KR20230124237A - Method for progressing non face to face exercise lecture using speech recogntion - Google Patents

Abstract

According to the present invention, a method for progressing a non-face-to-face exercise lecture through the voice recognition comprises: a step of tracking the voice of a user following a non-face-to-face exercise service or tracking the voice of a lecturer progressing the non-face-to-face exercise service in real time; a step of determining whether a preset word is recognized from the voice of the user or the voice of the lecturer tracked in real time; a step of, if the preset word is recognized, performing a preset function in accordance with the relevant word; and a step of providing the execution result of the preset function to a user device or a lecturer device. Therefore, the present invention is able to allow a lecturer and a student to more conveniently communicate with each other in a non-face-to-face real-time exercise lecture and prevent the inconvenience of having to use a device and chat by using a hand, thereby improving user satisfaction in a non-face-to-face exercise lecture.

Description

How to conduct a non-face-to-face exercise lecture through voice recognition {METHOD FOR PROGRESSING NON FACE TO FACE EXERCISE LECTURE USING SPEECH RECOGNTION}

The present invention relates to a non-face-to-face exercise lecture method through voice recognition that can conveniently communicate between an instructor and students through voice recognition in a non-face-to-face real-time exercise lecture and conduct an exercise lecture.

<R&D project supporting this invention>

-. Assignment number: CY201053

-. Institution specializing in task management: Seoul Business Agency

-. Research project name: 2020 post-corona specialized artificial intelligence (AI) technology commercialization support project

-. Research project title: Non-face-to-face education service for musculoskeletal treatment/prevention through artificial intelligence

-. Name of the organization performing the task: Wehild Co., Ltd.

Recently, as interest in health increases, various exercises for health, such as fitness, yoga, and Pilates, are spreading widely. Of course, most people are prepared to take the time and money to take care of their health. However, the reality is that it is not easy for most people to take a separate time and go to a place that helps them manage their health and exercise.

In particular, most of these exercises are performed while registering at a gym or sports center and receiving guidance from an instructor, so it is difficult for people who are usually pressed for time to take classes, and excessive costs are required to visit a gym and receive personal training. there was.

Therefore, recently, exercise programs such as broadcasts or apps that help individuals exercise at the office or at home have been developed and spread. Users using these exercise programs can follow the exercise while watching exercise broadcasting and exercise service images provided by expert instructors.

In addition, these exercise programs provide various types of exercise motions to users through exercise service images, and provide exercise images so that they can repeatedly follow certain exercise motions.

However, in order to ask a question while watching an exercise lecture in real time, the user has to hold the device with his hand and input and send chatting contents, so there is a problem in that a part of the exercise being conducted by the instructor may be missed. That is, when a user participates in an exercise program, in order to ask a question during exercise, the user has to chat using the device, so it is difficult for the user to communicate with the instructor.

In addition, from the instructor's point of view, it is difficult to quickly answer users' questions while conducting exercise lectures in real time, and it is difficult to deliver accurate exercise movements due to non-face-to-face.

Matters described in this background art section are prepared to enhance understanding of the background of the invention, and may include matters that are not prior art already known to those skilled in the art to which this technique belongs.

The present invention sets specific words and functions in advance, tracks the user's voice in non-face-to-face exercise lectures, and when a specific word set in advance is recognized, the function according to the word is performed and the exercise lecture can be performed through voice recognition. I would like to suggest a method for conducting a face-to-face exercise lecture.

In addition, in the present invention, when a specific word related to a question is recognized from a user's voice in a non-face-to-face exercise service, the user's voice after the word is recognized is converted into text and provided to the instructor through non-face-to-face speech recognition. I would like to suggest a method for conducting exercise lectures.

A method for conducting a non-face-to-face exercise lecture through voice recognition according to an embodiment of the present invention tracks the voice of a user following a non-face-to-face exercise service or tracks the voice of an instructor conducting the non-face-to-face exercise service in real time; Determining whether a preset word is recognized in the user's voice or the instructor's voice tracked in real time, performing a set function according to the word when the preset word is recognized, and performing a set function according to the set function and providing a result of the performance to a user device or an instructor device.

