US-12621214-B1 - Method and system for managing electronic data representing anomalous emergency alerts

Abstract

A system for managing electronic data representing emergency alerts comprises a computing device associated with an asset and a server. The server receives threshold data from the computing device and one or more data records representing reports of an event. The server computes an anomaly metric based on a comparison of the event to recent events and, if the anomaly metric does not exceed a threshold, computes a trend metric based on the frequency of similar events over time. If either metric exceeds its respective threshold, the server transmits a control signal comprising an alert to the computing device. The system may apply natural language processing, machine learning, and knowledge graphs to evaluate event characteristics and generate contextual summaries. By filtering alerts based on relevance and context, the system conserves computing resources and enables early detection of emerging threats, improving the responsiveness and efficiency of emergency alert infrastructure.

Inventors

• James Andrew NEUFELD
• Dan McEleney
• Sean Mark SOLBAK

Assignees

• SAMDESK CANADA INC.

Dates

Publication Date

20260505

Application Date

20251120

Claims (17)

1. 1 . A system for managing electronic data representing emergency alerts, the system comprising a computing device associated with an asset and configured to transmit threshold data; and a server configured to: receive the threshold data from the computing device; receive from a media server, one or more data records representing reports of an event; generate a control signal representing the one or more data records, the control signal comprising an alert; compute an anomaly metric representing a degree of similarity between the event and recent events by comparing characteristics of the event to characteristics of recent events stored in an event database; if the anomaly metric does not exceed an anomaly threshold included in the threshold data: retrieve similar recent events from among the recent events and similar historical events from historical events in the event database; and compute a trend metric for the event by comparing the similar recent events to the similar historical events; and if the anomaly metric exceeds the anomaly threshold or the trend metric exceeds a trend threshold included in the threshold data, transmit the control signal to the computing device.
2. 2 . The system of claim 1 wherein the control signal directs the computing device to activate a navigation system.
3. 3 . The system of claim 1 wherein the control signal directs the computing device to control a logistics system.
4. 4 . The system of claim 1 wherein the control signal directs the computing device to control an automated email system.
5. 5 . The system of claim 1 wherein the control signal directs the computing device to control a small message service system.
6. 6 . The system of claim 1 further comprising a plurality of devices for receiving alerts, wherein the server is configured to transmit the alert to the plurality of devices if the anomaly metric exceeds a global anomaly threshold or the trend metric exceeds a global trend threshold.
7. 7 . The system of claim 1 wherein the server is further configured to apply natural language processing and a machine learning algorithm to the plurality of data records to compute the anomaly metric.
8. 8 . The system of claim 1 wherein the server is further configured to apply natural language processing and knowledge graphs to the one or more data records to compute the trend metric.
9. 9 . The system of claim 1 wherein the server is further configured to apply a machine learning algorithm to generate a written summary of the event characteristics contributing to the anomaly metric, and wherein the alert includes the written summary.
10. 10 . The system of claim 1 wherein the server is further configured to: receive from the media server, a plurality of data records representing a plurality of events; and generate the control signal representing the plurality of data records.
11. 11 . A system for managing electronic records representing travel alerts, the system comprising: a computing device associated with an asset and configured to transmit itinerary data and threshold data; and a server configured to: receive the itinerary data and the threshold data from the computing device; retrieve event records from an event database, the event records representing reports of events; generate a control signal representing the event records, the control signal comprising travel alerts corresponding to the event records; and for each of the travel alerts, calculate an impact metric based on the itinerary data, the impact metric representing a predicted impact of the event on the asset; if the impact metric meets an impact threshold from the threshold data, transmit the control signal including the respective travel alert to the computing device; and if the impact metric does not meet the impact threshold, transmit the control signal excluding the respective travel alert to the computing device.
12. 12 . The system of claim 11 wherein the control signal directs the computing device to control a logistics system to regenerate the itinerary data.
13. 13 . The system of claim 11 wherein, for each of the travel alerts, the server is further configured to: retrieve similar recent events from among recent events stored in the event database and retrieve similar historical events from historical events in the event database; compute an anomaly metric representing a degree of similarity between the event record and recent events by comparing characteristics of the event record to characteristics of recent events stored in the event database; if the anomaly metric does not exceed an anomaly threshold included in the threshold data: retrieve similar recent events from among the recent events and similar historical events from historical events in the event database; and compute a trend metric for the event record by comparing the similar recent events to the similar historical events; and if the anomaly metric exceeds the anomaly threshold or the trend metric exceeds a trend threshold included in the threshold data, transmit the control signal including the respective travel alert.
14. 14 . The system of claim 13 wherein the itinerary data includes asset attributes representing one or more characteristics of the asset.
15. 15 . The system of claim 14 , wherein the itinerary data includes a travel location, and wherein the server is further configured to retrieve destination data from the memory, the destination data representing characteristics of the travel location.
16. 16 . The system of claim 15 , wherein the itinerary data includes a travel date, the server further configured to transmit the control signal to the computing device at a predetermined date prior to the travel date.
17. 17 . The system of claim 16 , wherein the server is further configured to generate an updated control signal in response to receiving further event records.

