CN113178208A - Intelligent on-line voice answer control method and system for chemists - Google Patents

Intelligent on-line voice answer control method and system for chemists Download PDF

Info

Publication number
CN113178208A
CN113178208A CN202110426022.4A CN202110426022A CN113178208A CN 113178208 A CN113178208 A CN 113178208A CN 202110426022 A CN202110426022 A CN 202110426022A CN 113178208 A CN113178208 A CN 113178208A
Authority
CN
China
Prior art keywords
answer
voice
student
online
value
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202110426022.4A
Other languages
Chinese (zh)
Inventor
樊星
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Squirrel Classroom Artificial Intelligence Technology Co Ltd
Original Assignee
Shanghai Squirrel Classroom Artificial Intelligence Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shanghai Squirrel Classroom Artificial Intelligence Technology Co Ltd filed Critical Shanghai Squirrel Classroom Artificial Intelligence Technology Co Ltd
Priority to CN202110426022.4A priority Critical patent/CN113178208A/en
Publication of CN113178208A publication Critical patent/CN113178208A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
    • G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
    • G—PHYSICS
    • G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
    • G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
    • G09B7/00—Electrically-operated teaching apparatus or devices working with questions and answers
    • G09B7/02—Electrically-operated teaching apparatus or devices working with questions and answers of the type wherein the student is expected to construct an answer to the question which is presented or wherein the machine gives an answer to the question presented by a student
    • G09B7/04—Electrically-operated teaching apparatus or devices working with questions and answers of the type wherein the student is expected to construct an answer to the question which is presented or wherein the machine gives an answer to the question presented by a student characterised by modifying the teaching programme in response to a wrong answer, e.g. repeating the question, supplying a further explanation
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
    • G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
    • G10L21/0208—Noise filtering

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Human Computer Interaction (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Computational Linguistics (AREA)
  • Signal Processing (AREA)
  • Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Educational Technology (AREA)
  • Business, Economics & Management (AREA)
  • Educational Administration (AREA)
  • Quality & Reliability (AREA)
  • Electrically Operated Instructional Devices (AREA)

Abstract

The invention provides an intelligent student on-line voice answer control method and system, which analyzes the actual answer voice information in the student on-line voice answer process through voice recognition and comparison, so as to automatically judge the correctness of the student on-line answer, and simultaneously determine the activity degree of the student on-line answer, thereby combining the correctness of the on-line answer and the activity degree of the on-line answer, updating the sequencing positions of the students in the sequence of the plurality of students completing the voice answer, and correspondingly adjusting the test time of the student on-line voice answer, which can comprehensively and accurately judge the correctness of the student on-line answer, thus not only realizing the automatic judgment of the student answer and reducing the workload of teachers in on-line teaching, but also effectively adjusting the answer time of the student according to the answer condition of the student, therefore, the teaching efficiency of on-line teaching is improved.

