CN114093221A

CN114093221A - Platform system for creating spoken language evaluation exercises

Info

Publication number: CN114093221A
Application number: CN202010856175.8A
Authority: CN
Inventors: 赵凯
Original assignee: Individual
Current assignee: Individual
Priority date: 2020-08-24
Filing date: 2020-08-24
Publication date: 2022-02-25

Abstract

The invention discloses a platform system for creating spoken language evaluation exercises, which comprises a media device, wherein the media device comprises: the input module, input module include microphone, touch screen and camera, analysis module include server equipment and wireless communication module, output module includes CPU, hard disk equipment and loudspeaker.

Description

Platform system for creating spoken language evaluation exercises

Technical Field

The invention relates to the field of audio learning, in particular to a platform system for creating spoken language evaluation exercises.

Background

In the existing market, a common language learning device is a learning machine device, corresponding course information is obtained by manually reading on a book or connecting the learning machine device with the internet, and the course information is played and read on the learning machine to achieve the effect of voice learning.

The oral assessment product in the existing market adopts course chapter content, the content is fixed along with a course system, the assessment practice is provided for a user, the content is not personalized enough, and the oral assessment product cannot be flexibly matched with course progress and student capability level.

Disclosure of Invention

The technical problem to be solved by the invention is to overcome the defects of the prior art and provide a platform system for creating spoken language evaluation exercises.

In order to solve the technical problems, the invention provides the following technical scheme:

the invention relates to a platform system for creating spoken language evaluation exercises, which comprises a media device, wherein the media device comprises:

the input module comprises a microphone, a touch screen and a camera and is used for inputting characters, voice and pictures;

the analysis module comprises server equipment and a wireless communication module and is used for analyzing and matching the target spoken language audio;

and the output module comprises a CPU, hard disk equipment and a loudspeaker and is used for scoring the recorded voice and outputting scoring information.

As a preferred technical solution of the present invention, the input module and the output module are electrically connected, and the input module and the output module are fixedly disposed adjacent to each other.

As a preferred technical scheme of the invention, the input module internally comprises an OCR character recognition algorithm which is used for converting information of manual input, voice input and picture recognition into text information and displaying the text information on the touch screen.

As a preferred technical solution of the present invention, the server device includes:

the LDA model information classification algorithm is used for grouping the data stored in the server equipment and forming an independent database in the server equipment;

and the DSSM matching algorithm is used for matching the input text information in a database in the server equipment so as to output the same text information and output the audio corresponding to the text information.

As a preferred technical solution of the present invention, the output module plays the corresponding audio information, and the output module includes an FFT algorithm for comparing the similarity between the audio of the read-along recording and the audio output by the DSSM matching algorithm, and generating a score.

Compared with the prior art, the invention has the following beneficial effects:

1: the evaluation content of the invention is flexible, and the teacher, the student or the parent can freely create the question for practice according to the self ability level condition of the user, thereby having stronger DIY effect.

2: the invention has various creation modes, and the creation mode of the subject can comprise manual input, voice input and picture recognition means, and the exercise text is quickly created through OCR character recognition and other modes.

3: the invention can record or synthesize the demonstration sound by voice, students can listen to the demonstration sound according to the created content and record the voice by themselves, and finally the student can compare the demonstration sound with the recorded voice during self-exercise to evaluate the score.

Drawings

The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:

FIG. 1 is a schematic overall flow diagram of the present invention;

FIG. 2 is a schematic block diagram of the present invention;

Detailed Description

The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.

Example 1

As shown in fig. 1-2, the present invention provides a platform system for creating a spoken language assessment exercise, comprising a media device, wherein the media device comprises:

The input module and the output module are electrically connected and are fixedly arranged adjacently.

The input module internally comprises an OCR character recognition algorithm which is used for converting information of manual input, voice input and picture recognition into text information and displaying the text information on the touch screen.

The server device includes:

And the output module plays the corresponding audio information, and the output module comprises an FFT algorithm and is used for carrying out similarity comparison on the audio of the follow-up record and the audio output by the DSSM matching algorithm and generating a score.

Specifically, the media device mainly comprises an input module and an output module, the input module and the output module are arranged adjacently, the analysis module is an external device and is in wireless connection with the media device through a wireless communication module, when the media device is used, a user mainly performs character recognition according to manual input on a touch screen, voice recognition of a microphone or picture recognition of a camera, and recognized characters are displayed on the touch screen. And modifying the error text according to the touch control of the user, and transmitting the text information to the analysis module by the input module through the built-in communication module after the text is adjusted.

The analysis module classifies the data stored inside mainly through LDA model information algorithm, for example, induction is carried out on phrases and sentences under different contexts, a Bayesian algorithm is adopted to set super parameters, then after the text of the input module is received, a character string with the length similar to that of a target string is read in a database according to DSSM matching algorithm, then the character string is operated, each operation replaces or deletes characters, the characters are matched with the text in the database, so that the corresponding matched database text information is obtained, finally, the corresponding text information is subjected to voice corresponding conversion and output through TTS algorithm, and is transmitted to the output module through the wireless communication module.

The output module is played in the loudspeaker after receiving the audio information, a user can read along according to the played audio, the read-along information can be recorded immediately through the microphone of the input module, the recorded audio is compared with the original output audio through an FFT algorithm in the output module, the similarity between the matching is scored, the output score is displayed on the touch screen, and therefore the effect of self scoring is achieved.

When necessary, the user can record the audio paragraph made by the user into the analysis module, and the user can use the audio paragraph made by the user when the user needs to output the audio paragraph, so as to achieve the effect of follow-up reading.

According to the invention, questions are freely created by teachers, students or parents in a role-like manner according to the self ability level condition of the user for practice, corresponding sentences are identified through various input modes to generate evaluation of words and sentences, and after the evaluation of the sentences is synthesized, the students can listen to demonstration sounds according to the created contents and automatically input voices to evaluate and grade, so that the effects of automatically selecting and evaluating spoken words are realized, the boring feeling brought by fixed courses is avoided, and the interest of learning is enhanced.

Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that changes may be made in the embodiments and/or equivalents thereof without departing from the spirit and scope of the invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A platform system for creating spoken assessment exercises, comprising a media device, wherein the media device comprises:

2. The platform system for creating spoken language assessment exercises according to claim 1, wherein said input module and said output module are electrically connected and fixedly arranged adjacent to each other.

3. The platform system for creating oral assessment exercises as claimed in claim 2, wherein said input module comprises OCR character recognition algorithm for converting information of manual input, voice input and picture recognition into text information and displaying on the touch screen.

4. The platform system for creating spoken language assessment exercises according to claim 2, wherein said server device comprises:

5. The platform system for creating spoken language assessment exercises as claimed in claim 4, wherein said output module plays the corresponding audio information, said output module comprising an FFT algorithm for comparing the similarity between the audio of the read-along recording and the audio output by the DSSM matching algorithm and generating the score.