# US 2018/0324030 A1 · Operational analytics in managed networks

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2018/0324030 A1
- Document ID: US20180324030A1
- Status: Published application
- Kind: A1
- Application number: 15/587,066
- Filed: 2017-05-04
- Published: 2018-11-08
- Earliest claimed: 2017-05-04
- Assignees: ServiceNow, Inc.
- Applicants: ServiceNow, Inc.
- Inventors: Kanwaldeep Dang; Purushottam Amradkar; Scott Tucker; Qingbin Li
- Web page: https://patentgrep.com/patent/US20180324030A1

## CPC

- H04L 41/5009: Determining service level performance parameters or violations of service level contracts, e.g. violations of agreed response time or mean time between failures [MTBF]
- H04L 41/065: {involving logical or physical relationship, e.g. grouping and hierarchies}
- H04L 41/0686: Additional information in the notification, e.g. enhancement of specific meta-data
- H04L 41/142: using statistical or mathematical methods
- H04L 41/147: for predicting network behaviour
- H04L 41/22: comprising specially adapted graphical user interfaces [GUI]
- H04L 43/0817: by checking functioning
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

A computing system and method for remote monitoring and forecasting of performance of a managed network is disclosed. The computing system may be disposed within a remote network management platform and be configured for monitoring respective performance of each of a plurality of network entities of the managed network. For each network entity, an alert may be issued in response to determining that the monitored respective performance is below a respective threshold performance level. Based on analysis of a group of alerts, a likelihood may be determined that a different alert will be issued for the monitored performance of a particular network entity of the plurality for which no respective alert has yet been issued. In response to the likelihood exceeding a threshold, an alert prediction for the performance of the particular network entity may be issued together with a score corresponding to the likelihood.

## Claims

### Claim 1

A computing system disposed within a remote network management platform and configured to support a managed network, the computing system comprising:
one or more processors;
memory; and
program instructions, stored in the memory, that upon execution by the one or more processors cause the computing system to perform operations including:
monitoring respective performance of each network entity of a plurality of network entities of the managed network, each network entity being at least one of a service of the managed network or a computing device of the managed network, wherein each service of the managed network executes on at least one computing device of the managed network;
for each of the plurality of network entities, issuing an alert in response to determining that the monitored respective performance is below a respective threshold performance level;
based on analysis of a first group of one or more issued alerts, determining a statistical likelihood that a different alert will be issued for the monitored respective performance of a particular network entity of the plurality for which no respective alert has yet been issued; and
issuing a score notification for the different alert in response to the determined statistical likelihood exceeding a score threshold, wherein the score notification includes the determined statistical likelihood and an identity of the particular network entity.

### Claim 2 (depends on 1)

The computing system of claim 1, wherein the operations further include:
based on analysis of a second group of one or more issued alerts, determining another statistical likelihood that another different alert will be issued for the monitored respective performance of another particular network entity of the plurality for which no respective alert has yet been issued; and
issuing another score notification for the other different alert in response to the determined other statistical likelihood exceeding another score threshold, wherein the other score notification includes the determined other statistical likelihood and an identity of the other particular network entity.

### Claim 3 (depends on 1)

The computing system of claim 1, wherein the remote management platform is communicatively connected to the plurality of network entities via an intermediary network device in the managed network,
and wherein monitoring the respective performance of each network entity of the plurality of network entities comprises:
transmitting one or more messages from the computing system to the intermediary network device requesting performance metrics of one or more network entities of the plurality; and
receiving data transmitted from the intermediary network device indicative of the requested performance metrics.

### Claim 4 (depends on 1)

The computing system of claim 1, wherein determining that the monitored respective performance is below the respective threshold performance level comprises determining that a metric indicative of performance is one of: below a target threshold, or outside of a target operating range.

### Claim 5 (depends on 1)

The computing system of claim 1, wherein determining the statistical likelihood based on analysis of the first group of one or more issued alerts comprises:
for each respective issued alert of the one or more issued alerts, determining a respective conditional probability that the monitored respective performance of the particular network entity will be below a particular threshold performance level given an occurrence of issuance of the respective issued alert.

### Claim 6 (depends on 5)

The computing system of claim 5, wherein determining the respective conditional probability that the monitored respective performance of the particular network entity will be below the particular threshold performance level given the occurrence of the issuance of the respective issued alert comprises:
compiling a historical record of alerts issued for both (i) the monitored respective performance of the network entities of the plurality associated with the first group of the one or more issued alerts, and (ii) the monitored respective performance of the particular network entity;
computing a joint probability distribution of the historical record; and
deriving the respective conditional probability from the computed joint probability distribution.

### Claim 7 (depends on 5)

The computing system of claim 5, wherein computing the joint probability distribution of the historical record comprises computing an analytic approximation of the joint probability distribution as a Chow-Liu tree.

### Claim 8 (depends on 1)

The computing system of claim 1, wherein the operations further include:
prior to determining the statistical likelihood, identifying the first group of the one or more issued alerts from among a plurality of issued alerts; and
prior to determining the statistical likelihood, identifying the different alert as a potential alert that is associated with the first group of the one or more issued alerts.

### Claim 9 (depends on 8)

The computing system of claim 8, wherein identifying the different alert as a potential alert that is associated with the first group of the one or more issued alerts comprises determining a causal relation between the first group of the one or more issued alerts and the potential alert.

