Abstract: A method of generating content in association with an information search and retrieval system. It begins by receiving a query from a user. The query is semantically-searched to identify a context. A conversation history between the user and the system is identified. An enriched query is then generated by associating to the query both the context and at least a portion of the conversation history. The enriched query is then evaluated/processed by a generative-AI. In response, information associated with the enriched query is received from the generative-AI. A response to the query is then generated using the information, e.g., by passing the information back to the user, by modifying (e.g., editing or supplementing) the information to generate modified information and passing the modified information back to the user, or by dismissing the information. If sensitive information is identified in the utterance, it is masked prior to generating the enriched query.

Abstract: Method and system to control a conversational bot uses a directed acyclic graph to specify a desired conversation flow. A graph node has synthetic conversation transcripts annotated with events, wherein an event in a synthetic conversation transcript has preconfigured event expressions that represent ways in which dialogue at the node can unfold. During an on-going conversation with an actor, the system provides a data model uniquely associated with the conversation and that specifies a linear sequence of observations. The data model includes events representing semantically-related conversation fragments located in annotated historical conversation transcripts. In response to receipt of an input in association with a current graph node, the system determines whether the input extends an event in the synthetic conversation transcript associated with the node. If so, a response that continues a current conversation flow in the graph is provided.

Abstract: A method to select a response in a multi-turn conversation between a user and a conversational bot. The conversation is composed of a set of events, wherein an event is a linear sequence of observations that are user speech or physical actions. Queries are processed against a set of conversations that are organized as a set of inter-related data tables, with events and observations stored in distinct tables. As the multi-turn conversation proceeds, a data model comprising an observation history, together with a hierarchy of events determined to represent the conversation up to at least one turn, is persisted. When a new input (speech or physical action) is received, it is classified using a statistical model to generate a result. The result is then mapped to an observation in the data model. Using the mapped observation, a look-up is performed into the data tables to retrieve a possible response.

Abstract: A technique for semantic search and retrieval that is event-based, wherein is event is composed of a sequence of observations that are user speech or physical actions. Using a first set of conversations, a machine learning model is trained against groupings of utterances therein to generate a speech act classifier. Observation sequences therein are organized into groupings of events and configured for subsequent event recognition. A set of second (unannotated) conversations are then received. The set of second conversations is evaluated using the speech act classifier and information retrieved from the event recognition to generate event-level metadata that comprises, for each utterance or physical action within an event, one or more associated tags. In response to a query, a search is performed against the metadata. Because the metadata is derived from event recognition, the search is performed against events learned from the set of first conversations.

Abstract: A method and computing platform to imitate human conversational response as a context transitions across multiple channels (e.g., chat, messaging, email, voice, third party communication, etc.) where inputs to the system are categorized into identified speech acts and physical acts, and a conversational bot is associated to the channels. In this approach, a data model associated with a multi-turn conversation is provided. The data model comprises an observation history, wherein an observation in the observation history includes an identification of a channel in which the observation originates. As turns are added to the multi-turn conversation, a conversational context across multiple channels is persisted using the data model. Using this approach, an AI-supported conversation started in one channel can move to another conversation channel while maintaining the context of the conversation intact and coherent.

Abstract: Method and system to control a conversational bot uses a directed acyclic graph to specify a desired conversation flow. A graph node has synthetic conversation transcripts annotated with events, wherein an event in a synthetic conversation transcript has preconfigured event expressions that represent ways in which dialogue at the node can unfold. During an on-going conversation with an actor, the system provides a data model uniquely associated with the conversation and that specifies a linear sequence of observations. The data model includes events representing semantically-related conversation fragments located in annotated historical conversation transcripts. In response to receipt of an input in association with a current graph node, the system determines whether the input extends an event in the synthetic conversation transcript associated with the node. If so, a response that continues a current conversation flow in the graph is provided.

Abstract: A conversational bot system uses a set of conversations that have been annotated to identify speech acts, wherein a speech act is a labeled grouping of utterances. To facilitate processing, a data model associated with a multi-turn conversation is received. The data model comprises an observation history. Upon receipt of query that includes a sequence of at least two or more utterances, an utterance ranking algorithm is applied. The algorithm selectively reorders the utterances in the sequence into a ranked order of importance that reflects a lowest to highest priority of response. In response to applying the utterance ranking algorithm, the data model is then updated to reflect the ranked order. In one embodiment, updating the data model positions the highest priority utterance as a most recent utterance in the observation history. The updated data model is then used to attempt to generate a coherent response to the query.

Abstract: A technique for semantic search and retrieval that is event-based, wherein is event is composed of a sequence of observations that are user speech or physical actions. Using a first set of conversations, a machine learning model is trained against groupings of utterances therein to generate a speech act classifier. Observation sequences therein are organized into groupings of events and configured for subsequent event recognition. A set of second (unannotated) conversations are then received. The set of second conversations is evaluated using the speech act classifier and information retrieved from the event recognition to generate event-level metadata that comprises, for each utterance or physical action within an event, one or more associated tags. In response to a query, a search is performed against the metadata. Because the metadata is derived from event recognition, the search is performed against events learned from the set of first conversations.

Abstract: A method to select a response in a multi-turn conversation between a user and a conversational bot. The conversation is composed of a set of events, wherein an event is a linear sequence of observations that are user speech or physical actions. Queries are processed against a set of conversations that are organized as a set of inter-related data tables, with events and observations stored in distinct tables. As the multi-turn conversation proceeds, a data model comprising an observation history, together with a hierarchy of events determined to represent the conversation up to at least one turn, is persisted. When a new input (speech or physical action) is received, it is classified using a statistical model to generate a result. The result is then mapped to an observation in the data model. Using the mapped observation, a look-up is performed into the data tables to retrieve a possible response.

Abstract: A method to select a response in a multi-turn conversation between a user and a conversational bot. The conversation is composed of a set of events, wherein an event is a linear sequence of observations that are user speech or physical actions. Queries are processed against a set of conversations that are organized as a set of inter-related data tables, with events and observations stored in distinct tables. As the multi-turn conversation proceeds, a data model comprising an observation history, together with a hierarchy of events determined to represent the conversation up to at least one turn, is persisted. When a new input (speech or physical action) is received, it is classified using a statistical model to generate a result. The result is then mapped to an observation in the data model. Using the mapped observation, a look-up is performed into the data tables to retrieve a possible response.