# US 2023/0058813 A1 · Adjustable data protection scheme using artificial intelligence

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

- Number: US 2023/0058813 A1
- Document ID: US20230058813A1
- Status: Published application
- Kind: A1
- Application number: 17/406,997
- Filed: 2021-08-19
- Published: 2023-02-23
- Earliest claimed: 2021-08-19
- Assignees: Micron Technology, Inc.
- Applicants: Micron Technology, Inc.
- Inventors: Ezra E. Hartz; Nicolas Soberanes; Joseph A. De La Cerda; Benjamin Rivera; Bruce J. Ford
- Web page: https://patentgrep.com/patent/US20230058813A1

## CPC

- G06F 3/0619: {in relation to data integrity, e.g. data losses, bit errors}
- G06F 11/10: Adding special bits or symbols to the coded information, e.g. parity check, casting out 9's or 11's
- G06F 3/0629: {Configuration or reconfiguration of storage systems}
- G06F 3/0679: {Non-volatile semiconductor memory device, e.g. flash memory, one time programmable memory [OTP]}
- G06F 11/1048: {using arrangements adapted for a specific error detection or correction feature}
- G06F 21/6218: {to a system of files or objects, e.g. local or distributed file system or database}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Apparatuses and methods can be related to implementing adjustable data protection schemes using artificial intelligence. Implementing adjustable data protection schemes can include receiving failure data for the plurality of memory devices and receiving an indication of a failure of a stripe of the plurality of memory devices based on the failure data. Based on failure data, and the indication of the failure of the stripe of the plurality of memory devices, a data protection scheme adjustment can be generated for the memory device. The data protection scheme adjustment can be received from the AI accelerator and can be implemented by a plurality of memory devices.

## Claims

### Claim 1

An apparatus comprising:
a plurality of memory devices implementing a data protection scheme;
an artificial intelligence (AI) accelerator coupled to the plurality of memory devices;
wherein the AI accelerator is configured to:
receive failure data for the plurality of memory devices;
receive an indication of a failure of a stripe of the plurality of memory devices based on the failure data; and
based on failure data, and the indication of the failure of the stripe of the plurality of memory devices, generate a data protection scheme adjustment for the plurality of memory devices;
wherein the plurality of memory devices are configured to:
receive the data protection scheme adjustment from the AI accelerator; and
implement the data protection scheme adjustment.

### Claim 2 (depends on 1)

The apparatus of claim 1, wherein the AI accelerator is further configured to receive the indication of the failure of a block of the plurality of memory devices.

### Claim 3 (depends on 1)

The apparatus of claim 1, wherein the AI accelerator is further configured to receive the indication of the failure of a word line of the plurality of memory devices.

### Claim 4 (depends on 1)

The apparatus of claim 1, wherein the plurality of memory devices configured to implement the data protection scheme adjustment are further configured to adjust a ratio of parity elements to storage elements.

### Claim 5 (depends on 1)

The apparatus of claim 1, wherein the plurality of memory devices configured to implement the data protection scheme adjustment are further configured to refrain from utilizing blocks of the plurality of memory devices.

### Claim 6 (depends on 1)

The apparatus of claim 1, wherein the plurality of memory devices configured to implement the data protection scheme adjustment are further configured to adjust a quantity of bits that each of a plurality of memory cells can store.

### Claim 7 (depends on 6)

The apparatus of claim 6, wherein the plurality of memory devices are configured to adjust the quantity of bit that each of the plurality of memory cells can store from a single-level cell (SLC) to a multi-level cell (MLC).

### Claim 8 (depends on 6)

The apparatus of claim 6, wherein the plurality of memory devices are configured to adjust the level of the plurality of memory cells from a multi-level cell (MLC) to a single-level cell (SLC).

### Claim 9 (depends on 1)

The apparatus of claim 1, wherein the AI accelerator is further configured to generate the data protection scheme adjustment utilizing an artificial neural network (ANN).

### Claim 10 (depends on 1)

The apparatus of claim 1, wherein the AI accelerator configured to generate the data protection scheme adjustment is further configured to select the data protection scheme adjustment by comparing the failure data to a plurality of signatures comprising failure data using a table.

### Claim 11 (depends on 1)

The apparatus of claim 1, wherein the AI accelerator is further configured to:
generate additional data protection scheme adjustments for a plurality of blocks of the plurality of memory devices based on cycle counts of the plurality of blocks of the plurality of memory devices and based on raw bit-error rates of the plurality of blocks of the plurality of memory devices,
wherein the plurality of blocks have erase latencies and program latencies that are similar to an erase latency corresponding to the failure data and a program latency corresponding to the failure data.

