# US 2024/0202449 A1 · Knowledge fact retrieval through natural language processing

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

- Number: US 2024/0202449 A1
- Document ID: US20240202449A1
- Status: Published application
- Kind: A1
- Application number: 18/066,128
- Filed: 2022-12-14
- Published: 2024-06-20
- Earliest claimed: 2022-12-14
- Assignees: ADP, Inc.
- Applicants: ADP, Inc.
- Inventors: Roberto COUTINHO; Roberto SILVEIRA; Guilherme GOMES; Carlos NASCIMENTO; Felipe Lisboa SUSLIK
- Web page: https://patentgrep.com/patent/US20240202449A1

## CPC

- G06F 40/30: Semantic analysis
- G06F 40/295: Named entity recognition
- G06V 30/19093: {Proximity measures, i.e. similarity or distance measures}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A method for fact retrieval includes receiving an input from a user, said input including a string of text that represents a user intent. The method includes performing natural language processing on the input to generate an embedding that corresponds to a semantic representation of the string of text, and based on the generated embedding, identifying an action that is associated with the user intent. The method includes executing the identified action, such that the executed action returns a result associated with the user intent, and providing the result to the user.

## Claims

### Claim 1

A method for fact retrieval, comprising:
receiving an input from a user, said input comprising a string of text that represents a user intent;
performing natural language processing on the input to generate an embedding that corresponds to a semantic representation of the string of text;
based on the generated embedding, identifying, from a plurality of actions, an action associated with the user intent, wherein each action in the plurality of actions is associated with a pre-determined embedding in a plurality of pre-determined embeddings;
executing the identified action, wherein executing the action returns a result associated with the user intent; and
providing the result to the user.

### Claim 2 (depends on 1)

The method of claim 1, wherein identifying the action comprises determining a similarity between the generated embedding and each of the plurality of pre-determined embeddings, and based on the determined similarity, selecting the action from the plurality of actions.

### Claim 3 (depends on 2)

The method of claim 2, wherein selecting the action comprises determining that the pre-determined embedding of the selected action is the most similar, out of all of the plurality of pre-determined embeddings, to the generated embedding.

### Claim 4 (depends on 1)

The method of claim 1, wherein the action comprises an identification of a storage from a plurality of storages, executing the action comprises performing a query to the identified storage, and the result comprises a response to the query from the identified storage.

### Claim 5 (depends on 4)

The method of claim 4, wherein the input further comprises a first-person identifier associated with the user, and the query to the identified storage comprises the first-person identifier.

### Claim 6 (depends on 4)

The method of claim 4, wherein the user is a first user, and the string of text comprises an ambiguous reference to a second user, the method further comprising:
identifying a plurality of user identifiers that at least partially match the ambiguous reference to the second user; and
selecting a user identifier from the plurality of user identifiers,
wherein the query to the identified storage comprises the selected user identifier.

### Claim 7 (depends on 6)

The method of claim 6, wherein the user identifier is selected by providing the identified plurality of user identifiers to the first user, and receiving a selection of the user identifier from the first user.

### Claim 8 (depends on 7)

The method of claim 7, wherein the input further comprises a role attribute associated with the first user, wherein the user identifier is selected based on the role attribute of the first user.

### Claim 9 (depends on 8)

The method of claim 8, wherein executing the action comprises determining, based on the role attribute of the first user, that the first user is authorized to receive the result from the identified action, wherein the user is not authorized to receive results from at least one other action in the plurality of actions.

### Claim 10 (depends on 4)

The method of claim 4, wherein the string of text comprises an ambiguous reference to an identifier, the method further comprising:
identifying a plurality of identifiers that at least partially match the ambiguous reference to the identifier;
providing the plurality of identifiers to the user; and
receiving a selection of the identifier from the user.
wherein the query to the identified storage comprises the selected identifier.

### Claim 11 (depends on 10)

The method of claim 10, wherein the identifier is for one of a place, a document, a person, an access role, a job title, and a date.

### Claim 12

A non-transitory computer-readable medium storing a set of instructions for fact retrieval, which when executed by a computer, configure the computer to:
receive an input from a user, said input comprising a string of text that represents a user intent;
perform natural language processing on the input to generate an embedding that corresponds to a semantic representation of the string of text;
based on the generated embedding, identify, from a plurality of actions, an action associated with the user intent, wherein each action in the plurality of actions is associated with a pre-determined embedding in a plurality of pre-determined embeddings;
execute the identified action, wherein executing the action returns a result associated with the user intent; and
provide the result to the user.

### Claim 13 (depends on 12)

The non-transitory computer-readable medium of claim 12, wherein identifying the action comprises determining a similarity between the generated embedding and each of the plurality of pre-determined embeddings, and based on the determined similarity, selecting the action from the plurality of actions.

### Claim 14 (depends on 13)

The non-transitory computer-readable medium of claim 13, wherein selecting the action comprises determining that the pre-determined embedding of the selected action is the most similar, out of all of the plurality of pre-determined embeddings, to the generated embedding.

### Claim 15 (depends on 12)

The non-transitory computer-readable medium of claim 12, wherein the action comprises an identification of a storage from a plurality of storages, executing the action comprises performing a query to the identified storage, and the result comprises a response to the query from the identified storage.

### Claim 16 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the input further comprises a first-person identifier associated with the user, and the query to the identified storage comprises the first-person identifier.

### Claim 17 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the user is a first user, and the string of text comprises an ambiguous reference to a second user, the instructions further configuring the computer to:
identify a plurality of user identifiers that at least partially match the ambiguous reference to the second user; and
select a user identifier from the plurality of user identifiers,
wherein the query to the identified storage comprises the selected user identifier.

### Claim 18 (depends on 17)

The non-transitory computer-readable medium of claim 17, wherein the user identifier is selected by providing the identified plurality of user identifiers to the first user, and receiving a selection of the user identifier from the first user.

### Claim 19 (depends on 18)

The non-transitory computer-readable medium of claim 18, wherein the input further comprises a role attribute associated with the first user, wherein the user identifier is selected based on the role attribute of the first user.

### Claim 20 (depends on 19)

The non-transitory computer-readable medium of claim 19, wherein executing the action comprises determining, based on the role attribute of the first user, that the first user is authorized to receive the result from the identified action, wherein the user is not authorized to receive results from at least one other action in the plurality of actions.

### Claim 21 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the string of text comprises an ambiguous reference to an identifier, the instructions further configuring the computer to:
identify a plurality of identifiers that at least partially match the ambiguous reference to the identifier;
provide the plurality of identifiers to the user; and
receive a selection of the identifier from the user,
wherein the query to the identified storage comprises the selected identifier.

### Claim 22 (depends on 21)

The non-transitory computer-readable medium of claim 21, wherein the identifier is for one of a place, a document, a person, an access role, a job title, and a date.
