# US 2024/0403553 A1 · Systems and methods for generating diagnostic assets for information retrieval and network pathway guidance

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

- Number: US 2024/0403553 A1
- Document ID: US20240403553A1
- Status: Published application
- Kind: A1
- Application number: 18/325,991
- Filed: 2023-05-30
- Published: 2024-12-05
- Earliest claimed: 2023-05-30
- Assignees: Capital One Services, LLC
- Applicants: Capital One Services, LLC
- Inventors: Jalen Isaiah CHASE; Matthew Evan SKINNER
- Web page: https://patentgrep.com/patent/US20240403553A1

## CPC

- G06F 40/211: Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
- G06F 40/40: Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Methods and systems are provided for information retrieval pathway guidance. In particular, the systems and methods provided apply artificial intelligence to novel tasks related to retrieving remotely accessible data such as detecting competency levels of users, generating personalized guidance for individual users based on the retrieval goals and initial competency level of a user, generating custom diagnostic assets for those goals based on current strengths and weaknesses, generating content for custom questions for those diagnostic assets, and dynamically tracking and updating the competency level of the user during the course.

## Claims

### Claim 1

A system for providing information retrieval and network pathway guidance using natural language processing, the system comprising:
one or more processors; and
a non-transitory, computer-readable medium comprising instructions that when executed by the one or more processors cause operations comprising:
receiving a user input of remote information for retrieval;
selecting a first diagnostic asset corresponding to the remote information;
processing the first diagnostic asset using a part-of-speech tagging algorithm to label a first word of the first diagnostic asset as corresponding to a first part-of-speech type and a second word of the first diagnostic asset as corresponding to a second part-of-speech type;
selecting a part-of-speech type for testing in the first diagnostic asset;
determining that the first part-of-speech type corresponds to the part-of-speech type for testing;
in response to determining that the first part-of-speech type corresponds to the part-of-speech type for testing, generating a first information retrieval question corresponding to the first word;
receiving a first user response to the first information retrieval question;
determining a first user competency level based on the first user response;
determining a first location of the remote information;
generating first information retrieval guidance corresponding to the first user competency level and the first location; and
simultaneously displaying, in a user interface, the first information retrieval guidance and a second diagnostic asset corresponding to the remote information.

### Claim 2

A method for providing information retrieval and network pathway guidance using natural language processing, the method comprising:
receiving a user input of remote information for retrieval;
selecting a diagnostic asset corresponding to the remote information;
processing the diagnostic asset using a part-of-speech tagging algorithm to label a first word of the diagnostic asset as corresponding to a first part-of-speech type and a second word of the diagnostic asset as corresponding to a second part-of-speech type;
selecting a part-of-speech type for testing in the diagnostic asset;
determining that the first part-of-speech type corresponds to the part-of-speech type for testing; and
in response to determining that the first part-of-speech type corresponds to the part-of-speech type for testing, generating an information retrieval question corresponding to the first word of the diagnostic asset.

### Claim 3 (depends on 2)

The method of claim 2, further comprising:
receiving a user response to the information retrieval question; and
determining a user competency level based on the user response.

### Claim 4 (depends on 2)

The method of claim 2, further comprising:
receiving a user response to the information retrieval question;
determining a user competency level based on the user response; and
generating information retrieval guidance corresponding to the user competency level.

### Claim 5 (depends on 2)

The method of claim 2, further comprising:
receiving a user response to the information retrieval question;
determining a user competency level based on the user response;
determining a location of the remote information; and
generating information retrieval guidance corresponding to the user competency level and the location.

### Claim 6 (depends on 2)

The method of claim 2, further comprising:
determining a location of the remote information;
determining a network pathway to the location; and
generating information retrieval guidance corresponding to the network pathway.

### Claim 7 (depends on 2)

The method of claim 2, further comprising:
determining that a threshold amount of time has passed since generating the information retrieval question; and
in response to determining that the threshold amount of time has passed, querying a remote user for the remote information.

### Claim 8 (depends on 2)

The method of claim 2, further comprising:
retrieving a content type preference of a user from a user profile; and
filtering available diagnostic assets based on the content type preference.

