuable information and can not be excavated, and these information possibly be beyond thought restricting relation or rule, can to battery extremely the improvement of management system very large help is provided.
Summary of the invention
One of the object of the invention provides a kind of electric automobile data digging system based on the cloud computing machine frame;
Another object of the present invention provides a kind of electric automobile data digging method based on the cloud computing machine frame.
The technical scheme that realizes first purpose of the present invention provides a kind of electric automobile data digging system based on the cloud computing machine frame, the digging system front-end module that comprises data acquisition module, links to each other through 3G network with data acquisition module, the cloud computing machine Hadoop cluster module that links to each other with the digging system front-end module.
Further; Said digging system front-end module comprises data importing module, association rule mining module, frequent highway section excavation module; Said data importing module links to each other through 3G network with data acquisition module, and association rule mining module, frequent highway section are excavated module and linked to each other with the data importing module respectively.
Further, said cloud computing machine Hadoop cluster module comprises data processing module and data memory module, and said data processing module excavates module with the association rule mining module with frequent highway section and links to each other.
Realize that another object of the present invention technical scheme provides a kind of electric automobile data digging method based on the cloud computing machine frame, comprises the steps:
Step 1, by the data collecting module collected data, and be sent to the digging system front end through 3G network, the data set cutting that the digging system front end will excavate is some independently data blocks and record;
All supports are greater than frequent 1 data field of minimum support in step 2, parallel each data block of statistics, and the result is stored among the F-list;
Step 3, frequent 1 the data field among the F-list is divided into G group;
Grouping executed in parallel FPGrowth algorithm in step 4, the cloud computing machine Hadoop cluster module,, generate and preserve relevant part and close the frequent mode collection;
Step 5, merge the part and close the frequent mode collection, what generate the overall situation closes the frequent mode collection, closes the frequent mode collection according to the overall situation at last and generates break-even correlation rule.
Further, in step 3, G each group of organizing is labeled as a G-List, and reference numeral gid.
Further, in step 4, when carrying out the FPGrowth algorithm, add fusion, beta pruning, closed inspection step.
The present invention has positive effect: in (1), the native system; Electric automobile long distance control system and data mining subsystem are perfectly combined; Both guaranteed the real-time service of long distance control system, made full use of again cloud computing platform Hadoop the storage enhanced scalability, calculate framework mapreduce high fault tolerance etc. and provide the foundation for the realization of data digging system.And the accessible data volume of system satisfies the growth requirement of electric automobile, and the mode of using data to excavate has been broken away from artificial statistics and analysis, excavates the incidence relation between the electric automobile data automatically.
(2), among the present invention, the method for digging of employing and is compared traditional P FPGrowth algorithm and is compared; The execution time of using is about the same, but the frequent mode quantity of excavating of closing is compared remarkable minimizing with complete frequent mode, and applicability is wide; Use data mining method to break away from artificial system and analysis, the incidence relation between the automatic mining electric automobile data, and indicate frequent highway section regional extent; Practicality is good, and its extensibility is strong, and the excavation time is short; The excavation result is irredundant, has guaranteed the development and the application of electric automobile.
Description of drawings
Fig. 1 is a system chart of the present invention;
Fig. 2 is a PFPGrowth algorithm flow chart of the present invention.
Embodiment
(embodiment 1)
A kind of electric automobile data digging system based on the cloud computing machine frame; See Fig. 1, the digging system front-end module 2 that comprises data acquisition module 1, links to each other through 3G network with data acquisition module 1,2 cloud computing machine Hadoop cluster module 3 links to each other with the digging system front-end module.
Digging system front-end module 2 comprises data importing module 21, association rule mining module 22, frequent highway section excavation module 23; Said data importing module 21 and data acquisition module 1 link to each other through 3G network, and association rule mining module 22, frequent highway section are excavated module 23 and linked to each other with data importing module 21 respectively.
Cloud computing machine Hadoop cluster module 3 comprises data processing module 31 and data memory module 32, and said data processing module 31 excavates module 23 with association rule mining module 22 with frequent highway section and links to each other.
Electric automobile long distance control system and data mining subsystem are perfectly combined; Both guaranteed the real-time service of long distance control system, made full use of again cloud computing platform Hadoop the storage enhanced scalability, calculate framework mapreduce high fault tolerance etc. and provide the foundation for the realization of data digging system.And the accessible data volume of system satisfies the growth requirement of electric automobile, and the mode of using data to excavate has been broken away from artificial statistics and analysis, excavates the incidence relation between the electric automobile data automatically.
