Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for evaluating dominance of participants in a conversation or interaction. An example system configured to practice the method first receives interaction data involving a plurality of participants, and can identify a type of interaction based on the interaction data. The system can parse the interaction data to identify dialog turns, and extract, from the interaction data and dialog turns, a plurality of participant features, wherein the plurality of participant features is selected based on the type of interaction. Then the system can generate, for each of the plurality of participants, a power index based on the respective participant features.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for aggregating and presenting tags. A system configured to practice the method identifies a type for each tag describing a media event received from a tagging system, generates aggregate tags representing at least a portion of the set of tags based on the identified types, associates each aggregate tag with the media event based on the at least the portion of the plurality of tags represented by each respective aggregate tag, and optionally outputs the aggregate tags with the media event. A system configured to combine media segments based on aggregated tags first retrieves aggregate tags associated with a media event, receives input from a user, identifies a subset of aggregate tags related to the input, and outputs portions of the media event associated with the subset of aggregate tags.

Abstract: An apparatus and methods are disclosed that enable a caller to specify a condition of availability for a return call when the caller is unable to reach the called user. A condition might indicate a time interval in which the caller is willing to accept a return call, a location, or some other constraints. In the illustrative embodiments, when a caller places a call and is unable to reach the called user, the caller is prompted via an interactive voice response (IVR) system for one or more conditions of availability for a return call. As soon as the called user's terminal becomes available, a software application checks whether the condition of availability is satisfied, and if so, establishes a call between the caller's terminal and the called user's terminal.

Abstract: Methods and apparatus are provided for controlling an availability of a user in an enterprise environment. If an enterprise user requests to change an availability status on one or more media, a determination is made as to whether to grant the request based on one or more predefined criteria associated with the enterprise. For example, the predefined criteria may comprise resource needs or one or more policies of the enterprise. The predefined criteria may be expressed as one or more rules in a rule base.

Abstract: Systems, methods, and computer-readable storage media for generating an immersive three-dimensional sound space for searching audio. The system generates a three-dimensional sound space having a plurality of sound sources playing at a same time, wherein each of the plurality of sound sources is assigned a respective location in the three-dimensional sound space relative to one another, and wherein a user is assigned a current location in the three-dimensional sound space relative to each respective location. Next, the system receives input from the user to navigate to a new location in the three-dimensional sound space. Based on the input, the system then changes each respective location of the plurality of sound sources relative to the new location in the three-dimensional sound space.

Abstract: Systems, methods, and computer-readable storage media for generating personalized tag recommendations using speech analytics. The system first analyzes an audio stream to identify topics in the audio stream. Next, the system identifies tags related to the topics to yield identified tags. Based on the identified tags, the system then generates a tag recommendation for tagging the audio stream. The system can also send the tag recommendation to a device associated with a user for presentation to the user.

Abstract: Systems, methods, and non-transitory computer-readable storage media for determining expertise through speech analytics. The system associates speakers with respective segments of an audio conversation to yield associated speaker segments. The system also identifies a number of times a speaker has spoken about a topic in the audio conversation by searching the associated speaker segments for a term associated with the topic. The system then ranks the speaker as an expert in the topic when the number of times the speaker has spoken about the topic in the audio conversation exceeds a threshold. The audio conversation can include a compilation of a plurality of audio conversations. Moreover, the system can tag the associated speaker segments having the term with keyword tags and match a respective segment from the associated speaker segments with the speaker, the respective segment having a keyword tag.

Abstract: Systems, methods, and computer-readable storage media for managing meeting agendas in a meeting or conference via a virtual agenda participant. The system maintains, prior to a communication session, a conference agenda associated with the communication session. During the communication session, the system identifies, via a virtual entity, communication items associated with the communication session to yield identified communication items, wherein the virtual entity dynamically monitors the communication session and processes data associated with the communication session to identify the communication items. The system then compares, via the virtual entity, the conference agenda with the identified communication items to determine which items from the conference agenda have been addressed during the communication session.

Abstract: A method is disclosed that enables the selection of a team of people in an organization, such as a business enterprise, to participate in a task that involves communicating with each other, in which the selection of the team seeks to maximize the team cohesiveness. The illustrative embodiment of the present invention incorporates the use of a social network model to describe the communication pattern in the organization. Based on the relationship between the organization's social network structure and the cohesiveness between the people in the organization, the technique of the illustrative embodiment estimates the dyadic cohesiveness of each pair of people, which is defined as the expected value of relationship strength between each evaluated pair of people. One component of the relationship strength is the number of interactions between the two people in the pair. The technique of the illustrative embodiment then uses the cohesiveness estimates to select teams.

Abstract: A method is disclosed that enables the selection of a team of people in an organization, such as a business enterprise, to participate in a task that involves communicating with each other, in which the selection of the team seeks to maximize the team cohesiveness. The illustrative embodiment of the present invention incorporates the use of a social network model to describe the communication pattern in the organization. Based on the relationship between the organization's social network structure and the cohesiveness between the people in the organization, the technique of the illustrative embodiment estimates the dyadic cohesiveness of each pair of people, which is defined as the expected value of relationship strength between each evaluated pair of people. One component of the relationship strength is the number of interactions between the two people in the pair. The technique of the illustrative embodiment then uses the cohesiveness estimates to select teams.