Description

Intelligent on-line voice answer control method and system for chemists
Technical Field
The invention relates to the technical field of intelligent education, in particular to an intelligent chemist online voice question answering control method and system.
Background
Online teaching has gradually become the primary mode of intelligent teaching. The teacher can give lessons and interactively ask and answer a lot of synchronizations through the mode of online teaching, and correspondingly, the students can answer questions provided by the teacher in an online voice mode. However, due to the large number of students and the time limitation, the teacher cannot analyze the speech information of the answers of all the students one by one, which results in that the teacher cannot fully and comprehensively judge the correctness of the answers of the students, and at the same time, the answering time of the students cannot be effectively adjusted according to the answering conditions of the students, which seriously reduces the teaching efficiency of on-line teaching.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides an intelligent student online voice answer control method and system, which are used for collecting actual answer voice information of a plurality of students in an online voice answer process and carrying out noise reduction pretreatment on the actual answer voice information; according to the sequence of the voice answer completion of a plurality of students, all the actual answer voice information is combined into a corresponding answer voice information sequence, and then the condition of standard answer key words contained in each actual answer voice information in the answer voice information sequence is identified, so that the correctness of the online voice answer of each student is judged; collecting the real-time answering state of each student in the online voice answering process so as to determine the activity degree of online voice answering of each student, and finally updating the sequencing position of each student in the sequence of completing voice answering of a plurality of students according to the correctness judgment result of the online voice answering of each student and the activity degree of the online voice answering; adjusting the testing time for performing online voice answering on each student according to the updated sequencing position; therefore, the intelligent student on-line voice answer control method and the system analyze the actual answer voice information in the student on-line voice answer process in a voice recognition and comparison mode, thereby automatically judging the correctness of the on-line answer of the student and simultaneously determining the active degree of the on-line answer of the student, thereby updating the sequencing positions of the students in the sequence of the plurality of students completing the voice answer by combining the correctness of the online answer and the activity degree of the online answer, and correspondingly adjusting the testing time of the online voice answer to the students, which can comprehensively and accurately judge whether the student answers on line or not, thus not only realizing the automatic judgment of the student answers and reducing the workload of teachers in on-line teaching, and can also carry out effectual adjustment to student's answer time to student's answer condition to this teaching efficiency that improves online teaching.
The invention provides an intelligent on-line voice question answering control method for a chemist, which is characterized by comprising the following steps of:
step S1, collecting actual answer voice information of a plurality of students in an online voice answer process, and carrying out noise reduction pretreatment on the actual answer voice information; according to the sequence of the voice answering completed by the students, all the actual answering voice information is combined into a corresponding answering voice information sequence;
step S2, recognizing the standard answer keyword condition contained in each actual answer voice information in the answer voice information sequence, thereby judging the correctness of each student on-line voice answer; collecting the real-time answering state of each student in the online voice answering process, thereby determining the active degree of each student in online voice answering;
step S3, updating the sequencing position of each student in the sequence of the plurality of students completing the voice answer according to the correctness judgment result of the online voice answer of each student and the active degree of the online voice answer; adjusting the testing time for performing online voice answering on each student according to the updated sequencing position;
further, in step S1, collecting actual answer speech information of a plurality of students in an online speech answer process, and performing noise reduction preprocessing on the actual answer speech information; and according to the order of the plurality of students completing the voice answering, all the actual answering voice information is combined into a corresponding answering voice information sequence, which specifically comprises the following steps:
step S101, instructing a microphone array to collect actual answer voice information of each student in an online voice answer process, and extracting and filtering background noise components contained in the actual answer voice information so as to realize noise reduction preprocessing;
step S102, recording the voice answer ending time corresponding to the online voice answer process of each student, and determining the sequence of all students completing voice answer according to the sequence of the voice answer ending time; then according to the order of completing the voice answering, all the actual answering voice information is sequentially combined into a corresponding answering voice information sequence;
further, in step S2, a standard answer keyword condition included in each actual answer speech information in the answer speech information sequence is identified, so as to determine the correctness of the online speech answer of each student; the method for acquiring the real-time answer state of each student in the online voice answer process so as to determine the activity degree of each student in the online voice answer specifically comprises the following steps:
step S201, using the following formula (1), comparing the standard voice information of the answer keywords contained in the standard answer corresponding to the question answered by each student with the actual answer voice information of each student, so as to obtain the number of the answer keywords contained in the actual answer voice information of each student as the standard answer keyword condition,
Figure BDA0003029584470000031
in the above formula (1), KaNumber f of answer keywords contained in actual answer speech information of the a-th studenta(n + m) represents the amplitude of the (n + m) th speech signal in the actual answer speech information of the (a) th student, fi(m) amplitude of mth speech signal in the standard speech information indicating the ith answer keyword included in the standard answer, fa(n+m)-fi(M) represents a volume amplitude difference between the (n + M) th speech signal in the actual answer speech information and the (M) th speech signal in the standard speech information of the ith answer keyword, MiThe total number of wave crests corresponding to the amplitude of the voice signal in the standard voice information of the ith answer keyword contained in the standard answer, NaThe method comprises the steps that the total number of wave crests corresponding to the amplitude of voice signals in actual answer voice information of an a-th student is represented, I represents the total number of answer keywords contained in a standard answer, delta { } represents a unit pulse function, the value of the unit pulse function is 1 when the numerical value in brackets is equal to 0, and the value of the unit pulse function is 0 when the numerical value in brackets is not equal to 0;
step S202, using the following formula (2) to judge the correctness of the on-line voice answer of each student,
Figure BDA0003029584470000041
in the above formula (2), PaRepresents the correctness evaluation value, Q, of the on-line voice answer of the a-th studentiThe method comprises the steps that the value of an ith answer keyword contained in a standard answer is represented, the value is preset, the value range of the value is 10-20, u { } represents a step function, the value of the step function is 1 when the value in brackets is greater than or equal to 0, and the value of the step function is 0 when the value in brackets is less than 0;
when P is presentaWhen the answer is 1, the answer of the a-th student is correct;
when P is presentaWhen the answer is 0, the online voice answer of the a-th student is incorrect;
step S203, collecting answering time of each student and communication connection times between each student and a voice answering terminal in the online voice answering process of each student; then the following formula (3) is used to determine the evaluation value of the activity degree of the online voice answering of each student,
Figure BDA0003029584470000042
in the above formula (3), ηaAn evaluation value T representing the activity degree of the online voice answer of the a-th studentaShows that the answer of the a-th student in the online voice answer process consumes time, Ta+bShows that the answer of the (a + b) th student is time-consuming in the process of the online voice answer, LaIndicates the communication connection times between the a-th student and the voice answering terminal in the process of the online voice answering, La+bThe method comprises the steps that the communication connection times between the a + b students and a voice answer terminal in the current online voice answer process are represented, and A represents the total number of students participating in the current online voice answer process;
further, in the step S3, updating the ranking position of each student in the answer voice information sequence according to the correctness judgment result of the online voice answer of each student and the activity degree of the online voice answer; and according to the updated answer voice information sequence, adjusting the test time for performing online voice answer on each student specifically comprises:
step S301, determining the sequencing moving value of each student in the answer speech information sequence when the sequencing position of each student in the answer speech information sequence is updated by using the following formula (4),
Figure BDA0003029584470000051
