Abstract: A filtering method and system. The method includes receiving by a computer processor an audio/video data file and filtering data. The computer processor analyzes the filtering data with respect to the audio/video data file and retrieves specified audio/video data portions comprising data objects within frames of the audio/video data file. The computer processor removes gaps existing in the audio/video data file and receives tags comprising instructions for presenting video data of the audio/video data file, audio data of the audio/video data file, and the specified audio/video data portions. The computer processor stores the video data in a first layer of a multimedia file, the audio data in a second layer of the multimedia file, and the specified audio/video data portions in additional layers of the multimedia file. Each of the first layer, the second layer, and the additional layers comprises a tag layer comprising the tags.

Abstract: One embodiment provides a method for predicting a next action in a conversation system that includes obtaining, by a processor, information from conversation logs and a conversation design. The processor further creates a dialog graph based on the conversation design. Weights and attributes for edges in the dialog graph are determined based on the information from the conversation logs. An unrecognized user input the conversation system is detected. The unrecognized user input is analyzed and a next action is predicted based on dialog nodes in the dialog graph and historical paths. A guiding conversation response is generated based on the predicted next action.

Abstract: An audio activity detector device is disclosed. The audio activity detector device comprises a closed loop feedback regulating circuit that supplies an input signal representative of a time-varying voltage signal to a quantizer circuit, wherein the quantizer circuit, as a function of the input signal, converts the input signal to a quantizer discrete-time signal; a first circuit that, as a function of the discrete-time signal, determines a key quantizer statistic value for the quantizer discrete-time signal; and a second circuit that, as a function of the key quantizer statistic value, determines a signal statistic value for the input signal and a gain control value.

Abstract: A system, method and computer product are provided for processing audio signals. An audio signal of a voice and background noise is input, and speech recognition is performed to retrieve speech content of the voice. There is retrieval of content metadata corresponding to the speech content, and environmental metadata corresponding to the background noise. There is a determination of preferences for media content corresponding to the content metadata and the environmental metadata, and an output is provided corresponding to the preferences.

Abstract: A method, system, and computer program product are provided. At least some received event candidate information concerning a possible event is stored as an event candidate in a database. A dialogue is generated with an occupant of a vehicle located in a vicinity of the possible event to obtain and store information to resolve any insufficiency or ambiguity regarding the event candidate in the database. When the information stored in the database regarding the event candidate is determined to be sufficient and unambiguous the event candidate is made into an event in the database. The event is reported to at least one vehicle approaching a location corresponding to the event.

Abstract: A voice-activated computing device configured to transmit a pilot tone and then capture or receive a signal, which corresponds to the pilot tone, reflected from within the environment containing the voice-activated computing device. The voice-activated computing device, or some other computing system or device, analyzes the received signal in order to determine analyze one or more characteristics present within the signal, i.e. noise, echo, etc. Based upon the analysis, models for signal processing can be determined, selected and/or altered. Future signals received by the voice-activated computing device can be processed with such models. The analysis can also allow for the models to be dynamically updated and for models to be dynamically created.

Abstract: In one example, the present disclosure describes a device, computer-readable medium, and method for sentiment analysis tuning. In one example, the method, includes acquiring a first sentiment analysis-generated score for a first string of text, wherein the first string of text includes a first plurality of words, and wherein the first sentiment analysis-generated score is calculated using a set of first values associated with the first plurality of words, calculating a second value for at least one word of the first plurality of words, based on a non-sentiment-analysis generated score associated with the first string of text, acquiring a second string of text, wherein the second string of text includes a second plurality of words, and wherein the second plurality of words includes the at least one word, and calculating a sentiment analysis-generated score for the second string of text, using the second value for the at least one word.

Abstract: From a set of information obtained about a user, a profile is constructed representing a speech skill of the user, the set of information including audio, video, and demographic information of the user and other users, the constructing creating new data corresponding to the speech skill of the user in the profile. By correlating analytics of new real-time audio and video information with the new data in the profile, an intervention instruction is triggered automatically, the intervention being directed to change in a voice communication pattern of the user. The intervention is converted to an intervention instruction and the intervention instruction is output in a natural language form. New real-time audio and video information received in response to the spoken natural language instruction is analyzed.

