Abstract: Disclosed in some examples are methods, systems, and machine readable mediums which provide summaries of topics determined within a corpus of documents. These summaries may be used by customer service associates, analysts, or other users to quickly determine both topics discussed and contexts of those topics over a large corpus of text. For example, a corpus of documents may be related to customer complaints and the topics may be summarized to produce summaries such as “credit report update due to stolen identity.” These summarizations may be used to efficiently spot trends and issues.

Abstract: In one embodiment, a method includes receiving, at a client system, an audio input, where the audio input comprises a coreference to a target object, accessing visual data from one or more camera associated with the client system, where the visual data comprises images portraying one or more objects, resolving the coreference to the target object from among the one or more objects, resoling the target object to a specific entity, and providing, at the client system, a response to the audio input, where the response comprises information about the specific entity.

Abstract: Disclosed is a system comprising a memory storing a first natural language understanding model. The memory stores instructions that, when executed, cause a processor to: receive a request for generating a second natural language understanding model in a second language different from the first language; translate the first set of utterances into a second set of utterances in the second language; provide a second set of tags or intents to the second set of utterances; provide a user interface for receiving at least one input for modifying from among the second set of utterances or the second set of tags or intents; generate a third set of utterances and a third set of tags or intents on the basis of the input received through the user interface; and establish the second natural language understanding model including the third set of utterances and the third set of tags or intents.

Abstract: Methods and systems are disclosed herein for a context assistance system converting a reference in a content item based on context associated with the content item. For example, the context assistance system identifies a first entity referenced in the content item associated with a first context. The context assistance system then determines at least one attribute of the first entity. Next, the context assistance system identifies a second context in which the content item is to be presented. The context assistance system determines the second entity based on the second context and on the at least one attribute of the first entity. The context assistance system replaces reference to the first entity in the content item with reference to the second entity.

Abstract: Participant inclusion determination can include generating a textual analysis of a draft of an electronic communication in response to a sender preparing the draft for conveyance over an electronic communications network. A word relevance score can be computed for each word of the draft based on the textual analysis. Probabilistically weighted distances between the sender, an initial recipient of the electronic communication, and more additional recipient candidates for additionally receiving the electronic communication can be determined. The probabilistically weighted distances can correspond to hierarchical distances within a hierarchical structure corresponding to an organization in which the sender, the initial recipient, and one or more additional recipient candidates are members.

Abstract: The present invention relates to a method for facilitating a human-machine conversation for responding to a user query received from a user. The method includes determining at least one of a category and a context of the user query and implementing a first model and a second model for responding to the user query. The second model is triggered when the first model is unable to respond to the user query. The method further includes configuring one or more crawlers for accessing corresponding one or more databases of a plurality of databases for retrieving the relevant information and generating a second model. The method also includes enabling the second model to present the relevant information to the user based on the second model score. The second model updates the first model with the relevant information and its corresponding second model score.

Abstract: A novel method provides an AI language virtual agent having self-improvement features and which uses language modeling and tree search techniques. The AI language virtual agent exchanges textual discussion with users and other simulated agents. The method includes receiving a current situational description depicting natural language user input, temperament qualities and textual tendencies of the virtual agent, and indicia regarding subject matter context of a present conversation. The indicia regarding subject matter context include textual logs from recent conversational exchanges. The current situational description includes audio, visual, and tactile inputs collected proximate to the virtual agent.

Abstract: Disclosed is an improved computer architecture for generating an electronic data layout by having a user input a portion of dataset and obtaining the remaining portion of the format data from a data storage that stores reusable data for various data layouts. A master data object is configured to store “request-agnostic data,” which is typically that portion of dataset that does not differ, or is common, between various data layouts. The data that differs between various data layouts, such as the data that is specific to a form, may be considered as “request-specific data.” When a data layout generation request is received, the user may be prompted to input request-specific data, but not the request-agnostic data. The system automatically obtains the request-agnostic data from the master data object, and integrates the request-agnostic data with the request-specific data to generate the form.

Abstract: A system and method for updating computerized language models is provided that automatically adds or deletes terms from the language model to capture trending events or products, while maximizing computer efficiencies by deleting terms that are no longer trending and use of knowledge bases, machine learning model training and evaluation corpora, analysis tools and databases.

Abstract: Computer-implemented methods, computer program products, and computer systems for improving intent determination in a messaging dialog manager system. The computer-implemented method for improving intent determination in a messaging dialog manager system may include one or more processors configured for receiving first agent entry data corresponding to a first agent communicating in a messaging dialog interface, determining that the first agent entry data expects a response that is within a first response domain, determining that a first user entry entered in the messaging dialog interface is not within the first response domain. Further, the computer-implemented may include identifying a second agent configured with a second response domain that includes the first user entry and transmitting the first user entry to the second agent to facilitate a seamless transition of an established communicational flow between the first agent and a first user.

Abstract: A consumer is identified at a transaction terminal. A natural-language voice chatbot is initiated for the transaction. The chatbot is configured with store information for a store associated with the terminal and, optionally, with preferences registered to the consumer. A natural language voice dialogue using, at least the store information, is initiated between the chatbot and the consumer while the consumer is at the terminal and during the transaction. The consumer may order store items from the store and pay for the items through the dialogue. In an embodiment, the items ordered are delivered to the terminal where the consumer is located.