(embodiment 2)
A kind of electric automobile data digging method based on the cloud computing machine frame is seen Fig. 2, comprises the steps:
Step 1, by the data collecting module collected data, and be sent to the digging system front end through 3G network, the data set cutting that the digging system front end will excavate is some independently data blocks and record;
All supports are greater than frequent 1 data field of minimum support in step 2, parallel each data block of statistics, and the result is stored among the F-list;
Step 3, frequent 1 the data field among the F-list is divided into G group;
Grouping executed in parallel FPGrowth algorithm in step 4, the cloud computing machine Hadoop cluster module,, generate and preserve relevant part and close the frequent mode collection;
Step 5, merge the part and close the frequent mode collection, what generate the overall situation closes the frequent mode collection, closes the frequent mode collection according to the overall situation at last and generates break-even correlation rule.
Further, in step 3, G each group of organizing is labeled as a G-List, and reference numeral gid.
Further, in step 4), when carrying out the FPGrowth algorithm, add fusion, beta pruning, closed inspection step.
Method for digging is compared with comparing traditional P FPGrowth algorithm, and the execution time of use is about the same; But the frequent mode quantity of excavating of closing is compared remarkable minimizing with complete frequent mode, and applicability is wide, uses data mining method to break away from artificial system and analysis; Incidence relation between the automatic mining electric automobile data, and indicate frequent highway section regional extent, practicality is good; And its extensibility is strong; The excavation time is short, and it is irredundant to excavate the result, has guaranteed the development and the application of electric automobile.
The electric automobile data that user (electric automobile research staff) screening is to be excavated, screening conditions comprise:
A) the vehicle scope is selected, selects bicycle or many cars.When the user need excavate information implicit in the data that a certain specific vehicle moves in a certain period, select the bicycle condition, comprise the number-plate number, vehicle operating zero-time and concluding time.When the user need excavate information implicit in the data that the electric automobile of a certain type moves in a certain period, select many spoke part, comprise model, vehicle operating zero-time and the concluding time of vehicle production date range, vehicle.
B) data area is selected.During correlation rule between the mining data, can from the data field of all battery data fields, motor data field, electric automobile dynamic change, select interested field to excavate.The gps data acquiescence has only longitude and two data fields of latitude, and SF can be set up on their own by the user, is defaulted as 100%.
According to last screening conditions, the electric automobile data that will meet screening conditions import to the HDFS file system from HBase.When importing, do following processing for the data of correlation rule between the electric automobile data:
A) null value is handled: the average by this data field is filled up.
B) data discreteization: a data recording for electric automobile, comprised the plurality of data field, these data fields can be divided into motor information, battery information and vehicle dynamic information.With the numeric coding of each data field is four integers.Represent the affiliated type of this data field for first, then then then be C for B, vehicle dynamic information for A, motor info class if belong to the battery information class.Second concrete title of representing this data field.The scope of data field is (∞, min ... Max ,+∞), wherein min is a minimum value, max is a maximal value.This scope is divided between several region, abnormal data will drop on the interval (∞, min) with (max ,+∞) in.Represent the interval numbering of the affiliated value of this numerical value for the 3rd and the 4th of coding.So just form the numerical value correspondence table of four integer coding and data field.This coded system has not only been compressed data, when generating correlation rule, relies on this correspondence table also to be easy to be reduced into natural language.
The pretreatment mode that frequent highway section data are done does, it is right to ignore incomplete longitude and latitude point, and adopting does not have replacement simple random sampling method (SRSWOR method) from N data, to extract n immediately capable.
The user submits mining task to.The user can oneself define some parameters relevant with algorithm when submitting mining task to, comprising: the extreme length of minimum support, min confidence, rule.Minimum support is high more, and the quantity of closing the frequent mode collection that obtains is just few more, and the quantity of the high more correlation rule that obtains of min confidence is just few more.According to the data rule and the excavation experiment experience of electric automobile, the default value that native system has been set minimum support is 40%, and the default value of min confidence is 80%.
In the Hadoop cluster, carry out electric automobile data association rule digging algorithm.Wherein the association rules mining algorithm between the electric automobile data carries out 10 to 60, and frequent highway section mining algorithm only carries out 10 to 50:
10 are divided into some separate data fragmentations with pretreated data set, and each data fragmentation comprises the several rows data recording, each data recording comprise some four coding integers, each coding integer is called a data item.
