Abstract: An embodiment includes a method, comprising: pruning a layer of a neural network having multiple layers using a threshold; and repeating the pruning of the layer of the neural network using a different threshold until a pruning error of the pruned layer reaches a pruning error allowance.

Abstract: An embodiment includes a method, comprising: pruning a layer of a neural network having multiple layers using a threshold; and repeating the pruning of the layer of the neural network using a different threshold until a pruning error of the pruned layer reaches a pruning error allowance.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for predicting the subject, logistics, and resources of associated with a communication event. Predictions and suggestions can occur prior to, during, or in response to communication events. The user can confirm the prediction or suggestion via user input such as a click or a voice command. The system can analyze past behavior patterns with respect to the subject, logistics and resources of communication events, followed by preparing ranked listings of which subjects, logistics, and resources are most likely to be used in a given situation. The predicted logistics may then include people to invite, time and date of the meeting, its duration, location, and anything else useful in helping potential participants gather together. The resources may include files attached, files used, communication event minutes, recordings made, Internet browsers and other programs which may be utilized by the user.

Abstract: An embodiment includes a method, comprising: pruning a layer of a neural network having multiple layers using a threshold; and repeating the pruning of the layer of the neural network using a different threshold until a pruning error of the pruned layer reaches a pruning error allowance.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for generating a context-based rich communication log. A system configured to practice the method performs a context-based analysis of a history of communication sessions over at least two communication modalities, wherein the context-based analysis considers semantic meaning, temporal relationship, and user activities. The system generates associations between the communication sessions based on the context-based analysis, and generates the context-based rich communication log based on the associations. The context-based analysis can be based on time, session participant identifications, ongoing events, and/or on-demand queries of the communication sessions. The system can then present the context-based rich communication log to a user.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for automatically establishing trusted relationships between users across organizational boundaries. A user makes a request to his system to create a trusted relationship with an individual of another organization. The system then analyzes the previous communication history between the user and the other individual, and, based on that analysis, sends a query to the other individual's system. The system then receives a response from the other individual's system, and if the response matches an expected response the system forms a trusted relationship between the user and the other individual.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for predicting the subject, logistics, and resources of associated with a communication event. Predictions and suggestions can occur prior to, during, or in response to communication events. The user can confirm the prediction or suggestion via user input such as a click or a voice command. The system can analyze past behavior patterns with respect to the subject, logistics and resources of communication events, followed by preparing ranked listings of which subjects, logistics, and resources are most likely to be used in a given situation. The predicted logistics may then include people to invite, time and date of the meeting, its duration, location, and anything else useful in helping potential participants gather together. The resources may include files attached, files used, communication event minutes, recordings made, Internet browsers and other programs which may be utilized by the user.

Abstract: Methods, systems, and computer-readable media for self-learning interactive communications privileges for governing interactive communications with entities outside a domain are disclosed. The interactive communications privileges can be used to process interactive communications requests between entities inside and outside a domain. The requested interactive communications are allowed if the interactive communications privileges configured for the entity outside the domain allow for the requested interactive communications. The interactive communications privileges are determined in an automated, self-learning manner in response to monitoring communication interactions between the entities inside and outside the domain. In this manner, the interactive communications privileges are not required to be provisioned and maintained by an administrator. The interactive communications privileges can be determined by gathering insight about the entities outside the domain.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for predicting the subject, logistics, and resources of associated with a communication event. Predictions and suggestions can occur prior to, during, or in response to communication events. The user can confirm the prediction or suggestion via user input such as a click or a voice command. The system can analyze past behavior patterns with respect to the subject, logistics and resources of communication events, followed by preparing ranked listings of which subjects, logistics, and resources are most likely to be used in a given situation. The predicted logistics may then include people to invite, time and date of the meeting, its duration, location, and anything else useful in helping potential participants gather together. The resources may include files attached, files used, communication event minutes, recordings made, Internet browsers and other programs which may be utilized by the user.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for facilitating communications based on a trusted relationships. A system configured to practice the method first receives a communication request from a second communication device for a specific resource, wherein the communication request is based, at least in part, on trust information generated by a previously established trusted relationship. The system confirms, via an access to a trust database and using the trust information, (1) an identity of a sender of the communication request and (2) access permissions for a requested resource. Then, if the identity and the access permissions are confirmed, the system establishes communications between the first communications device and the second communications device in response to the communication request according to the specific resource. The trust information can include a trust user ID and a trust key.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for identifying document topics. A system configured to practice the method receives a document from a corpus of documents, learns interpersonal relationships of users associated with the document, performs a lexical analysis of the document, and, based on the interpersonal relationships of the users and the lexical analysis, identifying a topic for the document. The approaches disclosed herein can integrate user-people relationships to identify topics for documents with low lexical or high contextual content. The system can learn this user-people relationship from context. The system uses this learned behavior to identify communication documents correctly. Another aspect is the separation of the two phases.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for facilitating communications based on a trusted relationships. A system configured to practice the method first receives a communication request from a second communication device for a specific resource, wherein the communication request is based, at least in part, on trust information generated by a previously established trusted relationship. The system confirms, via an access to a trust database and using the trust information, (1) an identity of a sender of the communication request and (2) access permissions for a requested resource. Then, if the identity and the access permissions are confirmed, the system establishes communications between the first communications device and the second communications device in response to the communication request according to the specific resource. The trust information can include a trust user ID and a trust key.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for facilitating communications based on a trusted relationships. A system configured to practice the method first receives a communication request from a second communication device for a specific resource, wherein the communication request is based, at least in part, on trust information generated by a previously established trusted relationship. The system confirms, via an access to a trust database and using the trust information, (1) an identity of a sender of the communication request and (2) access permissions for a requested resource. Then, if the identity and the access permissions are confirmed, the system establishes communications between the first communications device and the second communications device in response to the communication request according to the specific resource. The trust information can include a trust user ID and a trust key.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for predicting the subject, logistics, and resources of associated with a communication event. Predictions and suggestions can occur prior to, during, or in response to communication events. The user can confirm the prediction or suggestion via user input such as a click or a voice command. The system can analyze past behavior patterns with respect to the subject, logistics and resources of communication events, followed by preparing ranked listings of which subjects, logistics, and resources are most likely to be used in a given situation. The predicted logistics may then include people to invite, time and date of the meeting, its duration, location, and anything else useful in helping potential participants gather together. The resources may include files attached, files used, communication event minutes, recordings made, Internet browsers and other programs which may be utilized by the user.