in the above formula (4), QaExpressing the on-line voice answer score, Q, of the a-th studenta+bRepresents the on-line voice answer score, lambda, of the a + b th studentaRepresents the sorting movement value of the a-th student in the answering voice information sequence and when lambda isaWhen the answer is more than or equal to 0, the a-th student moves forwards by lambda from the current position of the answer voice information sequenceaI position, when lambdaaWhen the answer is less than 0, the position of the a-th student at the current answer voice information sequence is moved backwards by lambdaaL positions, ηa+bAn evaluation value representing the activity degree of the online voice answer of the (a + b) th student, A representing the total number of students participating in the online voice answer, u [, ]]The step function is represented, the value of the step function is 1 when the value in the brackets is greater than or equal to 0, the value of the step function is 0 when the value in the brackets is less than 0, delta { } represents the unit pulse function, the value of the unit pulse function is 1 when the value in the brackets is equal to 0, and the value of the unit pulse function is 0 when the value in the brackets is not equal to 0;
step S302, updating the sequencing position of the a-th student in the answer voice information sequence according to the sequencing moving value of the a-th student in the answer voice information sequence; increasing the testing time of the online voice answer of each student in the first half of the updated answer voice information sequence, and reducing the testing time of the online voice answer of each student in the second half of the updated answer voice information sequence.
The invention provides an intelligent student online voice answer control system which is characterized by comprising an online answer voice information acquisition and processing module, a student online answer correctness judgment module, a student online answer activity degree determination module and a student online answer adjustment module; wherein the content of the first and second substances,
the online answer voice information acquisition and processing module is used for acquiring actual answer voice information of a plurality of students in an online voice answer process and carrying out noise reduction pretreatment on the actual answer voice information; according to the sequence of the voice answering completed by the students, all the actual answering voice information is combined into a corresponding answering voice information sequence;
the student online answer correctness judging module is used for identifying the standard answer keyword condition contained in each actual answer voice information in the answer voice information sequence so as to judge the correctness of each student online voice answer;
the student online answer activity degree determining module is used for acquiring a real-time answer state of each student in an online voice answer process so as to determine the activity degree of each student online voice answer;
the student online answer adjusting module is used for updating the sequencing position of each student in the sequence of the plurality of students completing the voice answer according to the correctness judgment result of the online voice answer of each student and the activity degree of the online voice answer; adjusting the testing time for performing online voice answering on each student according to the updated sequencing position;
further, the online answer voice information acquisition and processing module acquires actual answer voice information of a plurality of students in an online voice answer process, and performs noise reduction pretreatment on the actual answer voice information; and according to the order of the plurality of students completing the voice answering, all the actual answering voice information is combined into a corresponding answering voice information sequence, which specifically comprises the following steps:
indicating a microphone array to collect actual answer voice information of each student in an online voice answer process, and extracting and filtering background noise components contained in the actual answer voice information so as to realize noise reduction preprocessing;
recording the voice answer ending time corresponding to the online voice answer process of each student, and determining the sequence of completing the voice answer of all students according to the sequence of the voice answer ending time; then according to the order of completing the voice answering, all the actual answering voice information is sequentially combined into a corresponding answering voice information sequence;
further, the module for judging correctness of online student answers identifies a standard answer keyword condition contained in each actual answer voice message in the answer voice message sequence, so that judging correctness of online student voice answers specifically comprises:
comparing the standard voice information of the answer key words contained in the standard answers corresponding to the questions answered by each student with the actual answer voice information of each student by using the following formula (1), thereby obtaining the number of the answer key words contained in the actual answer voice information of each student as the condition of the standard answer key words,
Figure BDA0003029584470000071
in the above formula (1), KaNumber f of answer keywords contained in actual answer speech information of the a-th studenta(n + m) represents the amplitude of the (n + m) th speech signal in the actual answer speech information of the (a) th student, fi(m) amplitude of mth speech signal in the standard speech information indicating the ith answer keyword included in the standard answer, fa(n+m)-fi(M) represents a volume amplitude difference between the (n + M) th speech signal in the actual answer speech information and the (M) th speech signal in the standard speech information of the ith answer keyword, MiAmplitude value pair of voice signal in standard voice information representing ith answer keyword contained in standard answerTotal number of peaks, NaThe method comprises the steps that the total number of wave crests corresponding to the amplitude of voice signals in actual answer voice information of an a-th student is represented, I represents the total number of answer keywords contained in a standard answer, delta { } represents a unit pulse function, the value of the unit pulse function is 1 when the numerical value in brackets is equal to 0, and the value of the unit pulse function is 0 when the numerical value in brackets is not equal to 0;
then, the correctness of the online voice answer of each student is judged by using the following formula (2),
Figure BDA0003029584470000072
in the above formula (2), PaRepresents the correctness evaluation value, Q, of the on-line voice answer of the a-th studentiThe method comprises the steps that the value of an ith answer keyword contained in a standard answer is represented, the value is preset, the value range of the value is 10-20, u { } represents a step function, the value of the step function is 1 when the value in brackets is greater than or equal to 0, and the value of the step function is 0 when the value in brackets is less than 0;
when P is presentaWhen the answer is 1, the answer of the a-th student is correct;
when P is presentaWhen the answer is 0, the online voice answer of the a-th student is incorrect;
and the number of the first and second groups,
the online student answer liveness determining module collects the real-time answer state of each student in the online voice answer process, so that the liveness determining module determines the liveness of each student in the online voice answer specifically comprises the following steps:
collecting the answering time of each student and the communication connection times between each student and a voice answering terminal in the online voice answering process of each student; then the following formula (3) is used to determine the evaluation value of the activity degree of the online voice answering of each student,
Figure BDA0003029584470000081
in the above formula (3), ηaAn evaluation value T representing the activity degree of the online voice answer of the a-th studentaShows that the answer of the a-th student in the online voice answer process consumes time, Ta+bShows that the answer of the (a + b) th student is time-consuming in the process of the online voice answer, LaIndicates the communication connection times between the a-th student and the voice answering terminal in the process of the online voice answering, La+bThe method comprises the steps that the communication connection times between the a + b students and a voice answer terminal in the current online voice answer process are represented, and A represents the total number of students participating in the current online voice answer process;
furthermore, the student online answer adjusting module updates the sequencing position of each student in the answer voice information sequence according to the correctness judgment result of each student online voice answer and the active degree of the online voice answer; and according to the updated answer voice information sequence, adjusting the test time for performing online voice answer on each student specifically comprises:
determining a ranking shift value of each student in the answer speech information sequence when updating the ranking position of each student in the answer speech information sequence using the following formula (4),
Figure BDA0003029584470000082
in the above formula (4), QaExpressing the on-line voice answer score, Q, of the a-th studenta+bRepresents the on-line voice answer score, lambda, of the a + b th studentaRepresents the sorting movement value of the a-th student in the answering voice information sequence and when lambda isaWhen the answer is more than or equal to 0, the a-th student moves forwards by lambda from the current position of the answer voice information sequenceaI position, when lambdaaWhen the answer is less than 0, the position of the a-th student at the current answer voice information sequence is moved backwards by lambdaaL positions, ηa+bIndicates that the a + b students are inAn evaluation value of activity degree of the on-line voice answer, A representing the total number of students participating in the on-line voice answer, u [ 2 ]]The step function is represented, the value of the step function is 1 when the value in the brackets is greater than or equal to 0, the value of the step function is 0 when the value in the brackets is less than 0, delta { } represents the unit pulse function, the value of the unit pulse function is 1 when the value in the brackets is equal to 0, and the value of the unit pulse function is 0 when the value in the brackets is not equal to 0;
