CN116013286A - Intelligent evaluation method, system, equipment and medium for English reading capability - Google Patents
Intelligent evaluation method, system, equipment and medium for English reading capability Download PDFInfo
- Publication number
- CN116013286A CN116013286A CN202211558336.0A CN202211558336A CN116013286A CN 116013286 A CN116013286 A CN 116013286A CN 202211558336 A CN202211558336 A CN 202211558336A CN 116013286 A CN116013286 A CN 116013286A
- Authority
- CN
- China
- Prior art keywords
- reading
- audio
- english
- user terminal
- data packet
- 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
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Electrically Operated Instructional Devices (AREA)
Abstract
The application relates to an intelligent evaluation method, system, equipment and medium for English reading capability, which comprises the steps of sending a pre-selected reading text to a user terminal when an evaluation request for English reading from the user terminal binding with student identity information is received; when receiving audio data generated by the user terminal according to the reading text, sending the audio data to a voice recognition model; the voice recognition model screens out standard audios of the pre-selected associated reading texts based on the reading texts; packaging the standard audio and the associated audio data to generate a reading data packet; and sending the reading data packet to the teacher terminal bound with the user terminal. The method has the effects of reducing labor cost and time cost for evaluating English reading ability of students and improving efficiency of evaluating English reading ability.
Description
Technical Field
The application relates to the technical field of English reading, in particular to an intelligent evaluation method, system, equipment and medium for English reading capability.
Background
Conventionally, for evaluating the English reading ability of students, a teacher is generally used for listening to the student reading on site, and evaluating the English reading quality and level of the students according to own experience.
However, the time and experience of teachers are limited, the time cost and labor cost for evaluating the reading ability of students in one-to-one correspondence in a classroom are too high, and the efficiency is low, so that improvement on the English reading ability evaluation mode of the students is required.
Disclosure of Invention
In order to reduce labor cost and time cost for English reading capability evaluation of students and improve efficiency of English reading capability evaluation, the application provides an intelligent English reading capability evaluation method, system, equipment and medium.
The first object of the present invention is achieved by the following technical solutions:
an intelligent evaluation method for English reading capability comprises the following steps:
when receiving an evaluation request for English reading from a user terminal bound with student identity information, transmitting a pre-selected reading text to the user terminal;
when receiving audio data generated by the user terminal according to the reading text, sending the audio data to a voice recognition model;
the voice recognition model screens out standard audios of the pre-selected associated reading texts based on the reading texts;
packaging the standard audio and the associated audio data to generate a reading data packet;
and sending the reading data packet to the teacher terminal bound with the user terminal.
By adopting the technical scheme, after the rest time of students is spent, an evaluation request is sent by the user terminal to obtain the pre-selected reading text, further the students can read or read according to the obtained English words and sentences, the audio frequency of the students during reading is recorded and stored to obtain audio data, the standard audio corresponding to the audio data of the students is further automatically identified in the voice recognition model, namely, the audio data and the standard audio of standard pronunciation of English words and sentences are packaged to obtain a reading data packet, and the reading data packet is sent to a teacher terminal bound with the user terminal, namely, a teacher can evaluate the English reading capability of the students of the class one by one and quickly through the teacher terminal in the rest time, the time cost and the labor cost are saved, and the teacher can evaluate the English reading capability of the students more easily by comparing the standard audio with the audio data of the students as a reference, so that the efficiency of evaluating the English reading capability is improved.
In a preferred example, the present application: if the type of the reading text is word type, after the step of packaging the standard audio and the associated audio data to generate a reading data packet, the following steps are executed:
transmitting the reading data packet to an audio frequency correction model;
the audio frequency correction model compares the approximation degree of the audio frequency data in the reading data packet with the standard audio frequency according to the comparison rule, and outputs a word class approximation value;
word class approximations are entered into the reading data packet.
By adopting the technical scheme, if the reading text is only a single word, the reading data packet is generated, then the reading data packet is further sent to the audio frequency correction model, the audio frequency data read by the student is compared with the standard audio frequency through the voice recognition function, the word class approximation value is obtained and is input into the reading data packet, and the word class approximation value is used as evaluation of one dimension of the reading capability of the student so as to assist a teacher in judging the English reading accuracy of the student.
