CN-122024537-A - Language interactive learning system and method

CN122024537ACN 122024537 ACN122024537 ACN 122024537ACN-122024537-A

Abstract

A language interactive learning system and method, the system includes a microphone unit, a speaker unit, a display unit, a storage unit and a control unit. The storage unit stores a language database, a plurality of learning pictures, and a plurality of predetermined answers, the learning pictures defining a question area. The control unit is provided with a voice recognition module, an auxiliary module and a voice synthesis module, wherein the voice synthesis module outputs a signal corresponding to the questioning area to the loudspeaker unit, the voice recognition module converts the input of the microphone unit into answer text information, the auxiliary module judges whether the answer text information accords with the preset answer corresponding to the questioning area, if not, the voice database is read according to the answer text information and a guiding dialogue is generated, and then the loudspeaker unit sends out interactive voice, so that the situation that a user possibly affects learning quality due to overmuch attention score and further the user generates a step-back condition can be avoided.

Inventors

ZENG PEIRONG
ZHENG BOHONG
CHEN ZIYU
PAN BAIWEI

Assignees

财团法人金属工业研究发展中心

Dates

Publication Date: 20260512
Application Date: 20250922
Priority Date: 20241111

Claims (13)

1. A language interactive learning system is characterized by comprising: a microphone unit for receiving a sentence from a user speaking and outputting a voice signal according to the sentence; A storage unit for storing a language database, a plurality of learning pictures and a plurality of predetermined answers, wherein each learning picture is provided with a question area, and each question area corresponds to one of the predetermined answers; the display unit is in information connection with the storage unit and is used for displaying the learning picture; A speaker unit, which is connected with the display unit in a signal manner and is used for outputting the information displayed in the questioning area corresponding to the learning picture to generate interactive voice, and The control unit is in signal connection with the microphone unit, the storage unit, the display unit and the loudspeaker unit, and comprises a voice recognition module, a voice synthesis module and an auxiliary module, wherein the voice recognition module is used for receiving and recognizing the voice signal and converting the voice signal into answer text information, the voice synthesis module is in information connection with the voice recognition module and is used for outputting the interactive voice, the auxiliary module is in information connection with the voice synthesis module and is used for judging whether the answer text information accords with the preset answer corresponding to the question area, and when the answer text information does not accord with the preset answer corresponding to the question area, the voice database is read according to the answer text information and a section of guiding dialogue prompted by positive language is generated, and the loudspeaker unit is used for outputting the interactive voice corresponding to the guiding dialogue.
2. The interactive learning system of claim 1 further comprising a word breaking module in communication with the speech synthesis module for breaking down at least one keyword or segmented sentence from the answer text information, and an analysis module in communication with the word breaking module for quantifying integrated assessment data based on the keyword and segmented sentence.
3. The language interactive learning system of claim 2, wherein the comprehensive evaluation data contains semantic rules corresponding to the keywords and defined according to meanings represented by the sentences themselves, grammatical rules corresponding to the segmented sentences and defined according to structures of the sentences and combinations thereof, and semantic rules achieving a certain implicit meaning according to an appropriate situation.
4. The interactive learning system of claim 1, further comprising an input unit in signal connection with the control unit, wherein the input unit is used for being controlled by the user to output an input signal related to a clicking position on a screen displayed by the display unit, each learning screen is further provided with a plurality of option areas for the user to operate, the control unit further comprises an integrating module in information connection with the auxiliary module, the integrating module is used for judging the option area where the position corresponding to the input signal is located to obtain option information, and judging whether the option information accords with the preset answer corresponding to the asking area, if not, the auxiliary module reads the language database according to the option information to generate the guiding dialogue.
5. The interactive learning system of claim 4 wherein the memory unit further stores a graphics card pattern, each of the learning pictures corresponding to the graphics card pattern further has an answer graphics card area, and the integration module is further configured to obtain the option information according to the option area where the position corresponding to the input signal was located when the previous selection condition was met when the position corresponding to the input signal was located in the answer graphics card area and the trigger condition was met.
6. The interactive learning system of claim 4 wherein the memory unit further stores a codebook pattern, each of the learning frames corresponding to the codebook pattern further has a button area corresponding to a voice recognition function, and the integration module is further configured to enable the voice recognition module to recognize the voice signal received next and convert the voice signal into the answer text information when the input signal is selected corresponding to the button area.
7. The language interactive learning system of any one of claims 1-6, wherein the language database has a security mechanism dataset and an alignment dataset.
8. The interactive language learning method applied to the interactive language learning system as claimed in claim 1, comprising the following steps: A learning screen display step in which the control unit causes the display unit to display one of the learning screens; a questioning step, wherein the control unit enables the loudspeaker unit to output the interactive voice; A user answering step, wherein the microphone unit receives the voice signal, recognizes the voice signal in the voice recognition module, and converts the voice signal into the answering text information; A reply step, wherein the auxiliary module judges whether the reply text information accords with the preset reply corresponding to the question area and outputs the corresponding interactive voice through the voice synthesis module, and And in the replying step, if the auxiliary module judges that the answer text information does not accord with the preset answer corresponding to the questioning area, the guiding step generates a guiding dialogue prompted by affirmative language through the auxiliary module reading the language database according to the answer text information, and outputs the interactive voice corresponding to the guiding dialogue through the voice synthesis module.
9. The method of claim 8, further comprising a disassembling step after the user answers and before the answer step, and an evaluating step after the answer step, wherein the disassembling step disassembles at least one keyword or segment sentence by information through a disassembling module connected with the speech synthesis module, and the evaluating step counts the keyword and the segment sentence to quantify the comprehensive evaluation data according to the keyword and the segment sentence by information through an analyzing module connected with the disassembling module.
10. The method of claim 8, wherein the assist module generates the pilot dialogue in relation to the predetermined answer but not including the predetermined answer when the answer is first judged no.
11. The method of claim 8, wherein said assistance module generates said guidance dialog associated with a portion of said predetermined responses but not including the complete said predetermined responses when said response step is initially determined as no and when said response step is also determined as no.
12. The method according to claim 9, wherein the integrated evaluation data includes semantic rules corresponding to the keywords and defined based on meaning represented by the sentence itself, grammar rules corresponding to the segmented sentence and defined based on structure of the sentence and combination thereof, and semantic rules reaching a certain implicit meaning based on an appropriate situation, and wherein in the response step, when the assist module determines that the answer text information is identical to a part of the word segmentation related to the semantic rules of the predetermined answer, and does not have meaning different with respect to the grammar rules or meaning different with respect to the semantic rules, the assist module determines that the two part of the word segmentation related to the semantic rules are identical, and then when the guidance step determines that the answer text information is partially identical, the assist module provides the guidance dialogue including the answer text information and the predetermined answer related to the rest of the predetermined answer.
13. The method of claim 12, wherein in the step of replying, the auxiliary module determines that the reply text information is inconsistent with the predetermined reply when the number of words, the meaning, or the word segmentation order are different.

