# US 2026/0073447 A1 · Data retrieval and validation for private credit asset onboarding

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0073447 A1
- Document ID: US20260073447A1
- Status: Published application
- Kind: A1
- Application number: 19/389,856
- Filed: 2025-11-14
- Published: 2026-03-12
- Earliest claimed: 2023-03-24
- Assignees: TRETE Inc.
- Applicants: TRETE Inc.
- Inventors: Damien Patton; Christian Gratton
- Web page: https://patentgrep.com/patent/US20260073447A1

## CPC

- G06Q 40/04: Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
- G06F 16/215: Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
- G06F 16/2358: {Change logging, detection, and notification (replication G06F16/27)}
- G06F 16/2379: {Updates performed during online database operations; commit processing}
- G06F 16/275: {Synchronous replication}
- G06Q 20/02: involving a neutral party, e.g. certification authority, notary or trusted third party [TTP]
- G06Q 20/065: {using e-cash}
- G06Q 20/363: {with the personal data of a user}
- G06Q 20/3674: {involving authentication}
- G06Q 20/381: {Currency conversion}
- G06Q 20/3829: {involving key management}
- G06Q 20/389: {Keeping log of transactions for guaranteeing non-repudiation of a transaction}
- G06Q 20/401: {Transaction verification}
- G06Q 20/42: Confirmation, e.g. check or permission by the legal debtor of payment
- G06Q 30/0613: {using intermediate agents}
- G06Q 40/06: Asset management; Financial planning or analysis
- H04L 9/3239: {involving non-keyed hash functions, e.g. modification detection codes [MDCs], MD5, SHA or RIPEMD}
- H04L 9/50: {using hash chains, e.g. blockchains or hash trees}
- H04L 67/1097: for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
- G06F 16/2365: {Ensuring data consistency and integrity}
- G06F 16/27: Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
- G06Q 2220/00: Business processing using cryptography
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

In certain aspects of the disclosure, a computer-implemented method includes collecting, via an artificial intelligence module, a first set of data associated with a private credit asset and creating identifiers associated with the first set of data. The method includes collecting a second set of data associated with the private credit asset based on the identifiers and comparing the first set of data and the second set of data based on the identifiers. The method includes determining validation of the first set of data based on the comparison and generating a result of approval or rejection based on the comparison.

## Claims

### Claim 1

A computer-implemented method comprising:
electronically collecting a first data set, purportedly defining characteristics of a private credit asset, into a database;
accessing unique identifiers corresponding to each of one or more items within the first data set;
formulating an object containing the one or more items;
assigning an additional unique identifier to the private credit asset;
creating a job on a queue containing the additional unique identifier and the object; and
pinging an artificial intelligence module there is an object in the queue;
automatically and subsequent to accessing the unique identifiers, utilizing the artificial intelligence module validating relevancy of the one or more items to the private credit asset, including:
sending out an asynchronous search for matches on the one or more items contained in the object electronically collecting a second data set into the database using the unique identifiers, the second data set considered as corresponding to the private credit asset based on the unique identifiers;
cross-referencing the first data set with the second data set; and
confirming relevancy of the one or more items to the private credit asset based on results of the cross-referencing;
listing the private credit asset at a financial exchange; and
automatically, as part of a constant training cycle, training the artificial intelligence module based on confirming the relevancy of the one or more items improving data validating performance of the artificial intelligence module.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
receiving user permission permitting a third-party system to provide the first data set; and
deploying an extraction model into the third-party system; and
wherein electronically collecting a first data set comprises utilizing the extraction model pushing the first data set from the third-party system into the database.

### Claim 3 (depends on 1)

The method of claim 1, wherein electronically collecting a second data set into the database comprises:
pulling a part of the second data set from a public data source into the database; and
pulling another part of the second data set from a non-public data source into a database;
wherein cross-referencing the first data set with the second data set comprises cross-referencing the first data set with the part of the second data set and cross-referencing the first data set with the other part of second data; and
wherein confirming relevancy of the one or more items comprises confirming the veracity of the one or more items.

### Claim 4 (depends on 1)

The method of claim 1, wherein confirming relevancy of the one or more items to the private credit asset comprises a model:
scoring the cross-referencing by generating a confidence score representing a probability the second data set is a fit for the first data set; and
determining the confidence score satisfies a control threshold.