Abstract: The present invention relates to a multilevel memory bus system for transferring information between at least one DMA controller and at least one solid-state semiconductor memory device, such as NAND flash memory devices or the like. This multilevel memory bus system includes at least one DMA controller coupled to an intermediate bus; a flash memory bus; and a flash buffer circuit between the intermediate bus and the flash memory bus. This multilevel memory bus system may be disposed to support: an n-bit wide bus width, such as nibble-wide or byte-wide bus widths; a selectable data sampling rate, such as a single or double sampling rate, on the intermediate bus; a configurable bus data rate, such as a single, double, quad, or octal data sampling rate; CRC protection; an exclusive busy mechanism; dedicated busy lines; or any combination of these.

Abstract: Implementations relate to techniques for providing context-dependent search results. A computer-implemented method includes receiving an audio stream at a computing device during a time interval, the audio stream comprising user speech data and background audio, separating the audio stream into a first substream that includes the user speech data and a second substream that includes the background audio, identifying concepts related to the background audio, generating a set of terms related to the identified concepts, influencing a speech recognizer based on at least one of the terms related to the background audio, and obtaining a recognized version of the user speech data using the speech recognizer.

Abstract: A computing device includes a display configured to present a graphical user interface. The graphical user interface includes a transcript portion configured to display an unannotated transcript representing an ordered sequence of one or more dialogue events involving a client and a computerized assistant, at least one of the dialogue events taking the form of an example client utterance, and an annotation portion configured to display a hierarchical menu including a plurality of candidate utterance annotations. An utterance annotation machine is configured to receive one or more computer inputs selecting, for each of one or more response parameters in the example client utterance, utterance annotations from the hierarchical menu that collectively define a machine-readable interpretation of the example client utterance. An annotated utterance having a predetermined format usable to train the computerized assistant is output to a data store based on the example client utterance.

Abstract: A method includes receiving marketing campaign associated data. The marketing campaign associated data is data associated with telephony communications from one or more telemarketing sources to a plurality of users. The method further includes applying a machine learning algorithm to the received marketing campaign associated data that determines anomalies associated with a subset of users of the plurality of users. The anomalies are determined based on audio signature of the telephony communications or based on telephony communications from a same source being disguised as different sources. The method includes identifying a marketing content within the telephony communications for the subset of users. The method also includes determining one or more common attributes between users within the subset of users and identifying a source of data breach based on the marketing content and further based on the one or more common attributes.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for speech recognition. One method includes obtaining an input acoustic sequence, the input acoustic sequence representing one or more utterances; processing the input acoustic sequence using a speech recognition model to generate a transcription of the input acoustic sequence, wherein the speech recognition model comprises a domain-specific language model; and providing the generated transcription of the input acoustic sequence as input to a domain-specific predictive model to generate structured text content that is derived from the transcription of the input acoustic sequence.

Abstract: Systems, methods and computer-readable media are provided for facilitating clinical decision support and managing patient population health by health-related entities including caregivers, health care administrators, insurance providers, and patients.

Abstract: A method for enhanced web browsing includes displaying additional information associated with potential leads referenced within the web content of web page. The method generally includes receiving, by an executable application associated with a web browser on a computer system, contents of a web page to be displayed by the web browser and parsing the content to identify one or more references to at least one potential lead, such as a business entity. The executable application then determines whether the at least one potential lead is associated with a record stored in a database, and displays the contents of the web page on the browser with the references highlighted and linked to the corresponding record in the database. Upon selecting the highlighted reference, an object comprising the information from the record in the database is displayed in the web browser.

Abstract: Methods and apparatus for audio identification during a performance are disclosed herein. An example method includes transforming a segment of audio into a log-frequency spectrogram based on a transform using a logarithmic frequency resolution. The log-frequency spectrogram is transformed into a binary image, each pixel of the binary image corresponding to a time frame and frequency channel pair. A matrix product of the binary image and a plurality of reference fingerprints is computed. Based on a number of frequency ranges represented in the binary image, the matrix product to form a similarity matrix is computed. Selecting an alignment of a line in the similarity matrix that intersects one or more bins in the similarity matrix with the largest calculated Hamming similarities. A reference fingerprint is selected based on the alignment.

Abstract: This disclosure describes, in part, techniques for identifying user-specific content items and/or time-based content items, as well as techniques for providing the content items to the user. For instance, a remote system may receive first audio data from an electronic device, where the first audio data represents a request to identify content related to a topic. The remote system can then store the topic in a database and use the topic to identify the content. Later, the remote system can then receive second audio data from the electronic device, where the second audio data represents a request for the content. The remote system can then send third audio data to the electronic device that represents at least a portion of the content.

