CN105320835A - Apparatus and method for time series data analysis method market - Google Patents
Apparatus and method for time series data analysis method market Download PDFInfo
- Publication number
- CN105320835A CN105320835A CN201410523988.XA CN201410523988A CN105320835A CN 105320835 A CN105320835 A CN 105320835A CN 201410523988 A CN201410523988 A CN 201410523988A CN 105320835 A CN105320835 A CN 105320835A
- Authority
- CN
- China
- Prior art keywords
- analytical approach
- various analysis
- time series
- cloud computing
- series data
- 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
- 238000000034 method Methods 0.000 title claims abstract description 65
- 238000007405 data analysis Methods 0.000 title 1
- 238000004458 analytical method Methods 0.000 claims abstract description 72
- 238000013459 approach Methods 0.000 claims description 160
- 238000011161 development Methods 0.000 claims description 10
- 230000018109 developmental process Effects 0.000 description 8
- 238000012731 temporal analysis Methods 0.000 description 6
- 238000000700 time series analysis Methods 0.000 description 6
- 238000013500 data storage Methods 0.000 description 5
- 238000013433 optimization analysis Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 230000007246 mechanism Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
- 230000036962 time dependent Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
accessing a plurality of analysis methods in a cloud computing environment; each of the plurality of the analysis methods performing operations for time series data; choosing one or more methods selected in the plurality of the analysis methods; uploading a group of the time series data to the cloud computing environment, and optimizing one method selected in the plurality of the analysis methods based on the group of the time series data.
Description
Technical field
Theme disclosed herein relates to time series data, and more particularly, relates to and carry out mutual analytical approach market with this data.
Background technology
Data are stored on data storage device in a variety of formats.In addition, utilize dissimilar data storage device to store data, and the cost of these data storage devices is different.In an example, can according to specific format memory data on the high cost equipment of such as random access storage device (RAM).In other instances, data can be stored on the low-cost equipment of such as hard disk.
A kind of data type stored is time series data.On the one hand, by sensor or the measuring equipment acquisition time sequence data of some type, and the function of time is it can be used as to store.Such as, survey sensor reads parameter with predetermined time interval, and each measurement result is stored in memory.Typically, because a large amount of data associate with time series measurement, the storage of this data becomes particularly troublesome.
The control of time series data and tissue segmentation are come by previous system.In other words, described time series data is dispersed in multiple position, and provides control in multiple different position.The segmentation controlled and organize makes control and shared information between the different user of time series data become difficulty.As a result, user can not learn the experience of other users or benefit from it.This has caused being discontented with for these prior method.
Summary of the invention
Method described herein provides open or concealed contributor can set up the approach with issuing time sequence data analytical approach, and other users can find, evaluate and adjust the performance of those Time series analysis method in based on the network environment of cloud computing.In other respects, process provides the platform allowing user to order the Optimal Example of those analytical approachs, then described example runs in the environment of their this locality.
In these embodiments many, by the various analysis of access based on cloud computing environment.Each execution operation to time series data in described various analysis.In cloud computing environment, to select in described various analysis select one or more.One group of time series data is uploaded to cloud computing environment, and based on this group time series data, the subset of selected various analysis is optimized.If have sufficiently high degree of accuracy, terminal user can select to order the analytical approach of described optimization and pay, thus runs these analytical approachs optimized based on their production time sequence data in the production environment of their this locality.
In other respects, obtain the copy of one or more methods selected in described multiple method for optimization analysis, and in home environment, perform described copy.Also in other respects, from home environment, obtain the performance data of described analytical approach.
In other embodiments, add in described various analysis by the development teams of analytical approach by additional analytical approach, the developer of described analytical approach can find in the owner in market and/or guardian.Also in other embodiments, add in described various analysis by third-party analytical approach developer by additional analytical approach, described third-party analytical approach developer and market owner and/or guardian do not have direct relation.
In other respects, method selected in described various analysis is ordered by user.Also in other respects, monitoring analysis method performance and to other user report of such as analytical approach developer.
