CN109545015A - A kind of recognition methods and private tutor's equipment of subject type - Google Patents
A kind of recognition methods and private tutor's equipment of subject type Download PDFInfo
- Publication number
- CN109545015A CN109545015A CN201910061395.9A CN201910061395A CN109545015A CN 109545015 A CN109545015 A CN 109545015A CN 201910061395 A CN201910061395 A CN 201910061395A CN 109545015 A CN109545015 A CN 109545015A
- Authority
- CN
- China
- Prior art keywords
- target
- subject
- voice
- information
- question information
- 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
- 238000000034 method Methods 0.000 title claims abstract description 66
- 238000012549 training Methods 0.000 claims abstract description 33
- 230000015654 memory Effects 0.000 claims description 22
- 230000001755 vocal effect Effects 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 8
- 230000008676 import Effects 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 6
- 230000005540 biological transmission Effects 0.000 claims description 4
- 235000013399 edible fruits Nutrition 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 abstract description 12
- 230000008569 process Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 230000007613 environmental effect Effects 0.000 description 6
- 239000000284 extract Substances 0.000 description 5
- 238000013135 deep learning Methods 0.000 description 4
- 230000007774 longterm Effects 0.000 description 4
- 238000007781 pre-processing Methods 0.000 description 4
- 241000167880 Hirundinidae Species 0.000 description 3
- 235000009508 confectionery Nutrition 0.000 description 3
- 244000078534 Vaccinium myrtillus Species 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000010295 mobile communication Methods 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 235000017848 Rubus fruticosus Nutrition 0.000 description 1
- 235000003095 Vaccinium corymbosum Nutrition 0.000 description 1
- 235000017537 Vaccinium myrtillus Nutrition 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 235000021029 blackberry Nutrition 0.000 description 1
- 235000021014 blueberries Nutrition 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 210000000232 gallbladder Anatomy 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 235000019640 taste Nutrition 0.000 description 1
Classifications
-
- 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
- G09B5/00—Electrically-operated educational appliances
- G09B5/06—Electrically-operated educational appliances with both visual and audible presentation of the material to be studied
-
- 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
-
- 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
- G10L15/00—Speech recognition
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
-
- 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
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- 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
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The present embodiments relate to field of Educational Technology, disclose the recognition methods and private tutor's equipment of a kind of subject type, this method comprises: private tutor's equipment, which obtains mass users, puts question to sample for the voice of multiple subject types, according to subject type, sample is putd question to be marked voice to obtain target voice and put question to sample, then put question to sample as training data using target voice, using the corresponding subject type of target voice sample as training result, training obtains subject identification model, then the voice question information for problem of target user's input is received, voice question information is imported into subject identification model, obtain the corresponding target subject of problem.Implement the embodiment of the present invention, the corresponding subject of problem can be distinguished, and then improve the efficiency of problem search.
Description
Technical field
The present invention relates to the recognition methods and private tutor's equipment of field of Educational Technology more particularly to a kind of subject type.
Background technique
With the rapid development of private tutor's machine, on-line study miscellaneous function (such as intelligent answer, problem that private tutor's machine can be provided
Search and answer check and correction etc.) it is more and more, User is dramatically facilitated by private tutor's machine to solve in learning process
In the problem of encountering.For example, User can search for the corresponding answer of problem encountered in learning process by private tutor's machine.So
And this method cannot distinguish between the corresponding subject of problem, so user needs to select the corresponding application of difference subject in private tutor's machine
Program (Application, APP) solves different section's purpose problems, alternatively, in selection private tutor's machine APP different subjects
Label solves different section's purpose problems.As it can be seen that this method reduces the efficiency of problem search.
Summary of the invention
The embodiment of the invention discloses a kind of recognition methods of subject type and private tutor's equipment, and it is corresponding can to distinguish problem
Subject, and then improve the efficiency of problem search.
First aspect of the embodiment of the present invention discloses a kind of recognition methods of subject type, comprising:
The voice that mass users are obtained for multiple subject types puts question to sample；
According to subject type, sample is putd question to be marked the voice to obtain target voice and put question to sample；
It puts question to sample as training data using the target voice, is instruction with the corresponding subject type of the target voice sample
Practice as a result, training obtains subject identification model；
Receive the voice question information for problem of target user's input；
The voice question information is imported into the subject identification model, obtains the corresponding target subject of the problem.
As an alternative embodiment, in first aspect of the embodiment of the present invention, it is defeated in the reception target user
It is after the voice question information for problem entered and described by the voice question information importing subject identification mould
Type, before obtaining the corresponding target subject of the problem, the method also includes:
The voice question information is identified to generate the text question information for being directed to the problem；
The text question information is exported in the display page and exports inquiry message；The inquiry message is described for inquiring
Whether first content indicated by text question information matches with the second content indicated by the problem；
Obtain the return information of target user's input；
If the return information shows indicated by first content indicated by the text question information and the problem
Second content matches, and execution is described to import the subject identification model for the voice question information, obtains the problem pair
The target family purpose step answered.
As an alternative embodiment, the voice is putd question to described in first aspect of the embodiment of the present invention
Information imports the subject identification model, after obtaining the corresponding target subject of the problem, the method also includes:
According to the target subject, the target search range of the problem is determined；
The corresponding answer of the problem is searched for from the target search range；
The answer is pushed to the target user.