Abstract: Aspects described herein may provide determination of compliance with accessibility rules by a webpage. A first version of a webpage may be compliant with the accessibility rules. The first version of the webpage may be modified to create the second version of the webpage. The second version of the webpage may be displayed. A voiceover of the second version of the webpage may be initiated. The voiceover may include starting automatic text-to-speech software that reads aloud the second version of the webpage. The voiceover of the second version of the webpage may be recorded and stored. A textual transcript of the stored recording may be generated. Compliance of the second version of the webpage with the accessibility rules may be determined based on the textual transcript of the stored recording and based on the first version of the webpage.

Abstract: An approach is provided that provides a tone optimization recommendation. The approach obtains a current tone inferred from digital content and a desired tone inference for a target audience. A tone optimization recommendation to reduce a difference between the current tone and the desired tone is determined using a processor. A memory is modified to save the tone optimization recommendation. The tone optimization recommendation is provided.

Abstract: Embodiments include method, systems and computer program products for enhancing a customer service process. Aspects include receiving customer data associated with a customer and creating a customer profile based on the customer data. Aspects also include obtaining customer service representative data comprising a customer service profile for each of a plurality of customer service representatives and determining a matching subset of the plurality of customer service representatives for the customer based upon the customer profile and the customer service representative data. Next, aspects include displaying, to the customer, the matching subset of the plurality of customer services representatives for the customer. Aspects also include selecting a first customer service representative from the matching subset of the plurality of customer service representatives for the customer based on a customer input.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for processing communications signals using a machine-learning network are disclosed. In some implementations, pilot and data information are generated for a data signal. The data signal is generated using a modulator for orthogonal frequency-division multiplexing (OFDM) systems. The data signal is transmitted through a communications channel to obtain modified pilot and data information. The modified pilot and data information are processed using a machine-learning network. A prediction corresponding to the data signal transmitted through the communications channel is obtained from the machine-learning network. The prediction is compared to a set of ground truths and updates, based on a corresponding error term, are applied to the machine-learning network.

Abstract: An electronic device is provided. The electronic device includes a microphone, a communication circuitry, an indicator configured to provide at least one visual indication, and a processor configured to be electrically connected with the microphone, the communication circuitry, and the indicator, and a memory. The memory stores instructions, when executed, cause the processor to receive a first voice input through the microphone, perform a first voice recognition for the first voice input, if a first specified word for waking up the electronic device is included in a result of the first voice recognition, display a first visual indication through the indicator, receive a second voice input through the microphone, perform a second voice recognition for the second voice input, and if a second specified word corresponding to the first visual indication is included in a result of the second voice recognition, wake up the electronic device.

Abstract: Techniques for naming devices via voice commands are described herein. For instance, a user may issue a voice command to a voice-controlled device stating, “you are the kitchen device”. Thereafter, the device may respond to voice commands directed, by name, to this device. For instance, the user may issue a voice command requesting to “play music on my kitchen device”. Given that the user has configured the device to respond to this name, the device may respond to the command by outputting the requested music.

Abstract: A data collection system is based on a general set of dialogue acts which are derived from a database schema. Crowd workers perform two types of tasks: (i) identification of sensical dialogue paths and (ii) performing context-dependent paraphrasing of these dialogue paths into real dialogues. The end output of the system is a set of training examples of real dialogues which have been annotated with their logical forms. This data can be used to train all three components of the dialogue system: (i) the semantic parser for understanding context-dependent utterances, (ii) the dialogue policy for generating new dialogue acts given the current state, and (iii) the generation system for both deciding what to say and how to render it in natural language.

Abstract: A computing system for virtual personal assistance includes technologies to, among other things, correlate an external representation of an object with a real world view of the object, display virtual elements on the external representation of the object and/or display virtual elements on the real world view of the object, to provide virtual personal assistance in a multi-step activity or another activity that involves the observation or handling of an object and a reference document.

Abstract: A method of operation of a navigation system includes: detecting a message overlap between a current audio message and a message delivery timeframe of a contemporaneous audio message; determining an audio message interchange between the current audio message and a contemporaneous audio message based on a message waveform of the current audio message, a remaining message duration of the current audio message, or a combination thereof; and delivering the current audio message and the contemporaneous audio message based on the audio message interchange.