### Claim 5 (depends on 1)

The method of claim 1, wherein the artificial intelligence module sending out an asynchronous search for matches comprises the artificial intelligence module sending out an asynchronous search across multiple search engines; and
further comprising utilizing pattern matching on returned links determining authoritativeness of corresponding data sources utilized to collect the second data set.

### Claim 6 (depends on 1)

The method of claim 1, further comprising electronically collecting a third data set into the database, the third data set collected from a different data source than the second data set; and
wherein cross-referencing the first data set with the second data set comprises cross-referencing the first data set with the second data set and the third data set.

### Claim 7 (depends on 1)

The method of claim 1, further comprising verifying quality of the first data set and the second data set prior to cross-referencing the first data set with the second data set.

### Claim 8

A system comprising:
a processor;
system memory coupled to the processor and storing instructions configured to cause the processor to:
electronically collect a first data set, purportedly defining characteristics of a private credit asset, into a database;
access unique identifiers corresponding to each of one or more items within the first data set;
formulate an object containing the one or more items;
assign an additional unique identifier to the private credit asset;
create a job on a queue containing the additional unique identifier and the object; and
ping an artificial intelligence module there is an object in the queue;
automatically and subsequent to accessing the unique identifiers, utilize the artificial intelligence module validating relevancy of the one or more items to the private credit asset, including:
send out an asynchronous search for matches on the one or more items contained in the object electronically collecting a second data set into the database using the unique identifiers, the second data set considered as corresponding to the private credit asset based on the unique identifiers;
cross-reference the first data set with the second data set; and
confirm relevancy of the one or more items to the private credit asset based on results of the cross-referencing;
list the private credit asset at a financial exchange; and
automatically, as part of a constant training cycle, train the artificial intelligence module based on confirming the relevancy of the one or more items improving data validating performance of the artificial intelligence module.

### Claim 9 (depends on 8)

The system of claim 8, further comprising instructions configured to cause the processor to:
receiving user permission permitting a third-party system to provide the first data set; and
deploying an extraction model into the third-party system; and
wherein electronically collecting a first data set comprises utilizing the extraction model pushing the first data set from the third-party system into the database.

### Claim 10 (depends on 8)

The system of claim 8, wherein instructions configured to cause the processor to electronically collect a second data set into the database comprise instructions configured to cause the processor to:
pull a part of the second data set from a public data source into the database; and
pull another part of the second data set from a non-public data source into a database;
wherein instructions configured to cause the processor to cross-reference the first data set with the second data set comprise instructions configured to cause the processor to cross-reference the first data set with the part of the second data set and cross-reference the first data set with the other part of second data;
wherein instructions configured to cause the processor to confirm relevancy of the one or more items comprise instructions configured to cause the processor to confirm the veracity of the one or more items.

### Claim 11 (depends on 8)

The system of claim 8, wherein instructions configured to cause the processor to confirm relevancy of the one or more items to the private credit asset comprise instructions for a model configured to cause the processor to:
score the cross-referencing by generating a confidence score representing a probability the second data set is a fit for the first data set; and
determine the confidence score satisfies a control threshold.

### Claim 12 (depends on 8)

The system of claim 8, wherein instructions configured to cause the processor to cause the artificial intelligence module to send out an asynchronous search for matches comprises the instructions configured to cause the processor to cause the artificial intelligence module to send out an asynchronous search across multiple search engines; and
further comprising instructions configured to cause the processor to utilize pattern matching on returned links determining authoritativeness of corresponding data sources utilized to collect the second data set.

### Claim 13 (depends on 8)

The system of claim 8, further comprising instructions configured to cause the processor to electronically collect a pulled third data set into the database, the third data set collected from a different data source than the second data set; and
wherein instructions configured to cause the processor to cross-reference the first data set with the second data set comprise instructions configured to cause the processor to cross-reference the first data set with the second data set and the third data set.

### Claim 14 (depends on 8)

The system of claim 8, further comprising instructions configured to cause the processor to verify quality of the first data set and the second data set prior to cross-referencing the first data set with the second data set.
