# US 2026/0064660 A1 · Automatically and intelligently creating journal entries to solve mismatches identified via the intercompany elimination reporting process

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

- Number: US 2026/0064660 A1
- Document ID: US20260064660A1
- Status: Published application
- Kind: A1
- Application number: 19/170,294
- Filed: 2025-04-04
- Published: 2026-03-05
- Earliest claimed: 2024-09-05
- Assignees: Oracle International Corporation
- Applicants: Oracle International Corporation
- Inventors: Pradeep Bansal; Margaret Reed; Sunil Sahu; John D. Clark, JR.; Varghese Mathew; Thomas Lefebvre; Tim Gaumont
- Web page: https://patentgrep.com/patent/US20260064660A1

## CPC

- G06F 16/2365: {Ensuring data consistency and integrity}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Systems, methods, and computer-readable media are provided for automatically and intelligently creating journal entries, such as journal entries to solve mismatches identified via the intercompany elimination reporting process. In an example, a machine learning model is trained to generate journal entries such as journal entries based on certain characteristics of historical journal entries associated with historical discrepancies. The trained machine learning model may be used, for example, to automatically generate a journal entry by recording a ledger acknowledging a discrepancy between a first data entry of a first entity and a second data entry of a second entity. The journal entry automatically generated using the machine learning model may reconcile the discrepancy, for example, by recording the ledger in alignment with the first data entry of the first entity or in alignment with the second data entry of the second entity.

## Claims

### Claim 1

A computer-implemented method comprising:
training a machine learning model to generate journal entries that reconcile discrepancies based at least in part on certain characteristics of historical journal entries associated with historical discrepancies;
accessing a first data structure from a first source comprising a first plurality of data entries against one or more first entities and one or more second entities; wherein the first data structure and the first source are associated with the one or more first entities;
accessing a second data structure from a second source comprising a second plurality of data entries against one or more third entities and one or more fourth entities; wherein the second data structure and the second source are associated with the one or more third entities;
automatically detecting, based at least in part on one or more first characteristics of one or more first data entries of the first plurality of data entries and one or more second characteristics of one or more second data entries of the second plurality of data entries, a first discrepancy between the one or more first data entries and the one or more second data entries and a second discrepancy between one or more other first data entries of the first plurality of data entries and one or more other second data entries of the second plurality of data entries;
receiving a selection of a first option to analyze discrepancies between the first plurality of data entries and the second plurality of data entries;
in response to the selection of the first option to analyze the discrepancies and without selection of individual discrepancies, using the machine learning model to automatically generate a first journal entry that reconciles the first discrepancy by recording a first ledger acknowledging, to the one or more first entities, the first discrepancy in alignment with the one or more second data entries, and automatically cause displaying of a second option to confirm generation of the first journal entry and a third option to roll back generation of the first journal entry;
automatically generating a second journal entry that reconciles the second discrepancy by recording a second ledger acknowledging the second discrepancy in alignment with the one or more other first data entries;
wherein selection of the third option is operable to cause deletion of the first journal entry as if the first journal entry never existed in the first data structure;
in response to a selection of the second option to confirm generation of the first journal entry, automatically persisting the first journal entry in the first data structure.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, wherein the one or more third entities are the one or more second entities, and wherein the one or more fourth entities are the one or more first entities.

### Claim 3 (depends on 1)

The computer-implemented method of claim 1, wherein the one or more third entities are the one or more second entities, and wherein the one or more fourth entities are different than the one or more first entities and the one or more second entities.

### Claim 4 (depends on 1)

The computer-implemented method of claim 1, wherein the one or more first entities comprise a plurality of first entities having a same parent entity, and wherein the first data structure is maintained for the parent entity.

### Claim 5 (depends on 1)

The computer-implemented method of claim 1, wherein the automatically generating the second journal entry is by using the machine learning model.

### Claim 6 (depends on 1)

The computer-implemented method of claim 1, wherein the training the machine learning model comprises training the machine learning model to learn relationships between journal entries associated with adjacent reporting periods.

### Claim 7 (depends on 1)

The computer-implemented method of claim 1, wherein the training the machine learning model is further based on currency exchange rates at historical times associated with the historical journal entries.

### Claim 8 (depends on 1)

The computer-implemented method of claim 1, wherein the certain characteristics of the historical journal entries include a characteristic that indicates whether a respective historical journal entry was accepted or rejected.

### Claim 9 (depends on 1)

The computer-implemented method of claim 1, wherein the certain characteristics of the historical journal entries include a characteristic that indicates an extent to which a respective historical journal entry is modified prior to being persisted in the first data structure or the second data structure.

### Claim 10 (depends on 1)

The computer-implemented method of claim 1, wherein the certain characteristics of the historical journal entries include a characteristic that indicates a seasonality of the historical journal entries.

