APPARATUSES, METHODS, AND COMPUTER PROGRAM PRODUCTS FOR PROCESSING MULTI-CHANNEL DATA OBJECTS TO INITIATE AUTOMATED RESOLUTION ACTIONS VIA AN INTENT ENGINE

1 . An apparatus comprising one or more processors and one or more storage devices storing instructions that are operable, when executed by the one or more processors, to cause the one or more processors to:

receive (i) a first unstructured service message via a first communication channel of a plurality of communication channels and (ii) a second unstructured service message via a second communication channel of the plurality of communication channels, wherein the first communication channel defines a first expected communication parameter set, and the second communication channel defines a second expected communication parameter set;

generate (i) a first structured service message object for the first unstructured service message and (ii) a second structured service message object for the second unstructured service message based at least in part on a feature extraction format for a machine learning model, wherein the first structured service message object defines a first feature dataset associated with the first communication channel, and the second structured service message object defines a second feature dataset associated with the second communication channel;

generate, using the machine learning model, support labels for the first service message object and the second service message object based at least in part, respectively, on the first feature dataset and on the second feature dataset; and

correlate the support labels for the first service message object and the second service message object to respective resolution data objects related to one or more resolution actions based at least in part, respectively, on the first expected communication parameter set and on the second expected communication parameter set.

2 . The apparatus of claim 1 , wherein the one or more storage devices store instructions that are operable, when executed by the one or more processors, to further cause the one or more processors to:

generate the support labels for the first structured service message object and the second structured service message object in response to a determination that the first feature dataset and the second feature dataset satisfy defined intent criteria for an intent model.

3 . The apparatus of claim 1 , wherein the one or more storage devices store instructions that are operable, when executed by the one or more processors, to further cause the one or more processors to:

generate a response message object for a client device via a communication channel of the plurality of communication channels in response to a determination that the first feature dataset and the second feature dataset do not satisfy defined intent criteria for an intent model;

receive at least a third unstructured structured service message object via at least a third communication channel of the plurality of communication channels, wherein the third communication channel defines a third expected communication parameter set;

generate a third structured service message object for the third unstructured service message based at least in part on the feature extraction format for the machine learning model

generate, using the machine learning model, a support label for the third structured service message object based at least in part on the third feature dataset.

4 . The apparatus of claim 1 , wherein the one or more storage devices store instructions that are operable, when executed by the one or more processors, to further cause the one or more processors to:

generate the first feature dataset or the second feature dataset based at least in part on a feature extraction process that extracts one or more text features from the first unstructured service message object or the second unstructured service message object.

5 . The apparatus of claim 1 , wherein the one or more storage devices store instructions that are operable, when executed by the one or more processors, to further cause the one or more processors to:

generate the respective resolution data objects based at least in part on a generative machine learning model or a generative system configured for generating data that represents at least a portion of a resolution action for a structured service message object.

6 . The apparatus of claim 1 , wherein the one or more storage devices store instructions that are operable, when executed by the one or more processors, to further cause the one or more processors to:

correlate the support labels for the first structured service message object and the second structured service message object to the respective resolution data objects based at least in part on a machine reading comprehension model configured for providing resolution predictions related to services messages.

7 . The apparatus of claim 1 , wherein the one or more storage devices store instructions that are operable, when executed by the one or more processors, to further cause the one or more processors to:

generate a resolution message object for a client device based at least in part on the respective resolution data objects, wherein the resolution message object is configured to render visual data associated with the respective resolution data objects via a user interface of the client device.

8 . The apparatus of claim 1 , wherein the one or more storage devices store instructions that are operable, when executed by the one or more processors, to further cause the one or more processors to:

query a knowledge base system based at least in part on the respective resolution data objects to determine a resolution message object for a client device.

9 . The apparatus of claim 1 , wherein the one or more storage devices store instructions that are operable, when executed by the one or more processors, to further cause the one or more processors to:

route a resolution ticket data object to a support device based at least in part on the respective resolution data objects.

10 . The apparatus of claim 1 , wherein the first communication channel and the second communication channel respectively correspond to an email communication channel, a network portal interface communication channel, a user interface widget communication channel, a chat communication channel, or an application programming interface (API) communication channel.

