Patent US186541A successfully refreshed from Google Patents.
Patent US7702482B2 successfully refreshed from Google Patents.
US7702482B2
Expired / Lapsed
US
⏱️ 0.0 years remaining
Dependency structure from temporal data
Assignee: Microsoft Technology Licensing LLC
•
Filing: 2004-12-30
•
Granted: 2010-04-20
•
Expires: 2024-12-30
Abstract
Abstract Based on the time series data from multiple components, the systems administrator or other managing entity may desire to find the temporal dependencies between the different time series data over time. For example, based on actions indicated in time series data from two or more servers in a server network, a dependency structure may be determined which indicates a parent/child or dependent relationship between the two or more servers. In some cases, it may also be beneficial to predict the state of a child component, and/or predict the average time to a state change or event of a child component based on the parent time series data. These determinations and predications may reflect the logical connections between actions of components. The relationships and/or predictions may be expressed graphically and/or in terms of a probability distribution.
Inventors
- 👤 Thore K H Graepel
- 👤 Ralf Herbrich
- 👤 Shyansundar Rajaram
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-07 13:35
CPC Classifications
G; G06; G06F; G06F11/00; G06F11/30; G06F11/34; G06F11/3452; G06F11/3447; G06F11/3466; G06F11/3495; G06F11/3409; G06F11/3419; G06F2201/00; G06F2201/835
Claims Analysis
Total Claims: 15
Claim 1
Independent Claim
185 words
A method comprising: a) gathering a first time series of event data of a first server; b) gathering a second time series of event data of a second server; c) partitioning a timeline of the first time series into at least one time segment based on the second time series and a predetermined time window duration; d) counting a number of events of the second time series in each of the at least one time segment; e) determining a likelihood of a dependency relationship of the first time series from the second time series based on the number of events in each of the at least one time segment; f) determining a likelihood of no dependency relationship of the first time series from the second time series including determining a probability of the first time series as a function of a normalization constant; and g) selecting, by a processor, a maximum of the likelihood of the dependency relationship of the first time series from the second time series, and the likelihood of no dependency relationship of the first time series from the second time series.
Claim 2
Independent Claim
185 words
A method comprising: a) gathering a first time series of event data of a first server; b) gathering a second time series of event data of a second server; c) partitioning a timeline of the first time series into at least one time segment based on the second time series and a predetermined time window duration; d) counting a number of events of the second time series in each of the at least one time segment; e) determining a likelihood of a dependency relationship of the first time series from the second time series based on the number of events in each of the at least one time segment; f) determining a likelihood of no dependency relationship of the first time series from the second time series including determining a probability of the first time series as a function of a normalization constant; and g) selecting, by a processor, a maximum of the likelihood of the dependency relationship of the first time series from the second time series, and the likelihood of no dependency relationship of the first time series from the second time series.
Claim 3
Dependent Claim
45 words
The method of claim 1 , wherein determining a likelihood of a dependency relationship of the first time series from the second time series includes determining a probability of the first time series given the second time series as a function of the normalization constant.
Claim 4
Dependent Claim
29 words
The method of claim 2 , wherein determining a probability of the first time series given the second time series includes approximating a probability distribution of a weighting parameter.
Claim 5
Dependent Claim
46 words
The method of claim 1 , further comprising gathering a third time series of event data of a third server and determining a likelihood of a dependency relationship of the first time series from a combination of the second time series and the third time series.
Claim 6
Dependent Claim
35 words
The method of claim 1 , wherein determining a likelihood of a dependency relationship includes formulating a generalized linear model for a hazard rate function based on the number of events in each time segment.
Claim 7
Dependent Claim
23 words
The method of claim 5 , wherein formulating a generalized linear model includes modeling the hazard rate function as an exponential weighting function.
Claim 8
Dependent Claim
44 words
The method of claim 1 , further comprising determining a dependency structure of a system comprising the first time series and the second time series by determining a likelihood of a dependency relationship for each of the first and second time series of data.