finally, updating the sequencing position of the a-th student in the answer voice information sequence according to the sequencing moving value of the a-th student in the answer voice information sequence; increasing the testing time of the online voice answer of each student in the first half of the updated answer voice information sequence, and reducing the testing time of the online voice answer of each student in the second half of the updated answer voice information sequence.
Compared with the prior art, the intelligent student online voice answer control method and system collect actual answer voice information of a plurality of students in an online voice answer process, and perform noise reduction pretreatment on the actual answer voice information; according to the sequence of the voice answer completion of a plurality of students, all the actual answer voice information is combined into a corresponding answer voice information sequence, and then the condition of standard answer key words contained in each actual answer voice information in the answer voice information sequence is identified, so that the correctness of the online voice answer of each student is judged; collecting the real-time answering state of each student in the online voice answering process so as to determine the activity degree of online voice answering of each student, and finally updating the sequencing position of each student in the sequence of completing voice answering of a plurality of students according to the correctness judgment result of the online voice answering of each student and the activity degree of the online voice answering; adjusting the testing time for performing online voice answering on each student according to the updated sequencing position; therefore, the intelligent student on-line voice answer control method and the system analyze the actual answer voice information in the student on-line voice answer process in a voice recognition and comparison mode, thereby automatically judging the correctness of the on-line answer of the student and simultaneously determining the active degree of the on-line answer of the student, thereby updating the sequencing positions of the students in the sequence of the plurality of students completing the voice answer by combining the correctness of the online answer and the activity degree of the online answer, and correspondingly adjusting the testing time of the online voice answer to the students, which can comprehensively and accurately judge whether the student answers on line or not, thus not only realizing the automatic judgment of the student answers and reducing the workload of teachers in on-line teaching, and can also carry out effectual adjustment to student's answer time to student's answer condition to this teaching efficiency that improves online teaching.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of an intelligent student online voice answer control method provided by the invention.
Fig. 2 is a schematic structural diagram of an intelligent student online voice answer control system provided by the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a schematic flow chart of an intelligent student online voice answer control method according to an embodiment of the present invention. The intelligent student online voice answer control method comprises the following steps:
step S1, collecting the actual answer voice information of a plurality of students in the online voice answer process, and carrying out noise reduction pretreatment on the actual answer voice information; according to the order of the plurality of students completing the voice answering, all the actual answering voice information is combined into a corresponding answering voice information sequence;
step S2, recognizing the standard answer keyword condition contained in each actual answer voice information in the answer voice information sequence, thereby judging the correctness of each student on-line voice answer; collecting the real-time answering state of each student in the online voice answering process, thereby determining the active degree of each student in online voice answering;
step S3, updating the sequencing position of each student in the sequence of the plurality of students completing the voice answer according to the correctness judgment result of the online voice answer of each student and the active degree of the online voice answer; and adjusting the testing time for carrying out on-line voice answering on each student according to the updated sequencing position.
The beneficial effects of the above technical scheme are: the intelligent student on-line voice answer control method analyzes the actual answer voice information of the student in the on-line voice answer process through the voice recognition and comparison mode, thereby automatically judging the correctness of the on-line answer of the student and simultaneously determining the active degree of the on-line answer of the student, thereby updating the sequencing positions of the students in the sequence of the plurality of students completing the voice answer by combining the correctness of the online answer and the activity degree of the online answer, and correspondingly adjusting the testing time of the online voice answer to the students, which can comprehensively and accurately judge whether the student answers on line or not, thus not only realizing the automatic judgment of the student answers and reducing the workload of teachers in on-line teaching, and can also carry out effectual adjustment to student's answer time to student's answer condition to this teaching efficiency that improves online teaching.
Preferably, in step S1, collecting actual answer voice information of a plurality of students during online voice answer, and performing noise reduction preprocessing on the actual answer voice information; and according to the order of the plurality of students completing the voice answering, all the actual answering voice information is combined into a corresponding answering voice information sequence, which specifically comprises the following steps:
step S101, instructing a microphone array to collect actual answer voice information of each student in an online voice answer process, and extracting and filtering background noise components contained in the actual answer voice information so as to realize noise reduction preprocessing;
step S102, recording the voice answer ending time corresponding to the online voice answer process of each student, and determining the sequence of all students completing voice answer according to the sequence of the voice answer ending time; and then, according to the sequence of completing the voice answering, sequentially combining all the actual answering voice information into a corresponding answering voice information sequence.
The beneficial effects of the above technical scheme are: the signal-to-noise ratio of the online answering voice information is reduced because the interference of background noise inevitably exists in the online voice answering process of students, and the reliability of the actual answering voice information can be improved to the maximum extent by extracting and filtering background noise components contained in the actual answering voice information. And the voice answer ending time corresponding to the online voice answer process of each student is recorded, and the sequence of completing the voice answer of all students is determined according to the sequence of the voice answer ending time, so that the initial form of answer voice information sequence can be efficiently and conveniently formed and used as the basis for subsequent sequence updating.
Preferably, in the step S2, a standard answer keyword condition included in each actual answer speech information in the answer speech information sequence is identified, so as to determine the correctness of the online speech answer of each student; the method for acquiring the real-time answer state of each student in the online voice answer process so as to determine the activity degree of each student in the online voice answer specifically comprises the following steps:
step S201, using the following formula (1), comparing the standard voice information of the answer key words contained in the standard answers corresponding to the questions answered by each student with the actual answer voice information of each student, so as to obtain the number of the answer key words contained in the actual answer voice information of each student as the condition of the standard answer key words,
Figure BDA0003029584470000121
in the above formula (1), KaNumber f of answer keywords contained in actual answer speech information of the a-th studenta(n + m) represents the amplitude of the (n + m) th speech signal in the actual answer speech information of the (a) th student, fi(m) amplitude of mth speech signal in the standard speech information indicating the ith answer keyword included in the standard answer, fa(n+m)_fi(M) represents a volume amplitude difference between the (n + M) th speech signal in the actual answer speech information and the (M) th speech signal in the standard speech information of the ith answer keyword, MiThe total number of wave crests corresponding to the amplitude of the voice signal in the standard voice information of the ith answer keyword contained in the standard answer, NaThe method comprises the steps that the total number of wave crests corresponding to the amplitude of voice signals in actual answer voice information of an a-th student is represented, I represents the total number of answer keywords contained in a standard answer, delta { } represents a unit pulse function, the value of the unit pulse function is 1 when the numerical value in brackets is equal to 0, and the value of the unit pulse function is 0 when the numerical value in brackets is not equal to 0;
step S202, using the following formula (2) to judge the correctness of the on-line voice answer of each student,
Figure BDA0003029584470000131
in the above formula (2), PaRepresents the correctness evaluation value, Q, of the on-line voice answer of the a-th studentiThe method comprises the steps that the value of the ith answer keyword contained in a standard answer is represented, the value is preset, the value range of the value is 10-20, u { } represents a step function, the value of the step function is 1 when the value in brackets is greater than or equal to 0, and the value of the step function is 0 when the value in brackets is less than 0;
when P is presentaWhen the answer is 1, the answer of the a-th student is correct;
when P is presentaWhen the answer is 0, the online voice answer of the a-th student is incorrect;
step S203, collecting answering time of each student and communication connection times between each student and a voice answering terminal in the online voice answering process of each student; then the following formula (3) is used to determine the evaluation value of the activity degree of the online voice answering of each student,
Figure BDA0003029584470000132
