# US 2026/0037559 A1 · Using crowdsourced reinforcement learning to optimize a natural language interface system

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

- Number: US 2026/0037559 A1
- Document ID: US20260037559A1
- Status: Published application
- Kind: A1
- Application number: 18/791,246
- Filed: 2024-07-31
- Published: 2026-02-05
- Earliest claimed: 2024-07-31
- Assignees: Cisco Technology, Inc.
- Applicants: Cisco Technology, Inc.
- Inventors: Timothy Simon Stirling; Yannick Weibel; Sofia Karygianni
- Web page: https://patentgrep.com/patent/US20260037559A1

## CPC

- G06F 16/3344: {using natural language analysis}
- G06F 16/2456: {Join operations}
- G06F 16/3329: Natural language query formulation
- G06F 16/383: using metadata automatically derived from the content
- G06F 16/90332: {Natural language query formulation or dialogue systems}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

In one implementation, a device receives a query from a user for input to a large language model. The device matches a pattern associated with the query with one or more prior chat exchanges between the large language model and one or more other users. The device generates an adjusted query based on the query and the one or more prior chat exchanges. The device provides an answer to the adjusted query from the large language model to the user.

## Claims

### Claim 1

A method comprising:
receiving, at a device, a query from a user for input to a large language model;
matching, by the device, a pattern associated with the query with one or more prior chat interactions between the large language model and one or more other users;
generating, by the device, an adjusted query based on the query and the one or more prior chat interactions; and
providing, by the device, an answer to the adjusted query from the large language model to the user.

### Claim 2 (depends on 1)

The method as in claim 1, wherein the one or more prior chat interactions include at least one follow up query to an answer provided by the large language model to the one or more other users.

### Claim 3 (depends on 1)

The method as in claim 1, wherein the device generates the adjusted query based further in part on one or more prior chat interactions between the user and the large language model.

### Claim 4 (depends on 1)

The method as in claim 1, wherein the device matches the query to the one or more prior chat interactions based on their semantic similarity.

### Claim 5 (depends on 1)

The method as in claim 1, wherein the device generates the adjusted query in part by merging the query with another query in the one or more prior chat interactions.

### Claim 6 (depends on 1)

The method as in claim 1, wherein the device generates the adjusted query based in part on a success metric associated with the one or more prior chat interactions.

### Claim 7 (depends on 6)

The method as in claim 6, wherein the success metric is computed based on a count of follow up queries in the one or more prior chat interactions.

### Claim 8 (depends on 1)

The method as in claim 1, further comprising:
maintaining, by the device, an interactions registry that includes the one or more prior chat interactions.

### Claim 9 (depends on 1)

The method as in claim 1, wherein the query requests information regarding a computer network.

### Claim 10 (depends on 9)

The method as in claim 9, wherein the query requests information regarding a particular networking entity in the computer network.

### Claim 11

An apparatus, comprising:
one or more network interfaces;
a processor coupled to the one or more network interfaces and configured to execute one or more processes; and
a memory configured to store a process that is executable by the processor, the process when executed configured to:
receive a query from a user for input to a large language model;
match a pattern associated with the query with one or more prior chat interactions between the large language model and one or more other users;
generate an adjusted query based on the query and the one or more prior chat interactions; and
provide an answer to the adjusted query from the large language model to the user.

### Claim 12 (depends on 11)

The apparatus as in claim 11, wherein the one or more prior chat interactions include at least one follow up query to an answer provided by the large language model to the one or more other users.

### Claim 13 (depends on 11)

The apparatus as in claim 11, wherein the apparatus generates the adjusted query based further in part on one or more prior chat interactions between the user and the large language model.

### Claim 14 (depends on 11)

The apparatus as in claim 11, wherein the apparatus matches the query to the one or more prior chat interactions based on their semantic similarity.

### Claim 15 (depends on 11)

The apparatus as in claim 11, wherein the apparatus generates the adjusted query in part by merging the query with another query in the one or more prior chat interactions.

### Claim 16 (depends on 11)

The apparatus as in claim 11, wherein the apparatus generates the adjusted query based in part on a success metric associated with the one or more prior chat interactions.

### Claim 17 (depends on 16)

The apparatus as in claim 16, wherein the success metric is computed based on a count of follow up queries in the one or more prior chat interactions.

### Claim 18 (depends on 11)

The apparatus as in claim 11, wherein the process when executed is further configured to:
maintain an interactions registry that includes the one or more prior chat interactions.

### Claim 19 (depends on 11)

The apparatus as in claim 11, wherein the query requests information regarding a computer network.

### Claim 20

A tangible, non-transitory, computer-readable medium storing program instructions that cause a device to execute a process comprising:
receiving, at the device, a query from a user for input to a large language model;
matching, by the device, a pattern associated with the query with one or more prior chat exchanges between the large language model and one or more other users;
generating, by the device, an adjusted query based on the query and the one or more prior chat exchanges; and
providing, by the device, an answer to the adjusted query from the large language model to the user.
