System and method of determining a backup schedule based on data analysis and machine learning

Patent metadata

Field	Value
Publication number	US-2020364113-A1
Application number	US-202016876499-A
Country	US
Kind code	A1
Filing date	May 18, 2020
Priority date	May 16, 2019
Publication date	Nov 19, 2020
Grant date	—

Abstract

Disclosed herein are systems and method for determining a backup schedule on a computer system. In one exemplary aspect, a method may comprise collecting user behavior data on the computer system and analyzing the user behavior data to determine an optimal time of a backup session to create backup copies of modified data stored on a volume of the computer system. The method may comprise determining an optimal duration of the backup session based on the analyzed user behavior and prioritizing portions of the modified data based on priority rules. The method may comprise determining a prioritized portion of the modified data that can be saved during the backup session based on the duration, computer system hardware and network bandwidth at the optimal time of backup, and performing the backup session comprising the prioritized portion.

First claim

What is claimed is:

1 . A method of determining a backup schedule on a computer system, comprising:
collecting user behavior data on the computer system; analyzing the user behavior data to determine an optimal time of a backup session to create backup copies of modified data stored on a volume of the computer system; determining an optimal duration of the backup session based on the analyzed user behavior; prioritizing portions of the modified data based on priority rules; determining a prioritized portion of the modified data that can be saved during the backup session based on the duration, computer system hardware and network bandwidth at the optimal time of backup; and performing the backup session comprising the prioritized portion.

2 . The method of claim 1 , wherein the user behavior data comprises: when the user frequently modifies data, when the user saves the data to the computer and usage of applications.

3 . The method of claim 1 , further comprising:
analyzing the user behavior data using neural networks in order to determine the optimal time of the backup session.

4 . The method of claim 1 , wherein the priority rules assess at least one of: (1) whether a user manually selected a respective portion, (2) whether the respective portion is accessed more than a threshold amount of times, (3) whether the respective portion is labelled a critical file by the computer system, (4) whether the respective portion is accessed for a longer than a threshold duration, (5) whether the respective portion was previously backed up within a threshold period of time.

5 . The method of claim 4 , wherein each priority rule is associated with a respective weight, and wherein prioritizing portions of the modified data further comprises:
identifying a plurality of portions in the modified data; determining a subset of the plurality of portions that satisfy any of the priority rules; and ranking, based on the respective weight of a respective priority rule, the subset of the plurality of portions.

6 . The method of claim 1 , wherein the analyzing of the user behavior is performed for activity occurring within a predetermined period of time, further comprising:
determining that the user is performing a particular activity based on an analysis of the user behavior; determining an optimal start, duration, and length of the backup session according to the particular activity.

7 . The method of claim 6 , wherein a respective portion with a higher rank is backed up prior to a respective portion with a lower rank.

8 . A system of determining a backup schedule on a computer system, the system comprising:
A hardware processor configured to: collect user behavior data on the computer system; analyze the user behavior data to determine an optimal time of a backup session to create backup copies of modified data stored on a volume of the computer system; determine an optimal duration of the backup session based on the analyzed user behavior; prioritize portions of the modified data based on priority rules; determine a prioritized portion of the modified data that can be saved during the backup session based on the duration, computer system hardware and network bandwidth at the optimal time of backup; and perform the backup session comprising the prioritized portion.

9 . The system of claim 8 , wherein the user behavior data comprises: when the user frequently modifies data, when the user saves the data to the computer and usage of applications.

10 . The system of claim 8 , wherein the hardware processor is further configured to analyze the user behavior data using neural networks in order to determine the optimal time of the backup session.

11 . The system of claim 8 , wherein the priority rules assess at least one of: (1) whether a user manually selected a respective portion, (2) whether the respective portion is accessed more than a threshold amount of times, (3) whether the respective portion is labelled a critical file by the computer system, (4) whether the respective portion is accessed for a longer than a threshold duration, (5) whether the respective portion was previously backed up within a threshold period of time.

12 . The system of claim 11 , wherein each priority rule is associated with a respective weight, and wherein the hardware processor is configured to prioritize portions of the modified data by:
identifying a plurality of portions in the modified data; determining a subset of the plurality of portions that satisfy any of the priority rules; and ranking, based on the respective weight of a respective priority rule, the subset of the plurality of portions.

13 . The system of claim 8 , wherein the hardware processor is configured to analyze the user behavior over a predetermined period of time, and wherein the hardware processor is further configured to:
determine that the user is performing a particular activity based on an analysis of the user behavior; determine an optimal start, duration, and length of the backup session according to the particular activity.

14 . The system of claim 12 , wherein a respective portion with a higher rank is backed up prior to a respective portion with a lower rank.

15 . A non-transitory computer readable medium storing thereon computer executable instructions for determining a backup schedule on a computer system, comprising instructions for:
collecting user behavior data on the computer system; analyzing the user behavior data to determine an optimal time of a backup session to create backup copies of modified data stored on a volume of the computer system; determining an optimal duration of the backup session based on the analyzed user behavior; prioritizing portions of the modified data based on priority rules; determining a prioritized portion of the modified data that can be saved during the backup session based on the duration, computer system hardware and network bandwidth at the optimal time of backup; and performing the backup session comprising the prioritized portion.

16 . The non-transitory computer readable medium of claim 15 , wherein the user behavior data comprises: when the user frequently modifies data, when the user saves the data to the computer and usage of applications.

17 . The non-transitory computer readable medium of claim 15 , further comprising instructions for:
analyzing the user behavior data using neural networks in order to determine the optimal time of the backup session.

18 . The non-transitory computer readable medium of claim 15 , wherein the priority rules assess at least one of: (1) whether a user manually selected a respective portion, (2) whether the respective portion is accessed more than a threshold amount of times, (3) whether the respective portion is labelled a critical file by the computer system, (4) whether the respective portion is accessed for a longer than a threshold duration, (5) whether the respective portion was previously backed up within a threshold period of time.

19 . The non-transitory computer readable medium of claim 18 , wherein each priority rule is associated with a respective weight, and wherein the instructions for prioritizing portions of the modified data further comprises instructions for:
identifying a plurality of portions in the modified data; determining a subset of the plurality of portions that satisfy any of the priority rules; and ranking, based on the respective weight of a respective priority rule, the subset of the plurality of portions.

Assignees

• Acronis Int Gmbh

Inventors

• Tormasov Alexander
• Beloussov Serguei
• Protasov Stanislav

Classifications

• G06F11/1466

  to make the backup process non-disruptive · CPC title

• G06F11/1464

  for networked environments · CPC title

• G06F11/1461 Primary

  Backup scheduling policy · CPC title

• G06F11/1451

  by selection of backup contents · CPC title

• G06F11/1469

  Backup restoration techniques · CPC title