Systems to infer identities of persons of interest rapidly and alert first responders

    公开(公告)号:US11600168B1

    公开(公告)日:2023-03-07

    申请号:US17444757

    申请日:2021-08-10

    Abstract: Systems, devices, and technical methods of the present disclosure leverage digital visitor logs from confinement facilities to identify people of interest that may be involved in incidents to which first responders are dispatched. When a phone call is received at phone public safety access point, a first query including a name associated with the call is transmitted to a digital visitor log for a confinement facility. A digital response to the first query identifies a visitee who was visited by a visitor by that name while the visitee was in confinement. The visitee's name is then transmitted in a second query to a digital repository containing release records; a digital response indicates the visitee was released before the call was received. An electronic notification that identifies the visitee is transmitted to a device associated with an agent who is responding to the call.

    METHOD AND SYSTEM FOR FACILITATING IMPROVED TRAINING OF A SUPERVISED MACHINE LEARNING PROCESS

    公开(公告)号:US20210089833A1

    公开(公告)日:2021-03-25

    申请号:US16581110

    申请日:2019-09-24

    Abstract: Methods, systems, and techniques for facilitating improved training of a supervised machine learning process, such as a decision tree. First and second object detections of an object depicted in a video are respectively generated using first and second object detectors, with the second object detector requiring more computational resources than the first object detector to detect the object. Whether a similarity and a difference between the first and second object detections respectively satisfy a similarity threshold and a difference threshold is determined. When the similarity threshold is satisfied, the first object detection is stored as a positive example for the machine learning training. When the difference threshold is satisfied, the first object detection is stored as a negative example for the machine learning training.

    Method and system for facilitating improved training of a supervised machine learning process

    公开(公告)号:US10997469B2

    公开(公告)日:2021-05-04

    申请号:US16581110

    申请日:2019-09-24

    Abstract: Methods, systems, and techniques for facilitating improved training of a supervised machine learning process, such as a decision tree. First and second object detections of an object depicted in a video are respectively generated using first and second object detectors, with the second object detector requiring more computational resources than the first object detector to detect the object. Whether a similarity and a difference between the first and second object detections respectively satisfy a similarity threshold and a difference threshold is determined. When the similarity threshold is satisfied, the first object detection is stored as a positive example for the machine learning training. When the difference threshold is satisfied, the first object detection is stored as a negative example for the machine learning training.

    Systems and methods for detecting anomalies in geographic areas

    公开(公告)号:US11164438B2

    公开(公告)日:2021-11-02

    申请号:US16837781

    申请日:2020-04-01

    Abstract: Methods for detecting anomalies in a geographic area include receiving, from an electronic computing device, expected relationship data indicating expected relationships between a plurality of entities within the geographic area; detecting the plurality of entities within the geographic area; generating observed relationship data indicating observed relationships between the plurality of entities; identifying the expected relationships between the plurality of entities based on the expected relationship data; determining that a given observed relationship between two entities of the plurality of entities is likely to represent an anomaly based on the expected relationship data; and providing an electronic notification to a safety officer, the electronic notification indicating that the given observed relationship is likely to represent the anomaly.

Patent Agency Ranking