Systems and methods for providing multi-modal interaction via user equipment

A non-transitory computer-readable medium storing a plurality of processor-executable instructions to:

• output, to a UE that is engaged in a call, a first instruction to present a set of visual information during the call;
• determine that confirmation of presentation of the set of visual information has not been received from the UE;
• and
• output, to the UE and based on the determination that the confirmation has not been received from the UE, a second instruction to obtain a particular application, wherein the UE obtains the particular application based on the second instruction and presents the set of visual information via the particular application during the call.

A method, comprising:

• outputting, to a UE that is engaged in a call, a first instruction to present a set of visual information during the call;
• determining that confirmation of presentation of the set of visual information has not been received from the UE;
• and
• outputting, to the UE and based on the determination that the confirmation has not been received from the UE, a second instruction to obtain a particular application, wherein the UE obtains the particular application based on the second instruction and presents the set of visual information via the particular application during the call.