Abstract: An analysis platform combines unsupervised and semi-supervised approaches to quickly surface and organize relevant user intentions from conversational text (e.g., from natural language inputs). An unsupervised and semi-supervised pipeline is provided that integrates the fine-tuning of high performing language models via a language models fine-tuning module, a distributed KNN-graph building method via a KNN-graph building module, and community detection techniques for mining the intentions and topics from texts via an intention mining module.

Abstract: Disclosed embodiments pertain to training an intelligent virtual assistant through phased observational learning tasks. A pre-trained language model can be updated offline to produce a second language model with self-supervised learning based on transcripts of historical interactions between one or more customers, one or more customer service agents, and one or more data stores. The second language model can be evaluated and determined to satisfy a predetermined performance threshold. Subsequently, the second language model can be updated online to produce a third language model with reinforcement learning based on received customer input and similarity between a response provided by a customer service agent and a predicted response generated by the second language model. The third language model can then be deployed with an intelligent virtual assistant to respond to received user input.

Abstract: To allow the human customer service agents to specialize in the instances where human service is preferred, but to scale to the volume of large call centers, systems and methods are provided in which human agents and intelligent virtual assistants (IVAs) co-handle a conversation with a customer. IVAs handle simple or moderate tasks, and human agents are used for those tasks that require or would benefit from human compassion or special handling. Instead of starting the conversation with an IVA and then escalating or passing control of the conversation to a human to complete, the IVAs and human agents work together on a conversation.

Abstract: Certain aspects of the present disclosure provide techniques for receiving audio data comprising a user voice command; determining a task to be completed by a remote service based on the user voice command; determining that a reference voice print associated with the user is stored in a user account; authenticating the user by determining that a sample voice print based on the user voice command matches the reference voice print associated with the user; storing authentication evidence associated with the task; and providing proof of user authentication to the remote service in order to initiate the task with the remote service.

Abstract: Certain aspects of the present disclosure provide techniques for receiving, from a user, a command for a virtual assistant to perform a task on behalf of the user; determining a communication channel for the virtual assistant to communicate with a remote service in order to perform the task; registering a communication session with an identity provider service, wherein the communication session is associated with the communication channel; initiating the communication session with the remote service using the communication channel; receiving a communication session authentication query from the remote service; and determining, in response to the communication session authentication query, whether the user is authenticated.

Abstract: To allow the human customer service agents to specialize in the instances where human service is preferred, but to scale to the volume of large call centers, systems and methods are provided in which human agents and intelligent virtual assistants (IVAs) co-handle a conversation with a customer. IVAs handle simple or moderate tasks, and human agents are used for those tasks that require or would benefit from human compassion or special handling. Instead of starting the conversation with an IVA and then escalating or passing control of the conversation to a human to complete, the IVAs and human agents work together on a conversation.

Abstract: A system including an interaction processing component is deployed to automatically validate information exchanged during an interaction.

Abstract: Systems and methods are described to automatically generate candidate questions and responses to speed the process of response creation and editing for commercial IVAs and chatbots. Rather than create the questions and responses from scratch for a new IVA, the system uses existing questions and responses from a previous or related IVA to train a model that can generate proposed responses to provided questions. The model, or a different model, can further be trained to generate responses using data taken from company or entity-specific data sources such as websites and knowledge bases. After a set of questions and responses have been generated for an IVA they may be reviewed by one or more human reviewers to ensure they are of a suitable quality. Where no previous or related IVA exists to provide example responses, the model may be trained solely using the company or entity-specific data.

Abstract: A system and method using blockchain for monitoring and tracking customer service representative actions are disclosed. In the system and method, customer service representative actions are encrypted using an encryption key specific to a company on whose behalf the customer service representative is acting. The customer service representative signs the encrypted action with a private key of a public/private key pair. The signed, encrypted action record is placed on the blockchain, which can later be accessed to review the actions of the customer service representative or actions of any customer service representative acting on behalf of the specific company.

Abstract: As described herein, a system for expanding contractions in electronically stored text includes expanding contractions having only on expanded form. For remaining contractions, a grammar check is performed for all possible expanded forms to determine if an expanded form can be selected based on context and grammar rules. If an expanded form is not evident from the first two steps, all possible expanded forms of the remaining contractions are converted to a vector representation along with the original text. A Word Movers Distance (WMD) for each possible expansion is calculated using the vectors for each possible expansion and the original text. An expanded form is chosen without human intervention based on the grammar score alone or the WMD and the grammar score.

