# US 2025/0156426 A1 · Metadata recommendations generation

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

- Number: US 2025/0156426 A1
- Document ID: US20250156426A1
- Status: Published application
- Kind: A1
- Application number: 18/505,768
- Filed: 2023-11-09
- Published: 2025-05-15
- Earliest claimed: 2023-11-09
- Assignees: American Express Travel Related Services Company, Inc.
- Applicants: American Express Travel Related Services Company, Inc.
- Inventors: Ashank GUPTA; Vaibhav GUPTA; Aditya Kumar MISHRA; Vinay DHINGRA; Purvi SHAH; Ritesh SAHA; Sanjeev Kumar YADAV; Anuj GUPTA
- Web page: https://patentgrep.com/patent/US20250156426A1

## CPC

- G06F 16/24578: {using ranking}
- G06F 16/243: {Natural language query formulation}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Disclosed herein are system, method, and computer program product embodiments for generating metadata element recommendations. For example, the method includes acquiring, by at least one processor and via a user interface, metadata associated with a data store. The method also includes performing natural language processing on the metadata to generate processed metadata, generating a candidate table name and a table description associated with the candidate table name for a table included in the metadata, and generating a first candidate attribute name, an attribute description associated with the first candidate attribute name, and a corresponding data type for each attribute associated with the table. The method also includes generating a second candidate attribute name for each attribute by extracting one or more keywords from the first candidate attribute name, and modifying the user interface to include at least the candidate table name.

## Claims

### Claim 1

A computer implemented method, comprising:
acquiring, by at least one processor and via a user interface, metadata associated with a data store;
performing, by the at least one processor, natural language processing on the metadata to generate processed metadata;
generating, by the at least one processor, a candidate table name and a table description associated with the candidate table name for a table included in the metadata based on at least the processed metadata;
generating, by the at least one processor, a first candidate attribute name, an attribute description associated with the first candidate attribute name, and a corresponding data type for each attribute associated with the table;
generating, by the at least one processor, a second candidate attribute name for each attribute by extracting one or more keywords from the first candidate attribute name, wherein the second candidate attribute name corresponds to a technical name; and
modifying, by the at least one processor, the user interface to include the first candidate attribute name, the second candidate attribute name, and the attribute description for each attribute associated with the table.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
identifying personally identifiable information in attributes included in the metadata; and
tagging an attribute corresponding to the identified personally identifiable information.

### Claim 3 (depends on 2)

The method of claim 2, wherein identifying the personally identifiable information comprises:
matching the attribute name with a list of technical attribute names.

### Claim 4 (depends on 1)

The method of claim 1, wherein the candidate table name is a first candidate table name;
and wherein the method further comprises:
generating a second candidate table name based on one or more of a table type, a table description, and the first candidate table name.

### Claim 5 (depends on 4)

The method of claim 4, wherein generating the second candidate table name further comprises:
generating a body of the name for the table by applying a keyword extracting algorithm; and
standardizing the body of the name to generate the second candidate table name by performing one or more operations, wherein the operations include expanding acronyms, checking syllable length, checking character length, and incorporating a uniqueness and inclusion diversity check.

### Claim 6 (depends on 5)

The method of claim 5, wherein applying the keyword extracting algorithm comprises:
assigning a score for each keyword in the metadata; and
determining the additional candidate name by identifying one or more keywords based on the score.

### Claim 7 (depends on 1)

The method of claim 1, wherein the metadata comprises at least an attribute name and an attribute description; and wherein generating the first candidate attribute name for each attribute comprises:
comparing the attribute name with one or more attributes names included in a frequent attribute list; and
in response to determining that there is no match between the attribute name and the one or more attributes, refining the attribute name to generate the first candidate attribute name.

### Claim 8 (depends on 1)

The method of claim 1, further comprising:
converting textual data for an attribute of the metadata into vectors by determining a relevancy score;
determining a similarity score between the vectors and a centroid associated with a data type; and
identifying the data type for the attribute based on the similarity score.

