Abstract: A method, computer program product, and computing system for automatically generating a dialogue graph is executed on a computing device and includes receiving a plurality of conversation data. A plurality of utterance pairs from the plurality of conversation data may be clustered into a plurality of utterance pair clusters. A dialogue graph may be generated with a plurality of nodes representative of the plurality of utterance pair clusters.

Abstract: Disclosed herein are methods and systems for an intelligent, interactive, and augmented reality (AR) based user interface platform. The platform can be implemented in many applications, such as providing real-time intelligent and interactive control between user input data and the resulting AR data, providing real-time and effective AR-based communication, or providing real-time control of physical devices in a remote network.

Abstract: An interactive system may be implemented in part by an audio device located within a user environment, which may accept speech commands from a user and may also interact with the user by means of generated speech. In order to improve performance of the interactive system, a user may use a separate device, such as a personal computer or mobile device, to access a graphical user interface that lists details of historical speech interactions. The graphical user interface may be configured to allow the user to provide feedback and/or corrections regarding the details of specific interactions.

Abstract: An assembly of a receiver and a microphone, such as for positioning in an ear canal of a person. The receiver and microphone are provided in an overlapping relationship to take up less space while being able to emit sound in one direction and receive sound from that direction. When the assembly if for use deep inside the ear canal of a person, the microphone may be very small, as it is exposed to very high sound levels.

Abstract: A guidance system includes first and second HMDs. The first HMD includes a first image display section, and a reception section receiving an instruction, and a first control section generating output information in response to an instruction received by the reception section and transmitting the output information to the second HMD. The second HMD includes a second image display section displaying an image to be visually recognized in an overlapping manner with external scenery, a second storage section storing AR content including an AR image combined with external scenery visually recognized in the second display section, and a second control section displaying an image based on at least one of the AR content stored in the second storage section and the output information on the second display section according to a position of the second HMD or a visual field of external scenery visually recognized in the second display section.

Abstract: Methods and systems are provided for customizing an action. In some implementations, voice input is received from a user and a context is determined from the voice input. Potential contextual data is identified based on the context and the voice input. A level of confidence is determined for an association of the potential contextual data and the context. An action is performed based on the voice input, the potential contextual data, and the level of confidence. The potential contextual data is used to customize the action.

Abstract: A system and method of processing a search request is provided. Identification of a desired content item is based on comparing a topic of the search request to previous user input. The method includes providing access to a set of content items with metadata that describes the corresponding content items and providing information about previous searches. The method further includes receiving a present input from the user and determining a relatedness measure between the information about the previous searches and an element of the present input. If the relatedness measure is high, the method also includes selecting a subset of content items based on comparing the present input and information about the previous searches with the metadata that describes the subset of content items. Otherwise, the method includes selecting a subset of content items based on comparing the present input with the metadata that describes the subset of content items.

Abstract: Systems and processes for accelerating task performance are provided. An example method includes, at an electronic device including a display and one or more input devices, displaying, on the display, a user interface including a suggestion affordance associated with a task, detecting, via the one or more input devices, a first user input corresponding to a selection of the suggestion affordance, in response to detecting the first user input: in accordance with a determination that the task is a task of a first type, performing the task, and in accordance with a determination that the task is a task of a second type different than the first type, displaying a confirmation interface including a confirmation affordance.

Abstract: Provided are various methods of data collection and providing feedback to business owners and other types of venues using a software application. The software application includes various levels including a venue software application level, a consumer software application level and a cloud-based server software application level. The consumer software application is downloaded onto a smart device and notifications are sent to the smart device when a consumer enters a venue's defined geo-fences. The notification informs the consumer of survey-voucher pairs, where vouchers may be redeemed in exchange for the consumer completing surveys. The information obtained from the surveys provides feedback to venues and business owners.

Abstract: Compiling selectable human computer interaction modes for at least one link on the multimedia interactive website, where the selectable human computer interaction modes at least include: a voice mode and a non-voice mode; monitoring a link to be accessed that is selected on the multimedia interactive website by a user, and identifying a human computer interaction mode that is selected by the user for the link to be accessed; when it is identified that the user selects the voice mode, jumping to a page used for guiding a user to provide a voice, guiding the user to provide a voice on the page, and acquiring voice data provided on the page by the user; and determining whether the voice data satisfies a set requirement for triggering the link to be accessed, and if yes, providing information corresponding to the link to be accessed.