The set word may include at least one of words related to a question, rest time, exercise speed, or exercise posture.

When the set word is recognized in the user's voice, and the recognized word is a word related to at least one of a question, break time, exercise speed, and exercise posture, the user's voice is converted into text in real time, and the converted The method may further include displaying the text in a chat window of the instructor device in real time.

If the word recognized by the user is a word related to a question, extracting at least one core keyword from the user's question content recognized after the question and the word are recognized, and the number of questions related to the extracted core keyword The method may further include extracting example answers from the database and providing the extracted example answers to a user device or an instructor device.

When the set word is recognized in the voice of the user or the instructor, and the recognized word is a word related to exercise posture, an image performing an operation related to the exercise posture is extracted from the database, and the extracted image is displayed on the user device or It may further include displaying on the instructor device.

Prior to the step of tracking the voices in real time, registering the voices of the user and the instructor may include analyzing and registering a frequency band, gender, timbre, and voice height of the user's voice or the instructor's voice.

In the real-time tracking of the voice, noise different from the registered voice may be removed by comparing the real-time tracked voice with a frequency band, gender, timbre, or voice height of the registered voice.

An apparatus for conducting non-face-to-face exercise lectures through voice recognition according to an embodiment of the present invention includes a voice tracking module that tracks in real time the voice of a user following a non-face-to-face exercise service or the voice of an instructor conducting a non-face-to-face exercise service, A word recognition module that determines whether a preset word is recognized in the user's voice or the instructor's voice tracked by, and when a preset word is recognized, performs a set function according to the word, and performs a set function according to the set function. It includes a control module that controls to provide performance results to user devices or instructor devices.

According to the present invention, the voice of a user following a non-face-to-face exercise service is tracked or the voice of an instructor performing the non-face-to-face exercise service is tracked in real time, and a preset word is tracked in real time in the user's voice or the instructor's voice. is recognized, by performing the set function according to the word, providing an environment for more convenient communication between the instructor and the students in the non-face-to-face real-time exercise lecture.

In addition, in the present invention, when the set word is recognized in the user's voice and the recognized word is a word related to at least one of a question, rest time, exercise speed, and exercise posture, the user's voice is converted into text in real time. And, by displaying the converted text in real time in the chat window of the instructor's device, you can prevent the inconvenience of using the device one by one and chatting with your hands, and you can quickly deliver questions by voice, so you don't miss the exercise the instructor is doing. It provides an environment that can be followed well and prevents user's voice exposure.

In addition, the present invention extracts at least one core keyword from the user's question content when the word recognized by the user is a word related to a question, and extracts an example of an answer to the question related to the extracted core keyword from a database. By providing it to the instructor device, quick questions and quick feedback between students and instructors are possible, and an environment in which convenient two-way communication between students and instructors is possible is provided.

In addition, in the present invention, when a word recognized in the voice of a user or an instructor is a word related to an exercise posture, an image performing an operation related to the exercise posture is extracted from a database, and the extracted image is displayed on a user device or an instructor device. By doing so, an environment in which user satisfaction can be improved by easily sharing exercise motions is provided.

In addition, the present invention registers the voices of the user and the instructor, analyzes and registers the frequency band, gender, timbre, and voice height of the user's voice or the instructor's voice, and registers the voice tracked in real time to the frequency band and gender of the registered voice. , timbre, or voice height to remove noise different from the registered voice, thereby providing an environment capable of improving the voice recognition rate.

