# US 2024/0202279 A1 · Training and implementing a steady state log analyzer

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

- Number: US 2024/0202279 A1
- Document ID: US20240202279A1
- Status: Published application
- Kind: A1
- Application number: 18/085,300
- Filed: 2022-12-20
- Published: 2024-06-20
- Earliest claimed: 2022-12-20
- Assignees: Microsoft Technology Licensing, LLC
- Applicants: Microsoft Technology Licensing, LLC
- Inventors: Mohit VERMA; Ananth GEETHANATH; Rakesh NAMINENI; Ali ALAM; Kamaljit Singh BATH; Ramanathan MUTHIAH; Suneel SURESH
- Web page: https://patentgrep.com/patent/US20240202279A1

## CPC

- G06F 11/3452: {Performance evaluation by statistical analysis}
- G06F 17/40: Data acquisition and logging (for input to computer G06F3/00)
- G06F 11/3006: {where the computing system is distributed, e.g. networked systems, clusters, multiprocessor systems (multiprogramming arrangements G06F9/46; allocation of resources G06F9/50)}
- G06F 11/3447: {Performance evaluation by modeling}
- G06F 17/16: Matrix or vector computation {, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization (matrix transposition G06F7/78)}
- G06F 18/2137: based on criteria of topology preservation, e.g. multidimensional scaling or self-organising maps
- G06F 18/2433: Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
- G06N 3/045: Combinations of networks
- G06F 11/0751: {Error or fault detection not based on redundancy (power supply failures G06F1/30; network fault management H04L41/06)}
- 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 11/3466: {Performance evaluation by tracing or monitoring}
- G06F 11/3476: {Data logging (G06F11/14, G06F11/2205 take precedence)}
- G06F 2201/865: Monitoring of software
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

The present disclosure relates to methods, systems, and computer readable media for analyzing log files for a wide variety of services (e.g., cloud computing services or microservices) to determine whether the services are operating as designed over some period of time associated with the log file(s). The present disclosure includes features and functionality for training or otherwise generating a model being configured to predict whether portions of an input log file include data reflective of normal operations of a corresponding service used to generate the input log file. The present disclosure provides a domain-agnostic approach to training an outlier detection model to analyze log files for a wide variety of services.

## Claims

### Claim 1

A method, comprising:
identifying a steady state log file for a service on a cloud computing system associated with normal operation of the service over a period of time;
applying an encoding model to the steady state log file to generate a multi-dimensional representation of the steady state log file, the multi-dimensional representation including a plurality of points representative of lines of the steady state log file within a multi-dimensional space;
generating an outlier detection model trained to determine a plurality of outlier scores for a plurality of lines of a given log file based on the multi-dimensional representation of the steady state log file being associated with normal operation of the service, wherein an outlier score indicates a predicted probability that a given line from the plurality of lines of the given log file is an outlier from normal operation of the service; and
applying the outlier detection model to an input log file to generate a plurality of outputs indicating lines of the input log file that are predicted to be outliers from normal operation of the service.

### Claim 2 (depends on 1)

The method of claim 1, wherein applying the encoding model to the steady state log file further includes:
encoding the steady state log file to be a matrix representation of the steady state log file, the matrix representation having a same dimensionality as the steady state log file; and
applying an autoencoder to the matrix representation of the steady state log file to reduce a dimensionality of the matrix representation to a target dimensionality of the multi-dimensional representation.

### Claim 3 (depends on 2)

The method of claim 2, wherein the autoencoder reduces dimensionality of the matrix representation using a principal component analysis (PCA) engine.

### Claim 4 (depends on 1)

The method of claim 1, wherein the multi-dimensional representation includes fewer dimensions than a number of columns of the steady state log file.

### Claim 5 (depends on 1)

The method of claim 1, wherein the multi-dimensional representation of the steady state log file is a two-dimensional representation of the steady state log file.

### Claim 6 (depends on 1)

The method of claim 1, wherein the outlier detection model includes a defined region of the multi-dimensional space associated with normal operation of the service based on locations of the plurality of points from the multi-dimensional representation of the steady state log file within the multi-dimensional space.

### Claim 7 (depends on 1)

The method of claim 1, wherein the outlier detection model is a machine learning model trained to determine whether the given file is associated with normal behavior of the service on the cloud computing system based on the multi-dimensional representation of the steady state log file.