Abstract: Some implementations are directed to selective invocation of a particular third-party (3P) agent by an automated assistant to achieve an intended action determined by the automated assistant during a dynamic dialog between the automated assistant and a user. In some of those implementations, the particular 3P agent is invoked with value(s) for parameter(s) that are determined during the dynamic dialog; and/or the particular 3P agent is selected, from a plurality of candidate 3P agents, for invocation based on the determined value(s) for the parameter(s) and/or based on other criteria. In some of those implementations, the automated assistant invokes the particular 3P agent by transmitting, to the particular 3P agent, a 3P invocation request that includes the determined value(s) for the parameter(s).

Abstract: Computer-based natural language understanding of input and output for a computer interlocutor is improved using a method of classifying conversation segments from transcribed conversations. The improvement includes one or more methods of splitting transcribed conversations into groups related to a conversation ontology using metadata; identifying dominant paths of conversational behavior by counting the frequency of occurrences of the behavior for a given path; creating a conversation model comprising conversation behaviors, metadata, and dominant paths; and using the conversation model to assign a probability score for a matched input to the computer interlocutor or a generated output from the computer interlocutor.

Abstract: Various implementations include wearable audio devices having a spatialized virtual personal assistant (VPA). In other implementations, a method of controlling a wearable audio device having a spatialized VPA is disclosed. Other implementations include a method of generating a spatialized VPA in a wearable audio device.

Abstract: Implementations include actions of obtaining a set of entities based on one or more terms of a query, obtaining one or more entities associated with each live event of a plurality of live events, identifying a live event that is responsive to the query based on comparing at least one entity in the set of entities to one or more entities associated with each live event of a plurality of live events, determining that an event search result corresponding to the live event is to be displayed in search results, and in response: providing the event search result for display, the event search result including information associated with the live event, the information including an indicator of an occurrence of the live event.

Abstract: In representative embodiments, a digital assistant is extended by service activities. A service activity executes as a service as part of the digital assistant. A service activity specifies a set of user data to be provided when invoked, at least one insight used to invoke the service activity in a proactive way and at least one intent used to invoke the service activity in a reactive way, and executable code that is executed when the service activity is invoked. A development environment provides templates to ease development of service activities. Service activities in development can be deployed alongside production services with access to service activities in development restricted to a set of authorized users.

Abstract: Sensor data is received from a physical environment sensor. A component region associated with at least a portion of the sensor data is identified. A physical environment has been defined to include a plurality of component regions. Context information associated with the identified component region is obtained. The context information is utilized in association with a prediction model.

Abstract: A computing system is provided. The computing system includes a processor of a display device configured to execute one or more programs. The processor is configured to receive a command from a user by way of natural language input. The processor is configured to identity a set of candidate objects within or adjacent a user's field of view having associated spatialized regions on which the command can be executed, the set of candidate objects identified at least partially by using a machine learning model. The processor is configured to use visual or audio indicators associated with the candidate objects and query the user for disambiguation input. The processor is configured to receive the disambiguation input from the user that selects a target object, executing the command on the target object. The processor is configured to train the machine learning model using the disambiguation input and data about the spatialized regions.

Abstract: A system that incorporates teachings of the present disclosure may include, for example, a system that generates an avatar having a first behavior determined by a user profile of a user. An avatar profile is received from a content source for modifying the avatar according to a second behavior. The avatar is modified to generate an adaptive avatar based on the avatar profile. The adaptive avatar has, at least in part, the second behavior determined by the avatar profile, while retaining, at least in part, the first behavior determined by the user profile of the user. Other embodiments are disclosed.

Abstract: Provided are systems and methods for implementing a digital assistant for therapeutic treatments via a transmitting device (e.g., smartphone, tablet, laptop, smart speaker, smart-wearable, etc.) In one example, the method may include one or more of receiving a speech input command from a transmitting device, converting the speech input command into text and identifying a user from among a plurality of users based on the text converted from the speech input command, determining a treatment to be performed for the identified user based on historical treatments given to the identified user stored in a database, and outputting, to the transmitting device, a speech response describing the determined treatment to be performed on the identified user.

Abstract: A selective sensor polling system for a voice activated data packet based computer network environment is provided. A system can receive audio signals detected by a microphone of a device. The system can parse the audio signal to identify trigger keyword and request. The system can select a template for an action data structure with a plurality of fields. The system can determine to poll a first sensor for data for the first field. The system can determine to obtain data in memory previously collected by the second sensor. The system can generate and transmit the action data structure with the data from the sensor and memory, and transmit the action data structure to a third party device.

Abstract: A speech interface device is configured to process user speech by storing, in volatile memory of the speech interface device, audio data that represents user speech, and inputting first audio data, of the stored audio data, to an automatic speech recognition (ASR) component of the speech interface device, determining that a criterion is satisfied, and, based on the criterion being satisfied, maintaining second audio data in the volatile memory. The ASR component may generate text data based on the first audio data, a natural language understanding (NLU) component of the speech interface device may generate NLU data based on the text data, and, if the NLU data corresponds to a recognized intent, the second audio data may be deleted. Otherwise, speech processing can be resumed by inputting the second audio data to the ASR component.