As an alternative embodiment, in first aspect of the embodiment of the present invention, the method also includes:
The audio that search matches with the answer；
The target audio to match with the target subject is screened from the audio；
While pushing the answer to the target user, the target audio is played.
As an alternative embodiment, being given in first aspect of the embodiment of the present invention in the push answer
After the target user, the method also includes:
The vocal print feature of the target user is extracted from the voice question information；
According to the vocal print feature, the identity information of the target user is identified；
According to the identity information, the information of the teacher of class where determining the target user；
The information of the corresponding target teacher of the target subject is determined from the information of the teacher；
The voice question information for problem and the answer are sent to the instructional terminal of the target teacher, so as to
The target teacher specific aim readjusting operations topic.
Second aspect of the embodiment of the present invention discloses a kind of private tutor's equipment, comprising:
First acquisition unit puts question to sample for the voice of multiple subject types for obtaining mass users；
Marking unit, for puing question to sample to be marked to obtain target voice and mention the voice according to subject type
Ask sample；
Training unit, it is corresponding with the target voice sample for puing question to sample as training data using the target voice
Subject type be training result, training obtain subject identification model；
Receiving unit, for receiving the voice question information for problem of target user's input；
Second acquisition unit obtains the problem for the voice question information to be imported the subject identification model
Corresponding target subject.
As an alternative embodiment, in second aspect of the embodiment of the present invention, private tutor's equipment further include:
First recognition unit, the voice for problem for receiving target user's input in the receiving unit put question to letter
After breath and the second acquisition unit is by the voice question information importing subject identification model, obtains the difficulty
Before inscribing corresponding target subject, the voice question information is identified to generate the text question information for being directed to the problem；
Inquiry unit, for exporting the text question information in the display page and exporting inquiry message；The inquiry letter
Breath for inquire first content indicated by the text question information whether with the second content phase indicated by the problem
Match；
The first acquisition unit is also used to obtain the return information of target user's input；
The second acquisition unit, specifically for showing indicated by the text question information the when the return information
When second content indicated by one content and the problem matches, the voice question information is imported into the subject and identifies mould
Type obtains the corresponding target subject of the problem.
As an alternative embodiment, in second aspect of the embodiment of the present invention, private tutor's equipment further include:
First determination unit is identified for the voice question information to be imported the subject in the second acquisition unit
Model after obtaining the corresponding target subject of the problem, according to the target subject, determines the target search model of the problem
It encloses；
Search unit, for searching for the corresponding answer of the problem from the target search range；
Push unit, for pushing the answer to the target user.
As an alternative embodiment, in second aspect of the embodiment of the present invention, private tutor's equipment further include:
Described search unit is also used to search for the audio to match with the answer；
Screening unit, for screening the target audio to match with the target subject from the audio；
Broadcast unit is used for while the push unit pushes the answer to the target user, described in broadcasting
Target audio.
As an alternative embodiment, in second aspect of the embodiment of the present invention, private tutor's equipment further include:
Extraction unit is used for after the push unit pushes the answer to the target user, from the voice
The vocal print feature of the target user is extracted in question information；
Second recognition unit, for identifying the identity information of the target user according to the vocal print feature；
Second determination unit, for determining the letter of the teacher of the target user place class according to the identity information
Breath；
Second determination unit is also used to determine the corresponding target teacher's of the target subject from the information of the teacher
Information；
Transmission unit, for sending the voice question information for problem and the answer to the target teacher's
Instructional terminal, so as to target teacher specific aim readjusting operations topic.
The third aspect of the embodiment of the present invention discloses a kind of private tutor's equipment, comprising:
It is stored with the memory of executable program code；
The processor coupled with the memory；
The processor calls the executable program code stored in the memory, executes the embodiment of the present invention the
A kind of recognition methods of subject type disclosed in one side.
Fourth aspect of the embodiment of the present invention discloses a kind of computer readable storage medium, stores computer program, wherein
The computer program makes computer execute a kind of recognition methods of subject type disclosed in first aspect of the embodiment of the present invention.
The 5th aspect of the embodiment of the present invention discloses a kind of computer program product, when the computer program product is calculating
When being run on machine, so that the computer executes some or all of any one method of first aspect step.
The aspect of the embodiment of the present invention the 6th disclose a kind of using distribution platform, and the application distribution platform is for publication calculating
Machine program product, wherein when the computer program product is run on computers, so that the computer executes first party
Some or all of any one method in face step.
Compared with prior art, the embodiment of the present invention has the advantages that
In the embodiment of the present invention, private tutor's equipment obtains mass users and puts question to sample for the voice of multiple subject types；Root
According to subject type, sample is putd question to be marked voice to obtain target voice and put question to sample；It is with target voice enquirement sample
Training data, using the corresponding subject type of target voice sample as training result, training obtains subject identification model；Receive target
The voice question information for problem of user's input；Voice question information is imported into subject identification model, it is corresponding to obtain problem
Target subject.As it can be seen that implementing the embodiment of the present invention, by training subject identification model, the voice that target user inputs is mentioned
Ask that information imports subject identification model to obtain the target subject that matches of voice question information with target user's input, it can
The corresponding subject of problem is distinguished, and then improves the efficiency of problem search.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to needed in the embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for ability
For the those of ordinary skill of domain, without creative efforts, it can also be obtained according to these attached drawings other attached
Figure.
