US-20260127957-A1 - LEVERAGING A LARGE LANGUAGE MODEL FOR UNIVERSAL DISPATCH MESSAGING

US20260127957A1US 20260127957 A1US20260127957 A1US 20260127957A1US-20260127957-A1

Abstract

Embodiments of leveraging a large language model (LLM) for universal dispatch messaging is described. A computer aided dispatch (CAD) message describing an event is received from a dispatch service of a plurality of dispatch services. The CAD message is in a first format, and at least some of the plurality of dispatch services generate CAD messages that are in a different format. The LLM is prompted to generate a structured message from the CAD message. The LLM may be prompted, based in part on the CAD message, to generate announcement text. An event record is stored that includes the structured message and may also include the announcement text. User devices are identified that are associated with users based in part on content of the structured message. Alerts are provided of the event to the user devices based in part on the structured message and user preferences of the users.

Inventors

Richard Walker
Thomas Alva Sharp, III
Beck Everett Mitchell
James Andrew Ballance

Assignees

Tango Tango, Inc.

Dates

Publication Date: 20260507
Application Date: 20241105

Claims (20)

1 . A method, performed at a computer system comprising a processor and a computer-readable medium, comprising: receiving, from a dispatch service of a plurality of dispatch services, a computer aided dispatch (CAD) message describing an event and the CAD message is in a first format, where at least some of the plurality of dispatch services generate CAD messages that are in a format other than the first format; prompting a large language model to generate a structured message from the CAD message in the first format; prompting the large language model to generate announcement text, wherein the announcement text is based in part on the CAD message; storing an event record that includes the structured message and the announcement text; identifying user devices that are associated with users based in part on content of the structured message; and providing alerts of the event to the user devices based in part on the structured message and user preferences of the users.
2 . The method of claim 1 , further comprising: extracting a street address from the structured message; converting the street address to geographic coordinates; and updating the structured message with geographic coordinates.
3 . The method of claim 1 , further comprising: prompting the large language model to determine a priority level based in part on the structured message; and updating the structured message with the priority level.
4 . The method of claim 1 , wherein prompting the large language model to generate the structured message from the CAD message in the first format, further comprises: prompting the large language model to generate a title for the structured message using the CAD message.
5 . The method of claim 1 , further comprising: determining that the CAD message is an update to a previously received CAD message using an identifier in the structured message; linking the event record to an event record associated with the previously received CAD message; and prior to providing the alerts of the event to the user devices, updating the alerts to indicate that the structured message is an update to a previous structured message, wherein the previous structured message is associated with the previously received CAD message.
6 . The method of claim 1 , further comprises: converting the announcement text to audio data that corresponds to the announcement text, wherein providing the alerts of the event to the user devices associated with users based in part on the structured message and user preferences for the users, further comprises: determining a user preference for a user of a user device of the user devices, to have alerts sent to the user device via a wireless broadcast, wherein the audio data is provided to the user device via a wireless broadcast.
7 . The method of claim 1 , wherein prompting the large language model to generate the announcement text, comprises: prompting the large language model to generate the announcement text using the structured message.
8 . The method of claim 1 , wherein prompting the large language model to generate the announcement text, comprises: prompting the large language model to generate announcement text using the CAD message.
9 . The method of claim 8 , wherein prompting the large language model to generate announcement text using the CAD message is performed in parallel with prompting the large language model to generate the structured message from the CAD message in the first format.
10 . The method of claim 1 , further comprising: providing a user interface to a user device, of the user devices, the user interface presenting one or more alerts that have been provided to the user device; receiving, from the user device, a selection of an alert of the one or more alerts; retrieving an event record based in part on the selection; and presenting based in part on the event record, information from the alert, a CAD message associated with the alert, and an option to provide feedback regarding the alert.
11 . The method of claim 1 , further comprising: generating a prompt using the CAD message, instructions to generate the structured message from the CAD message, and contextual information, wherein the contextual information includes at least one specific training example approved by a user associated with a user device of the user devices.
12 . The method of claim 1 , wherein the dispatch service provides the CAD message to a set of user devices that are associated with users, and providing the alerts of the event to the user devices based in part on the structured message and user preferences of the users comprises: providing an alert to a user device that is associated with a user who is not one of the users associated with the set of user devices.
13 . A computer program product comprising a non-transitory computer readable storage medium having instructions encoded thereon that, when executed by a processor of a computer system, cause the computer system to perform steps comprising: receiving, from a dispatch service of a plurality of dispatch services, a computer aided dispatch (CAD) message describing an event and the CAD message is in a first format, where at least some of the plurality of dispatch services generate CAD messages that are in a format other than the first format; prompting a large language model to generate a structured message from the CAD message in the first format; identifying user devices that are associated with users based in part on content of the structured message; and providing alerts of the event to the user devices based in part on the structured message and user preferences of the users.
14 . The computer program product of claim 13 , further comprising encoded instructions that when executed cause the computer system to perform steps comprising: extracting a street address from the structured message; converting the street address to geographic coordinates; and updating the structured message with geographic coordinates.
15 . The computer program product of claim 13 , further comprising encoded instructions that when executed cause the computer system to perform steps comprising: prompting the large language model to determine a priority level based in part on the structured message; and updating the structured message with the priority level, wherein the encoded instructions for providing the alerts of the event to the user devices based in part on the structured message and the user preferences for the users cause the computer system to perform steps comprising: providing the alerts of the event to the user devices based in part on the structured message, the user preferences for the users, and the priority level.
16 . The computer program product of claim 13 , wherein the encoded instructions for prompting the large language model to generate the structured message from the CAD message in the first format cause the computer system to perform steps comprising: prompting the large language model to generate a title for the structured message using the CAD message.
17 . The computer program product of claim 13 , further comprising encoded instructions that when executed cause the computer system to perform steps comprising: prompting the large language model to generate announcement text, wherein the announcement text is based in part on the CAD message; and converting the announcement text to audio data that corresponds to the announcement text, wherein the encoded instructions for providing the alerts of the event to the user devices associated with users based in part on the structured message and user preferences for the users cause the computer system to perform steps comprising: determining a user preference for a user of a user device of the user devices, to have alerts sent to the user device via a wireless broadcast, wherein the audio data is provided to the user device via a wireless broadcast.
18 . The computer program product of claim 17 , wherein the encoded instructions for prompting the large language model to generate the announcement text cause the computer system to perform steps comprising: prompting the large language model to generate the announcement text using the structured message.
19 . The computer program product of claim 13 , wherein the dispatch service provides the CAD message to a set of user devices that are associated with users, and the encoded instructions for providing the alerts of the event to the user devices based in part on the structured message and user preferences of the users cause the computer system to perform steps comprising: providing an alert to a user device that is associated with a user who is not one of the users associated with the set of user devices.
20 . A computer system comprising: a processor; and a non-transitory computer readable storage medium having instructions encoded thereon that, when executed by the processor, cause the computer system to perform steps comprising: receiving, from a dispatch service of a plurality of dispatch services, a computer aided dispatch (CAD) message describing an event and the CAD message is in a first format, where at least some of the plurality of dispatch services generate CAD messages that are in a format other than the first format, prompting a large language model to generate a structured message from the CAD message in the first format, identifying user devices that are associated with users based in part on content of the structured message, and providing alerts of the event to the user devices based in part on the structured message and user preferences of the users.

