Abstract: The present disclosure is directed to providing search results based on user interaction with content. A server receives identification of a plurality of clicks of encoded uniform resource locator (URL) links and identifies, for each of the plurality of clicks, data about a user who clicked an encoded URL link and traffic data associated with a device from which the user clicked the encoded URL link. The server may store a record comprising data about the user and traffic data associated with each click. The server may determine, based on the records, a relevancy score for each content identified from decoding the encoded URL links. The server may communicate, responsive to receiving a request to search content based on a keyword, a set of search results based on the keyword and the relevancy score.

Abstract: The present disclosure is directed to a method for tracking influence of a user on content shared via encoded uniform resource locator (URL) links. Measuring influence of a user may identify what level of engagement the user drives to content when the user shares content with other users, such as via encoded links. A high influencer may be a user who drives a high level of engagement with content when the user shares content. A low influencer may be a user who does not drive a high level of engagement, or otherwise drives a low level of engagement with content when the user shares content. The method may include receiving, by a server, identification of a user for each of a plurality of encoded uniform resource locator (URL) links. The server may identify a plurality of keywords from content identified by each encoded URL link. The server may determine a number of actions via a plurality of users that decoded each encoded URL link of the plurality of encoded URL links of the user.

Abstract: The present disclosure is directed to a method for tracking influence of a user on content shared via encoded uniform resource locator (URL) links. Measuring influence of a user may identify what level of engagement the user drives to content when the user shares content with other users, such as via encoded links. A high influencer may be a user who drives a high level of engagement with content when the user shares content. A low influencer may be a user who does not drive a high level of engagement, or otherwise drives a low level of engagement with content when the user shares content. The method may include receiving, by a server, identification of a user for each of a plurality of encoded uniform resource locator (URL) links. The server may identify a plurality of keywords from content identified by each encoded URL link. The server may determine a number of actions via a plurality of users that decoded each encoded URL link of the plurality of encoded URL links of the user.

Abstract: The present disclosure is directed to a method for tracking influence of a user on content shared via encoded uniform resource locator (URL) links. Measuring influence of a user may identify what level of engagement the user drives to content when the user shares content with other users, such as via encoded links. A high influencer may be a user who drives a high level of engagement with content when the user shares content. A low influencer may be a user who does not drive a high level of engagement, or otherwise drives a low level of engagement with content when the user shares content. The method may include receiving, by a server, identification of a user for each of a plurality of encoded uniform resource locator (URL) links. The server may identify a plurality of keywords from content identified by each encoded URL link. The server may determine a number of actions via a plurality of users that decoded each encoded URL link of the plurality of encoded URL links of the user.

Abstract: An image processing system involves a camera, at least one processor associated with the camera, non-transitory storage, a lexical database of terms and image classification software. The image processing system uses the image classification software to assign hyponyms and associated probabilities to an image and then builds a subset hierarchical tree of hypernyms from the lexical database of terms. The processor then scores the hypernyms and identifies at least one hypernym for the image that has a score that is calculated to have a value that is greater than one of: a pre-specified threshold score, or all other calculated level scores within the subset hierarchical tree. The associated methods are also disclosed.

Abstract: An image processing system involves a camera, at least one processor associated with the camera, non-transitory storage, a lexical database of terms and image classification software. The image processing system uses the image classification software to assign hyponyms and associated probabilities to an image and then builds a subset hierarchical tree of hypernyms from the lexical database of terms. The processor then scores the hypernyms and identifies at least one hypernym for the image that has a score that is calculated to have a value that is greater than one of: a pre-specified threshold score, or all other calculated level scores within the subset hierarchical tree. The associated methods are also disclosed.

Abstract: A computerized method for generating and evaluating natural language-generated text involves receiving, in a computer, data input by a user, generating, using a natural language generation technique, multiple instances of text stories based upon both contents of a corpus and the received data; analyzing the multiple instances of text stories as a weighted combination of computed geographic scores, distance scores, information content scores, replacement scores and extra aspect scores, providing a ranked set of the generated text stories to a user, receiving a selection of one of the text stories in the ranked set, and storing the selected story.

Abstract: An image processing system involves a camera, at least one processor associated with the camera, non-transitory storage, a lexical database of terms and image classification software. The image processing system uses the image classification software to assign hyponyms and associated probabilities to an image and then builds a subset hierarchical tree of hypernyms from the lexical database of terms. The processor then scores the hypernyms and identifies at least one hypernym for the image that has a score that is calculated to have a value that is greater than one of: a pre-specified threshold score, or all other calculated level scores within the subset hierarchical tree. The associated methods are also disclosed.

Abstract: An image processing system involves a camera, at least one processor associated with the camera, non-transitory storage, a lexical database of terms and image classification software. The image processing system uses the image classification software to assign hyponyms and associated probabilities to an image and then builds a subset hierarchical tree of hypernyms from the lexical database of terms. The processor then scores the hypernyms and identifies at least one hypernym for the image that has a score that is calculated to have a value that is greater than one of: a pre-specified threshold score, or all other calculated level scores within the subset hierarchical tree. The associated methods are also disclosed.

Abstract: The present disclosure is directed to a method for tracking influence of a user on content shared via encoded uniform resource locator (URL) links. Measuring influence of a user may identify what level of engagement the user drives to content when the user shares content with other users, such as via encoded links. A high influencer may be a user who drives a high level of engagement with content when the user shares content. A low influencer may be a user who does not drive a high level of engagement, or otherwise drives a low level of engagement with content when the user shares content. The method may include receiving, by a server, identification of a user for each of a plurality of encoded uniform resource locator (URL) links. The server may identify a plurality of keywords from content identified by each encoded URL link. The server may determine a number of actions via a plurality of users that decoded each encoded URL link of the plurality of encoded URL links of the user.

