An intelligent automated assistant system engages with the user in an integrated, conversational manner using natural language dialog, and invokes external services when appropriate to obtain information or perform various actions. The system can be implemented using any of a number of different platforms, such as the web, email, smartphone, and the like, or any combination thereof. In one embodiment, the system is based on sets of interrelated domains and tasks, and employs additional functionally powered by external services with which the system can interact.

Intelligent Automated Assistant

One embodiment of a method for facilitating creation of an annotated media stream by a user includes receiving the media stream from the user, mapping at least one item of supplemental content to at least a portion of the media stream to produce the annotated media stream, and storing the annotated media stream. In another embodiment, a method for distributing an annotated media stream provided by a user includes receiving the annotated media stream from the user, where the annotated media stream includes at least one item of supplemental content mapped to at least a portion of a media stream to produce the annotated media stream, storing the annotated media stream, receiving a request from a viewer to view the annotated media stream, and distributing the annotated media stream to the viewer.

Method and apparatus for annotating media streams

A virtual assistant uses context information to supplement natural language or gestural input from a user. Context helps to clarify the user's intent and to reduce the number of candidate interpretations of the user's input, and reduces the need for the user to provide excessive clarification input. Context can include any available information that is usable by the assistant to supplement explicit user input to constrain an information-processing problem and/or to personalize results. Context can be used to constrain solutions during various phases of processing, including, for example, speech recognition, natural language processing, task flow processing, and dialog generation.

Using context information to facilitate processing of commands in a virtual assistant

A method involving computer-mediated linguistic analysis of online technical documentation to extract and catalog from the documentation knowledge essential to, for example, creating a online help database useful in providing online assistance to users in performing a task. The method comprises stripping markup tags from the documentation, linguistically analyzing and annotating the text, including the steps of morphologically and lexically analyzing the text, disambiguating between possible parts-of-speech for each word, and syntactically analyzing and labeling each word. The method further comprises the steps of combining the linguistically analyzed, annotated, and labeled text and previously stripped markup information into a merged file, mining the merged file for domain knowledge, including the steps of identifying and creating a list of technical terminology, mining the merged file for manifestations of domain primitives and maintaining a list of manifestations of such domain primitives in an observations file, analyzing the discourse context of each sentence or phrase in the merged file, analyzing the frequency of manifestations of domain primitives in the observations file to determine those that are important, expanding the list of key terms by searching for terms sanctioned by a domain primitive deemed important in the previous step, and searching the merged file for larger relations by searching for particular lexico-syntactic patterns involving key terms and manifestations of domain primitives previously identified. The method further comprises the steps of structuring the knowledge thus mined and building a domain catalog.

Method for extracting knowledge from online documentation and creating a glossary, index, help database or the like

A method is provided for modifying an image. The method comprises displaying an image, the image comprising a portion of an object; and determining if an edge of the object is in a location within the portion. The method further comprises detecting movement, in a member direction, of an operating member with respect to the edge. The method still further comprises moving, if the edge is not in the location, the object in an object direction corresponding to the detected movement; and modifying, if the edge is in the location, the image in response to the detected movement, the modified image comprising the edge in the location.

Information processing apparatus, information processing method and program

A metadata preparing device comprising a content reproducing unit (1) for reproducing and outputting content, a monitor (3) for monitoring the content reproduced by the content reproducing unit, a voice input unit (4), a voice recognition unit (5) for recognizing a voice signal input from the voice input unit, a metadata generation unit (6) for converting information recognized by the voice recognition unit into metadata, and an identification information imparting unit (7) for acquiring identification information that identifies respective parts in the content from the reproduced content supplied from the content reproducing unit, for imparting to metadata, wherein the generated metadata is so constructed as to be associated with respective parts in the content.

Metadata preparing device, preparing method therefor and retrieving device

A document data filing apparatus automatically selects attribute values indicating visual features of a desired document from the code data of document data inputted. The attribute value generation unit generates attribute values indicating visual features of the document data inputted as coded data from the document data input unit. At this point, the presence or absence of dot data and specific words and characters are judged. The document data storage unit stores the document data in association with its attribute for retrieval. The attribute value designation unit makes an operator designate the attribute value as retrieval key to the document data to be retrieved The readout unit reads the document data corresponding to the designated attribute value from the document data storage unit. The display unit displays the document data. The retrieving technique is applied to a word processor.

Document data filing apparatus for generating visual attribute values of document data to be filed

A content shooting apparatus is provided, in which thresholds for generating metadata concerning shot images can be calibrated in accordance with shooting conditions. In a content shooting apparatus (Acc) for converting content data (Dc) into a stream (AV) and recording the stream (AV) to a recording medium (214) in combination with content-related metadata (Dm), a camera (101) shoots a subject (105) and generates the content data (Dc), a camerawork statistics portion (206 s) detects movement (σ) of the camera, a camera microcomputer (206) compares the detected movement (σ) with a predetermined value (Th) to generate the metadata (Dm), and an automatic threshold setting portion (206 t) changes the predetermined value (Th) in accordance with the detected movement (σ).

Content shooting apparatus

A PLL circuit for a phase comparator, a low-pass filter (LPF), a voltage-controlled oscillator (VCO) and a frequency divider. A first control circuit is responsive to a discontinuous phase change of a reference signal of the PLL circuit for inhibiting the operation of the phase comparator or disconnecting the LPF from the phase comparator during a predetermined period so that the discontinuous phase change information is not transmitted through the LPF to the VCO. At the same time, a second control circuit resets the frequency divider by a pulse of the reference signal after the discontinuous phase change or applies a voltage corresponding to the discontinuous phase change to the VCO so that the output signal of the frequency divider is locked in phase to the reference signal after the discontinuous phase change. With the cooperation of the first and second control circuits, the PLL circuit quickly recovers its stable state after the discontinuous phase change of the reference signal.

Phase locked loop circuit with quickly recoverable stability

A digital signal magnetic recording/reproducing apparatus converts a digital signal into multi-value digital signals and performs recording/reproducing of a multi-value quadrature amplitude-modulated signal. By using the multi-value quadrature amplitude modulation, it is possible to remove the DC component in the recording signal and improve the utilization efficiency of the recording frequency band. Further, using a system to memorize the frequency characteristic of the magnetic recording/reproducing unit and effect Viterbi decoding regarding the intersymbol interference caused by the frequency as a convolutional coding, it is possible to detect the level without necessitating frequency equalization. Accordingly, there arises no deterioration of the S/N ratio by frequency equalization. Furthermore, by providing an encoder for error control coding by increasing the number of multi-values and a corresponding decoder, the error rate can be improved against the deterioration of the S/N ratio. Further, by bias recording the multi-value quadrature amplitude modulated signal, non-linearity of the electromagnetic conversion system is relaxed, and deterioration of the S/N ratio by distortion is improved.

Masaaki Kobayashi

Papers

Metadata preparing device, preparing method therefor and retrieving device

Document data filing apparatus for generating visual attribute values of document data to be filed

Content shooting apparatus

Phase locked loop circuit with quickly recoverable stability

Digital signal magnetic recording/reproducing apparatus using multi-level QAM modulation and maximum likelihood decoding