Interpretation of user interaction using model platform
A platform can receive information regarding a user interaction, wherein the user interaction is associated with one or more channels that correspond to respective interfaces or media for the user interaction; retrieve supplemental information associated with the user interaction, wherein the supplemental information relates to at least one of: a state of a managed device associated with the user interaction, or a previous user interaction; identify, based on the information regarding the user interaction or the one or more channels, one or more models to process the information regarding the user interaction and the supplemental information, wherein the one or more models are identified from a plurality of models; determine, using the one or more models, an action to be performed with regard to the user interaction; and provide information identifying the action.
1. A platform, comprising:
one or more memories; and
one or more processors, communicatively coupled to the one or more memories, to:
receive information regarding a user interaction,
wherein the user interaction is associated with one or more channels,
wherein the one or more channels correspond to respective interfaces or media for the user interaction;
retrieve supplemental information associated with the user interaction,
wherein the supplemental information relates to a state of a managed device associated with the user interaction;
identify, based on the information regarding the user interaction or the one or more channels, one or more models to process the information regarding the user interaction and the supplemental information,
wherein the one or more models are identified from a plurality of models;
determine, using the one or more models and based on historical data associated with the user interaction, one or more insights associated with the user interaction;
determine, based on prioritizing the one or more insights, an action to be performed with regard to the user interaction,
wherein the one or more insights are prioritized based on a parameter that indicates how well each of the one or more insights correlate to the user interaction; and
provide information identifying the action.
2. The platform of claim 1 , wherein the one or more processors are further to:
determine a result of the action; and
update the one or more models based on the result and using a machine learning technique.
3. The platform of claim 1 , where the one or more processors are further to:
predict a reason for the user interaction using the one or more models or a rule,
wherein the action is based on the reason.
4. The platform of claim 1 , wherein the action relates to the managed device associated with the user interaction, and
wherein the one or more processors are further to:
automatically perform the action with regard to the managed device.
5. The platform of claim 1 , wherein the one or more processors are further to:
determine the supplemental information based on a data stream,
wherein the data stream indicates the state of the managed device associated with the user interaction.
6. The platform of claim 1 , wherein a model, of the one or more models, is associated with an external device external to the platform, and
wherein the one or more processors are further to:
provide at least part of the information regarding the user interaction or the supplemental information to the external device; and
receive a result from the external device,
wherein the action is determined based on the result.
7. A non-transitory computer-readable medium storing instructions, the instructions comprising:
one or more instructions that, when executed by one or more processors, cause the one or more processors to:
receive information regarding a user interaction, wherein the user interaction is associated with one or more channels,
wherein the one or more channels correspond to respective interfaces or media for the user interaction;
retrieve supplemental information associated with the user interaction,
wherein the supplemental information relates to a state of a managed device associated with the user interaction;
identify, based on the information regarding the user interaction, one or more models to process the information regarding the user interaction and the supplemental information,
wherein the one or more models are identified from a plurality of models;
determine, using the one or more models and based on historical data associated with the user interaction, one or more insights associated with the user interaction;
determine, based on prioritizing the one or more insights, an action to be performed with regard to the user interaction,
wherein the one or more insights are prioritized based on a parameter that indicates how well each of the one or more insights correlate to the user interaction; and
provide information identifying the action.
8. The non-transitory computer-readable medium of claim 7 , wherein the one or more instructions, when executed by the one or more processors, further cause the one or more processors to:
determine a result of the action; and
update the one or more models based on the result and using a machine learning technique.
9. The non-transitory computer-readable medium of claim 7 , wherein the one or more instructions, when executed by the one or more processors, further cause the one or more processors to:
predict a reason for the user interaction using the one or more models or a rule,
wherein the action is based on the reason.
10. The non-transitory computer-readable medium of claim 7 , wherein the action relates to the managed device associated with the user interaction, and wherein the one or more instructions, when executed by the one or more processors, further cause the one or more processors to:
automatically perform the action with regard to the managed device.
11. The non-transitory computer-readable medium of claim 7 , wherein the one or more instructions, when executed by the one or more processors, further cause the one or more processors to:
determine the supplemental information based on a data stream,
wherein the data stream indicates the state of the managed device associated with the user interaction.
12. The non-transitory computer-readable medium of claim 7 , wherein a model, of the one or more models, is associated with an external device, and wherein the one or more instructions, when executed by the one or more processors, further cause the one or more processors to:
provide at least part of the information regarding the user interaction or the supplemental information to the external device; and
receive a result from the external device, wherein the action is determined based on the result.
13. A method, comprising:
receiving, by a platform, information regarding a user interaction, wherein the user interaction is associated with one or more channels,
wherein the one or more channels correspond to respective interfaces or media for the user interaction;
retrieving, by the platform, supplemental information associated with the user interaction,
wherein the supplemental information relates to a state of a managed device associated with the user interaction;
identifying, by the platform and based on the information regarding the user interaction, one or more models to process the information regarding the user interaction and the supplemental information,
wherein the one or more models are identified from a plurality of models;
determining, by the platform, using the one or more models, and based on historical data associated with the user interaction, one or more insights associated with the user interaction;
determining, by the platform and based on prioritizing the one or more insights, an action to be performed with regard to the user interaction,
wherein the one or more insights are prioritized based on a parameter that indicates how well each of the one or more insights correlate to the user interaction; and
providing, by the platform, information identifying the action.
14. The method of claim 13 , further comprising:
determining a result of the action; and
updating the one or more models based on the result and using a machine learning technique.
15. The method of claim 13 , further comprising:
predicting a reason for the user interaction using the one or more models or a rule,
wherein the action is based on the reason.
16. The method of claim 13 , wherein the action relates to the managed device associated with the user interaction, and wherein the method further comprises:
automatically performing the action with regard to the managed device.
17. The method of claim 13 , further comprising:
determining the supplemental information based on a data stream,
wherein the data stream indicates the state of the managed device associated with the user interaction.
18. The platform of claim 1 , wherein the one or more processors are further to:
determine, based on determining that none of the one or more insights are associated with a confidence score that satisfies a threshold, another insight using a static rule; and
determine, based on the other insight, an action to be performed with regard to the user interaction.
19. The non-transitory computer-readable medium of claim 7 , wherein the one or more instructions, when executed by the one or more processors, further cause the one or more processors to:
determine, based on determining that none of the one or more insights are associated with a confidence score that satisfies a threshold, another insight using a static rule; and
determine, based on the other insight, an action to be performed with regard to the user interaction.
20. The method of claim 13 , further comprising:
determining, based on determining that none of the one or more insights are associated with a confidence score that satisfies a threshold, another insight using a static rule; and
determining, based on the other insight, an action to be performed with regard to the user interaction.