Abstract: A method of providing a task assistant to provide an interface to an application is described. The method comprises receiving input from a user through multimodal input including a plurality of speech input, typing input, and touch input, interpreting the input, and providing a formatted query to the application, receiving data from the application in response to the query, and providing a response to the user through multimodal output including a plurality of: speech output, text output, non-speech audio output, haptic output, and visual non-text output.

Abstract: A method of providing a task assistant to provide an interface to an application is described. The method comprises receiving input from a user through multimodal input including a plurality of speech input, typing input, and touch input, interpreting the input, and providing a formatted query to the application, receiving data from the application in response to the query, and providing a response to the user through multimodal output including a plurality of: speech output, text output, non-speech audio output, haptic output, and visual non-text output.

Abstract: A method of providing a task assistant to provide an interface to an application, the method comprising activating the task assistant, the activation having an associated visual display. The method in one embodiment includes receiving input from a user through multimodal input including a plurality of speech input, typing input, and touch input, interpreting the input, and providing a formatted query to the application, receiving data from the application in response to the query, and providing a response to the user through multimodal output including a plurality of: speech output, text output, non-speech audio output, haptic output, and visual non-text output, wherein the task assistant has a plurality of active states, each of the active states having an associated visual display.

Abstract: A method of providing a task assistant to provide an interface to an application is described. The method comprises receiving input from a user through multimodal input including a plurality of speech input, typing input, and touch input, interpreting the input, and providing a formatted query to the application, receiving data from the application in response to the query, and providing a response to the user through multimodal output including a plurality of: speech output, text output, non-speech audio output, haptic output, and visual non-text output.

Abstract: A method of providing a task assistant is described. The task assistant is designed to receive input from a user through multimodal input including a plurality of speech input, typing input, and touch input, determine the meaning of the input, and determining whether there is a context based on prior interactions with the user. The method further to generate an interpreted input based on a combination of the input and the context, and providing a formatted query to an application. The method further to receive data from the application in response to the formatted query, and provide a response to the user through multimodal output including a plurality of: speech output, text output, non-speech audio output, haptic output, and visual non-text output. The method further to update the context based on the interpreted input.

Abstract: Customer service and/or care providers generally have multiple communications channels (i.e., modes of communications, such as an Internet webpage, live agent telephones, Interactive Voice Response (IVR) system) of communication with which a customer may interact with the customer service provider. Currently, customers must select the communications channel by guessing which communications channel would best accommodate the customer's purpose/need for communicating with the customer service provider. In some scenarios, the customer may select the wrong communications channel because the selected channel is not able to service the customer's need. In another scenario, the customer may select a channel that is more cumbersome to service the customer's particular need than another channel of the customer service provider.

Abstract: A method of providing a task assistant to provide an interface to an application is described. The method includes, in one embodiment, identifying a user and determining whether there is a push notification to be shown to the user. When there is a push notification to be shown to the user, the task assistant displaying the push notification to the user, such that when the user acknowledges the push notification, the user is directed to a push destination. When there is no push notification, receiving input from a user through multimodal input including a plurality of speech input, typing input, and touch input, interpreting the input, and providing a formatted query to the application, receiving data from the application in response to the query, and providing a response to the user through multimodal output including a plurality of: speech output, text output, non-speech audio output, haptic output, and visual non-text output.

Abstract: A method of speech-enabling a human-to-machine interface comprises uniquely identifying a plurality of input fields and corresponding input field identifications (IDs) associated with a human-to-machine interface. The method further comprises mapping the input field IDs to grammar slot names to produce a speech-to-field mapping. The grammar slot names may be associated with speech-to-text rendering of speech expected to be received by a speech-to-text renderer configured to output representations of the speech having correspondence with the grammar slot names. The method also comprises enabling a flow of representations of speech to the input fields via the speech-to-field mapping. The input fields may include interactive elements displayed on a screen view including at least one of radio buttons, text fields, buttons, and drop down menus.

Abstract: Current interactive voice response (IVR) systems only allow customers to interact with a company's database using a telephone keypad or by speech recognition. Such IVR systems require a customer to listen to and remember instructions or options presented by the IVR system. The instructions may be complicated, or there may be many options. An embodiment of the present invention enhances an IVR system by composing visual representations of states of the IVR system to display to the customer and enabling the customer to interact with the IVR via the visual representations. The use of the visual representations enables a user to interact with the IVR in a simplified and more expedient manner in part because a linear set of options is presented in a randomly-accessible list or tree structure format.

Abstract: A method of providing biometric authorization comprising enabling a user to log into an account, and determining whether there is a hold on the account. When there is a hold on the account, informing the user of the hold, and enabling the user to respond to a transaction that caused the hold. The method, in one embodiment further comprising prompting the user to enter a biometric authentication, in conjunction with the response, and processing the unblock request in real-time upon receiving and validating the biometric authentication.

