# US 2019/0378426 A1 · Generating customized learning paths

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

- Number: US 2019/0378426 A1
- Document ID: US20190378426A1
- Status: Published application
- Kind: A1
- Application number: 16/001,198
- Filed: 2018-06-06
- Published: 2019-12-12
- Earliest claimed: 2018-06-06
- Assignees: Microsoft Technology Licensing, LLC
- Applicants: Microsoft Technology Licensing, LLC
- Inventors: Pan Wu; Daniel Patrick Tweed-Kent; Sally Limb; Marshall David Miller; Yiying Cheng
- Web page: https://patentgrep.com/patent/US20190378426A1

## CPC

- G09B 5/00: Electrically-operated educational appliances (working with questions and answers G09B7/00; simulators G09B9/00; advertising or displaying in general G09F)
- G09B 5/02: with visual presentation of the material to be studied, e.g. using film strip
- G09B 7/00: Electrically-operated teaching apparatus or devices working with questions and answers (mechanically operated G09B3/00; computing arrangements G06F)
- G09B: EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS (devices for psychotechnics or for testing reaction times A61B5/16; games, sports, amusements A63; projectors, projector screens G03B)

## Abstract

Techniques for generating customized learning paths are provided. In one technique, consumption data that indicates consumption of multiple learning resources by multiple users is recorded. Based on the consumption data, multiple learning resource tuples are generated, each learning resource tuple indicating that one learning resource that was consumed by a user prior to another learning resource that was consumed by the user. Multiple aggregations are performed, where each aggregation involves aggregating different sets of learning resource tuples, where each set of learning resource tuples comprises the same two learning resources in the same order. Based on a subset of the aggregations, a customized learning path that comprises a set of learning resources is generated for a particular user. The customized learning path is presented to the particular user.

## Claims

### Claim 1

A method for generating customized learning paths, the method comprising:
recording consumption data that indicates consumption of a plurality of learning resources by a plurality of users;
based on the consumption data, generating a plurality of learning resource tuples, each learning resource tuple indicating that one learning resource that was consumed by a user prior to another learning resource that was consumed by the user;
performing a plurality of aggregations, wherein each aggregation in the plurality of aggregations involves aggregating different sets of learning resource tuples in the plurality of learning resource tuples, wherein each set of learning resource tuples comprises the same two learning resources in the same order;
based on a subset of the plurality of aggregations, generating, for a first user, a first customized learning path that comprises a first set of learning resources;
causing the first customized learning path to be displayed to the first user;
wherein the method is performed by one or more computing devices.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
generating, for the first user, a second customized learning path that comprises a second set of learning resources that is different than the first set of learning resources;
causing the first and second customized learning paths to be displayed concurrently to the first user.

### Claim 3 (depends on 1)

The method of claim 1, further comprising:
determining a group of users that are similar to the first user;
for each user in the group of users, identifying a set of learning resources that was consumed by said each user;
wherein the plurality of aggregations is based on the sets of learning resources consumed, respectively, by each user in the group of users.

### Claim 4 (depends on 3)

The method of claim 3, further comprising:
identifying one or more attribute values associated with the first user, wherein determining the group of users comprises determining that each user in the group of users is associated with the one or more attribute values;
wherein the one or more attribute values indicate a particular industry, a particular job title, a particular level experience, or a particular geographic region.

### Claim 5 (depends on 4)

The method of claim 4, wherein:
identifying the one or more attribute values comprises identifying a first profile associated with the first user, wherein the first profile includes data that the first user inserted into the first profile;
determining that each user in the group of users is associated with the one or more attribute values comprises identifying, for each user in the group of users, a second profile that is associated with the said each user and includes data that said each user inserted into the second profile.

### Claim 6 (depends on 4)

The method of claim 4, wherein the one or more attribute values are a plurality of attribute values that indicate two or more of the particular industry, the particular job title, the particular level of experience, or the particular geographic region.

### Claim 7 (depends on 1)

The method of claim 1, further comprising:
determining that a particular user consumed a first particular learning resource prior to a second particular learning resource;
generating a first learning resource pair that identifies the first particular learning resource and the second particular learning resource;
performing a first aggregation that aggregates the first learning resource pair with one or more other first learning resource pairs;
wherein the first customized learning path is generated based on the first aggregation;
performing a second aggregation that aggregates the first learning resource pair with one or more other second learning resource pairs;
based on the second aggregation, generating a second customized learning path for a second user that is different than the first user.

### Claim 8 (depends on 1)

The method of claim 1, further comprising:
determining that a particular user consumed a first particular learning resource prior to a second particular learning resource;
determining whether the particular user consumed a particular amount of the first particular learning resource, wherein the particular amount is less than the entirety of the first particular learning resource;
generating a learning resource pair for the first particular learning resource and the second particular learning resource only in response to determining that the particular amount is greater than a particular threshold.

