# US 2023/0412627 A1 · Method and apparatus for anomaly detection

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

- Number: US 2023/0412627 A1
- Document ID: US20230412627A1
- Status: Published application
- Kind: A1
- Application number: 18/188,677
- Filed: 2023-03-23
- Published: 2023-12-21
- Earliest claimed: 2022-06-10
- Assignees: Nokia Solutions and Networks Oy
- Applicants: Nokia Solutions and Networks Oy
- Inventors: Péter SZILÁGYI; Gabor HORVATH; Attila KADAR
- Web page: https://patentgrep.com/patent/US20230412627A1

## CPC

- G06F 11/0751: {Error or fault detection not based on redundancy (power supply failures G06F1/30; network fault management H04L41/06)}
- G06F 40/30: Semantic analysis
- G06F 11/0709: {in a distributed system consisting of a plurality of standalone computer nodes, e.g. clusters, client-server systems}
- G06F 11/0766: {Error or fault reporting or storing}
- G06F 11/0775: {Content or structure details of the error report, e.g. specific table structure, specific error fields}
- 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)}
- G06F 11/3476: {Data logging (G06F11/14, G06F11/2205 take precedence)}
- G06F 16/35: Clustering; Classification
- G06F 40/216: using statistical methods
- G06F 40/284: Lexical analysis, e.g. tokenisation or collocates
- G06F 2201/83: the solution involving signatures
- G06N 3/0455: Auto-encoder networks; Encoder-decoder networks
- G06N 3/084: Backpropagation, e.g. using gradient descent
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

An apparatus for anomaly detection, the apparatus comprising means for: Collecting a plurality of log messages from a data processing system, log messages comprising textual content and numeric attributes, Classifying the plurality of log messages into a plurality of clusters as a function of a number of the numeric attributes in the log messages, such that the log messages within a cluster have a given number of the numeric attributes, For at least one of the clusters, computing at least one encoding vector associated to a numeric attribute, Computing a combined semantic embedding vector from the textual contents of the plurality of log messages, Combining the at least one encoding vector with the combined semantic embedding vector into a final encoding vector, and Feeding the final encoding vector to an anomaly detection module intended to detect an anomaly in the data processing system.

## Claims

### Claim 1

An apparatus to detect anomalies, the apparatus comprising at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to perform:
Collecting a plurality of log messages from a data processing system, the log messages reporting events that occur as the data processing system operates, the log messages comprising textual content and numeric attributes,
Classifying the plurality of log messages into a plurality of clusters as a function of a number of the numeric attributes in the log messages, such that the log messages within a cluster have a given number of the numeric attributes,
For at least one of the clusters, computing at least one encoding vector associated to a numeric attribute, wherein the at least one encoding vector is computed as a function of a representative value of the numeric attribute across a plurality of the log messages within the cluster and of a rank of the numeric attribute, wherein the rank is representative of an order of the numeric attribute within the given number of the numeric attributes of the log messages within the cluster,
Computing a combined semantic embedding vector from the textual contents of the plurality of log messages,
Combining the at least one encoding vector with the combined semantic embedding vector into a final encoding vector, and
Feeding the final encoding vector to an anomaly detection module intended to detect an anomaly in the data processing system.

### Claim 2 (depends on 1)

An apparatus according to claim 1, wherein the apparatus is further caused to perform: computing at least one encoding vector associated to a numeric attribute for a plurality of the clusters.

### Claim 3 (depends on 1)

An apparatus according to claim 1, wherein the apparatus is further caused to perform: computing a plurality of encoding vectors associated to a plurality of numeric attributes for at least one of the clusters.

### Claim 4 (depends on 3)

An apparatus according to claim 3, wherein the apparatus is further caused to perform: combining the plurality of encoding vectors with the combined semantic embedding vector into the final encoding vector.

### Claim 5 (depends on 1)

An apparatus according to claim 1, wherein the apparatus is further caused to perform: computing at least one additional numeric attribute from the log messages of at least one of the clusters, and appending the at least one additional numeric attribute to the numeric attributes within the at least one of the clusters and increasing the given number of the numeric attributes of the log messages within the cluster.

### Claim 6 (depends on 1)

An apparatus according to claim 1, wherein the apparatus is further caused to compute the plurality of clusters as a function of the textual contents in the log messages.

### Claim 7 (depends on 1)

An apparatus according to claim 1, wherein the apparatus is further caused to perform: computing a plurality of semantic embedding vectors from the textual contents and for combining the plurality of semantic embedding vectors into the combined semantic embedding vector.

### Claim 8 (depends on 1)

An apparatus according to claim 1, wherein the apparatus is further caused to convert the plurality of average values into high dimensional polar coordinates.

### Claim 9 (depends on 1)

An apparatus according to claim 1, wherein the apparatus is further caused to compute an intermediate encoding vector from the representative value of the numeric attribute and to select a projection vector within a basis of orthogonal vectors as a function of the rank of the numeric attribute and to compute the encoding vector by projecting the intermediate encoding vector on the projection

### Claim 10 (depends on 1)

An apparatus according to claim 1, wherein the apparatus is further caused to compute a transitional encoding vector from the representative value of the numeric attribute and to multiply at least one coordinate of the transitional encoding vector by a factor depending on an index of the at least one coordinate and the rank of the numeric attribute.

### Claim 11 (depends on 1)

An apparatus according to claim 1, wherein the apparatus is further caused to perform: returning an anomaly detection signal to the data processing system in order to cause a corrective action in the data processing system, the anomaly detection signal being computed by the anomaly detection module.

### Claim 12 (depends on 1)

An apparatus according to claim 1, wherein the anomaly detection module is an autoencoder.

### Claim 13 (depends on 12)

An apparatus according to claim 12, wherein the apparatus is further caused to perform: receiving a reconstruction loss computed by the autoencoder and classifying a value of the reconstruction loss higher than an anomaly threshold as an anomaly.

### Claim 14 (depends on 1)

An apparatus according to claim 1, wherein the apparatus comprises is further caused to perform: training the anomaly detection module using a plurality of training encoding vectors, the plurality of training encoding vectors being computed from a training dataset of log messages.

### Claim at position 15

A method for anomaly detection, the method comprising:
Collecting a plurality of log messages from a data processing system, the log messages reporting events that occur as the data processing system operates, the log messages comprising textual content and numeric attributes,
Classifying the plurality of log messages into a plurality of clusters as a function of a number of the numeric attributes in the log messages, such that the log messages within a cluster have a given number of the numeric attributes,
For at least one of the clusters, computing at least one encoding vector associated to a numeric attribute, wherein the at least one encoding vector is computed as a function of a representative value of the numeric attribute across a plurality of the log messages within the cluster and of a rank of the numeric attribute, wherein the rank is representative of an order of the numeric attribute within the given number of the numeric attributes of the log messages within the cluster,
Computing a combined semantic embedding vector from the textual contents of the plurality of log messages,
Combining the at least one encoding vector with the combined semantic embedding vector into a final encoding vector, and
Feeding the final encoding vector to an anomaly detection module intended to detect an anomaly in the data processing system.

### Claim 16 (depends on 15)

A method according to claim 15, further comprising returning an anomaly detection signal representing the anomaly.

### Claim 17 (depends on 16)

A method according to claim 16, further comprising performing corrective action as a function of the anomaly detection signal.

### Claim 18 (depends on 17)

A method according to claim 17, wherein the corrective action is performed in the data processing system.
