# US 2024/0176719 A1 · Apparatuses, methods, and computer program products for context-conscious sensor signature profiling with impression acquisition and scavenging

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

- Number: US 2024/0176719 A1
- Document ID: US20240176719A1
- Status: Published application
- Kind: A1
- Application number: 18/060,326
- Filed: 2022-11-30
- Published: 2024-05-30
- Earliest claimed: 2022-11-30
- Assignees: Honeywell International Inc.
- Applicants: Honeywell International Inc.
- Inventors: Bhabesh Chandra Acharya; Manu Taranath
- Web page: https://patentgrep.com/patent/US20240176719A1

## CPC

- G06F 11/3089: {Monitoring arrangements determined by the means or processing involved in sensing the monitored data, e.g. interfaces, connectors, sensors, probes, agents (software debugging using additional hardware using a specific debug interface G06F11/3656; performance evaluation by tracing or monitoring G06F11/3466)}
- 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 16/22: Indexing; Data structures therefor; Storage structures
- G06F 16/258: {Data format conversion from or to a database}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Sensor characteristic profiles for different sensor types for sensors of an operational system are generated based at least in part on aggregated time series sensor data from the sensors and context data for the sensors. The sensor characteristic profiles for each sensor type are stored in a sensor type profile database. Sensor information is generated based at least in part on the stored sensor characteristic profiles. Each of the sensor characteristic profiles comprises sensor type information identifying the sensor type and a sensor data signature for the sensor type. Sample sensor data from a particular sensor is used to determine information about the particular sensor based on the stored sensor characteristic profiles. Device characteristic profiles for different device types and/or virtual sensor characteristic profiles for different virtual sensors defined with respect to particular combinations of the sensors can be generated based on the stored sensor characteristic profiles.

## Claims

### Claim 1

An apparatus comprising at least one processor and at least one non-transitory memory comprising program code, wherein the at least one non-transitory memory and the program code are configured to, with the at least one processor, cause the apparatus to at least:
receive aggregated time series sensor data and context data for a plurality of sensors of a plurality of different sensor types;
generate one or more sensor characteristic profiles for each sensor type of the plurality of different sensor types based at least in part on the aggregated time series sensor data and the context data, wherein each of the one or more sensor characteristic profiles comprises sensor type information identifying the sensor type and a sensor data signature for the sensor type;
store the one or more sensor characteristic profiles for each sensor type in a sensor type profile database; and
generate sensor information based at least in part on the stored one or more sensor characteristic profiles.

### Claim 2 (depends on 1)

The apparatus of claim 1, wherein the sensor information includes sensor identification information, sensor type information, and/or context data for a particular sensor.

### Claim 3 (depends on 2)

The apparatus of claim 2, wherein the apparatus is further configured to determine the sensor identification information, sensor type information, and/or context data for the particular sensor based at least in part on sample sensor data from the particular sensor and the stored one or more sensor characteristic profiles.

### Claim 4 (depends on 3)

The apparatus of claim 3, wherein the apparatus is further configured to determine the sensor identification information, sensor type information, and/or context data for the particular sensor by generating a sample sensor data signature for the particular sensor based at least in part on the sample sensor data from the particular sensor and matching the sample sensor data signature against sensor data signatures of the stored one or more sensor characteristic profiles.

### Claim 5 (depends on 1)

The apparatus of claim 1, wherein the apparatus is further configured to generate the sensor information based at least in part on comparing sensor data signatures of the stored one or more sensor characteristic profiles, the compared sensor data signatures being for similar sensor types of different sensor makes, and evaluating the compared sensor data signatures against each other.

### Claim 6 (depends on 1)

The apparatus of claim 1, wherein the apparatus is further configured to generate device characteristic profiles for a plurality of devices to which the plurality of sensors are connected based at least in part on the one or more sensor characteristic profiles, the device characteristic profiles comprising device type information identifying a device type and a device profile score for the device type.

### Claim 7 (depends on 1)

The apparatus of claim 1, wherein the one or more sensor characteristic profiles for each sensor type include one or more normalized profiles, and the apparatus is further configured to generate the one or more normalized profiles by converting different instances of time series sensor data for different sensors to a common index system.