Fig. 1 is a kind of flow diagram of the recognition methods of subject type disclosed by the embodiments of the present invention；
Fig. 2 is the flow diagram of the recognition methods of another subject type disclosed by the embodiments of the present invention；
Fig. 3 is a kind of structural schematic diagram of private tutor's equipment disclosed by the embodiments of the present invention；
Fig. 4 is the structural schematic diagram of another private tutor's equipment disclosed by the embodiments of the present invention；
Fig. 5 is the structural schematic diagram of another private tutor's equipment disclosed by the embodiments of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that the described embodiment is only a part of the embodiment of the present invention, instead of all the embodiments.Based on this
Embodiment in invention, every other reality obtained by those of ordinary skill in the art without making creative efforts
Example is applied, shall fall within the protection scope of the present invention.
It should be noted that term " first ", " second ", " third " in description and claims of this specification and
" 4th " etc. is not use to describe a particular order for distinguishing different objects.The term " includes " of the embodiment of the present invention
" having " and their any deformation, it is intended that cover it is non-exclusive include, for example, containing series of steps or list
The process, method, system, product or equipment of member those of are not necessarily limited to be clearly listed step or unit, but may include not having
There are other step or units being clearly listed or intrinsic for these process, methods, product or equipment.
The embodiment of the invention discloses a kind of recognition methods of subject type and private tutor's equipment, and it is corresponding can to distinguish problem
Subject, and then improve the efficiency of problem search.It is described in detail below in conjunction with attached drawing.
Embodiment one
Referring to Fig. 1, Fig. 1 is a kind of flow diagram of the recognition methods of subject type disclosed by the embodiments of the present invention.
As shown in Figure 1, this method may comprise steps of.
101, private tutor's equipment obtains mass users and puts question to sample for the voice of multiple subject types.
In the embodiment of the present invention, private tutor's equipment is accessible and transfers in server mass users and is directed to multiple subject types
Voice put question to sample, such as Chinese language voice put question to sample, for mathematics voice put question to sample and needle English language
Sound puts question to sample, and the embodiment of the present invention is not construed as limiting.
In the embodiment of the present invention, private tutor's equipment can be study plate, learning machine, study mobile phone, point for users to use
Reading machine, cell phone, mobile plate, personal digital assistant (Personal Digital Assistant, PDA), moves Jia Jiaoji
Various equipment, the embodiment of the present invention such as dynamic internet device (Mobile Internet Device, MID), television set do not limit
It is fixed.
In the embodiment of the present invention, private tutor's equipment shown below can be any one above-mentioned private tutor's equipment, the present invention
Embodiment is not construed as limiting.Wherein, the operating system of above-mentioned private tutor's equipment may include but be not limited to Android operation system, IOS
Operating system, Symbian (Saipan) operating system, Black Berry (blackberry, blueberry) operating system, Windows Phone8 operation system
System etc., the embodiment of the present invention is not construed as limiting.
In the embodiment of the present invention, private tutor's equipment can support including but not limited to following network technology: global mobile communication
System (Global System for Mobile Communications, GSM), General Packet Radio Service (General
Packet Radio Service, GPRS), CDMA (Code Division Multiple Access, CDMA), broadband
CDMA (W-CDMA), CDMA2000, IMT single carrier (IMT Single Carrier), enhanced data rates for gsm evolution
(Enhanced Data Rates for GSM Evolution, EDGE), Long Term Evolution (Long-Term
Evolution, LTE), it is senior long term evolution technology, time-division Long Term Evolution (Time-Division LTE, TD-LTE), high
Performance radio lan (High Performance Radio Local Area Network, HiperLAN), high-performance without
Line electricity wide area network (HiperWAN), local multiple spot distribute business (Local Multipoint Distribution Service,
LMDS), full micro-wave access global inter communication (WiMAX), ZigBee protocol (ZigBee), bluetooth, orthogonal frequency division multiplexi (OFDM),
Large capacity space-division multiple access (HC-SDMA), Universal Mobile Telecommunications System (UMTS), Universal Mobile Telecommunications System time division duplex
(UMTS-TDD), evolved high-speed packet access (HSPA+), TD SDMA (TD-SCDMA), evolution data are optimal
Change (EV-DO), Digital Enhanced Cordless Communications (DECT) and other.
102, private tutor's equipment puts question to sample to be marked voice to obtain target voice and put question to sample according to subject type
This.
In the embodiment of the present invention, private tutor's equipment can be mentioned voice according to subject type (such as Chinese language, mathematics and English)
Ask that sample is marked to obtain target voice and put question to sample.For example, if voice put question to sample include Chinese idiom, classic poetry and
The contents such as phonetic, such as " what meaning is endured hardships to accomplish some ambition is ", private tutor's equipment can be marked as Chinese language and put question to sample；If voice mentions
Ask that sample includes the contents such as formula, operator and unknown number, such as " 5 are equal to 20, X is how many plus X ", private tutor's equipment can be by it
Sample is putd question to labeled as mathematics；If it includes the contents such as English alphabet and English word that voice, which puts question to sample, such as " I like please be translate
Learning ", private tutor's equipment can be marked as English and put question to sample.Wherein, above-mentioned Chinese language puts question to sample, mathematics to put question to sample
It is that target voice puts question to sample that this, which puts question to sample with English,.
103, private tutor's equipment puts question to sample as training data using target voice, with the corresponding subject type of target voice sample
For training result, training obtains subject identification model.
