Abstract: The present teaching relates to method, system, and computer programming product for dynamic vector allocation. Machine learning is conducted using training data constructed based on a target vector having a plurality of feature entries, wherein each of the plurality of feature entries is mapped from at least one original attribute from one or more original source vectors. A feature entry in the target vector is identified based on a first criterion associated with an assessment of the machine learning, for replacing the corresponding at least one original attribute from the one or more original source vectors. At least one alternative attribute from alternative source vectors based on a second criterion is determined, wherein the at least one alternative attribute is to be mapped to the feature entry of the target vector. The feature entry of the target vector is populated based on the at least one alternative attribute.

Abstract: A method of adaptive online user profiles includes displaying a website for a particular topic of interest based on a user request, receiving a request from the user to display user profile data, obtaining the user profile data, the user profile data including topic-area-specific user-specific profile information for multiple topic areas, comparing a topic area of the displayed website to a topic area for each topic-area-specific user-specific profile information, and displaying the user profile data such that the topic-area-specific user-specific profile information most closely matching the topic area of the displayed website is displayed most prominently.

Abstract: One or more systems and/or methods for filtering user profiles based upon sensitive topics are provided. A set of candidate topics labeled with sensitivity labels corresponding to whether candidate topics are sensitive topics or non-sensitive topics are generated. The sensitivity labels are applied to an unknown entity space of entities to label the entities with the sensitivity labels to create a set of labeled topics labeled as either the sensitive topics or the non-sensitive topics. The set of labeled topics and metadata for the set of labeled topics are stored within a central sensitivity data store. The set of labeled topics and metadata within the central sensitivity data store are used to filter sensitive topics from user profiles of users.

Abstract: The present teaching relates to method, system, medium, and implementations for identifying k nearest neighbors. One or more KNN lists corresponding to one or more source data points are received. Each KNN list includes K neighbors of a source data point and each of the K neighbors is a data point represented by an index. Neighbor pairs and reverse neighbor pairs are generated based on the one or more KNN lists. The neighbor pairs and reverse neighbor pairs having the same source data point are grouped to generate a grouped pairs of neighbors for the source data point. A local join operation is performed based on grouped pairs of neighbors for each source data point to generate a combined neighborhood for the source data point, which is then sent to a KNN server, where combined neighborhoods generated by multiple local join executors are integrated to update a plurality of global KNN lists.

Abstract: Disclosed are systems and methods for improving interactions with and between computers in content searching, hosting and/or providing systems supported by or configured with devices, servers and/or platforms. The disclosed systems and methods for efficiently monitoring and following up on delivered messages for which a user expects and/or requires a reply. The disclosed functionality provides a fully automated, personalized, easy and efficient way to identify and manage outgoing mail messages that require reply by marking outbound messages as RSVP messages, which are those messages determined to require a reply. Such functionality is based on the ability of the disclosed framework to distinguish between a “satisfactory response” (i.e., a response that includes the required information) and a response that is not.

Abstract: The present teaching relates to online advertising. Bids directed to a display ad opportunity are received, where the display ad opportunity involves a user and an associated context and each bid includes a candidate advertisement. Auxiliary features are obtained for each bid based on a code generated by an autoencoder based on the bid and a predicted performance metric is determined for the candidate advertisement associated with the bid based on the auxiliary features associated with the bid. A winning advertisement is selected from candidate advertisements of the bids according to a ranking determined based on the respective predicted performance metrics of the candidate advertisements.

Abstract: Techniques for a natural language interface for searching and retrieval of digitally-stored information are disclosed. In one embodiment, a computerized method is disclosed comprising receiving, at a computing device, natural language input from a user; generating, by the computing device, a prompt using the natural language input; submitting, by the computing device, the prompt to a large language model (LLM); receiving, by the computing device, from the LLM, a response to the submitted prompt, the response comprising a logical expression of the natural language input generated by the LLM using the prompt; generating, by the computing device, for a data source, a query using the logical expression; retrieving, by the computing device, a query result set from the data source using the query; and generating, by the computing device, a response to the natural language input using the query result set.

Abstract: In some implementations, the techniques described herein relate to a method including: (i) obtaining, by a processor, at least one statistic related to a recent history of a fantasy athletic team managed by a user within a fantasy athletic league, (ii) creating, by the processor, a prompt for a large language model (LLM), the prompt comprising, the at least one statistic and a set of constraints configured to produce as output from the LLM a fantasy team recap that conforms to at least one predetermined guideline, (iii) providing, by the processor, the prompt to the LLM as input, and (iv) causing display, by the processor, of the fantasy team recap output by the LLM in response to the prompt.

Abstract: Techniques for evaluating a user experience experiment designed to use one user experience variant selected from a number of user experience variants as a global-best user experience variant to be used across users relative to a machine model trained to use user data to identify a user-preferred user experience variant. Disclosed systems and methods provide techniques for optimizing user response. In one embodiment, a global-best user experience variant is evaluated by comparing an aggregate user response determined for the global-best user experience variant to an aggregate user response determined using user response predictions determined using the trained machine model, and using the outcome of the comparison to make a recommendation as to which one of the global-best user experience variant and the trained machine model to adopt for providing a user experience to users.

Abstract: The present teaching relates to providing content. Online documents are searched based on a query from a user. For each searched online document, enriched information thereof is created based on social data associated thereto and, if existing, private information previously provided by the user to privately evaluate the online document. An enhanced search result is generated based on the online documents with their respective enriched information and provided to the user in response to the query.

