# US 2020/0404058 A1 · Edge-computing-based forensic feedback architecture

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

- Number: US 2020/0404058 A1
- Document ID: US20200404058A1
- Status: Published application
- Kind: A1
- Application number: 16/446,740
- Filed: 2019-06-20
- Published: 2020-12-24
- Earliest claimed: 2019-06-20
- Assignees: Bank of America Corporation
- Applicants: Bank of America Corporation
- Inventors: Stephen T. Shannon; William August Stahlhut
- Web page: https://patentgrep.com/patent/US20200404058A1

## CPC

- H04L 67/125: involving control of end-device applications over a network
- H04L 67/30: Profiles
- G06N 20/00: Machine learning
- H04L 67/10: in which an application is distributed across nodes in the network (software deployment G06F8/60; multiprogramming arrangements G06F9/46)
- H04L 67/1059: {Inter-group management mechanisms, e.g. splitting, merging or interconnection of groups}
- H04L 67/1068: {Discovery involving direct consultation or announcement among potential requesting and potential source peers}
- H04L 67/52: specially adapted for the location of the user terminal
- H04L 67/535: {Tracking the activity of the user (network monitoring arrangements H04L43/00; recording of computer activity G06F11/34)}
- H04L 67/562: Brokering proxy services
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Aspects of the disclosure relate to systems and methods for maintaining situational stability at a target location. The systems may include a database of machine-learning (“ML”)-derived event profiles. The systems may include a plurality of edge-nodes that are proximal to the target location. Each edge-node may generate a data stream of situational data pertaining to the target location. Each edge-node may transmit its data stream to the other edge-nodes. Each edge-node may conglomerate its own data stream with the data streams received from the other edge-nodes to create a conglomerated data stream. Each edge-node may monitor its conglomerated data stream for data that matches one of the event profiles. When a consensus is determined among the edge-nodes that a match occurred, the systems may execute a pre-determined response.

## Claims

### Claim 1

A method for maintaining situational stability at a target location via a set of digital devices at a network edge, the method comprising:
generating, via a machine-learning (“ML”) engine, a database of event profiles;
accessing the set of digital devices, wherein:
each digital device from the set of digital devices comprises a processor, a memory, a sensor, and a communication element for communicating with other digital devices and/or a centralized server; and
the set of digital devices is located within sensor range of the target location;
generating, via the sensors of each digital device in the set of digital devices, a data stream comprising situational data that pertains to the target location;
transmitting, from each digital device in the set of digital devices to all the other digital devices in the set of digital devices, the data stream generated by said each digital device;
conglomerating, via the processor of each digital device in the set of digital devices, the data stream generated by the sensor of said each digital device with the data streams received from the other digital devices in the set of digital devices, to create a conglomerated data stream, and each digital device in the set of digital devices stores the conglomerated data stream;
monitoring the conglomerated data stream for one of the event profiles, said monitoring performed independently, via the processors of each digital device in the set of digital devices; and
when a consensus is determined that one of the event profiles is detected, executing, via one or more of the digital devices, a predetermined response to the one of the event profiles.

### Claim 2 (depends on 1)

The method of claim 1, wherein at least one of the event profiles comprises data associated with a pattern of activity, said pattern which indicates that:
an emergency situation occurred at the target location; or
a piece of equipment in the target location is in a condition of reduced operability.

### Claim 3 (depends on 2)

The method of claim 2, wherein the piece of equipment is an automated teller machine (“ATM”) or a furniture item, said furniture item being a table, desk, carpet, light fixture, and/or a door.

### Claim 4 (depends on 2)

The method of claim 2, wherein the situational data includes:
a number of people who use the piece of equipment;
a period of time over which the piece of equipment was used;
visual evidence of decay in the piece of equipment; and/or
a threshold change in user interaction with the piece of equipment.

### Claim 5 (depends on 4)

The method of claim 4, wherein the threshold change in user interaction comprises a threshold increase and/or decrease in a size of a queue of users waiting to operate the piece of equipment.

### Claim 6 (depends on 1)

The method of claim 1, wherein the conglomerated data streams are ephemeral, wherein the method further comprises each device deleting its conglomerated data stream after a predetermined time period lapses without an event profile being detected.

### Claim 7 (depends on 1)

The method of claim 1, wherein the set of devices comprises a specialized set of devices installed at the target location for detecting situational data.

### Claim 8 (depends on 1)

The method of claim 1, wherein the set of devices comprises at least one privately-owned device, and the privately-owned device is configured to receive permission for the accessing from an owner of said privately-owned device, and the permission is received:
in response to a message that is transmitted to the privately-owned device, said transmission that is triggered when the privately-owned device enters the sensor range of the target location; or
in response, at least in part, to the owner opting-in to a default permission setting on the privately-owned device, wherein opting-in to the default permission triggers the accessing when the privately-owned device enters the sensor range of the target location.

### Claim 9 (depends on 1)

The method of claim 1, wherein:
each device is assigned a weight in determining the consensus; and
the consensus is a majority consensus, said majority consensus comprising a scenario in which at least a half of the digital devices determine that the event profile was detected.