Abstract: A retrieval result providing device includes a retrieval unit which acquires an individual retrieval result having item values of a plurality of items by a retrieval based on a keyword, an unprocessed sentence generation unit which generates an unprocessed sentence where retrieval result corresponding sentences with the item values arranged are arranged, an output sentence generation unit which performs at least one of a first process of erasing some of the sentences on the basis of a commonality between a word and the keyword contained in the retrieval result corresponding sentences, a second process of erasing some of the sentences on the basis of a commonality of the item values of specific items in the different sentences, and a third process of erasing some of the sentences on the basis of a commonality of the item values of a plurality of different items in one sentence so as to generate an output sentence, and an output sentence output unit which outputs a voice based on the output sentence.

Abstract: It is determined whether a first voice instruction received by a first voice control device and a second voice instruction received by a second voice control device are repetitive instructions. Output by an output apparatus is restricted if it is determined that the first voice instruction and the second voice instruction are repetitive instructions.

Abstract: Systems and methods are described for recognizing and responding to commands. A system may receive voice data and determine an intended command. The system may then determine a position and viewpoint orientation of the user to be able to determine one or more digital assets associated with the user. The system may then determine a current state associated with each digital asset of the one or more digital assets to be able to determine at least one digital asset that is configured to process the command. The system can then apply the command to at least a first digital asset of the at least one digital asset that is configured to process the command.

Abstract: The present disclosure relates to generating digital responses based on digital dialog states generated by a neural network having a dynamic memory network architecture. For example, in one or more embodiments, the disclosed system provides a digital dialog having one or more segments to a dialog state tracking neural network having a dynamic memory network architecture that includes a set of multiple memory slots. In some embodiments, the dialog state tracking neural network further includes update gates and reset gates used in modifying the values stored in the memory slots. For instance, the disclosed system can utilize cross-slot interaction update/reset gates to accurately generate a digital dialog state for each of the segments of digital dialog. Subsequently, the system generates a digital response for each segment of digital dialog based on the digital dialog state.

Abstract: Methods, systems, and computer program products for unsupervised learning of interpretable conversation models from conversation logs are provided herein. A computer-implemented method includes obtaining human-to-human conversation logs; training a deep learning model by (i) learning, in an unsupervised manner, semantic labels for dialog contexts in the multiple human-to-human conversation logs, (ii) mapping the learned semantic labels to query responses across the multiple human-to-human conversation logs, and (iii) inferring one or more entities from the multiple conversation logs based at least in part on the mapping; constructing a human-interpretable conversation model based at least in part on patterns determined via the trained deep learning model; and outputting the human-interpretable conversation model to at least one user.

Abstract: A system, apparatus, and method for generating one or more path rules or combination or path rules for performing the operations of an application. According to various embodiments, a user terminal through an intelligence server may generate a path rule and may perform the operation of an application based on the path rule to provide a service. The user terminal may provide a user with the processing status of a user utterance and may receive an additional user input to process the user utterance. For example, when a keyword (or parameter) required to process the user utterance is insufficient, the user terminal may provide the user with a state requiring additional information and may output feedback corresponding to the insufficient state in order to receive the necessary information from the user.

Abstract: A computer-implemented method for verifying identity of a speaker is proposed. A low dimensional p-vector based on a speech of the speaker is extracted from the generated high dimensional speaker model and is then compared with the stored specific speaker's p-vector obtained previously during the enrollment process. The resulting biometric score is then used to determine whether to verify the speaker, or not.

Abstract: Utterance-based user interfaces can include activation trigger processing techniques for detecting activation triggers and causing execution of certain commands associated with particular command pattern activation triggers without waiting for output from a separate speech processing engine. The activation trigger processing techniques can also detect speech analysis patterns and selectively activate a speech processing engine.

Abstract: A method of controlling illumination emitted by one or more illumination sources of a lighting system is disclosed. The method comprises automatically performing operations of: receiving from a speech recognition system a first input indicative of a first speech command; in response to the first input, controlling the lighting system to transition from a first state comprising a first value of a parameter of the illumination to a second state comprising a second value of the parameter; receiving from the speech recognition system a second input indicative of a second speech command, the second input indicating that the second speech command specifies a further change in the parameter; mapping the second input to an adjustment defined at least in part based on the first and second values of the parameter; and controlling the lighting system to transition from the second state to a further adjusted state by adjusting the parameter.

