Methods, computer-readable media, systems, and/or apparatuses for providing offer and insight generation functions are provided. For instance, user input may be received requesting generation of an offer. In response to receiving the request, an application may be transmitted to a device, such as a mobile device of a user. In some examples, the application may be executed by the device and may facilitate establishing a communication session with a third party system, identifying and extracting data from the third party system, and transmitting the extracted data to an entity for evaluation. In some examples, evaluation by the entity may include generating one or more insights, outputs and the like. In some arrangements, the evaluation may be performed using machine learning and, in some examples, may be performed in real-time or near real-time.

Examples provide a self-supervised language model for document-to-document similarity scoring and ranking long documents of arbitrary length in an absence of similarity labels. In a first stage of a two-staged hierarchical scoring, a sentence similarity matrix is created for each paragraph in the candidate document. A sentence similarity score is calculated based on the sentence similarity matrix. In the second stage, a paragraph similarity matrix is constructed based on aggregated sentence similarity scores associated with the first candidate document. A total similarity score for the document is calculated based on the normalize the paragraph similarity matrix for each candidate document in a collection of documents. The model is trained using a masked language model and intra-and-inter document sampling. The documents are ranked based on the similarity scores for the documents.

A method for estimating response relevance with respect to a received query includes receiving a set of user feedback items, a set of historical feedback data, and a set of context data, creating a user profile model according to the set of historical feedback data, wherein the user profile model indicates a weighting attribute based on the set of historical feedback data, weighting the set of user feedback items according to the created user profile model, creating a response relevance estimation model based on the weighted set of user feedback items, the received set of context data, and the received set of historical feedback data, and ranking one or more responses according to the created response relevance estimation model. The method may further include adjusting the user profile model and the response relevance estimation model responsive to receiving additional data.

The present invention relates to summarizing cross-network user behavioral data. The summarizing cross-network user behavioral data may particularly include publishing the data to one or more data structures that become accessible to a server hosting an authorized domain when a user accesses the authorized domain.

A method of selecting and presenting content based on learned user preferences is provided. The method includes providing a content system including a set of content items organized by genre characterizing the content items, and wherein the set of content items contains microgenre metadata further characterizing the content items. The method also includes receiving search input from the user for identifying desired content items and, in response, presenting a subset of content items to the user. The method further includes receiving content item selection actions from the user and analyzing the microgenre metadata within the selected content items to learn the preferred microgenres of the user. The method includes, in response to receiving subsequent user search input, selecting and presenting content items in an order that portrays as relatively more relevant those content items containing microgenre metadata that more closely match the learned microgenre preferences of the user.

A method and apparatus for generation and implementation of location-based testing and verification is provided. In various implementations, location-based testing is generated and administered in response to a user requesting verification of an account with a location or other community trait. In various further implementations, location-based testing is improved by soliciting and utilizing digital representations of traits or locations to improve testing procedures. In various further implementations, machine learning and verified community feedback is employed to improve location-based testing.

A system and method for learning user preferences operates by posing topics in a manner similar to a human-to-human conversation. The system learns which topics to present to a human user from an initially seeded response database containing natural language phrases. The system then records user responses into the same response database or a connected response database. The system assigns user responses into categories, such as positive, negative, request for information, null, and potentially others. The system then bases future topics on what it learns during the interaction, including user responses, user response categories, time of data, location, how busy the human user typically is at difference times of day or certain days, and the like.

A processor may receive a submission of a command. The processor may analyze the command for at least one commonality with a previous command and predict a predicted reason for the submission of the command based on historical learning. The processor may integrate the predicted reason into a corpus specific to a user, wherein the corpus includes user preference data, and wherein the processor predicts one or more orders of the user using the corpus.

The system described herein can automatically match, link, or otherwise associate electronic activities with one or more record objects. For an electronic activity that is eligible or qualifies to be matched with one or more record objects, the system can identify one or more set of rules or rule sets. Using the rule sets, the system can identify candidate record objects. The system can then rank the identified candidate record objects to select one or more record objects with which to associate the electronic activity. The system can then store an association between the electronic activity and the selected one or more record objects.

A computer generates a navigation profile corresponding to a user by identifying one or more user preferences within an associated social media network. The computer receives a user input identifying a starting location and a destination, from which the computer identifies one or more potential routes between the starting location and destination. The computer generates one or more route profiles corresponding to the one or more potential routes detailing one or more characteristics associated with each of the potential routes. The computer then compares the navigation profile associated with the user to the route profiles associated with the one or more potential routes and, based on the comparison, determines an optimal route of the one or more potential routes.