Description

FIELD The present specification is directed to computer-networking communications and more specifically, computer networking involving the management of electronic data representing emergency alerts. BACKGROUND The widespread availability of electronic communications, such as social media posts, news articles, and government reports has enabled real-time reporting of events such as fires, shootings, and protests. Systems have been developed to aggregate and process such information and to notify users of incidents. For example, U.S. Pat. No. 10,750,346 describes a platform that collects data from mobile devices, video feeds, and social media to identify and classify emergency events, however these types of systems can generate excessive notifications, including for routine or low-priority events. This can lead to inefficient use of computing resources, including unnecessary consumption of device memory, network bandwidth, and server capacity. SUMMARY An aspect of the specification provides a system for managing electronic data representing emergency alerts. The system includes a computing device associated with an asset and configured to transmit threshold data. The system also includes a server configured to receive the threshold data from the computing device and to receive, from a media server, one or more data records representing reports of an event. The server is configured to generate a control signal representing the one or more data records, where the control signal includes an alert. The server is further configured to compute an anomaly metric representing a degree of similarity between the event and recent events by comparing characteristics of the event to characteristics of recent events stored in an event database. If the anomaly metric does not exceed an anomaly threshold included in the threshold data, the server retrieves similar recent events from among the recent events and similar historical events from historical events in the event database and computes a trend metric for the event by comparing the similar recent events to the similar historical events. If the anomaly metric exceeds the anomaly threshold or the trend metric exceeds a trend threshold included in the threshold data, the server transmits the control signal to the computing device. In one example, the control signal directs the computing device to activate a navigation system. In another example, the control signal directs the computing device to control a logistics system. In a further example, the control signal directs the computing device to control an automated email system. In a yet further example, the control signal directs the computing device to control a small message service system. In one example, the system includes a plurality of devices for receiving alerts, and the server is configured to transmit the alert to the plurality of devices if the anomaly metric exceeds a global anomaly threshold or the trend metric exceeds a global trend threshold. In another example, the server is configured to apply natural language processing and a machine learning algorithm to the one or more data records to compute the anomaly metric. In a further example, the server is configured to apply natural language processing and knowledge graphs to the one or more data records to compute the trend metric. In a yet further example, the server is configured to apply a machine learning algorithm to generate a written summary of the event characteristics contributing to the anomaly metric, and the alert includes the written summary. In one example, the server is further configured to receive from the media server a plurality of data records representing a plurality of events and to generate the control signal representing the plurality of data records. A further aspect of the specification provides a system for managing electronic data representing emergency alerts. The system includes a computing device associated with an asset and configured to transmit threshold data and a server configured to receive the threshold data and one or more media records from a media server. The server is configured to generate a control signal including an alert and compute an anomaly metric representing a degree of similarity between the event and recent events. If the anomaly metric exceeds the anomaly threshold, the server transmits the control signal to the computing device. In one example, the control signal directs the computing device to activate a navigation system. In a further example, the control signal directs the computing device to control a logistics system. In a yet further example, the control signal directs the computing device to control an automated email system. In another example, the control signal directs the computing device to control a small message service system. In one example, the system includes a plurality of devices for receiving alerts, and the server is configured to transmit the alert to the plurality of devices if