Abstract: The invention relates to a method for determining and assisting an impairment in a patient's cognitive or emotional condition, the method comprising, receiving, by one or more computing devices, a first set of data from a patient, gathering, by one or more computing devices, a second set of data from a patients' computing device, analyzing, by one or more computing devices, a first portion of the first set of data with a pre-trained neural net, processing, by one or more computing devices, a second portion of the second set of data, calculating, by one or more computing devices, a value based on the analyzed first portion of the first set of data and the processed second portion of the second set of data.

Abstract: Various exemplary embodiments of the present disclosure relate to an operating method and an electronic device for sharing schedules between a first electronic device and a second electronic device. The method includes, detecting, at the first electronic device, a user input in a schedule sharing menu displayed on an email application screen. The method also includes, displaying, at the first electronic device, a schedule sharing input region according to the user input. The method further includes, receiving, at the first electronic device, schedule information input in the schedule sharing input region. The method also includes, storing, at the first electronic device, the schedule information in a schedule management application and a transfer protocol header. The method also includes, transmitting, at the first electronic device, an email including the transfer protocol header to the second electronic device.

Abstract: Embodiments are disclosed for transliteration based on a machine translation model training pipeline. A method according to some embodiments includes steps of: training a probabilistic model for transliteration from a first script system to a second script system using a machine translation model training pipeline; segmenting, using the probabilistic model, an input string in the first script system into phonemes that correspond to characters in the second script system; converting the phonemes in the first script system into the characters in the second script system, the characters forming a word or a word prefix in the second script system; and outputting the word or the word prefix in the second script system.

Abstract: The disclosed system continuously refines a model used by an Automatic Speech Recognition (ASR) system to enable fast and accurate transcriptions of detected speech activity. The ASR system analyzes speech activity to generate text transcriptions and associated metrics (such as minimum Bayes risk and/or perplexity) that correspond to the quality of or confidence in each generated transcription. The system employs a filtering process to select certain text transcriptions based in part on one or more associated quality metrics. In addition, the system corrects for known systemic errors within the ASR system and provides a mechanism for manual review and correction of transcriptions. The system selects a subset of transcriptions based on factors including confidence score, and uses the selected subset of transcriptions to re-train the ASR model. By continuously retraining the ASR model, the system is able to provide ever faster and more accurate text transcriptions of detected speech activity.

Abstract: An example symbol-based watermark detection method disclosed herein includes, in response to a comparison of a first count of occurrences of a first potential symbol value corresponding to a first symbol within a watermark and a second count of occurrences of a second potential symbol value corresponding to the first symbol, (i) determining a first accumulated signal to noise ratio value corresponding to the occurrences of the first potential symbol value, (ii) determining a second accumulated signal to noise ratio value corresponding to the occurrences of the second potential symbol value, and (iii) selecting one of the first or the second potential symbol value having a greatest accumulated signal to noise ratio value as a likely symbol value for the first symbol. The example method also includes concatenating the likely symbol value with other likely symbol values corresponding to other symbols of the watermark to detect the watermark.

Abstract: Methods, systems and computer program products for resource position planning are provided herein. A computer-implemented method includes generating a multi-commodity flow network for locations of a distributed service network over a planning horizon. The method also includes obtaining a set of candidate outage scenarios for the distributed service network, each of the set of candidate outage scenarios being associated with a corresponding probability of occurrence. The method also includes generating a resource positioning configuration for resources in the multi-commodity flow network utilizing an optimization model that reduces unmet demand for each of the set of candidate outage scenarios based at least in part on the probability of occurrence of each of the set of candidate outage scenarios.

Abstract: Methods described herein provide functionality for automatic speech recognition (ASR). One such embodiment performs speech recognition using received speech recognition result candidates, where the received candidates were generated by performing Statistical Language Model (SLM) based speech recognition on one or more frames of audio data. In turn, such an embodiment transmits results of the speech recognition, performed using the received speech recognition result candidates, to a user device via a communications network. Results of the speech recognition are available with lower latency than pure cloud based ASR solution.

Abstract: A method for mapping a plurality of input channels of an input channel configuration to output channels of an output channel configuration includes providing a set of rules associated with each input channel of the plurality of input channels, wherein the rules define different mappings between the associated input channel and a set of output channels. For each input channel of the plurality of input channels, a rule associated with the input channel is accessed, determination is made whether the set of output channels defined in the accessed rule is present in the output channel configuration, and the accessed rule is selected if the set of output channels defined in the accessed rule is present in the output channel configuration. The input channels are mapped to the output channels according to the selected rule.

