Systems and methods relating to bot authoring by mining intents from conversation data via intent seeding

A system for automating aspects of authoring a conversational bot, the system comprising:

• a processor;
• and
• a memory, wherein the memory stores instructions that, when executed by the processor, cause the processor to perform:
• receiving conversation data, the conversation data comprising text derived from conversations, wherein each of the conversations is between a customer and a customer service representative;
• receiving seed intent data that comprises seed intents, each of the seed intents comprising a seed intent label and sample intent-bearing utterances associated with the seed intent;
• using an intent mining algorithm to automatically mine the conversation data to determine new utterances to associate with the seed intent;
• augmenting the seed intent data to include the mined new utterances associated with the seed intents;
• and
• uploading the augmented seed intent data into the conversation bot and using the conversational bot to conduct automated conversations with other customers;
• wherein the intent mining algorithm comprises:
• analyzing utterances occurring within the conversations of the conversation data to identify intent-bearing utterances, wherein:
• the utterances each comprise a turn within the conversations whereby the customer, in the form of a customer utterance, or the customer service representative, in the form of a customer service representative utterance, is communicating;
• and
• an intent bearing utterance is defined as one of the utterances determined to have an increased likelihood of expressing an intent;
• analyzing the identified intent-bearing utterances to identify candidate intents, wherein the candidate intents are each identified as being a text phrase occurring within one of the intent-bearing utterances that has two parts:
• an action, which comprises a word or phrase describing a purpose or task, and an object, which comprises a word or phrase describing an object or thing upon which the action operates;
• for each of the seed intents, identifying seed intent alternatives from the sample intent-bearing utterances associated with the seed intent, wherein the seed intent alternatives are identified as being a text phrase occurring within one of the sample intent-bearing utterances that includes two parts:
• an action, which comprises a word or phrase describing a purpose or task, and an object, which comprises a word or phrase describing an object or thing upon which the action operates;
• and
• associating the intent-bearing utterances from the conversation data with the seed intents via determining a degree of semantic similarity between:
• the candidate intents present in the intent-bearing utterances;
• and the seed intent alternatives belonging to each of the seed intent labels.