# US 2021/0342541 A1 · Stable identification of entity mentions

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

- Number: US 2021/0342541 A1
- Document ID: US20210342541A1
- Status: Published application
- Kind: A1
- Application number: 17/306,656
- Filed: 2021-05-03
- Published: 2021-11-04
- Earliest claimed: 2020-05-01
- Assignees: salesforce.com, inc.
- Applicants: salesforce.com, inc.
- Inventors: Aaron Michael Taylor; Henry Forrest Leanna Wallace; John Randolph Frank; Andrew Richard Gallant
- Web page: https://patentgrep.com/patent/US20210342541A1

## CPC

- G06F 40/295: Named entity recognition
- G06F 16/3328: {using graphical result space presentation or visualisation}
- G06N 5/02: Knowledge representation; Symbolic representation
- G06N 5/022: Knowledge engineering; Knowledge acquisition
- G06N 5/04: Inference or reasoning models
- G06F 40/197: Version control (for software G06F8/71)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

An entity-based platform stores a database of entity mentions and related, entity-based information obtained by processing text in a corpus of documents such as content from a public network or content from a document management system. The platform may analyze changes to a previously-processed document in order to align mentions in the modified document to mentions in a prior document and/or to identify new mentions not present in the previously-processed document. As the underlying documents in the corpus change over time, this advantageously permits sustained use of knowledge graphs and other entity-based representations or analysis linked to specific entity mentions.

## Claims

### Claim 1

A method for stable identification of entities mentioned in dynamic documents comprising:
processing a corpus of documents to identify a first plurality of mentions of a first plurality of entities;
assigning a unique identifier to each of the first plurality of mentions identified in the corpus of documents;
storing each unique identifier and each corresponding one of the first plurality of mentions in a database;
detecting an updated document containing a change to text in a document from the corpus of documents;
processing the updated document to identify a second plurality of mentions of a second plurality of entities;
comparing the second plurality of mentions to the first plurality of mentions;
for an aligned mention from the second plurality of mentions in the updated document corresponding to one of the first plurality of mentions in the document, storing the aligned mention in the database in association with one of the unique identifiers for the one of the first plurality of mentions; and
for a new mention from the second plurality of mentions not corresponding to one of the first plurality of mentions, storing the new mention in the database as a new entry with a new unique identifier.

### Claim 2 (depends on 1)

The method of claim 1 wherein the corpus of documents includes content from a public network.

### Claim 3 (depends on 1)

The method of claim 1 wherein the corpus of documents includes content from a document management system.

### Claim 4 (depends on 1)

The method of claim 1 wherein the document and the updated document are uniquely identified on the web by a Uniform Resource Locator.

### Claim 5 (depends on 1)

The method of claim 1 wherein the document and the updated document are uniquely identified within a corporate network by a filename and path.

### Claim 6 (depends on 1)

The method of claim 1 wherein the document and the updated document are uniquely identified in a document management system by a document identifier.

### Claim 7 (depends on 1)

The method of claim 1 further comprising generating and displaying a knowledge graph using at least one of the aligned mentions and at least one of the new mentions in the database.

### Claim 8 (depends on 1)

The method of claim 1 further comprising generating a suggestion for at least one additional document using at least one of the aligned mentions and at least one of the new mentions in the database.

### Claim 9 (depends on 1)

The method of claim 1 further comprising, for a missing mention included in the first plurality of mentions and missing from the second plurality of mentions, updating a corresponding one of the unique identifiers to indicate that the missing mention has been removed from the updated document.

### Claim 10 (depends on 9)

The method of claim 9 further comprising updating a knowledge graph to remove any entity relationships associated with the missing mention.

### Claim 11

A computer program product for stable identification of entities mentioned in dynamic documents, the computer program product comprising computer-readable program code to be executed by one or more processors when retrieved from a non-transitory computer-readable medium, the program code comprising instructions configurable to cause:
processing a corpus of documents to identify a first plurality of mentions of a first plurality of entities;
assigning a unique identifier to each of the first plurality of mentions identified in the corpus of documents;
storing each unique identifier and each corresponding one of the first plurality of mentions in a database;
detecting an updated document containing a change to text in a document from the corpus of documents;
processing the updated document to identify a second plurality of mentions of a second plurality of entities;
comparing the second plurality of mentions to the first plurality of mentions;
for each aligned mention from the second plurality of mentions in the updated document corresponding to one of the first plurality of mentions in the document, storing the aligned mention in the database in association with one of the unique identifiers for the one of the first plurality of mentions; and
for each new mention from the second plurality of mentions not corresponding to one of the first plurality of mentions, storing the new mention in the database as a new entry with a new unique identifier.

### Claim 12 (depends on 11)

The computer program product of claim 11 wherein the corpus of documents includes content from a public network.

### Claim 13 (depends on 11)

The computer program product of claim 11 wherein the corpus of documents includes content from a document management system.

### Claim 14 (depends on 11)

The computer program product of claim 11 wherein the document and the updated document are uniquely identified on the web by a Uniform Resource Locator.

### Claim 15 (depends on 11)

The computer program product of claim 11 wherein the document and the updated document are uniquely identified within a corporate network by a filename and path.

### Claim 16 (depends on 11)

The computer program product of claim 11 wherein the document and the updated document are uniquely identified in a document management system by a document identifier.

### Claim 17 (depends on 11)

The computer program product of claim 11 further comprising code that performs the step of generating and displaying a knowledge graph using at least one of the aligned mentions and at least one of the new mentions in the database.

### Claim 18 (depends on 11)

The computer program product of claim 11 further comprising code that performs the step of generating a suggestion for at least one additional document using at least one of the aligned mentions and at least one of the new mentions in the database.

### Claim 19

A database system comprising:
at least one database storing entity mentions from a corpus of documents and corresponding identifiers; and
at least one server having at least one processor capable of executing instructions configured to cause the server to perform the steps of:
processing the corpus of documents to identify a first plurality of mentions of a first plurality of entities;
assigning a unique identifier to each of the first plurality of mentions identified in the corpus of documents;
storing each unique identifier and each corresponding one of the first plurality of mentions in the at least one database;
detecting an updated document containing a change to text in a document from the corpus of documents;
processing the updated document to identify a second plurality of mentions of a second plurality of entities;
comparing the second plurality of mentions to the first plurality of mentions to identify one or more repeated ones of the first plurality of mentions in the second plurality of mentions;
for each aligned mention from the second plurality of mentions in the updated document corresponding to one of the first plurality of mentions in the document, storing the aligned mention in the at least one database in association with one of the unique identifiers for the corresponding one of the first plurality of mentions; and
for each new mention from the second plurality of mentions not corresponding to one of the first plurality of mentions, storing the new mention in the at least one database as a new entry with a new unique identifier.

### Claim 20 (depends on 19)

The database system of claim 19, wherein the database system includes a multi-tenant database.