In these embodiments many, by Equipments Setting for utilize time series data to adjust analytical approach in cloud computing environment, then perform these analytical approachs in this locality, described equipment comprises interface and controller.Described interface has input end and output terminal.
Described controller is coupled to described interface, and is configured as the various analysis in access cloud computing environment.Often kind of method in described various analysis is all to time series data executable operations.Further, described controller is configured in described cloud computing environment, select one selected in described various analysis.Further, described controller is configured to pass described input end and one group of time series data is uploaded to cloud computing environment, and based on this group time series data, one selected in described various analysis is optimized.
In other respects, described controller is configured to further the copy of the described multiple method for optimization analysis subset providing user to select, thus carries out disposing the execution for producing in home environment.In other respects, described controller is configured to further in home environment from described analytical approach receptivity data.
In other embodiments, described controller is configured to add additional analytical approach to described various analysis, described analytical approach is provided by the development teams of analytical approach, and the developer of described analytical approach can find in the owner in market and/or guardian.In other embodiments, add in described various analysis by third-party analytical approach developer by additional analytical approach, described third-party analytical approach developer and market owner and/or guardian do not have direct relation.
In other respects, be further configured to by described controller and receive order by described input end, described order orders subset selected in described various analysis.In other respects, described controller is further configured to the performance monitoring described analytical approach.
Technical scheme 1: a kind of time series data that utilizes in cloud computing environment is to adjust analytical approach and to perform the method for described analytical approach in this locality, and described method comprises:
In cloud computing environment, access various analysis, often kind in described various analysis to time series data executable operations;
In cloud computing environment, to select in various analysis select one or more;
Upload one group of time series data to cloud computing environment, and based on this group time series data to optimize in various analysis select one or more.
Technical scheme 2: the method according to technical scheme 1, comprises further, obtains one or more copy selected in described various analysis, and in home environment, runs described copy.
Technical scheme 3: the method according to technical scheme 2, comprises further, obtains a kind of performance data selected in described various analysis in home environment.
Technical scheme 4: the method according to technical scheme 1, comprises further, increase analyzing adjuncts method to described various analysis from independent source, described independent source operates in cloud computing environment.
Technical scheme 5: the method according to technical scheme 1, comprise further, increase analyzing adjuncts method to described various analysis, described analyzing adjuncts method is provided by the analytical approach development teams found in the market of market owner, one of the analytical approach development teams or third party developer that find in the market of market guardian.
Technical scheme 6: the method according to technical scheme 1, comprises further, order one or more in the various analysis selected.
Technical scheme 7: the method according to technical scheme 1, comprises further, monitors the performance of described analytical approach, and is reported to analytical approach creator.
Technical scheme 8: a kind of equipment, it is configured in cloud computing environment, utilize time series data to adjust analytical approach, and then perform described analytical approach in this locality, described equipment comprises:
There is the interface of input end and output terminal;
Controller, described controller is coupled to described interface, and be configured to access the various analysis in cloud computing environment, wherein, often kind in described various analysis to time series data executable operations, described controller is configured to select selected one or more in described various analysis further in described cloud computing environment, described controller is configured to one group of time series data to upload to cloud computing environment further, and to optimize in described various analysis selected one or more based on this group time series data.
Technical scheme 9: the equipment according to technical scheme 8, wherein, described controller is further configured to and obtains a kind of copy selected in described various analysis, and sends it to home environment for performing.
Technical scheme 10: the equipment according to technical scheme 9, wherein, described controller is further configured to the performance data receiving described analytical approach from home environment.
Technical scheme 11: the equipment according to technical scheme 8, wherein, described controller is configured to increase analyzing adjuncts method from independent source to described various analysis, and described independent source operates in cloud computing environment.
Technical scheme 12: the equipment according to technical scheme 8, wherein, described controller is configured to increase analyzing adjuncts method to described various analysis, and described analyzing adjuncts method is provided by the analytical approach development teams found in the market of market owner, one of the analytical approach development teams or third party developer that find in the market of market guardian.
