Citibank, N.a.

Jason Ryan Engelbrecht

Alberto Cetoli

John E Ortega, Jr

Youval Bitner

Joel Branch

Ines Teixeira

Yael Man

Minjeong Cho

James Myers

Ganesh Prasad Bhat

Wei Jie Ng

Subramanian Sankaran

Ramee S Karthikeyan

Alex Michael Eng

Cameron Paul Lim

Matthew Ryan Mitsui

William Franklin Cameron

Alexis Rialt

Jakub Cysar

Mark Fullbrook

Isabelle Choudhry

Ryan Bergeron

Haolin Jin

Sourabh Deb

Zheyu Wang

Systems and methods disclosed herein are enabled to dynamically generate structured documents using one or more artificial intelligence models. A computing device receives an output generation request and uses a first AI model to retrieve data chunks from source documents and applicable templates. A second AI model ranks the retrieved chunks based on one or more metrics, such as vector similarity, keyword density, and temporal relevance. A third AI model subsequently generates a response using the ranked chunks, templates, and predefined operational boundaries for each chunk. The generated response is tagged with source identifiers to enable the traceability of the response back to corresponding chunks. The system transmits, via the computing device, the response, the retrieved chunks, and/or the source identifiers.

Generating structured documents with traceable source lineage

The systems and methods disclosed herein obtain (e.g., via a user interface) a collection of unstructured data, where each document includes a content set. Using a first AI model set, multiple summaries are generated by categorizing each document into clusters based on vector comparisons of content sets and summarizing the content for each cluster. A second AI model set (same as or different from the first AI model set) identifies duplicate content within the unstructured data by generating similarity values between pairs of summaries and determining if the similarity values meet a predefined threshold. A report is generated (e.g., on the user interface) indicating the duplicate content sets and/or the collection of unstructured data.

Remediation of unstructured data using artificial intelligence

Systems and methods are disclosed comprising instructions to receive a request to evaluate authorization of a development service that comprises a digital artifact set, each digital artifact in the digital artifact set, access an authorization schema set available for the development service, identify an applicable authorization schema from the authorization schema set via comparing the content embeddings of the digital artifacts and the reference embeddings of the authorization schemas, retrieve a historical artifact attribute set representing tracked development actions for prior development services authorized via the applicable authorization schema, predict an authorization status for the development service using the historical artifact attribute set and the artifact attribute set, configure for display a visual representation of the applicable authorization schema and the mapped at least one digital artifact of the development service.

Robust artifacts mapping and authorization systems and methods for operating the same

The systems and methods disclosed herein receive a dataset including an observed set of values for a set of variables. The system can use a first set of AI models to identify a set of anomalies in the observed set of values by comparing an observed set of patterns against multiple reference patterns. The system can use a second set of AI models to evaluate the identified anomalies by comparing an observed set of association rules with an expected set of association rules. The system can use a third set of AI models to generate reconfiguration commands to remove the identified anomalies. The reconfiguration commands can be automatically executed to modify the observed association rules to align with the expected association rules.

Detecting data anomalies using artificial intelligence

The systems and methods disclosed herein generates responses generated by artificial intelligence (AI) models such as large language models (LLM) using intent-based rankings of retrieved information. The systems and methods disclosed herein receives an output generation request for the generation of an output using a set of AI models. Using a first AI model, a set of documents are retrieved using the received output generation request. The set of documents are partitioned into chunks. The chunks are ranked using a distance between the vector representation of the received output generation request and the vector representation of each chunk. A second AI model classifies the output generation request and chunks using an intent of the respective output generation request or chunk, and generates a second set of rankings using the intents. The set of AI models generate a response using the second set of rankings.

Using intent-based rankings to generate large language model responses

The systems and methods disclosed herein enable the dynamic selection of one or more AI models to generate an output in response to an input. The system receives, from a computing device, an output generation request including an input for the generation of an output using one or more models from a plurality of models. The system generates expected values for a set of output attributes of the output generation request. For each particular model in the plurality of models, the system determines the capabilities of the particular model, and dynamically select a subset of models from the plurality of models. The system dynamically selects a subset of available system resources to process the input included in the output generation request. The system generates the output by processing the input included in the output generation request using the selected subset of available system resources.

Dynamic system resource-sensitive model software and hardware selection

The systems and methods disclosed herein generate context-aware responses using semantically chunked information. The systems and methods disclosed herein partition a set of artifacts responsive to a query (e.g., a prompt for an artificial intelligence model such as a large language model) into a set of continuous chunks and associate each continuous chunk with a knowledge graph. The knowledge graph includes nodes representing chunks and edges indicating common attributes. The systems and methods disclosed herein modify node(s) in the graph by determining values of feature variables and adjusting edges in accordance with the values and generate contextualized chunks by associating or linking continuous chunks of node pairs using shared edges. The systems and methods disclosed herein use the contextualized chunks and query to generate a response using the artificial intelligence model.

Context-aware semantic chunking for information retrieval in large language models

Growing community of inventors

London, United Kingdom

Jason Ryan Engelbrecht