JPMorgan Chase

Abstract A method and a system for determining similarities between entities are provided. The method includes: receiving a request to determine an estimate for a first instrument; generating a query to identify corresponding first data sources that contain data about an entity; identifying, using the generated query, the corresponding first data sources from a system of computer networks; filtering the corresponding first data sources in order to determine at least one primary data source; extracting corresponding first information that relates to the respective entity from the at least one primary data source; identifying, using a large language model, corresponding entity-specific information based on the extracted corresponding first information; comparing the entity-specific information of a first entity with entity-specific information for a plurality of entities; and generating a similarity ranking that list each respective entity from among the plurality of entities in relation to the first entity.

Abstract Methods and systems for performing a combinatorial optimization task are provided. The method includes: receiving a first set of data items and discretizing each of the first set of data items in order to generate a first discretized set of data items; receiving a second set of data items and discretizing each of the second set of data items in order to generate a second discretized set of data items; reorganizing the first and second discretized sets of data items into two respective groups of positive integers; using the two groups of positive integers to generate two respective tables for storing a feasibility of obtaining at least one subset sum from among the elements of the first and second discretized sets of data items; and performing a subset sum matching procedure upon the two tables in order to identify the at least one subset sum.

Abstract In some aspects, the techniques described herein relate to a method including: receiving, by a capture module, a reception notification from an email server, wherein the reception notification is triggered by an event handler of the email server and the event handler is configured to generate the reception notification upon receipt of an email in a mailbox of the email server; generating, by the capture module, a reception event including metadata related to the email that is received at the mailbox of the email server; sending, by the capture module, the reception event to an event streaming platform; retrieving, by a workflow engine, email metadata, wherein the email metadata is related to the email that is received at the mailbox of the email server; and providing, by the workflow engine and as input to a rules-based procedure, the email metadata.

Abstract A method of selecting accessibility plugins for disabled users is disclosed. In one example, the method includes determining accessibility requirements of a user to access a website. The method then selects, without user intervention, one of many accessibility plugins to satisfy the accessibility requirements of the user to access the website. Here, each one of the accessibility plugins has an accessibility requirement different from that of another accessibility plugin. The method then installs, without user intervention, the selected accessibility plugin to facilitate use of the website by the user.

Abstract Various methods and processes, apparatuses or systems, and media for using generative AI models to automatically generate responses to customer requests in an efficient and accurate manner are disclosed. The method includes: receiving a query from a user; analyzing the query to determine a topic that is relevant to the query; publishing the query to a topic queue that corresponds to the determined topic; identifying a generative artificial intelligence (AI) model that is trained by using data that corresponds to the determined topic; submitting the query to the generative AI model; receiving an answer to the first query from the generative AI model; storing the received answer to the query in a semantic memory; and transmitting the answer to the user.

Abstract Systems and methods for enhanced payment codes are disclosed. According to one embodiment, a method for presenting a machine-readable code to a transaction terminal may include (1) a computer payment application executed by a computer processor of a mobile electronic device displaying an image of a first payment device on a display; (2) the computer payment application receiving a signal from a sensor in the mobile electronic device indicating that the display is being presented to a transaction terminal; (3) the computer application requesting a machine readable code from a provider of machine-readable codes for the first payment device; (4) the computer application receiving the machine readable code for the first payment device; and (5) the computer application displaying the machine readable code on the display.

Abstract Systems and methods for prefetching Payment Card Industry (PCI) data. A method may include a tokenization service in a cloud environment: (1) receiving a request to prefetch a plurality of tokens from a client application; (2) generating the plurality of tokens and a co-relation indicator for each of the plurality of tokens; (3) storing the plurality of tokens and the co-relation indicators in a token vault in the cloud environment; (4) returning the plurality of tokens and the co-relation indicators to the client electronic device; (5) receiving a mapping request comprising a source value and the co-relation indicator for one of the plurality of tokens; (6) identifying the token of the plurality of tokens associated with the co-relation indicator; (7) mapping the token to the source value; and (8) returning a message indicating successful mapping to the client application.

Abstract A method and a system for dynamic request for quotation (RFQ) pricing using proportional-integral-derivative (PID) control with Bayesian optimization in order to determine an optimal linear state-feedback controller for tracking a metric are provided. The method includes: receiving bid price information and ask price information that relates to a financial instrument; selecting a metric to be used in conjunction with a determination of an RFQ price with respect to the financial instrument; estimating an output of a PID controller based on a predetermined function of the metric; adjusting the estimate by using a Bayesian optimization process; and using the PID controller, the adjusted estimate, the bid price information, and the ask price information to determine the RFQ price.