# US 12,183,217 B2 · Language learning method, electronic device executing the method, and storage medium storing the method program files

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

- Number: US 12,183,217 B2
- Document ID: US12183217B2
- Status: Granted
- Kind: B2
- Application number: 17/198,331
- Filed: 2021-03-11
- Published: 2021-07-01
- Granted: 2024-12-31
- Earliest claimed: 2018-09-11
- Assignees: Guangdong Zhimeiyuntu Tech. Corp., Ltd.
- Applicants: Guangdong Zhimeiyuntu Tech. Corp., Ltd.
- Inventors: Libang Deng
- Web page: https://patentgrep.com/patent/US12183217B2

## CPC

- G09B 5/04: with audible presentation of the material to be studied (sound recording or reproducing G11B)
- G06F 3/167: {Audio in a user interface, e.g. using voice commands for navigating, audio feedback}
- G06F 18/21: Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06N 3/045: Combinations of networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/08: Learning methods
- G06N 3/09: Supervised learning
- G06V 10/764: using classification, e.g. of video objects
- G06V 10/82: using neural networks
- G06V 20/20: in augmented reality scenes
- G09B 7/04: characterised by modifying the teaching programme in response to a wrong answer, e.g. repeating the question or supplying a further explanation
- G09B 7/06: of the multiple-choice answer-type, i.e. where a given question is provided with a series of answers and a choice has to be made from the answers
- G09B 19/04: Speaking (with audible presentation of the material to be studied G09B5/04)
- G09B 19/06: Foreign languages (with audible presentation of material to be studied G09B5/04)
- 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)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

The disclosure provides a language learning method including task feedback and image check. The task feedback includes playing, by a sound module according to a learning instruction, the vocal content of a word, and taking, by a user, an object image corresponding to the word through a camera module of a terminal device. The image check includes receiving, by a processor module, the object image; identifying the object image according to a preestablished identification model; acquiring an identification result and comparing the identification result with the word; judging whether the object image taken by the user is correct; and feeding back, by a display module or the sound module, a judgment result.

## Claims

### Claim 1

A method, comprising:
playing, by a sound module according to a learning instruction, a vocal content of a word in a second language;
prompting a user to take an object image corresponding to the word through a camera module of a terminal device and upload the object image;
if the object image is uploaded:
receiving, by a processor module, the object image;
identifying the object image according to identification model having standard features for the word, by extracting features from the object image and comparing the extracted features from the object image with the standard features for the word; and judging whether the object image taken by the user is correct;
if the object image taken by the user is correct, feeding back an award to the user by a display module or the sound module; and
if the object image taken by the user is incorrect, feeding backing a correct image of an object corresponding to the word to the user, and/or prompting the user to take an image again; and
if no object image is uploaded during a set period of time, feeding back to the user a vocal content corresponding to the word in a first language.

### Claim 2 (depends on 1)

The method of claim 1, further comprising establishing the identification model by means of:
comprising acquiring a plurality of object images corresponding to a plurality of words in different light from various angles;
learning and training by a convolutional neural network algorithm, and establishing the identification model of the plurality of words corresponding to the plurality of object images; and
storing the identification model into the terminal device or a cloud storage module.

### Claim 3 (depends on 2)

The method of claim 2, wherein establishing the identification model comprises graying each object image, extracting features of each object image, extracting a standard template by recognition training, and creating a standard feature library.

### Claim 4 (depends on 3)

The method of claim 3, wherein the plurality of object images for each word comprise a plurality of standard templates.

### Claim 5 (depends on 3)

The method of claim 3, wherein graying each object image comprises processing objects in each object image into a uniform specification by centroid alignment, linear interpolation, and enlargement.

### Claim 6 (depends on 1)

The method of claim 1, further comprising replaying the vocal content of the word, and the vocal content of an example sentence comprising the word through the sound module according to a user's request.

### Claim 7 (depends on 1)

An electronic device, comprising a memory, processor, and computer program stored in the memory and executed by the processor to conduct the method of claim 1; wherein when the processor executes the computer program, the method is implemented.

### Claim 8 (depends on 1)

A computer-readable storage medium comprising a computer program for conducting the method of claim 1; when executed by a processor, the computer program performs the method.