# US 2022/0027222 A1 · Approach to automated detection of dominant errors in cloud provisions

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

- Number: US 2022/0027222 A1
- Document ID: US20220027222A1
- Status: Published application
- Kind: A1
- Application number: 16/935,123
- Filed: 2020-07-21
- Published: 2022-01-27
- Earliest claimed: 2020-07-21
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Anupama Jagannathan; Karthick Rajamani; Han Na; Amos A. Omokpo
- Web page: https://patentgrep.com/patent/US20220027222A1

## CPC

- G06F 11/079: {Root cause analysis, i.e. error or fault diagnosis (in a hardware test environment G06F11/22; in a software test environment G06F11/36)}
- G06F 11/0709: {in a distributed system consisting of a plurality of standalone computer nodes, e.g. clusters, client-server systems}
- G06F 11/0712: {in a virtual computing platform, e.g. logically partitioned systems}
- G06F 11/0751: {Error or fault detection not based on redundancy (power supply failures G06F1/30; network fault management H04L41/06)}
- G06F 11/0778: {Dumping, i.e. gathering error/state information after a fault for later diagnosis}
- G06F 11/0793: {Remedial or corrective actions (recovery from an exception in an instruction pipeline G06F9/3861; by retry G06F11/1402; for recovering from a failure of a protocol instance or entity H04L69/40)}
- G06N 20/00: Machine learning
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A system is configured to determine a dominant error causing a provisioning step to become stuck during provisioning of a machine in a cloud environment. The system includes memory for storing instructions, and a processor configured to execute said instructions to determine an inverse error frequency (IEF) value for pre-intervention errors in a set of intervention provisioning data; determine a dominant error for a provision during said provisioning step in said set of intervention provisioning data based on a pre-intervention error that has a maximum IEF value; determine a duration frequency (DuF) value for the provision at said provisioning step for provisions in a set of non-intervention provisioning data; and determine said dominant error for each provision during said provisioning step in said set of non-intervention provisioning data based on an error that resulted in DuF value.

## Claims

### Claim 1

An automated method for provisioning a machine in a cloud environment, the method comprising:
receiving training provisioning data;
generating a set of non-intervention provisioning data and a set of intervention provisioning data by identifying provisions from the training provisioning data that required intervention to complete, wherein the set of non-intervention provisioning data comprises a first set of provisions that do not have any recorded intervention, and wherein the set of intervention provisioning data comprises a second set of provisions that have a recorded intervention;
identifying errors that occurred for each of the provisions during a provisioning step in the set of intervention provisioning data;
encoding the errors for each of the provisions that occurred during the provisioning step in the set of intervention provisioning data as one of a pre-intervention error and a post-intervention error, wherein the pre-intervention error occurred before an intervention, and wherein the post-intervention error occurred after the intervention;
determining a numeric statistic for each of the pre-intervention errors in the set of intervention provisioning data;
determining the numeric statistic for each provision in the set of non-intervention provisioning data;
determining a dominant error for a provision during the provisioning step in the set of intervention provisioning data, wherein the dominant error for the provision during the provisioning step in the set of intervention provisioning data is a pre-intervention error that has a maximum value for the numeric statistic;
determining the dominant error for the provision during the provisioning step in the set of non-intervention provisioning data, wherein the dominant error for the provision during the provisioning step in the set of non-intervention provisioning data is a provisioning error that resulted in a value of the numeric statistic;
determining based on the dominant error whether waiting a certain time period may enable the provisioning of the machine in the cloud environment to self-resolve without requiring the intervention when the provisioning step becomes stuck during the provisioning of the machine in the cloud environment; and
progressing with the provisioning of the machine in the cloud environment after the provisioning has self-resolved when the dominant error indicates that waiting the certain time period may enable the provisioning to self-resolve without requiring the intervention.

### Claim 2 (depends on 1)

The method of claim 1, wherein the numeric statistic is an Inverse Error Frequency (IEF) value for an error determined using the following equation: Log {total number of provisions in the provisioning step/(sum of a number of provisions in the set of non-intervention data containing the error and a number of provisions in the set of intervention provisioning data containing the error prior to the intervention)}.

### Claim 3 (depends on 1)

The method of claim 1, further comprising:
determining a duration frequency (DuF) value for every provision at the provisioning step for provisions in the set of non-intervention provisioning data; and
determining the dominant error for each provision during the provisioning step in the set of non-intervention provisioning data, wherein the dominant error for the provision during the provisioning step in the set of non-intervention provisioning data is the provisioning error that resulted in the DuF value, computed as a maximum of error durations for the provision.

### Claim 4 (depends on 3)

The method of claim 3, further comprising training a model based on the dominant error determined for each provision at each provisioning step of the provision.

### Claim 5 (depends on 4)

The method of claim 4, further comprising
receiving a set of event logs associated with a provisioning step of a test provision; and
determining from the set of event logs a predicted dominant error for the provisioning step of the test provision.