Abstract: Systems and processes are disclosed for dynamically adjusting a speech trigger threshold, which can be used in triggering a virtual assistant. Audio input can be received via a microphone. The received audio input can be sampled, and a confidence level can be determined of whether the sampled audio input includes a portion of a spoken trigger. In response to the confidence level exceeding a threshold, a virtual assistant can be triggered to receive a user command from the audio input. The threshold can be dynamically adjusted in response to perceived events (e.g., events indicating a user may be more or less likely to initiate speech interactions, events indicating a trigger may be difficult to detect, events indicating a trigger was missed, etc.), thereby minimizing both missed triggers and false positive triggering events.

Abstract: This invention is an improvement of technology for automatically generating response voice to voice uttered by a speaker (user), and is characterized by controlling a pitch of the response voice in accordance with a pitch of the speaker's utterance. A voice signal of the speaker's utterance (e.g., question) is received, and a pitch (e.g., highest pitch) of a representative portion of the utterance is detected. Voice data of a responsive to the utterance is acquired, and a pitch (e.g., average pitch) based on the acquired response voice data is acquired. A pitch shift amount for shifting the acquired pitch to a target pitch having a particular relationship to the pitch of the representative portion is determined. When response voice is to be synthesized on the basis of the response voice data, the pitch of the response voice to be synthesized is shifted in accordance with the pitch shift amount.

Abstract: A method and device for temporally sequenced recommendations of activities delivers to users temporally sequenced objects comprising user activities, wherein the delivered objects are selected based, at least in part, on inferences of preferences from usage behaviors. The delivered objects may include activities associated with processor-based devices in addition to human activities. Variations of the system and method include delivering the temporally sequenced objects in accordance with the contents of the objects and user feedback with regard to the objects. Information as to why objects were delivered to users may be provided to the users.

Abstract: A method, and device, for enhancing speech generated from bone and tissue conduction of a user of an In-ear device in a noisy environment, the Intra-aural device having an in-ear microphone adapted to be in fluid communication with the ear canal of the user and an outer-ear microphone adapted to be in fluid communication with the environment outside the ear. The method comprises applying an adaptive filter on the in-ear microphone signal, using the outer-ear microphone signal as a reference for the ambient noise and interrupting the application of the adaptive filter to the In-ear microphone signal upon detecting speech by the user.

Abstract: Systems and methods determine whether domain names are potentially maliciously registered variants of a set of monitored domain names. A computer system can receive domain names from a feed of newly registered domain names. For each received domain name, the computer system can generate a series of images of the domain name in different fonts and/or with various distortions applied thereto. The computer system can then transform the domain name images back to text via optical character recognition. Due to the differences in fonts and/or distortions applied to the generated images of the received domain name, the optical character recognition process can produce different text strings than the originally received domain name. The converted textual domain names are then analyzed to determine whether any one is sufficiently similar to a monitored domain name, indicating that the received domain name could be a malicious variant thereof.

Abstract: A method at a first electronic device of a local group of connected electronic devices includes: receiving a first voice command including a request for a first operation; determining a first target device for the first operation from among the local group; establishing a focus session with respect to the first target device; causing the first operation to be performed by the first target device; receiving a second voice command including a request for a second operation; determining that the second voice command does not include an explicit designation of a second target device; determining that the second operation can be performed by the first target device; determining whether the second voice command satisfies one or more focus session maintenance criteria; and if the second voice command satisfies the focus session maintenance criteria, causing the second operation to be performed by the first target device.

Abstract: A navigation system includes a detector configured to detect a situation in a movable object, a determiner configured to determine a degree of activity of conversation in the movable object on the basis of a detection result by the detector, a movement plan setter configured to set a movement plan on the basis of setting information which is set by a user, and to change at least part of the set movement plan on the basis of a determination result by the determiner, and a navigator configured to navigate the movable object on the basis of the movement plan which is set or changed by the movement plan setter.

Abstract: A User Equipment (UE) may receive a coverage mode transition request at a first time and upon determining that the coverage mode transition request includes a request to transition to an Enhanced Coverage (EC) mode, the UE may determine, based on parameters in the coverage mode transition request, an expected communication delay for transmission of a Reference Signal Time Difference (RSTD) measurement report. The UE may initiate transmission of the RSTD measurement report for the positioning measurement session at a second time not exceeding a specified RSTD measurement time. The second time may precede an RSTD measurement timeout time for the positioning measurement session by at least the expected communication delay. Disclosed embodiments also pertain to communication of the expected communication delay between a Location Server (e.g. Evolved Serving Mobile Location Center) and a Base Station (e.g. evolved NodeB) using Long Term Evolution Positioning Protocol Annex (LPPa) messages.

