Abstract: Embodiments of the invention relate to managing user interactions and, more particularly, to performing analysis on data generated by user interactions. Embodiments of the invention use text mining to extract personal information of users from user interactions automatically. A topic model is used to reduce the number of dimensions required to represent the text, yet all the information of interest is highly pronounced. This enables a lower dimensional representation of the data leading to significantly faster computations.

Abstract: The stages of an interaction between a potential customer (the user) and a sales representative (the agent) during a sales interaction are identified to understand the interaction factors that drive sales and, by doing so, to serve the customer better and thus increase sales. Initially, a user makes contact with an agent via a communications network. During the interaction, a dropping point is reached, i.e. the point in the interaction at which either the user or the agent ends the interaction. The dropping point and other interaction factors is analyzed. Based upon such analysis, various recommendations are made to the agents to improve the user's sales experience.

Abstract: A computer-implemented method and an apparatus for facilitating speech application testing generate a plurality of test scripts. A test script is generated by initiating a voice call interaction with a speech application including a network of interaction nodes, and repeatedly performing, until a stopping condition is encountered, the steps of, executing the voice call interaction by traversing through interaction nodes until an interaction node requiring a response is encountered, selecting an utterance generation mode, determining a response to be provided corresponding to the interaction node, and providing the response to the speech application. The test script comprises instructions for traversing interaction nodes and for provisioning one or more responses during the course of the voice call interaction. One or more test scripts from among the plurality of test scripts are identified based on a pre-determined objective and provided to a user for facilitating testing of the speech application.

Abstract: A customer support system diverts a customer to an integrated support service to serve the customer better in situations where the use of a single mode of interaction is insufficient. Embodiments of the invention find use where an email or SMS is sent to a customer's smart devices with a link to visual content which helps customer better understand the information.

Abstract: A context sensitive slider content area provides a slide out mechanism that is automatically actuated when additional information is needed during a chat session between an agent and a visitor, e.g. where a pre-chat and/or exit form is to be completed. The context sensitive slide out content area also provides problem resolution information to the visitor to help in solving problems, e.g. the top five problems; and also provides a self-service step-by-step wizard. A history section is provided with which the visitor can track back all previous steps carried out within the smart client. A history bar provides an iconic representation of all previous activities. A technique is also disclosed for executing various actions, such as form filling or requests for additional services, in a chat session.

Abstract: A context sensitive slider content area provides a slide out mechanism that is automatically actuated when additional information is needed during a chat session between an agent and a visitor, e.g. where a pre-chat and/or exit form is to be completed. The context sensitive slide out content area also provides problem resolution information to the visitor to help in solving problems, e.g. the top five problems; and also provides a self-service step-by-step wizard. A history section is provided with which the visitor can track back all previous steps carried out within the smart client. A history bar provides an iconic representation of all previous activities. A technique is also disclosed for executing various actions, such as form filling or requests for additional services, in a chat session.

Abstract: Embodiments of the invention provide techniques for increasing user engagement with video ads and content. The invention is not limited to video advertisements, but is applicable to any other content. Embodiments of the invention provide engagement formats that use interesting frames in a video or objects within video frames to increase user engagement in the video, one or more frames of the video, or any object within the video.

Abstract: An IVR system is disclosed in which customer experience is enhanced by improving the accuracy and intent prediction capabilities of an interactive voice response system. Customers are allowed to make a natural language queries to specify their intent, while the accuracy of traditional IVR systems is maintained by using key features in language along with the customer's past transactions, CRM attributes, and customer segment attributes to identify customer intent.

Abstract: A data assist application allows people to share structured data, and update and/or collaborate in real time. Companies can use embodiments of the invention to send and/or receive structured data. Embodiments of the data assist application work standalone or while a user is talking to a person or a company. In use, information is spread when people share data with non-users. The data are preferably owned and/or controlled by the user and stored on user devices. Further embodiments of the invention integrate with OS-supplied data and third party apps.

Abstract: A computer implemented method and an apparatus for facilitating voice user interface (VUI) design are provided. The method comprises identifying a plurality of user intentions from user interaction data. The method further comprises associating each user intention with at least one feature from among a plurality of features. One or more features from among the plurality of features are extracted from natural language utterances associated with the user interaction data. Further, the method comprises computing a plurality of distance metrics corresponding to pairs of user intentions from among the plurality of user intentions. A distance metric is computed for each pair of user intentions from among the pairs of user intentions. Furthermore, the method comprises generating a plurality of clusters based on the plurality of distance metrics. Each cluster comprises a set of user intentions. The method further comprises provisioning a VUI design recommendation based on the plurality of clusters.