### Claim 12 (depends on 1)

The apparatus of claim 1, wherein the AI accelerator is further configured to:
provide data corresponding to the failure data to a cloud system to be added to a pool of failures; and
receive additional data protection scheme adjustments corresponding to the pool of failures from the cloud system;
generate data protection scheme adjustments for failures that have not been experienced by the plurality of memory devices by selecting the data protection scheme adjustments from the additional data protection scheme adjustments.

### Claim 13 (depends on 1)

The apparatus of claim 1, wherein the failure data includes latency data, read latency data, erase latency data, and raw bit error rates (RBERs).

### Claim 14

A method, comprising:
receiving temperature data for a memory device, coupled to an artificial intelligence (AI) accelerator, implementing a data protection scheme during operation of the memory device;
receiving an indication of a failure of a stripe of the memory device;
based on the temperature data and the indication of the failure of the stripe of the memory device, generating, at the AI accelerator, a data protection scheme adjustment for the memory device; and
implementing the data protection scheme adjustment at the memory device.

### Claim 15 (depends on 14)

The method of claim 14, further comprising determining, at the AI accelerator, whether the temperature data indicates that a temperature, corresponding to the temperature data, is greater than a threshold temperature of the memory device.

### Claim 16 (depends on 15)

The method of claim 15, further comprising:
receiving a plurality of raw bit-error rates (RBERs) experienced by the memory device at a time prior to when the temperature data is generated; and
generating, at the AI accelerator, the threshold temperature based on the plurality of RBERs and the prior temperature data.

### Claim 17 (depends on 14)

The method of claim 14, further comprising:
receiving a different indication of a lack of failures of the memory device; and
based on the temperature data and the different indication of the lack of failures of the memory device, generating, at the artificial intelligence (AI) accelerator, a different data protection scheme adjustment for the memory device.

### Claim 18 (depends on 16)

The method of claim 16, wherein the data protection scheme adjustment tightens data protection scheme coverage in the memory device and the different data protection scheme adjustment loosens RAIN coverage in the memory device.

### Claim 19

An apparatus, comprising:
a memory device implementing a data protection scheme;
an artificial intelligence (AI) accelerator coupled to the memory device;
wherein the AI accelerator is configured to:
receive a raw bit-error rate (RBER) for the memory device and during operation of the memory device;
receive data corresponding to a passing or failing condition of the memory device; and
based on the RBER and the data, generate a data protection scheme adjustment for the memory device to extend a life of the memory device;
wherein the memory device is configured to implement the data protection scheme adjustment.

### Claim 20 (depends on 19)

The apparatus of claim 19, wherein the AI accelerator is configured to receive the data corresponding to a passing or failing condition of a block or a word line of the memory device.

### Claim 21 (depends on 19)

The apparatus of claim 19, wherein the AI accelerator is configured to generate the data protection scheme adjustment for a block or word line of the memory device.

### Claim 22 (depends on 19)

The apparatus of claim 19, wherein the AI accelerator is further configured to:
generate an average margin to the failing condition utilizing the data and the RBER; and
generate the data protection scheme adjustment based on the average margin and the failing condition;

### Claim 23

A system, comprising:
an AI accelerator implement in a cloud system;
a plurality of memory devices implementing a data protection scheme;
wherein the AI accelerator is configured to:
receive fabrication data and testing data;
receive state data describing a state of the plurality of memory devices;
receive fuse identification (ID) corresponding to at least one of the plurality of memory devices;
responsive to receipt of the fabrication data, the testing data, and the state data, generating a data protection scheme adjustment for memory cells corresponding to the fuse ID; and
wherein the plurality of memory devices are configured to implement the data protection scheme adjustment for the memory cells corresponding to the fuse ID.

### Claim 24 (depends on 23)

The system of claim 23, wherein the AI accelerator is further configured to generate a summary report for failures of a stripe of the plurality of memory devices described in the state data that are not adjusted by the data protection scheme adjustment.

### Claim 25 (depends on 24)

The system of claim 24, wherein the AI accelerator is further configured to provide the summary report including the state data for including in a pool of unsupported failures.

### Claim 26 (depends on 25)

The system of claim 25, wherein the pool of unsupported failures is utilized for fabricating and testing NAND memory devices.

### Claim 27 (depends on 23)

The system of claim 23, wherein the data protection scheme is a redundant array of independent NAND (RAIN).