In the embodiment of the present invention, target voice puts question to sample to include at least Chinese language and puts question to sample, mathematics enquirement sample and English
Language puts question to sample, and the embodiment of the present invention is not construed as limiting.In the embodiment of the present invention, private tutor's equipment can put question to sample from target voice
The way to put questions feature of its affiliated subject type is extracted, and using these way to put questions features as default way to put questions feature, then will be put up a question in advance
Method feature establishes mapping relations with corresponding subject type, forms the section that subject type can be identified based on voice question information
Mesh identification model, for when target user input for problem voice question information when, according to voice question information identify
It poses a difficult problem corresponding target subject.
104, private tutor's equipment receives the voice question information for problem of target user's input.
In the embodiment of the present invention, the corresponding target subject of above-mentioned problem can be Chinese language, or mathematics can also be
English, the embodiment of the present invention are not construed as limiting.
In the embodiment of the present invention, after the training of step 101- step 103 obtains subject identification model, private tutor's equipment is opened
Learn the APP of class, receives the voice question information for problem of target user's input, and voice question information is imported into subject
Identification model obtains the corresponding target subject of problem.
As an alternative embodiment, private tutor's equipment can be built-in with microphone, correspondingly private tutor's equipment can lead to
Cross the voice question information for problem that the microphone built in it receives target user's input.Further, private tutor's equipment can
To reject environmental noise from voice question information, then the voice question information after rejecting environmental noise is imported into subject and identifies mould
Type obtains the corresponding target subject of problem.
Implement above embodiment, the voice question information for problem of target user's input received by microphone,
Then to the voice question information it is further proposed that environmental noise, can accelerate computer to the identification speed of voice question information
Rate improves the corresponding target family purpose of problem and obtains efficiency.
105, voice question information is imported subject identification model by private tutor's equipment, obtains the corresponding target subject of problem.
In the embodiment of the present invention, for convenience of understanding, the embodiment of the present invention is carried out so that target subject is the problem of Chinese language as an example
Description, such as, the information that problem includes is " please explain and endure hardships to accomplish some ambition ", and the voice for problem of target user's input is putd question to
Information is " what meaning is endured hardships to accomplish some ambition is ", and private tutor's equipment receives the voice question information that target user inputs, and " enduring hardships to accomplish some ambition is
What meaning ", then imports subject identification model for the voice question information, and it is corresponding to obtain problem " please explain and endure hardships to accomplish some ambition "
Target subject is Chinese language.
As an alternative embodiment, subject identification model may include extraction module, comparison module, mark module
And voice question information is imported subject identification model by determining module, step 105 private tutor equipment, obtains the corresponding target family of problem
Purpose mode specifically:
Private tutor's equipment inputs voice question information in the extraction module of subject identification model, to extract voice question information
Way to put questions feature, and using the way to put questions feature as pretreatment way to put questions feature；
It is special to compare pretreatment way to put questions by the comparison module for pre-processing way to put questions feature input subject identification model for private tutor's equipment
Sign and multiple default way to put questions features, to obtain the similarity of pretreatment way to put questions feature and multiple default way to put questions features；Wherein, multiple
Default way to put questions feature is that the voice of multiple subject types puts question to sample corresponding way to put questions feature；
The mark module label and pretreatment way to put questions characteristic similarity of private tutor's equipment utilization subject identification model are highest pre-
Rhetoric question method feature is target way to put questions feature；
Private tutor's equipment inputs target way to put questions spy in the determining module of subject identification model, to determine target way to put questions feature pair
The subject type answered, and the corresponding subject type of target way to put questions feature is determined as the corresponding target subject of problem.
Implement above embodiment, determines difficulty by comparing the similarity for pre-processing way to put questions feature and default way to put questions feature
Corresponding target subject is inscribed, can be improved the precision of subject identification.
As it can be seen that implement method described in Fig. 1, it is defeated to target user based on deep learning algorithm training subject identification model
The voice question information entered is identified, the target subject to match with the voice question information of target user's input, energy are obtained
The corresponding subject of problem is enough distinguished, and then improves the efficiency of problem search.
Embodiment two
Referring to Fig. 2, Fig. 2 is the process signal of the recognition methods of another subject type disclosed by the embodiments of the present invention
Figure.As shown in Fig. 2, this method may comprise steps of.
201-204；Wherein, step 201- step 204 is identical as the step 101- step 104 in embodiment one, herein not
It repeats again.
205, private tutor's equipment identification voice question information is to generate the text question information for being directed to problem.
In the embodiment of the present invention, private tutor's equipment can use automatic speech recognition (Automatic Speech
Recognition, ASR) technology, the voice question information that target user inputs is converted to human-readable text question information
And text question information is shown in the display page.
206, private tutor's equipment in display page output character question information and exports inquiry message.
In the embodiment of the present invention, inquiry message for inquire first content indicated by text question information whether with problem
The second indicated content matches, for example, the information that problem includes is " please explain and endure hardships to accomplish some ambition ", target user's input
The voice question information for problem be a segment of audio, audio content is " endure hardships to accomplish some ambition is what meaning ", private tutor's equipment benefit
The text question information produced with ASR technology is " what meaning is endured hardships to accomplish some ambition is ", at this point, private tutor's equipment is in display page output
" enduring hardships to accomplish some ambition is any meaning ", and inquiry message " whether you want to ask what meaning is endured hardships to accomplish some ambition is " exported.
