# US 2019/0173312 A1 · Utility usage classification

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

- Number: US 2019/0173312 A1
- Document ID: US20190173312A1
- Status: Published application
- Kind: A1
- Application number: 16/210,047
- Filed: 2018-12-05
- Published: 2019-06-06
- Earliest claimed: 2017-12-05
- Assignees: Fortum Oyj
- Applicants: Fortum Oyj
- Inventors: Naba Kumar
- Web page: https://patentgrep.com/patent/US20190173312A1

## CPC

- H02J 9/002: {in which a reserve is maintained in an energy source by disconnecting non-critical loads, e.g. maintaining a reserve of charge in a vehicle battery for starting an engine}
- G01D 4/004: {Remote reading of utility meters to a fixed location}
- G06Q 50/06: Energy or water supply
- H02J 1/14: Balancing load and power generation in DC networks
- H02J 1/15: characterised by load management
- H04Q 2209/60: for transmitting utility meters data, i.e. transmission of data from the reader of the utility meter
- H02J: ELECTRIC POWER NETWORKS; CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- G01D: MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- H04Q: SELECTING (switches, relays, selectors H01H; wireless communication networks H04W)

## Abstract

According to an example aspect of the present invention, there is provided an apparatus comprising a memory configured to store classifier parameters, and at least one processing core configured to use a classifier and the classifier parameters to determine a category of least one data composition, the at least one data composition comprising utility usage information concerning a utility unit, the category comprising a life condition present in the at least one utility unit.

## Claims

### Claim 1

An apparatus comprising:
a memory configured to store classifier parameters, and
at least one processing core configured to use a classifier and the classifier parameters to determine a category of least one data composition, the at least one data composition comprising utility usage information concerning a utility unit, the category comprising a life condition present in the at least one utility unit, the life condition comprising a utility non-interruption priority condition.

### Claim 2 (depends on 1)

The apparatus according to claim 1, wherein the apparatus is further configured to trigger a modification in a utility delivery network as a response to the determined category.

### Claim 3 (depends on 1)

The apparatus according to claim 1, wherein the at least one processing core is further configured to use, by the classifier, supplementary information along with the classifier parameters in determining the category.

### Claim 4 (depends on 3)

The apparatus according to claim 3, wherein the supplementary information comprises at least one of the following: weather information, regional information, demographic information, age information, income information, social media information, third-party consumer information, Internet use information and sensor data originating in at least one sensor in the utility unit.

### Claim 5 (depends on 2)

The apparatus according to claim 2, wherein the modification in the utility delivery network comprises either prioritizing higher the utility unit, thereby decreasing risk that the utility unit experiences an interruption in receiving the utility, or prioritizing lower the utility unit.

### Claim 6 (depends on 5)

The apparatus according to claim 5, wherein the prioritizing comprises allocating remaining resources to the utility unit in case of a failure condition that reduces a baseline amount of deliverable utility resources.

### Claim 7 (depends on 2)

The apparatus according to claim 2, wherein the modification in the utility delivery network comprises interrupting delivery of the utility to the utility unit.

### Claim 8 (depends on 1)

The apparatus according to claim 1, wherein the utility unit comprises at least one of a home, an industrial facility, a business and a medical facility.

### Claim 9 (depends on 1)

The apparatus according to claim 1, wherein the life condition comprises at least one of: whether the utility unit is occupied by humans, whether humans in the utility unit are healthy, whether the utility unit is occupied by a teen-aged human, whether the utility unit is occupied by at least one toddler, whether humans in the utility unit watch television in excess of a first threshold time per day, whether humans in the utility unit play video games in excess of a second threshold time per day, whether humans inhabiting the utility unit are employed outside of the utility unit, and whether humans in the utility unit own an electric vehicle.

### Claim 10 (depends on 1)

The apparatus according to claim 1, wherein the utility usage comprises usage of at least one of: electricity, water, heat, data connectivity and gas.