In a preferred example, the present application: if the type of the reading text is sentence type, after the step of sending the reading data packet to the audio collation model, executing the following steps:
the audio frequency correction model screens out standard audio frequency corresponding to the key word group based on the pre-selected key word group in the reading text;
performing approximation comparison on the audio data of the key word group and the standard audio of the key word group according to the comparison rule, and outputting sentence approximation values;
sentence class approximations are input into the reading data packet.
By adopting the technical scheme, in order to better evaluate the grasp of students to terminal word groups and save the time consumption of comparing audio data with standard audio, when the type of the reading text is sentence type, only the key word groups in the reading text are extracted, and only the audio data of the key word groups are compared with the standard audio of the key word groups, so that the comparison of key word group approximation values in the reading text is realized, sentence approximation values are input into the reading data packet, and the English reading capability of the students can be evaluated more comprehensively and accurately by combining with the evaluation of teachers to the whole reading text.
In a preferred example, the present application: the step of comparing the approximation degree of the audio data in the reading data packet and the standard audio by the audio frequency correction model according to the comparison rule and outputting the word class approximation value comprises the following specific steps:
the audio frequency correction model obtains the audio frequency characteristic information of the audio frequency data;
acquiring standard characteristic information of standard audio from a cloud platform based on the reading text;
and comparing the audio characteristic information with the standard characteristic information, and calculating to obtain word class approximation values based on comparison results of the audio characteristic information and the standard characteristic information.
By adopting the technical scheme, the audio characteristics of the audio read by students are extracted, namely, the audio waveforms of all syllables of words are subjected to framing, the sound waveforms of audio data and the sound waveforms of standard audio are subjected to frame-by-frame comparison, approximate judgment is carried out through the superposition condition of the waveforms, and a word class approximate value is obtained.
In a preferred example, the present application: after the step of sending the audio data to the speech recognition model when receiving the audio data generated from the user terminal according to the reading text, the following steps are executed:
when the audio data is sent to the voice recognition model, starting countdown of a preset interval duration;
and when the countdown of the preset interval duration is finished, sending the next preset reading text to the user terminal, wherein the interval duration is set by the user terminal in a self-defining way.
Through adopting above-mentioned technical scheme, when the student accomplishes reading of an english word or sentence paragraph through user terminal to after generating audio data, through setting up the interval duration of predetermineeing, user terminal can realize automatic switch english word, sentence paragraph's reading, and interval duration can be set up by user terminal self-definition, makes things convenient for the student to carry out continuous english reading exercise, and the regulation of interval duration promotes user experience and feels.
In a preferred example, the present application: the intelligent evaluation method for English reading capability further comprises the following steps:
acquiring all sentence approximation values generated by the user terminal in the past, and calculating the average value of the sentence approximation values;
identifying an approximate value interval to which the average value belongs;
acquiring associated preset interval time based on the approximate value interval;
and adjusting the interval duration of reading text transmission to the acquired interval time.
By adopting the technical scheme, through the evaluation results of the historical reading exercise of each student, namely the average value of the historical sentence approximation values, and through determining the approximation value interval in which the average value is located, the approximation value interval is 0% -100%, different approximation value intervals correspond to different interval time, wherein the larger the average value is, the larger the corresponding approximation value interval is, the longer the interval time is, namely the interval time for reading text switching can be automatically adjusted through the reading ability of different students, the shorter the interval time required by the student with better reading ability is, the longer the interval time is for the student with worse reading ability is, and further, better reading experience is provided for the student with worse reading ability, and more efficient reading evaluation is provided for the student with better reading ability.
The second object of the present invention is achieved by the following technical solutions:
an intelligent evaluating system for spoken english practice, comprising:
the evaluation request module is used for sending a pre-selected reading text to the user terminal when receiving an evaluation request for English reading from the user terminal bound with the student identity information;
the audio sending module is used for sending the audio data to the voice recognition model when receiving the audio data generated by the user terminal according to the reading text;
the standard audio module is used for screening out standard audio of the pre-selected associated reading text based on the reading text by the voice recognition model;
the audio packaging module is used for packaging the standard audio and the associated audio data to generate a reading data packet;
and the data packet sending module is used for sending the reading data packet to the teacher terminal bound with the user terminal.