207, private tutor's equipment obtains the return information of target user's input.
If 208, return information shows the second content indicated by first content indicated by text question information and problem
Match, voice question information is imported subject identification model by private tutor's equipment, obtains the corresponding target subject of problem.
In the embodiment of the present invention, implementation steps 205- step 208 is directed to problem by identification voice question information to generate
Text question information and display page output character question information and output inquiry message, when target user reply text mention
When asking that the second content indicated by first content indicated by information and problem matches, private tutor's equipment leads voice question information
Enter subject identification model, obtains the corresponding target subject of problem, can be improved the accuracy of problem search.
209, private tutor's equipment determines the target search range of problem according to target subject.
210, private tutor's equipment searches for the corresponding answer of problem from target search range.
211, private tutor's equipment pushes answer to target user.
It in the embodiment of the present invention, is described so that target subject is Chinese language as an example, the information that problem includes is that " please explain sleeping
Firewood tastes gallbladder ", the voice question information for problem of target user's input is " what meaning is endured hardships to accomplish some ambition is ", and private tutor's equipment connects
The voice question information " what meaning is endured hardships to accomplish some ambition is " for receiving target user's input, then imports subject for the voice question information
Identification model obtains problem " please explain and endure hardships to accomplish some ambition " corresponding target subject as Chinese language, and then private tutor's equipment determines problem
Target search range is Chinese language range, and the corresponding answer of problem is searched for from Chinese language range, such as " endure hardships to accomplish some ambition be one at
Language means and describes that a people swallows humiliation and bears a heavy load, and with firm resolve to succeed, final sweet are the fruits of labor ", then the answer is pushed to by private tutor's equipment
Target user.
In the embodiment of the present invention, implementation steps 209- step 210, private tutor's equipment first determines search model according to target subject
It encloses, the corresponding answer of problem is then searched in the search range, answer is finally pushed to user, can be improved problem search
Efficiency.
212, the audio that the search of private tutor's equipment matches with answer.
213, private tutor's equipment screens the target audio to match with target subject from audio.
214, private tutor's equipment plays target audio while pushing answer to target user.
In the embodiment of the present invention, the audio that the search of private tutor's equipment matches with answer, such as, answer is " to endure hardships to accomplish some ambition
It is a Chinese idiom, means and describe that a people swallows humiliation and bears a heavy load, with firm resolve to succeed, final sweet are the fruits of labor ", private tutor's equipment is searched and is answered
The audio that case matches is " " endure hardships to accomplish some ambition-Luo Yusheng ", " enemy-English Listening Comprehension of dedicating one's life to the cause of the country of enduring hardships to accomplish some ambition " etc. ", then according to target
Subject is Chinese language, and the target audio to match with Chinese language is screened from the audio searched, such as " " endure hardships to accomplish some ambition-Luo Yusheng " ",
And it is given in push " enduring hardships to accomplish some ambition is a Chinese idiom, means and describes that a people swallows humiliation and bears a heavy load, and with firm resolve to succeed, final sweet are the fruits of labor "
While target user, play " " endure hardships to accomplish some ambition-Luo Yusheng " ".
In the embodiment of the present invention, implementation steps 212- step 214, private tutor's equipment is by searching for the sound to match with answer
Frequently, the target audio to match with target subject is then filtered out in the audio, and in push answer to the same of target user
When, target audio is played, the interest of study can be improved in learning process, improves learning experience.
215, private tutor's equipment extracts the vocal print feature of target user from voice question information.
In the embodiment of the present invention, private tutor's equipment can use sound groove recognition technology in e and extract target use from voice question information
The vocal print feature at family.Wherein, sound groove recognition technology in e be the acoustical signal of speaker be converted to computer-readable electric signal again into
Row identification, since vocal print feature is uniquely, the vocal print feature of different people is different, so, vocal print feature can be used as
Identify the foundation of the identity information of speaker.
216, private tutor's equipment identifies the identity information of target user according to vocal print feature.
217, private tutor's equipment is according to identity information, the information of the teacher of class where determining target user.
In the embodiment of the present invention, private tutor's equipment is according to the identity information of the target user identified, from instruction management platform
In determine class where target user teacher information, wherein instruction management platform be stored with student with it is interclass
Information and teacher and interclass information.Because may there is the information of the teacher of class where the target user determined
Chinese language teacher, math teacher and English teacher, private tutor's equipment are communicated with the eyes the information of the corresponding Chinese language teacher of text according to target family, then
The instructional terminal of Chinese language teacher will be sent to for the voice question information of problem and answer, when Chinese language teacher sees private tutor's equipment
Send for the voice question information of problem and answer when, can targetedly inscribe readjusting operations, better auxiliary mark use
Family study.
218, private tutor's equipment determines the information of the corresponding target teacher of target subject from the information of teacher.
219, private tutor's equipment send for problem voice question information and answer to target teacher instructional terminal, so as to
Target teacher's specific aim readjusting operations topic.
Illustratively, in the embodiment of the present invention, step 215- step 219 can execute before step 212- step 214,
It can also execute, can also be performed simultaneously with step 212- step 214, the embodiment of the present invention after step 212- step 214
It is not construed as limiting.
In the embodiment of the present invention, implementation steps 215- step 219, the problem that private tutor's equipment can be searched for according to user, really
The information for being responsible for target family purpose teacher of class where user is made, then for the voice question information of problem and will be answered
Case can facilitate target teacher's specific aim readjusting operations to inscribe to the instructional terminal of target teacher, further assist user's study.