Abstract: Disclosed are systems, methods, and non-transitory computer-readable storage media for analyzing an event via social media. A system configured to practice the method segments a document associated with an event based on a plurality of inferred topics to yield a plurality of segments. Next, the system assigns each message in a corpus of messages associated with the event to one of the inferred topics to yield assigned topics. The messages can include at least one of a status update, a tweet, a blog post, a tag, a chat message, a comment, and a check-in. Moreover, the messages can originate from different social networks. Based on the assigned topics, the system then associates each message in the corpus of messages with at least one of the document, a segment from the plurality of segments, and a segment of the event.

Abstract: Methods are disclosed in which participants in a communication session contribute tags—during the course of the communication session—such that the tags are visible to at least some of the participants as the communication session progresses. This creates a “live” collaborative tagging environment. Tags are contributed by some or all the participants on the communication session. The tags are displayed as they are generated. Moreover, one who declines to speak on the communication session can still actively tag. In this way, a tagger can participate and contribute in a collaborative live manner while the communication session is in progress. This approach departs from traditional “after the fact” or “note-taking” techniques in the prior art.

Abstract: A method of determining which users are experts and which tags are appropriate without some of the disadvantages of the prior art is described. The level of a user's expertise is determined based on previous tags, the categorization of one or more tags, and the rating of the tags previously left by the user. The appropriateness of a tag is based on previous tagging of information by the user, by the number of times a user has tagged information with the same categorization, and the rating of a user.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for processing media highlights. A first method includes displaying a real-time media event to a user, and, upon receiving a first indication from the user at a first time, generating a highlight of the real-time media event based on the first time, the highlight being associated with a portion of the real-time media event at the first time, and associating, in a highlight database, the highlight with an individual profile of the user. The highlight can include parameters for media content and/or duration. The highlight duration can be based on an analysis of content of the real-time media event. Highlights can be assigned to specific highlight categories. Other aspects disclosed herein apply to playback of media highlights during playback of a recorded media event, and managing stored highlights.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for simplifying and clarifying user interfaces, both their design and usage. The disclosed system creates and applies rules user options. Upon application of the rules, the system automatically organizes the user options in accordance with the rules, such that the programmer no longer needs to organize every aspect of an options menu and a user can quickly and efficiently choose from the options. Statistics regarding usage and probability are stored to make the options presented more efficient.

Abstract: Techniques are disclosed for determining, for each candidate communication medium, the availability of one or more telecommunications endpoint users for participating in a communication session of interest (i.e., either new or existing) via the evaluated medium. In accordance with the illustrative embodiment of the present invention, an availability manager determines the availability based on (i) one or more discrete rules, or (ii) one or more continuous functions, or both. The continuous functions are specified with respect to the time that has elapsed since a previous session, the time remaining in an active session, and the expected duration of a new session. Once it has determined the availability of one or more participants in the communication session, the availability manager of the illustrative embodiment transmits one or more signals to a call-processing server, which then sets up the participants on the session via the appropriate communication medium such as voice, instant messaging, and so forth.

Abstract: Methods and apparatus are provided for establishing a conference based on the presence or preferences (or both) of one or more invitees. The presence of each invitee is evaluated on one or more devices. A media type is selected based on the presence information. User preference information may be evaluated for those invitees who are not currently present on a device. The selected media type for the conference may optionally be required to support the requirements of the conference, such as document sharing or video links. In this manner, the same communication application can trigger conferences of different media types (where the selected media type is most likely to lead to the successful establishment of the conference). In addition, the present invention allows a media type to be selected that will be more likely to lead to the successful establishment of a conference.

Abstract: A method of determining which users are experts and which tags are appropriate without some of the disadvantages of the prior art is described. The level of a user's expertise is determined based on previous tags, the categorization of one or more tags, and the rating of the tags previously left by the user. The appropriateness of a tag is based on previous tagging of information by the user, by the number of times a user has tagged information with the same categorization, and the rating of a user.

Abstract: Methods and apparatus are provided for analyzing user activity and for recording such user activity in an entity relationship model. A network is searched for materials associated with a user and content analysis techniques are performed on the associated materials to extract one or more characteristics from the associated materials based on predefined criteria. The extracted information is stored in an entity relationship model that relates the user to the extracted characteristics. The characteristics may include activity information, expertise information and location information. The entity relationship model can thereafter be searched to identify and optionally contact one or more users having desired characteristics.

Abstract: Methods and apparatus are disclosed for collecting presence information about a user from one or more presence sources associated with the user, such as applications, devices and locations. A presence agent is associated with each presence source; and the presence agents provide presence information to one or more presence servers. Typically, the presence agents execute on a processor associated with the corresponding presence source. The presence agent reports one or more of macropresence events and micropresence events. The presence agent optionally prompts the user to update the presence information based on one or more criteria, such as exceeding a time threshold since the last presence event. Continuous presence functions are generated for each presence source that characterize the likelihood of the user to be present on the corresponding presence source at a given time.