Cross-device presentation with conversational user interface

A system, comprising:

• at least one processor;
• and
• a memory communicatively coupled to the at least one processor, the memory storing instructions which, when executed by the at least one processor, cause the at least one processor to perform operations comprising:
• receiving, from an input computing device, speech data provided by a user during a speech interaction with a conversational user interface (CUI) executing on the input computing device;
• analyzing the speech data to determine at least one search term that is specified by the user through the speech interaction;
• determining an item score for each of a plurality of items, wherein the item score indicates a predicted affinity of the user for a respective item and is determined based at least partly on a degree of correspondence between the at least one search term and criteria information for the respective item;
• generating a recommendation describing at least one recommended item for which the respective item score is at least a threshold value;
• and
• automatically detecting at least one output computing device of the user that is available to display the recommendation, the at least one output computing device being different from the input computing device, wherein the detecting comprises:
• automatically detecting that the at least one output computing device is turned on and network-accessible;
• and
• in response to automatically detecting that the at least one output computing device is turned on and network-accessible, prompting, through the CUI executing on the input computing device, the user to confirm whether the recommendation is to be presented on the at least one output computing device;
• and
• in response to receiving the user’s confirmation that the recommendation is to be presented on the at least one output computing device, transmitting, by the at least one processor, the recommendation for display on the at least one output computing devices.

One or more non-transitory computer-readable media storing instructions which, when executed by at least one processor, cause the at least one processor to perform operations comprising:

• receiving, from an input computing device, speech data provided by a user during a speech interaction with a conversational user interface (CUI) executing on the input computing device;
• analyzing the speech data to determine at least one search term that is specified by the user through the speech interaction;
• determining an item score for each of a plurality of items, wherein the item score indicates a predicted affinity of the user for a respective item and is determined based at least partly on a degree of correspondence between the at least one search term and criteria information for the respective item;
• generating a recommendation describing at least one recommended item for which the respective item score is at least a threshold value;
• and
• automatically detecting at least one output computing device of the user that is available to display the recommendation, the at least one output computing device being different from the input computing device, wherein the detecting comprises:
• automatically detecting that the at least one output computing device is turned on and network-accessible;
• and
• in response to automatically detecting that the at least one output computing device is turned on and network-accessible, prompting, through the CUI executing on the input computing device, the user to confirm whether the recommendation is to be presented on the at least one output computing device;
• and
• in response to receiving the user’s confirmation that the recommendation is to be presented on the at least one output computing device, transmitting, by the at least one processor, the recommendation for display on the at least one output computing devices.