Abstract: An apparatus and method is provided for creating, updating, and deleting business rules with ease by use of a rule manager. Business rules are represented as tables that map a set of inputs to a set of outputs. Inputs are represented as enumerations with predefined allowable values. All possible unique combinations of values for a given set of inputs are automatically generated, and a business user can then set the outputs for each desired input value combination.

Abstract: An intelligent IVR system identifies a customer based on previous customer interactions. Customer intent is predicted for an ongoing interaction and personalized services are proactively offered to the customer. A self-optimizing algorithm improves intent prediction, customer identity, and customer willingness to engage and use IVR.

Abstract: The disclosure is related to mining of text to derive information from the text that is useful for a variety of purposes. The text mining process can be implemented in a service oriented industry such as a call center, where a customer and an agent engage in a dialog, e.g., to discuss product/service related issues. The messages in dialogues between the customers and the agents are tagged with features that describe an aspect of the conversation. The text mining process can mine various dialogues and identify a set of features and messages based on prediction algorithms. The identified set of features and messages can be used to infer an intent of a particular customer for contacting the agent, and to generate a recommendation based on the determined intent.

Abstract: A computer implemented method and an apparatus for determining user browsing behavior are provided. One or more web pages corresponding to a web domain are configured by associating the one or more web pages with tags. A control file is downloaded on a user device when a first web page access by a user to a tagged web page from among the one or more tagged web pages is detected. The control file facilitates recording of user activity related to a web domain on one or more tabs of a web browser associated with the user device. Recorded user activity corresponding to at least one web browsing session is received and user browsing behavior is determined based on the recorded user activity.

Abstract: User intent is identified while the user browses online and recommendations are provided to the user. The recommendations are based on the identified intent, interests, and preferences of the user who is performing the searches. The determination of user intent and interests is based on a statistical model derived from data compiled from the user and a plurality of other users. Other resources may also be determined to be relevant, for example, because of past interactions of the user, memberships of the user in ecommerce websites, the user's interests and preferences are similar to those of other users, and so on. The result of the user search is a ranked set of recommendations that is provided to the user.

Abstract: The stages of an interaction between a potential customer (the user) and a sales representative (the agent) during a sales interaction are identified to understand the interaction factors that drive sales and, by doing so, to serve the customer better and thus increase sales. Initially, a user makes contact with an agent via a communications network. During the interaction, a dropping point is reached, i.e. the point in the interaction at which either the user or the agent ends the interaction. The dropping point and other interaction factors is analyzed. Based upon such analysis, various recommendations are made to the agents to improve the user's sales experience.

Abstract: A system for providing automated assistance to an agent includes a database that stores an automated assistance session in association with a client terminal. The automated assistance session comprises communications between the client terminal and an agent terminal during a communication session. The automated assistance session is restored in response to a connection being reestablished with the client terminal after the client terminal disconnects during the communication session. A client communication is received from the client terminal, and a plurality of statements is determined based on the client communication and the communications of the automated assistance session stored in the database. The statements are configured to be manually selected by an agent or automatically selected by an automated agent. The automated agent is engaged for automatically selecting one of the statements in response to a predetermined condition.

Abstract: User interactions are categorized into predefined hierarchical categories by classifying user interactions, such as queries, during a user interaction session by labeling text data into predefined hierarchical categories, and building a scoring model. The scoring model is then executed on untagged user interaction data to classify the user interactions into either action-based or information-based interactions.

Abstract: The customer experience is enhanced by detecting leakage-to-voice from chats and providing recommendations to operations, chat agents, and customers. A chat is classified into leakage-to-voice or leakage-to-text chat and actionable recommendations are then provided to operations, chat agents, and customers based on the leakage information. Once leakage is identified, various other insights are extracted from chats and such insights are fed into the knowledge-base. Such insights also used in agent training and are provided to chat agents as recommendations. This results in a better customer experience.

Abstract: Embodiments of the invention provide a method and apparatus (“system”) that overcome the above-mentioned problems among others and provide an innovative solution aimed at creating an interactive, dynamic and effective multi-media object with HIP capabilities which may be used in online advertising, security, and user-defined security. The system leverages the existing HIP CAPTCHA real estate to create multi-media objects that guarantee a captivated audience, especially in online advertising. Combining interactive multi-media objects with HIP capabilities helps to meet a very critical need faced by advertisers and websites today—creating an effective impression of any multi-media object on a user (a guaranteed eyeball). Embodiments of the current invention introduce a variety of formats that involve interacting with a multi-media object to provide a more natural user interaction and ease of use while maintaining security.