Liveperson, Inc.

Matthew Dunn

Michael Higgins

Joe Bradley

Laura Onu

Eswar Priyadarshan

Ravikiran Chittari

Robert LoCascio

Joseph Bradley

Jonathan Altschuler

Jian Wang

Suresh Ramakrishnaiah

Akshay Hazare

Htet Win

Andrew Maurer

George Bonev

Chuqing He

Kristen Howell

The present disclosure relates generally to facilitating two-way communications. One example involves receiving input data as part of a two-way communication session associated with a plurality of bots, accessing confidence scores from the bots. Mapped scores are then generated for the plurality of bots from the confidence scores using a bot score mapper. A selected bot is identified using the mapped scores, and the two-way communication session is facilitated using the selected bot. Further, techniques are provided to track performance of the selected bot and dynamically updated mapping adjustments in the bot score mapper using feedback and machine learning systems.

Systems and methods for bot selection calibration in two-way communications

An intent confusion evaluation engine receives conversation data corresponding to conversations between customers and agents. The engine evaluates annotations in the conversation data corresponding to intents identified from messages exchanged between customers and agents to determine levels of confusion amongst different intents. Based on these levels of confusion, the engine creates a graphical representation that illustrates the various intents and the level of confusion between different pairings of intents for the set of conversations. If an update is provided to the annotations, the graphical representation is updated dynamically and in real-time to provide updated levels of confusion amongst the various intents in accordance with the update.

Data-driven taxonomy for annotation resolution

Systems, methods, devices, instructions, and other examples are described for natural language processing. One example includes accessing natural language processing general encoder data, where the encoder data is generated from a general-domain dataset that is not domain specific. A domain specific dataset is accessed and filtered encoder data using a subset of the encoder data is generated. The filtered encoder data is trained using the domain specific dataset to generate distilled encoder data, and tuning values for the distilled encoder data are generated to configure task outputs associated with the domain specific dataset.

Domain adaptation of AI NLP encoders with knowledge distillation

Disclosed embodiments provide a framework for intent discovery based on user input and execution of processes based on the discovered intents. An intent processing system provides, via an interface, a graphical representation of different intent clusters corresponding to different intents. An intent cluster includes a set of intent terms and/or phrases that can be used to submit a request or issue that is associated with an intent. As a user selects intent terms and/or phrases from an intent cluster via the interface, the intent processing system can identify actions that can be performed to address the user's request or issue.

Systems and methods for intent discovery and process execution

Methods and systems for transcript-based bot creation are provided. Information may be stored in memory regarding different automation templates associated with different statement types. A transcript may be imported that includes statements, which may be analyzed and classified as one or more of the different statement types. The imported transcript may be displayed in a graphic user interface with its statements displayed in accordance with the automation templates associated with the respective statement type. User input may be received, including modification input that modifies at least one automation template associated with at least one statement of the displayed transcript designated as an integration point. A custom bot may thereafter be generated based on the modification input and configured to conduct a conversation based on the imported template and to initiate a workflow at the integration point in accordance with the modified automation template.

Automatic bot creation based on scripts

The present disclosure relates generally to systems and methods for analyzing intent. Intents may be analyzed to determine to which device or agent to route a communication. The analyzed intent information can also be used to formulate reports and analyze the accuracy of the identified intents with respect to the received communication.

Systems and methods for communication system intent analysis

Disclosed embodiments provide a framework to assist bot managers and builders in identifying particular friction points between bots and customers to allow for real-time identification of bot conversation issues and to train bots to improve conversation flows. Conversation data is processed using machine learning models to detect bot states within conversations and calculate a Meaningful Automated Connection Score (MACS) for these conversations. The MACS for a conversation is provided to bot builders to allow the bot builders to identify friction points and update bots accordingly.

Conversational bot evaluation and reinforcement using meaningful automated connection scores

The present disclosure relates generally to providing an intent-driven contact center. The contact center according to some embodiments analyzes intents to determine to which device or agent to route a communication. The analyzed intent information can also be used to formulate reports and analyze the accuracy of the identified intents with respect to the received communication.

Growing community of inventors

Arlington, MA, United States of America

Matthew Dunn