1 is a diagram briefly showing a non-face-to-face exercise lecture progress system through voice recognition according to an embodiment of the present invention.
2 is a block diagram showing a schematic configuration of a non-face-to-face exercise lecture progressing device through voice recognition according to an embodiment of the present invention.
3 shows the process of tracking a user's voice in a non-face-to-face exercise lecture progress system through voice recognition and performing a non-face-to-face exercise lecture when a specific word is recognized according to an embodiment of the present invention. It is a simplified flow chart.
4 shows a process in which a non-face-to-face exercise lecture progressing device tracks a user's voice to recognize a word, extracts a corresponding exercise posture image when it is a word related to an exercise posture, and provides it to the user according to an embodiment of the present invention. It is a simplified flow chart.
5 is a diagram illustrating a user's question content converted into text and provided to a chat window of an instructor device when a specific word related to a question is recognized from a user according to an embodiment of the present invention, and key keywords are extracted from the user's question content. A flowchart briefly illustrating a process of extracting examples of answers to questions related to core keywords from a database and providing them to a user device.

Hereinafter, a preferred embodiment of the present invention will be described in detail based on the accompanying drawings.

Prior to this, the embodiments described in this specification and the configurations shown in the drawings are only one of the most preferred embodiments of the present invention and do not represent all of the technical ideas of the present invention. It should be understood that there may be many equivalents and variations.

Hereinafter, with reference to the accompanying drawings, embodiments of the present invention will be described in detail so that those skilled in the art can easily carry out the present invention. However, the present invention may be embodied in many different forms and is not limited to the embodiments described herein. And in order to clearly explain the present invention in the drawings, parts irrelevant to the description are omitted, and similar reference numerals are attached to similar parts throughout the specification.

Since the size and thickness of each component shown in the drawings are arbitrarily shown for convenience of description, the present invention is not necessarily limited to what is shown in the drawings, and the thickness is enlarged to clearly express various parts and regions.

Throughout the specification, when a certain component is said to "include", it means that it may further include other components without excluding other components unless otherwise stated. In addition, terms such as “… unit”, “… unit”, and “module” described in the specification mean a unit that processes at least one function or operation, which may be implemented as hardware or software or a combination of hardware and software. there is.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by a person of ordinary skill in the art to which the embodiment belongs. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related art, and unless explicitly defined in the present application, they should not be interpreted in an ideal or excessively formal meaning. don't

In addition, in describing the embodiments, if it is determined that a detailed description of a related known technology may unnecessarily obscure the gist of the embodiment, the detailed description will be omitted.

Now, with reference to FIGS. 1 to 5, a system for conducting a non-face-to-face exercise lecture through voice recognition according to an embodiment of the present invention and a method for conducting a non-face-to-face exercise lecture through voice recognition using the same will be described in detail.

1 is a diagram briefly showing a non-face-to-face exercise lecture progress system through voice recognition according to an embodiment of the present invention. At this time, the non-face-to-face exercise lecture progress system 10 through voice recognition only shows a schematic configuration necessary for explanation according to the embodiment of the present invention, but is not limited to this configuration.

1, the non-face-to-face exercise lecture progress system 10 through voice recognition according to an embodiment of the present invention uses the non-face-to-face exercise lecture lecture device 100 to listen to the user's voice following the non-face-to-face exercise service. It is possible to track the voice of an instructor who is tracking or performing the non-face-to-face exercise service in real time, and determine whether a preset word is recognized in the voice of the user or the voice of the instructor that is tracked in real time. In addition, the non-face-to-face exercise lecture progress system 10 through voice recognition according to an embodiment of the present invention performs the function set according to the word when a preset word is recognized from the user or instructor, and the corresponding execution result may be provided to the user device or instructor device.

The non-face-to-face exercise lecture system 10 through voice recognition according to an embodiment of the present invention may include a user device 20, a non-face-to-face exercise lecture lecture device 100, and an instructor device 30.

The non-face-to-face exercise lecture progressing device 100 tracks the voice of the user who follows the non-face-to-face exercise service through the user device 20 or the instructor device 30 or tracks the voice of the instructor conducting the non-face-to-face exercise service in real time. can be tracked with

The non-face-to-face exercise lecture progressing device 100 may compare the voice tracked in real time with the frequency band, gender, timbre, or voice height of the registered voice to remove noise different from the registered voice.