### Claim 9 (depends on 1)

The method of claim 1, further comprising:
providing the user interface for acquiring the metadata from the user;
displaying the acquired metadata; and
receiving one or modifications to the metadata from the user via the user interface.

### Claim 10 (depends on 1)

The method of claim 1, further comprising:
determining a readability score for the candidate name of the table.

### Claim 11 (depends on 1)

The method of claim 1, wherein generating the second candidate attribute name is based on the first candidate attribute name and the attribute description by extracting and ranking one or more keywords from the first candidate attribute name and the attribute description.

### Claim 12

A system, comprising:
a memory; and
at least one processor coupled to the memory and configured to:
acquire, via a user interface, metadata associated with a data store;
perform natural language processing on the metadata to generate processed metadata;
generate a candidate table name and a table description associated with the candidate table name for a table included in the metadata based on at least the processed metadata;
generate a first candidate attribute name, an attribute description associated with the first candidate name, and a corresponding data type for each attribute associated with the table;
generate a second candidate attribute name for each attribute by extracting one or more keywords from the first candidate attribute name, wherein the second candidate attribute name corresponds to a technical name; and
modify the user interface to include the first candidate attribute name, the second attribute candidate name, and the attribute description for each attribute associated with the table.

### Claim 13 (depends on 12)

The system of claim 12, wherein the at least one processor is further configured to:
identify personally identifiable information in attributes included in the metadata; and
tag an attribute corresponding to the identified personally identifiable information.

### Claim 14 (depends on 13)

The system of claim 13, wherein the at least one processor is further configured to:
match the attribute name with a list of technical attribute names.

### Claim 15 (depends on 12)

The system of claim 12, wherein the candidate table name is a first candidate table name;
and wherein the at least one processor is further configured to:
generate a second candidate table name for the table based on one or more of a table type, a table description, and the first candidate table name.

### Claim 16 (depends on 15)

The system of claim 15, wherein the at least one processor is further configured to:
generate a body of the name for the table by applying a keyword extracting algorithm; and
standardize the body of the name to generate the second candidate table name by performing one or more operations, wherein the operations includes expanding acronyms, checking syllable length, checking character length, and incorporating a uniqueness and inclusion diversity check.

### Claim 17 (depends on 12)

The system of claim 12, wherein the metadata comprises at least an attribute name and an attribute description; and wherein the at least one processor is further configured to:
compare the attribute name with one or more attributes included in a frequent attribute list; and
in response to determining that there is no match between the attribute name and the one or more attributes, refine the attribute name.

### Claim 18 (depends on 12)

The system of claim 12, wherein the at least one processor is further configured to:
convert textual data for an attribute of the metadata into vectors by determining a relevancy score;
determine a similarity score between the vectors and a centroid associated with a data type; and
identify the data type for the attribute based on the similarity score.

### Claim 19

A non-transitory computer-readable device having instructions stored thereon that, when executed by at least one computing device, cause the at least one computing device to perform operations comprising:
acquiring, via a user interface, metadata associated with a data store;
performing natural language processing on the metadata to generate processed metadata;
generating a candidate table name and a table description associated with the candidate table name for a table included in the metadata based on at least the processed metadata;
generating a first candidate attribute name, an attribute description associated with the first candidate attribute name, and a corresponding data type for each attribute associated with the table;
generating an second candidate attribute name by extracting one or more keywords from the first candidate attribute name, wherein the second candidate attribute name corresponds to a technical name; and
modifying the user interface to include the first candidate attribute name, the second candidate attribute name, and the attribute description for each attribute associated with the table.

### Claim 20 (depends on 19)

The non-transitory computer-readable device of claim 19, the operations further comprising:
identifying personally identifiable information in attributes included in the metadata; and
tagging an attribute corresponding to the identified personally identifiable information.