### Claim 8 (depends on 1)

The apparatus of claim 1, wherein the one or more sensor characteristic profiles for each sensor type include one or more central sensor characteristic profiles, and the apparatus is further configured to generate a central characteristic profile by identifying a time window within which sensor data for sensors of the sensor type is sufficiently representative of the sensor type, extracting sensor data within the identified time window for sensors of the sensor type, and generating the sensor data signature of the central characteristic profile with respect to the extracted sensor data from within the identified time window.

### Claim 9 (depends on 1)

The apparatus of claim 1, wherein the apparatus is further configured to generate one or more virtual sensor characteristic profiles for one or more virtual sensor types, each of which is defined with respect to a particular combination of different sensor types of the plurality of sensor types, by combining the sensor data signatures of the sensor characteristic profiles for the particular combination of different sensor types.

### Claim 10 (depends on 1)

The apparatus of claim 1, wherein the sensor information includes comparison information for different sensor types of the plurality of sensor types and/or evaluation information indicating performance of a sensor type of the plurality of sensor types.

### Claim 11

A method comprising:
at a device with one or more processors and one or more memories:
receiving aggregated time series sensor data and context data for a plurality of sensors of a plurality of different sensor types;
generating one or more sensor characteristic profiles for each sensor type of the plurality of different sensor types based at least in part on the aggregated time series sensor data and the context data, wherein each of the one or more sensor characteristic profiles comprises sensor type information identifying the sensor type and a sensor data signature for the sensor type;
storing the one or more sensor characteristic profiles for each sensor type in a sensor type profile database; and
generating sensor information based at least in part on the stored one or more sensor characteristic profiles.

### Claim 12 (depends on 11)

The method of claim 11, wherein the sensor information includes sensor identification information, sensor type information, and/or context data for a particular sensor.

### Claim 13 (depends on 12)

The method of claim 12, further comprising determining the sensor identification information, sensor type information, and/or context data for the particular sensor based at least in part on sample sensor data from the particular sensor and the stored one or more sensor characteristic profiles.

### Claim 14 (depends on 13)

The method of claim 13, further comprising determining the sensor identification information, sensor type information, and/or context data for the particular sensor by generating a sample sensor data signature for the particular sensor based at least in part on the sample sensor data from the particular sensor and matching the sample sensor data signature against sensor data signatures of the stored one or more sensor characteristic profiles.

### Claim 15 (depends on 11)

The method of claim 11, further comprising generating the sensor information based at least in part on comparing sensor data signatures of the stored one or more sensor characteristic profiles, the compared sensor data signatures being for similar sensor types of different sensor makes, and evaluating the compared sensor data signatures against each other.

### Claim 16 (depends on 11)

The method of claim 11, further comprising generating device characteristic profiles for a plurality of devices to which the plurality of sensors are connected based at least in part on the one or more sensor characteristic profiles, the device characteristic profiles comprising device type information identifying a device type and a device profile score for the device type.

### Claim 17 (depends on 11)

The method of claim 11, wherein the one or more sensor characteristic profiles for each sensor type include one or more normalized profiles, and the method further comprises generating the one or more normalized profiles by converting different instances of time series sensor data for different sensors to a common index system.

### Claim 18 (depends on 11)

The method of claim 11, wherein the one or more sensor characteristic profiles for each sensor type include one or more central sensor characteristic profiles, and the method further comprises generating a central characteristic profile by identifying a time window within which sensor data for sensors of the sensor type is sufficiently representative of the sensor type, extracting sensor data within the identified time window for sensors of the sensor type, and generating the sensor data signature of the central characteristic profile with respect to the extracted sensor data from within the identified time window.

### Claim 19 (depends on 11)

The method of claim 11, further comprising generating one or more virtual sensor characteristic profiles for one or more virtual sensor types, each of which is defined with respect to a particular combination of different sensor types of the plurality of sensor types, by combining the sensor data signatures of the sensor characteristic profiles for the particular combination of different sensor types.

### Claim 20

A computer program product comprising at least one non-transitory computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions comprising an executable portion configured to:
receive aggregated time series sensor data and context data for a plurality of sensors of a plurality of different sensor types;
generate one or more sensor characteristic profiles for each sensor type of the plurality of different sensor types based at least in part on the aggregated time series sensor data and the context data, wherein each of the one or more sensor characteristic profiles comprises sensor type information identifying the sensor type and a sensor data signature for the sensor type;
store the one or more sensor characteristic profiles for each sensor type in a sensor type profile database; and
generate sensor information based at least in part on the stored one or more sensor characteristic profiles.
