Abstract: Various embodiments of the present disclosure provide query processing techniques for generating optimized query results. The techniques include generating using a machine learning framework, one or more predictions for a natural language query. The one or more predictions may include an intent prediction and an event prediction. The technique may include generating an intent classification for the natural language query based on the intent prediction and the event prediction. The techniques may include in response to the intent classification corresponding to a target query intent: generating, a plurality of candidate data objects based on an identifier associated with the natural language query, identifying one or more relevant data objects from the plurality of candidate data objects based on a relevancy score for each of the plurality of candidate data object; and providing, via a user interface, a natural language query result.

Abstract: Various embodiments of the present disclosure provide methods, apparatus, systems, computing devices, computing entities, and/or the like for ranking entities provided in response to a search query by identifying one or more categorical identifiers based on a semantic similarity between a query embedding and a plurality of categorical description embeddings, generating a predicted distance preference for the search query based on a location associated with a querying user, identifying one or more entities based on the location associated with the querying user, the predicted distance preference, and entity activity data entries comprising a plurality of categorical descriptions matching the identified one or more categorical identifiers.

Abstract: Systems and methods for pill identification based on image and user claims data are disclosed. A pill identification request, including one or more images of a pill and a user identifier of a user associated with the pill, is received. A first machine learning system is used to generate one or more image embeddings based on the one or more images. The user identifier is used to retrieve claims data of the user, and the claims data are encoded to generate a claims embedding. A second machine learning system is used to identify the pill based on the one or more image embeddings and the claims embedding. A response to the pill identification request is generated based on the identifying.

Abstract: Various embodiments of the present disclosure provide methods, apparatus, systems, computing devices, computing entities, and/or the like for retrieving relevant items for user queries by generating, using a search engine machine learning model, a prediction-based action for the query input wherein query input embeddings of the query input are generated. For each query input embedding, a k-Nearest-Neighbor (KNN) search is performed with respect to search engine repository item embeddings to generate initial search results, and for each initial set result, performing N hops within a semantic graph starting from nodes associated with the initial search result to generate related search results. The search engine machine learning model is trained by generating a search engine repository item embeddings according to embedding techniques for respective content categories and generating the semantic graph based at least in part on a measure of similarity for pairs of search engine repository item embeddings.

Abstract: Systems and methods for improved spelling checking are disclosed. A method includes receiving a search query from a user device and determining that the search query does not exist in a data store that stores (a) a corpus of correctly spelled words or (b) forced correction mapping data. The method further includes, in response to the determining, determining a plurality of suggested search queries generated by a plurality of respective spell corrector models, selecting a suggested search query determined using a spell corrector model from the plurality of spell corrector models based on at least one of a frequency of the suggested search query in historical search data or a weightage associated with the spell corrector model, and causing the suggested search query to be displayed on the user device.

Abstract: Various embodiments of the present disclosure provide query processing techniques for generating optimized query results. The techniques include generating using a machine learning framework, one or more predictions for a natural language query. The one or more predictions may include an intent prediction and an event prediction. The technique may include generating an intent classification for the natural language query based on the intent prediction and the event prediction. The techniques may include in response to the intent classification corresponding to a target query intent: generating, a plurality of candidate data objects based on an identifier associated with the natural language query, identifying one or more relevant data objects from the plurality of candidate data objects based on a relevancy score for each of the plurality of candidate data object; and providing, via a user interface, a natural language query result.

Abstract: Systems and methods for improved spelling checking are disclosed. A method includes receiving a search query from a user device and determining that the search query does not exist in a data store that stores (a) a corpus of correctly spelled words or (b) forced correction mapping data. The method further includes, in response to the determining, determining a plurality of suggested search queries generated by a plurality of respective spell corrector models, selecting a suggested search query determined using a spell corrector model from the plurality of spell corrector models based on at least one of a frequency of the suggested search query in historical search data or a weightage associated with the spell corrector model, and causing the suggested search query to be displayed on the user device.

Abstract: Methods, apparatuses, systems, computing devices, and/or the like are provided. An example method may include retrieving an initial ranking data object associated with a plurality of search result data objects, retrieving a plurality of relevance score data objects, generating a plurality of ranking comparison score data objects, generating a multi-measure optimized ranking data object associated with the plurality of search result data objects, and performing one or more prediction-based actions based at least in part on the multi-measure optimized ranking data object.

Abstract: Various embodiments of the present invention provide methods, apparatus, systems, computing devices, computing entities, and/or the like for performing personalized autocomplete predictions. Certain embodiments of the present invention utilize systems, methods, and computer program products that perform personalized autocomplete predictions using a general search corpus and/or individual curated search corpus.

Abstract: Various embodiments of the present disclosure provide methods, apparatus, systems, computing devices, computing entities, and/or the like for retrieving relevant items for user queries by generating, using a search engine machine learning model, a prediction-based action for the query input wherein query input embeddings of the query input are generated. For each query input embedding, a k-Nearest-Neighbor (KNN) search is performed with respect to search engine repository item embeddings to generate initial search results, and for each initial set result, performing N hops within a semantic graph starting from nodes associated with the initial search result to generate related search results. The search engine machine learning model is trained by generating a search engine repository item embeddings according to embedding techniques for respective content categories and generating the semantic graph based at least in part on a measure of similarity for pairs of search engine repository item embeddings.

Abstract: A method for user identification of a desired document is provided. The method includes receiving an identification of a prototype document, providing a database identifying a catalog of documents, identifying as candidate documents all documents within the catalog of documents which are within a threshold T1 relative to the prototype document, the threshold T1 being a member of the group consisting of (i) a distance representing dissimilarity and (ii) a score determined in dependence on a view of user preferences and dissimilarity, identifying a collection of fewer than all of the candidate documents, receiving, from the user, a selection of one or more documents from the collection identified toward the user, reducing the threshold T1 by a predetermined amount, and removing, from the candidate documents, all documents within the catalog of documents having a distance greater than the reduced threshold T1 from the selected one or more documents.