Abstract: A computerized method for generating and evaluating natural language-generated text involves receiving, in a computer, data input by a user, generating, using a natural language generation technique, multiple instances of text stories based upon both contents of a corpus and the received data; analyzing the multiple instances of text stories as a weighted combination of computed geographic scores, distance scores, information content scores, replacement scores and extra aspect scores, providing a ranked set of the generated text stories to a user, receiving a selection of one of the text stories in the ranked set, and storing the selected story.

Abstract: The present disclosure is directed to systems and methods for measuring influence of a user may identify what level of engagement the user drives to content when the user shares content with other users, such as via encoded links. A high influencer may be a user who drives a high level of engagement with content when the user shares content. A low influencer may be a user who does not drive a high level of engagement, or otherwise drives a low level of engagement with content when the user shares content.

Abstract: The present disclosure is directed to a method for providing a recommended list of uniform resource locators (URLs) responsive to a uniform resource locator (URL). The method may include identifying, by a server, a plurality of users that clicked on an encoded uniform resource locator (URL) link corresponding to a URL. The server may identify a plurality of encoded URL links clicked by each of the plurality of users. The server may determine a number of users who clicked on each encoded URL link of the plurality of encoded URL links and also clicked on the encoded URL link. The server may enumerate, responsive a request comprising the URL, a list of URLs and their corresponding score based on the determination, each URL of the list of URLs corresponding to one of the plurality of encoded URL links.

Abstract: The present disclosure is directed to a method for identifying which phrases are trending across an aggregate of users that are relevant to a specific user. The method may include receiving, by a server, identification of a user. The server may identify a plurality of phrases that are trending upwards based on velocity of clicks to content containing, related to or associated with the plurality of phrases. The server may identify trending or temporally popular phrases based on aggregating multiple users' interactions with an aggregate of content. The server may determine a relevance score for each phrase of the plurality of phrases that are trending upwards based on identification of the user and actions of the user on content associated with each phrase, such as user clicking on content identifying or related to each phrase. The server may identify one or more phrases of the plurality of phrases based on relevance score.

Abstract: The present disclosure is directed to providing search results based on user interaction with content. A server receives identification of a plurality of clicks of encoded uniform resource locator (URL) links and identifies, for each of the plurality of clicks, data about a user who clicked an encoded URL link and traffic data associated with a device from which the user clicked the encoded URL link. The server may store a record comprising data about the user and traffic data associated with each click. The server may determine, based on the records, a relevancy score for each content identified from decoding the encoded URL links. The server may communicate, responsive to receiving a request to search content based on a keyword, a set of search results based on the keyword and the relevancy score.

Abstract: The present disclosure is directed to systems and methods to identify trending or temporally popular phrases based on aggregating multiple users' interactions with an aggregate of content. A server may receive identification of a plurality of clicks of encoded uniform resource locator (URL) links. The server may identify, for each of the plurality of clicks, in content identified from decoding the encoded URL links, a plurality of phrases that correspond to a predetermined set of keywords. The server may determine a velocity of clicks on content corresponding to each phrase of the plurality of phrases and identify a trend in one or more phrases of the plurality of phrases based on the velocity of clicks.

Abstract: The present disclosure is directed to systems and methods that score content, URLs, domains, phrases or any entity based on an expected relevance to an individual user which may be based on that user's previous engagement with digital resources. A server receives identification of a plurality of actions of a user, which may include a click by the user on a link associated with a digital resource of a plurality of digital resources. The server may receive identification of actions of the user to share one or more digital resources of the plurality of digital resources. The server may identify a plurality of keywords from content of the plurality of digital resources, classify patterns from the actions of the users and the keywords and generate, based on the pattern classification, a relevance score responsive to receiving a user identifier and a digital resource keyword.

Abstract: The present disclosure is directed to systems and methods that score content, URLs, domains, phrases or any entity based on an expected relevance to an individual user which may be based on that user's previous engagement with digital resources. A server receives identification of a plurality of actions of a user, which may include a click by the user on a link associated with a digital resource of a plurality of digital resources. The server may receive identification of actions of the user to share one or more digital resources of the plurality of digital resources. The server may identify a plurality of keywords from content of the plurality of digital resources, classify patterns from the actions of the users and the keywords and generate, based on the pattern classification, a relevance score responsive to receiving a user identifier and a digital resource keyword.

Abstract: The present disclosure is directed to systems and methods to identify trending or temporally popular phrases based on aggregating multiple users' interactions with an aggregate of content. A server may receive identification of a plurality of clicks of encoded uniform resource locator (URL) links. The server may identify, for each of the plurality of clicks, in content identified from decoding the encoded URL links, a plurality of phrases that correspond to a predetermined set of keywords. The server may determine a velocity of clicks on content corresponding to each phrase of the plurality of phrases and identify a trend in one or more phrases of the plurality of phrases based on the velocity of clicks.

Abstract: The present disclosure is directed to a method for providing a recommended list of uniform resource locators (URLs) responsive to a uniform resource locator (URL). The method may include identifying, by a server, a plurality of users that clicked on an encoded uniform resource locator (URL) link corresponding to a URL. The server may identify a plurality of encoded URL links clicked by each of the plurality of users. The server may determine a number of users who clicked on each encoded URL link of the plurality of encoded URL links and also clicked on the encoded URL link. The server may enumerate, responsive a request comprising the URL, a list of URLs and their corresponding score based on the determination, each URL of the list of URLs corresponding to one of the plurality of encoded URL links.