### Claim 10 (depends on 8)

The computing system of claim 8, wherein the computing system further comprises an interactive display device,
and wherein identifying the first group of the one or more issued alerts from among a plurality of issued alerts comprises:
displaying the plurality of issued alerts on the interactive display device; and
using an interactive cursor of the interactive display device to select the first group of the one or more issued alerts from among the displayed plurality of issued alerts.

### Claim 11 (depends on 1)

The computing system of claim 1, wherein issuing a score notification for the different alert comprises:
computing a prediction score as a statistical confidence level that an alert will be issued for the monitored respective performance of the particular network entity; and
reporting the prediction score.

### Claim 12 (depends on 1)

The computing system of claim 1, wherein the operations further include:
setting the respective threshold performance level of each of the plurality of network entities; and
setting the score threshold.

### Claim 13

A computer-implemented method carried out by a computing system disposed within a remote network management platform and configured to support a managed network, the method comprising:
monitoring respective performance of each network entity of a plurality of network entities of the managed network, each network entity being at least one of a service of the managed network or a computing device of the managed network, wherein each service of the managed network executes on at least one computing device of the managed network;
for each of the plurality of network entities, issuing an alert in response to determining that the monitored respective performance is below a respective threshold performance level;
based on analysis of a first group of one or more issued alerts, determining a statistical likelihood that a different alert will be issued for the monitored respective performance of a particular network entity of the plurality for which no respective alert has yet been issued; and
issuing a score notification for the different alert in response to the determined statistical likelihood exceeding a score threshold, wherein the score notification includes the determined statistical likelihood and an identity of the particular network entity.

### Claim 14 (depends on 13)

The method of claim 13, wherein the remote management platform is communicatively connected to the plurality of network entities via an intermediary network device in the managed network,
and wherein monitoring the respective performance of each network entity of the plurality of network entities comprises:
transmitting one or more messages from the computing system to the intermediary network device requesting performance metrics of one or more network entities of the plurality; and
receiving data transmitted from the intermediary network device indicative of the requested performance metrics.

### Claim 15 (depends on 13)

The method of claim 13, wherein determining the statistical likelihood based on analysis of the first group of one or more issued alerts comprises:
compiling a historical record of alerts issued for both (i) the monitored respective performance of the network entities of the plurality associated with the first group of the one or more issued alerts, and (ii) the monitored respective performance of the particular network entity;
computing a joint probability distribution of the historical record; and
for each respective issued alert of the one or more issued alerts, deriving from the computed joint probability distribution a respective conditional probability that the monitored respective performance of the particular network entity will be below a particular threshold performance level given an occurrence of issuance of the respective issued alert.

### Claim 16 (depends on 13)

The method of claim 13, wherein the computing system further comprises an interactive display device,
and wherein the method further comprises:
prior to determining the statistical likelihood, using an interactive cursor of the interactive display device to select the first group of the one or more issued alerts from among a plurality of issued alerts displayed on the interactive display device; and
prior to determining the statistical likelihood, identifying the different alert as a potential alert that is causally related to the first group of the one or more issued alerts.

### Claim 17

A non-transitory computer-readable medium having instructions stored thereon that, when executed by one or more processors of a computing system disposed within a remote network management platform and configured to support a managed network, cause the computing system to carry out operations including:
monitoring respective performance of each network entity of a plurality of network entities of the managed network, each network entity being at least one of a service of the managed network or a computing device of the managed network, wherein each service of the managed network executes on at least one computing device of the managed network;
for each of the plurality of network entities, issuing an alert in response to determining that the monitored respective performance is below a respective threshold performance level;
based on analysis of a first group of one or more issued alerts, determining a statistical likelihood that a different alert will be issued for the monitored respective performance of a particular network entity of the plurality for which no respective alert has yet been issued; and
issuing a score notification for the different alert in response to the determined statistical likelihood exceeding a score threshold, wherein the score notification includes the determined statistical likelihood and an identity of the particular network entity.

### Claim 18 (depends on 17)

The non-transitory computer-readable medium of claim 17, wherein the remote management platform is communicatively connected to the plurality of network entities via an intermediary network device in the managed network,
and wherein monitoring the respective performance of each network entity of the plurality of network entities comprises:
transmitting one or more messages from the computing system to the intermediary network device requesting performance metrics of one or more network entities of the plurality; and
receiving data transmitted from the intermediary network device indicative of the requested performance metrics

### Claim 19 (depends on 17)

The non-transitory computer-readable medium of claim 17, wherein determining the statistical likelihood based on analysis of the first group of one or more issued alerts comprises:
compiling a historical record of alerts issued for both (i) the monitored respective performance of the network entities of the plurality associated with the first group of the one or more issued alerts, and (ii) the monitored respective performance of the particular network entity;
computing a joint probability distribution of the historical record; and
for each respective issued alert of the one or more issued alerts, deriving from the computed joint probability distribution a respective conditional probability that the monitored respective performance of the particular network entity will be below a particular threshold performance level given an occurrence of issuance of the respective issued alert

### Claim 20 (depends on 17)

The non-transitory computer-readable medium of claim 17, wherein the computing system further comprises an interactive display device,
and wherein the method further comprises:
prior to determining the statistical likelihood, using an interactive cursor of the interactive display device to select the first group of the one or more issued alerts from among a plurality of issued alerts displayed on the interactive display device; and
prior to determining the statistical likelihood, identifying the different alert as a potential alert that is causally related to the first group of the one or more issued alerts.