Abstract: A handheld electronic device may include a microphone for receiving voice commands, a speaker for providing audio feedback, a display for providing visual output and receiving touch input, and a motion sensor for receiving gesture input. The handheld electronic device may include control circuitry that processes voice commands differently depending on the application running on the handheld electronic device and the icon being displayed on the display. The control circuitry may determine the location of the handheld electronic device and may provide content based on the location. For example, a remote control interface for controlling an external device may be displayed when the handheld electronic device approaches the external device. A head-mounted device may display virtual images based on the location of the handheld electronic device. The virtual images may include a live video feed from a video call, virtual images associated with voice commands, or other virtual images.

Abstract: Systems and methods are provided for using a registry to assure parties receiving a communication, such as an incoming phone call, that the party sending the communication, such as the caller is, who it appears to be. In some embodiments the registry is a publicly accessible database which stores communication identifiers such as telephone numbers for parties in association with other data including data provided by the parties or others. The other data may include the name of the party associated with the identifier, a cryptographic public key used by the party as part of a public/private key pair, data representing the intent of the party in sending a communication, and parameters set by parties to be satisfied to receive communications or in determining how such communications should be handled. The system may provide the data representing the party's specific intention in that call or other communication to the party receiving the communication.

Abstract: A method may include for intent-based natural language processing may include conversation engine: receiving from a conversation program executed on a user electronic device, a unique identifier for a user; calling an external controls program with the unique identifier and a type of the user electronic device, wherein the external controls program identifies a directive of intent and an alternate action; receiving the directive of intent and the alternate action; receiving text of an utterance in a conversation from the conversation program; selecting one of a plurality a priority of intents based on the text of the utterance; receiving a plurality of potential intents and a confidence score for each potential intent from a natural language understanding computer program; selecting a selected intent; determining that the directive of intent matches the selected intent; and executing the alternate action.

Abstract: Systems and methods associated with generation and/or provision of predictive content are disclosed. One exemplary method includes receiving communications associated with a plurality of customers; determining a message type for each message of the communications; splitting first messages of the first message type into a first set of subcomponent text sections; splitting second messages of the second message type into a second set of subcomponent text sections; analyzing the first set and the second set to generate a plurality of semantic numerical scores for each respective subcomponent text section; determining at least one impactful semantic category for a target audience by selecting at least one semantic category corresponding to at least one semantic numerical score of at least one subcomponent text section of the first set or the second set that is equal to or higher than a first pre-determined threshold value; generating personalized textual content targeting the audience.

Abstract: A method including receiving, in a machine learning model (MLM), a corpus including words. The MLM includes layers configured to extract keywords from the corpus, plus a retrospective layer. A first keyword and a second keyword from the corpus are identified in the layers. The first and second keywords are assigned first and second probabilities. Each probability is a likelihood that a keyword is to be included in a key phrase. A determination is made, in the retrospective layer, of a first probability modifier that modifies the first probability based on a first dependence relationship between the second keyword being placed after the first keyword. The first probability is modified using the first probability modifier. The first modified probability is used to determine whether the first keyword and the second keyword together form the key phrase. The key phrase is stored in a non-transitory computer readable storage medium.

Abstract: System and method for handling a transaction between a waiting party and queuing party include an independent communication system (ICS) managing calls between the waiting party and calling party for handling sensitive data as well as call-attached data. The ICS manages the transaction in different stages and with different levels of sensitivity. Either party is allowed to modify the call or call preferences during the transaction. The ICS works independently from the queuing party calling system.

Abstract: There are provided a method, a system configured to perform the method, and a computer program product comprising instructions which when executed by processing circuitry of the system cause the system to perform the method. The method comprises determining, by at least one computer processor communicatively coupled to and configured to operate in a contact center system, a plurality of available contacts, wherein each of the plurality of available contacts is available for pairing to an agent of a plurality of agents using either a first pairing strategy or a second pairing strategy, wherein the first pairing strategy is different from the second pairing strategy.

Abstract: A system processes unstructured data to identify a plurality of subsets of text in a set of text in the unstructured data and determines, for a subset from the plurality of subsets, probabilities based on a position of the subset in the set of text, a part of speech (POS) of each word in the subset, and POSs of one or more words on left and right hand sides of the subset, a number of the one or more words being selected based on a length of the set of text. The system generates a feature vector for the subset, the feature vector including the probabilities and additional features of the subset; and classifies, using a classifier, the subset into one of a plurality of classes based on the feature vector for the subset, the plurality of classes representing an ontology of a domain of knowledge.

Abstract: An electronic device receives a first audio content item that includes a plurality of sound sources. The electronic device generates a representation of the first audio content item. The electronic device determines, from the representation of the first audio content item: a representation of an isolated sound source, and frequency data associated with the isolated sound source. Determining the representation of the isolated sound source and the frequency data associated with the isolated sound source includes using a neural network to jointly determine the representation of the isolated sound source and the frequency data associated with the isolated sound source. The electronic device determines that a portion of a second audio content item matches the first audio content item using the representation of the isolated sound source and/or the frequency data associated with the isolated sound source.