Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using frames for performing tasks. One of the methods includes receiving a first request to perform a task, the first request comprising user speech identifying the task; generating a frame associated with the task, wherein the frame comprises one or more types of values necessary to perform the task, and wherein each type of value can be satisfied by a respective value; receiving a second request to provide information related to a question, the second request comprising user speech identifying the question; providing information identifying the question to a search engine, and receiving a response identifying one or more terms; determining that at least one term can satisfy a type of value necessary to perform the task; and storing the at least one term in the frame.

The present application discloses a method and an apparatus for information query, and an electronic device, which relates to a field of deep learning (DL), natural language processing (NLP) and artificial intelligence (AI) technology. The method includes: receiving a query sentence, segmenting the query sentence to obtain word segments, and obtaining a dependency relationship between two word segments and part of speech of the word segments; obtaining a coding sequence of the query sentence according to the dependency relationship and the part of speech of the word segments; matching the coding sequence with a generalized template to obtain a core corpus of the query sentence, wherein the generalized template comprises part of speech to be extracted and a dependency relationship to be extracted; and obtaining a query result corresponding to the query sentence based on the core corpus. The application no longer relies on the accumulation of massive business scenario data to enhance a generalization ability, which ensures accurate and efficient information query, and improves the efficiency and reliability of the information query process. At the same time, it may support information query in different business scenarios, with strong expansion capability and high universality.

The present application discloses a method and an apparatus for information query, and an electronic device, which relates to a field of deep learning (DL), natural language processing (NLP) and artificial intelligence (AI) technology. The method includes: receiving a query sentence, segmenting the query sentence to obtain word segments, and obtaining a dependency relationship between two word segments and part of speech of the word segments; obtaining a coding sequence of the query sentence according to the dependency relationship and the part of speech of the word segments; matching the coding sequence with a generalized template to obtain a core corpus of the query sentence, wherein the generalized template comprises part of speech to be extracted and a dependency relationship to be extracted; and obtaining a query result corresponding to the query sentence based on the core corpus. The application no longer relies on the accumulation of massive business scenario data to enhance a generalization ability, which ensures accurate and efficient information query, and improves the efficiency and reliability of the information query process. At the same time, it may support information query in different business scenarios, with strong expansion capability and high universality.

A system, method, and computer-readable medium are disclosed for performing a lexicon construction operation. The lexicon construction operation includes: identifying a corpus, the corpus comprising a plurality of training events, each of the plurality of training events comprising a term; grouping terms from the plurality of training events into topic clusters; analyzing the plurality of topic clusters, the analyzing providing a plurality of classified clusters; and, deriving a plurality of learned lexicons from the plurality of classified clusters.

A system, method, and computer-readable medium are disclosed for performing a lexicon construction operation. The lexicon construction operation includes: identifying a corpus, the corpus comprising a plurality of training events, each of the plurality of training events comprising a term; grouping terms from the plurality of training events into topic clusters; analyzing the plurality of topic clusters, the analyzing providing a plurality of classified clusters; and, deriving a plurality of learned lexicons from the plurality of classified clusters.

Devices and techniques are generally described for application determination in speech processing. Input data corresponding to a spoken utterance may be received. Speech recognition processing may be performed on the input data to generate text data. A machine learning encoder may generate a vector representation of the input data. A first binary classifier may determine a first probability that the input data corresponds to a first speech-processing application. A second binary classifier may determine a second probability that the input data corresponds to a second speech-processing application. A selection between the first speech-processing application and the second speech-processing application may be made based at least in part on the first probability and the second probability.

Devices and techniques are generally described for application determination in speech processing. Input data corresponding to a spoken utterance may be received. Speech recognition processing may be performed on the input data to generate text data. A machine learning encoder may generate a vector representation of the input data. A first binary classifier may determine a first probability that the input data corresponds to a first speech-processing application. A second binary classifier may determine a second probability that the input data corresponds to a second speech-processing application. A selection between the first speech-processing application and the second speech-processing application may be made based at least in part on the first probability and the second probability.

Systems and methods for cognitive training using voice command are described. One aspect includes a device to repeatedly present visual stimuli to a user that require performance of a task. A microphone may be positioned to provide audio input from the user to the device, with the audio input from the user providing input required to measure task performance. A processing system may perform real-time analysis of measured task performance.

Computer-implemented methods, computer program products, and computer systems for detecting and resolving fraudulent calls. The computer-implemented methods include one or more processors configured for receiving voice call data corresponding to an incoming telephone call placed to a user device, wherein the voice call data comprises caller voice data. Further, the computer-implemented methods may include one or more processors configured for converting the caller voice data to caller text data comprising one or more text phrases. Further embodiments of the computer-implemented method include processors configured for determining that the one or more text phrases satisfies a first condition, and responsive to determining that the one or more text phrases satisfies the first condition, transmitting a user alert to the user device.

Computer-implemented methods, computer program products, and computer systems for detecting and resolving fraudulent calls. The computer-implemented methods include one or more processors configured for receiving voice call data corresponding to an incoming telephone call placed to a user device, wherein the voice call data comprises caller voice data. Further, the computer-implemented methods may include one or more processors configured for converting the caller voice data to caller text data comprising one or more text phrases. Further embodiments of the computer-implemented method include processors configured for determining that the one or more text phrases satisfies a first condition, and responsive to determining that the one or more text phrases satisfies the first condition, transmitting a user alert to the user device.