### Claim 9 (depends on 1)

The method of claim 1, further comprising:
determining that a first number of users consumed a second particular learning resource after consuming a first particular learning resource;
determining that a second number of users consumed a third particular learning resource after consuming the first particular learning resource;
based on the first number being greater than the second number, including the second particular learning resource in the first customized learning path instead of the third particular learning resource.

### Claim 10 (depends on 1)

The method of claim 1, further comprising:
identifying one or more learning resources that the first user has already consumed;
wherein generating the first customized learning path is also based on the one or more learning resources.

### Claim 11

One or more storage media storing instructions for generating customized learning paths, wherein the instructions, when executed by the one or more processors, cause:
recording consumption data that indicates consumption of a plurality of learning resources by a plurality of users;
based on the consumption data, generating a plurality of learning resource tuples, each learning resource tuple indicating that one learning resource that was consumed by a user prior to another learning resource that was consumed by the user;
performing a plurality of aggregations, wherein each aggregation in the plurality of aggregations involves aggregating different sets of learning resource tuples in the plurality of learning resource tuples, wherein each set of learning resource tuples comprises the same two learning resources in the same order;
based on a subset of the plurality of aggregations, generating, for a first user, a first customized learning path that comprises a first set of learning resources;
causing the first customized learning path to be displayed to the first user.

### Claim 12 (depends on 11)

The one or more storage media of claim 11, wherein the instructions, when executed by the one or more processors, further cause:
generating, for the first user, a second customized learning path that comprises a second set of learning resources that is different than the first set of learning resources;
causing the first and second customized learning paths to be displayed concurrently to the first user.

### Claim 13 (depends on 11)

The one or more storage media of claim 11, wherein the instructions, when executed by the one or more processors, further cause:
determining a group of users that are similar to the first user;
for each user in the group of users, identifying a set of learning resources that was consumed by said each user;
wherein the plurality of aggregations is based on the sets of learning resources consumed, respectively, by each user in the group of users.

### Claim 14 (depends on 13)

The one or more storage media of claim 13, wherein the instructions, when executed by the one or more processors, further cause:
identifying one or more attribute values associated with the first user, wherein determining the group of users comprises determining that each user in the group of users is associated with the one or more attribute values;
wherein the one or more attribute values indicate a particular industry, a particular job title, a particular level experience, or a particular geographic region.

### Claim 15 (depends on 14)

The one or more storage media of claim 14, wherein:
identifying the one or more attribute values comprises identifying a first profile associated with the first user, wherein the first profile includes data that the first user inserted into the first profile;
determining that each user in the group of users is associated with the one or more attribute values comprises identifying, for each user in the group of users, a second profile that is associated with the said each user and includes data that said each user inserted into the second profile.

### Claim 16 (depends on 14)

The one or more storage media of claim 14, wherein the one or more attribute values are a plurality of attribute values that indicate two or more of the particular industry, the particular job title, the particular level of experience, or the particular geographic region.

### Claim 17 (depends on 11)

The one or more storage media of claim 11, wherein the instructions, when executed by the one or more processors, further cause:
determining that a particular user consumed a first particular learning resource prior to a second particular learning resource;
generating a first learning resource pair that identifies the first particular learning resource and the second particular learning resource;
performing a first aggregation that aggregates the first learning resource pair with one or more other first learning resource pairs;
wherein the first customized learning path is generated based on the first aggregation;
performing a second aggregation that aggregates the first learning resource pair with one or more other second learning resource pairs;
based on the second aggregation, generating a second customized learning path for a second user that is different than the first user.

### Claim 18 (depends on 11)

The one or more storage media of claim 11, wherein the instructions, when executed by the one or more processors, further cause:
determining that a particular user consumed a first particular learning resource prior to a second particular learning resource;
determining whether the particular user consumed a particular amount of the first particular learning resource, wherein the particular amount is less than the entirety of the first particular learning resource;
generating a learning resource pair for the first particular learning resource and the second particular learning resource only in response to determining that the particular amount is greater than a particular threshold.

### Claim 19 (depends on 11)

The one or more storage media of claim 11, wherein the instructions, when executed by the one or more processors, further cause:
determining that a first number of users consumed a second particular learning resource after consuming a first particular learning resource;
determining that a second number of users consumed a third particular learning resource after consuming the first particular learning resource;
based on the first number being greater than the second number, including the second particular learning resource in the first customized learning path instead of the third particular learning resource.

### Claim 20 (depends on 11)

The one or more storage media of claim 11, wherein the instructions, when executed by the one or more processors, further cause:
identifying one or more learning resources that the first user has already consumed;
wherein generating the first customized learning path is also based on the one or more learning resources.
