# US 12,118,085 B2 · Systems and methods for machine learning enhanced intelligent building access endpoint security monitoring and management

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

- Number: US 12,118,085 B2
- Document ID: US12118085B2
- Status: Granted
- Kind: B2
- Application number: 18/370,523
- Filed: 2023-09-20
- Published: 2024-01-11
- Granted: 2024-10-15
- Earliest claimed: 2018-12-21
- Assignees: Ambient AI, Inc.
- Applicants: Ambient AI, Inc.
- Inventors: Shikhar Shrestha; Vikesh Khanna; James Douglas Connor
- Web page: https://patentgrep.com/patent/US12118085B2

## CPC

- G06F 21/554: {involving event detection and direct action}
- G06F 18/21: Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F 18/2431: Multiple classes
- G06F 21/31: User authentication
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/09: Supervised learning
- G06N 3/092: Reinforcement learning
- G06N 5/04: Inference or reasoning models
- G06N 20/20: Ensemble learning
- G06V 10/25: Determination of region of interest [ROI] or a volume of interest [VOI]
- G06V 10/82: using neural networks
- G06V 20/41: {Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items (segmenting video sequences G06V20/49)}
- G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69)
- G06V 30/19173: {Classification techniques}
- G06V 30/274: {Syntactic or semantic context, e.g. balancing}
- G08B 13/19613: {Recognition of a predetermined image pattern or behaviour pattern indicating theft or intrusion}
- G08B 13/19671: {Addition of non-video data, i.e. metadata, to video stream}
- G08B 29/186: {Fuzzy logic; neural networks}
- G08B 29/188: {Data fusion; cooperative systems, e.g. voting among different detectors}
- H04N 7/18: Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N 23/90: Arrangement of cameras or camera modules, e.g. multiple cameras in TV studios or sports stadiums
- G06N 3/045: Combinations of networks
- G06Q 50/265: {Personal security, identity or safety}
- G06V 20/44: {Event detection}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G08B: SIGNALLING SYSTEMS, e.g. PERSONAL CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION
- 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

## Abstract

Systems and methods for correlating access-system primitives generated by an access control system and semantic primitives generated by a sensor data comprehension system.

## Claims

### Claim 1

A method, comprising:
determining a set of access primitives based on a first set of signals from an access point state sensor;
determining a set of authorization primitives based on a second set of signals from a security credentialing system;
determining a set of semantic primitives based on a third set of signals from a camera system;
determining a correlation between the set of access primitives, the set of semantic primitives, and the set of authorization primitives;
determining a context classification based on the correlation; and
based on the correlation, determining a security risk associated with the context classification.

### Claim 2 (depends on 1)

The method of claim 1, wherein the access point state sensor comprises a door sensor.

### Claim 3 (depends on 1)

The method of claim 1, wherein the context classification comprises tailgating.

### Claim 4 (depends on 1)

The method of claim 1, wherein the security risk is determined using probabilistic methods.

### Claim 5 (depends on 1)

The method of claim 1, wherein the security risk is determined using machine learning methods.

### Claim 6 (depends on 1)

The method of claim 1, further comprising performing a security action in response to determining the security risk.

### Claim 7

A system, comprising:
a processing system configured to:
determine a set of access primitives based on a first set of access signals from a sensor at an electronic access system;
determine a set of authorization primitives based on a second set of signals from a security credentialing system;
determine a set of semantic primitives based on a third set of signals from a camera system;
determine a correlation between the set of access primitives, the set of authorization primitives, and the set of semantic primitives;
determine a context classification based on the correlation; and
based on the correlation, determine a security risk associated with the context classification.

### Claim 8 (depends on 7)

The method of claim 7, wherein the sensor comprises a door sensor.

### Claim 9 (depends on 1)

The method of claim 1, wherein the security credentialing system comprises an access credential input device at the electronic access system.

### Claim 10 (depends on 7)

The method of claim 7, wherein the context classification comprises as at least one of a valid security event or a false security event.

### Claim 11 (depends on 10)

The method of claim 10, wherein the security risk is presented at a user interface when the context classification comprises a valid security event.

### Claim 12 (depends on 10)

The method of claim 10, wherein the security risk comprises at least one of a door held open event or a door forced open event.

### Claim 13 (depends on 10)

The method of claim 10, wherein a false security event comprises a malfunction associated with the electronic access system.

### Claim 14 (depends on 7)

The method of claim 7, wherein the processing system is remote from the camera system.

### Claim 15

A method, comprising:
determining a set of access primitives based on a first set of signals from an electronic access system;
determining a set of semantic primitives based on a second set of signals from a camera system, wherein the semantic primitives identify a tailgater accessing an access point;
determining a correlation between the set of access primitives and the set of semantic primitives;
determining a context classification based on the correlation; and
based on the correlation, determining a security risk associated with the context classification, wherein the security risk comprises tailgating.

### Claim 16 (depends on 15)

The method of claim 15, wherein the electronic access system comprises a security credentialing system, wherein the access primitives identify that a valid access credential for the tailgater is not detected.

### Claim 17 (depends on 15)

The method of claim 15, wherein the electronic access system comprises an access point state sensor, wherein the access primitives identify the access point in an open state.

### Claim 18 (depends on 15)

The method of claim 15, wherein the security risk is determined in real-time.

### Claim 19 (depends on 15)

The method of claim 15, wherein the semantic primitives are determined using computer vision methods.