Abstract: A signal source identification device includes: a feature value calculation unit configured to calculate feature values corresponding to paths where signals from generation sources of the signals transmit, based on signals received by a plurality of sensors; and an identification unit configured to identify whether or not a feature value calculated by the feature value calculation unit is a signal from a predetermined signal source by using an identification range that is a range within which feature values based on signals from the predetermined signal source fall and that is previously determined based on the feature values calculated by the feature value calculation unit.

Abstract: According to an aspect of an embodiment, operations may include obtaining multiple electronic documents and obtaining a theme text. The method may also include selecting a seed text based on a semantic similarity between the seed text and the theme text. The method may also include changing a seed weight included in a weight vector that is used in identification of topics of the multiple electronic documents. The changed seed weight may bias the identification of topics of the plurality of electronic documents in favor of the seed text as compared to one or more other text strings of the weight vector. The method may also include generating, a representation of a topic model for display to a user, the topic model may be based on the multiple electronic documents and the weight vector.

Abstract: An artificial intelligence (AI) model, using logistic regression and gradient boosting tree, may determine a priority score for a user. The priority score may be associated with a likelihood of redemption of investment funds of the user by the user. Based on the priority score for the user, a server may prioritize transmission of a communication message to the user via one of a plurality of communication channels. The communication message may describe why the user should continue with their investment funds without redemption.

Abstract: A user of an automated natural language system may submit an ambiguous or incomplete request, and interactive techniques may be used to obtain clarification information from the user and then determine a response for presentation to the user. A user's initial request may be processed to compute a category score for each possible category of request. The category scores may be processed to determine if clarification of the request is needed. Where clarification is needed, one or more tags may be selected to determine a clarification question to be presented to the user. For example, a tag clarification score may be computed for each tag that indicates a value of the tag in clarifying the request. After receiving the clarification information from the user, one or more categories may be selected or, where needed, additional clarification information may be obtained.

Abstract: A mobile application and a method are described for servicing a second line service (“SLS”) based communication request originating from a subscriber's telecommunications device (“TD”) even if the call signal does not include sufficient information to identify the phone number from which the subscriber initiated the call. The method involves associating the SLS phone number of the subscriber, the primary number of the subscriber and the primary number of a third party via a special relationship number.

Abstract: Systems, devices, and methods discussed herein acquiring new definitions for entities from natural language queries. User input comprising a natural language expression may be obtained. A definiendum entity and one or more defining predicates may be identified from the natural language expression based at least in part on a predefined logical form template. An ontology may be search to determine whether the definiendum entity has a previously provided definition in the ontology. The defining predicates are converted to a logical form representation and optimized such that executing the optimized representation as a query against a knowledge base generates a number of results within a predefined acceptable range (e.g., meets/exceeds a lower threshold and/or meets/falls under an upper threshold). The optimized representation may then be added to the ontology.

Abstract: A machine translation method includes: receiving to-be-processed information expressed in a source language; encoding the to-be-processed information, and generating an expression vector sequence of the to-be-processed information; and predicting feature information of a target foresight word at a first moment by using a prediction model. The feature information includes at least one of a part of speech or a word category of the target foresight word. The method also includes: determining a context vector corresponding to the first moment in the expression vector sequence according to the feature information of the target foresight word; and decoding the context vector by using a decoder, to obtain target content that corresponds to the context vector and expressed in a target language.

Abstract: The present disclosure provides method and apparatus for generating responses in automated chatting. A message may be received in a session. An intention vector may be determined based at least on the message and the session through dynamic memory network (DMN), the intention vector indicating an attention point and an intention. A response may be generated based at least on the intention vector.

Abstract: Methods, systems, and computer-readable media are provided for communicating healthcare-related information in languages specified by communication recipients (e.g., patients and/or patient proxies) utilizing a healthcare IT platform. Aspects herein provide a tool for applying language maps specific to patient-specified languages to information associated with one or more segments of Health Level 7 (HL7) messages to generate communications that can be consumed and understood by communication recipients regardless of the language in which such communication recipients prefer to communicate and whether or not a communication recipient's preferred language is the same as that of a communicating healthcare provider or organization.

Abstract: In some implementations, a computing device can present a multi-language grouping of topics. For example, the computing device can determine a primary and secondary language for a user of the computing device. The computing device can request configuration that includes a tag language mapping that can be used to translate topic tags corresponding to the secondary language to topic tags corresponding to the primary language. When the computing device receives tagged content items associated with the secondary language, the computing device can translate the secondary language tags corresponding to the tagged content items into semantically equivalent topic tags in the primary language. The computing device can then group primary language content items and secondary language content items into multi-language groupings based on the topics corresponding to the translated content item tags. The computing device can then present the multi-language topic groupings of content items.