in the above formula (3), ηaAn evaluation value T representing the activity degree of the online voice answer of the a-th studentaShows that the answer of the a-th student in the online voice answer process consumes time, Ta+bShows that the answer of the (a + b) th student is time-consuming in the process of the online voice answer, LaIndicates the communication connection times between the a-th student and the voice answering terminal in the process of the online voice answering, La+bThe number of communication connections between the (a + b) th student and the voice answer terminal in the current online voice answer process is represented, and A represents the total number of students participating in the current online voice answer process.
The beneficial effects of the above technical scheme are: because each question corresponds to a standard answer in the online answering process, the standard answer is composed of a plurality of Chinese and/or foreign characters, and each Chinese and/or foreign character group forms an answer keyword of the standard answer. By using the formula (1), the standard voice information corresponding to the answer keyword (the standard voice information can be obtained by performing artificial voice conversion on the answer keyword, which belongs to the conventional means of intelligent voice conversion, and is not described in further detail here) is compared with the voice signal amplitude of the actual answer voice information of each student, so that the number of the standard answer keyword contained in the actual answer voice information can be quickly and accurately obtained. And by using the formula (2), the correctness of the online voice answer of the student can be quantitatively evaluated, so that the condition of misjudgment is effectively avoided. And by using the formula (3), the activity degree of the online voice answer of the student can be objectively and quantitatively evaluated on the basis of the answering time of the student and the communication connection frequency between the student and the voice answer terminal.
Preferably, in the step S3, updating the ranking position of each student in the answering voice information sequence according to the correctness judgment result of the online voice answer of each student and the activity degree of the online voice answer; and according to the updated answer voice information sequence, adjusting the test time for performing online voice answer on each student specifically comprises:
step S301, using the following formula (4), determining the ranking shift value of each student in the answer speech information sequence when updating the ranking position of each student in the answer speech information sequence,
Figure BDA0003029584470000141
in the above formula (4), QaExpressing the on-line voice answer score, Q, of the a-th studenta+bRepresents the on-line voice answer score, lambda, of the a + b th studentaRepresents the sorting movement value of the a-th student in the answering speech information sequence and when lambda isaWhen the answer is more than or equal to 0, the a-th student moves forward to the position where the answer voice information sequence is locatedaI position, when lambdaaIf < 0, the position of the a-th student at the current answer voice information sequence is adjustedPost-shift | λaL positions, ηa+bAn evaluation value representing the activity degree of the online voice answer of the (a + b) th student, A representing the total number of students participating in the online voice answer, u [, ]]The step function is represented, the value of the step function is 1 when the value in the brackets is greater than or equal to 0, the value of the step function is 0 when the value in the brackets is less than 0, delta { } represents the unit pulse function, the value of the unit pulse function is 1 when the value in the brackets is equal to 0, and the value of the unit pulse function is 0 when the value in the brackets is not equal to 0;
step S302, updating the sequencing position of the a-th student in the answer voice information sequence according to the sequencing moving value of the a-th student in the answer voice information sequence; increasing the testing time of the online voice answer of each student in the first half of the updated answer voice information sequence, and reducing the testing time of the online voice answer of each student in the second half of the updated answer voice information sequence.
The beneficial effects of the above technical scheme are: through the formula (4), the accuracy judgment result of the on-line voice answer of the students and the active degree of the on-line voice answer can be taken as comprehensive consideration factors, and the sequencing positions of the students in the answer voice information sequence are accurately and pertinently updated, so that the on-line voice answer state quality distribution of all the students can be conveniently updated in a short time. And increasing the testing time of the online voice answer of each student in the first half of the updated answer voice information sequence and reducing the testing time of the online voice answer of each student in the second half of the updated answer voice information sequence, so that the online answer testing time of each student can be distributed fairly, and the efficiency of online teaching can be improved.
Fig. 2 is a schematic structural diagram of an intelligent student online voice answer control system according to an embodiment of the present invention. The intelligent student online voice answer control system comprises an online answer voice information acquisition and processing module, a student online answer correctness judgment module, a student online answer activity degree determination module and a student online answer adjustment module; wherein the content of the first and second substances,
the online answer voice information acquisition and processing module is used for acquiring actual answer voice information of a plurality of students in an online voice answer process and carrying out noise reduction pretreatment on the actual answer voice information; according to the order of the plurality of students completing the voice answering, all the actual answering voice information is combined into a corresponding answering voice information sequence;
the student online answer correctness judging module is used for identifying the standard answer keyword condition contained in each actual answer voice information in the answer voice information sequence so as to judge the correctness of each student online voice answer;
the student online answer activity degree determining module is used for acquiring a real-time answer state of each student in an online voice answer process so as to determine the activity degree of each student online voice answer;
the student online answer adjusting module is used for updating the sequencing position of each student in the sequence of the plurality of students completing the voice answer according to the correctness judgment result of the online voice answer of each student and the activity degree of the online voice answer; and adjusting the testing time for carrying out on-line voice answering on each student according to the updated sequencing position.
The beneficial effects of the above technical scheme are: the intelligent student on-line voice answer control system analyzes the actual answer voice information of the student in the on-line voice answer process through the voice recognition and comparison mode, thereby automatically judging the correctness of the on-line answer of the student and simultaneously determining the active degree of the on-line answer of the student, thereby updating the sequencing positions of the students in the sequence of the plurality of students completing the voice answer by combining the correctness of the online answer and the activity degree of the online answer, and correspondingly adjusting the testing time of the online voice answer to the students, which can comprehensively and accurately judge whether the student answers on line or not, thus not only realizing the automatic judgment of the student answers and reducing the workload of teachers in on-line teaching, and can also carry out effectual adjustment to student's answer time to student's answer condition to this teaching efficiency that improves online teaching.
Preferably, the online answer voice information acquisition and processing module acquires actual answer voice information of a plurality of students in an online voice answer process, and performs noise reduction preprocessing on the actual answer voice information; and according to the order of the plurality of students completing the voice answering, all the actual answering voice information is combined into a corresponding answering voice information sequence, which specifically comprises the following steps:
indicating a microphone array to collect actual answer voice information of each student in an online voice answer process, and extracting and filtering background noise components contained in the actual answer voice information so as to realize noise reduction preprocessing;
recording the voice answer ending time corresponding to the online voice answer process of each student, and determining the sequence of completing the voice answer of all students according to the sequence of the voice answer ending time; and then, according to the sequence of completing the voice answering, sequentially combining all the actual answering voice information into a corresponding answering voice information sequence.
The beneficial effects of the above technical scheme are: the signal-to-noise ratio of the online answering voice information is reduced because the interference of background noise inevitably exists in the online voice answering process of students, and the reliability of the actual answering voice information can be improved to the maximum extent by extracting and filtering background noise components contained in the actual answering voice information. And the voice answer ending time corresponding to the online voice answer process of each student is recorded, and the sequence of completing the voice answer of all students is determined according to the sequence of the voice answer ending time, so that the initial form of answer voice information sequence can be efficiently and conveniently formed and used as the basis for subsequent sequence updating.
Preferably, the module for judging correctness of student online answer identifies a standard answer keyword condition contained in each actual answer voice message in the answer voice message sequence, so that judging correctness of each student online voice answer specifically comprises:
