130 results about "Context recognition" patented technology

A system and method for translation of electronic communications automatically selects and deploys specialized dictionaries based upon context recognition and other factors. Software tools can be employed for continual dictionary enhancement. The invention can accept speech and text inputs and can be used to translate electronic mail, instant messages, chat, SMS messages, electronic text and word processing files, Internet web pages, Internet search results, and other textual communications for a variety of device types, including wireless devices. In one embodiment, language pairs are automatically determined in real-time.

An architecture for context-aware advertisement and delivery among mobile communication devices over a communication network, in which the architecture is stored and executed as an application for use by network devices. The architecture includes a navigation module, which provides map data vehicles on the network and a context recognition module, which interprets data provided by sensors within the vehicle. Advertising data is received by a data reception module. A configuration module determines presentation slot availability. The value and content of the authenticated advertisement is verified by the advertisement management module; selected advertisements are presented to the vehicle user.

A method or system for selecting or pruning applicable verbal commands associated with speech recognition based on a user's motions detected from a depth camera. Depending on the depth of the user's hand or arm, the context of the verbal command is determined and verbal commands corresponding to the determined context are selected. Speech recognition is then performed on an audio signal using the selected verbal commands. By using an appropriate set of verbal commands, the accuracy of the speech recognition is increased.

A file includes data and semantic context. The semantic context identifies limitations on the use of the data in the file. Semantic context may include, among other possibilities, source information about a parameter, acceptable values for a parameter, presentation information, a record of the use of the data, and information to synchronize the use of the data with another file.

Provided is a service system for providing context information based on a ubiquitous sensor network and a method thereof. The context information providing service system includes: a sensing block for collecting context information of each user; an intermediating block for changing the user context information transmitted from the sensing block into a request to store the request in a context recognizing block, transmitting the request to the context recognizing block, and transmitting a service request to the context recognizing block; and a context recognizing block for storing context information of each user according to a context information storing request transmitted from the intermediating block, and providing a relevant service by using the user context information.

A system and method of supporting packet-switched handover of a mobile station (MS) from a GERAN/UTRAN cell to a Generic Access Network (GAN) cell within a GAN. If the MS is within coverage of the GAN cell, the MS registers within the GAN triggering initiation of the packet-switched handover from the GERAN/UTRAN cell to the GAN cell. A preparation phase is then conducted for executing the packet-switched handover. The preparation phase includes identifying the MS context as part of the preparation phase and activating the GA-PSR TC towards the MS. Next, the packet-switched handover is executed, resulting in the MS switching to GAN mode. The MS then begins transferring packets via the GAN cell. The system and method also supports a packet-switched handover from the GAN cell to the GERAN/UTRAN cell.

Systems and methods for providing an enhanced viewing experience for a user of an interactive media guidance application are provided. In some aspects, an interactive media guidance application implemented on control circuitry receives a selection of a media asset from a user. The control circuitry analyzes the media asset to determine a context for a portion of the media asset. The control circuitry identifies content related to the portion of the media asset based on the context. The identified content is different from the media asset and is displayed in response to the user selection of the media asset.

Mobile device (102) comprising a number of sensing entities (230) for obtaining data indicative of the context of the mobile device and/or user thereof, a feature determination logic (230) for determining a plurality of representative feature values utilizing the data, and a context recognition logic (228) including an adaptive linear classifier (234), configured to map, during a classification action, the plurality of feature values to a context class, wherein the classifier is further configured to adapt (236) the classification logic thereof on the basis of the feature values and feedback information by the user of the mobile device. A method to be performed by the mobile device is presented.

A method is provided for providing a tutorial message to a driver in a vehicle using an in-vehicle tutorial system including a multimodal user interface. The method includes assigning an area of improvement, including at least one tutorial task, to the tutorial system, identifying a driving context for which a tutorial task is to be performed, based on the tutorial task and the driving context, selecting a tutorial message encouraging a desired driving behavior, and providing the selected tutorial message to the driver using the multimodal user interface.