### Claim 8 (depends on 1)

The method of claim 1, wherein the input log file is generated by the service over a second period of time with an unknown level of service.

### Claim 9 (depends on 1)

The method of claim 1, wherein the input log file is generated by a same type of service as the service associated with the steady state log file.

### Claim 10 (depends on 1)

The method of claim 1, wherein the plurality of outputs includes a subset of lines from the input log file that are predicted to be outliers.

### Claim 11 (depends on 1)

The method of claim 1, wherein the plurality of outputs includes a set of rankings for a predetermined number of lines with highest scores associated with a high likelihood of associated lines from the input log file being outliers from normal operation of the service.

### Claim 12 (depends on 1)

The method of claim 1, further comprising:
identifying a second steady state log file for a second service on the cloud computing system associated with normal operation of the second service;
applying the encoding model to the second steady state log file to generate a second multi-dimensional representation of the second log file, the second multi-dimensional representation including a second plurality of points representative of lines of the second steady state log file within a second multi-dimensional space; and
generating a second outlier detection model trained to determine outlier scores for a second plurality of lines of a second log file based on the second multi-dimensional representation of the second steady state log file being associated with normal operation of the second service.

### Claim 13 (depends on 12)

The method of claim 12, further comprising applying the second outlier detection model to a second input log file to determine a second plurality of outputs associated with performance by the second service.

### Claim 14

A system, comprising:
at least one processor;
memory in electronic communication with the at least one processor; and
instructions stored in the memory, the instructions being executable by a computing device to:
identify a steady state log file for a service on a cloud computing system associated with normal operation of the service over a period of time;
apply an encoding model to the steady state log file to generate a multi-dimensional representation of the steady state log file, the multi-dimensional representation including a plurality of points representative of lines of the steady state log file within a multi-dimensional space;
generate an outlier detection model trained to determine a plurality of outlier scores for a plurality of lines of a given log file based on the multi-dimensional representation of the steady state log file being associated with normal operation of the service, wherein an outlier score indicates a predicted probability that a given line from the plurality of lines of the given log file is an outlier from normal operation of the service; and
apply the outlier detection model to an input log file to generate a plurality of outputs indicating lines of the input log file that are predicted to be outliers from normal operation of the service.

### Claim 15 (depends on 14)

The system of claim 14, wherein applying the encoding model to the steady state log file further includes:
encoding the steady state log file to be a matrix representation of the steady state log file, the matrix representation having a same dimensionality as the steady state log file; and
applying an autoencoder to the matrix representation of the steady state log file to reduce a dimensionality of the matrix representation to a target dimensionality of the multi-dimensional representation.

### Claim 16 (depends on 14)

The system of claim 14, wherein the multi-dimensional representation of the steady state log file is a two-dimensional representation of the steady state log file.

### Claim 17 (depends on 14)

The system of claim 14, wherein the outlier detection model is a machine learning model trained to determine whether the given file is associated with normal behavior of the service on the cloud computing system based on the multi-dimensional representation of the steady state log file.

### Claim 18 (depends on 14)

The system of claim 14, wherein the plurality of outputs includes a subset of lines from the input log file that are predicted to be outliers.

### Claim 19

A non-transitory computer readable medium storing instructions thereon that, when executed by at least one processor, causes computing device to:
identify a steady state log file for a service on a cloud computing system associated with normal operation of the service over a period of time;
apply an encoding model to the steady state log file to generate a multi-dimensional representation of the steady state log file, the multi-dimensional representation including a plurality of points representative of lines of the steady state log file within a multi-dimensional space;
generate an outlier detection model trained to determine a plurality of outlier scores for a plurality of lines of a given log file based on the multi-dimensional representation of the steady state log file being associated with normal operation of the service, wherein an outlier score indicates a predicted probability that a given line from the plurality of lines of the given log file is an outlier from normal operation of the service; and
apply the outlier detection model to an input log file to generate a plurality of outputs indicating lines of the input log file that are predicted to be outliers from normal operation of the service.

### Claim 20 (depends on 19)

The non-transitory computer readable medium of claim 19, wherein applying the encoding model to the steady state log file further includes:
encoding the steady state log file to be a matrix representation of the steady state log file, the matrix representation having a same dimensionality as the steady state log file; and
applying an autoencoder to the matrix representation of the steady state log file to reduce a dimensionality of the matrix representation to a target dimensionality of the multi-dimensional representation.