Description

FIELD OF THE INVENTION The disclosure relates generally to computer aided dispatch, and more specifically to leveraging a large language model for universal dispatch messaging. BACKGROUND Many entities (e.g., fire departments, police departments, government agencies, etc.) receive notification of events via their own respective dispatch service. These notifications may also dispatch units (e.g., ambulance, fire truck, etc.) to handle the events. Each dispatch service generally reports events that are material (e.g., within a region of responsibility of an entity) to its entity(ies) via computer aided dispatch (CAD) messages. However, different dispatch services generally are closed systems that generate CAD messages in different formats and have different means of presentation. Moreover, the ability to receive CAD messages is often limited by the computing platform in which they are hosted (e.g., a WINDOWS system), and CAD messages are designed to be consumed by clients using a particular platform (e.g., WINDOWS system). For example, a first application is used to view CAD messages from a first dispatch service and a second application is used to view CAD messages from a second dispatch service. But, as the first CAD messages have a different format than the second CAD application, generally the second application cannot be used to view CAD messages from the first dispatch service, and vice versa. As such, a user wanting to access messages from different dispatch services may have to use a different means for each dispatch service. This can be particularly problematic when users of a particular entity need to have access to CAD messages coming from a dispatch service of another entity. Conventionally, there are messaging forwarding systems that an entity can use to make their messages available to other types of clients used by their users. These message forwarding systems generally maintain separate, strict parsers for each possible CAD input format. However, there are many (e.g., hundreds) different formats for CAD messages and input formats generally vary across all CAD users. Accordingly, it is very labor intensive for message forwarding systems to keep parsers up to date for each possible format. Moreover, because of this, message forwarding systems tend to produce erroneous messages responsive to receiving CAD messages in unexpected (e.g., a variation on an existing format or a new format) formats. SUMMARY In accordance with one or more aspects of the disclosure, leveraging a large language for universal dispatch messaging is described. A universal dispatch system receives computer aided dispatch (CAD) messages from a plurality of dispatch services (e.g., associated with different entities). Some or all of the received CAD messages are in different formats from each other. Responsive to receiving a CAD message describing an event, the universal dispatch system uses the large language model to generate a structured message. The structured message organizes information from the CAD message in a standardized structured form. For example, the structured message may be in a JavaScript Object Notation (JSON) format, an extensible markup language (XML) format, yet another markup language (YAML) format, etc. The universal dispatch system may also use the large language model to generate announcement text using the structured message and/or the CAD message. The universal dispatch system may store (e.g., in a data store) an event record that includes the structured message and the announcement text in a data store. The universal dispatch system identifies user devices that are associated with users for notification based in part on content of the structured message. The universal dispatch system provides alerts of the event to the user devices based in part on the structured message and user preferences for the users. In the above manner, a user device can receive information about the event from the universal dispatch system, even though it is part of an entity that is not associated with the dispatch service. Moreover, the universal dispatch system may be used in lieu of or in addition to the dispatch service to provide information (alerts) to user devices of users that are to respond (or have responded) to the event. The universal dispatch system also uses a large language model to generate structured messages from CAD messages instead of parsers for each possible CAD message format. Additionally, to the extent a new CAD message format may result in inaccuracies in the structured message (or announcement text), prompts to the large language model may be easily modified to handle the new format (versus having to build a new parser, and then maintain the parser going forward). BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 illustrates an example system environment for a universal dispatch system, in accordance with one or more embodiments. FIG. 2 illustrates an example system architecture for a universal dispatch sy