Anticipatory sample analysis for application management

Patent metadata

Field	Value
Publication number	US-10169330-B2
Application number	US-201615370810-A
Country	US
Kind code	B2
Filing date	Dec 6, 2016
Priority date	Oct 31, 2016
Publication date	Jan 1, 2019
Grant date	Jan 1, 2019

Abstract

A device may receive a set of first samples of textual content. A device may identify a set of clusters of first samples of the set of first samples. A device may identify a pattern of occurrence based on the set of clusters. The pattern of occurrence to identify two or more clusters, of the set of clusters, based on an order in which first samples associated with the two or more clusters were generated or received. A device may receive one or more second samples of textual content. A device may determine that the one or more second samples are semantically similar to one or more corresponding clusters associated with the pattern of occurrence. A device may identify a predicted sample based on the pattern of occurrence and the one or more corresponding clusters. A device may perform an action based on identifying the predicted sample.

First claim

What is claimed is:

1. A device, comprising:
one or more processors to:
receive a plurality of first samples of textual content;
identify a plurality of clusters of the plurality of the first samples,
a cluster, of the plurality of clusters, to be identified based on semantic similarity of samples included in the cluster;

identify a pattern of occurrence based on the plurality of clusters,
the pattern of occurrence to identify two or more clusters, of the plurality of clusters, based on an order in which samples associated with the two or more clusters were generated or received;

receive one or more second samples of textual content;
determine that the one or more second samples are semantically similar to one or more corresponding clusters associated with the pattern of occurrence;
identify a predicted sample based on the pattern of occurrence and the one or more corresponding clusters; and
perform an action based on identifying the predicted sample,
the action including reconfiguring another device to mitigate or prevent an event associated with the predicted sample,
reconfiguration of the other device including a modification of at least one of:
 a performance of the other device,
 a utilization of processor resources, or
 downtime of the other device.

2. The device of claim 1 , where the one or more processors are further to:
identify a first set of clusters and a second set of clusters of the plurality of clusters,
the first set of clusters and the second set of clusters including at least one shared cluster, of the plurality of clusters, and at least one non-shared cluster of the plurality of clusters; and

determine a ratio of shared clusters to non-shared clusters of the first set of clusters and the second set of clusters; and
where the one or more processors, when identifying the pattern of occurrence, are to:
identify the pattern of occurrence based on the ratio of shared clusters to non-shared clusters satisfying a threshold.

3. The device of claim 1 , where the one or more processors are further to:
identify a first set of clusters and a second set of clusters of the plurality of clusters,
the first set of clusters and the second set of clusters including at least one shared cluster, of the plurality of clusters, and at least one non-shared cluster of the plurality of clusters; and

determine a rank correlation coefficient of the first set of clusters and the second set of clusters; and
where the one or more processors, when identifying the pattern of occurrence, are to:
identify the pattern of occurrence based on the rank correlation coefficient satisfying a threshold.

4. The device of claim 3 , where the one or more processors are further to:
identify a sequence of clusters, of the first set of clusters or the second set of clusters, based on each cluster of the sequence of clusters being associated with a particular identifier; and
replace the sequence of clusters with a single cluster associated with the particular identifier.

5. The device of claim 1 , where the one or more processors are further to:
identify a first set of clusters and a second set of clusters of the plurality of clusters,
the first set of clusters and the second set of clusters including at least one shared cluster, of the plurality of clusters, and at least one non-shared cluster of the plurality of clusters,
the first set of clusters being associated with a first time window based on first times at which samples associated with the first set of clusters were received, and
the second set of clusters being associated with a second time window based on second times at which samples associated with the first set of clusters were received; and

determine a difference between the first time window and the second time window; and
where the one or more processors, when identifying the pattern of occurrence, are to:
identify the pattern of occurrence based on the difference satisfying a threshold.

6. The device of claim 1 , where the one or more processors are further to:
identify a remaining cluster, of the two or more clusters associated with the pattern of occurrence, other than the one or more corresponding clusters; and
where the one or more processors, when identifying the predicted sample, are to:
select, from a group of the first samples associated with the remaining cluster, the predicted sample.

7. The device of claim 1 , where the pattern of occurrence is a particular pattern of occurrence of a plurality of patterns of occurrence; and
where the one or more processors, when identifying the particular pattern of occurrence, are to:
identify the particular pattern of occurrence based on the one or more corresponding clusters being a proper prefix of the two or more clusters of the particular pattern of occurrence.

8. A method, comprising:
receiving, by a device, a plurality of first samples of textual content;
identifying, by the device, a plurality of clusters of the plurality of the first samples,
each cluster, of the plurality of clusters, to be identified based on semantic similarity of samples included in each cluster;

identifying, by the device, a pattern of occurrence based on the plurality of clusters,
the pattern of occurrence to identify two or more clusters, of the plurality of clusters, based on an order in which samples associated with the two or more clusters were generated or received;

receiving, by the device, one or more second samples of textual content;
determining, by the device, that the one or more second samples are semantically similar to one or more corresponding clusters associated with the pattern of occurrence;
identifying, by the device and based on the pattern of occurrence and the one or more corresponding clusters, a predicted sample; and
performing, by the device, an action based on identifying the predicted sample,
the action including reconfiguring another device to mitigate or prevent an event associated with the predicted sample,
reconfiguration of the other device including a modification of at least one of:
a performance of the other device,
a utilization of processor resources, or
downtime of the other device.

9. The method of claim 8 , where performing the action further comprises:
identifying a worker associated with one or more samples of the two or more clusters; and
assigning the worker to the predicted sample.

10. The method of claim 8 , further comprising:
receiving information identifying a plurality of priority levels associated with the plurality of the first samples;
determining a predicted priority level associated with the predicted sample based on the information identifying the plurality of priority levels; and
providing information identifying the predicted priority level.

11. The method of claim 10 , where determining the predicted priority level comprises:
determining the predicted priority level based on particular priority levels of the plurality of priority levels,
the particular priority levels being associated with samples, of the plurality of the first samples, corresponding to the two or more clusters.

12. The method of claim 8 , where the predicted sample is a particular predicted sample of a plurality of predicted samples; and
where the method further comprises:
identifying respective probabilities of occurrence associated with the plurality of predicted samples based on the pattern of occurrence; and

where identifying the particular predicted sample comprises:
selecting the particular predicted sample based on a particular probability of occurrence, of the respective probabilities of occurrence, associat

Assignees

• Accenture Global Solutions Ltd

Inventors

• Misra Janardan
• Rawat Divya
• Savagaonkar Milind
• Podder Sanjay

Classifications

• G06F40/30 Primary

  Semantic analysis · CPC title

• G06F40/253

  Grammatical analysis; Style critique · CPC title

• G06F40/211

  Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars · CPC title

• G06N20/00 Primary

  Machine learning · CPC title

• G06F11/0766

  Error or fault reporting or storing · CPC title