In addition, the non-face-to-face exercise lecture progressing device 100 determines whether a preset word is recognized in the user's voice or the instructor's voice tracked in real time, and when the preset word is recognized, according to the corresponding word The set function may be performed, and the result of the set function may be provided to the user device 20 or the instructor device 30 . Here, the set word may include at least one of words related to a question, rest time, exercise speed, or exercise posture.

For example, the non-face-to-face exercise lecture progressing device 100 recognizes the set word in the user's voice, and the recognized word is a word related to at least one of a question, break time, exercise speed, and exercise posture, The user's voice content may be converted into text in real time, and the converted text may be displayed in the chat window of the instructor device 30 in real time.

In addition, when the word recognized by the user is a word related to a question, the non-face-to-face exercise lecture progressing device 100 selects at least one key keyword from the user's question content recognized after the question and word are recognized. It is possible to extract, extract examples of answers to questions related to the extracted core keywords from the database, and provide the extracted examples of answers to the user device 20 or the instructor device 30 .

In addition, the non-face-to-face exercise lecture progressing device 100 recognizes the set word in the voice of the user or the instructor, and when the recognized word is a word related to the exercise posture, an image of performing an operation related to the exercise posture may be extracted from the database, and the extracted image may be displayed on the user device 20 or the instructor device 30.

Therefore, the present invention tracks the voice of a user following a non-face-to-face exercise service or tracks the voice of an instructor performing the non-face-to-face exercise service in real time, and tracks a preset word in the real-time tracked user's voice or the instructor's voice is recognized, by performing the set function according to the word, providing an environment for more convenient communication between the instructor and the students in the non-face-to-face real-time exercise lecture.

2 is a block diagram showing a schematic configuration of a non-face-to-face exercise lecture progressing device through voice recognition according to an embodiment of the present invention. At this time, the user device 100 only shows schematic configurations necessary for explanation according to the embodiment of the present invention, but is not limited to these configurations.

Referring to FIG. 2, the user device 100 according to an embodiment of the present invention includes a control module 110, a setting module 120, a voice tracking module 130, a word recognition module 140, and an exercise lecture progress module. 150, a transmission/reception module 160, and a database 170.

The control module 110 tracks the user's voice or the instructor's voice in real time in the non-face-to-face exercise service, and when a preset word is recognized in the user's voice or the instructor's voice tracked in real time, the corresponding It is possible to control the operation of each part to perform a function set according to a word.

The setting module 120 may set a specific word in advance and set a function according to the set word. Here, the set word may include at least one of words related to a question, rest time, exercise speed, or exercise posture.

In addition, the setting module 120 registers the voices of the user and the instructor, and may analyze and register the frequency band, gender, timbre, and voice height of the user's voice or the instructor's voice.

The setting module 120 includes a user voice registration unit 122 and a word setting unit 124 according to an embodiment of the present invention.

The user voice registration unit 122 may analyze and register the frequency band, gender, timbre, and voice height of the user's voice or instructor's voice. Accordingly, the present invention can improve the voice recognition rate by effectively removing noise such as music sounds or other people's voices generated in the surroundings when tracking a user's voice.

The word setting unit 124 may set a specific word in advance and set a function according to the set word. The set word may include at least one of words related to a question, rest time, exercise speed, or exercise posture.

The voice tracking module 130 may track the voice of a user following the non-face-to-face exercise service or the voice of an instructor performing the non-face-to-face exercise service in real time.

Also, the voice tracking module 130 compares the tracked voice in real time with the frequency band, gender, timbre, or voice height of the registered voice to remove noise different from the registered voice.

The word recognition module 140 may determine whether a preset word is recognized in the user's voice or the instructor's voice tracked in real time by the voice tracking module 130 .

When a preset word is recognized in the word recognition module 140, the exercise lecture proceeding module 150 may perform a function set according to the corresponding word. In addition, the exercise lecture progress module 150 may provide the user device 20 or instructor device 30 with a result of performing the set function through the transmission/reception module 160 .