By adopting the technical scheme, after the rest time of students is spent, an evaluation request is sent by the user terminal to obtain the pre-selected reading text, further the students can read or read according to the obtained English words and sentences, the audio frequency of the students during reading is recorded and stored to obtain audio data, the standard audio corresponding to the audio data of the students is further automatically identified in the voice recognition model, namely, the audio data and the standard audio of standard pronunciation of English words and sentences are packaged to obtain a reading data packet, and the reading data packet is sent to a teacher terminal bound with the user terminal, namely, a teacher can evaluate the English reading capability of the students of the class one by one and quickly through the teacher terminal in the rest time, the time cost and the labor cost are saved, and the teacher can evaluate the English reading capability of the students more easily by comparing the standard audio with the audio data of the students as a reference, so that the efficiency of evaluating the English reading capability is improved.
Optionally, if the type of the read text is a word type, the method further includes:
the audio frequency proofreading module is used for sending the reading data packet to the audio frequency proofreading model;
the approximate value module is used for comparing the approximate degree of the audio data in the reading data packet with the standard audio according to the comparison rule by the audio comparison model and outputting a word class approximate value;
and the word class approximation input module is used for inputting the word class approximation into the reading data packet.
By adopting the technical proposal, the utility model has the advantages that,
the third object of the present application is achieved by the following technical solutions:
a computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of an intelligent assessment method of english reading ability as described above when the computer program is executed by the processor.
The fourth object of the present application is achieved by the following technical solutions:
a computer readable storage medium storing a computer program which, when executed by a processor, implements the steps of an intelligent assessment method for english reading ability described above.
In summary, the present application includes at least one of the following beneficial technical effects:
1. the teacher can evaluate the English reading ability of the students in the class one by one and quickly through the teacher terminal and the rest time, so that the time cost and the labor cost are saved, and the teacher can evaluate the English reading ability of the students more easily by taking the standard audio and the audio data of the students as reference contrast, and the efficiency of evaluating the English reading ability is improved;
2. if the reading text is only a single word, the reading data packet is generated, the reading data packet is further sent to an audio frequency correction model, the audio frequency data read by the student is compared with the standard audio frequency through a voice recognition function, a word class approximation value is obtained and is input into the reading data packet, and the word class approximation value is used as evaluation of one dimension of the reading capability of the student to assist a teacher in judging the English reading accuracy of the student;
3. in order to better evaluate the grasp of students to terminal word groups and save the time consumption of comparing audio data with standard audio, when the type of a reading text is sentence type, only the key word group in the reading text is extracted, and only the audio data of the key word group and the standard audio of the key word group are compared, so that the comparison of key word group approximate values in the reading text is realized, sentence approximate values are input into a reading data packet, and the evaluation of the whole section of reading text by combining with a teacher can evaluate the English reading capability of the students more comprehensively and accurately;
4. when students finish reading English words or sentence fragments through the user terminal and generate audio data, the user terminal can automatically switch the reading of the English words or sentence fragments by setting preset interval time, the interval time can be set by the user terminal in a self-defined mode, continuous English reading exercise is convenient for the students, and user experience is improved through adjustment of the interval time.
Drawings
FIG. 1 is a flowchart of an implementation of an embodiment of an intelligent evaluation method for English reading ability of the present application;
FIG. 2 is an interface display diagram of an embodiment of an intelligent evaluation method for English reading ability according to the present application;
FIG. 3 is another interface presentation diagram in an embodiment of an intelligent assessment method for English reading ability of the present application;
FIG. 4 is a flowchart of an implementation of the method for intelligently evaluating English reading ability according to an embodiment of the present invention after step S40;
FIG. 5 is a flowchart of another implementation after step S41 in an embodiment of an intelligent evaluation method for English reading ability of the present application;
FIG. 6 is a flowchart showing an implementation of step S42 in an embodiment of an intelligent evaluation method for English reading ability of the present application;
FIG. 7 is a flowchart of another implementation in an embodiment of an intelligent assessment method for English reading ability of the present application;
fig. 8 is a schematic block diagram of an intelligent evaluation system for english reading ability of the present application.
Detailed Description
The present application is described in further detail below in conjunction with figures 1-8.