Technical scheme 13: the equipment according to technical scheme 8, wherein, described controller is further configured to be received by described input end and orders, and described order orders selected one or more in various analysis.
Technical scheme 14: the equipment according to technical scheme 8, wherein, described controller is further configured to the performance monitoring described analytical approach, and is reported to analytical approach creator.
Accompanying drawing explanation
In order to the comprehend disclosure, with reference to the detailed description and the accompanying drawings below, wherein:
Fig. 1 comprises the block scheme in the data time series analysis method market according to different embodiments of the invention;
Fig. 2 comprises the process flow diagram for realizing the data time series analysis method market according to different embodiments of the invention; And
Fig. 3 comprises the block scheme for realizing the data time series analysis method market according to different embodiments of the invention.
Technician is appreciated that the element of illustrating in figure is for the sake of simplicity with clear.Further, can understand, can specifically describe or describe some behavior and/or step by order of occurrence, however it will be appreciated by those skilled in the art that in fact do not need this about order appointment.Equally, be appreciated that except not here proposes particular meaning, otherwise term used herein and wording have the respective inquiry corresponding to these terms and wording and its ordinary meaning in learning areas.
Embodiment
Method described herein provides a kind of market of cloud computing analytical approach, and user's (such as: data science man) can upload thus and operate in analytical approach in time series data and model.Themselves personal time sequence data can be uploaded to system for cloud computing by terminal user anonymously, and uses these data to train or optimize the performance of analytical approach described in one or more and/or model.After described training/optimizing process completes, often kind of analytical approach produces the results of property of such as overall precision, true and false positive rate.
If user accepts or likes described results of property, they can select to order described analytical approach.When user orders a kind of analytical approach, in their environment, described analytical approach enables to run in the time series data of their this locality automatically.In this way, terminal user need not the privacy concern of concern of data, and such as, when worrying to process in system for cloud computing, their data are stolen.As long as terminal user have subscribed described analytical approach, described analytical approach just can be run in the environment of their this locality.
On the other hand, this method is collected in the performance information of the analytical approach example disposed in their home environment.Described terminal user is allowed to upload new time series data at any time to cloud computing environment, to readjust the analytical approach that they ordered.In some respects, if the order of user terminates, then described analytical approach automatically stops and does not rerun.Return in the example of performance information terminal user to cloud computing environment, analytical approach creator can utilize described feedback to optimize their analytical approach further.Therefore, process provides a kind of base configuration, the exploitation of analytical approach thus can by team's mass-rent of analytical approach creator (such as: data science man and analytical approach model creator), similarly, analytical approach evaluation and feedback can by user group's mass-rent of analytical approach.
Many mechanisms and user are to its patent data and computing basic facility being placed in cloud environment the doubt had more or less, and concern of data is stolen or other safety problems.This method allows mechanism and user to utilize cloud computing service to test and evaluation analysis method on the data set that themselves is unique, use a group analyzing method creator (as, data science man) indirect one that provides and assistance, it can not be used for proving relational expression that is formal, standard usually.Meanwhile, ordered analytical approach is in local production run, and what therefore do not need to continue calculates facility to long-distance cloud and load private data.
In other respects, terminal user has the ability to analyze and optimize a group analyzing method, and can determine which kind of analytical approach is only required for them.This special advantage make terminal user can by experiment access time sequence data potential and googol according to storehouse.Further, describedly buying test before analytical approach or testing the ability of this analytical approach very attractive for terminal user, particularly the user of huge research budget there is no to those or the user that a group data science man deals with problems can not be accessed.
Once make the decision using which kind of analytical approach, those analytical approachs can seamless configuration in the local computing environments of terminal user.If preferential analytical approach is too strong for the local operating conditions of terminal user, cloud computing platform then can provide an alternatives flexibly, such as, for directly running central processing unit (CPU) based on plenty of time sequence data in cloud environment and storing strengthening analytical approach.