For example, the exercise lecture progress module 150 recognizes the set word in the user's voice, and the recognized word is a word related to at least one of a question, break time, exercise speed, and exercise posture, the user It is possible to convert the voice contents into text in real time and display the converted text in the chat window of the instructor device 30 in real time.

In addition, when the set word is recognized in the voice of the user or the instructor and the recognized word is a word related to the exercise posture, the exercise lecture progress module 150 records an image of performing an operation related to the exercise posture in a database. It can be extracted from, and the extracted image can be displayed on the user device 20 or the instructor device 30.

The exercise lecture progress module 150 includes a text conversion unit 152 and an extraction unit 154 according to an embodiment of the present invention.

The text conversion unit 152 recognizes the set word in the user's voice, and when the recognized word is a word related to at least one of a question, a break time, an exercise speed, and an exercise posture, the text conversion unit 152 converts the user's voice content into an STT. It can be converted into text in real time using the (Speech-to-text) method.

For example, when the user says the word 'question', the text conversion unit 152 may start recording from the next sentence spoken by the user and convert the recorded voice into text in real time.

When the word recognized by the user is a word related to a question, the extractor 154 may extract at least one key keyword from the content of the user's question recognized after the question and word are recognized.

In addition, the extractor 154 may extract examples of answers to questions related to the extracted core keywords from the database and provide the extracted examples of answers to the user device 20 or the instructor device 30 .

In addition, when the set word is recognized in the voice of the user or the instructor and the recognized word is a word related to the exercise posture, the extractor 154 extracts an image of performing an operation related to the exercise posture from the database. And, the extracted image can be displayed on the user device 20 or the instructor device 30. At this time, the present invention can simultaneously display the video of the non-face-to-face exercise lecture and the exercise posture image extracted from the database.

The database 170 may store voices of users and instructors, and may store preset words and functions of each word. In addition, the database 170 may store examples of answers according to specific keywords and images related to motions of specific exercise postures.

3 shows the process of tracking a user's voice in a non-face-to-face exercise lecture progress system through voice recognition and performing a non-face-to-face exercise lecture when a specific word is recognized according to an embodiment of the present invention. This is a simplified flow chart. At this time, the following flowcharts will be described using the same reference numerals in association with the configurations of FIGS. 1 and 2 .

Referring to FIG. 3, the non-face-to-face exercise lecture progress system 10 through voice recognition according to an embodiment of the present invention sets specific words to be tracked in the voices of users and instructors, and sets functions related to the words. It can (S102). Here, the specific words may include at least one of words related to a question, rest time, exercise speed, or exercise posture.

In addition, the non-face-to-face exercise lecture progress system 10 through voice recognition according to an embodiment of the present invention tracks the voice of a user who follows the non-face-to-face exercise service or tracks the voice of an instructor conducting the non-face-to-face exercise service in real time. It can be tracked as (S104).

In addition, the non-face-to-face exercise lecture progress system 10 through voice recognition according to an embodiment of the present invention can determine whether a preset word is recognized in the user's voice or the instructor's voice tracked in real time. (S106).

In addition, when a preset word is recognized, the non-face-to-face exercise lecture progress system 10 through voice recognition according to an embodiment of the present invention extracts a function set according to the word and performs the corresponding function. (S108 and S110).

For example, in the non-face-to-face exercise lecture progress system 10 through voice recognition according to an embodiment of the present invention, the set word is recognized in the user's voice tracked through the user device 20, and the recognized word If is a word related to at least one of a question, break time, exercise speed, and exercise posture, the user's voice is converted into text in real time, and the converted text is displayed in the chat window of the instructor device 30 in real time. can

4 shows a process in which a non-face-to-face exercise lecture progressing device tracks a user's voice to recognize a word, extracts a corresponding exercise posture image when it is a word related to an exercise posture, and provides it to the user according to an embodiment of the present invention. This is a simplified flow chart. At this time, the following flowcharts will be described using the same reference numerals in association with the configurations of FIGS. 1 and 2 .

