Message generation based on multichannel context
Example methods and systems provide a workplace assistant application that can detect one or more received messages associated with a remote user and access multiple communication channels connected to a workplace assistant client application. Received message(s), information from the channels, and stored metadata can be submitted to one or more predictive models to provide a context for the message(s). The system can generate, using output from the predictive model(s), a response message based at least in part on the context of the received message. The system can display the response in the workplace assistant client application for acceptance or editing by the user, or transmit the response message.
1. A method comprising:
detecting, at a workplace assistant client application on a client device, at least one received message associated with a remote user from among a plurality of remote users;
accessing a plurality of channels communicatively coupled to the workplace assistant client application;
submitting the at least one received message and additional information from the plurality of channels to predictive models to provide a multichannel context for the at least one received message;
generating, from the plurality of remote users, a who-is-looking list of remote users looking for a user of the client device, wherein the who-is-looking list is sorted by relevance based on the multichannel context;
generating, using output from the predictive models and the relevance, a response message based at least in part on the multichannel context of the received message;
displaying the who-is-looking list of remote users using the workplace assistant client application on the client device; and
displaying the response message using the workplace assistant client application on the client device.
2. The method of claim 1 , wherein the predictive models further comprises comprise a large language model, an intent detection model, and an urgency model.
3. The method of claim 2 , wherein submitting the at least one received message and additional information from the plurality of channels to the predictive models further comprises submitting the at least one received message and additional information over a network.
4. The method of claim 2 , wherein submitting the at least one received message and additional information from the plurality of channels to the predictive models further comprises submitting the at least one received message and additional information to at least one of the large language model, the intent detection model, or the urgency model on the client device.
5. The method of claim 4 , wherein the at least one of the large language model, the intent detection model, or the urgency model is configured for training in part using generic data and in part using secured user data stored in association with the workplace assistant client application on the client device.
6. The method of claim 1 , wherein the workplace assistant client application is configured to detect the at least one received message in any of the plurality of channels, and wherein the plurality of channels includes email, chat, and at least one teleconferencing channel.
7. The method of claim 1 , wherein the multichannel context is further based on metadata including mentions in stored documents and at least one of relationship, presence, group membership, active channels, or previous interactions.
8. A system comprising:
a processor; and
at least one memory device including instructions that are executable by the processor to cause the processor to:
detect, at a workplace assistant client application on a client device, at least one received message associated with a remote user from among a plurality of remote users;
access a plurality of channels communicatively coupled to the workplace assistant client application;
submit the at least one received message and additional information from the plurality of channels to predictive models to provide a multichannel context for the at least one received message;
generate, from the plurality of remote users, a who-is-looking list of remote users looking for a user of the client device, wherein the who-is-looking list is sorted by relevance based on the multichannel context;
generate, using output from the predictive models and the relevance, a response message based at least in part on the multichannel context of the received message;
display the who-is-looking list of remote users using the workplace assistant client application on the client device; and
display the response message using the workplace assistant client application on the client device.
9. The system of claim 8 , wherein the predictive models further comprise a large language model, an intent detection model, and an urgency model.
10. The system of claim 9 , wherein the workplace assistant client application is configured to access at least one of the large language model, the intent detection model, or the urgency model over a network.
11. The system of claim 9 , wherein the workplace assistant client application is associated with at least one of the large language model, the intent detection model, or the urgency model on a client device.
12. The system of claim 11 , wherein the at least one of the large language model, the intent detection model, or the urgency model is configured for training in part using generic data and in part using secured user data stored in association with the workplace assistant client application.
13. The system of claim 8 , wherein the workplace assistant client application is configured to detect the at least one received message in any of the plurality of channels, and wherein the plurality of channels includes email, chat, and at least one teleconferencing channel.
14. The system of claim 8 , wherein the multichannel context is further based on metadata including mentions in stored documents and at least one of relationship, presence, group membership, active channels, or previous interactions.
15. A non-transitory computer-readable medium comprising code that is executable by a processor for causing the processor to:
detect, at a workplace assistant client application on a client device, at least one received message associated with a remote user from among a plurality of remote users;
access a plurality of channels communicatively coupled to the workplace assistant client application;
submit the at least one received message and additional information from the plurality of channels to predictive models to provide a multichannel context for the at least one received message;
generate, from the plurality of remote users, a who-is-looking list of remote users looking for a user of the client device, wherein the who-is-looking list is sorted by relevance based on the multichannel context;
generate, using output from the predictive models and the relevance, a response message based at least in part on the multichannel context of the received message;
display the who-is-looking list of remote users using the workplace assistant client application on the client device; and
display the response message using the workplace assistant client application on the client device.
16. The non-transitory computer-readable medium of claim 15 , wherein the predictive models further comprise a large language model, an intent detection model, and an urgency model.
17. The non-transitory computer-readable medium of claim 16 , wherein the workplace assistant client application is configured to access at least one of the large language model, the intent detection model, or the urgency model over a network.
18. The non-transitory computer-readable medium of claim 16 , wherein the workplace assistant client application is associated with at least one of the large language model, the intent detection model, or the urgency model on a client device.
19. The non-transitory computer-readable medium of claim 18 , wherein the at least one of the large language model, the intent detection model, or the urgency model is configured for training in part using generic data and in part using secured user data stored in association with the workplace assistant client application.
20. The non-transitory computer-readable medium of claim 15 , wherein the multichannel context is further based on metadata including mentions in stored documents and at least one of relationship, presence, group membership, active channels, or previous interactions.