When not needing obtain actual usage data and protect privacy, As time goes on described analytical approach can also make moderate progress based on the performance-relevant feedback of analytical approach in user environment.Assuming that described data science man and other analytical approachs creator have powerful clairvoyance to travel through and develop their analytical approach, when there being great amount of terminals user to provide feedback, the platform that this method provides makes mass-rent method (crowd-sourcedapproach) can provide the feedback of analytical approach and how to improve them.
In other advantages, the analytical approach market that method described herein provides is that one has very cost-benefit environment for data scientist and other analytical approachs creator, these data sciences man and other analytical approachs creator submit analytical approach to, and terminal user can order these analytical approachs by the mode paid.In this method, the most useful analytical approach is easily determined, and the analytical approach useless to consumer can be return or adjust.This just requires that analytical approach creator has and is clearly familiar with and pays close attention to those real profitable analytical approachs.
To terminal user (as, the user of analytical approach is used in production environment), another benefit of these methods is that the value that can produce based on those analytical approachs weighs cost (cost of particularly operating analysis method).In other words, there is not the serial important front-end investment of a kind of needs.Described market also allows user participate in (e.g., user expert) assessment result and advise.Attemperator can provide feedback and suggested terminals user based on analytical approach results of property, and allow terminal user's Internet access expert team, they can not be regular employees.One includes analytical approach creator, the large team of tester and terminal user may reduce whole support costs, and available mass-rent support.
In the front end of system, terminal user can upload primordial time series data sample (together with any metadata be associated), and use described raw data set to adjust or optimize a kind of concrete analytical approach or various analysis to its unique data set.If the final accuracy of user to one or more analytical approachs described is satisfied, user just can select to order one or more analytical approachs.These analytical approachs can run (or directly running in primary climate) at local infrastructure by Time-Dependent sequence data.Described user, in its selected environment, can order and regular (optionally report analysis method performance in the environment e.g., monthly) or the payment when each executions of often kind of analytical approach, and selected by them.
In the rear end (e.g., ultimate consumer cannot touch and side that network control personnel and operating personnel can arrive) of system, data science man and other experts can set up and issue new analytical approach to user, for user's assessment with use.These experts can be the interior employees of mechanism, such as, set up analytical approach storehouse, or provide new analytical approach to market and have benefited from its analytical approach by the third party used for ordering.
As shown in Figure 1, a system for data time series analysis method market is specifically described.Described system 100 comprises system for cloud computing 102, the first home environment 106 (with first user 110), the second home environment 108 (with the second user 112).System for cloud computing 102 can be the combination of any one network or multiple network, such as cellular telephone network, the Internet, wide area network and LAN (Local Area Network).First home environment 106 and the second home environment 108 can comprise the combination of any one network type or above multiple network.First home environment 106 and the second home environment 108 can also comprise the electronic equipment of server, computing machine, processor or other type, and these electronic equipments are for performing function as described herein.Such as, the first home environment 106 and the second home environment 108 all adopt LAN (Local Area Network).First home environment 106 and the second home environment 108 all adopt beam coupling mode (e.g., wired or wireless) to be connected to system for cloud computing 102.
System for cloud computing 102 comprises analytical approach enforcement engine 114, first analytical approach 116 and the second analytical approach 118.First analytical approach 116 and the second analytical approach 118 are the analytical approachs based on time series data operation.The example of analytical approach comprises linear regression method of interpolation and abnormal detection method.Other analytical approach is also passable.Analytical approach enforcement engine 114, first analytical approach 116 and the second analytical approach 118 can be realized by moving calculation machine instruction on general purpose processing device.Very first time sequence data 104 generates and stores at the first home environment 106 place (as, be stored in the first data storage device 122), second time series data 120 generates and stores (e.g., being stored in the second data storage device 124) at the second home environment 108 place.
