Servicenow, Inc.

Paymentus Corporation

Billeo, Inc.

Srinivas Satyasai Sunkara

Edwin Vito Sapugay

Murali B Subbarao

Anil Kumar Madamala

Maxim Naboka

Lewis Savio Landry Santos

Suzanne D Usiskin

Suzzanne D Usiskin

Lewis Savio Santos

Edwin Sapugay

Present embodiment include a prosody subsystem of a natural language understanding (NLU) framework that is designed to analyze collections of written messages for various prosodic cues to break down the collection into a suitable level of granularity (e.g., into episodes, sessions, segments, utterances, and/or intent segments) for consumption by other components of the NLU framework, enabling operation of the NLU framework. These prosodic cues may include, for example, source prosodic cues that are based on the author and the conversation channel associated with each message, temporal prosodic cues that are based on a respective time associated with each message, and/or written prosodic cues that are based on the content of each message. For example, to improve the domain specificity of the agent automation system, intent segments extracted by the prosody subsystem may be consumed by a training process for a ML-based structure subsystem of the NLU framework.

Written-modality prosody subsystem in a natural language understanding (NLU) framework

A system and method for creating and accessing a bifurcated digital wallet is described. The method comprises of processor implemented steps of authenticating by an authentication server one or more authentication information sent by a user terminal to the authentication server; extracting a first set of information by the authentication server based on the authentication of the authentication information; extracting a second set of information by one or more second servers based on the authentication of the authentication information; collating the first set of information and second set of information and displaying the collated information at the user terminal for processing a transaction.

Bifurcated digital wallet systems and methods for processing transactions using information extracted from multiple sources

An agent automation system includes a memory configured to store a reasoning agent/behavior engine (RA/BE) including a first persona and a current context and a processor configured to execute instructions of the RA/BE to cause the first persona to perform actions comprising: receiving intents/entities of a first user utterance; recognizing a context overlay cue in the intents/entities of the first user utterance, wherein the context overlay cue defines a time period; updating the current context of the RA/BE by overlaying context information from at least one stored episode associated with the time period; and performing at least one action based on the intents/entities of the first user utterance and the current context of the RA/BE.

System for focused conversation context management in a reasoning agent/behavior engine of an agent automation system

An agent automation system implements a virtual agent that is capable of learning new words, or new meanings for known words, based on exchanges between the virtual agent and a user in order to customize the vocabulary of the virtual agent to the needs of the user or users. The agent automation framework has access to a corpus of previous exchanges between the virtual agent and the user, such as one or more chat logs. New words and/or new meanings for known words are identified within the corpus and new word vectors are generated for these new words and/or new meanings for known words and added to refine a word vector distribution model. The refined word vector distribution model is then utilized by the agent automation system to interact with the user.

Systems and method for vocabulary management in a natural learning framework

An agent automation system includes a memory configured to store a natural language understanding (NLU) framework and a processor configured to execute instructions of the NLU framework to cause the agent automation system to perform actions. These actions comprise: generating an annotated utterance tree of an utterance using a combination of rules-based and machine-learning (ML)-based components, wherein a structure of the annotated utterance tree represents a syntactic structure of the utterance, and wherein nodes of the annotated utterance tree include word vectors that represent semantic meanings of words of the utterance; and using the annotated utterance tree as a basis for intent/entity extraction of the utterance.

Hybrid learning system for natural language understanding

Described are systems and methods for product recommendation refinement in a topic-based virtual storefront embedded in a topical community web page. A system and method may facilitate determining user and community member activity in the virtual storefront based on which weighted keywords are derived. A topic set containing various weighted keywords may be iteratively configured for extracting and ordering one or more products that are extracted from a plurality of heterogeneous sources. A server may be configured for refining the topic set by modifying a baseline session keyword weight or a baseline contextual keyword weight based on a total topic set weight, an elasticity parameter, core topic keyword weights associated with core topic keywords, session keyword weights, and/or contextual keyword weights; and identifying, based at least on the configured topic set, products to be presented to a user as product recommendations in the virtual storefront.

Systems and methods for product recommendation refinement in topic-based virtual storefronts

An agent automation system includes a memory configured to store a corpus of utterances and a semantic mining framework and a processor configured to execute instructions of the semantic mining framework to cause the agent automation system to perform actions, wherein the actions include: detecting intents within the corpus of utterances; producing intent vectors for the intents within the corpus; calculating distances between the intent vectors; generating meaning clusters of intent vectors based on the distances; detecting stable ranges of cluster radius values for the meaning clusters; and generating an intent/entity model from the meaning clusters and the stable ranges of cluster radius values, wherein the agent automation system is configured to use the intent/entity model to classify intents in received natural language requests.

Method and system for automated intent mining, classification and disposition

Methods and Systems for displaying product recommendations at a virtual storefront by receiving product recommendations from a plurality of heterogeneous sources. The source servers send the product recommendations from their end that are then normalized and refined by a recommendation engine based on a plurality of factors ensuring that the products are presentable and sellable on the storefront. The recommendation collation is accomplished using a pipeline of stateless processors, thereby providing a highly scalable platform perfectly suited for cloud-based computational platforms.

Systems and methods for marketplace catalogue population

Systems and methods for product recommendation refinement in a topic-based virtual storefront embedded in a topical community web page. The systems and methods facilitate continuous monitoring of user activity and community member activity in the topic-based virtual storefront based on which one or more weighted keywords are derived. A topic set containing various weighted keywords is iteratively configured for extracting and ordering one or more products that are extracted from a plurality of heterogeneous sources.

An agent automation system includes a memory configured to store a natural language understanding (NLU) framework and a model, wherein the model includes at least one original meaning representation. The system includes a processor configured to execute instructions of the NLU framework to cause the agent automation system to perform actions including: performing rule-based generalization of the model to generate at least one generalized meaning representation of the model from the at least one original meaning representation of the model; performing rule-based refinement of the model to prune or modify the at least one generalized meaning representation of the model, or the at least one original meaning representation of the model, or a combination thereof; and after performing the rule-based generalization and the rule-based refinement of the model, using the model to extract intents/entities from a received user utterance.

Growing community of inventors

Sunnyvale, CA, United States of America

Srinivas Satyasai Sunkara