Further, as an alternative embodiment, after executing step 219, private tutor's equipment be can also be performed
Following steps:
Private tutor's equipment is received is inscribed by the operation that the instructional terminal of target teacher is sent；
Private tutor's equipment is by operation topic output to target user；
Private tutor's equipment receives the operation answer of target user's input；
Private tutor's equipment carries out scoring to the operation answer and obtains operation score, and the operation score is sent to target teacher
Instructional terminal.
Implement above embodiment, private tutor's equipment is exported by the operation topic for arranging target teacher to target user, right
The operation answer of target user carries out scoring and obtains operation score and operation score is sent to target teacher, and target can be made old
Teacher understands the study situation of target user, further auxiliary mark user study in time.
Further, as an alternative embodiment, equipment of teaching in a family carries out scoring acquisition to the operation answer
After operation score, following steps are can also be performed in private tutor's equipment:
Private tutor's equipment judges whether operation score is greater than preset fraction threshold value；
When operation score is greater than preset fraction threshold value, above-mentioned operation topic and operation answer are reported to teaching by private tutor's equipment
Platform is managed, so that instruction management platform announces above-mentioned operation topic and operation answer to the student's of class where target user
Student's equipment is referred to for the student of class where target user；
Implement above embodiment, equipment of teaching in a family judges that the operation score of target user is greater than preset fraction threshold value
When, show the operation answer of target user very close to model answer, private tutor's equipment will be in above-mentioned operation topic and above-mentioned operation answer
Instruction management platform is offered, instruction management platform is announced student's equipment of other students to class where target user,
For other students reference, interactive learning can be realized, improve learning experience.
As it can be seen that implement method described in Fig. 2, it is defeated to target user based on deep learning algorithm training subject identification model
The voice question information entered is identified, the target subject to match with the voice question information of target user's input, energy are obtained
The corresponding subject of problem is enough distinguished, and then improves the efficiency of problem search.In addition, implementing method described in Fig. 2, can be improved
The accuracy of problem search and the efficiency of problem search.In addition, implementing method described in Fig. 2, can be mentioned in learning process
The interest of height study, improves learning experience.In addition, implementing method described in Fig. 2, target teacher's specific aim can be facilitated whole
Operation topic is managed, user's study is further assisted.
Embodiment three
Referring to Fig. 3, Fig. 3 is a kind of structural schematic diagram of private tutor's equipment disclosed by the embodiments of the present invention.As shown in figure 3,
Private tutor's equipment may include:
First acquisition unit 301 puts question to sample for the voice of multiple subject types for obtaining mass users.
Marking unit 302, for according to subject type, puing question to sample to be marked voice to obtain target voice enquirement
Sample.
Training unit 303, for puing question to sample as training data using target voice, with the corresponding subject of target voice sample
Type is training result, and training obtains subject identification model.
In the embodiment of the present invention, target voice puts question to sample to include at least Chinese language and puts question to sample, mathematics enquirement sample and English
Language puts question to sample, and the embodiment of the present invention is not construed as limiting.In the embodiment of the present invention, training unit 303 can be putd question to from target voice
Sample extracts the way to put questions feature of its affiliated subject type, and using these way to put questions features as default way to put questions feature, then will be pre-
Rhetoric question method feature establishes mapping relations with corresponding subject type, and formation can identify subject type based on voice question information
Subject identification model, for when receiving unit 304 receive target user input for problem voice question information when,
Second acquisition unit 305 identifies corresponding target subject of posing a difficult problem according to voice question information.
Receiving unit 304, for receiving the voice question information for problem of target user's input.
As an alternative embodiment, receiving unit 304 can be built-in with microphone, correspondingly receiving unit 304
The voice question information for problem of target user's input can be received by the microphone built in it.Further, it receives
Unit 304 can reject environmental noise from voice question information, then, after second acquisition unit 305 will reject environmental noise
Voice question information import subject identification model and obtain the corresponding target subject of problem.
Implement above embodiment, the voice question information for problem of target user's input received by microphone,
Then to the voice question information it is further proposed that environmental noise, can accelerate computer to the identification speed of voice question information
Rate improves the corresponding target family purpose of problem and obtains efficiency.
Second acquisition unit 305 obtains the corresponding target of problem for voice question information to be imported subject identification model
Subject.
As an alternative embodiment, subject identification model may include extraction module, comparison module, mark module
And voice question information is imported subject identification model by determining module, second acquisition unit 305, obtains the corresponding target family of problem
Purpose mode specifically:
Second acquisition unit 305 inputs voice question information in the extraction module of subject identification model, to extract voice
The way to put questions feature of question information, and using the way to put questions feature as pretreatment way to put questions feature；
Second acquisition unit 305 is relatively located in advance by the comparison module for pre-processing way to put questions feature input subject identification model
Way to put questions feature and multiple default way to put questions features are managed, to obtain the similarity of pretreatment way to put questions feature and multiple default way to put questions features；
Wherein, multiple default way to put questions features are that the voice of multiple subject types puts question to sample corresponding way to put questions feature；
Second acquisition unit 305 is marked with pretreatment way to put questions characteristic similarity most using the mark module of subject identification model
High default way to put questions feature is target way to put questions feature；
Second acquisition unit 305 inputs target way to put questions spy in the determining module of subject identification model, to determine that target is asked
The corresponding subject type of method feature, and the corresponding subject type of target way to put questions feature is determined as the corresponding target family of problem
Mesh.