11 . The apparatus of claim 1 , wherein the support labels for the first structured service message object and the second structured service message object comprise at least one support label from a group consisting of an intent classification label, a request type label, a message type label, a user identifier label, a location label, and a timestamp label for the respective services messages.

12 . A computer-implemented method, comprising:

receiving (i) a first unstructured service message via a first communication channel of a plurality of communication channels and (ii) a second unstructured service message via a second communication channel of the plurality of communication channels, wherein the first communication channel defines a first expected communication parameter set, and the second communication channel defines a second expected communication parameter set;

generating (i) a first structured service message object for the first unstructured service message and (ii) a second structured service message object for the second unstructured service message based at least in part on a feature extraction format for a machine learning model, wherein the first structured service message object defines a first feature dataset associated with the first communication channel, and the second structured service message object defines a second feature dataset associated with the second communication channel;

generating, using the machine learning model, support labels for the first service message object and the second service message object based at least in part, respectively, on the first feature dataset and on the second feature dataset; and

correlating the support labels for the first service message object and the second service message object to respective resolution data objects related to one or more resolution actions based at least in part, respectively, on the first expected communication parameter set and on the second expected communication parameter set.

13 . The computer-implemented method of claim 12 , further comprising:

generating the support labels for the first structured service message object and the second structured service message object in response to a determination that the first feature dataset and the second feature dataset satisfy defined intent criteria for an intent model.

14 . The computer-implemented method of claim 12 , further comprising:

generating a response message object for a client device via a communication channel of the plurality of communication channels in response to a determination that the first feature dataset and the second feature dataset do not satisfy defined intent criteria for an intent model;

receiving at least a third unstructured structured service message object via at least a third communication channel of the plurality of communication channels, wherein the third communication channel defines a third expected communication parameter set;

generating a third structured service message object for the third unstructured service message based at least in part on the feature extraction format for the machine learning model generating, using the machine learning model, a support label for the third structured service message object based at least in part on the third feature dataset.

15 . The computer-implemented method of claim 12 , further comprising:

generating the first feature dataset or the second feature dataset based at least in part on a feature extraction process that extracts one or more text features from the first unstructured service message object or the second unstructured service message object.

16 . The computer-implemented method of claim 12 , further comprising:

generating the respective resolution data objects based at least in part on a generative machine learning model or a generative system configured for generating data that represents at least a portion of a resolution action for a structured service message object.

17 . The computer-implemented method of claim 12 , further comprising:

correlating the support labels for the first structured service message object and the second structured service message object to the respective resolution data objects based at least in part on a machine reading comprehension model configured for providing resolution predictions related to services messages.

18 . The computer-implemented method of claim 12 , further comprising:

generating a resolution message object for a client device based at least in part on the respective resolution data objects, wherein the resolution message object is configured to render visual data associated with the respective resolution data objects via a user interface of the client device.

19 . The computer-implemented method of claim 12 , further comprising:

querying a knowledge base system based at least in part on the respective resolution data objects to determine a resolution message object for a client device.

20 . A computer program product, stored on a computer readable medium, comprising instructions that when executed by one or more computers cause the one or more computers to: receive (i) a first unstructured service message via a first communication channel of a plurality of communication channels and (ii) a second unstructured service message via a second communication channel of the plurality of communication channels, wherein the first communication channel defines a first expected communication parameter set, and the second communication channel defines a second expected communication parameter set;

generate (i) a first structured service message object for the first unstructured service message and (ii) a second structured service message object for the second unstructured service message based at least in part on a feature extraction format for a machine learning model, wherein the first structured service message object defines a first feature dataset associated with the first communication channel, and the second structured service message object defines a second feature dataset associated with the second communication channel;

generate, using the machine learning model, support labels for the first service message object and the second service message object based at least in part, respectively, on the first feature dataset and on the second feature dataset; and

correlate the support labels for the first service message object and the second service message object to respective resolution data objects related to one or more resolution actions based at least in part, respectively, on the first expected communication parameter set and on the second expected communication parameter set.