Abstract: An information processing device includes a processor configured to acquire voice data of a voice uttered by a user, recognize the acquired voice, determine a timing of an interjection in accordance with time from completion of the voice data acquisition to start of output of a response generated based on a result of the voice recognition, output the interjection at the determined timing of the interjection, and output the response at the time of start of the output of the response.

Abstract: The present disclosure relates to traversing and processing objects in an object graph. The method and system evaluate an object in the graph to identify one or more objects referenced by the first object. The second object is evaluated to determine whether it is present in a list or previously visited objects, and when it is not, the second object is added to a container of objects and the second object is added to the list of previously visited objects. The first object is processed and then the next object in the container is evaluated.

Abstract: Systems and methods for voice control of computing devices are disclosed. Applications may be downloaded and/or accessed by a device having a display, and content associated with the applications may be displayed. Many applications do not allow for voice commands to be utilized to interact with the displayed content. Improvements described herein allow for non-voice-enabled applications to utilize voice commands to interact with displayed content by determining screen data displayed by the device and utilizing the screen data to determine an intent associated with the application. Directive data to perform an action corresponding to the intent may be sent to the device and may be utilized to perform the action on an object associated with the displayed content.

Abstract: Computer-based systems and methods add extra terms to the objective function of machine learning systems (e.g., neural networks) in an ensemble for selected items of training data. This selective training is designed to penalize and decrease any tendency for two or more members of the ensemble to make the same mistake on any item of training data, which should result in improved performance of the ensemble in operation.

Abstract: For one embodiment, a computerized method for detecting exploit attacks on an interpreter comprises configuring a virtual machine including a user mode and a kernel mode and processing an object by an application operating in the user mode of the virtual machine. Responsive to the processing of the object, detecting a loading of an interpreter. Furthermore, responsive to the loading of the interpreter, inserting one or more intercept points for detecting one or more types of software calls from the interpreter or for detecting a certain type or certain types of activities occurring within the interpreter. Thereafter, an exploit attack is detected as being conducted by the object in response to the interpreter invoking a software call that corresponds to the one or more types of software calls that is considered anomalous when invoked by the interpreter or an anomalous activity being conducted within the interpreter.

Abstract: The present disclosure describes a communication environment having a service provider server that receives an audio command from a display control device within the communication environment. The service provider server can translate this audio command into an electrical command for controlling the display device. The service provider server autonomously performs a specifically tailored search of a catalog of command words and/or phrases for the audio command to translate the audio command to the electrical command. This specifically tailored search can include one or more searching routines having various degrees of complexity. The most simplistic searching routine from among these searching routines represents a textual search to identify one or more command words and/or phrases from the catalog of command words and/or phrases that match the audio command.

Abstract: Provided are methods, systems, and apparatuses for detecting, processing, and responding to audio signals, including speech signals, within a designated area or space. A platform for multiple media devices connected via a network is configured to process speech, such as voice commands, detected at the media devices, and respond to the detected speech by causing the media devices to simultaneously perform one or more requested actions. The platform is capable of scoring the quality of a speech request, handling speech requests from multiple end points of the platform using a centralized processing approach, a de-centralized processing approach, or a combination thereof, and also manipulating partial processing of speech requests from multiple end points into a coherent whole when necessary.

Abstract: The present disclosure relates to a method and apparatus for controlling an artificial intelligent smart illumination device, such as a light bulb, LED light, or the like. In one embodiment, a switching circuit for providing switchable power to the illumination device, and a processing circuit coupled to the switching circuit, for detecting one or more power toggles of the power received by the male base, and for controlling illumination of the illumination device based on the detection of one or more detected toggles (e.g., switches) is disclosed. The disclosure includes an artificial intelligent system, which can determine a lighting status based on the user's preference, living behaviors, time of a day, energy efficiency, energy costs, and any other light using conditions and factors.

Abstract: Embodiments of the present disclosure relate to a recurrent framework based on Recurrent Highway Networks (RHNs) for sequence modeling using batch normalization. In certain embodiments, constraints within the RHNs are relaxed to reduce or avoid gradient vanishing or exploding by normalizing the current transition units in highway layers.

Abstract: A system and method is provided for providing searchable customer call indexes. Consistent with disclosed embodiments, a system may receive call information associated with telephone conversations between callers and a vendor, the call information including an audio recording or transcript for each telephone conversation. The system may also identify one or more keywords from the audio recordings or transcripts and index the call information into one or more indexes based on the identified keywords. Finally, the system may determine search results responsive to a search query based on the indexing. In some embodiments, changes to customer service may be identified based on the search results.