Abstract: A method of predicting a mood state of a user may include recording an audio sample via a microphone of a mobile computing device of the user based on the occurrence of an event, extracting a set of acoustic features from the audio sample, generating one or more emotion values by analyzing the set of acoustic features using a trained machine learning model, and determining the mood state of the user, based on the one or more emotion values. In some embodiments, the audio sample may be ambient audio recorded periodically, and/or call data of the user recorded during clinical calls or personal calls.

Abstract: An enhanced abandoned call recovery (“E-ACR”) process allows certain abandoned calls to be eligible for a callback call. An E-ACR assignment point defines which abandoned calls in an inbound campaign or interactive voice response (“IVR”) menu are eligible to be processed to determine whether the E-ACR callback should occur. The determination of whether a callback occurs involves various compliance tests, such as ensuring calling window, call attempts, and other regulatory concerns are addressed. Once a callback is determined to occur, it is associated with a specific campaign to ensure the called party is provided with agents having the skill set as defined for that assignment point. In this manner, only eligible callers receive an E-ACR callback, and further receive the callback in a compliant manner and handled by the same skill set of agents as would have been allocated to the caller had they not abandoned their call.

Abstract: In at least one embodiment, a vehicle apparatus is provided. The apparatus includes a core, a nose, a first loudspeaker, and a first loudspeaker housing. The core is positioned within a headrest for a seat of a vehicle. The nose attaches to the core and is positioned within the headrest. The first loudspeaker is positioned on the nose for providing an audio signal from the headrest. The first loudspeaker housing receives the first loudspeaker and is positioned on the nose. The first loudspeaker housing extends along a first outer edge of the core to decrease an overall length of the core and the nose along a first axis in the vehicle.

Abstract: Systems and methods of instant-messaging bot for robotic process automation (RPA) and robotic textual-content extraction from digital images include a chatbot application, a software RPA manager, and an instant-messaging (IM) platform, all built for an enterprise. The enterprise IM platform is connected to one or more public IM platforms over the Internet. The RPA manager contains multiple modules of enterprise workflows and receives instructions from the enterprise chatbot for executing individual workflows. The system allows enterprise users connected to the enterprise IM platform, and external users connected to the public IM platforms, to use instant messaging to initiate enterprise workflows that are automated with the help of the enterprise chatbot and delivered via instant messaging. Furthermore, textual-content extraction from digital images is incorporated in the RPA manager as an enterprise workflow, and provides improved convolutional neural network (CNN) methods for textual-content extraction.

Abstract: An example home bridge may perform receiving an out dial call from a user, parsing a call number to determine a country code, querying a bridge location database to determine a closest designated bridge to a country associated with the country code, providing to the designated bridge out dial data for the call, and lending the out dial call at the designated bridge.

Abstract: An adaptive conversational system may simultaneously monitor multiple active calls or ongoing voice or telephone conversations, may extract a different set of conversation elements from a current point in each conversation in real-time as each conversation proceeds, may determine different rules that apply to current points of different ongoing conversations based on the extracted conversation elements satisfying different rule triggers, and may control different conversations at different times according to actions of different rules that are applied at different times to different conversations. The system may selectively control the conversations when the conversations become non-compliant, deviate from best practices, or can be controlled to more effectively reach a positive disposition than when allowing a telephone agent to independently control the conversation.

Abstract: Systems and methods are provided to pre-train projection networks for use as transferable natural language representation generators. In particular, example pre-training schemes described herein enable learning of transferable deep neural projection representations over randomized locality sensitive hashing (LSH) projections, thereby surmounting the need to store any embedding matrices because the projections can be dynamically computed at inference time.

Abstract: An electronic device has one or more microphones that pick up a sound. At least one feature extractor processes the audio signals from the microphones, that contain the picked up the sound, to determine several features for the sound. The electronic device also includes a classifier that has a machine learning model which is configured to determine a sound classification, such as artificial versus natural for the sound, based upon at least one of the determined features. Other aspects are also described and claimed.

Abstract: This application relates to a systems and methods for trending issue identification in text streams. In one embodiment, a method for improving resolution of a trending issue identified in a set of text streams includes presenting a user interface of an application that is being executed by a computing device. The method also includes receiving a notification including the trending issue that has been identified in the set of text streams based at least in part on textual analysis performed on the set of text streams, and presenting the trending issue on the user interface of the application to enable an action to be performed to resolve the trending issue.

Abstract: A device and a method for generating a machine translation model and a machine translation device are disclosed. The device inputs a source training sentence of a source language and a dictionary data to a generator network so that the generator network outputs a target training sentence of a target language according to the source training sentence and the dictionary data. Then, the device inputs the target training sentence and a correct translation of the source training sentence to a discriminator network so as to calculate an error between the target training sentence and the correct translation according to the output of the discriminator network, and trains the generator network and the discriminator network respectively. The trained generator network is the machine translation model.