Fmr Corp.

I2 Technologies Us, Inc.

Allen Detmer

Maria Lucena

Elio Dante Querze

Byung Chun

Stephen W Blessin

Steven C Bailey

Amanda Bedard

Tito Thomas

Niranjan Vasan

Naveen Rajamoorthy

Manikanta Panati

Keith Pepin

Methods and systems for efficient caching and retrieval of responses in conversation service applications includes a server that captures an utterance and converts the utterance into an utterance index key. The server searches a first response cache to determine whether the utterance index key matches a response index key. When there is a match, the server transmits a response that matches the utterance index key to a client device. When there is not a match, the server converts the utterance into an utterance embedding and searches a second response cache to identify a response embedding. The server captures a fuzzy response index key associated with the closest matching response embedding and searches the first response cache to identify a response index key that matches the fuzzy response index key.

Efficient caching and retrieval of responses in conversation service application communication sessions

Systems and methods for switching between natural language processing units during an interaction using a dialog delegation processor. The method includes receiving a dialog utterance from a user via a user device. The method further includes determining a general intent based on the dialog utterance using a general natural language processor. The method also includes determining at least one specific intent corresponding to the general intent using the general natural language processor. The method also includes selecting a specific natural language processor corresponding to the at least one specific intent. The method further includes determining a dialog response corresponding to the at least one of specific intent using the specific natural language processor. The method also includes generating for display the dialog response on the user device.

Systems and methods for bot dialog delegation

Methods and apparatuses are described for intelligent dialogue recovery in virtual assistant communication sessions. A chat session is established between a virtual assistant (VA) and a remote device. A primary dialogue is created between the VA and the remote device, including (i) requesting from a first natural language processing (NLP) service an intent associated with user messages and (ii) waiting for a corresponding response. A secondary dialogue is created between the VA and the remote device that is synchronized to a state of the primary dialogue. When the response from the first NLP service succeeds, primary messages are generated and transmitted to the remote device in the primary dialogue. When the response from the first NLP service fails, an intent is requested from the second NLP service, and secondary messages are generated and transmitted to the remote device in the secondary dialogue.

Intelligent dialogue recovery for virtual assistant communication sessions

Methods and apparatuses are described for dynamic option reselection in virtual assistant (VA) communication sessions. A chat session is established between a VA application and a remote computing device. The VA application captures a first conversation intent generated by a user of the remote device, where the first conversation intent is part of a first workflow. The VA application generates an option selection feature based upon the first conversation intent, comprising a plurality of options and associated with a reference identifier. The VA application receives a selection of a first option in the option selection feature from the remote device. The VA application initiates a second workflow in response to the selected. The VA application detects a selection of a second option in the option selection feature from the remote device and restores the chat session to a state in the first workflow using the reference identifier.

Dynamic option reselection in virtual assistant communication sessions

Methods and apparatuses are described for capturing and utilizing context data in virtual assistant communication sessions. A chat-based communication session is established between a virtual assistant application and a remote device. An event manager captures a first data event of the virtual assistant application. A parent software application receives the first data event and selects one or more session context data elements using a callback function of the first data event. The event manager captures a second data event of the parent software application comprising the session context data elements. The virtual assistant receives the second data event and inserts one or more messages comprising the session context data elements from the second data event into the chat-based communication session.

Capturing and utilizing context data in virtual assistant communication sessions

Methods and apparatuses are described for session-based data storage for chat-based communication sessions. A computing device connects to a data storage area associated with an active chat-based communication session, the data storage area comprising data storage slots. The computing device identifies a first data event during the chat-based communication session, the first data event comprising one of a data capture event, a data retrieval event, or a data prefill event. The computing device identifies a data storage slot in the data storage area corresponding to the first data event, the data storage slot comprising a slot name and a slot value. The computing device selects data elements associated with the chat-based communication session for insertion into the data storage slot based upon the event type of the first data event. The computing device stores the selected data elements in the data storage slot for retrieval during the chat-based communication session.

Session-based data storage for chat-based communication sessions

In one aspect of the invention, a computer-implemented database system ( ) includes a first table ( ) including rows each corresponding to a keyword and each including an identifier uniquely identifying the keyword. Each keyword corresponds to one or more items for which a parametric search may be performed. A second table ( ) includes rows each corresponding to an attribute of one or more items and each including an identifier uniquely identifying the attribute and a name of the attribute. A third table ( ) includes rows each corresponding to a keyword-attribute combination and each including the identifier for the keyword, the identifier for the attribute, and a set of all valid attribute values for this combination. A fourth table ( ) includes rows each corresponding to an item and each including an identifier uniquely identifying the item, a name for the item, and the identifier for the keyword for the item. A fifth table ( ) includes rows each corresponding to an attribute value of an attribute of an item and each including the attribute value, the identifier for the attribute, the identifier for the item, and the identifier for the keyword for the item.

Growing community of inventors

Patriot, IN, United States of America

Allen Detmer