# US 2024/0265822 A1 · System and method for generating and delivering automated oral summary of learning activities

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

- Number: US 2024/0265822 A1
- Document ID: US20240265822A1
- Status: Published application
- Kind: A1
- Application number: 18/164,412
- Filed: 2023-02-03
- Published: 2024-08-08
- Earliest claimed: 2023-02-03
- Assignees: Chegg, Inc.
- Applicants: Chegg, Inc.
- Inventors: Vincent LE CHEVALIER
- Web page: https://patentgrep.com/patent/US20240265822A1

## CPC

- G09B 5/04: with audible presentation of the material to be studied (sound recording or reproducing G11B)
- 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

In an embodiment, a method for automatically providing an oral summary based on learning activities includes obtaining data associated with one or more learning activities of a user on the online education platform, the data indicating one or more content items associated with the learning activities; extracting one or more concepts associated with the learning activities of the user; generating a text content record based on the one or more extracted concepts; generating an oral summary of the one or more extracted concepts based on the text content record; receiving, from one or more client devices associated with the user, physiological data of the user; detecting a triggering event based at least in part on the physiological data; and in response to detecting the triggering event, sending the oral summary to the one or more client devices for streaming to the user.

## Claims

### Claim 1

A system for automatically providing an oral summary based on learning activities, comprising one or more processors and a non-transitory computer readable medium storing instructions that, when executed by the one or more processors, cause the system to perform operations comprising:
obtaining, from an online education platform, data associated with one or more learning activities of a user on the online education platform, the data indicating one or more content items associated with the learning activities;
extracting one or more concepts associated with the learning activities of the user using a machine-learning model, wherein the machine-learning model is configured to assign the one or more concepts to the one or more content items;
generating a text content record based on the one or more extracted concepts, wherein the text content record comprises the one or more extracted concepts and content related to each of the one or more extracted concepts;
generating an oral summary of the one or more extracted concepts based on the text content record;
receiving, from one or more client devices associated with the user, physiological data of the user;
detecting a triggering event based at least in part on the physiological data; and
in response to detecting the triggering event, sending the oral summary to the one or more client devices for streaming to the user.

### Claim 2 (depends on 1)

The system of claim 1, wherein detecting a triggering event based at least in part on the physiological data comprises:
determining, based on the physiological data, that the user is in at least one of a plurality of target wellness conditions, wherein the target wellness conditions include one or more of:
laying down in a horizontal position;
having no motion for a preset period;
breathing slowly; or
having a slow heart rate.

### Claim 3 (depends on 2)

The system of claim 2, wherein the operations further comprise:
detecting, based at least in part on the physiological data, that at least one of one or more termination events has occurred, wherein the one or more termination events comprise that the user has fallen asleep or that the user has exited the at least one target wellness condition; and
in response to detecting the termination event, sending an instruction to the one or more client devices to terminate the streaming of the oral summary.

### Claim 4 (depends on 1)

The system of claim 1, wherein each of the one or more client devices is configured to collect the physiological data of the user or to play back the oral summary and the one or more client devices comprise at least one of:
a smart watch;
a smart phone;
a connected finger ring;
a connected mattress;
a connected pillow;
a connected speaker; or
a connected audio headset.

### Claim 5 (depends on 1)

The system of claim 1, wherein generating an oral summary of the one or more extracted concepts comprises generating the oral summary based on one or more preference settings of the user, the preference settings comprising at least one of:
a maximum duration of the oral summary;
a maximum number of concepts in the oral summary;
a number of repetitions of the oral summary;
a characteristic of the voice in which the oral summary is rendered;
a speech property of the text-to-speech conversion; or
an acoustic effect to be included in the oral summary.

### Claim 6 (depends on 1)

The system of claim 1, wherein generating a text content record based on the one or more extracted concepts comprises determining an order of the extracted concepts based on at least one of the following factors:
a course associated with each extracted concept;
a timing of a learning activity associated with each extracted concept;
a level of difficulty of each extracted concept; or
a type of content item to which each extracted concept is assigned.

### Claim 7 (depends on 1)

The system of claim 1, wherein the operations further comprise:
receiving one or more calendar settings from the user, the one or more calendar settings specify one or more times for automatically streaming oral summaries to the user;
determining that a current time is one of the one or more times for automatically streaming oral summaries to the user; and
sending the oral summary to the one or more client devices for streaming to the user.

### Claim 8 (depends on 1)

The system of claim 1, wherein generating an oral summary of the one or more extracted concepts based on the text content record comprises:
generating one or more audio records associated with the text content record, wherein each of the one or more audio records is generated by text-to-speech conversion of a portion of the text content record corresponding to one of the one or more extracted concepts and the content related to the one extracted concept; and
interleaving one or more acoustic effects between the one or more audio records to construct the oral summary.