Abstract: A method of authentication of a verifying device by a confirming device includes the confirming device receiving and storing a shared secret derived from at least a password of a user and sending a challenge. The method further includes the confirming device receiving a response to the challenge using the shared secret; determining if the response to the challenge is correct and if the response to the challenge is correct, authenticating the verifying device.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for predicting the subject, logistics, and resources of associated with a communication event. Predictions and suggestions can occur prior to, during, or in response to communication events. The user can confirm the prediction or suggestion via user input such as a click or a voice command. The system can analyze past behavior patterns with respect to the subject, logistics and resources of communication events, followed by preparing ranked listings of which subjects, logistics, and resources are most likely to be used in a given situation. The predicted logistics may then include people to invite, time and date of the meeting, its duration, location, and anything else useful in helping potential participants gather together. The resources may include files attached, files used, communication event minutes, recordings made, Internet browsers and other programs which may be utilized by the user.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for scheduling an event to automatically join a user to a conference call. In one aspect, the method includes receiving an invitation for a user to join a conference call, extracting from the invitation a scheduled conference call time, conference call address information, conference call authentication information, and a conference call modality, and scheduling an event to join the user to the conference call via the conference call modality at the scheduled conference call time based on the conference call address information and the conference call authentication information. In another aspect, the system retrieves a scheduled event at a scheduled time, extracts the address, authentication, and modality information for the conference, and joins the user to the conference automatically at the scheduled time.

Abstract: Methods, systems, and computer-readable media for self-learning interactive communications privileges for governing interactive communications with entities outside a domain are disclosed. The interactive communications privileges can be used to process interactive communications requests between entities inside and outside a domain. The requested interactive communications are allowed if the interactive communications privileges configured for the entity outside the domain allow for the requested interactive communications. The interactive communications privileges are determined in an automated, self-learning manner in response to monitoring communication interactions between the entities inside and outside the domain. In this manner, the interactive communications privileges are not required to be provisioned and maintained by an administrator. The interactive communications privileges can be determined by gathering insight about the entities outside the domain.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for automatically establishing trusted relationships between users across organizational boundaries. A user makes a request to his system to create a trusted relationship with an individual of another organization. The system then analyzes the previous communication history between the user and the other individual, and, based on that analysis, sends a query to the other individual's system. The system then receives a response from the other individual's system, and if the response matches an expected response the system forms a trusted relationship between the user and the other individual.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for identifying document topics. A system configured to practice the method receives a document from a corpus of documents, learns interpersonal relationships of users associated with the document, performs a lexical analysis of the document, and, based on the interpersonal relationships of the users and the lexical analysis, identifying a topic for the document. The approaches disclosed herein can integrate user-people relationships to identify topics for documents with low lexical or high contextual content. The system can learn this user-people relationship from context. The system uses this learned behavior to identify communication documents correctly. Another aspect is the separation of the two phases.