In an embodiment of Dynamic System as shown in Figure 1, the first user 110 in the first home environment 106 accesses the first analytical approach 116 and the second analytical approach 118 in system for cloud computing 102.First analytical approach 116 and the second analytical approach 118 are separately to time series data executable operations.In the cloud computing environment based on system for cloud computing 102, select in the first analytical approach 116 and the second analytical approach 118 one or both.Upload one group of time series data (as, very first time sequence data 104) to system for cloud computing 102, and based on this group time series data to optimize in various analysis the one (e.g., the first analytical approach 116 and the second analytical approach 118 one or both) selected.
In other respects, to obtain in described multiple method for optimization analysis selected one (as, the optimization version of the first analytical approach 116 and the second analytical approach 118) copy, and run described copy in home environment (e.g., the first home environment 106 or the second home environment 108).In addition, the performance data of analytical approach (e.g., the first analytical approach 116 or the second analytical approach 118) is obtained in home environment (e.g., the first home environment 106 or the second home environment 108).
In other embodiments, increase a kind of analyzing adjuncts method (e.g., the 3rd analytical approach 126) to described various analysis from an independent source 128, described independent source 128 runs in system for cloud computing 102.In other embodiments, from an independent source give described various analysis (first analytical approach 116 and the second analytical approach 118) increase a kind of analyzing adjuncts method (as, 3rd analytical approach 126), described independent source runs cloud computing environment outside (e.g., system for cloud computing 102 is outside).
Also in other embodiments, described various analysis one or more (e.g., first analytical approach 116 and second analytical approachs 118) are ordered by a user (e.g., first user 110 or the second user 112).In addition, monitor the performance of described analytical approach (first analytical approach 116 and the second analytical approach 118), and be reported to other users (e.g., first user 110 or the second user 112).When the example (copy) of analytical approach performs at system for cloud computing 102, first user 110 or the second user 112 provide feedback, make the first analytical approach 116 and the second analytical approach 118 can realize fine setting.
As shown in Figure 2, a kind of method of generation time sequence data analytical approach market is specifically described.In step 202, in cloud computing environment, access various analysis.Often kind in described various analysis to time series data executable operations.In step 204, in cloud computing environment, to select in various analysis the one selected.In step 206, upload one group of time series data to cloud computing environment, and in step 208, based on this group time series data to optimize in various analysis the one selected.
In other respects, obtain the copy of a kind of analytical approach selected in described multiple method for optimization analysis, and run described copy in home environment.In addition, the performance data of described analytical approach is obtained in home environment.
In other embodiments, add in described various analysis by the development teams of analytical approach by additional analytical approach, the developer of described analytical approach can find in the owner in market and/or guardian.In other embodiments, add in described various analysis by third-party analytical approach developer by additional analytical approach, described third-party analytical approach developer and market owner and/or guardian do not have direct relation.
In other embodiments, user orders described various analysis.In addition, monitor the performance of described analytical approach, and be reported to analytical approach creator.
As shown in Figure 3, equipment 300 comprises interface 302 and controller 304, and described equipment 300 is configured in cloud computing environment, utilize time series data to adjust analytical approach, then performs these analytical approachs in this locality.Interface 302 has input end 306 and output terminal 308.Equipment 300 can be the combination of any hardware cell or software unit, and in a certain embodiment, be included in the computer instruction that general purpose processing device runs.In one embodiment, equipment 300 realizes some or all functions of analytical approach enforcement engine 114 in Fig. 1, and is deployed in system for cloud computing.Other arrangement examples of described equipment 300 are also possible.And should be appreciated that, the function of described equipment 300 can be separated and be distributed to multiple position or equipment.
Described controller 304 is coupled to described interface 302, and is configured to the various analysis 305 of being accessed by output terminal 308 in cloud computing environment.Often kind of method in described various analysis 305 is all to time series data 310 executable operations.Described controller 304 is configured to select one selected in described various analysis 305 by output terminal 308 further in described cloud computing environment.Described controller 304 is configured to one group of time series data 310 to upload to cloud computing environment by input end 306 further, and is optimized one selected in described various analysis 305 based on this group time series data.
