# US 2021/0341910 A1 · Sensor attribution 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 2021/0341910 A1
- Document ID: US20210341910A1
- Status: Published application
- Kind: A1
- Application number: 17/223,251
- Filed: 2021-04-06
- Published: 2021-11-04
- Earliest claimed: 2020-04-08
- Assignees: NEC Laboratories America, Inc.
- Applicants: NEC Laboratories America, Inc.
- Inventors: Dongjin Song; Takehiko Mizoguchi; Cristian Lumezanu; Haifeng Chen
- Web page: https://patentgrep.com/patent/US20210341910A1

## CPC

- G05B 19/41875: {characterised by quality surveillance of production}
- G05B 19/4183: {characterised by data acquisition, e.g. workpiece identification}
- G05B 23/0235: {based on a comparison with predetermined threshold or range, e.g. "classical methods", carried out during normal operation; threshold adaptation or choice; when or how to compare with the threshold}
- G05B 23/0289: {Reconfiguration to prevent failure, e.g. usually as a reaction to incipient failure detection}
- G05B 19/4184: {characterised by fault tolerance, reliability of production system}
- G05B 2219/31294: Compare measurements from sensors to detect defective sensors
- Y02P 90/02: Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
- G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G)
- Y02P: CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS

## Abstract

Methods and systems for detecting and correcting anomalies includes generating historical binary codes from historical time series segments. The historical time series segments are each made up of measurements from respective sensors. A latest binary code is generated from a latest time series segment. It is determined that the latest time series segment represents anomalous behavior, based on a comparison of the latest binary code to the historical binary codes. The sensors are ranked, based on a comparison of time series data of the sensors in the latest time series segment to respective time series data of the historical time series, to generate a sensor ranking. A corrective action is performed responsive to the detected anomaly, prioritized according to the sensor ranking.

## Claims

### Claim 1

A method of detecting and correcting anomalies, comprising:
generating historical binary codes from a plurality of historical time series segments, the plurality of historical time series segments each being made up of measurements from respective sensors;
generating a latest binary code from a latest time series segment;
determining that the latest time series segment represents anomalous behavior, based on a comparison of the latest binary code to the historical binary codes;
ranking the sensors, based on a comparison of time series data of the sensors in the latest time series segment to respective time series data of the plurality of historical time series, to generate a sensor ranking; and
performing a corrective action responsive to the detected anomaly, prioritized according to the sensor ranking.

### Claim 2 (depends on 1)

The method of claim 1, wherein determining that the latest time series segment represents anomalous behavior includes:
grouping the historical time series segments in buckets; and
determining exemplars of the buckets, wherein the comparison of the latest binary code to the historical binary codes includes comparing the latest binary code to binary codes of the exemplars.

### Claim 3 (depends on 2)

The method of claim 2, wherein the historical time series segments are grouped into buckets according to prefixes of the historical binary codes.

### Claim 4 (depends on 2)

The method of claim 2, wherein the exemplar of a given bucket is determined as a time series segment that is nearest to a centroid of the historical time series grouped into the given bucket.

### Claim 5 (depends on 2)

The method of claim 2, wherein determining the exemplars of the buckets includes determining exemplars for only those buckets which have an above-threshold percentage of the plurality of historical time series segments.

### Claim 6 (depends on 2)

The method of claim 2, wherein ranking the sensors comprises determining a difference between sensor values of the latest time series segment and sensor values of each of the exemplars.

### Claim 7 (depends on 6)

The method of claim 6, wherein ranking the sensors further comprises determining a divergence vector from the differences, with each value of the divergence vector representing a ranking score of the sensors.

### Claim 8 (depends on 7)

The method of claim 7, wherein each value of the divergence vector is determined as a minimum absolute difference of a corresponding sensor across the exemplars.

### Claim 9 (depends on 1)

The method of claim 1, wherein the comparison of the latest binary code to the historical binary codes includes determining a Hamming distance between the latest binary code and each of the historical binary codes.

### Claim 10 (depends on 1)

The method of claim 1, wherein the corrective action includes an action selected from the group consisting of changing a security setting for an application or hardware component, changing an operational parameter of an application or hardware component, halting an application, restarting an application, halting a hardware component, rebooting a hardware component, changing an environmental condition, and changing a network interface's status.

### Claim 11

A method of detecting and correcting anomalies, comprising:
generating historical binary codes from a plurality of historical time series segments, the plurality of historical time series segments each being made up of measurements from respective sensors;
generating a latest binary code from a latest time series segment;
determining that the latest time series segment represents anomalous behavior, based on a comparison of the latest binary code to the historical binary codes, including:
grouping the historical time series segments in buckets according to prefixes of the historical binary codes; and
determining exemplars of the buckets, wherein the comparison of the latest binary code to the historical binary codes includes comparing the latest binary code to binary codes of the exemplars;
ranking the sensors, based on a comparison of measured values of the sensors in the latest time series segment to respective time series data of the plurality of historical time series, comparing the latest time series segment to each of the exemplars, to generate a sensor ranking; and
performing a corrective action responsive to the detected anomaly, prioritized according to the sensor ranking.

### Claim 12

A system for detecting and correcting anomalies, comprising:
a hardware processor; and
a memory that stores computer program code, which, when executed by the hardware processor, causes the hardware processor to:
generate historical binary codes from a plurality of historical time series segments, the plurality of historical time series segments each being made up of measurements from respective sensors;
generate a latest binary code from a latest time series segment;
determine that the latest time series segment represents anomalous behavior, based on a comparison of the latest binary code to the historical binary codes;
rank the sensors, based on a comparison of time series data of the sensors in the latest time series segment to respective time series data of the plurality of historical time series, to generate a sensor ranking; and
perform a corrective action responsive to the detected anomaly, prioritized according to the sensor ranking.

### Claim 13 (depends on 12)

The system of claim 12, wherein the computer program code further causes the hardware processor to:
group the historical time series segments in buckets; and
determine exemplars of the buckets, wherein the comparison of the latest binary code to the historical binary codes includes comparing the latest binary code to binary codes of the exemplars.

### Claim 14 (depends on 13)

The system of claim 13, wherein the historical time series segments are grouped into buckets according to prefixes of the historical binary codes.

### Claim 15 (depends on 13)

The system of claim 13, wherein the exemplar of a given bucket is determined as a time series segment that is nearest to a centroid of the historical time series grouped into the given bucket.

### Claim 16 (depends on 13)

The system of claim 13, wherein the computer program code further causes the hardware processor to determine exemplars for only those buckets which have an above-threshold percentage of the plurality of historical time series segments.

### Claim 17 (depends on 13)

The system of claim 13, wherein the computer program code further causes the hardware processor to determine a difference between sensor values of the latest time series segment and sensor values of each of the exemplars.

### Claim 18 (depends on 17)

The system of claim 17, wherein the computer program code further causes the hardware processor to determine a divergence vector from the differences, with each value of the divergence vector representing a ranking score of the sensors.

### Claim 19 (depends on 18)

The system of claim 18, wherein each value of the divergence vector is determined as a minimum absolute difference of a corresponding sensor across the exemplars.

### Claim 20 (depends on 12)

The system of claim 12, wherein the corrective action includes an action selected from the group consisting of changing a security setting for an application or hardware component, changing an operational parameter of an application or hardware component, halting an application, restarting an application, halting a hardware component, rebooting a hardware component, changing an environmental condition, and changing a network interface's status.