An error detection and correction system extracts editing patterns and derives correction rules from them by observing differences between draft documents and corresponding edited documents, and/or by observing editing operations performed on the draft documents to produce the edited documents. The system develops classifiers that partition the space of all possible contexts into equivalence classes and assigns one or more correction rules to each such class). Once the system has been trained, it may be used to detect and (optionally) correct errors in new draft documents. When presented with a draft document, the system identifies first content (e.g., text) in the draft document and identifies a context of the first content. The system identifies a correction rule based on the first content and the first context. The system may use a classifier to identify the correction rule. The system applies the correction rule to the first content to produce second content.

A context recognition unit decides a user's context by comparing context recognition rules to the user's information, and outputs context recognition data based on the user's context. A processing selection unit decides a contents type by comparing processing selection rules to the context recognition data, and outputs contents creation request data based on the contents type. A contents delivery unit obtains contents based on the contents creation request data, and delivers the contents to the user's terminal. A question creation unit creates a question about the contents delivery for the user. Each context recognition rule and each processing selection rule includes a priority degree. The question creation unit specifies the context recognition rule or the processing selection rule based on the user's answer to the question, and changes the priority degree of the specified rule.

The invention provides a method for correcting error-prone words in voice interaction. The method comprises the steps of context recognition, automatic error correction based on semantic restriction, and artificial error correction based on semantic feedback. Through voice interaction with users and perception and recognition of the context of a topic, automatic error correction of an entity with a specific meaning can be achieved by using the named entity recognition technology within the limited semantic range, additional semantics can be obtained through artificial feedback so as to conduct error correction, and higher input efficiency and more convenient wrong word correction than existing voice recognition software are realized.

A search system generates an ordered list of destination targets including identified individuals and data objects, based on applying a user context to an information context and to a connection context. The user context identifies a search context (i.e., the information the user is seeking) relative to an identity of the user, and the information context identifies destinations accessible by the user, including data objects and communications-based actions (e.g., voice over IP telephony calls, instant messaging session transcripts, etc.). The connection context identifies relationships between chosen destinations throughout the system, and the strength of those relationships determined from artifacts of the chosen destinations: the connection context is updated based on artifact detection. The portion of the connection context that is relevant to the user context is used to order the portion of the information context that is relevant to the user context, resulting in the ordered list of destination targets.

A system and method for identifying and establishing preferred modalities or channels for communications based on participants' preferences and capabilities is provided. In one approach, the system attempts to optimize the inferred or directly accessed preferences of a contactee given the accessed or inferred preferences, capabilities and goals of the contactor while keeping the rationale and context of the contactee private. Such optimization can be achieved using preferences and policies concerning handling the attempted contact based on a deterministic specification or through inferring context, content and task under uncertainty by employing decision-theoretic inferences to attempt to maximize the expected utility of the communication to the contactee. The methods may include a consideration of metadata within a standard schema that is transmitted along with a communication attempt, representing information about such attributes as the identity of the contactor, the task at hand, the overall context of the contactor, and the communication capabilities available to the contactor. The invocation of the communication service may be performed in a variety of ways, including single button invocations, and via a communication service that is more deeply integrated with other applications and functionalities. The service can also include automated rescheduling of communications based on a consideration of forecasts of availability of both the contactor and contactee.

A method, system and computer program product are disclosed for searching for an inferred lexical answer type from the context of a question. One embodiment comprises determining from a question an original lexical answer type (LAT), extracting the context in which said original LAT occurs within the question, and identifying a set of context fragments from said context. This embodiment further comprises using the set of context fragments to search through a defined database to produce a search result including a plurality of text strings having a specified relationship with said context fragments, and processing said search result to search for one or more inferred LAT of the question. In one embodiment, the processing includes extracting a plurality of LATs from the text strings in the search result, and selecting one or more of the extracted LATs as the one or more inferred LAT of the question.

A system for detecting streaming of advertisements that occur while streaming a media program is provided. The system includes a broadcast content receiving module, a feature extracting module, an advertisement detecting module, a weight computing module, and a neighborhood context identifying module. The broadcast content receiving module receives a broadcast content from a content source. The feature extracting module extracts video features, audio features, and metadata features associated with broadcast chunks of the broadcast content for time segments. The advertisement detecting module analyzes the video features, the audio features, and the metadata features for the time segments. The weight computing module computes final weight for validating start and end of first advertisement slot based on the weight. The neighborhood context identifying module validates a start time of a first advertisement slot based on a content type of a first broadcast chunk and a second broadcast chunk.