In other respects, described controller 304 is further configured to and obtains a kind of copy selected in described multiple method for optimization analysis 305, and sends it to home environment execution by output terminal 308.Still in these areas, described controller 304 is further configured to and receives the performance data of described analytical approach example at input end 306 from home environment.
In other embodiments, described controller 304 is configured to add additional analytical approach to described various analysis, described analytical approach is provided by the development teams of analytical approach, and the developer of described analytical approach can find in the owner in market and/or guardian.In other embodiments, add in described various analysis by third-party analytical approach developer by additional analytical approach, described third-party analytical approach developer and market owner and/or guardian do not have direct relation.
In other respects, be further configured to by described controller 304 and receive order 312 by described input end 306, described order 312 orders one selected in described various analysis.In other respects, described controller 304 is further configured to the performance monitoring described analytical approach, and receives monitor message 311 at input end 306, then by output terminal 308, monitor message is reported to user.
It should be appreciated by those skilled in the art that and can modify to previous embodiment in many aspects.Other changes are also obviously feasible, and in scope and spirit of the present invention.The present invention proposed has the characteristic in claims.Should think, the spirit and scope of the present invention comprise embodiment described herein such as have ordinary skill and be familiar with this application instruct the apparent modifications and variations of personnel.
Claims (10)
1. in cloud computing environment, utilize time series data to adjust then analytical approach performs a described analytical approach method in this locality, described method comprises:
In cloud computing environment, access various analysis, often kind in described various analysis to time series data executable operations;
In described cloud computing environment, to select in described various analysis selected one or more;
Upload one group of time series data to described cloud computing environment, and to optimize described in described various analysis selected one or more based on this group time series data.
2. method according to claim 1, comprises further, obtains one or more copy selected described in described various analysis, and in home environment, runs described copy.
3. method according to claim 2, comprises further, obtains a kind of performance data selected described in described various analysis in home environment.
4. method according to claim 1, comprises further, and increase analyzing adjuncts method to described various analysis from independent source, described independent source operates in described cloud computing environment.
5. method according to claim 1, comprise further, increase analyzing adjuncts method to described various analysis, described analyzing adjuncts method is provided by the analytical approach development teams found in the market of market owner, one of the analytical approach development teams or third party developer that find in the market of market guardian.
6. method according to claim 1, comprises further, to order described in described various analysis selected one or more.
7. method according to claim 1, comprises further, monitors the performance of described analytical approach, and is reported to described analytical approach creator.
8. an equipment, be configured in cloud computing environment, utilize time series data to adjust analytical approach, then perform described analytical approach in this locality, described equipment comprises:
There is the interface of input end and output terminal;
Controller, described controller is coupled to described interface, and be configured to access the various analysis in described cloud computing environment, wherein, often kind in described various analysis to time series data executable operations, described controller is configured to select selected one or more in described various analysis further in described cloud computing environment, described controller is configured to one group of time series data to upload to described cloud computing environment further, and to optimize described in described various analysis selected one or more based on this group time series data.
9. equipment according to claim 8, wherein, described controller is further configured to and obtains a kind of copy selected described in described various analysis, and sends it to home environment for performing.