In an embodiment, as shown in fig. 1, the application discloses an intelligent evaluation method for english reading ability, which specifically includes the following steps:
s10: when receiving an evaluation request for English reading from a user terminal bound with student identity information, transmitting a pre-selected reading text to the user terminal;
in this embodiment, the user terminal is a mobile terminal or a PC terminal such as a smart phone, a tablet computer, etc. for students to use. The student logs in the APP through the user terminal to send an evaluation request, the reading text comprises English words, single English sentences, single English sections and other reading types, and referring to FIG. 2, the student can perform self-defined selection of the reading type of the reading text through the user terminal, namely, the word book or the sentence book is selected, the pre-selection of the reading text is further performed, and the reading text corresponds to the current grade of the student.
Specifically, after logging in the user terminal through self identity information, the student sends out an evaluation request for requesting English reading capability evaluation to select the reading type of the reading text, after the reading type is selected, based on the reading text selected by the evaluation request, the preset English word and sentence library sends the corresponding reading type and the selected reading text to the user terminal.
S20: when receiving audio data generated by the user terminal according to the reading text, sending the audio data to a voice recognition model;
in the embodiment, the student reads or follows the reading text displayed by the user terminal and records the audio data of the student, wherein the audio data is the audio read by the student;
the speech recognition model is a trained linear model for screening standard audio corresponding to the audio data based on the read text.
Specifically, referring to fig. 3, after receiving the reading text, the student triggers a recording function through the user terminal, and spells out the corresponding reading text to obtain audio data, wherein the audio data is stored according to the unit name, and the audio data is covered when recording again. The audio data is further sent to a speech recognition model.
S30: the voice recognition model screens out standard audios of the pre-selected associated reading texts based on the reading texts;
in this embodiment, the standard audio is a pronunciation standard of the pre-recorded reading text, and may be pre-recorded by a professional.
Specifically, each standard audio is associated with a corresponding reading text in advance, and each standard audio is associated with one reading text, so that the voice recognition model can screen out the standard audio corresponding to the audio data read by the student through the reading text.
S40: packaging the standard audio and the associated audio data to generate a reading data packet;
in the embodiment, after the standard audio and the audio data of the student are packaged into the reading data packet, the reading capability of the student is conveniently evaluated.
If the reading text is the whole English paragraph, the audio data and standard audio of each English sentence in the paragraph are packed independently.
Specifically, the data of the record generated by the student according to the reading text and the standard pronunciation of the record are packed to obtain the reading data packet of the student.
S50: and sending the reading data packet to the teacher terminal bound with the user terminal.
In this embodiment, the teacher terminal is a smart phone, a tablet computer or a PC terminal for a teacher, and the english teacher can bind with the user terminal of his class student through the teacher terminal.
Specifically, all reading data packets generated by the English reading evaluation of the students are sent to the teacher terminal.
In one embodiment, if the type of the read text is a word type, referring to fig. 4, the following steps are performed after step S40:
s41: transmitting the reading data packet to an audio frequency correction model;
s42: the audio frequency correction model compares the approximation degree of the audio frequency data in the reading data packet with the standard audio frequency according to the comparison rule, and outputs a word class approximation value;
s43: word class approximations are entered into the reading data packet.
In this embodiment, the audio collation model is a feature comparison model that is trained and communicatively connected to the big data cloud platform.
The comparison rule is a preset rule for comparing the waveform similarity of the audio.
Specifically, the reading data packet is sent to the audio frequency checking model, the audio frequency checking model compares the similarity between the audio frequency data in the reading data packet and the standard audio frequency after receiving the reading data, obtains the approximate value of the audio frequency data and the standard audio frequency according to the comparison rule, inputs the obtained approximate value into the reading data packet and sends the obtained approximate value to the teacher terminal together.
The approximation given can assist the teacher in evaluating the student's reading ability.
In an embodiment, if the type of the reading text is sentence type, referring to fig. 5, after step S41, the following steps are further performed:
S42A: the audio frequency correction model screens out standard audio frequency corresponding to the key word group based on the pre-selected key word group in the reading text;
S43A: performing approximation comparison on the audio data of the key word group and the standard audio of the key word group according to the comparison rule, and outputting sentence approximation values;
S44A: sentence class approximations are input into the reading data packet.
In this embodiment, the keyword group is a representative word or word group screened from the english sentence and conforming to the learning stage of the student, for example, the english sentence is a sentence making conforming to the word currently learned by the student, and if the word is the keyword group of the english sentence, only the audio data of the pronunciation of the keyword group in the english sentence is compared when the similarity comparison is performed, so that the efficiency of comparing the reading text is improved.