### Claim 9 (depends on 2)

The method of claim 2, further comprising:
retrieving a user competency level from a user profile; and
selecting the information retrieval question corresponding to the first word of the diagnostic asset based on the user competency level.

### Claim 10 (depends on 2)

The method of claim 2, further comprising:
retrieving a first competency level for the first part-of-speech type from a user profile;
comparing the first competency level to a threshold competency level; and
selecting the part-of-speech type for testing in the diagnostic asset based on the first competency level not equaling or exceeding the threshold competency level.

### Claim 11 (depends on 2)

The method of claim 2, further comprising:
retrieving a first competency level for the first part-of-speech type from a user profile;
retrieving a second competency level for the second part-of-speech type from the user profile;
comparing the first competency level to the second competency level; and
selecting the part-of-speech type for testing in the diagnostic asset based on the first competency level not equaling or exceeding the second competency level.

### Claim 12 (depends on 2)

The method of claim 2, further comprising:
training an artificial intelligence model to detect a known user competency level based on a labeled first user action and a labeled third user action, wherein the labeled first user action is from a first user that is interacting with a first different diagnostic asset, and wherein the labeled third user action is from a third user that is interacting with a third different diagnostic asset;
receiving a second user action from a second user while the second user is interacting with a second diagnostic asset;
inputting the second user action into the artificial intelligence model; and
receiving an output from the artificial intelligence model indicating that the second user has the known user competency level.

### Claim 13 (depends on 2)

The method of claim 2, further comprising:
receiving a first user action from a first user that is interacting with a first diagnostic asset, wherein the first user action has a first characteristic;
labeling the first user action with a known user competency level;
training an artificial intelligence model to detect the known user competency level on the first user action;
receiving a second user action from a second user that is interacting with a second diagnostic asset, wherein the second user action has a second characteristic;
inputting the second user action into the artificial intelligence model; and
receiving an output from the artificial intelligence model indicating that the second user has the known user competency level.

### Claim 14 (depends on 13)

The method of claim 13, wherein training the artificial intelligence model to detect the known user competency level on the first user action comprises:
determining a range for the second characteristic for the second user action based on the first characteristic; and
determining that the second characteristic is within the range.

### Claim 15

A non-transitory, computer-readable medium comprising instructions that when executed by one or more processors cause operations comprising:
receiving a user input of remote information for retrieval;
selecting a diagnostic asset corresponding to the remote information;
processing the diagnostic asset using a part-of-speech tagging algorithm to label a first word of the diagnostic asset as corresponding to a first part-of-speech type and a second word of the diagnostic asset as corresponding to a second part-of-speech type;
selecting a part-of-speech type for testing in the diagnostic asset;
determining that the first part-of-speech type corresponds to the part-of-speech type for testing; and
in response to determining that the first part-of-speech type corresponds to the part-of-speech type for testing, generating an information retrieval question corresponding to the first word of the diagnostic asset.

### Claim 16 (depends on 15)

The non-transitory, computer-readable medium of claim 15, wherein the instructions further cause operations comprising:
receiving a user response to the information retrieval question; and
determining a user competency level based on the user response.

### Claim 17 (depends on 15)

The non-transitory, computer-readable medium of claim 15, wherein the instructions further cause operations comprising:
receiving a user response to the information retrieval question;
determining a user competency level based on the user response; and
generating information retrieval guidance corresponding to the user competency level.

### Claim 18 (depends on 15)

The non-transitory, computer-readable medium of claim 15, wherein the instructions further cause operations comprising:
receiving a user response to the information retrieval question;
determining a user competency level based on the user response;
determining a location of the remote information; and
generating information retrieval guidance corresponding to the user competency level and the location.

### Claim 19 (depends on 15)

The non-transitory, computer-readable medium of claim 15, wherein the instructions further cause operations comprising:
determining a location of the remote information;
determining a network pathway to the location; and
generating information retrieval guidance corresponding to the network pathway.

### Claim 20 (depends on 15)

The non-transitory, computer-readable medium of claim 15, wherein the instructions further cause operations comprising:
determining that a threshold amount of time has passed since generating the information retrieval question; and
in response to determining that the threshold amount of time has passed, querying a remote user for the remote information.