Abstract: In some implementations, the techniques described herein relate to a method including: (i) identifying, by a processor, a generative machine learning model trained on image data, (ii) generating, by the generative machine learning model executed by the processor, an image based on at least one parameter, (iii) editing, by an image-editing algorithm executed by the processor, the image to comprise a specified string of text in a selected area of the image, and (iv) causing display, by the processor, of the edited image.

Abstract: The present teaching relates to merging data sketches from different data sketch sources. To satisfy performance metrics specified with respect to quality of a merged sketch, sketch merging parameters are generated, which include a first set of parameters for creating obfuscated keys of the data sketches and a second set of parameters for identifying matching obfuscated keys. Keys of the data sketches are obfuscated using the first set of sketch merging parameters. The data sketches are merged by identifying matching obfuscated keys in accordance with the second set of sketch merging parameters to generate a merged sketch.

Abstract: Disclosed are systems and methods that provide a decision-intelligence (DI)-based, computerized framework for deterministically identifying and extracting content from network resources, and generating focused content based therefrom for delivery to electronic users. The framework enables real-time customization of extraction tasks, which can cause tailored, accurate results that are contextually relevant and tied into the purpose of the extraction task. This data can then be compiled and/or leveraged to generate content campaigns that can target specific sets of users, geographies, time periods, trends and the like. The framework can leverage a large language model (LLM) to seamlessly extract relevant information from network resources, which enables the generation and execution of extraction requests that can be dynamically executed and updated, which can enable the framework to “drill-down” on contextual and/or topical aspects of categories of data.

Abstract: The present teaching relates to identify events of interests. Given each of video clips, each capturing an event of interest, spatial attention regions are identified therefrom, each of which includes objects that meet a first condition. A temporal attention region is determined in each video clip according to a second condition. An action that causes an event of interest in the temporal attention region is labeled. The video clips, the respective spatial/temporal attention regions, and the action labels are then used to generate training data for machine learning of models for automatically determining, from an input video clip, a temporal attention zone for an event of interest and an action that causes the event of interest.

Abstract: Techniques for automatically generating a natural language (NL) translation of computer code are disclosed. In one embodiment, a computer-implemented method is disclosed comprising receiving, from a user, a code translation request in connection with code generated by a code generation system based on natural language (NL) input, analyzing the computer-generated code and generating a natural language (NL) translation of the computer-generated code based on the analysis, generating a graphical user interface (GUI) comprising the NL input, the NL translation of the computer-generated code and GUI control elements for receiving input from the user in connection with at least one of the NL input and the NL translation; causing the GUI to be displayed at a client device of the user, and receiving input from the user via at least one GUI control element and causing performance of at least one operation in response to the input.

Abstract: The present teaching relates to method, system, medium, and implementations for personalized content service. Information related to a user is first obtained with a user profile indicative of multiple interests of the user. User embeddings are computed with respect to some interests of the user based on interest embeddings of such interests to capture semantics of such interests as well as additional interests temporally related to the interests. Personalized content is identified based on the user embeddings and is provided to the user.

Abstract: In some implementations, the techniques described herein relate to a method including (i) receiving, by a processor, user input describing at least one parameter for a query image, (ii) generating, via a generative machine learning model executed by the processor, the query image based at least in part on the user input describing the at least one parameter for the query image, (iii) providing, by the processor, the query image as input to an image-based search algorithm, and (iv) returning a result received by the processor from the image-based search algorithm.

Abstract: The present teaching relates to method, system, medium, and implementations for identifying k nearest neighbors. A plurality of combined neighborhoods are received from a plurality of local join executors. Each combined neighborhood represents a neighborhood of a source data point and has one or more pairs of neighbors, each of which includes the source data point, a neighbor of the source point, and a distance in-between. A plurality of KNN lists corresponding to a plurality of source data points are obtained. Each KNN list includes K neighbors to a corresponding source data point, each of which is represented by an index of the neighbor and a distance between the source data point and the neighbor. The plurality of KNN lists are updated based on the plurality of combined neighborhoods to generate updated KNN lists.

Abstract: In some implementations, the techniques described herein relate to a method including: (i) identifying, by a processor, an electronic message addressed to an inbox of a user that comprises a confirmation of a transaction involving a platform, (ii) searching, by the processor, for an additional electronic message addressed to the inbox indicating an alteration applicable to the transaction, (iii) causing display, by the processor, of a prompt informing the user of the alteration applicable to the transaction, (iv) composing, by a large language model (LLM) executed by the processor, a potential electronic message to an operator of the platform requesting the alteration be retroactively applied to the transaction, and (v) in response to receiving user input regarding the potential electronic message, sending, by the processor, a subsequent electronic message to the operator of the platform requesting the alteration be retroactively applied to the transaction.

Abstract: A location-aware search assist capability identifies location-aware search query suggestions using location information associated with the location-aware search query suggestions. A user's search query input and location and a location associated with each location-aware search query suggestion candidates may be used to identify a set of search query suggestions for presentation to the user. Location-aware search query suggestion candidates may be ranked in accordance with a closeness of each one's location to the user's location. The ranking may be performed using a score, such as a popularity score associated with each search query suggestion candidate. The location-aware search query suggestion candidates having a location closer to the user's location may be promoted by adjusting each candidate's popularity score upward, and the search query suggestion candidates that are farther away from the user's location may be demoted by adjusting each such candidate's popularity score downward.