Specifically, each reading text is pre-selected with a keyword group in the reading text, after the audio frequency correction model receives the audio frequency data, the keyword group in the reading text is screened out based on the reading text of the audio frequency data, the standard audio frequency of the keyword group is further screened out, the audio frequency data of the keyword group is compared with the standard audio frequency to obtain a sentence approximation value representing the approximation degree of English sentence audio frequency, and the sentence approximation value is input into a reading data packet and is sent to a teacher terminal. So as to assist a teacher in evaluating the English sentence reading capability of the student.
In one embodiment, referring to fig. 6, step S42 is specifically:
s421: the audio frequency correction model obtains the audio frequency characteristic information of the audio frequency data;
s422: acquiring standard characteristic information of standard audio from a cloud platform based on the reading text;
s423: and comparing the audio characteristic information with the standard characteristic information, and calculating to obtain word class approximation values based on comparison results of the audio characteristic information and the standard characteristic information.
In this embodiment, the comparison of the audio feature information and the standard feature information refers to frame comparison of the student records, that is, the comparison of the waveform data of each pronunciation frame of each word in the audio data and the waveform data of each pronunciation frame of the standard audio. Because of the huge voice database, the comparison of waveform data is carried out on the cloud platform, so that the comparison time can be shortened, and the comparison accuracy can be improved.
And comparing sentence approximation values, namely acquiring the audio characteristic information of the keyword group, and comparing the audio characteristic information with the standard characteristic information of the keyword group on the cloud platform.
Specifically, the audio frequency correction model obtains audio frequency characteristic information of audio frequency data, based on reading text corresponding to the audio frequency data, standard characteristic information of standard audio frequency corresponding to the audio frequency characteristic information is screened out from the cloud platform, standard audio frequency characteristics of frames corresponding to a plurality of audio frequency characteristic information are subjected to one comparison, and word class approximation values are obtained by counting the sum of similarity degree of the audio frequency characteristic information of each frame and dividing the sum by the number of frames of waveform data. The same calculation method can obtain sentence approximation values.
In one embodiment, after step S20, the following steps are performed:
s21: when the audio data is sent to the voice recognition model, starting countdown of a preset interval duration;
s22: and when the countdown of the preset interval duration is finished, sending the next preset reading text to the user terminal, wherein the interval duration is set by the user terminal in a self-defining way.
In this embodiment, the interval duration refers to an interval time when the reading text is sent to the user terminal, and the interval time is generally set in a custom range from 10 seconds to 1 minute.
Specifically, when the audio data is sent to the voice recognition model, the student is proved to finish recording of a single reading text, the interval duration starts to count down, the preselected next reading text is sent to the user terminal after counting down, and the student can start recording of the next reading text.
Further, full-automatic switching of the reading text can be set, namely, the user terminal starts timing after receiving the reading text, and automatically sends the next reading text to the user terminal when timing is finished.
In an embodiment, referring to fig. 7, the intelligent evaluation method for english reading ability further includes the steps of:
s60: acquiring all sentence approximation values generated by the user terminal in the past, and calculating the average value of the sentence approximation values;
s61: identifying an approximate value interval to which the average value belongs;
s62: acquiring associated preset interval time based on the approximate value interval;
s63: and adjusting the interval duration of reading text transmission to the acquired interval time.
In this embodiment, sentence approximations obtained by all reading evaluations of the past user terminal in 1 to 3 months are generally obtained. Similarly, sentence approximation values obtained by reading and evaluating all the past 1 to 3 months of the user terminal can be obtained to calculate an average value; further, the number of sentence class approximations and the number of word class approximations of the user terminal passing 1 to 3 months are compared, and the average value calculation is performed by giving a larger number of approximations.
The approximation interval is custom-set for the teacher terminal, and generally comprises intervals of 100% to 80%, 79% to 50%, 49% to 20%, 0% to 19%, and the like. Each approximation interval corresponds to a preset interval time, and the higher the approximation interval is, the shorter the corresponding preset interval time is.
