Enabling smart communication networks using asset information in a supply chain environment

1. A method, comprising:

obtaining sensor data collected from a tracking device associated with an asset;

determining, based at least in part on the sensor data, that an adverse event occurred in connection with the asset;

providing an indication of the adverse event to a communications system;

submitting, by the communications system, a request to an intelligence engine to determine target users for the adverse event;

identifying, by a machine-learning (ML) model of the intelligence engine and based at least in part on the sensor data, a user of the communications system, wherein the ML model is used to determine that the adverse event is relevant to the user;

establishing, by the communications system, a smart communications group associated with the asset, wherein the smart communications group comprises two or more users comprising the user;

determining, by the communications system, user interactions between the two or more users of the smart communications group;

obtaining additional sensor data collected from the tracking device associated with the asset;

determining, based at least in part on the additional sensor data, resolution of the adverse event; and

updating the ML model based at least in part on the user interactions.

2. The method of claim 1 , further comprising:

obtaining historical user interaction data;

obtaining historical event data; and

training the (ML) model based at least in part on the historical user interaction data and the historical event data.

3. The method of claim 2 , wherein:

the identification of the user is based at least in part on determining co-occurrences of the historical user interaction data with the historical event data similar to the adverse event.

4. The method of claim 1 , wherein the user interactions comprise the user manually adding an additional user to the smart communications group.

5. The method of claim 1 , wherein the user interactions comprise the user manually leaving the smart communications group.

6. The method of claim 1 , further comprising:

determining a first preferred mode of communication for the user;

determining a second preferred mode of communication for a second user of the two or more users; and

establishing the smart communications group using the first preferred mode of communication for the user and the second preferred mode of communication for the second user.

7. The method of claim 1 , further comprising:

providing, to the smart communications group, an indication of the adverse event associated with the asset.

8. The method of claim 1 , further comprising:

training the ML model to predict whether users are likely to perform respective user interactions based at least in part on asset states.

9. The method of claim 8 , wherein the training is based at least in part on user interaction data and event data, and wherein the training comprises training the ML model to identify co-occurrences of the user interaction data the event data to identify whether a respective event is relevant to a respective user.

10. The method of claim 8 , wherein the training comprises training the ML model to detect trends and patterns between assets and asset states, and relevance of events to respective users.

11. A system, comprising:

at least one processor; and

at least one memory storing computer-executable instructions, that when executed by the at least one processor, cause the at least one processor to:

obtain sensor data collected from a tracking device associated with an asset;

determine, based at least in part on the sensor data, that an adverse event occurred in connection with the asset;

provide an indication of the adverse event to a communications system;

submit, by the communications system, a request to an intelligence engine to determine target users for the adverse event;

identify, by a machine-learning (ML) model of the intelligence engine and based at least in part on the sensor data, a user of the communications system, wherein the ML model is used to determine that the adverse event is relevant to the user;

establish, by the communications system, a smart communications group associated with the asset, wherein the smart communications group comprises two or more users comprising the user;

determine, by the communications system, user interactions between the two or more users of the smart communications group;

obtain additional sensor data collected from the tracking device associated with the asset;

determine, based at least in part on the additional sensor data, resolution of the adverse event; and

update the ML model based at least in part on the user interactions.

12. The system of claim 11 , wherein the two or more users include a second user, and the at least one processor is further configured to:

determine a first preferred mode of communication for the user;

determine a second preferred mode of communication for the second user; and

establish the smart communications group using the first preferred mode of communication for the user and the second preferred mode of communication for the second user.

13. The system of claim 11 , wherein the two or more users are downstream users of a flow associated with the asset.

14. The system of claim 11 , wherein the instructions further cause the at least one processor to:

train the ML model to predict whether users are likely to perform respective user interactions based at least in part on asset states.

15. The system of claim 14 , wherein the training is based at least in part on user interaction data and event data, and wherein the training comprises training the ML model to identify co-occurrences of the user interaction data and the event data to identify whether a respective event is relevant to a respective user.

16. The system of claim 14 , wherein the training comprises training the ML model to detect trends and patterns between assets and asset states, and relevance of events to respective users.

17. A non-transitory computer-readable medium including computer-executable instructions stored thereon, which when executed by at least one processor, cause the at least one processor to:

obtain sensor data collected from a tracking device associated with an asset;

determine, based at least in part on the sensor data, that an adverse event occurred in connection with the asset;

provide an indication of the adverse event to a communications system;

submit, by the communications system, a request to an intelligence engine to determine target users for the adverse event;

identify, by a machine-learning (ML) model of the intelligence engine and based at least in part on the sensor data, a user of the communications system, wherein the ML model is used to determine that the adverse event is relevant to the user;

establish, by the communications system, a smart communications group associated with the asset, wherein the smart communications group comprises two or more users comprising the user;

determine, by the communications system, a user interactions between the two or more users of the smart communications group;

obtain additional sensor data collected from the tracking device associated with the asset;

determine, based at least in part on the additional sensor data, resolution of the adverse event; and

update the ML model based at least in part on the user interactions.

18. The non-transitory computer-readable medium of claim 17 , wherein the two or more users includes a second user, and the instructions further cause the at least one processor to:

determine a first preferred mode of communication for the user;

determine a second preferred mode of communication for the second user; and

establish the smart communications group using the first preferred mode of communication for the user and the second preferred mode of communication for the second user.

19. The non-transitory computer-readable medium of claim 17 , wherein the two or more users are downstream users of a flow associated with the asset.

20. The non-transitory computer-readable medium of claim 17 , wherein the sensor data is collected as real-time event data.