# US 2022/0036892 A1 · User profile linking

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

- Number: US 2022/0036892 A1
- Document ID: US20220036892A1
- Status: Published application
- Kind: A1
- Application number: 17/405,120
- Filed: 2021-08-18
- Published: 2022-02-03
- Earliest claimed: 2019-06-27
- Assignees: Amazon Technologies, Inc.
- Applicants: Amazon Technologies, Inc.
- Inventors: Fabien Hertschuh; Mohit Mittal; John Montague Howard; Akshit Proothi; Rahul Manne
- Web page: https://patentgrep.com/patent/US20220036892A1

## CPC

- G06Q 10/10: Office automation; Time management
- G06F 3/167: {Audio in a user interface, e.g. using voice commands for navigating, audio feedback}
- G06Q 10/40: Business processes related to social networking or social networking services
- G06Q 30/02: Marketing; Price estimation or determination; Fundraising
- G06Q 30/0641: {utilising user interfaces specially adapted for shopping}
- G10L 15/07: to the speaker
- G10L 15/1815: {Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning}
- G10L 15/1822: {Parsing for meaning understanding}
- G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L 17/00: Speaker identification or verification techniques
- G10L 17/04: Training, enrolment or model building
- G10L 17/26: Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices
- G10L 2015/223: {Execution procedure of a spoken command}
- G10L 2015/227: {of the speaker; Human-factor methodology}
- G10L 2015/228: {of application context}
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

Described are techniques for linking generating a skill-stored user profile, and linking same with a natural language processing (NLP) system-stored user profile. In at least some examples, a user may provide a natural language input to a NLP system. The NLP system may determine a skill is to process to perform an action responsive to the natural language input. To perform the action, the skill may require the user have a user profile stored by the skill, but the user may not have such a user profile. However, the NLP system may store a user profile for the user. The NLP system may determine the user profile stored thereby and may send, with user permission, information in the user profile to the skill. The skill may use the received information to generate and store a user profile for the user. Thereafter, the skill may provide the NLP system with a user profile identifier that the skill may use to identify the user's profile stored thereby. The NLP system may store the received user profile identifier in the user's profile stored by the NLP system, thereby linking the user profiles and enabling the skill to thereafter personalize processing with respect to natural language inputs of the user.

## Claims

### Claim at position 1

-20. (canceled)

### Claim 21

A computer-implemented method, comprising:
operating a first device in association with a first user profile;
receiving, from the first device, a request to perform an action to be associated with a second user profile;
determining a first type of information is requested to perform the action;
determining user permission to use first information to perform the action, the first information corresponding to the first type;
determining second user profile data corresponding to the action;
storing an association between the second user profile data and the first user profile; and
sending an instruction to perform the action using the second user profile data.

### Claim 22 (depends on 21)

The computer-implemented method of claim 21, wherein the first user profile and the second user profile are associated with a same user.

### Claim 23 (depends on 21)

The computer-implemented method of claim 21, wherein the first type of information corresponds to an email address.

### Claim 24 (depends on 21)

The computer-implemented method of claim 21, wherein the second user profile data is determined based at least in part on the first information.

### Claim 25 (depends on 21)

The computer-implemented method of claim 21, further comprising:
retrieving, using the first user profile, the first information.

### Claim 26 (depends on 21)

The computer-implemented method of claim 21, wherein the first user profile corresponds to a first system and the second user profile corresponds to a second system different from the first system.

### Claim 27 (depends on 21)

The computer-implemented method of claim 21, wherein the first information is specific to a user associated with the first user profile.

### Claim 28 (depends on 21)

The computer-implemented method of claim 21, wherein the second user profile corresponds to a website corresponding to the action.

### Claim 29 (depends on 21)

The computer-implemented method of claim 21, wherein the second user profile corresponds to an application to be operated in conjunction with the first device.

### Claim 30 (depends on 21)

The computer-implemented method of claim 21, further comprising:
determining that a user associated with the first user profile has been recognized using a user recognition technique,
wherein sending the second user profile data is performed in response to determining that the user has been recognized.

### Claim 31

A system comprising:
at least one processor; and
at least one memory comprising instructions that, when executed by the at least one processor, cause the system to:
operate a first device in association with a first user profile;
receive, from the first device, a request to perform an action to be associated with a second user profile;
determine a first type of information is requested to perform the action;
determine user permission to use first information to perform the action, the first information corresponding to the first type;
determine second user profile data corresponding to the action;
store an association between the second user profile data and the first user profile; and
send an instruction to perform the action using the second user profile data.

### Claim 32 (depends on 31)

The system of claim 31, the first user profile and the second user profile are associated with a same user.

### Claim 33 (depends on 31)

The system of claim 31, the first type of information corresponds to an email address.

### Claim 34 (depends on 31)

The system of claim 31, the second user profile data is determined based at least in part on the first information.

### Claim 35 (depends on 31)

The system of claim 31, wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
retrieve, using the first user profile, the first information.

### Claim 36 (depends on 31)

The system of claim 31, wherein the first user profile corresponds to a first system and the second user profile corresponds to a second system different from the first system.

### Claim 37 (depends on 31)

The system of claim 31, wherein the first information is specific to a user associated with the first user profile.

### Claim 38 (depends on 31)

The system of claim 31, wherein the second user profile corresponds to a website corresponding to the action.

### Claim 39 (depends on 31)

The system of claim 31, wherein the second user profile corresponds to an application to be operated in conjunction with the first device.

### Claim 40 (depends on 31)

The system of claim 31, wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
determine that a user associated with the first user profile has been recognized using a user recognition technique,
wherein sending the second user profile data is performed in response to determining that the user has been recognized.