Implement above embodiment, determines difficulty by comparing the similarity for pre-processing way to put questions feature and default way to put questions feature
Corresponding target subject is inscribed, can be improved the precision of subject identification.
As it can be seen that private tutor's equipment described in implementing Fig. 3, uses target based on deep learning algorithm training subject identification model
The voice question information of family input is identified, the target family to match with the voice question information of target user's input is obtained
Mesh can distinguish the corresponding subject of problem, and then improve the efficiency of problem search.
Example IV
Referring to Fig. 4, Fig. 4 is the structural schematic diagram of another private tutor's equipment disclosed by the embodiments of the present invention.Wherein, Fig. 4
Shown in private tutor's equipment be that private tutor's equipment as shown in Figure 3 advanced optimizes.Compared with private tutor's equipment shown in Fig. 3
Compared with private tutor's equipment shown in Fig. 4 can also include:
First recognition unit 306, the voice for problem for receiving target user's input in receiving unit 304 are putd question to
After information and second acquisition unit 305 is by voice question information importing subject identification model, obtains the corresponding target of problem
Before subject, voice question information is identified to generate the text question information for being directed to problem.
In the embodiment of the present invention, the first recognition unit 306 can use automatic speech recognition (Automatic Speech
Recognition, ASR) technology, the voice question information that target user inputs is converted to human-readable text question information
And text question information is shown in the display page.
Inquiry unit 307, for showing page output character question information and exporting inquiry message.
Wherein, whether inquiry message is for inquiring first content indicated by text question information with indicated by problem the
Two contents match.
First acquisition unit 301 is also used to obtain the return information of target user's input.
Second acquisition unit 305, specifically for when return information show first content indicated by text question information with
When second content indicated by problem matches, voice question information is imported into subject identification model, obtains the corresponding mesh of problem
Mark subject.
First determination unit 308, for voice question information to be imported subject identification model in second acquisition unit 305,
After obtaining the corresponding target subject of problem, according to target subject, the target search range of problem is determined.
Search unit 309, for searching for the corresponding answer of problem from target search range.
Push unit 310, for pushing answer to target user.
Search unit 309 is also used to search for the audio to match with answer.
Screening unit 311, for screening the target audio to match with target subject from audio.
Broadcast unit 312, for playing target audio while push unit 310 pushes answer to target user.
Extraction unit 313 is used for after push unit 310 pushes answer to target user, from voice question information
Extract the vocal print feature of target user.
In the embodiment of the present invention, extraction unit 313 can use sound groove recognition technology in e and extract mesh from voice question information
Mark the vocal print feature of user.Wherein, sound groove recognition technology in e is that the acoustical signal of speaker is converted to computer-readable electric signal
Identified again, due to vocal print feature be it is unique, the vocal print feature of different people is different, so, vocal print feature can be with
The foundation of identity information as identification speaker.
Second recognition unit 314, for identifying the identity information of target user according to vocal print feature.
Second determination unit 315, for determining the information of the teacher of target user place class according to identity information.
Second determination unit 315 is also used to determine the information of the corresponding target teacher of target subject from the information of teacher.
Transmission unit 316, for send be directed to problem voice question information and answer to target teacher instructional terminal,
So as to target teacher's specific aim readjusting operations topic.
Further, as an alternative embodiment, private tutor's equipment can also include first unit, in transmission unit
After 316 send the voice question information for being directed to problem and answer to the instructional terminal of target teacher, first unit can also be held
Row following steps:
First unit is received is inscribed by the operation that the instructional terminal of target teacher is sent；
First unit is by operation topic output to target user；
First unit receives the operation answer of target user's input；
First unit carries out scoring to the operation answer and obtains operation score, and the operation score is sent to target teacher
Instructional terminal.
Implement above embodiment, first unit is exported by the operation topic for arranging target teacher to target user, right
The operation answer of target user carries out scoring and obtains operation score and operation score is sent to target teacher, and target can be made old
Teacher understands the study situation of target user, further auxiliary mark user study in time.
Further, as an alternative embodiment, private tutor's equipment can also include second unit, when the first list
After member carries out scoring acquisition operation score to the operation answer, following steps are can also be performed in second unit:
Second unit judges whether operation score is greater than preset fraction threshold value；
When operation score is greater than preset fraction threshold value, above-mentioned operation topic and operation answer are reported to teaching by second unit
Platform is managed, so that instruction management platform announces above-mentioned operation topic and operation answer to the student's of class where target user
Student's equipment is referred to for the student of class where target user；
Implement above embodiment, when second unit judges that the operation score of target user is greater than preset fraction threshold value
When, show the operation answer of target user very close to model answer, second unit will be in above-mentioned operation topic and above-mentioned operation answer
Instruction management platform is offered, instruction management platform is announced student's equipment of other students to class where target user,
For other students reference, interactive learning can be realized, improve learning experience.