Description

Language interactive learning system and method Technical Field The present invention relates to learning systems and methods, and more particularly, to a system and method for interactive learning of language. Background Autism group (Autism Spectrum Disorder, ASD) belongs to a neurological disorder, and autism children usually have slow language development, and compared with the same ages, the autism group has fewer words, serious sentence errors and even no words. Autistic children typically receive language therapy from a language therapist at least once a week (30 minutes) and learn language on weekdays with family accompaniment (180 minutes/week). Thus, in addition to treatment by language, more learning time can be added to advance language ability. However, language growth requires a time accumulation of months to years. In most cases, it is often difficult for families to combine work and accompanying learning, resulting in insufficient language learning time. And the negative emotion such as responsibility, anger and the like in the accompanying learning process can be caused because the family members accumulate the spirit and the living pressure for a long time, so that the language learning will and the effect of the children are reduced, and the possibility of fatigue and depression of the family members is further increased. Disclosure of Invention The invention aims to provide a language interactive learning system which can be used for users to learn by themselves. The invention relates to a language interactive learning system, which comprises: a microphone unit for receiving a sentence from a user speaking and outputting a voice signal according to the sentence; A storage unit for storing a language database, a plurality of learning pictures and a plurality of predetermined answers, wherein each learning picture is provided with a question area, and each question area corresponds to one of the predetermined answers; the display unit is in information connection with the storage unit and is used for displaying the learning picture; A speaker unit, which is connected with the display unit in a signal manner and is used for outputting the information displayed in the questioning area corresponding to the learning picture to generate interactive voice, and The control unit is in signal connection with the microphone unit, the storage unit, the display unit and the loudspeaker unit, and comprises a voice recognition module, a voice synthesis module and an auxiliary module, wherein the voice recognition module is used for receiving and recognizing the voice signal and converting the voice signal into answer text information, the voice synthesis module is in information connection with the voice recognition module and is used for outputting the interactive voice, the auxiliary module is in information connection with the voice synthesis module and is used for judging whether the answer text information accords with the preset answer corresponding to the question area, and when the answer text information does not accord with the preset answer corresponding to the question area, the voice database is read according to the answer text information and a section of guiding dialogue prompted by positive language is generated, and the loudspeaker unit is used for outputting the interactive voice corresponding to the guiding dialogue. The language interactive learning system further comprises a word separation module which is connected with the voice synthesis module in a message mode and is used for separating at least one keyword or fragment sentence from the answer text information, and an analysis module which is connected with the word separation module in a message mode and is used for quantifying comprehensive evaluation data integrated according to the keyword and the fragment sentence. The language interactive learning system of the invention, the comprehensive evaluation data contains semantic rules corresponding to the keywords and defined according to the meaning represented by the words and sentences, grammar rules corresponding to the segment sentences and defined according to the structures of the words and sentences and the combination modes thereof, and semantic rules achieving a certain implicit meaning according to proper situations. The invention also comprises an input unit connected with the control unit through signals, wherein the input unit is used for controlling the user to output an input signal related to a clicking position on a picture displayed by the display unit, each learning picture is also provided with a plurality of option areas which can be operated by the user, the control unit also comprises an integration module connected with the auxiliary module through information, the integration module is used for judging the option area where the position corresponding to the input signal is located to obtain option information, judging whether the option information ac