10. equipment according to claim 9, wherein, described controller is further configured to the performance data receiving described analytical approach from described home environment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410523988.XA CN105320835A (en) | 2014-07-15 | 2014-07-15 | Apparatus and method for time series data analysis method market |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410523988.XA CN105320835A (en) | 2014-07-15 | 2014-07-15 | Apparatus and method for time series data analysis method market |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105320835A true CN105320835A (en) | 2016-02-10 |
Family
ID=55248214
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410523988.XA Pending CN105320835A (en) | 2014-07-15 | 2014-07-15 | Apparatus and method for time series data analysis method market |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105320835A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101511099A (en) * | 2009-04-01 | 2009-08-19 | 南京邮电大学 | Collection method for wireless sensor network data based on time series prediction model |
| CN101782976A (en) * | 2010-01-15 | 2010-07-21 | 南京邮电大学 | Automatic selection method for machine learning in cloud computing environment |
| CN103164742A (en) * | 2013-04-02 | 2013-06-19 | 南京邮电大学 | Server performance prediction method based on particle swarm optimization nerve network |
| US20130262866A1 (en) * | 2012-03-27 | 2013-10-03 | Fudan University | Large-scale data processing cloud computing system |
| CN103853918A (en) * | 2014-02-21 | 2014-06-11 | 南京邮电大学 | Cloud computing server dispatching method based on idle time prediction |
-
2014
- 2014-07-15 CN CN201410523988.XA patent/CN105320835A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101511099A (en) * | 2009-04-01 | 2009-08-19 | 南京邮电大学 | Collection method for wireless sensor network data based on time series prediction model |
| CN101782976A (en) * | 2010-01-15 | 2010-07-21 | 南京邮电大学 | Automatic selection method for machine learning in cloud computing environment |
| US20130262866A1 (en) * | 2012-03-27 | 2013-10-03 | Fudan University | Large-scale data processing cloud computing system |
| CN103164742A (en) * | 2013-04-02 | 2013-06-19 | 南京邮电大学 | Server performance prediction method based on particle swarm optimization nerve network |
| CN103853918A (en) * | 2014-02-21 | 2014-06-11 | 南京邮电大学 | Cloud computing server dispatching method based on idle time prediction |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Giagopoulos et al. | Structural health monitoring and fatigue damage estimation using vibration measurements and finite element model updating | |
| US10652164B2 (en) | Instant notification of load balance and resource scheduling based on resource capacities and event recognition | |
| Storlie et al. | Calibration of computational models with categorical parameters and correlated outputs via Bayesian smoothing spline ANOVA | |
| Wei et al. | Using the reliability theory for assessing the decision confidence probability for comparative life cycle assessments | |
| Jiang et al. | Reduction of epistemic model uncertainty in simulation-based multidisciplinary design | |
| Tamura et al. | Optimisation analysis for reliability assessment based on stochastic differential equation modelling for open source software | |
| Krishnapriyan et al. | Learning continuous models for continuous physics | |
| Ko et al. | Condition-based joint maintenance optimization for a large-scale system with homogeneous units | |
| Löfstrand et al. | A model for predicting and monitoring industrial system availability | |
| Mazak et al. | Model-based generation of run-time data collection systems exploiting AutomationML | |
| Anselin | Quantile local spatial autocorrelation | |
| Pan et al. | Identification of external forces via truncated response sparse decomposition under unknown initial conditions | |
| US20210142286A1 (en) | Automated Parameterized Modeling And Scoring Intelligence System | |
| Pacheco et al. | An open source cyberinfrastructure for collecting, processing, storing and accessing high temporal resolution residential water use data | |
| KR102543838B1 (en) | Method and appartus for obtaining information | |
| Dabiri et al. | Fractional rheology-informed neural networks for data-driven identification of viscoelastic constitutive models | |
| JP2018101201A (en) | Policy introduction effect prediction device, policy introduction effect prediction program and policy introduction effect prediction method | |
| Lin et al. | Response covariance-based sensor placement for structural damage detection | |
| Marountas et al. | Recommending database architectures for social queries: A Twitter case study | |
| Jiang et al. | Multiattribute group decision making with unknown decision expert weights information in the framework of interval intuitionistic trapezoidal fuzzy numbers | |
| Grow et al. | Statistical emulation | |
| CN105320835A (en) | Apparatus and method for time series data analysis method market | |
| US20140278770A1 (en) | Generating economic model based on business transaction messages | |
| Selvitopi et al. | Numerical results for the Klein‐Gordon equation in de Sitter spacetime | |
| Chu et al. | A unified framework for assessing interaction effects among environmental exposures in epidemiologic studies: A case study on temperature, air pollution, and kidney-related conditions in New York state |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20160210 |
|
| WD01 | Invention patent application deemed withdrawn after publication |