US 10,705,767 B2Granted

Optimizing user satisfaction when training a cognitive hierarchical storage-management system

AssigneeInternational Business Machines Corporation

InventorsThorsten Muehge, Stefan M. Ravizza, Erik Rueger, Tim U. Scheideler

Life of this patent

Estimating the term…

Loading patent…

Abstract

A cognitive hierarchical storage-management system receives feedback describing users' satisfaction with the way that one or more prior data-access requests were serviced. The system uses this feedback to associate each previously requested data element's metadata and storage tier with a level of user satisfaction, and to optimize user satisfaction when the system is trained. As feedback continues to be received, the system uses machine-learning methods to identify how closely specific metadata patterns correlate with certain levels of user satisfaction and with certain storage tiers. The system then uses the resulting associations when determining whether to migrate data associated with a particular metadata pattern to a different tier. Data elements may be migrated between different tiers when two metadata sets share metadata values. A user's degree of satisfaction may be encoded as a metadata element that may be used to train a neural network of a machine-learning module. If detecting that two metadata sets share metadata values, the system determines whether to migrate data elements to different tiers.

Claims20

Dependent claims

A cognitive hierarchical storage-management system,

comprising a processor, a memory coupled to the processor, and a computer-readable hardware storage device coupled to the processor, the storage device containing program code configured to be executed by the processor via the memory to implement operations for optimizing user satisfaction when training the cognitive hierarchical storage-management system, the operations comprising:
receiving, by the processor, feedback from a first user that describes the first user's degree of satisfaction with the hierarchical storage-management system's response to a first data-access request,
where the first data-access request comprises the first user's request to the hierarchical storage-management system for access to a first data element of a set of data elements, and
where the response comprises providing, to the first user, access to a copy of the first data element stored on a first storage device of a set of storage devices, the first storage device being associated with a first tier of a set of tiers of a tiered storage environment managed by the hierarchical storage-management system;
identifying a first metadata set associated with the first data element;
associating the first metadata set with the first user's degree of satisfaction,
where the associating comprises:
inferring meaning from a pattern of metadata values of the first metadata set, where the meaning consists of a correlation between a degree of user satisfaction and at least one metadata value of the first metadata set,
updating a set of inferential insights stored in an insight database as a function of the correlation,
where the inferential insights consist of learning algorithms, which define steps by which the processor self-learns how to more effectively improve storage performance, and a set of storage-management models, and
where the processor uses the inferential insights to intelligently determine when to migrate data elements, of the set of data elements, between distinct tiers of the set of tiers;
and
migrating the first data element to a second storage device,
where the migrating is performed as a function of the associating,
where the second storage device is associated with a second tier of the set of tiers, and
where the first tier and the second tier are distinct.

13 more elements

A method for optimizing user satisfaction when training a cognitive hierarchical storage-management system, the method comprising:

receiving, by the processor, feedback from a first user that describes the first user's degree of satisfaction with the hierarchical storage-management system's response to a first data-access request,
where the first data-access request comprises the first user's request to the hierarchical storage-management system for access to a first data element of a set of data elements, and
where the response comprises providing, to the first user, access to a copy of the first data element stored on a first storage device of a set of storage devices, the first storage device being associated with a first tier of a set of tiers of a tiered storage environment managed by the hierarchical storage-management system;
identifying a first metadata set associated with the first data element;
associating the first metadata set with the first user's degree of satisfaction,
where the associating comprises:
inferring meaning from a pattern of metadata values of the first metadata set, where the meaning consists of a correlation between a degree of user satisfaction and at least one metadata value of the first metadata set,
updating a set of inferential insights stored in an insight database as a function of the correlation,
where the inferential insights consist of learning algorithms, which define steps by which the processor self-learns how to more effectively improve storage performance, and a set of storage-management models, and
where the processor uses the inferential insights to intelligently determine when to migrate data elements, of the set of data elements, between distinct tiers of the set of tiers;
and
migrating the first data element to a second storage device,
where the migrating is performed as a function of the associating,
where the second storage device is associated with a second tier of the set of tiers, and
where the first tier and the second tier are distinct.

12 more elements

A computer program product, comprising a computer-readable hardware storage device storing computer-readable program code, the program code configured to be executed by a processor of a cognitive hierarchical storage-management system comprising the processor and a memory coupled to the processor to implement operations for optimizing user satisfaction when training the cognitive hierarchical storage-management system, the operations comprising:

receiving, by the processor, feedback from a first user that describes the first user's degree of satisfaction with the hierarchical storage-management system's response to a first data-access request,
where the first data-access request comprises the first user's request to the hierarchical storage-management system for access to a first data element of a set of data elements, and
where the response comprises providing, to the first user, access to a copy of the first data element stored on a first storage device of a set of storage devices, the first storage device being associated with a first tier of a set of tiers of a tiered storage environment managed by the hierarchical storage-management system;
a tiered storage environment managed by the hierarchical storage-management system;
identifying a first metadata set associated with the first data element;
associating the first metadata set with the first user's degree of satisfaction,
where the associating comprises:
inferring meaning from a pattern of metadata values of the first metadata set, where the meaning consists of a correlation between a degree of user satisfaction and at least one metadata value of the first metadata set,
updating a set of inferential insights stored in an insight database as a function of the correlation,
where the inferential insights consist of learning algorithms, which define steps by which the processor self-learns how to more effectively improve storage performance, and a set of storage-management models, and
where the processor uses the inferential insights to intelligently determine when to migrate data elements, of the set of data elements, between distinct tiers of the set of tiers;
and
migrating the first data element to a second storage device,
where the migrating is performed as a function of the associating,
where the second storage device is associated with a second tier of the set of tiers, and
where the first tier and the second tier are distinct.

13 more elements

Dependencies are inferred from the claim text.

Facts

Application: 15/654,840Filed 20 Jul 2017
Published: US 2019/0026048 A124 Jan 2019
Granted: 7 Jul 2020
Term ends: Not estimatedThe source records don’t support an estimate.

Classification11 codes

G06F 3/0685
Plurality of storage devices: hybrid storage combining heterogeneous device types, e.g. hierarchical storage, hybrid arrays
G06N 3/08
Neural networks: learning methods
G06F 3/0605
Improving or facilitating administration, e.g. storage management: by facilitating the interaction with a user or administrator
G06F 3/0649
Migration mechanisms: lifecycle management