comparing the standard voice information of the answer key words contained in the standard answers corresponding to the questions answered by each student with the actual answer voice information of each student by using the following formula (1), thereby obtaining the number of the answer key words contained in the actual answer voice information of each student as the condition of the standard answer key words,
Figure BDA0003029584470000171
in the above formula (1), KaNumber f of answer keywords contained in actual answer speech information of the a-th studenta(n + m) represents the amplitude of the (n + m) th speech signal in the actual answer speech information of the (a) th student, fi(m) amplitude of mth speech signal in the standard speech information indicating the ith answer keyword included in the standard answer, fa(n+m)_fi(M) represents a volume amplitude difference between the (n + M) th speech signal in the actual answer speech information and the (M) th speech signal in the standard speech information of the ith answer keyword, MiThe total number of wave crests corresponding to the amplitude of the voice signal in the standard voice information of the ith answer keyword contained in the standard answer, NaThe method comprises the steps that the total number of wave crests corresponding to the amplitude of voice signals in actual answer voice information of an a-th student is represented, I represents the total number of answer keywords contained in a standard answer, delta { } represents a unit pulse function, the value of the unit pulse function is 1 when the numerical value in brackets is equal to 0, and the value of the unit pulse function is 0 when the numerical value in brackets is not equal to 0;
then, the correctness of the online voice answer of each student is judged by using the following formula (2),
Figure BDA0003029584470000181
in the above formula (2), PaRepresents the correctness evaluation value, Q, of the on-line voice answer of the a-th studentiThe value of the ith answer key word in the standard answer is represented, the value is preset, the value range of the value is 10-20, and u { } represents the value of the ith answer key word in the standard answerStep function, and the value of the step function is 1 when the value in the bracket is greater than or equal to 0, and the value of the step function is 0 when the value in the bracket is less than 0;
when P is presentaWhen the answer is 1, the answer of the a-th student is correct;
when P is presentaWhen the answer is 0, the online voice answer of the a-th student is incorrect;
and the number of the first and second groups,
this online answer liveness degree of student confirms module gathers the online pronunciation answer in-process real-time answer state of every student to confirm that the liveness degree of online pronunciation answer of every student specifically includes:
collecting the answering time of each student and the communication connection times between each student and a voice answering terminal in the online voice answering process of each student; then the following formula (3) is used to determine the evaluation value of the activity degree of the online voice answering of each student,
Figure BDA0003029584470000182
in the above formula (3), ηaAn evaluation value T representing the activity degree of the online voice answer of the a-th studentaShows that the answer of the a-th student in the online voice answer process consumes time, Ta+bShows that the answer of the (a + b) th student is time-consuming in the process of the online voice answer, LaIndicates the communication connection times between the a-th student and the voice answering terminal in the process of the online voice answering, La+bThe number of communication connections between the (a + b) th student and the voice answer terminal in the current online voice answer process is represented, and A represents the total number of students participating in the current online voice answer process.
The beneficial effects of the above technical scheme are: because each question corresponds to a standard answer in the online answering process, the standard answer is composed of a plurality of Chinese and/or foreign characters, and each Chinese and/or foreign character group forms an answer keyword of the standard answer. By using the formula (1), the standard voice information corresponding to the answer keyword (the standard voice information can be obtained by performing artificial voice conversion on the answer keyword, which belongs to the conventional means of intelligent voice conversion, and is not described in further detail here) is compared with the voice signal amplitude of the actual answer voice information of each student, so that the number of the standard answer keyword contained in the actual answer voice information can be quickly and accurately obtained. And by using the formula (2), the correctness of the online voice answer of the student can be quantitatively evaluated, so that the condition of misjudgment is effectively avoided. And by using the formula (3), the activity degree of the online voice answer of the student can be objectively and quantitatively evaluated on the basis of the answering time of the student and the communication connection frequency between the student and the voice answer terminal.
Preferably, the student online answer adjusting module updates the sequencing position of each student in the answer voice information sequence according to the correctness judgment result of each student online voice answer and the activity degree of the online voice answer; and according to the updated answer voice information sequence, adjusting the test time for performing online voice answer on each student specifically comprises:
determining a ranking shift value of each student in the answer speech information sequence when updating the ranking position of each student in the answer speech information sequence by using the following formula (4),
Figure BDA0003029584470000191
in the above formula (4), QaExpressing the on-line voice answer score, Q, of the a-th studenta+bRepresents the on-line voice answer score, lambda, of the a + b th studentaRepresents the sorting movement value of the a-th student in the answering speech information sequence and when lambda isaWhen the answer is more than or equal to 0, the a-th student moves forward to the position where the answer voice information sequence is locatedaI position, when lambdaaWhen the answer is less than 0, the position of the a-th student at the current answer voice information sequence is moved backwards by lambdaaThe number of the | positions is,ηa+ban evaluation value representing the activity degree of the online voice answer of the (a + b) th student, A representing the total number of students participating in the online voice answer, u [, ]]The step function is represented, the value of the step function is 1 when the value in the brackets is greater than or equal to 0, the value of the step function is 0 when the value in the brackets is less than 0, delta { } represents the unit pulse function, the value of the unit pulse function is 1 when the value in the brackets is equal to 0, and the value of the unit pulse function is 0 when the value in the brackets is not equal to 0;
finally, updating the sequencing position of the a-th student in the answer voice information sequence according to the sequencing moving value of the a-th student in the answer voice information sequence; increasing the testing time of the online voice answer of each student in the first half of the updated answer voice information sequence, and reducing the testing time of the online voice answer of each student in the second half of the updated answer voice information sequence.
The beneficial effects of the above technical scheme are: through the formula (4), the accuracy judgment result of the on-line voice answer of the students and the active degree of the on-line voice answer can be taken as comprehensive consideration factors, and the sequencing positions of the students in the answer voice information sequence are accurately and pertinently updated, so that the on-line voice answer state quality distribution of all the students can be conveniently updated in a short time. And increasing the testing time of the online voice answer of each student in the first half of the updated answer voice information sequence and reducing the testing time of the online voice answer of each student in the second half of the updated answer voice information sequence, so that the online answer testing time of each student can be distributed fairly, and the efficiency of online teaching can be improved.
From the content of the above embodiment, the intelligent student online voice answer control method and system collects the actual answer voice information of a plurality of students in the online voice answer process, and performs noise reduction preprocessing on the actual answer voice information; according to the sequence of the voice answer completion of a plurality of students, all the actual answer voice information is combined into a corresponding answer voice information sequence, and then the condition of standard answer key words contained in each actual answer voice information in the answer voice information sequence is identified, so that the correctness of the online voice answer of each student is judged; collecting the real-time answering state of each student in the online voice answering process so as to determine the activity degree of online voice answering of each student, and finally updating the sequencing position of each student in the sequence of completing voice answering of a plurality of students according to the correctness judgment result of the online voice answering of each student and the activity degree of the online voice answering; adjusting the testing time for performing online voice answering on each student according to the updated sequencing position; therefore, the intelligent student on-line voice answer control method and the system analyze the actual answer voice information in the student on-line voice answer process in a voice recognition and comparison mode, thereby automatically judging the correctness of the on-line answer of the student and simultaneously determining the active degree of the on-line answer of the student, thereby updating the sequencing positions of the students in the sequence of the plurality of students completing the voice answer by combining the correctness of the online answer and the activity degree of the online answer, and correspondingly adjusting the testing time of the online voice answer to the students, which can comprehensively and accurately judge whether the student answers on line or not, thus not only realizing the automatic judgment of the student answers and reducing the workload of teachers in on-line teaching, and can also carry out effectual adjustment to student's answer time to student's answer condition to this teaching efficiency that improves online teaching.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.