Specifically, sentence approximation values obtained by students through reading and evaluating through the user terminal in three months in the past are obtained, and the average value of all sentence approximation values is calculated. Further identifying an approximate value interval to which the average value belongs, obtaining a preset interval time corresponding to the approximate value interval, and adjusting the interval duration of reading text transmission to the interval time corresponding to the obtained approximate value interval.
It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic of each process, and should not limit the implementation process of the embodiment of the present application in any way.
In an embodiment, an intelligent evaluating system for spoken english is provided, where the intelligent evaluating system for spoken english corresponds to an intelligent evaluating method for reading ability of english in the foregoing embodiment. The intelligent evaluating system for the spoken English comprises:
the evaluation request module is used for sending a pre-selected reading text to the user terminal when receiving an evaluation request for English reading from the user terminal bound with the student identity information;
the audio sending module is used for sending the audio data to the voice recognition model when receiving the audio data generated by the user terminal according to the reading text;
the standard audio module is used for screening out standard audio of the pre-selected associated reading text based on the reading text by the voice recognition model;
the audio packaging module is used for packaging the standard audio and the associated audio data to generate a reading data packet;
and the data packet sending module is used for sending the reading data packet to the teacher terminal bound with the user terminal.
Optionally, if the type of the read text is a word type, the method further includes:
the audio frequency proofreading module is used for sending the reading data packet to the audio frequency proofreading model;
the approximate value module is used for comparing the approximate degree of the audio data in the reading data packet with the standard audio according to the comparison rule by the audio comparison model and outputting a word class approximate value;
and the word class approximation input module is used for inputting the word class approximation into the reading data packet.
Optionally, if the type of the reading text is sentence type, the method further includes:
the key phrase splitting module is used for screening standard audio corresponding to the key phrase based on the pre-selected key phrase in the reading text by the audio frequency correction model;
the keyword comparison module is used for performing approximation comparison on the audio data of the keyword group and the standard audio of the keyword group according to the comparison rule and outputting sentence approximation values;
and the sentence class approximation value input module is used for inputting sentence class approximation values into the reading data packet.
Optionally, the approximation module includes:
the characteristic acquisition sub-module is used for acquiring audio characteristic information of the audio data by the audio collation model;
the standard characteristic acquisition sub-module is used for acquiring standard characteristic information of standard audio from the cloud platform based on the reading text;
the feature comparison sub-module is used for performing one comparison on the audio feature information and the standard feature information, and calculating to obtain word class approximation values based on comparison results of the audio feature information and the standard feature information.
Optionally, the method further comprises:
the interval timing module is used for starting countdown of the preset interval duration when the audio data are sent to the voice recognition model;
and the interval sending module is used for sending the preselected next reading text to the user terminal when the countdown of the preset interval duration is finished, and the interval duration is set by the user terminal in a self-defining way.
Optionally, the method further comprises:
the average value calculation module is used for obtaining all sentence approximation values generated by the user terminal in the past and calculating the average value of the sentence approximation values;
the interval determining module is used for identifying an approximate value interval to which the average value belongs;
the interval time acquisition module is used for acquiring associated preset interval time based on the approximate value interval;
and the interval duration adjusting module is used for adjusting the interval duration of reading text transmission to the acquired interval time.
For a specific definition of an intelligent evaluation system for spoken english may be referred to the definition of an intelligent evaluation method for reading ability of english hereinabove, and will not be repeated here. The modules in the intelligent evaluating system for the spoken English can be fully or partially realized by software, hardware and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, and the internal structure of which may be as shown in fig. 8. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for storing English words, sentence libraries, voice recognition models, an audio proofreading module, audio data and standard audio. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program, when executed by the processor, implements an intelligent evaluating method for spoken English.
In one embodiment, a computer device is provided that includes a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing a method for intelligent evaluation of spoken English when executing the computer program.
In one embodiment, a computer readable storage medium having a computer program stored thereon, which when executed by a processor, implements a method for intelligent evaluation of spoken English.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the various embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions.
The above embodiments are only for illustrating the technical solution of the present application, and are not limiting; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application.
Claims (10)
1. An intelligent evaluation method for English reading capability is characterized by comprising the following steps of: the method comprises the following steps:
when receiving an evaluation request for English reading from a user terminal bound with student identity information, transmitting a pre-selected reading text to the user terminal;
when receiving audio data generated by the user terminal according to the reading text, sending the audio data to a voice recognition model;
the voice recognition model screens out standard audios of the pre-selected associated reading texts based on the reading texts;
packaging the standard audio and the associated audio data to generate a reading data packet;
and sending the reading data packet to the teacher terminal bound with the user terminal.
