Pure Storage has been granted a patent for a system that utilizes machine learning to identify and compare characteristics of storage media. The system can determine the type of change associated with a second storage media based on the comparison. This technology can be used in a telemetry process to qualify types of storage media. GlobalData’s report on Pure Storage gives a 360-degree view of the company including its patenting strategy. Buy the report here.

According to GlobalData’s company profile on Pure Storage, M2M communication interfaces was a key innovation area identified from patents. Pure Storage's grant share as of September 2023 was 69%. Grant share is based on the ratio of number of grants to total number of patents.

Machine learning model for qualifying types of storage media

Source: United States Patent and Trademark Office (USPTO). Credit: Pure Storage Inc

A recently granted patent (Publication Number: US11775491B2) describes a system and method for evaluating changes in storage media using machine learning. The system includes a memory and a processing device that is configured to provide data associated with a first storage media as input to a machine learning model. The model identifies characteristics of the first storage media and compares them with characteristics of a second storage media. Based on this comparison, the machine learning model determines the type of change associated with the second storage media.

The data provided to the machine learning model can include telemetry data associated with the first storage media. The processing device is further configured to determine whether to accept or reject the second storage media based on the type of change identified by the machine learning model. Additionally, the processing device can provide firmware for the second storage media to the storage system, even if the second storage media differs from the first storage media.

The characteristics used for comparison can include error rates, data retention times, modes of failure, read disturb counts, number of program/erase cycles, temperature, powered-on/powered-off times, and latencies. The processing device can also determine whether support for the second storage media exists within the firmware of the storage system based on performance parameters received from the machine learning model.

In summary, this patent describes a system and method that utilize machine learning to evaluate changes in storage media. By comparing characteristics of different storage media, the system can determine the type of change and make decisions regarding acceptance or rejection of the new storage media. This technology has the potential to improve the efficiency and reliability of storage systems by leveraging machine learning algorithms.

To know more about GlobalData’s detailed insights on Pure Storage, buy the report here.

Premium Insights


The gold standard of business intelligence.

Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.


GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.

GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.