Motorola Corporation

Motorola Solutions, Inc.

William K Thompson

Paul C Davis

Harry M Bliss

Andrew William Mackie

Thomas Eric Hayosh

Anurag Kumar Gupta

Hang S Lee

Guido A Minnen

One automatically accesses () a hierarchical task model as corresponds to a particular task to be executed by a given end user to thereby identify one or more presently un-executed agenda elements. One also automatically accesses () characterizing information for that given end user. (By one approach, for example, this characterizing information can comprise information regarding the given end user's knowledge.) This information regarding the un-executed agenda elements and the characterizing information are then used () to identify a highest hierarchical level within the hierarchical task model as corresponds to the given end user's wherewithal to successfully execute without also needing lower hierarchical level content within the hierarchical task model. The identified highest hierarchical level within the hierarchical task model is then used () to generate a presentation to present to the given end user to thereby facilitate execution of the particular task by the given end user.

Method and apparatus to facilitate using a hierarchical task model with respect to corresponding end users

A Statechart for management of an interaction is generated automatically from a frame that describes the interaction by extracting a data model and a set of goals from frame and then generating a Statechart from the data model and the set of goals. The data model includes a set of data fields to be completed during the interaction Procedural logic is extracted from the frame and used to annotate the Statechart with, for example, initial and final rules, prompts and grammar. The Statechart may be stored for future use or editing, or used to manage a current interaction.

Statechart generation using frames

A frame definition for use by dialog system during an interaction with a user, the frame definition includes at least one data field and at least one goal comprising a Boolean function of one or more filled predicates, each of which takes a reference to a field of the frame as its argument. A goal is satisfied during a dialog if the Boolean function evaluates to true. A goal may be used to control the focus of the interaction.

Frame goals for dialog system

A method and system for assisting a user in interacting with a multi-modal dialog system () is provided. The method includes interpreting a 'What Can I Do? (WCID)' question from a user in a turn of the dialog. A multi-modal grammar () is generated, based on the current context of the dialog. One or more user multi-modal utterances are generated, based on the WCID question and the multi-modal grammar. One or more user multi-modal utterances are conveyed to the user.

Method and system for assisting users in interacting with multi-modal dialog systems

A Statechart is generated automatically from a set of goals for completion of a data model. A set of states is generated corresponding to completion states of the data model, an initial pseudo-state and a final state. Transitions are generated from the initial pseudo-state to an empty state of the set of states and between each state and its subset states. Outgoing transitions are generated from any state that satisfies at least one goal of the set of goals and a transition is generated from that state to the final state. The resulting Statechart may be used to manage an interactive dialog to complete a data model having a set of data fields.

Hierarchical state machine generation for interaction management using goal specifications

A program, system and method for decoding a packed representation of multiple parses that creates an unpacked forest to be read by a semantic interpretation module from a packed representation is provided. The packaged representation includes at least one edgenode and each edgenode includes a substitution list. A current forest object is created and is replicated for each edgenode having a substitution list containing greater than one edgenode. Each replica of the current forest object is updated with one of the edgenodes from the substitution list. Each edgenode of the packed representation is traversed using a depth-first traversal.

System and method of decoding a packed representation of multiple parses

A chart parser and a method for generating a parse chart for a sequence of input symbols in accordance with an abbreviated representation of a grammar. According to the method, an abbreviated representation of a grammar is stored as a set of finite-state automata, each finite-state automaton corresponding to a rule of the grammar. Chart edges are derived chart edges from the sequence of input symbols in accordance with the set of finite-state automata and are stored in the parse chart. Each chart edge spans a portion of the sequence of input symbols and may include a left input vertex index corresponding to the start of the span of the chart edge, a right input vertex index corresponding to the end of the span of the chart edge, a rule number, indicating which finite-state automaton of the plurality of finite-state automata has been used to generate the chart edge, a left state index, indicating the left most state of the finite-state automaton that has been matched and a right state index, indicating the right most state of the finite-state automaton that has been matched, the left-hand side of the rule and a path through the finite state comprising the right-hand side of the rule or so-called backpointers to the edges used to derive the current edge. The chart parser includes a chart controller and an agenda controller, together with associated memory.

Chart parsing using compacted grammar representations

The current invention provides a method for managing a dialogue between a processing system and a user. It addresses the problem of inferring possible feature values by automatically generating an SQL query from a frame representation posting this query to a relational database containing the relevant domain knowledge, and updating the frame representation to reflect the results of this query. Because the method is not dependent on particular information of the domain utilizing the method, it can be readily implemented for any specific application which benefits from inferring possible feature values by extracting data from a database.

Growing community of inventors

Evanston, IL, United States of America

William K Thompson