The invention discloses a commodity name recognition method based on a full-text attention mechanism. The method comprises the following steps: establishing a depth neural network model with a full-text attention mechanism; adding a full-text attention layer into the depth neural network model; in the full-text attention layer, the full-text information being represented by a method of embedding aword into a vector; the full-text attention layer being represented by a full-text information embedding vector. Then, for each word to be annotated, the similarity between them and the full-text attention-level word vector is calculated, so that the word can obtain the 'attention weight' of the full-text, that is, the word can focus on the context information of the document, and the additionalfeatures of each word can be calculated by using the sum of the attention-level weight, so as to identify the trade name. The method of the invention can effectively extract commodity names from irregular texts, solves the problem of inconsistent identification of the same commodity in context, and improves the accuracy of identification.

The invention discloses an IPTV (internet protocol television) program recommendation method based on context recognition for multiple users. By means of clustering analysis to program viewing time, the time slots at which the viewing times of users are concentrated relatively are acquired, different users' preferences to programs at different time slots are computed, similarity of the preferences to programs at the different time slots is analyzed, the time slots of the similar programs viewed by users are combined into a new context, and then recommendation is made according to the information of the context. Therefore, to some extent, problems about multiple users in IPTV portal service are solved, and recommendation quality is improved.

Systems and methods for identifying, in a network environment in which users watch videos that are downloaded or streamed over a network, a video in which a user is likely to be interested based on session context. For example, a server or other computing system identifies prior session contexts in which prior users watched videos and session progress data for prior sessions in which these prior users watched the videos. The server or other computing system determines a session context of a user for whom a video is to be recommended. For this user, the server or other computing system generates a recommendation identifying one or more videos in which the user is likely to be interested, where the user has not previously watched the recommended videos. The recommendation is generated based on the prior session contexts, the session progress data, and the session context of the user.

Method for user micro context recognition using sound signatures. The method includes: recording an environment sound sample from a microphone into a mobile device by a trigger stimulus; simultaneous to recording an environment sound sample, collecting hardware and software macro context data from available mobile devices; extracting a sound signature from the recorded sound sample based on sound features and spectrograms; comparing for similar patterns the recorded sound signature with reference sound signatures stored in a sound database; updating the sound database; checking if the recorded sound was recognized; performing a logical association between the sound label and the available macro context data; comparing for similar patterns the recorded context with a reference context stored in a context database; updating the context database; checking if the micro context was recognized; and returning to a mobile context-aware application the micro context label.

The invention relates to a placename recognition technology, and provides an intelligent placename recognition technology based on a statistical model. The intelligent placename recognition technology based on the statistical model comprises the steps that firstly, a basic word segmentation sequence is obtained and placenames are labeled in a statistical probability model and dictionary mode, then, some placenames are determined at first through independent placename recognition, then, superior and subordinate placename recognition, placename statistical model context recognition, placename ambiguity elimination in person names and other information are adopted for screening placename quality for the passible placenames, and finally statistical analysis is carried out on the placenames recognized in the full text so as to further filter out mistaken placenames. According to the intelligent placename recognition technology, various flexible modes for placename description by means of Chinese are fully utilized, the higher accuracy of practical levels is provided for placename recognition, and forceful help is provided for text division according to geographic attributions and mechanism recognition.

A method, a system and a computer program product for determining one or more characteristics of a caller, such as the mood, gender, age, and urgency of the caller, utilizing the biometric characteristics of the caller. One or more biometric characteristics are detected when a request to place an outgoing call to one or more destinations is received at a first telecommunication device. When the request to place an outgoing call is a verbal request, one or more biometric voice samples are obtained. The biometric voice samples comprise the biometric characteristics of the caller. The biometric characteristics are extracted from the biometric voice samples, encoded into a datagram, and transmitted from the first telecommunication device to the outgoing call destination (i.e. a second telecommunication device). When the biometric characteristics are analyzed at the second telecommunication device, a display is generated depicting the mood, gender, age, urgency or other characteristics of the caller associated with the incoming call.