Claims (8)

1. The intelligent chemist online voice answer control method is characterized by comprising the following steps:
step S1, collecting actual answer voice information of a plurality of students in an online voice answer process, and carrying out noise reduction pretreatment on the actual answer voice information; according to the sequence of the voice answering completed by the students, all the actual answering voice information is combined into a corresponding answering voice information sequence;
step S2, recognizing the standard answer keyword condition contained in each actual answer voice information in the answer voice information sequence, thereby judging the correctness of each student on-line voice answer; collecting the real-time answering state of each student in the online voice answering process, thereby determining the active degree of each student in online voice answering;
step S3, updating the sequencing position of each student in the sequence of the plurality of students completing the voice answer according to the correctness judgment result of the online voice answer of each student and the active degree of the online voice answer; and adjusting the testing time for carrying out on-line voice answering on each student according to the updated sequencing position.
2. The intelligent student online voice question answering control method of claim 1, characterized in that: in step S1, collecting actual answer speech information of a plurality of students during online speech answering, and performing noise reduction preprocessing on the actual answer speech information; and according to the order of the plurality of students completing the voice answering, all the actual answering voice information is combined into a corresponding answering voice information sequence, which specifically comprises the following steps:
step S101, instructing a microphone array to collect actual answer voice information of each student in an online voice answer process, and extracting and filtering background noise components contained in the actual answer voice information so as to realize noise reduction preprocessing;
step S102, recording the voice answer ending time corresponding to the online voice answer process of each student, and determining the sequence of all students completing voice answer according to the sequence of the voice answer ending time; and then according to the sequence of completing the voice answering, sequentially combining all the actual answering voice information into a corresponding answering voice information sequence.
3. The intelligent student online voice question answering control method of claim 2, characterized in that: in step S2, recognizing a standard answer keyword condition contained in each actual answer speech information in the answer speech information sequence, so as to determine correctness of online speech answer of each student; the method for acquiring the real-time answer state of each student in the online voice answer process so as to determine the activity degree of each student in the online voice answer specifically comprises the following steps:
step S201, using the following formula (1), comparing the standard voice information of the answer keywords contained in the standard answer corresponding to the question answered by each student with the actual answer voice information of each student, so as to obtain the number of the answer keywords contained in the actual answer voice information of each student as the standard answer keyword condition,
Figure FDA0003029584460000021
in the above formula (1), KaNumber f of answer keywords contained in actual answer speech information of the a-th studenta(n + m) represents the amplitude of the (n + m) th speech signal in the actual answer speech information of the (a) th student, fi(m) amplitude of mth speech signal in the standard speech information indicating the ith answer keyword included in the standard answer, fa(n+m)-fi(M) represents a volume amplitude difference between the (n + M) th speech signal in the actual answer speech information and the (M) th speech signal in the standard speech information of the ith answer keyword, MiThe total number of wave crests corresponding to the amplitude of the voice signal in the standard voice information of the ith answer keyword contained in the standard answer, NaThe method comprises the steps that the total number of wave crests corresponding to the amplitude of voice signals in actual answer voice information of an a-th student is represented, I represents the total number of answer keywords contained in a standard answer, delta { } represents a unit pulse function, the value of the unit pulse function is 1 when the numerical value in brackets is equal to 0, and the value of the unit pulse function is 0 when the numerical value in brackets is not equal to 0;
step S202, using the following formula (2) to judge the correctness of the on-line voice answer of each student,
Figure FDA0003029584460000031
in the above formula (2), PaRepresents the correctness evaluation value, Q, of the on-line voice answer of the a-th studentiThe method comprises the steps that the value of an ith answer keyword contained in a standard answer is represented, the value is preset, the value range of the value is 10-20, u { } represents a step function, the value of the step function is 1 when the value in brackets is greater than or equal to 0, and the value of the step function is 0 when the value in brackets is less than 0;
when P is presentaWhen the answer is 1, the answer of the a-th student is correct;
when P is presentaWhen the answer is 0, the online voice answer of the a-th student is incorrect;
step S203, collecting answering time of each student and communication connection times between each student and a voice answering terminal in the online voice answering process of each student; then the following formula (3) is used to determine the evaluation value of the activity degree of the online voice answering of each student,
Figure FDA0003029584460000032
in the above formula (3), ηaAn evaluation value T representing the activity degree of the online voice answer of the a-th studentaShows that the answer of the a-th student in the online voice answer process consumes time, Ta+bShows that the answer of the (a + b) th student is time-consuming in the process of the online voice answer, LaIndicates the communication connection times between the a-th student and the voice answering terminal in the process of the online voice answering, La+bThe communication connection times between the a + b students and the voice answer terminal in the current on-line voice answer process are shown, A shows the students taking part in the current on-line voice answer processThe total number of (c).
4. The intelligent student online voice question answering control method of claim 3, characterized in that: in step S3, updating the ranking position of each student in the answer speech information sequence according to the correctness judgment result of the online speech answer of each student and the activity degree of the online speech answer; and according to the updated answer voice information sequence, adjusting the test time for performing online voice answer on each student specifically comprises:
step S301, determining the sequencing moving value of each student in the answer speech information sequence when the sequencing position of each student in the answer speech information sequence is updated by using the following formula (4),
Figure FDA0003029584460000041
in the above formula (4), QaExpressing the on-line voice answer score, Q, of the a-th studenta+bRepresents the on-line voice answer score, lambda, of the a + b th studentaRepresents the sorting movement value of the a-th student in the answering voice information sequence and when lambda isaWhen the answer is more than or equal to 0, the a-th student moves forwards by lambda from the current position of the answer voice information sequenceaI position, when lambdaaWhen the answer is less than 0, the position of the a-th student at the current answer voice information sequence is moved backwards by lambdaaL positions, ηa+bAn evaluation value representing the activity degree of the online voice answer of the (a + b) th student, A representing the total number of students participating in the online voice answer, u [, ]]The step function is represented, the value of the step function is 1 when the value in the brackets is greater than or equal to 0, the value of the step function is 0 when the value in the brackets is less than 0, delta { } represents the unit pulse function, the value of the unit pulse function is 1 when the value in the brackets is equal to 0, and the value of the unit pulse function is 0 when the value in the brackets is not equal to 0;
step S302, updating the sequencing position of the a-th student in the answer voice information sequence according to the sequencing moving value of the a-th student in the answer voice information sequence; increasing the testing time of the online voice answer of each student in the first half of the updated answer voice information sequence, and reducing the testing time of the online voice answer of each student in the second half of the updated answer voice information sequence.
5. The intelligent student online voice answer control system is characterized by comprising an online answer voice information acquisition and processing module, a student online answer correctness judging module, a student online answer activity degree determining module and a student online answer adjusting module; wherein the content of the first and second substances,
the online answer voice information acquisition and processing module is used for acquiring actual answer voice information of a plurality of students in an online voice answer process and carrying out noise reduction pretreatment on the actual answer voice information; according to the sequence of the voice answering completed by the students, all the actual answering voice information is combined into a corresponding answering voice information sequence;
the student online answer correctness judging module is used for identifying the standard answer keyword condition contained in each actual answer voice information in the answer voice information sequence so as to judge the correctness of each student online voice answer;
the student online answer activity degree determining module is used for acquiring a real-time answer state of each student in an online voice answer process so as to determine the activity degree of each student online voice answer; the student online answer adjusting module is used for updating the sequencing position of each student in the sequence of the plurality of students completing the voice answer according to the correctness judgment result of the online voice answer of each student and the activity degree of the online voice answer; and adjusting the testing time for carrying out on-line voice answering on each student according to the updated sequencing position.
6. The intelligent student online voice question answering control system of claim 5, wherein: the online answer voice information acquisition and processing module acquires actual answer voice information of a plurality of students in an online voice answer process, and performs noise reduction pretreatment on the actual answer voice information; and according to the order of the plurality of students completing the voice answering, all the actual answering voice information is combined into a corresponding answering voice information sequence, which specifically comprises the following steps:
indicating a microphone array to collect actual answer voice information of each student in an online voice answer process, and extracting and filtering background noise components contained in the actual answer voice information so as to realize noise reduction preprocessing;
recording the voice answer ending time corresponding to the online voice answer process of each student, and determining the sequence of completing the voice answer of all students according to the sequence of the voice answer ending time; and then according to the sequence of completing the voice answering, sequentially combining all the actual answering voice information into a corresponding answering voice information sequence.
7. The intelligent student online voice question answering control system of claim 6, wherein: the module for judging correctness of on-line student answer identifies the condition of the standard answer key words contained in each actual answer voice message in the answer voice message sequence, so that the judgment of correctness of on-line student voice answer specifically comprises the following steps:
comparing the standard voice information of the answer key words contained in the standard answers corresponding to the questions answered by each student with the actual answer voice information of each student by using the following formula (1), thereby obtaining the number of the answer key words contained in the actual answer voice information of each student as the condition of the standard answer key words,
Figure FDA0003029584460000061
in the above formula (1), KaNumber f of answer keywords contained in actual answer speech information of the a-th studenta(n + m) represents the actual answer of the a-th studentAmplitude, f, of the n + m-th speech signal in the speech informationi(m) amplitude of mth speech signal in the standard speech information indicating the ith answer keyword included in the standard answer, fa(n+m)-fi(M) represents a volume amplitude difference between the (n + M) th speech signal in the actual answer speech information and the (M) th speech signal in the standard speech information of the ith answer keyword, MiThe total number of wave crests corresponding to the amplitude of the voice signal in the standard voice information of the ith answer keyword contained in the standard answer, NaThe method comprises the steps that the total number of wave crests corresponding to the amplitude of voice signals in actual answer voice information of an a-th student is represented, I represents the total number of answer keywords contained in a standard answer, delta { } represents a unit pulse function, the value of the unit pulse function is 1 when the numerical value in brackets is equal to 0, and the value of the unit pulse function is 0 when the numerical value in brackets is not equal to 0;
then, the correctness of the online voice answer of each student is judged by using the following formula (2),
Figure FDA0003029584460000071
in the above formula (2), PaRepresents the correctness evaluation value, Q, of the on-line voice answer of the a-th studentiThe method comprises the steps that the value of an ith answer keyword contained in a standard answer is represented, the value is preset, the value range of the value is 10-20, u { } represents a step function, the value of the step function is 1 when the value in brackets is greater than or equal to 0, and the value of the step function is 0 when the value in brackets is less than 0;
when P is presentaWhen the answer is 1, the answer of the a-th student is correct;
when P is presentaWhen the answer is 0, the online voice answer of the a-th student is incorrect;
and the number of the first and second groups,
the online student answer liveness determining module collects the real-time answer state of each student in the online voice answer process, so that the liveness determining module determines the liveness of each student in the online voice answer specifically comprises the following steps: collecting the answering time of each student and the communication connection times between each student and a voice answering terminal in the online voice answering process of each student; then the following formula (3) is used to determine the evaluation value of the activity degree of the online voice answering of each student,
Figure FDA0003029584460000072
in the above formula (3), ηaAn evaluation value T representing the activity degree of the online voice answer of the a-th studentaShows that the answer of the a-th student in the online voice answer process consumes time, Ta+bShows that the answer of the (a + b) th student is time-consuming in the process of the online voice answer, LaIndicates the communication connection times between the a-th student and the voice answering terminal in the process of the online voice answering, La+bThe number of communication connections between the (a + b) th student and the voice answer terminal in the current online voice answer process is represented, and A represents the total number of students participating in the current online voice answer process.
8. The intelligent student online voice question answering control system of claim 7, wherein: the student online answer adjusting module updates the sequencing position of each student in the answer voice information sequence according to the correctness judgment result of each student online voice answer and the active degree of the online voice answer; and according to the updated answer voice information sequence, adjusting the test time for performing online voice answer on each student specifically comprises:
determining a ranking shift value of each student in the answer speech information sequence when updating the ranking position of each student in the answer speech information sequence using the following formula (4),
Figure FDA0003029584460000081
in the above formula (4), QaExpressing the on-line voice answer score, Q, of the a-th studenta+bRepresents the on-line voice answer score, lambda, of the a + b th studentaRepresents the sorting movement value of the a-th student in the answering voice information sequence and when lambda isaWhen the answer is more than or equal to 0, the a-th student moves forwards by lambda from the current position of the answer voice information sequenceaI position, when lambdaaWhen the answer is less than 0, the position of the a-th student at the current answer voice information sequence is moved backwards by lambdaaL positions, ηa+bAn evaluation value representing the activity degree of the online voice answer of the (a + b) th student, A representing the total number of students participating in the online voice answer, u [, ]]The step function is represented, the value of the step function is 1 when the value in the brackets is greater than or equal to 0, the value of the step function is 0 when the value in the brackets is less than 0, delta { } represents the unit pulse function, the value of the unit pulse function is 1 when the value in the brackets is equal to 0, and the value of the unit pulse function is 0 when the value in the brackets is not equal to 0;
finally, updating the sequencing position of the a-th student in the answer voice information sequence according to the sequencing moving value of the a-th student in the answer voice information sequence; increasing the testing time of the online voice answer of each student in the first half of the updated answer voice information sequence, and reducing the testing time of the online voice answer of each student in the second half of the updated answer voice information sequence.
CN202110426022.4A 2021-04-20 2021-04-20 Intelligent on-line voice answer control method and system for chemists Pending CN113178208A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110426022.4A CN113178208A (en) 2021-04-20 2021-04-20 Intelligent on-line voice answer control method and system for chemists

