Servicenow, Inc.

Anil Kumar Madamala

Edwin Vito Sapugay

Maxim Naboka

Murali B Subbarao

Lewis Savio Landry Santos

Srinivas Satyasai Sunkara

Omer Anil Turkkan

Srinivas SatyaSai Sunkara

Sagar Davasam Suryanarayan

Quaizar Vohra

Aniruddha Madhusudan Thakur

Mitul Tiwari

Sriram Palapudi

Srivatsava Daruru

Jonggun Park

Sathwik Tejaswi Madhusudhan

Rammohan Narendula

Jignesh Parmar

Olivier Nguyen

Edward Cheung

Vipulkumar Popat Mahadik

Roshnee Sharma

Hari Subramani

Soham Parikh

Ziaul Hasan Hashmi

Orlando Marquez

Patrice Bechard

Shounak Purkayastha

Lewis Savio Santos

Edwin Sapugay

A method is provided for efficiently providing sentiments or other manual labels for textual training data. The method includes using an embedding model to project acquired user text to an embedding vector in an embedding space. Distances (e.g., cosine similarities) between this embedding vector and the embedding vectors determined for a plurality of already-label user text training examples are then determined. The already-labeled user text that has the shortest distance is determined and the label thereof is prospectively applied to the acquired user text and presented to a user for approval. The user can approve the prospectively applied label, in which case the newly acquired text is added to the training data with the prospectively applied label associated therewith for later use in training a language model. Alternatively, the user can decline the prospectively applied label and apply an alternative label to the newly acquired text.

Method for filtering and semi-automatically labeling training data

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 natural language understanding (NLU) framework includes a lookup source framework, which enables a lookup source system to be defined having one or more lookup sources. The lookup source system can operate in a number of different manners to facilitate repository-aware inference of user utterances, for example, by facilitating vocabulary injection during compilation of an utterance meaning model and/or an understanding model. Additionally, the lookup source system can be leveraged to cleanse client-specific training data of sensitive values to generate generic training data that can be used to train the NLU framework of other clients. The lookup sources can be compiled in a synchronous or asynchronous manner, which enables lookup sources to be compiled in an on-demand basis from test source data. Additionally, understanding models that reference lookup sources can be periodically recompiled while leveraging the latest versions of the lookup sources for vocabulary injection.

System and method for repository-aware natural language understanding (NLU) using a lookup source framework

A natural language understanding (NLU) framework includes a lookup source framework, which enables a lookup source system to be defined having one or more lookup sources. Each lookup source of the lookup source system includes a respective source data representation that is compiled from respective source data. For example, a source data representation may include source data arranged in a finite state transducer (IFST) structure as a set of finite-state automata (FSA) states, wherein each state is associated with a token that represents underlying source data. Different producers can be applied during compilation of a source data representation to derive additional states within the source data representation from the source data. Certain states of the source data representation that contain sensitive data can be selectively protected through encryption and/or obfuscation, while other portions of the source data representation that are not sensitive may remain in clear-text form.

Lookup source framework for a natural language understanding (NLU) framework

A natural language understanding (NLU) framework includes a modeling and optimization system that enables enhanced understanding and explainability to the operation of the NLU framework. The NLU framework includes a configuration vector storing settings of various components that may be applied during NLU inference of an utterance, such as which components should be activated or deactivated, as well as which numerical values (e.g., threshold values, coefficients, weight values) that are used by these components during operation. By using this configuration vector to systematically disable and adjust numerical parameters of the components of the NLU framework, and then determining the performance of the NLU framework in these configurations, the modeling and optimization system determines relationships between, as well as the relative importance of, the components of the NLU framework. The modeling and optimization system automatically determines or optimizes configurations for the NLU framework to accommodate various NLU performance and/or resource constraints.

Operational modeling and optimization system for a natural language understanding (NLU) framework

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 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.

Templated rule-based data augmentation for intent extraction

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

The present disclosure is directed to an agent automation framework that is capable of extracting meaning from user utterances and suitably responding using a search-based natural language understanding (NLU) framework. The NLU framework includes a meaning extraction subsystem capable of detecting multiple alternative meaning representations for a given natural language utterance. Furthermore, the NLU framework includes a meaning search subsystem that enables elastic confidence thresholds (e.g., elastic beam-width meaning searches), forced diversity, and cognitive construction grammar (CCG)-based predictive scoring functions to provide an efficient and effective meaning search. As such, the disclosed meaning extraction subsystem and meaning search subsystem improve the performance, the domain specificity, the inference quality, and/or the efficiency of the NLU framework.

System and method for performing a meaning search using a natural language understanding (NLU) 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

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.

Growing community of inventors

Sunnyvale, CA, United States of America

Anil Kumar Madamala