Jpmorgan Chase Bank, N.a.

Zhen Zeng

Tucker Richard Balch

Maria Manuela Veloso

Manuela Veloso

Naftali Y Cohen

William Watson

Naan Cho

Sameena Shah

Salwa Husam Alamir

Daniel Borrajo

Natraj Raman

Keshav Ramani

Srijan Sood

Alec Louis Clemente Candidato

Saba Rahimi

Matthew Brian MacKay

A method for using a large language model to generate executable code for workflow execution in a manner that integrates user feedback and adjusts the workflow as needed while preserving data privacy is provided. The method includes: receiving first information that relates to a workflow context, second information that relates to at least one application programming interface (API), and third information that relates to a code generation request; using the received information to generate a lecture, and transmitting the lecture to a language model; receiving a user query that relates to performing a task, and transmitting the query to the language model; receiving a workflow that is automatically generated by the language model based on the lecture and the query; and executing the workflow in order to generate an output that is responsive to the query.

Method and system for automatic workflow generation by large language models

A method for forecasting a change in a market is provided. The method includes: using historical market data to generate a plurality of first images that correspond to a predetermined time sequence; generating, based on the plurality of first images, second images that correspond to a future time point with respect to the predetermined time sequence; and determining a prediction of future market data based on the second images. The generation of the second images and the prediction of the future market data are implemented by applying a convolutional neural network (CNN) algorithm that implements a stochastic latent residual video prediction (SRVP) technique with respect to a group of financial assets.

Method and system for using deep video prediction for economic forecasting

A method for providing a domain-specific language model to facilitate natural language data analytics is disclosed. The method includes aggregating documents from various sources, each of the documents including natural language data; ingesting each of the documents to generate structured data sets that are organized according to a contextual hierarchy; determining prompts that provide domain-specific information for a language model, the domain-specific information including instructions to access the structured data sets; receiving a request via a graphical user interface, the request relating to questions in a natural language format; generating, by using the language model, software codes for the request based on the prompts; and executing each of the software codes to identify results for the request from the structured data sets.

Method and system for analyzing natural language data by using domain-specific language models

A method and system for detecting, segmenting, and extracting salient regions in documents by using attention tracking sensors is provided. The method includes: receiving an image that corresponds to a document; receiving, from a sensor, a sequence of measurements that correspond to a human reading of the document; determining, based on the sequence of measurements, at least one region of the document as being a salient document region; demarcating the salient document region in an electronically displayable manner; and outputting a file that includes a displayable version of the document with the demarcated document region. The salient document region may include a title, a section header, and/or a table. The sensor may be an eye-tracking sensor that detects a sequence of eye-gaze positions on the document as a function of time.

Method of detecting, segmenting and extracting salient regions in documents using attention tracking sensors

A method for using images that represent time-series data to forecast future images depicting future values as pixelated information is provided. The method includes: receiving a first set of time-series data; converting the received first set of time-series data into a first image; and using the first image to forecast a future image depicting future values as pixelated information that corresponds to a future time interval Training sets of time-series data are used to generate historical data that provides input to a machine learning algorithm, which provides, as an output, a composite image that depicts the future values as pixelated information that reflects associated uncertainties in the value predictions.

Method for automatically identifying signals or patterns in time series data by treating series as image

Growing community of inventors

Ypsilanti, MI, United States of America

Zhen Zeng