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110426022.4A CN113178208A (en) 2021-04-20 2021-04-20 Intelligent on-line voice answer control method and system for chemists

Publications (1)

Publication Number Publication Date
CN113178208A true CN113178208A (en) 2021-07-27

Family

ID=76924409

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110426022.4A Pending CN113178208A (en) 2021-04-20 2021-04-20 Intelligent on-line voice answer control method and system for chemists

Country Status (1)

Country Link
CN (1) CN113178208A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113506585A (en) * 2021-09-09 2021-10-15 深圳市一号互联科技有限公司 Quality evaluation method and system for voice call
CN114566167A (en) * 2022-02-28 2022-05-31 安徽淘云科技股份有限公司 Voice answer method and device, electronic equipment and storage medium

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113506585A (en) * 2021-09-09 2021-10-15 深圳市一号互联科技有限公司 Quality evaluation method and system for voice call
CN114566167A (en) * 2022-02-28 2022-05-31 安徽淘云科技股份有限公司 Voice answer method and device, electronic equipment and storage medium

Similar Documents

Publication Publication Date Title
CN113178208A (en) Intelligent on-line voice answer control method and system for chemists
CN111144191B (en) Font identification method, font identification device, electronic equipment and storage medium
CN110544481B (en) S-T classification method and device based on voiceprint recognition and equipment terminal
CN114841841A (en) Intelligent education platform interaction system and interaction method for teaching interaction
CN116259004A (en) Student learning state detection method and system applied to online education
CN112015783B (en) Interactive learning process generation method and system
CN1581293A (en) Man-machine interacting method and device based on limited-set voice identification
CN116092639A (en) Aphasia rehabilitation training system and method based on course self-adaptive adjustment
CN113674572A (en) Method and system for prompting student to answer questions through playing voice
CN113035236B (en) Quality inspection method and device for voice synthesis data
CN114372476A (en) Semantic truncation detection method, device and equipment and computer readable storage medium
CN112016431B (en) Intelligent detection and analysis method and system for teaching quality
CN113593326A (en) English pronunciation teaching device and method
CN112991826A (en) English pronunciation quality recognition and evaluation system
CN113409635A (en) Interactive teaching method and system based on virtual reality scene
CN112948554A (en) Real-time multi-modal dialogue emotion analysis method based on reinforcement learning and domain knowledge
CN112163975A (en) Intelligent learning guiding and prompting method and system
CN114625302B (en) Electronic question making method, device, system and storage medium
CN114743541B (en) Interactive system for English listening and speaking learning
CN111261193B (en) Pronunciation training and teaching system
CN110992739B (en) Student on-line dictation system
CN112711675B (en) Teaching video selection method, device and equipment and readable storage medium
CN111369998B (en) Data processing method and electronic equipment
CN116797416A (en) Question correction method, device, electronic equipment and storage medium
CN115240494A (en) Online education achievement analysis method based on big data

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination