# US 2021/0342208 A1 · Cognitive control of runtime resource monitoring scope

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

- Number: US 2021/0342208 A1
- Document ID: US20210342208A1
- Status: Published application
- Kind: A1
- Application number: 16/862,616
- Filed: 2020-04-30
- Published: 2021-11-04
- Earliest claimed: 2020-04-30
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: BING QIAN; YI XIN SONG; BO CHEN ZHU; TIAN MING PAN; PENG FEI TIAN
- Web page: https://patentgrep.com/patent/US20210342208A1

## 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 11/3409: {for performance assessment}
- G06F 11/0706: {the processing taking place on a specific hardware platform or in a specific software environment}
- G06F 11/0754: {by exceeding limits}
- G06F 11/076: {by exceeding a count or rate limit, e.g. word- or bit count limit}
- G06F 11/0769: {Readable error formats, e.g. cross-platform generic formats, human understandable formats}
- G06F 11/1474: in transactions (updating of structured data in databases G06F16/23)
- 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 11/3058: {Monitoring arrangements for monitoring environmental properties or parameters of the computing system or of the computing system component, e.g. monitoring of power, currents, temperature, humidity, position, vibrations (thermal management in cooling arrangements of a computing system G06F1/206)}
- G06F 11/326: {for error or online/offline status}
- G06F 11/3452: {Performance evaluation by statistical analysis}
- G06F 2201/81: Threshold
- G06F 2201/87: Monitoring of transactions
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Embodiments include cognitive control of runtime resource monitoring scope. Aspects include obtaining historical data for each of a plurality of metrics for a computer system and calculating, based on the historical data, an anomaly relationship score for each of the plurality of metrics. Aspects also include calculating, based on the historical data, a sensitivity score for each of the plurality of metrics and determining a priority score for each of the plurality of metrics based upon a weighted combination of the anomaly relationship score and the priority score. Aspects further include receiving real-time data for each of the plurality of metrics and presenting a subset of the real-time data to a user, the subset created by selecting one or more of the plurality of metrics based on the priority score of each of the plurality of metrics.

## Claims

### Claim 1

A computer-implemented method for cognitive control of runtime resource monitoring scope, the method comprising:
obtaining historical data for each of a plurality of metrics for a computer system;
calculating, based on the historical data, an anomaly relationship score for each of the plurality of metrics;
calculating, based on the historical data, a sensitivity score for each of the plurality of metrics;
determining a priority score for each of the plurality of metrics based upon a weighted combination of the anomaly relationship score and the sensitivity score, wherein both the anomaly relationship score and the sensitivity score have a value between zero and one and a sum of the anomaly relationship score and the sensitivity score is equal to two and wherein the weighted combination is determined by a user setting a position of an icon on a sliding bar that ranges from an anomaly relationship score of two at one end and zero at the other end with the sensitivity score having the opposite configuration;
receiving real-time data for each of the plurality of metrics;
creating a subset of the real-time data by selecting one or more of the plurality of metrics based on the priority score of each of the plurality of metrics, wherein the one or more of the plurality of metrics is determined based upon a threshold value provided by a user, and
presenting the subset of the real-time data to the user.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, wherein calculating the anomaly relationship score for each of the plurality of metrics comprises:
calculating a distribution function for each of the plurality of metrics;
calculating a pair distribution function for each possible combination of two of the plurality of metrics;
calculating a pointwise mutual information value for each possible combination of two of the plurality of metrics; and
determining the anomaly relationship score for a selected metric of the plurality of metrics by summing the pointwise mutual information value for each of the possible combination of two of the plurality of metrics that includes the selected metric.

### Claim 3 (depends on 1)

The computer-implemented method of claim 1, wherein calculating the sensitivity score for each of the plurality of metrics comprises:
serializing the historical data for a selected metric of the plurality of metrics to create data pairs that each include a data value and a transaction rate at the time the data value was captured;
performing a statistical analysis on the data pairs to identify an approximation function for the data value as a function of the transaction rate;
obtaining an abnormal threshold from the user and a current transaction rate; and
determining the sensitivity score for the selected metric by dividing the abnormal threshold by a value of the approximation function for the current transaction rate.

### Claim 4 (depends on 3)

The computer-implemented method of claim 3, wherein the abnormal threshold is a function of the transaction rate.

### Claim 5 (depends on 1)

The computer-implemented method of claim 1, wherein the priority score is determined to be the sum of the anomaly relationship score multiplied by a root cause analysis factor and the sensitivity score multiplied by an error prediction factor.

### Claim 6 (depends on 5)

The computer-implemented method of claim 5, wherein each of the root cause analysis factor and the error prediction factor are provided by the user.

### Claim 7 (depends on 6)

The computer-implemented method of claim 6, wherein each of the root cause analysis factor and the error prediction factor have a value between zero and one and wherein the sum of the root cause analysis factor and the error prediction factor is two.

