An adaptive interface for a programmable system, for predicting a desired user function, based on user history, as well as machine internal status and context. The apparatus receives an input from the user and other data. A predicted input is presented for confirmation by the user, and the predictive mechanism is updated based on this feedback. Also provided is a pattern recognition system for a multimedia device, wherein a user input is matched to a video stream on a conceptual basis, allowing inexact programming of a multimedia device. The system analyzes a data stream for correspondence with a data pattern for processing and storage. The data stream is subjected to adaptive pattern recognition to extract features of interest to provide a highly compressed representation that may be efficiently processed to determine correspondence. Applications of the interface and system include a video cassette recorder (VCR), medical device, vehicle control system, audio device, environmental control system, securities trading terminal, and smart house. The system optionally includes an actuator for effecting the environment of operation, allowing closed-loop feedback operation and automated learning.

Adaptive pattern recognition based control system and method

A mobile communications device comprising a location sensing system, producing a location output; a memory, storing a set of locations and associated events; a telecommunications device, communicating event and location information between a remote system and said memory; and a processor, processing said location output in conjunction with said stored locations and associated events in said memory, to determine a priority thereof.

Mobile communication device

A vehicle information system which includes an in-vehicle system 105 and a centralized server system 120 . The in-vehicle system communicates with the server system using a wireless communication link 110 , such as over a cellular telephone system. A position system, such as a set of GPS satellites 140 , provides positioning signals that are used by the in-vehicle systems, and optionally by the centralized server system to increase the accuracy of position estimates. In one version of the system, an operator specifies a destination to an in-vehicle system which validates the destination. The in-vehicle system transmits specification of the destination to a server system 125 at the centralized server. The server system computes a route to the destination and transmits the computed route to the in-vehicle system. The in-vehicle system guides the operator along the route. If the in-vehicle system detects that the vehicle has deviated from the planned route, it replans a new route to the destination using an in-vehicle map database.

Vehicle information system

Location sharing and tracking using mobile phones or other wireless devices

Provided is a fully automated web service with location based services generally involved in transmission of situational location dependent information to automatically located mobile receiving data processing systems. The web service communicates with a receiving data processing system in a manner by delivering information to the device when appropriate without the device requesting it at the time of delivery. There are varieties of configurations made by different user types of the web service for configuring information to be delivered, and for receiving the information. The web service maximizes anonymity of users, provides granular privacy control with a default of complete privacy, and supports user configurable privileges and features for desired web service behavior and interoperability. The web service is fully automated to eliminate human resources required to operate services. Integrated with the web service are enhanced location based services providing map solutions, alerts, sharing of novel services between users, and complete user control for managing heterogeneous device interoperability through the web service.

System and method for anonymous location based services

A system located in an automobile provides personalized traffic informationnd route planning capabilities. This system uses equipment which is becoming standard in automobiles, such as on-board navigation systems and cellular telephones. On-board navigation systems use global positioning system (GPS) satellites to position the automobile with respect to streets in a map database. As the automobile moves, the navigation system updates the location. A central database includes travel time information for each street segment and transition between street segments in the map database. Based upon the travel time information in the database, a route from a current location to a desired destination, or series of destinations, can be planned in order to have a minimum travel time. The route can be provided to the on-board navigation system, which then directs the driver in traveling the route. The cellular telephone in the automobile can be used for communicating with the central database to obtain travel times for route planning. In order to provide dynamic travel time information to the central database, each automobile in the system operates as a data collector. As various street segments are traversed, the travel time for each segment is recorded. The travel time and street segment information is periodically transferred to the central database through the cellular telephone connection. The central database then combines the travel time data from each automobile to create accurate travel time data for each street segment.

Automobile navigation system with dynamic traffic data

A system is provided for spelling correction in which the context of a wordn a sentence is utilized to determine which of several alternative or possible words was intended. The probability that a particular alternative was the word that was intended is determined through Bayesian analysis utilizing multiple kinds of features of the context of the target word, such as the presence of certain characteristic words within some distance of the target word, or the presence of certain characteristic patterns of words and part-of-speech tags around the target word. The system successfully combines multiple types of features via Bayesian analysis through means for resolving egregious interdependencies among features. The system first recognizes the interdependencies, and then resolves them by deleting all but the strongest feature involved in each interdependency, thereby allowing it to make its decisions based on the strongest non-conflicting set of features. In addition, the robustness of the system's decisions is enhanced by the pruning or deletion from consideration of certain features, in one case by deleting features for which there is insufficient evidence in the training corpus to support reliable decision-making, and secondly by deleting features which are uninformative at discriminating among the alternative spellings of the target word under consideration.

System for spelling correction in which the context of a target word in a sentence is utilized to determine which of several possible words was intended

A context-based dictionary entry access system includes selecting and rang an entry based on the part-of-speech assigned to the given word in a sentence. The entries corresponding to the word in context are first selected, followed by availability of entries that are not relevant to the current context. The part of speech of the given word in context is selected based on the utilization of a part-of-speech tagger such that only those entries are selected in which the corresponding word makes syntactic sense in the sentence.

Context based system for accessing dictionary entries

A Bayesian classifier includes an algorithm for estimating the true probability
that a feature is present within a given class of examples by performing a linear
interpolation between the maximum likelihood estimate of the probability that
the feature is present within the class, and the maximum likelihood estimate of
the probability that the feature is present in any class. The weighting factor used
in the interpolation is based on the probability that the presence of the feature
is independent of the given class. In one embodiment, this weighting factor is
calculated as the chi-square probability that the observed association between
the presence of the feature and the class is due to chance. The subject algorithm
incorporated into the Bayesian classifier may be used to provide more accurate
estimates of the so-called likelihood probabilities used by the Bayesian classifier,
thus to allow the Bayesian classifier to perform more accurate classifications,
with the Bayesian classifier being used for numerous applications in natural
language processing and other fields. In one embodiment, the Bayesian classifier
is applied to the natural-language processing task of correcting textual errors in
which an incorrect word was inadvertently substituted for a correct word within
a sentence.

Andrew R. Golding

Papers

Automobile navigation system with dynamic traffic data

System for spelling correction in which the context of a target word in a sentence is utilized to determine which of several possible words was intended

Context based system for accessing dictionary entries

Smoothing algorithm for bayesian classifier