10 results about "Re ranking" patented technology

Embodiments described herein provide a method for building an artificial intelligence (AI) agent to respond to a user query. The method includes: receiving a user query; retrieving a set of documents that are ranked based on respective relevance scores of a first type to the user query; generating a core question that filters out irrelevant texts from the user query; generating a first summary of a first document from the set of documents and a first reasoning output explaining how the first summary addresses the core question; generating a relevance score of a second type and a corresponding reranking for the first document based at least in part on a combination of the core question and the first reasoning output; generating a response to the user query using one or more top-ranked documents according to generated rerankings of the set of documents.

Certain aspects of the disclosure provide for information retrieval that exploits context derived from document structure. Source documents can be preprocessed to identify fields and determine context attributes related to each field based on the structural layout of a source document. Resource documents can also be preprocessed to segment a resource document into passages and determine context related to the passages based on structural layout. Queries pertaining to a field can be enhanced by adding context metadata associated with the field. A query embedding can be generated and compared with previously generated passage embeddings to locate candidate matches based on similarity. A machine learning model can be provided with the top-ranked passages and tasked with re-ranking the passages based on relevancy to the original query. The highest re-ranked passage or set of passages can be output in response to the query.

A technique for predicting and recommending service offerings includes obtaining an initial dataset related to a user interaction with an online recommendation system during a user online session, generating a predicted intent of the user online session, and generating an initial set of recommendations based on the predicted intent of the user online session. The technique includes ranking the initial set of recommendations to generate a set of ranked recommendations, generating a predicted sequence of actions of the user, and determining that the ranked set of recommendations are to be re-ranked into a re-ranked set of recommendations. The technique includes generating a semantically customized ranked set of recommendations using at least one of the ranked set of recommendations or the re-ranked set of recommendations and providing the semantically customized ranked set of recommendations to the user.

A system and method for augmented semantic search, including: a vector store including a set of embeddings, each representing a structured data representation of a media perspective of a media item; a query execution service including functionality to receive a search request including a query string from a client application; a query classification service including functionality to execute a first machine learning model to generate a classification object in a structured classification format; a filter extraction service including functionality to execute a second machine learning model to generate a filter object including a set of filters in a structured filter format; a recaller service including functionality to: execute an encoder model on the input query and execute a vector similarity operation on the query embedding to generate a result set; and a re-ranking service including functionality to: execute a large language model to re-rank the result set.

There is provided a system for retrieving and analyzing news articles for a company. The news articles may be converted and stored in a vector database. The vector database may be queried based on environmental, social and governance factors and metrics which are the most material to that company. Articles with the highest similarity scores in the vector database may be summarized. Summarized articles may be reranked based on the similarity between a metric and factor. New headlines for highest-ranked articles may be generated together with a rationale on why the article had a high similarity score.

Embodiments of the present disclosure provide a method, device, and medium for ranking objects. The method comprises ranking a set of objects according to a predetermined policy. The method further comprises obtaining a set of object embeddings of the set of objects. The method further comprises determining a plurality of similarity scores based on the set of object embeddings. In addition, the method further comprises re-ranking the ranked set of objects based on the plurality of similarity scores for display.

The application discloses a method and system for collaborative calculation of large models and small recommendation models. The method of the application designs an end-cloud collaborative recommendation model framework, wherein a large model based on the cloud generates a candidate list and an initial ranking using historical data, and a small model on an end-side device dynamically rearranges the list using the latest user data. The collaborative decision request evaluates the need to call the large model by evaluating the consistency between the initial ranking of the large model and the subsequent rearrangement of the small model. The combination of the feature extraction capability of the large language model and the convenience of the small recommendation model enhances the practicability and accuracy of the large language model on the device.

A device may include a processor. The processor may be configured to: receive a request to re-rank a list of ranked agents or callers; when there are more agents than callers, generate a list of re-ranked agents based on the list of ranked agents; and provide the list of re-ranked agents to a component in a system for routing calls to one of agents identified in the list of re-ranked agents.

A system including a processor and a non-transitory computer-readable media storing computing instructions that, when executed on the processor, cause the processor to perform operations comprising receiving user session information for a current session for a user; generating, using a ranking model, a first listing of items based on the user session information; generating, using a query model, a query intent measurement based on the user session information; generating, using a cart context model, a cart context measurement based on the user session information; generating a second listing of items based on the first listing of items, the query intent measurement, and the cart context measurement; and displaying the second listing of items in a graphical user interface to the user. Other embodiments are described.