Referring to FIG. 4, the non-face-to-face exercise lecture progress system 10 through voice recognition according to an embodiment of the present invention tracks the user's voice following the non-face-to-face exercise service or an instructor who conducts the non-face-to-face exercise service. The voice of can be tracked in real time (S202).

In addition, the non-face-to-face exercise lecture progress system 10 through voice recognition according to an embodiment of the present invention can determine whether a preset word is recognized in the user's voice or the instructor's voice tracked by time. (S204).

For example, in the non-face-to-face exercise lecture progress system 10 through voice recognition according to an embodiment of the present invention, the set word is recognized in the voice of the user or the instructor, and the recognized word is a word related to exercise posture. In the case of , an image performing an operation related to the exercise posture may be extracted from the database (S206).

In addition, the non-face-to-face exercise lecture progress system 10 through voice recognition according to an embodiment of the present invention may display the extracted image on the user device 20 or the instructor device 30 (S208).

5 is a diagram illustrating a user's question content converted into text and provided to a chat window of an instructor device when a specific word related to a question is recognized from a user according to an embodiment of the present invention, and key keywords are extracted from the user's question content. A flowchart briefly illustrating a process of extracting examples of answers to questions related to core keywords from a database and providing them to a user device. At this time, the following flowcharts will be described using the same reference numerals in association with the configurations of FIGS. 1 and 2 .

5, the non-face-to-face exercise lecture progress system 10 through voice recognition according to an embodiment of the present invention registers the voices of the user and the instructor, but the frequency band, gender, tone, And it is possible to register the unique voice of the user and instructor by analyzing the voice height (S302).

In addition, the non-face-to-face exercise lecture progress system 10 through voice recognition according to an embodiment of the present invention compares the voice tracked in real time with the frequency band, gender, tone, or voice height of the registered voice, Noise different from voice can be removed (S304).

In addition, the non-face-to-face exercise lecture progress system 10 through voice recognition according to an embodiment of the present invention can determine whether a preset word is recognized in the user's voice or the instructor's voice tracked in real time. (S306).

For example, when the non-face-to-face exercise lecture progress system 10 through voice recognition according to an embodiment of the present invention recognizes the word 'question' from the user, the user's voice content recognized later by the user may be converted into text in real time, and the converted text may be displayed in real time in the chat window of the instructor device 30 (S308 to S312).

In addition, the non-face-to-face exercise lecture progress system 10 through voice recognition according to an embodiment of the present invention, when the word recognized by the user is a word related to a question, the question and word recognized after being recognized At least one core keyword may be extracted from the user's question content (S314).

In addition, the non-face-to-face exercise lecture progress system 10 through voice recognition according to an embodiment of the present invention may extract examples of answers to questions related to the extracted core keywords from the database (S316).

In addition, the non-face-to-face exercise lecture progress system 10 through voice recognition according to an embodiment of the present invention may provide extracted examples of answers to the chat window of the user device 20 or instructor device 30 (S318). ).

As such, the method for conducting a non-face-to-face exercise lecture through voice recognition according to an embodiment of the present invention tracks the voice of a user following a non-face-to-face exercise service or tracks the voice of an instructor conducting the non-face-to-face exercise service in real time. And, if a preset word is recognized in the user's voice or the instructor's voice tracked in real time, the function set according to the word is performed, thereby creating an environment for more convenient communication between the instructor and the students in non-face-to-face real-time exercise lectures. to provide.

In addition, in the present invention, when the set word is recognized in the user's voice and the recognized word is a word related to at least one of a question, rest time, exercise speed, and exercise posture, the user's voice is converted into text in real time. And, by displaying the converted text in real time in the chat window of the instructor's device, you can prevent the inconvenience of using the device one by one and chatting with your hands, and you can quickly deliver questions by voice, so you don't miss the exercise the instructor is doing. It can be followed well and provides an environment that can prevent user's voice exposure.