Abstract: A system and method for providing an easy-to-use interface for verifying semantic tags in a steering application in order to generate a natural language grammar. The method includes obtaining user responses to open-ended steering questions, automatically grouping the user responses into groups based on their semantic meaning, and automatically assigning preliminary semantic tags to each of the groups. The user interface enables the user to validate the content of the groups to ensure that all responses within a group have the same semantic meaning and to add or edit semantic tags associated with the groups. The system and method may be applied to interactive voice response (IVR) systems, as well as customer service systems that can communicate with a user via a text or written interface.

Abstract: A method and an apparatus to disambiguate requests are presented. In one embodiment, the method includes receiving a request for information from a user. Then data is retrieved from a back-end database in response to the request. Based on a predetermined configuration of a disambiguation system and the data retrieved, the ambiguity within the request is dynamically resolved.

Abstract: A method of providing a task assistant comprising starting to receive speech input from a user, and identifying a format associated with a destination for speech input based on a flag associated with the destination field. When the format comprises dictation, converting the speech to text, and inserting it into the destination location, and when the format comprises an intent, determining a meaning of the input, and sending a formatted query to an application. The method further comprising receiving data from the application in response to the intent and providing a response to the user through multimodal output.

Abstract: Generally, human-to-machine interfaces are configured to accept speech input from a user. However, such interfaces, e.g., web browsers, must be configured to enable acceptance of speech input from the user. Some interfaces, such as mobile browsers, have less configuration adaptability and are not able to be configured to accept speech input from a user. Embodiments of the present invention speech-enable human-to-machine interfaces by loading content of the human-to-machine interface and adding logic configured to enable speech interaction with the content to the interface. The embodiment then activates speech interaction with the content via the logic for the user. Thus, embodiments of the present invention enable speech interaction with interfaces that are not configured to be adapted to allow speech interaction and are able to enable the speech interaction in a seamless manner.

Abstract: Current human-to-machine interfaces enable users to interact with a company's database and enter into a series of transactions (e.g., purchasing products/services and paying bills). Each transaction may require several operations or stages requiring user input or interaction. Some systems enable a user to enter a voice input parameter providing multiple operations of instruction (e.g., single natural language command). However, users of such a system do not know what types of commands the system is capable of accepting. Embodiments of the present invention facilitate communications for user transactions by determining a user's goal transaction and presenting a visual representation of a voice input parameter for the goal transaction. The use of visual representations notifies the user of the system's capability of accepting single natural language commands and the types of commands the system is capable of accepting, thereby enabling a user to complete a transaction in a shorter period of time.

Abstract: A system and method for providing an easy-to-use interface for verifying semantic tags in a steering application in order to generate a natural language grammar. The method includes obtaining user responses to open-ended steering questions, automatically grouping the user responses into groups based on their semantic meaning, and automatically assigning preliminary semantic tags to each of the groups. The user interface enables the user to validate the content of the groups to ensure that all responses within a group have the same semantic meaning and to add or edit semantic tags associated with the groups. The system and method may be applied to interactive voice response (IVR) systems, as well as customer service systems that can communicate with a user via a text or written interface.

Abstract: Generally, human-to-machine interfaces are configured to accept speech input from a user. However, such interfaces, e.g., web browsers, must be configured to enable acceptance of speech input from the user. Some interfaces, such as mobile browsers, have less configuration adaptability and are not able to be configured to accept speech input from a user. Embodiments of the present invention speech-enable human-to-machine interfaces by loading content of the human-to-machine interface and adding logic configured to enable speech interaction with the content to the interface. The embodiment then activates speech interaction with the content via the logic for the user. Thus, embodiments of the present invention enable speech interaction with interfaces that are not configured to be adapted to allow speech interaction and are able to enable the speech interaction in a seamless manner.

Abstract: A system and method for providing an easy-to-use interface for verifying semantic tags in a steering application in order to generate a natural language grammar. The method includes obtaining user responses to open-ended steering questions, automatically grouping the user responses into groups based on their semantic meaning, and automatically assigning preliminary semantic tags to each of the groups. The user interface enables the user to validate the content of the groups to ensure that all responses within a group have the same semantic meaning and to add or edit semantic tags associated with the groups. The system and method may be applied to interactive voice response (IVR) systems, as well as customer service systems that can communicate with a user via a text or written interface.

Abstract: A method of providing a task assistant to provide an interface to an application is described. The method includes, in one embodiment, receiving input from a user through multimodal input including a plurality of each input, typing input, and touch input, interpreting the input, and providing a formatted query to the application, and receiving data from the application in response to the query. The method further includes identifying a destination providing a response to the query, identifying an anchor pointing to a specific location in the application associated with the response to the query, and directing the user to the specific location, using the anchor, the specific location providing a response to the user.

Abstract: A method of providing a task assistant is described. The task assistant is designed to receive input from a user through multimodal input including a plurality of speech input, typing input, and touch input, determine the meaning of the input, and determining whether there is a context based on prior interactions with the user. The method further to generate an interpreted input based on a combination of the input and the context, and providing a formatted query to an application. The method further to receive data from the application in response to the formatted query, and provide a response to the user through multimodal output including a plurality of: speech output, text output, non-speech audio output, haptic output, and visual non-text output. The method further to update the context based on the interpreted input.