### Claim 11 (depends on 1)

The apparatus according to claim 1, wherein the classifier is comprised in the following list: a support vector machine, an artificial neural network, a linear classifier, a quadratic classifier, a kernel estimator, a decision tree, a K-nearest neighbour classifier, a random forest, and a Bayesian network.

### Claim 12

A method comprising:
storing classifier parameters, and
using a classifier and the classifier parameters to determine a category of least one data composition, the at least one data composition comprising utility usage information concerning a utility unit, the category comprising a life condition present in the at least one utility unit, and the life condition comprising a utility non-interruptions priority condition.

### Claim 13 (depends on 12)

The method according to claim 12, further comprising triggering a modification in a utility delivery network as a response to the determined category.

### Claim 14 (depends on 12)

The method according to claim 12, further comprising using, by the classifier, supplementary information along with the classifier parameters in determining the category.

### Claim 15 (depends on 14)

The method according to claim 14, wherein the supplementary information comprises at least one of the following: weather information, regional information, demographic information, age information, income information, social media information, third-party consumer information, Internet use information and sensor data originating in at least one sensor in the utility unit.

### Claim 16 (depends on 13)

The method according to claim 13, wherein the modification in the utility delivery network comprises either prioritizing higher the utility unit, thereby decreasing risk that the utility unit experiences an interruption in receiving the utility, or prioritizing lower the utility unit.

### Claim 17 (depends on 16)

The method according to claim 16, wherein the prioritizing comprises allocating remaining resources to the utility unit in case of a failure condition that reduces a baseline amount of deliverable utility resources.

### Claim 18 (depends on 13)

The method according to claim 13, wherein the modification in the utility delivery network comprises interrupting delivery of the utility to the utility unit.

### Claim 19 (depends on 12)

The method according to claim 12, wherein the utility unit comprises at least one of a home, an industrial facility, a business and a medical facility.

### Claim 20 (depends on 12)

The method according to claim 12, wherein the life condition comprises at least one of: whether the utility unit is occupied by humans, whether humans in the utility unit are healthy, whether the utility unit is occupied by a teen-aged human, whether the utility unit is occupied by at least one toddler, whether humans in the utility unit watch television in excess of a first threshold time per day, whether humans in the utility unit play video games in excess of a second threshold time per day, whether humans inhabiting the utility unit are employed outside of the utility unit, and whether humans in the utility unit own an electric vehicle.

### Claim 21 (depends on 12)

The method according to claim 12, wherein the utility usage comprises usage of at least one of: electricity, water, heat, data connectivity and gas.

### Claim 22 (depends on 12)

The method according to claim 12, wherein the classifier is comprised in the following list: a support vector machine, an artificial neural network, a linear classifier, a quadratic classifier, a kernel estimator, a decision tree, a K-nearest neighbour classifier, a random forest, and a Bayesian network.

### Claim 23

An apparatus comprising:
a memory configured to store classifier parameters, and
at least one processing core configured to use a classifier and training data to optimize the classifier parameters, to thereby train the classifier to determine categories of data compositions which comprise utility usage information concerning a utility unit, the categories comprising life conditions present in the utility unit, and the life conditions comprising a utility non-interruption priority condition.

### Claim 24

A method comprising:
storing classifier parameters, and
using a classifier and training data to optimize the classifier parameters, to thereby train the classifier to determine categories of data compositions which comprise utility usage information concerning a utility unit, the categories comprising life conditions present in the utility unit, and the life condition comprising a utility non-interruption priority condition.

### Claim 25

(canceled)

### Claim 26

A non-transitory computer readable medium having stored thereon a set of computer readable instructions that, when executed by at least one processor, cause an apparatus to at least:
store classifier parameters, and
use a classifier and the classifier parameters to determine a category of least one data composition, the at least one data composition comprising utility usage information concerning a utility unit, the category comprising a life condition present in the at least one utility unit, and the life conditions comprising a utility non-interruption priority condition.

### Claim 27

(canceled)
