Abstract: As described herein, a system, method, and computer program are provided for using shared customer data and artificial intelligence to predict customer classifications. A first system of a first business entity receives an artificial intelligence model generated using output of a secure multi-party computation applied to: a first schema of first customer data stored by the first system, and a second schema of second customer data stored by a second system of a second business entity. Additionally, the first system executes the artificial intelligence model on the first customer data stored by the first system to generate a predictor, the predictor configured to receive input and process the input to predict a classification for the input. Further, the first system distributes the predictor for use by the second system of the second business entity to predict at least one classification for the second customer data.

Abstract: As described herein, a system, method, and computer program are provided for evaluating third party AI models. A request is received from an interested party to evaluate an AI model created by a third party, where the request includes a portion of private data of the interested party, and an expected output of the AI model when applied to the portion of private data of the interested party. The AI model created by the third party is received. The AI model is evaluated by: causing the AI model to process the portion of private data of the interested party, accessing an actual output of the AI model resulting from the processing, and comparing the actual output with the expected output to generate an evaluation of the AI model. The evaluation of the AI model is then reported to the interested party.

Abstract: As described herein, a system, method, and computer program are provided for using moving network connected vehicles to deliver high level network connectivity. In use, a request for digital content to be provided to a requesting device is received, the requesting device being a residential network router or a mobile device of a user. Additionally, responsive to the request, one or more moving network connected vehicles available to obtain the digital content when moving in a vicinity of a network and to provide the digital content to the requesting device when moving in a vicinity of the requesting device are determined. Further, the one or more moving network connected vehicles are caused to obtain the digital content when moving in the vicinity of the network and to provide the digital content to the requesting device when moving in the vicinity of the requesting device.

Abstract: As described herein, a system, method, and computer program are provided for network experience optimization using a residential network router. In use, an electronic calendar is accessed by a residential network router. Additionally, the residential network router determines a plurality of events saved to the electronic calendar, wherein the plurality of events require, at least in part, simultaneous network resource (e.g. bandwidth) usage. Further, the plurality of events are prioritized, using the residential network router. Still yet, available network resources are assigned among the plurality of events, using the residential network router, based on the prioritization.

Abstract: As described herein, a machine learning system, method, and computer program are provided to predict which resident of a residential space is watching television for content targeting purposes. In use, a login to a television service on a television device in a residential space is detected. Additionally, information defining a plurality of residents of the residential space is identified. Further, a profile determined for the login is identified, where the profile is associated with a particular resident of the plurality of residents or a particular resident group of the plurality of residents. Still yet, the profile and the information defining the plurality of residents of the residential space is input to a machine learning model to predict one or more residents of the plurality of residents that is consuming the television service on the television device.

Abstract: As described herein, a system, method, and computer program are provided for using moving network connected vehicles to deliver high level network connectivity. In use, a request for digital content to be provided to a requesting device is received, the requesting device being a residential network router or a mobile device of a user. Additionally, responsive to the request, one or more moving network connected vehicles available to obtain the digital content when moving in a vicinity of a network and to provide the digital content to the requesting device when moving in a vicinity of the requesting device are determined. Further, the one or more moving network connected vehicles are caused to obtain the digital content when moving in the vicinity of the network and to provide the digital content to the requesting device when moving in the vicinity of the requesting device.

Abstract: As described herein, a system, method, and computer program are provided for using in-video annotations to select relevant advertisements for distribution to users. In use, one or more in-video annotations are automatically created for a video content, using video analysis of the video content. Also, the one or more in-video annotations included within the video content is identified. Additionally, real-time bidding is used to select an advertisement relevant to the video content, wherein the real-time bidding is performed based on the one or more in-video annotations. Further, the advertisement is presented in association with the video content.

Abstract: As described herein, a system, method, and computer program are provided for edge management of geographically dispersed sensors. An edge device within a network accesses observations of a plurality of geographically dispersed sensors. Additionally, the edge device processes the observations to determine overlapping portions of the observations. Further, the edge device optimizes the observations to form optimized observations for transmission to a cloud processing system, wherein the optimizing is based on the determined overlapping portions of the observations.

Abstract: As described herein, a system, method, and computer program are provided for network experience optimization using a residential network router. In use, an electronic calendar is accessed by a residential network router. Additionally, the residential network router determines a plurality of events saved to the electronic calendar, wherein the plurality of events require, at least in part, simultaneous network resource (e.g. bandwidth) usage. Further, the plurality of events are prioritized, using the residential network router. Still yet, available network resources are assigned among the plurality of events, using the residential network router, based on the prioritization.

Abstract: A system, method, and computer program product are provided for determining and marking on a document what may be of interest to a user. In operation, a system identifies at least one document of potential interest to at least one user. The system identifies interest points associated with the at least one document for the at least one user based on one or more of: previously identified interest points in the at least one document, previously identified interest points in other similar documents, and characteristics of the at least one document. Further, the system marks in the at least one document the identified interest points associated with the at least one document for easy viewing by the at least one user.

Abstract: A system, method, and computer program product are provided for automatic management of intent classification. In operation, an intent classification system identifies a conversation including a plurality of utterances for which to identify intent of a user associated with the plurality of utterances. The intent classification system identifies one or more actions performed in association with the plurality of utterances. Further, the intent classification system correlates at least one of the one or more actions to at least one of the plurality of utterances based on which of the one or more actions were performed as a result of the plurality of utterances. The intent classification system automatically determines an intent of the user based on the correlation of the at least one of the one or more actions to the at least one of the plurality of utterances. Additionally, the intent classification system stores an indication of the intent based on the at least one of the plurality of utterances.