# US 2026/0290062 A1 · Information processing apparatus, information processing method, and non-transitory recording medium

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

- Number: US 2026/0290062 A1
- Document ID: US20260290062A1
- Status: Published application
- Kind: A1
- Application number: 19/566,133
- Filed: 2026-03-13
- Published: 2026-09-24
- Earliest claimed: 2025-03-18
- Assignees: Ricoh Company, Ltd.
- Inventors: Ryo Iwasaki
- Web page: https://patentgrep.com/patent/US20260290062A1

## CPC

- G06V 30/412: Layout analysis of documents structured with printed lines or input boxes, e.g. business forms or tables
- G06F 40/40: Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30)
- G06V 10/764: using classification, e.g. of video objects
- G06V 10/82: using neural networks
- G06V 30/10: Character recognition
- G06V 30/19: Recognition using electronic means
- G06V 30/26: Techniques for post-processing, e.g. correcting the recognition result
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

An information processing apparatus includes circuitry to extract a value of an item from a past form image which is an image of a same form as a form image to be analyzed; store, in a memory, extraction results and information related to a correction to the value of the item extracted from the past form image; determine, based on the information related to the correction, an item for which a large language model is used to extract a value among items included in the form image to be analyzed; extract a value of the determined item from the form image to be analyzed by using the large language model; and register, in the memory, the value extracted using the large language model from the form image to be analyzed.

## Claims

### Claim 1

An information processing apparatus comprising
circuitry configured to:
extract a value of an item from a past form image, the past form image being an image of a same form as a form image to be analyzed;
store, in a memory, extraction results and information related to a correction to the value of the item extracted from the past form image;
determine, based on the information related to the correction, an item for which a large language model is used to extract a value among items included in the form image to be analyzed;
extract a value of the determined item from the form image to be analyzed by using the large language model; and
register, in the memory, the value extracted using the large language model from the form image to be analyzed.

### Claim 2 (depends on 1)

The information processing apparatus according to claim 1, wherein the circuitry is further configured to:
receive a correction of the value of the item extracted from the past form image; and
determine, as the item for which the large language model is used, the item for which the correction is received.

### Claim 3 (depends on 2)

The information processing apparatus according to claim 2, wherein the circuitry is further configured to:
recognize characters from the past form image; and
output an instruction to the large language model to extract the value of the determined item from a first recognition result obtained by recognizing the form image to be analyzed, the instruction including a second recognition result obtained by character recognition of the past form image, and a corrected value of the item for which the correction is received among values of the items extracted from the second recognition result.

### Claim 4 (depends on 2)

The information processing apparatus according to claim 2,
wherein the circuitry is configured to:
extract the values of the item from the past form image and the form image to be analyzed, based on form definition information that defines positional relationships between the item and the value of the item;
extract the value of the item from the past form image and the form image to be analyzed, based on training data including the correction; and
determine, as the item for which the large language model is used, the item that is extracted based on the training data and has the value for which the correction is received.

### Claim 5 (depends on 1)

The information processing apparatus according to claim 1,
wherein the circuitry is configured to output an instruction to the large language model to classify the form image to be analyzed to cause the large language model to determine a type of the form image to be analyzed.

### Claim 6 (depends on 1)

The information processing apparatus according to claim 1, wherein
the form image to be analyzed includes a plurality of form images, and
the circuitry is configured to output, to the large language model, an instruction to divide form image data representing the plurality of form images into individual form image data.

### Claim 7 (depends on 1)

The information processing apparatus according to claim 1, wherein the form image to be analyzed and the past form image are of the same form.

### Claim 8 (depends on 1)

The information processing apparatus according to claim 1, wherein the circuitry is further configured to output data for causing a display device to display a screen including the form image to be analyzed and the value of the item extracted from the form image to be analyzed.

### Claim 9

An information processing method comprising:
extracting a value of an item from a past form image, the past form image being an image of a same form as a form image to be analyzed;
storing, in a memory, extraction results and information related to a correction to the value of the item extracted from the past form image;
determining, based on the information related to the correction, an item for which a large language model is used to extract a value among items included in the form image to be analyzed;
extracting a value of the determined item from the form image to be analyzed by using the large language model; and
registering, in the memory, the value extracted using the large language model from the form image to be analyzed.

### Claim 10

A non-transitory recording medium storing a plurality of program codes which, when executed by one or more processors, causes the one or more processors to perform a method, the method comprising:
extracting a value of an item from a past form image, the past form image being an image of a same form as a form image to be analyzed;
storing, in a memory, extraction results and information related to a correction to the value of the item extracted from the past form image;
determining, based on the information related to the correction, an item for which a large language model is used to extract a value among items included in the form image to be analyzed;
extracting a value of the determined item from the form image to be analyzed by using the large language model; and
registering, in the memory, the value extracted using the large language model from the form image to be analyzed.