### Claim 8

A computer program product comprising a memory device with computer executable instructions therein, the instructions when executed by a processing unit perform a method for cognitive control of runtime resource monitoring scope, the method comprising:
obtaining historical data for each of a plurality of metrics for a computer system;
calculating, based on the historical data, an anomaly relationship score for each of the plurality of metrics;
calculating, based on the historical data, a sensitivity score for each of the plurality of metrics;
determining a priority score for each of the plurality of metrics based upon a weighted combination of the anomaly relationship score and the sensitivity score, wherein both the anomaly relationship score and the sensitivity score have a value between zero and one and a sum of the anomaly relationship score and the sensitivity score is equal to two and wherein the weighted combination is determined by a user setting a position of an icon on a sliding bar that ranges from an anomaly relationship score of two at one end and zero at the other end with the sensitivity score having the opposite configuration;
receiving real-time data for each of the plurality of metrics;
creating a subset of the real-time data by selecting one or more of the plurality of metrics based on the priority score of each of the plurality of metrics, wherein the one or more of the plurality of metrics is determined based upon a threshold value provided by a user, and
presenting the subset of the real-time data to the user.

### Claim 9 (depends on 8)

The computer program product of claim 8, wherein calculating the anomaly relationship score for each of the plurality of metrics comprises:
calculating a distribution function for each of the plurality of metrics;
calculating a pair distribution function for each possible combination of two of the plurality of metrics;
calculating a pointwise mutual information value for each possible combination of two of the plurality of metrics; and
determining the anomaly relationship score for a selected metric of the plurality of metrics by summing the pointwise mutual information value for each of the possible combination of two of the plurality of metrics that includes the selected metric.

### Claim 10 (depends on 8)

The computer program product of claim 8, wherein calculating the sensitivity score for each of the plurality of metrics comprises:
serializing the historical data for a selected metric of the plurality of metrics to create data pairs that each include a data value and a transaction rate at the time the data value was captured;
performing a statistical analysis on the data pairs to identify an approximation function for the data value as a function of the transaction rate;
obtaining an abnormal threshold from the user and a current transaction rate; and
determining the sensitivity score for the selected metric by dividing the abnormal threshold by a value of the approximation function for the current transaction rate.

### Claim 11 (depends on 10)

The computer program product of claim 10, wherein the abnormal threshold is a function of the transaction rate.

### Claim 12 (depends on 8)

The computer program product of claim 8, wherein the priority score is determined to be the sum of the anomaly relationship score multiplied by a root cause analysis factor and the sensitivity score multiplied by an error prediction factor.

### Claim 13 (depends on 12)

The computer program product of claim 12, wherein each of the root cause analysis factor and the error prediction factor are provided by the user.

### Claim 14 (depends on 13)

The computer program product of claim 13, wherein each of the root cause analysis factor and the error prediction factor have a value between zero and one and wherein the sum of the root cause analysis factor and the error prediction factor is two.

### Claim 15

A system comprising:
a memory; and
a processor coupled to the memory, the processor configured to perform a method of cognitive control of runtime resource monitoring scope, the method comprising:
obtaining historical data for each of a plurality of metrics for a computer system;
calculating, based on the historical data, an anomaly relationship score for each of the plurality of metrics;
calculating, based on the historical data, a sensitivity score for each of the plurality of metrics;
determining a priority score for each of the plurality of metrics based upon a weighted combination of the anomaly relationship score and the sensitivity score, wherein both the anomaly relationship score and the sensitivity score have a value between zero and one and a sum of the anomaly relationship score and the sensitivity score is equal to two and wherein the weighted combination is determined by a user setting a position of an icon on a sliding bar that ranges from an anomaly relationship score of two at one end and zero at the other end with the sensitivity score having the opposite configuration;
receiving real-time data for each of the plurality of metrics;
creating a subset of the real-time data by selecting one or more of the plurality of metrics based on the priority score of each of the plurality of metrics, wherein the one or more of the plurality of metrics is determined based upon a threshold value provided by a user, and
presenting the subset of the real-time data to the user.

### Claim 16 (depends on 15)

The system of claim 15, wherein calculating the anomaly relationship score for each of the plurality of metrics comprises:
calculating a distribution function for each of the plurality of metrics;
calculating a pair distribution function for each possible combination of two of the plurality of metrics;
calculating a pointwise mutual information value for each possible combination of two of the plurality of metrics; and
determining the anomaly relationship score for a selected metric of the plurality of metrics by summing the pointwise mutual information value for each of the possible combination of two of the plurality of metrics that includes the selected metric.

### Claim 17 (depends on 15)

The system of claim 15, wherein calculating the sensitivity score for each of the plurality of metrics comprises:
serializing the historical data for a selected metric of the plurality of metrics to create data pairs that each include a data value and a transaction rate at the time the data value was captured;
performing a statistical analysis on the data pairs to identify an approximation function for the data value as a function of the transaction rate;
obtaining an abnormal threshold from the user and a current transaction rate; and
determining the sensitivity score for the selected metric by dividing the abnormal threshold by a value of the approximation function for the current transaction rate.

### Claim 18 (depends on 17)

The system of claim 17, wherein the abnormal threshold is a function of the transaction rate.

### Claim 19 (depends on 15)

The system of claim 15, wherein the priority score is determined to be the sum of the anomaly relationship score multiplied by a root cause analysis factor and the sensitivity score multiplied by an error prediction factor.

### Claim 20 (depends on 19)

The system of claim 19, wherein each of the root cause analysis factor and the error prediction factor are provided by the user.