Abstract: An intelligent virtual assistant (IVA) is deployed to place a call/chat to customer service on behalf of the customer, thus saving them time and frustration. The IVA contacts a specific company over one or more channels, for example, chat, phone call, Application Programming Interface (API), or email, in order to complete open-ended task(s) requested by its user. Before the IVA contacts the company, a specific user profile is injected into an IVA dialog state. The IVA contacts the company or agency and answers customer service agent (CSA) questions by using the specific user profile provided for the call. The IVA then stores the task outcome for the user to review. If something prevents the task from succeeding, the IVA alerts the user that either it needs more information or the user may need to perform some action before the task can be completed, such as filling out or emailing a form.

Abstract: An intelligent virtual assistant (IVA) is deployed to place a call/chat to customer service on behalf of the customer, thus saving them time and frustration. The IVA contacts a specific company over one or more channels, for example, chat, phone call, Application Programming Interface (API), or email, in order to complete open-ended task(s) requested by its user. Before the IVA contacts the company, a specific user profile is injected into an IVA dialog state. The IVA contacts the company or agency and answers customer service agent (CSA) questions by using the specific user profile provided for the call. The IVA then stores the task outcome for the user to review. If something prevents the task from succeeding, the IVA alerts the user that either it needs more information or the user may need to perform some action before the task can be completed, such as filling out or emailing a form.

Abstract: An intelligent virtual assistant (IVA) is deployed to place a call/chat to customer service on behalf of the customer, thus saving them time and frustration. The IVA contacts a destination entity over one or more channels, for example, chat, phone call, Application Programming Interface (API), or email, in order to complete open-ended task(s) requested by another computer. Before the IVA contacts the destination entity, a specific user profile is injected into an IVA dialog state. The IVA contacts the destination entity and answers customer service agent (CSA) questions by using the specific user profile inserted. The IVA then stores the task outcome for the user to review. If something prevents the task from succeeding, the IVA alerts the user that either it needs more information or the user may need to perform some action before the task can be completed, such as filling out, or emailing a form.

Abstract: This disclosure describes techniques and architectures for evaluating conversations. In some instances, conversations with users, virtual assistants, and others may be analyzed to identify potential risks within a language model that is employed by the virtual assistants and other entities. The potential risks may be evaluated by administrators, users, systems, and others to identify potential issues with the language model that need to be addressed. This may allow the language model to be improved and enhance user experience with the virtual assistants and others that employ the language model.

Abstract: Disclosed is a system and method for detecting and addressing bias in training data prior to building language models based on the training data. Accordingly system and method, detect bias in training data for Intelligent Virtual Assistant (IVA) understanding and highlight any found. Suggestions for reducing or eliminating them may be provided This detection may be done for each model within the Natural Language Understanding (NLU) component. For example, the language model, as well as any sentiment or other metadata models used by the NLU, can introduce understanding bias. For each model deployed, training data is automatically analyzed for bias and corrections suggested.

Abstract: Features, libraries, and techniques are provided herein for determining the kinds of relational language that are present. Applying audio, emojis, and sentiment shifts as features may be used to determine whether the customer is providing backstory, whether there is ranting, etc. Textual features may be considered, as well as audio features may be considered.

Abstract: A set of documents related to a particular topic, industry, or entity are received. Sentences are extract from each document. The sentences are grouped into tuples of one, two, or three consecutive sentences (i.e., short text sequences). The sentence tuples are clustered based on vector representations of the sentences. For each cluster, a set of tuples that best represents or best fits the cluster is selected. These sentence tuples are fed to an ontology to determine ontological entities associated with each tuple. These determined ontological entities are associated with the clusters corresponding to each tuple. The sentence tuples associated with each cluster are labeled based on the ontological entities associated with the cluster. The labeled sentence tuples may then be used for a variety of purposes such as training a model to determine the topic of short text sequences.

Abstract: A system and method using blockchain for monitoring and tracking service provider involvement in a transaction on behalf of a customer company. In the system and method, session information related to the transactions are encrypted using an encryption key specific to a company on whose behalf the service provider is acting. The encrypted action is signed the with a private key of a public/private key pair. The signed, encrypted action record is placed on the blockchain, which can later be accessed to review the actions on behalf of the specific company.

Abstract: An IVR and chatbot, or other system, employing a language model, the language model resulting from a method and computer product encoding the method is available for preparing a domain or subdomain specific glossary. The method included using probabilities, word context, common terminology and different terminology to identify domain and subdomain specific language and a related glossary updated according to the method.

Abstract: Certain aspects of the present disclosure provide techniques for generating multivariate time series data utilizing a variational auto-encoder (VAE) having an architecture for injecting custom temporal structures into the generated multivariate time series data. A method for generating multivariate time series data includes sampling a multivariate distribution forming a latent space vector, processing the latent space vector with an interpretable decoder of a variational auto-encoder, an architecture of the interpretable decoder comprising a plurality of blocks including one or more blocks configured to inject one or more temporal structures into multivariate time series data, and outputting, from the interpretable decoder, generated multivariate time series data comprising one or more temporal structures defined by the injected one or more temporal structures.