Conversational bot interaction with utterance ranking

A software-as-a-service computing platform, comprising:

• computing hardware;
• computer software executing on the computer hardware, the computer software comprising computer program instructions executed on the computing hardware and configured to imitating a human conversational response using a set of conversations that have been annotated to identify speech acts, and physical acts, wherein a speech act is a labeled grouping of utterances, the computer program instructions comprising program code executing in association with an automated conversational bot and configured to:
• receive a data model associated with a multi-turn conversation, the data model comprising an observation history;
• upon receipt of a query that includes a sequence of two or more utterances, apply an utterance ranking algorithm that outputs a ranked order of importance of the utterances in the sequence, wherein the utterance ranking algorithm (i) separates the utterances in the sequence into sub-groups of utterances according to utterance type and content score, (ii) within each sub-group, internally ranks the utterances therein according to their content scores to create a list, and (iii) joins the lists according to an ordering that places non-statement and statement-based utterances with higher content scores before non-statement and statement-based utterances with lower content scores;
• in response to applying the utterance ranking algorithm, update the data model to reflect the ranked order;
• and
• use the updated data model to attempt to generate a coherent response to the query for the automated conversational bot;
• the program code further controlling the automated conversational bot to return the coherent response to the input.