Abstract: Embodiments presented herein provide techniques for inferring the current emotional state of a user based on paralinguistic features derived from audio input from that user. If the emotional state meets triggering conditions, the system provides the user with a prompt which allows the user to connect with a support agent. If the user accepts, the system selects a support agent for the user based on the predicted emotional state and on attributes of the support agent found in an agent profile. The system can also determine a priority level for the user based on the score and based on a profile of the user and determine where to place the user in a queue for the support agent.

Abstract: An example apparatus for routing audio streams includes an audio receiver to receive audio from a microphone. The apparatus also includes a classifier to semantically generate a result set based on the audio. The apparatus further includes a scheduler to select a spoken language understanding (SLU) engine based on the result set. The apparatus includes a router to route the audio to the selected SLU engine.

Abstract: Aspects of the subject disclosure may include, for example, detect a first user interaction with a control button, disable an initiation of an action for a communication service, detect a second user interaction with the icon, and transmit an identification signal to a second communication device that causes the second communication device to present identification information describing the action for the communication service. Other embodiments are disclosed.

Abstract: A multi-cloud user interface apparatus facilitates transparent use of multiple Internet-based clouds. A network interface compatibly interacts with the multiple Internet-based clouds, a database management system of information, and a user interface that includes a non-human agent. The database management system pertains to a world model that represents a plurality of entities such as workgroups, products, humans, animals, plants, positions, and assets. The database itself can be configured such that the items of information are partially but not wholly stored on individual ones of each of the multiple Internet-based clouds. The non-human agent can be configured to receive input from a human user and to respond to the input by accessing the database. The nature of the response can be automatically derived as a function of an information relevance measurement that is itself calculated as a function, at least in part, of an entity relationship-based metric.

Abstract: Wireless headphones with user controls and methods for using are disclosed. In one embodiment, a wireless headphone includes a left earcup comprising a left speaker driver and a left earcup housing; and a right earcup comprising a right speaker driver and a right earcup housing; a processor; a microphone; user controls including: a voice assistant activator control; a volume slider; a play control slider; a play-pause control; and instructions configuring the processor to: commence a voice assistant recognition routine when sound received by the microphone matches a wake word, and perform an action based on instructions returned from the voice assistant; update a current volume of the headphone to a higher volume when the volume slider receives a swipe; skip to a next track of a current media content when the play control slider receives a swipe; and toggle playback of the media content when the play-pause control is activated.

Abstract: An electronic device includes an audio synthesizer. The audio synthesizer can generate a voice-synthesized audio output stream as a function of one or more audible characteristics extracted from voice input received from an authorized user of the electronic device. The audio synthesizer can also apply an acoustic watermark to the voice-synthesized audio output stream, the acoustic watermark indicating that the voice-synthesized audio output stream is machine made.

Abstract: A system for generating a psychographic device fingerprint includes a server in communication with a network and memory storing a program which, when executed by the server, performs steps for (a) detecting reception at a computing device of media content delivered via the network, (b) reading device elements stored on the computing device, (c) reading a geographic indicator from the computing device, (d) reading a content indicator identifying the media content, (e) determining a timing parameter associated with reception of the content at the computing device, and (f) deriving from the device type, the geographic indicator, the content indicator, and the timing parameter, the psychographic device fingerprint as computer readable code uniquely identifying a user of the computing device. The steps may further include recording media content received by multiple computing devices, and generating a viewership report relating computing devices and psychographic device fingerprints to the media content received.

Abstract: A natural language query (NLQ) is translated to a structured data query (e.g., a SQL statement) by extracting entities from the NLQ and replacing them with generic variables to form a generic query. The generic query is associated with a structured question type which includes structured data variables using natural language classifiers (NLCs). Specific data is inserted in the structured question type in relation to the structured data variables based on the extracted entities to form the structured data query. An ensemble of NLCs trained with different ground truths can be used to yield multiple candidate question types. One of the candidate question types is selected based on confidence levels. The multiple NLCs can include an NLC which is optimized according to a focus of the generic query. For example, an NLC can be optimized for a specific data structure (such as SQL), or for comparative queries.