20 parallel statisticss are concentrated the data item of all supports greater than minimum support.Wherein each Mapper reads in a data burst, is input as (key, value=T
i), T
iBe a data recording, output (key=a
j, value '=1), a
jBe T
iA data item, a
j∈ T
iReducer is designated as S with the pairing value addition of identical key value, if S, then exports key-value pair (key "=a greater than minimum support
j, value "=S).Mean data item a
jThe total degree that occurs is S, greater than minimum support.Reducer is exported the result to be saved among the F-list.
30 are divided into Q with F-list organizes, and every group has one independently to number gid.The result is kept among the Hashmap, is designated as G-list.
40 divide into groups carries out based on closing Mining Algorithms of Frequent Patterns.Each Mapper input G-list and data burst (key=gid, a value=T
i), T wherein
iBe data recording.To belong to T
iEach data item a
iReplace with corresponding gid.Mapper output (key '=gid, value '={ T
i[1] ... T
i[L] }), wherein L is at data recording T
iMiddle gid begins the Position Number of appearance for the first time from the right side.But the Reduce stage like this is the merger data item relevant with each gid just, and total Q group is carried out following mining algorithm in every group of collection of data items, and step is following:
410 calculate local frequent 1 collection, with its arrangement, set up the head table.
420 according to the data item in the order descending sort data recording of head table.And set up the local frequent pattern tree (fp tree) of a compression.K raft of initialization is safeguarded the preceding big closed frequent mode of K of the concentrated support of this group data item.
430 because the electric automobile data belong to the repetition rate higher data, only adopt bottom-up method for digging recurrence to excavate local frequent pattern tree (fp tree).For a data item a in the head table
i, structure a
iThe condition pattern base, and according to the upright a of condition pattern capital construction
iFor the condition pattern tree of prefix, carry out 4440) to 4460) strategy.
440 convergence strategies: if a
iAll conditions pattern base all comprise public prefix Y and do not have the superset of Y, a so
i∪ Y is that a candidate closes frequent mode.Step 4460) it is carried out the closure inspection.If, then this candidate is closed frequent mode and be saved in the k raft of this group, adjust raft, otherwise abandon this Candidate Set through inspection.
450 beta pruning strategies: for candidate's frequent mode X, if having one excavated close frequent mode Z, Z is the superset of X, and X has identical support with Z, but the descendants of X and X can be cut.
460 closed inspections, according to CLOSET+, for a candidate's the frequent mode that closes, only need with the k raft in the result that excavated relatively, if not any one closes the subclass of frequent mode in the K raft, then candidate pattern is added in the K raft, and adjustment K raft.
470 recurrence are excavated a
iCondition pattern tree.Recurrence carries out 4430) to 4470).
50 merge the local frequent mode collection of all groups.Carrying out closed inspection once more, is closure with the frequent mode collection of guaranteeing the overall situation.Each Mapper input gid and relevant local frequent mode collection with it, (key=s, value): support s of key, value have the frequent mode that support is s in output.The frequent mode of the identical support of Reducer merger, the frequent mode of checking the support that this is identical concentrate whether exist two close frequent mode X and Y, X is the superset of Y, then Y is removed if exist.Reducer output (key ', value ') key ' be a support, and the value ' frequent mode that closes of support for this reason gathers.
60 according to overall frequent mode set generation correlation rule.Any two that close in the frequent mode for the overall situation are closed frequent mode X; Y; If satisfy: X ∪ Y also is one and closes frequent mode; And the degree of confidence of not closing frequent mode Z feasible
and X and Y gained generates correlation rule X-＞Y so greater than min confidence.
To excavate the result and return to client, and display with intelligible mode.
Obviously, the above embodiment of the present invention only be for clearly the present invention is described and is done for example, and be not to be qualification to embodiment of the present invention.For the those of ordinary skill in affiliated field, on the basis of above-mentioned explanation, can also make other multi-form variation or change.Here need not also can't give exhaustive to all embodiments.And these belong to conspicuous variation or the change that connotation of the present invention extends out and still belong to protection scope of the present invention.
Claims (6)
1. electric automobile data digging system based on the cloud computing machine frame, the digging system front-end module that comprises data acquisition module, links to each other through 3G network with data acquisition module, the cloud computing machine Hadoop cluster module that links to each other with the digging system front-end module.
2. the electric automobile data digging system based on the cloud computing machine frame according to claim 1; It is characterized in that: said digging system front-end module comprises data importing module, association rule mining module, frequent highway section excavation module; Said data importing module links to each other through 3G network with data acquisition module, and association rule mining module, frequent highway section are excavated module and linked to each other with the data importing module respectively.