### Claim 11

A computer-program product comprising one or more non-transitory machine-readable storage media, including stored instructions configured to cause a computing system to perform a set of actions including:
training a machine learning model to generate journal entries that reconcile discrepancies based at least in part on certain characteristics of historical journal entries associated with historical discrepancies;
accessing a first data structure from a first source comprising a first plurality of data entries against one or more first entities and one or more second entities; wherein the first data structure and the first source are associated with the one or more first entities;
accessing a second data structure from a second source comprising a second plurality of data entries against one or more third entities and one or more fourth entities; wherein the second data structure and the second source are associated with the one or more third entities;
automatically detecting, based at least in part on one or more first characteristics of one or more first data entries of the first plurality of data entries and one or more second characteristics of one or more second data entries of the second plurality of data entries, a first discrepancy between the one or more first data entries and the one or more second data entries and a second discrepancy between one or more other first data entries of the first plurality of data entries and one or more other second data entries of the second plurality of data entries;
receiving a selection of a first option to analyze discrepancies between the first plurality of data entries and the second plurality of data entries;
in response to the selection of the first option to analyze the discrepancies and without selection of individual discrepancies, using the machine learning model to automatically generate a first journal entry that reconciles the first discrepancy by recording a first ledger acknowledging, to the one or more first entities, the first discrepancy in alignment with the one or more second data entries, and automatically cause displaying of a second option to confirm generation of the first journal entry and a third option to roll back generation of the first journal entry;
automatically generating a second journal entry that reconciles the second discrepancy by recording a second ledger acknowledging the second discrepancy in alignment with the one or more other first data entries;
wherein selection of the third option is operable to cause deletion of the first journal entry as if the first journal entry never existed in the first data structure;
in response to a selection of the second option to confirm generation of the first journal entry, automatically persisting the first journal entry in the first data structure.

### Claim 12 (depends on 11)

The computer-program product of claim 11, wherein the one or more third entities are the one or more second entities, and wherein the one or more fourth entities are the one or more first entities.

### Claim 13 (depends on 11)

The computer-program product of claim 11, wherein the one or more third entities are the one or more second entities, and wherein the one or more fourth entities are different than the one or more first entities and the one or more second entities.

### Claim 14 (depends on 11)

The computer-program product of claim 11, wherein the one or more first entities comprise a plurality of first entities having a same parent entity, and wherein the first data structure is maintained for the parent entity.

### Claim 15 (depends on 11)

The computer-program product of claim 11, wherein the automatically generating the second journal entry is by using the machine learning model.

### Claim 16

A system comprising:
one or more processors;
one or more non-transitory computer-readable media storing instructions, which, when executed by the system, cause the system to perform a set of actions including:
training a machine learning model to generate journal entries that reconcile discrepancies based at least in part on certain characteristics of historical journal entries associated with historical discrepancies;
accessing a first data structure from a first source comprising a first plurality of data entries against one or more first entities and one or more second entities; wherein the first data structure and the first source are associated with the one or more first entities;
accessing a second data structure from a second source comprising a second plurality of data entries against one or more third entities and one or more fourth entities; wherein the second data structure and the second source are associated with the one or more third entities;
automatically detect, based at least in part on one or more first characteristics of one or more first data entries of the first plurality of data entries and one or more second characteristics of one or more second data entries of the second plurality of data entries, a first discrepancy between the one or more first data entries and the one or more second data entries and a second discrepancy between one or more other first data entries of the first plurality of data entries and one or more other second data entries of the second plurality of data entries;
receiving a selection of a first option to analyze discrepancies between the first plurality of data entries and the second plurality of data entries;
in response to the selection of the first option to analyze the discrepancies and without selection of individual discrepancies, using the machine learning model to automatically generate a first journal entry that reconciles the first discrepancy by recording a first ledger acknowledging, to the one or more first entities, the first discrepancy in alignment with the one or more second data entries, and automatically cause displaying of a second option to confirm generation of the first journal entry and a third option to roll back generation of the first journal entry;
automatically generating a second journal entry that reconciles the second discrepancy by recording a second ledger acknowledging the second discrepancy in alignment with the one or more other first data entries;
wherein selection of the third option is operable to cause deletion of the first journal entry as if the first journal entry never existed in the first data structure;
in response to a selection of the second option to confirm generation of the first journal entry, automatically persisting the first journal entry in the first data structure.

### Claim 17 (depends on 16)

The system of claim 16, wherein the training the machine learning model is further based on currency exchange rates at historical times associated with the historical journal entries.

### Claim 18 (depends on 16)

The system of claim 16, wherein the certain characteristics of the historical journal entries include a characteristic that indicates whether a respective historical journal entry was accepted or rejected.

### Claim 19 (depends on 16)

The system of claim 16, wherein the certain characteristics of the historical journal entries include a characteristic that indicates an extent to which a respective historical journal entry is modified prior to being persisted in the first data structure or the second data structure.

### Claim 20 (depends on 16)

The system of claim 16, wherein the certain characteristics of the historical journal entries include a characteristic that indicates a seasonality of the historical journal entries.