### Claim 6 (depends on 5)

The method of claim 5, further comprising determining from the set of event logs a step duration of the provisioning step, all errors that occur as part of the provisioning step, and an error duration for each of the errors.

### Claim 7 (depends on 5)

The method of claim 5, further comprising:
determining a response category for the test provision and the predicted dominant error.

### Claim 8

A system configured to provision a machine in a cloud environment, the system comprising memory for storing instructions, and a processor configured to execute the instructions to:
determine an inverse error frequency (IEF) value for pre-intervention errors in a set of intervention provisioning data;
determine a dominant error for a provision during a provisioning step in the set of intervention provisioning data, wherein the dominant error for the provision during the provisioning step in the set of intervention provisioning data is a pre-intervention error that has a maximum IEF value;
determine a duration frequency (DuF) value for each provision at the provisioning step for provisions in a set of non-intervention provisioning data;
determine the dominant error for each provision during the provisioning step in the set of non-intervention provisioning data, wherein the dominant error for the provision during the provisioning step in the set of non-intervention provisioning data is as an error that resulted in the DuF value, computed as a maximum of error durations for the provision;
determine based on the dominant error whether waiting a certain time period may enable the provisioning of the machine in the cloud environment to self-resolve without requiring the intervention when the provisioning step becomes stuck during the provisioning of the machine in the cloud environment; and
progress with the provisioning of the machine in the cloud environment after the provisioning has self-resolved when the dominant error indicates that waiting the certain time period may enable the provisioning to self-resolve without requiring the intervention.

### Claim 9 (depends on 8)

The system of claim 8, wherein the processor is further configured to execute the instructions to generate the set of intervention provisioning data and the set of non-intervention provisioning data from historic provisioning data.

### Claim 10 (depends on 8)

The system of claim 8, wherein the processor is further configured to execute the instructions to encode errors for each of the provisions that occurred during the provisioning step in the set of intervention provisioning data as one of a pre-intervention error and a post-intervention error.

### Claim 11 (depends on 8)

The system of claim 8, wherein the processor is further configured to execute the instructions to train a model based on the dominant error determined for each provision at each provisioning step of the provision.

### Claim 12 (depends on 11)

The system of claim 11, wherein the processor is further configured to execute the instructions to:
receive a set of event logs associated with a provisioning step of a test provision; and
determine from the set of event logs a predicted dominant error for the provisioning step of the test provision.

### Claim 13 (depends on 12)

The system of claim 12, wherein the processor is further configured to execute the instructions to determine from the set of event logs a step duration of the provisioning step, all errors that occur as part of the provisioning step, and an error duration for each of the errors.

### Claim 14 (depends on 12)

The system of claim 12, wherein the processor is further configured to execute the instructions to determine a response category for the test provision and the predicted dominant error.

### Claim 15

A computer program product for provisioning a machine in a cloud environment, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor of a system to cause the system to:
determine an inverse error frequency (IEF) value for pre-intervention errors in a set of intervention provisioning data;
determine a dominant error for a provision during a provisioning step in the set of intervention provisioning data, wherein the dominant error for the provision during the provisioning step in the set of intervention provisioning data is a pre-intervention error that has a maximum IEF value;
determine a duration frequency (DuF) value for each provision at the provisioning step for provisions in a set of non-intervention provisioning data;
determine the dominant error for each provision during the provisioning step in the set of non-intervention provisioning data, wherein the dominant error for the provision during the provisioning step in the set of non-intervention provisioning data is as an error that resulted in the DuF value, computed as a maximum of error durations for the provision;
determine based on the dominant error whether waiting a certain time period may enable the provisioning of the machine in the cloud environment to self-resolve without requiring the intervention when the provisioning step becomes stuck during the provisioning of the machine in the cloud environment; and
progress with the provisioning of the machine in the cloud environment after the provisioning has self-resolved when the dominant error indicates that waiting the certain time period may enable the provisioning to self-resolve without requiring the intervention.

### Claim 16 (depends on 15)

The computer program product of claim 15, the program instructions executable by the processor of the system to further cause the system to execute the instructions to generate the set of intervention provisioning data and the set of non-intervention provisioning data from historic provisioning data.

### Claim 17 (depends on 15)

The computer program product of claim 15, wherein the program instructions executable by the processor of the system to further cause the system to train a model based on the dominant error determined for each provision at each provisioning step of the provision.

### Claim 18 (depends on 17)

The computer program product of claim 17, wherein the program instructions executable by the processor of the system to further cause the system to:
receive a set of event logs associated with a provisioning step of a test provision; and
determine from the set of event logs a predicted dominant error for the provisioning step of the test provision.

### Claim 19 (depends on 18)

The computer program product of claim 18, the program instructions executable by the processor of the system to further cause the system to determine from the set of event logs a step duration of the provisioning step, all errors that occur as part of the provisioning step, and an error duration for each of the errors.

### Claim 20 (depends on 18)

The computer program product of claim 18, the program instructions executable by the processor of the system to further cause the system to determine a response category for the test provision and the predicted dominant error.