### Claim 10

A system for maintaining situational stability at a target location, said system comprising:
a set of digital devices at a network edge, wherein:
each digital device from the set of digital devices comprises:
a processor;
a memory;
a sensor;
a communication element for communicating with other digital devices and/or a centralized server; and
a database of event profiles generated by a machine-learning (“ML”) engine; and
the set of digital devices is located within sensor range of the target location;
wherein:
the sensors of each digital device in the set of digital devices are configured to generate a data stream comprising situational data that pertains to the target location;
each digital device in the set of digital devices is configured to transmit, to at least a plurality selected from the other digital devices in the set of digital devices, the data stream generated by said each digital device;
the processor of each of the plurality of digital devices is configured to conglomerate the data stream generated by the sensor of said each digital device with the data streams received from the other digital devices, to create a conglomerated data stream, and each of the plurality of digital devices is configured to store a copy of the conglomerated data stream;
the processor of each of the plurality of digital devices is configured to independently monitor the conglomerated data stream for one of the event profiles; and
when a consensus is determined that one of the event profiles is detected, the system is configured to execute, via one or more of the digital devices, a predetermined response to the one of the event profiles.

### Claim 11 (depends on 10)

The system of claim 10, wherein at least one of the event profiles comprises data associated with a pattern of activity, said pattern which indicates that:
a piece of equipment in the target location is in a condition of reduced operability; or
an emergency situation occurred at the target location.

### Claim 12 (depends on 11)

The system of claim 11, wherein the piece of equipment is:
an automated teller machine (“ATM”) or a furniture item; and
the situational data includes:
a number of people who use the piece of equipment;
a period of time over which the piece of equipment was used;
visual evidence of decay in the piece of equipment; and/or
a threshold change in a user interaction with the piece of equipment.

### Claim 13 (depends on 12)

The system of claim 12, wherein the threshold change in user interaction comprises a threshold increase and/or decrease in a size of a queue of users waiting to operate the piece of equipment.

### Claim 14 (depends on 10)

The system of claim 10, wherein the set of devices comprises a specialized set of devices installed at the target location for detecting situational data.

### Claim 15 (depends on 10)

The system of claim 10, wherein the set of devices comprises at least one privately-owned device, and the privately-owned device is configured to receive permission for the accessing from an owner of said privately-owned device, and the permission is received:
in response to a message that is transmitted to the privately-owned device, said transmission that is triggered when the privately-owned device enters the sensor range of the target location; or
in response, at least in part, to the owner opting-in to a default permission setting on the privately-owned device, wherein opting-in to the default permission triggers the accessing when the privately-owned device enters the sensor range of the target location.

### Claim 16 (depends on 10)

The system of claim 10, wherein the consensus is a majority consensus, said majority consensus comprising a scenario in which at least a half of the plurality of digital devices determine that the event profile was detected.

### Claim 17

A computer-based method for invoking a situational response associated with a malfunction of a physical asset, said invoking being executed via a set of digital devices at a network edge, the method comprising:
generating a database of event profiles, each event profile comprising data associated with a pattern of activity, said pattern that indicates that the asset is compromised;
accessing the set of digital devices, wherein:
each digital device from the set of digital devices comprises a processor, a memory, a sensor, and a communication element for communicating with other digital devices and/or a centralized server; and
the set of digital devices is located within sensor range of the asset;
generating, via the sensors of each digital device in the set of digital devices, a data stream comprising situational data that pertains to the asset;
transmitting, from each digital device in the set of digital devices to all the other digital devices in the set of digital devices, the data stream generated by said each digital device;
conglomerating, via the processor of each digital device in the set of digital devices, the data stream generated by the sensor of said each digital device with the data streams received from the other digital devices in the set of digital devices, to create a conglomerated data stream, and each digital device in the set of digital devices stores a copy of the conglomerated data stream;
monitoring the conglomerated data stream for one of the event profiles, said monitoring performed independently, via the processors of each digital device in the set of digital devices; and
when a consensus is determined that one of the event profiles is detected, executing, via one or more of the digital devices, a predetermined response to the one of the event profiles.

### Claim 18 (depends on 17)

The method of claim 17, wherein the asset is:
an automated teller machine (“ATM”) or a furniture item; and
the situational data comprises:
a number of people who use the asset;
a period of time over which the asset was used;
visual evidence of decay in the asset; and/or
a threshold change in user interaction with the asset, said change in interaction comprising a threshold increase and/or decrease in a size of a queue of users waiting to operate the asset.

### Claim 19 (depends on 17)

The method of claim 17, wherein the set of devices comprises a specialized set of devices installed proximal to the asset for detecting situational data.

### Claim 20 (depends on 17)

The method of claim 17, wherein the set of devices comprises at least one privately-owned device, and the privately-owned device is configured to receive permission for the accessing from an owner of said privately-owned device, and the permission is received:
in response to a message that is transmitted to the privately-owned device, said transmission that is triggered when the privately-owned device enters within sensor range of the asset; or
in response, at least in part, to the owner opting-in to a default permission setting on the privately-owned device, wherein opting-in to the default permission triggers the accessing when the privately-owned device enters the sensor range of the target location.