2. The intelligent evaluation method for english reading ability according to claim 1, wherein: if the type of the reading text is word type, after the step of packaging the standard audio and the associated audio data to generate a reading data packet, the following steps are executed:
transmitting the reading data packet to an audio frequency correction model;
the audio frequency correction model compares the approximation degree of the audio frequency data in the reading data packet with the standard audio frequency according to the comparison rule, and outputs a word class approximation value;
word class approximations are entered into the reading data packet.
3. The intelligent evaluation method for english reading ability according to claim 2, wherein: if the type of the reading text is sentence type, after the step of sending the reading data packet to the audio collation model, executing the following steps:
the audio frequency correction model screens out standard audio frequency corresponding to the key word group based on the pre-selected key word group in the reading text;
performing approximation comparison on the audio data of the key word group and the standard audio of the key word group according to the comparison rule, and outputting sentence approximation values;
sentence class approximations are input into the reading data packet.
4. The intelligent evaluation method for english reading ability according to claim 2, wherein: the step of comparing the approximation degree of the audio data in the reading data packet and the standard audio by the audio frequency correction model according to the comparison rule and outputting the word class approximation value comprises the following specific steps:
the audio frequency correction model obtains the audio frequency characteristic information of the audio frequency data;
acquiring standard characteristic information of standard audio from a cloud platform based on the reading text;
and comparing the audio characteristic information with the standard characteristic information, and calculating to obtain word class approximation values based on comparison results of the audio characteristic information and the standard characteristic information.
5. The intelligent evaluation method for english reading ability according to claim 1, wherein: after the step of sending the audio data to the speech recognition model when receiving the audio data generated from the user terminal according to the reading text, the following steps are executed:
when the audio data is sent to the voice recognition model, starting countdown of a preset interval duration;
and when the countdown of the preset interval duration is finished, sending the next preset reading text to the user terminal, wherein the interval duration is set by the user terminal in a self-defining way.
6. The intelligent evaluation method for english reading ability according to claim 5, wherein: the intelligent evaluation method for English reading capability further comprises the following steps:
acquiring all sentence approximation values generated by the user terminal in the past, and calculating the average value of the sentence approximation values;
identifying an approximate value interval to which the average value belongs;
acquiring associated preset interval time based on the approximate value interval;
and adjusting the interval duration of reading text transmission to the acquired interval time.
7. An intelligent evaluating system for spoken english practice, comprising:
the evaluation request module is used for sending a pre-selected reading text to the user terminal when receiving an evaluation request for English reading from the user terminal bound with the student identity information;
the audio sending module is used for sending the audio data to the voice recognition model when receiving the audio data generated by the user terminal according to the reading text;
the standard audio module is used for screening out standard audio of the pre-selected associated reading text based on the reading text by the voice recognition model;
the audio packaging module is used for packaging the standard audio and the associated audio data to generate a reading data packet; and the data packet sending module is used for sending the reading data packet to the teacher terminal bound with the user terminal.
8. The intelligent evaluating system for spoken english practice according to claim 7, wherein:
if the type of the read text is a word type, the method further comprises:
the audio frequency proofreading module is used for sending the reading data packet to the audio frequency proofreading model;
the approximate value module is used for comparing the approximate degree of the audio data in the reading data packet with the standard audio according to the comparison rule by the audio comparison model and outputting a word class approximate value;
and the word class approximation input module is used for inputting the word class approximation into the reading data packet.
9. Computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of a method for intelligent evaluation of english reading ability according to any of claims 1 to 6 when the computer program is executed by the processor.
10. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of an intelligent assessment method of english reading ability according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211558336.0A CN116013286A (en) | 2022-12-06 | 2022-12-06 | Intelligent evaluation method, system, equipment and medium for English reading capability |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211558336.0A CN116013286A (en) | 2022-12-06 | 2022-12-06 | Intelligent evaluation method, system, equipment and medium for English reading capability |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116013286A true CN116013286A (en) | 2023-04-25 |
Family
ID=86032512
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211558336.0A Pending CN116013286A (en) | 2022-12-06 | 2022-12-06 | Intelligent evaluation method, system, equipment and medium for English reading capability |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116013286A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108428382A (en) * | 2018-02-14 | 2018-08-21 | 广东外语外贸大学 | It is a kind of spoken to repeat methods of marking and system |
| CN109979484A (en) * | 2019-04-03 | 2019-07-05 | 北京儒博科技有限公司 | Pronounce error-detecting method, device, electronic equipment and storage medium |
| CN111078179A (en) * | 2019-05-10 | 2020-04-28 | 广东小天才科技有限公司 | Control method for dictation and reading progress and electronic equipment |
| CN111369980A (en) * | 2020-02-27 | 2020-07-03 | 网易有道信息技术(北京)有限公司江苏分公司 | Voice detection method and device, electronic equipment and storage medium |
| CN111681470A (en) * | 2020-07-15 | 2020-09-18 | 朱万里 | Artificial intelligence english teaching system |
| CN113486970A (en) * | 2021-07-15 | 2021-10-08 | 北京全未来教育科技有限公司 | Reading capability evaluation method and device |
-
2022
- 2022-12-06 CN CN202211558336.0A patent/CN116013286A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108428382A (en) * | 2018-02-14 | 2018-08-21 | 广东外语外贸大学 | It is a kind of spoken to repeat methods of marking and system |
| CN109979484A (en) * | 2019-04-03 | 2019-07-05 | 北京儒博科技有限公司 | Pronounce error-detecting method, device, electronic equipment and storage medium |
| CN111078179A (en) * | 2019-05-10 | 2020-04-28 | 广东小天才科技有限公司 | Control method for dictation and reading progress and electronic equipment |
| CN111369980A (en) * | 2020-02-27 | 2020-07-03 | 网易有道信息技术(北京)有限公司江苏分公司 | Voice detection method and device, electronic equipment and storage medium |
| CN111681470A (en) * | 2020-07-15 | 2020-09-18 | 朱万里 | Artificial intelligence english teaching system |
| CN113486970A (en) * | 2021-07-15 | 2021-10-08 | 北京全未来教育科技有限公司 | Reading capability evaluation method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8371857B2 (en) | System, method and device for language education through a voice portal | |
| CN110136691B (en) | Speech synthesis model training method and device, electronic equipment and storage medium | |
| CN105679122A (en) | Multifunctional college English teaching management system | |
| WO2021134581A1 (en) | Prosodic feature prediction-based speech synthesis method, apparatus, terminal, and medium | |
| KR20200002141A (en) | Providing Method Of Language Learning Contents Based On Image And System Thereof | |
| CN108897771B (en) | Automatic question answering method and device, computer readable storage medium and electronic equipment | |
| CN110827595A (en) | Interaction method and device in virtual teaching and computer storage medium | |
| CN113486970B (en) | Reading capability evaluation method and device | |
| CN111079501A (en) | Character recognition method and electronic equipment | |
| CN116013286A (en) | Intelligent evaluation method, system, equipment and medium for English reading capability | |
| CN112883174A (en) | Automatic generation method and system for online programming test questions | |
| CN111949870A (en) | Intelligent language learning method based on memory curve and storage medium | |
| CN111081088A (en) | Dictation word receiving and recording method and electronic equipment | |
| JP2006178334A (en) | Language learning system | |
| JP2017021245A (en) | Language learning support device, language learning support method, and language learning support program | |
| CN114203201A (en) | Spoken language evaluation method, device, equipment, storage medium and program product | |
| KR20190070682A (en) | System and method for constructing and providing lecture contents | |
| CN114691903A (en) | Intelligent course testing method and system, electronic equipment and storage medium | |
| CN117079222B (en) | Teaching plan generation method and system based on classroom audio and video intelligent analysis | |
| KR100687441B1 (en) | Method and system for evaluation of foring language voice | |
| CN111967255A (en) | Internet-based automatic language test paper evaluation method and storage medium | |
| KR20140051607A (en) | Apparatus providing analysis information based on level of a student and method thereof | |
| CN111026871A (en) | Dictation content acquisition method based on knowledge graph and electronic equipment | |
| CN115629894B (en) | Speech prompting method and related device | |
| CN116596268B (en) | On-line education-based teacher-student operation interaction method and system |
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 |