Generating parameterized record from electronic messages

Patent metadata

Field	Value
Publication number	US-12182766-B2
Application number	US-202318325965-A
Country	US
Kind code	B2
Filing date	May 30, 2023
Priority date	May 30, 2023
Publication date	Dec 31, 2024
Grant date	Dec 31, 2024

Abstract

Methods and systems are described herein for generating parameterized records using communications data. A generation system may be used to facilitate generating the parameterized records. The system may encode a plurality of electronic messages into bag-of-words embeddings and input a plurality of bag-of-words embeddings into a machine learning model to identify electronic messages containing itemized records, each including corresponding item identifiers. The system may transmit a request to identify server records associated with the itemized records, wherein the request comprises the corresponding item identifiers, and wherein the record identification server uses the corresponding item identifiers to identify the itemized records. The system may receive the server records each of which includes corresponding parameters. The system may, in response to determining that the corresponding parameters match sets of a plurality of sets of criteria, generate a parameterized record for the itemized records including the itemized records and corresponding parameter data.

First claim

What is claimed is:

1. A system for generating parameterized records using electronic message data, the system comprising:
one or more processors; and
a non-transitory, computer-readable storage medium storing instructions that when executed by the one or more processors cause the one or more processors to perform operations comprising:
receiving, a plurality of electronic messages associated with a user;
encoding the plurality of electronic messages into a plurality of bag-of-words embeddings;
inputting the plurality of bag-of-words embeddings into a machine learning model to identify one or more electronic messages containing one or more purchase records, wherein the machine learning model is trained to identify bag-of-words embeddings containing one or more purchase records, and wherein each purchase record of the one or more purchase records comprises corresponding purchased item identifiers;
transmitting, to a record identification server, a request to identify one or more server records associated with the one or more purchase records, wherein the request comprises the corresponding item identifiers, wherein the record identification server uses the corresponding item identifiers to identify the one or more server records, and wherein each server record corresponds to a transfer of a purchased item associated with an item identifier;
receiving, from the record identification server, the one or more server records, wherein each server record of the one or more server records comprises corresponding parameters that correspond to a respective purchase record of a respective purchased item;
comparing, for each server record of the one or more server records, the corresponding parameters with a plurality of sets of criteria;
in response to determining that the corresponding parameters match one or more sets of the plurality of sets of criteria, generating a parameterized transaction record for the one or more server records, wherein the parameterized transaction record comprises the one or more purchase records and corresponding parameter data; and
transmitting the parameterized transaction record to a remote server.

2. The system of claim 1 , wherein the instructions cause the one or more processors to perform operations comprising:
receiving, from the remote server, an indication that no server record matches a first purchase record of the one or more purchase records;
transmitting, to a user device, a second request for obtaining item data associated with the first purchase record of the one or more purchase records, wherein the second request comprises a plurality of data fields to be filled in by the user;
receiving, from the user device, the item data associated with the first purchase record of the one or more purchase records; and
based on the item data matching a set of the plurality of sets of criteria, adding the first purchase record and the item data to the parameterized transaction record.

3. A method for generating parameterized records using communications data, the method comprising:
encoding a plurality of electronic messages into a plurality of bag-of-words embeddings;
inputting the plurality of bag-of-words embeddings into a machine learning model to identify one or more electronic messages containing one or more transaction records, wherein the machine learning model is trained to identify bag-of-words embeddings containing one or more transaction records, and wherein each transaction record of the one or more transaction records comprises corresponding item identifiers;
transmitting, to a record identification server, a request to identify one or more server records associated with the one or more transaction records, wherein the request comprises the corresponding item identifiers, and wherein the record identification server uses the corresponding item identifiers to identify the one or more server records;
determining, based on one or more mutable parameters of the one or more server records, a value for a period of time during which a user is allowed to perform an action associated with the one or more server records;
receiving, from the record identification server, the one or more server records, wherein each server record of the one or more server records comprises corresponding parameters that correspond to a respective purchase record of a respective purchased item; and
in response to determining that the corresponding parameters match one or more sets of a plurality of sets of criteria, generating a parameterized transaction record for the one or more transaction records, wherein the parameterized transaction record comprises the one or more transaction records and corresponding parameter data.

4. The method of claim 3 , wherein generating the parameterized transaction record comprises:
retrieving a plurality of parameterized transaction record field identifiers;
retrieving values for a first portion of the plurality of parameterized transaction record field identifiers from the one or more transaction records;
in response to determining that values for a second portion of the plurality of parameterized transaction record field identifiers are not in the one or more transaction records, retrieving values for the second portion of the plurality of parameterized transaction record field identifiers from the one or more server records; and
inserting, into the parameterized transaction record, the values of the first portion and second portion of the plurality of parameterized transaction record field identifiers.

5. The method of claim 3 , further comprising:
receiving, from a remote server, an indication that no record matches a first transaction record of the one or more transaction records; and
transmitting, to a user device, a second request for obtaining item data associated with the first transaction record of the one or more transaction records, wherein the second request comprises a plurality of data fields to be filled in by a user.

6. The method of claim 5 , further comprising:
receiving, from the user device, the item data associated with the first transaction record of the one or more transaction records; and
based on the item data matching a set of the plurality of sets of criteria, adding the first transaction record and the item data to the parameterized transaction record.

7. The method of claim 3 , wherein determining that the corresponding parameters match one or more sets of the plurality of sets of criteria comprises:
selecting a first set of criteria of the plurality of sets of criteria, wherein the first set of criteria comprises a plurality of fields with a plurality of corresponding threshold values for evaluating a record;
determining a first subset of fields having values stored in the one or more transaction records and a second subset of fields having values stored in the one or more server records;
retrieving the values of the first subset of fields from the one or more transaction records and values of the second subset of fields from the one or more server records; and
comparing the values to the plurality of corresponding threshold values to evaluate a record of the one or more transaction records.

8. The method of claim 3 , further comprising:
receiving, from the record identification server, (1) the one or more server records associated with the one or more transaction records and (2) the corresponding parameters associated with the one or more server records;
determining, for each record of the one or more server records, one or more mutable parameters of the corresponding parameters;
generating, based on at least one value of the one or more mutable parameters, a message for a user, wherein the message causes a user device to display a prompt to perfo

Assignees

• Capital One Services Llc

Inventors

• Maiman Tyler
• Wu Jerry
• Yee Bryant

Classifications

• H04L51/21

  Monitoring or handling of messages · CPC title

• G06Q10/107 Primary

  Computer-aided management of electronic mailing [e-mailing] · CPC title