### Claim 9

A computer-implemented method for automatically providing an oral summary based on learning activities, comprising:
obtaining, from an online education platform, data associated with one or more learning activities of a user on the online education platform, the data indicating one or more content items associated with the learning activities;
extracting one or more concepts associated with the learning activities of the user using a machine-learning model, wherein the machine-learning model is configured to assign the one or more concepts to the one or more content items;
generating a text content record based on the one or more extracted concepts, wherein the text content record comprises the one or more extracted concepts and content related to each of the one or more extracted concepts;
generating an oral summary of the one or more extracted concepts based on the text content record;
receiving, from one or more client devices associated with the user, physiological data of the user;
detecting a triggering event based at least in part on the physiological data; and
in response to detecting the triggering event, sending the oral summary to the one or more client devices for streaming to the user.

### Claim 10 (depends on 9)

The method of claim 9, wherein detecting a triggering event based at least in part on the physiological data comprises:
determining, based on the physiological data, that the user is in at least one of a plurality of target wellness conditions, wherein the target wellness conditions include one or more of:
laying down in a horizontal position;
having no motion for a preset period;
breathing slowly; or
having a slow heart rate.

### Claim 11 (depends on 10)

The method of claim 10, further comprising:
detecting, based at least in part on the physiological data, that at least one of one or more termination events has occurred, wherein the one or more termination events comprise that the user has fallen asleep or that the user has exited the at least one target wellness condition; and
in response to detecting the termination event, sending an instruction to the one or more client devices to terminate the streaming of the oral summary.

### Claim 12 (depends on 9)

The method of claim 9, wherein each of the one or more client devices is configured to collect the physiological data of the user or to play back the oral summary and the one or more client devices comprise at least one of:
a smart watch;
a smart phone;
a connected finger ring;
a connected mattress;
a connected pillow;
a connected speaker; or
a connected audio headset.

### Claim 13 (depends on 9)

The method of claim 9, wherein generating an oral summary of the one or more extracted concepts comprises generating the oral summary based on one or more preference settings of the user, the preference settings comprising at least one of:
a maximum duration of the oral summary;
a maximum number of concepts in the oral summary;
a number of repetitions of content in the oral summary;
a characteristic of a voice in which the oral summary is rendered;
a speech property of the text-to-speech conversion; or
an acoustic effect to be included in the oral summary.

### Claim 14 (depends on 9)

The method of claim 9, wherein generating a text content record based on the one or more extracted concepts comprises determining an order of the extracted concepts based on at least one of the following factors:
a course associated with each extracted concept;
a timing of a learning activity associated with each extracted concept;
a level of difficulty of each extracted concept; or
a type of content item to which each extracted concept is assigned.

### Claim 15 (depends on 9)

The method of claim 9, further comprising:
receiving one or more calendar settings from the user, the one or more calendar settings specify one or more times for automatically streaming oral summaries to the user;
determining that a current time is one of the one or more times for automatically streaming oral summaries to the user; and
sending the oral summary to the one or more client devices for streaming to the user.

### Claim 16 (depends on 9)

The method of claim 9, wherein generating an oral summary of the one or more extracted concepts based on the text content record comprises:
generating one or more audio records associated with the text content record, wherein each of the one or more audio records is generated by text-to-speech conversion of a portion of the text content record corresponding to one of the one or more extracted concepts and the content related to the one extracted concept; and
interleaving one or more acoustic effects between the one or more audio records to construct the oral summary.

### Claim 17

A non-transitory computer-readable storage medium for automatically providing an oral summary based on learning activities, configured with instructions executable by one or more processors to cause the one or more processors to perform operations comprising:
obtaining, from an online education platform, data associated with one or more learning activities of a user on the online education platform, the data indicating one or more content items associated with the learning activities;
extracting one or more concepts associated with the learning activities of the user using a machine-learning model, wherein the machine-learning model is configured to assign the one or more concepts to the one or more content items;
generating a text content record based on the one or more extracted concepts, wherein the text content record comprises the one or more extracted concepts and content related to each of the one or more extracted concepts;
generating an oral summary of the one or more extracted concepts based on the text content record;
receiving, from one or more client devices associated with the user, physiological data of the user;
detecting a triggering event based at least in part on the physiological data; and
in response to detecting the triggering event, sending the oral summary to the one or more client devices for streaming to the user.

### Claim 18 (depends on 17)

The medium of claim 17, wherein detecting a triggering event based at least in part on the physiological data comprises:
determining, based on the physiological data, that the user is in at least one of a plurality of target wellness conditions, wherein the target wellness conditions include one or more of:
laying down in a horizontal position;
having no motion for a preset period;
breathing slowly; or
having a slow heart rate.

### Claim 19 (depends on 18)

The medium of claim 18, further comprising:
detecting, based at least in part on the physiological data, that at least one of one or more termination events has occurred, wherein the one or more termination events comprise that the user has fallen asleep or that the user has exited the at least one target wellness condition; and
in response to detecting the termination event, sending an instruction to the one or more client devices to terminate the streaming of the oral summary.

### Claim 20 (depends on 17)

The medium of claim 17, wherein generating an oral summary of the one or more extracted concepts based on the text content record comprises:
generating one or more audio records associated with the text content record, wherein each of the one or more audio records is generated by text-to-speech conversion of a portion of the text content record corresponding to one of the one or more extracted concepts and the content related to the one extracted concept; and
interleaving one or more acoustic effects between the one or more audio records to construct the oral summary.