3. the electric automobile data digging system based on the cloud computing machine frame according to claim 2; It is characterized in that: said cloud computing machine Hadoop cluster module comprises data processing module and data memory module, and said data processing module excavates module with the association rule mining module with frequent highway section and links to each other.
4. the electric automobile data digging method based on the cloud computing machine frame comprises the steps:
Step 1, by the data collecting module collected data, and be sent to the digging system front end through 3G network, the data set cutting that the digging system front end will excavate is some independently data blocks and record;
All supports are greater than frequent 1 data field of minimum support in step 2, parallel each data block of statistics, and the result is stored among the F-list;
Step 3, frequent 1 the data field among the F-list is divided into G group;
Grouping executed in parallel FPGrowth algorithm in step 4, the cloud computing machine Hadoop cluster module,, generate and preserve relevant part and close the frequent mode collection;
Step 5, merge the part and close the frequent mode collection, what generate the overall situation closes the frequent mode collection, closes the frequent mode collection according to the overall situation at last and generates break-even correlation rule.
5. according to the electric automobile data digging method described in the claim 4, it is characterized in that based on the cloud computing machine frame: in step 3, G each group of organizing is labeled as a G-List, and reference numeral gid.
6. according to the electric automobile data digging method described in the claim 5, it is characterized in that: in step 4, when carrying out the FPGrowth algorithm, add fusion, beta pruning, closed inspection step based on the cloud computing machine frame.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011104314536A CN102567488A (en) | 2011-12-21 | 2011-12-21 | System and method for mining data of electric vehicle based on cloud computer framework |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011104314536A CN102567488A (en) | 2011-12-21 | 2011-12-21 | System and method for mining data of electric vehicle based on cloud computer framework |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102567488A true CN102567488A (en) | 2012-07-11 |
Family
ID=46412891
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2011104314536A Pending CN102567488A (en) | 2011-12-21 | 2011-12-21 | System and method for mining data of electric vehicle based on cloud computer framework |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102567488A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102917031A (en) * | 2012-09-25 | 2013-02-06 | 浙江图讯科技有限公司 | Data computing system of safety production cloud service platform for industrial and mining enterprises |
| CN103150163A (en) * | 2013-03-01 | 2013-06-12 | 南京理工大学常熟研究院有限公司 | Map/Reduce mode-based parallel relating method |
| CN103678521A (en) * | 2013-11-30 | 2014-03-26 | 电子科技大学 | Distributed file monitoring system based on Hadoop frame |
| CN104346376A (en) * | 2013-07-31 | 2015-02-11 | 克拉玛依红有软件有限责任公司 | Method and system for dynamically inserting data mining algorithm into data mining platform |
| CN104809180A (en) * | 2014-12-15 | 2015-07-29 | 安徽四创电子股份有限公司 | Method for identifying illegal operation vehicle based on non-supervision intelligent learning algorithm |
| CN104834557A (en) * | 2015-05-18 | 2015-08-12 | 成都博元科技有限公司 | Data analysis method based on Hadoop |
| CN110489448A (en) * | 2019-07-24 | 2019-11-22 | 西安理工大学 | The method for digging of big data correlation rule based on Hadoop |
| CN113641726A (en) * | 2021-08-06 | 2021-11-12 | 国网北京市电力公司 | Unsupervised sheath current data mining system based on generation countermeasure network |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102024999A (en) * | 2010-11-16 | 2011-04-20 | 上海交通大学 | Electric car running power management system |
| CN102185927A (en) * | 2011-05-31 | 2011-09-14 | 北京亿赞普网络技术有限公司 | Knowledge-as-service cloud computing platform |
-
2011
- 2011-12-21 CN CN2011104314536A patent/CN102567488A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102024999A (en) * | 2010-11-16 | 2011-04-20 | 上海交通大学 | Electric car running power management system |
| CN102185927A (en) * | 2011-05-31 | 2011-09-14 | 北京亿赞普网络技术有限公司 | Knowledge-as-service cloud computing platform |
Non-Patent Citations (2)
| Title |
|---|
| 缪裕青: "频繁闭合项目集的并行挖掘算法研究", 《计算机科学》, vol. 31, no. 5, 31 December 2004 (2004-12-31), pages 166 - 168 * |