In addition, the present invention extracts at least one core keyword from the user's question content when the word recognized by the user is a word related to a question, and extracts an example of an answer to the question related to the extracted core keyword from a database. By providing it to the instructor device, quick questions and quick feedback between students and instructors are possible, and an environment in which convenient two-way communication between students and instructors is possible is provided.

In addition, in the present invention, when a word recognized in the voice of a user or an instructor is a word related to an exercise posture, an image performing an operation related to the exercise posture is extracted from a database, and the extracted image is displayed on a user device or an instructor device. By doing so, an environment in which user satisfaction can be improved by easily sharing exercise motions is provided.

In addition, the present invention registers the voices of the user and the instructor, analyzes and registers the frequency band, gender, timbre, and voice height of the user's voice or the instructor's voice, and registers the voice tracked in real time to the frequency band and gender of the registered voice. , timbre, or voice height to remove noise different from the registered voice, thereby providing an environment capable of improving the voice recognition rate.

The embodiments of the present invention described above are not implemented only through devices and methods, and may be implemented through programs that realize functions corresponding to the configuration of the embodiments of the present invention or a recording medium on which the programs are recorded. Such a recording medium may be executed in a user device as well as a server.

Although the embodiments of the present invention have been described in detail above, the scope of the present invention is not limited thereto, and various modifications and improvements made by those skilled in the art using the basic concept of the present invention defined in the following claims are also included in the scope of the present invention. that fall within the scope of the right.

Claims (8)

Tracking the voice of a user following a non-face-to-face exercise service or tracking the voice of an instructor performing the non-face-to-face exercise service in real time;
Determining whether a preset word is recognized in the user's voice or the instructor's voice tracked in real time;
If a preset word is recognized, performing a set function according to the word; and
Providing a result of performing the set function to a user device or instructor device
Non-face-to-face exercise lecture method through voice recognition that includes. In paragraph 1,
The set words are
A non-face-to-face exercise lecture method through voice recognition, characterized in that it includes at least one of words related to questions, break time, exercise speed, or exercise posture. In paragraph 1,
When the set word is recognized in the user's voice, and the recognized word is a word related to at least one of a question, break time, exercise speed, and exercise posture, the user's voice is converted into text in real time, and the converted The step of displaying the text in real time in the chat window of the instructor's device
How to proceed with a non-face-to-face exercise lecture through voice recognition further comprising. In paragraph 1,
If the word recognized by the user is a word related to a question, extracting at least one key keyword from the user's question content recognized after the question and word are recognized; and
Extracting examples of answers to questions related to the extracted key keywords from the database, and providing the extracted examples of answers to a user device or instructor device
How to proceed with a non-face-to-face exercise lecture through voice recognition further comprising. In paragraph 1,
When the set word is recognized in the voice of the user or the instructor, and the recognized word is a word related to exercise posture, an image performing an operation related to the exercise posture is extracted from the database, and the extracted image is displayed on the user device or Steps to display on instructor device
How to proceed with a non-face-to-face exercise lecture through voice recognition further comprising. In paragraph 1,
Prior to the step of tracking the voice in real time,
Registering the user's and instructor's voices, analyzing and registering the frequency band, gender, timbre, and voice height of the user's or instructor's voice
Non-face-to-face exercise lecture method through voice recognition that includes. In paragraph 6,
The step of tracking the voice in real time,
A non-face-to-face exercise lecture method through voice recognition, characterized in that the voice tracked in real time is compared with the frequency band, gender, timbre, or voice height of the registered voice to remove noise different from the registered voice. A voice tracking module that tracks the voice of the user following the non-face-to-face exercise service or the voice of the instructor conducting the non-face-to-face exercise service in real time;
A word recognition module for determining whether a preset word is recognized in the user's voice or the instructor's voice tracked in real time; and
When a preset word is recognized, a control module that controls to perform a set function according to the word and provide a result of the set function to a user device or instructor device.
Non-face-to-face exercise lecture progress device through voice recognition that includes.