Claim 9
Dependent Claim
37 words
The method of claim 1 , further comprising predicting an event of the first time series based on the second time series and the determined dependency relationship of the first time series from the second time series.
Claim 10
Dependent Claim
85 words
The method of claim 1 , further comprising displaying the determined dependency relationship of the first time series on the second time series on a display device of a computer system, wherein the first time series is displayed as a first node and the second time series is displayed as a second node, and the dependency relationship is displayed as a directed connector from the second node to the first node, and a strength of the determined dependency relationship is associated with the directed connector.
Claim 11
Dependent Claim
298 words
One or more computer storage media containing computer executable instructions that, when implemented, perform a method comprising: a) storing a first time series of data of a first server as a sequence of time stamps, each time stamp being associated with one of a state up indicator and a state down indicator; b) storing a second time series of data of a second server as a sequence of time stamps, each time stamp being associated with one of a state up indicator and a state down indicator; c) partitioning a timeline of the first time series into at least one time segment based on the second time series; d) determining a likelihood of a dependency relationship of the first time series from the second time series; e) determining a likelihood of no dependency relationship of the first time series from the second time series including determining a probability of the first time series as a function of a normalization constant; f) selecting a maximum of the likelihood of the dependency relationship of the first time series from the second time series and the likelihood of no dependency relationship of the first time series from the second time series; and g) when the selected maximum is the likelihood of the dependency relationship of the first time series from the second time series, displaying the determined dependency relationship of the first time series on the second time series on a display device of a computer system, wherein the first time series is displayed as a first node and the second time series is displayed as a second node, and the dependency relationship is displayed as a directed connector from the second node to the first node, and a strength of the determined dependency relationship is associated with the directed connector.
Claim 12
Dependent Claim
298 words
One or more computer storage media containing computer executable instructions that, when implemented, perform a method comprising: a) storing a first time series of data of a first server as a sequence of time stamps, each time stamp being associated with one of a state up indicator and a state down indicator; b) storing a second time series of data of a second server as a sequence of time stamps, each time stamp being associated with one of a state up indicator and a state down indicator; c) partitioning a timeline of the first time series into at least one time segment based on the second time series; d) determining a likelihood of a dependency relationship of the first time series from the second time series; e) determining a likelihood of no dependency relationship of the first time series from the second time series including determining a probability of the first time series as a function of a normalization constant; f) selecting a maximum of the likelihood of the dependency relationship of the first time series from the second time series and the likelihood of no dependency relationship of the first time series from the second time series; and g) when the selected maximum is the likelihood of the dependency relationship of the first time series from the second time series, displaying the determined dependency relationship of the first time series on the second time series on a display device of a computer system, wherein the first time series is displayed as a first node and the second time series is displayed as a second node, and the dependency relationship is displayed as a directed connector from the second node to the first node, and a strength of the determined dependency relationship is associated with the directed connector.
Claim 13
Dependent Claim
33 words
The one or more computer storage media of claim 10 , wherein partitioning includes partitioning only segments of the timeline associated with a state up indicator of the first time series of data.
Claim 14
Dependent Claim
31 words
The one or more computer storage media of claim 10 , wherein the state up indicator indicates a component up condition and the state down indicator indicates a component down condition.
Claim 15
Dependent Claim
43 words
The one or more computer storage media of claim 10 , wherein the state up indicator indicates zero events occurring in a predetermined window in the past, and the state down indicator indicates one event occurring in a predetermined window in the past.
References Cited (Backward Citations)
US5896552A
Cited
US6618725B1
Cited
US20040002969A1
Cited
US20050172306A1
Cited
US20060041659A1
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2013-04-19 | 2013-10-19 | 2014-04-20 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2017-04-19 | 2017-10-19 | 2018-04-20 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2021-04-19 | 2021-10-19 | 2022-04-20 | $7700.00 | Window Closed / Lapsed |