US 2020/0027162 A1Published application

Crypto-Machine Learning Enabled Blockchain Based Profile Pricer

AssigneeBank of America Corporation

InventorsAwadhesh Pratap Singh, Vinay Laxmikant Bade

Life of this patent

Estimating the term…

Loading patent…

Abstract

Methods and systems for a crypto-machine learning enabled blockchain based profile pricer are described herein. In one example, computer-readable instructions are stored in memory, and one or more processors execute the instructions to determine requested information for a user that can be displayed on a user interface in real-time or near real-time of the user's request. In addition, the provided data can be customized for the user based on a user profile stored in the memory as well as based on third party data stored in a database of related information. The data is communicated to the user using blockchains. At least some advantages of such an arrangement are providing requested data to a user, for display on a user interface, in a transparent, secure, and timely manner.

Claims20

Dependent claims

A cryptography machine learning enabled blockchain based apparatus, the apparatus comprising:

one or more interfaces for communications with a plurality of users and a plurality of blockchain nodes;
one or more processors configured to execute computer-executable instructions;
and
memory storing the computer-executable instructions that, when executed by the one or more processors, cause the apparatus to:
identify, based on third party data received via a network, a user profile of a plurality of user profiles;
receive, via the one or more interfaces, and from a first computing device, a request for a new datum;
determine whether a prior request for a prior datum was accepted by a first user of a plurality of users;
determine, based on an indication that the prior request was accepted by the first user and based on the prior datum, the new datum;
determine, based on an indication that the prior request was not accepted by the first user and based on the prior datum and at least a portion of the third party data, the new datum;
communicate, via a permissioned blockchain distributed ledger accessible via a private key, and to the plurality of blockchain nodes, an indication of the new datum, wherein a duration between determination of the prior datum and the new datum is displayed, on a user interface of the first computing device, in real-time or near real-time with the request;
monitor, by a monitoring engine, communications to and from the plurality of blockchain nodes to determine a level of control associated with each user of the plurality of users;
compare, by the monitoring engine, the level of control associated with each user of the plurality of users to a first threshold;
and
switch communications, based on an indication that the level of control for the first user or a second user of the plurality of users satisfies the first threshold, from using blockchain communications to using multi-lateral private messages.

11 more elements

A method for generating a real-time or near real-time quote for an exchange of foreign currency comprising:

receiving, by a machine learning profile pricing server, third party data corresponding to exchange of a plurality of foreign currencies;
determining, by one or more processors and using the third party data, a plurality of user profiles, wherein a first user profile of the plurality of user profiles is associated with a first user that is a party to at least one smart contract associated with an exchange of foreign currency;
receiving, from a plurality of computing devices, a plurality of requests for quotations for an exchange of foreign currency, wherein the requests comprises an indication of a buy currency and an indication of a sell currency;
generating the quotes using the machine learning profile pricing server, wherein each quote comprises a proposed spread corresponding to each of the plurality of requests generated by:
determining a user spread for one or more exchanges of the buy currency and the sell currency by the user;
performing a regression analysis to calculate:
an intercept constant;
and
one or more coefficients for:
an indication of market conditions;
an indication of liquidity;
and
the first user spread;
summing results from the regression analysis;
and
transmitting, via a permissioned blockchain distributed ledger accessible via a private key, and to a plurality of blockchain nodes, an indication of each quote of a plurality of quotations, wherein for each of the plurality of quotations, a time duration between receiving third party data and generating a quotation is provided for display on a user interface of a requesting computing device, in real-time or near real-time with each request;
and.
monitoring, by a monitoring engine, communications to and from the plurality of blockchain nodes to determine a level of control associated with each user of the plurality of users;
comparing, by the monitoring engine, the level of control associated with each user of the plurality of users to a first threshold;
and
switching a communication method, based on an indication that the level of control for the first user or a second user of the plurality of users satisfies the first threshold, from using blockchain communications to using multi-lateral private messages.

18 more elements

A cryptography machine learning enabled blockchain based apparatus, the apparatus comprising:

one or more interfaces for communications with a plurality of users and a plurality of blockchain nodes;
one or more processors configured to execute computer-executable instructions;
and
memory storing the computer-executable instructions that, when executed by the one or more processors, cause the apparatus to:
receive, by a machine learning profile pricing server, third party data corresponding to exchange of a plurality of foreign currencies;
determine, by one or more processors and using the third party data, a plurality of user profiles, wherein a first user profile of the plurality of user profiles is associated with a first user that is a party to at least one smart contract associated with an exchange of foreign currency;
receive, from a plurality of computing devices, a plurality of requests for quotations for an exchange of foreign currency, wherein the requests comprises an indication of a buy currency and an indication of a sell currency;
generate the quotes using the machine learning profile pricing server, wherein each quote comprises a proposed spread corresponding to each of the plurality of requests generated by:
determine a user spread for one or more exchanges of the buy currency and the sell currency by the user;
perform a regression analysis to calculate:
an intercept constant;
and
one or more coefficients for:
an indication of market conditions;
an indication of liquidity;
and
the first user spread;
sum results from the regression analysis;
and
transmit, via a permissioned blockchain distributed ledger accessible via a private key, and to a plurality of blockchain nodes, an indication of each quote of a plurality of quotations, wherein for each of the plurality of quotations, a time duration between receiving third party data and generating a quotation is provided for display on a user interface of a requesting computing device, in real-time or near real-time with each request;
and.
monitor, by a monitoring engine, communications to and from the plurality of blockchain nodes to determine a level of control associated with each user of the plurality of users;
compare, by the monitoring engine, the level of control associated with each user of the plurality of users to a first threshold;
and
switch communications, based on an indication that the level of control for the first user or a second user of the plurality of users satisfies the first threshold, from using blockchain communications to using multi-lateral private messages.

22 more elements

Dependencies are inferred from the claim text.

Facts

Application: 16/586,030Filed 27 Sep 2019
Priority: 13 Nov 2017
Published: 23 Jan 2020
Term ends: Not estimatedThe source records don’t support an estimate.

Classification12 codes

G06Q 40/04
Finance; Insurance; Tax strategies; Processing of corporate or income taxes: trading; Exchange, e.g. stocks, commodities, derivatives or currency…
H04L 9/3239
Using cryptographic hash functions: involving non-keyed hash functions, e.g. modification detection codes [MDCs], MD5, SHA or RIPEMD
H04L 9/50
Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols: using hash chains, e.g.…
G06N 20/00
Machine learning

Family

Application15/811,108Continuation · filed 13 Nov 2017
Application16/586,030Continuation
US 10,977,730 B2Related patent
US 11,042,934 B2Related patent
US 11,244,396 B2Related patent
US 2019/0147532 A1Published application
US 2020/0027162 A1This patent

From the US filing history. Foreign family members aren’t listed.