# US 2026/0075167 A1 · Reducing information loss via vector encoding, and related systems, devices, units, and methods

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

- Number: US 2026/0075167 A1
- Document ID: US20260075167A1
- Status: Published application
- Kind: A1
- Application number: 19/326,847
- Filed: 2025-09-12
- Published: 2026-03-12
- Earliest claimed: 2024-09-12
- Assignees: LiveView Technologies, LLC
- Applicants: LiveView Technologies, LLC
- Inventors: Michael N. Abbott; Ilya Reznik
- Web page: https://patentgrep.com/patent/US20260075167A1

## CPC

- H04N 7/183: {for receiving images from a single remote source}
- G06V 10/70: using pattern recognition or machine learning (optical pattern recognition or electronic computations therefor G06V10/88)
- G06V 10/82: using neural networks
- G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69)
- G06V 20/70: Labelling scene content, e.g. deriving syntactic or semantic representations
- G06V 40/10: Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V 2201/08: Detecting or categorising vehicles
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

Various embodiments relate to systems including a surveillance unit. A system may include a surveillance unit comprising at least one camera for capturing data including one or more objects. The surveillance unit may also include a first model for generating at least one vector representation based on the one or more objects of the captured data. The system may also include a server communicatively coupled to the surveillance unit including a second model to receive the at least one vector representation and generate output data based on the at least one vector representation. The surveillance unit may further be configured to receive the output data and convey, via at least one output device, an output based on the output data. Associated methods are also disclosed.

## Claims

### Claim 1

A system including a surveillance unit, comprising:
a surveillance unit comprising:
at least one camera for capturing data including one or more objects; and
a first model for generating at least one vector representation based on the one or more objects of the captured data; and
a server communicatively coupled to the surveillance unit and including a second model to:
receive the at least one vector representation; and
generate output data based on the at least one vector representation;
the surveillance unit configured to receive the output data from the server and convey, via at least one output device, an output based on the output data.

### Claim 2 (depends on 1)

The system of claim 1, wherein the first model comprises an encoder model and the second model comprises a generative transformer model.

### Claim 3 (depends on 1)

The system of claim 1, wherein the at least one output device comprises a speaker and the output comprises at least an audio message.

### Claim 4 (depends on 1)

The system of claim 1, wherein the output data comprises one or more of a text file or an audio file.

### Claim 5 (depends on 4)

The system of claim 4, wherein the data comprises one or more of image data or video data.

### Claim 6 (depends on 1)

The system of claim 1, wherein the surveillance unit further comprises an analytics pipeline configured to receive an output from the at least one camera and convey at least one of image data, video data, or metadata to the first model.

### Claim 7 (depends on 1)

The system of claim 1, wherein the second model comprises a large language model (LLM).

### Claim 8 (depends on 1)

The system of claim 1, wherein the first model generates at least one vector representation response to receipt of at least one of image data, video data, or metadata associated with the captured data.

### Claim 9

A system, comprising:
a surveillance unit comprising:
at least one camera for capturing data including one or more objects;
a model for generating metadata associated with at least one object of the one or more objects; and
a communication device to:
send the metadata to a remote device; and
receive response data from the remote device, wherein the response data is based on the metadata; and
an output device for conveying a response based on the response data.

### Claim 10 (depends on 9)

The system of claim 9, wherein the metadata comprises at least one vector representation of the one or more objects.

### Claim 11 (depends on 9)

The system of claim 9, wherein:
the response data comprises at least one of text data or audio data;
the output device comprises a speaker; and
the response comprises an audio message.

### Claim 12 (depends on 9)

The system of claim 9, further comprising the remote device, wherein the remote device comprises a cloud server.

### Claim 13 (depends on 9)

The system of claim 9, wherein a cloud server comprises a large language model (LLM) for generating the response data.

### Claim 14 (depends on 9)

The system of claim 9, wherein the model comprises an encoder model.

### Claim 15

A method of operating a system including a surveillance unit, the method comprising:
capturing data including one or more objects via at least input device of the surveillance unit;
generating at least one vector representation of the one or more objects;
conveying the at least one vector representation from the surveillance unit to a remote device;
receiving, at the surveillance unit, response data from the remote device; and
conveying, via an output device of the surveillance unit, a response based on the response data.

### Claim 16 (depends on 15)

The method of claim 15, wherein conveying the response comprises conveying an audio message via a speaker of the surveillance unit.

### Claim 17 (depends on 15)

The method of claim 15, wherein generating the at least one vector representation comprises generating the at least one vector representation via an encoder model at the surveillance unit.

### Claim 18 (depends on 15)

The method of claim 15, further comprising generating the response data via a generative transformer model at a cloud server remote from the surveillance unit.

### Claim 19 (depends on 15)

The method of claim 15, wherein capturing the data comprises capturing at least one of a video or an image via at least one camera of the surveillance unit.

### Claim 20 (depends on 15)

The method of claim 15, wherein generating the at least one vector representation comprises generating the at least one vector representation via an encoder model at the surveillance unit.