| 蔡建新等: "基于云计算平台的海量数据挖掘技术在塑料电子商务平台中的应用", 《广东科技》, no. 16, 31 August 2011 (2011-08-31), pages 58 - 59 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102917031A (en) * | 2012-09-25 | 2013-02-06 | 浙江图讯科技有限公司 | Data computing system of safety production cloud service platform for industrial and mining enterprises |
| CN103150163A (en) * | 2013-03-01 | 2013-06-12 | 南京理工大学常熟研究院有限公司 | Map/Reduce mode-based parallel relating method |
| CN104346376A (en) * | 2013-07-31 | 2015-02-11 | 克拉玛依红有软件有限责任公司 | Method and system for dynamically inserting data mining algorithm into data mining platform |
| CN104346376B (en) * | 2013-07-31 | 2017-11-03 | 红有软件股份有限公司 | Method and system of the data mining algorithm dynamic insertion to data mining platform |
| CN103678521A (en) * | 2013-11-30 | 2014-03-26 | 电子科技大学 | Distributed file monitoring system based on Hadoop frame |
| CN103678521B (en) * | 2013-11-30 | 2016-08-17 | 电子科技大学 | A kind of distributed document monitoring system based on Hadoop framework |
| CN104809180A (en) * | 2014-12-15 | 2015-07-29 | 安徽四创电子股份有限公司 | Method for identifying illegal operation vehicle based on non-supervision intelligent learning algorithm |
| CN104809180B (en) * | 2014-12-15 | 2018-09-07 | 安徽四创电子股份有限公司 | Illegal vehicle in use recognition methods based on unsupervised intelligence learning algorithm |
| CN104834557A (en) * | 2015-05-18 | 2015-08-12 | 成都博元科技有限公司 | Data analysis method based on Hadoop |
| CN110489448A (en) * | 2019-07-24 | 2019-11-22 | 西安理工大学 | The method for digging of big data correlation rule based on Hadoop |
| CN113641726A (en) * | 2021-08-06 | 2021-11-12 | 国网北京市电力公司 | Unsupervised sheath current data mining system based on generation countermeasure network |
| CN113641726B (en) * | 2021-08-06 | 2024-01-30 | 国网北京市电力公司 | Unsupervised sheath current data mining system based on generation of countermeasure network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102567488A (en) | System and method for mining data of electric vehicle based on cloud computer framework | |
| CN103729478B (en) | LBS interest point discovery method based on MapReduce | |
| CN104618343B (en) | A kind of method and system of the website threat detection based on real-time logs | |
| CN105868075A (en) | System and method for monitoring and analyzing large amount of logs in real time | |
| CN105488641A (en) | Provincial highway operation management data center system and implementation method thereof | |
| CN104915456A (en) | Mass power utilization data mining method on the basis of data analysis system | |
| CN105069025A (en) | Intelligent aggregation visualization and management and control system for big data | |
| CN102968494A (en) | System and method for acquiring traffic information by microblog | |
| CN108268569A (en) | The acquisition of water resource monitoring data and analysis system and method based on big data technology | |
| CN109582714A (en) | A kind of government affairs item data processing method based on time fading correlation | |
| Huang et al. | Dynamic changes and transitions of agricultural landscape patterns in mountainous areas: A case study from the hinterland of the Three Gorges Reservoir Area | |
| CN101894129A (en) | Video topic finding method based on online video-sharing website structure and video description text information | |
| CN110019070A (en) | A kind of security log clustering method based on Hadoop and system of calling to account | |
| Li et al. | Study of identification and simulation of ecological zoning through integration of landscape ecological risk and ecosystem service value | |
| Zhang et al. | Research on intelligent analysis of port logistics information based on dynamic data mining | |
| CN107995278B (en) | A kind of scene intelligent analysis system and method based on metropolitan area grade Internet of Things perception data | |
| CN102957821A (en) | Alarm short massage service system for space environment disaster incidents | |
| CN117171244A (en) | Enterprise data management system based on data middle platform construction and data analysis method thereof | |
| CN104778355A (en) | Trajectory outlier detection method based on wide-area distributed traffic system | |
| CN104156440B (en) | A kind of traffic data acquisition methods based on microblogging | |
| Chen et al. | Internet of things technology in ecological security assessment system of intelligent land | |
| CN104933491A (en) | Industrial enterprise energy consumption diagnosis early warning system | |
| CN104268270A (en) | Map Reduce based method for mining triangles in massive social network data | |
| CN101345691A (en) | Method for intelligently generating data analysis report and dispatching through wireless/wired technology | |
| CN102945271A (en) | Simplified storing and backtracking method for several times of historical relation changes of single land parcel |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20120711 |