Abstract: A device control apparatus controls an operation device. A plurality of persons is engaged in operations of the operation device. The device control apparatus comprises a control circuit configured to obtain voice instructions or voice responses from the plurality of persons, the voice instructions or voice responses including modalities of operations of the operation device, classify the modalities included in the voice instructions or voice responses, and determine a preferential operation of the operation device according to consistency between a first modalities classified from the voice instructions or a second modalities classified from the voice responses and priorities predefined for each person of the plurality of persons.

Abstract: This disclosure describes, in part, voice-controlled light dimmers that act as voice-controlled endpoints at which users may provide voice commands. These light dimmers include a front panel module coupled to a power module using a hardware interface. The front panel module may receive input from a user indicating commands for controlling appliances, and send communications to the power module using the hardware interface to control the appliances. In some examples, the communications involve encrypted data sent using an inter-integrated circuit (I2C) protocol using the hardware interface to an electrically isolated power module. The power provided to the appliances may be controlled by the power module of the voice-controlled light dimmer.

Abstract: Input access may be provided. A user interface may be displayed on a user device. Upon receiving a selection of at least one element of the user interface, a plurality of input receiving modes of the user device may be activated.

Abstract: Systems and methods for performing a task via a simple code. Combination of a unique marker and a simple code represents a task. A simple code is submitted by manual methods or voice inputs. Voice recognition techniques are used. In an aspect, a task is executed when a voice input comprises a device name and a simple code. In another aspect, a task is executed when a voice input comprises a simple code and a user gazes or gestures at a device.

Abstract: Provided is a method of recognizing text in a terminal, the method including generating first tag information about a kind of language set in a user interface (UI) for inputting text and a location of a cursor at a time point when a text input has started, when the UI for inputting text displayed on the terminal is executed; when a language switch request that requests the terminal to switch the kind of language set in the UI is received, generating second tag information about a kind of switched language and a location of the cursor at a time point of receiving the language switch request; when the text input is finished, storing a screen image of the terminal; and recognizing the text input to the terminal based on at least one piece of tag information and the screen image.

Abstract: The disclosure is directed to a software-hardware separated voice-controlled Bluetooth headset, which includes a receiver, a storage module, a voice receiving and transmitting module; a command receiving module and a Bluetooth module. and is used for converting audio electrical signals and sound signals. The storage module and the Bluetooth module which is electrically connected to the storage module are used for storing system firmware and system configuration files. The voice receiving and transmitting module is electrically connected with the Bluetooth module, and is configured to transmit the received voice information to a Bluetooth device that matches the headset. The command receiving module which is electrically connected to the Bluetooth module is designed to receive a voice message recognized by a Bluetooth device that matches the headset and send out a command.

Abstract: A voice recognition system includes a call connection control device that controls the call destination of a user, and a computer. The computer is configured to perform voice recognition of speech voice data of the user, determine an intention of a speech of the user based on a voice recognition result of the speech voice data, evaluate the reliability of a response generated by the computer for the user based on the determined intention of the speech of the user, and cause the call connection control device to switch the call destination of the user to an operator terminal in a case where the reliability of the response is equal to or less than a threshold value.

Abstract: Exemplary embodiments relate to a system for recovering a conversation between a user and the system when the system is unable to properly respond to a user's input. The system may process the user input and determine an error condition exists. The system may query one or more storage systems to identify candidate text data based on their semantic similarity to the user input. The storage systems may store data related to past frequently entered inputs and/or user-generated inputs. Alternative text data is selected from the candidate text data, and presented to the user for confirmation.

Abstract: Methods and computing systems are disclosed for a digital assistant platform that includes a cross-platform bot that can be used to bridge existing chat-bot platforms. The cross-platform bot would have its own single set of protocols and standards, such that a developer of a task-specific bot would only need to integrate with the cross-platform bot to enable its use across all the different chat-bot platforms. The cross-platform bot would enable the task-specific bots to coordinate to combine their functionality, while end users may continue using an existing chat-bot platform of their choice.

Abstract: A display apparatus, an electronic device, an interactive system, and controlling methods thereof are provided. The display apparatus includes: a storage unit which stores peripheral device control information in which a remote control signal for controlling a peripheral device of the display apparatus matches with a control signal corresponding to a user voice; a voice collector which the user voice; a communicator which transmits the collected user voice to the display apparatus and receives the control signal corresponding to the user voice from the display apparatus; an infrared ray (IR) transmitter which transmits the remote control signal for controlling the peripheral device; and a controller which, if the control signal is received from the display apparatus, controls the IR transmitter to transmit a remote control signal corresponding to the received control signal among remote control signals stored in the storage unit, to the peripheral device.