As it can be seen that implementing private tutor's equipment described in Fig. 4, target is used based on deep learning algorithm training subject identification model
The voice question information of family input is identified, the target family to match with the voice question information of target user's input is obtained
Mesh can distinguish the corresponding subject of problem, and then improve the efficiency of problem search.It is set in addition, implementing private tutor described in Fig. 4
It is standby, believed by identification voice question information with generating to be directed to the text question information of problem and put question in display page output character
Breath and output inquiry message, when target user replys second indicated by first content indicated by text question information and problem
When content matches, voice question information is imported into subject identification model, the corresponding target subject of problem is obtained, can be improved difficulty
Inscribe the accuracy of search.In addition, implementing private tutor's equipment described in Fig. 4, search range is determined according to target subject, then at this
The corresponding answer of problem is searched in search range, answer is finally pushed to user, can be improved the efficiency of problem search.This
Outside, implement private tutor's equipment described in Fig. 4, by searching for the audio to match with answer, then filtered out in the audio with
The target audio that target subject matches, and while pushing answer to target user, target audio is played, can learnt
The interest of study is improved in the process, improves learning experience.In addition, implement private tutor's equipment described in Fig. 4, it can be according to user
The problem of search, the information for being responsible for target family purpose teacher of class where determining user, then will be directed to the language of problem
Sound question information and answer can facilitate target teacher's specific aim readjusting operations to inscribe, further to the instructional terminal of target teacher
Assist user's study.
Embodiment five
Referring to Fig. 5, Fig. 5 is the structural schematic diagram of another private tutor's equipment disclosed by the embodiments of the present invention.Such as Fig. 5 institute
Show, which may include:
It is stored with the memory 501 of executable program code；
The processor 502 coupled with memory 501；
Wherein, processor 502 calls the executable program code stored in memory 501, and it is any one to execute FIG. 1 to FIG. 2
The recognition methods of kind subject type.
The embodiment of the present invention discloses a kind of computer readable storage medium, stores computer program, wherein the computer
Program makes the recognition methods of computer execution any one subject type of FIG. 1 to FIG. 2.
The embodiment of the present invention is also disclosed a kind of using distribution platform, wherein using distribution platform for issuing computer journey
Sequence product, wherein when computer program product is run on computers, so that computer executes such as the above each method embodiment
In some or all of method step.
It should be understood that " one embodiment " or " embodiment " that specification is mentioned in the whole text mean it is related with embodiment
A particular feature, structure, or characteristic is included at least one embodiment of the present invention.Therefore, occur everywhere in the whole instruction
" in one embodiment " or " in one embodiment " not necessarily refer to identical embodiment.In addition, these special characteristics, structure
Or characteristic can combine in any suitable manner in one or more embodiments.Those skilled in the art should also know that
Embodiment described in this description belongs to alternative embodiment, and not necessarily the present invention must for related actions and modules
Must.
In various embodiments of the present invention, it should be appreciated that magnitude of the sequence numbers of the above procedures are not meant to execute suitable
Successively, the execution sequence of each process should be determined by its function and internal logic the certainty of sequence, without coping with the embodiment of the present invention
Implementation process constitutes any restriction.
Above-mentioned unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be object unit, can be in one place, or may be distributed over multiple networks
On unit.Some or all of units can be selected to achieve the purpose of the solution of this embodiment according to the actual needs.
In addition, each functional unit in various embodiments of the present invention can integrate in one processing unit, it is also possible to
Each unit physically exists alone, and can also be integrated in one unit with two or more units.Above-mentioned integrated unit
Both it can take the form of hardware realization, can also realize in the form of software functional units.
If above-mentioned integrated unit is realized in the form of SFU software functional unit and when sold or used as an independent product,
It can store in a retrievable memory of computer.Based on this understanding, technical solution of the present invention substantially or
Person says all or part of of the part that contributes to existing technology or the technical solution, can be in the form of software products
It embodies, which is stored in a memory, including several requests are with so that a computer is set
Standby (can be personal computer, server or network equipment etc., specifically can be the processor in computer equipment) executes
Some or all of each embodiment above method of the invention step.
In embodiment provided by the present invention, it should be appreciated that " B corresponding with A " indicates that B is associated with A, can be with according to A
Determine B.It is also to be understood that determine that B is not meant to determine B only according to A according to A, it can also be according to A and/or other information
Determine B.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of above-described embodiment is can
It is completed with instructing relevant hardware by program, which can be stored in a computer readable storage medium, storage
Medium include read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory,
RAM), programmable read only memory (Programmable Read-only Memory, PROM), erasable programmable is read-only deposits
Reservoir (Erasable Programmable Read Only Memory, EPROM), disposable programmable read-only memory (One-
Time Programmable Read-Only Memory, OTPROM), the electronics formula of erasing can make carbon copies read-only memory
(Electrically-Erasable Programmable Read-Only Memory, EEPROM), CD-ROM (Compact
Disc Read-Only Memory, CD-ROM) or other disc memories, magnetic disk storage, magnetic tape storage or can
For carrying or any other computer-readable medium of storing data.
Detailed Jie has been carried out to the recognition methods and private tutor's equipment of a kind of subject type disclosed by the embodiments of the present invention above
It continues, used herein a specific example illustrates the principle and implementation of the invention, and the explanation of above embodiments is only
It is to be used to help understand method and its core concept of the invention；At the same time, for those skilled in the art, according to this hair
Bright thought, there will be changes in the specific implementation manner and application range, in conclusion the content of the present specification should not manage
Solution is limitation of the present invention.
Claims (12)
1. a kind of recognition methods of subject type characterized by comprising
The voice that mass users are obtained for multiple subject types puts question to sample；
According to subject type, sample is putd question to be marked the voice to obtain target voice and put question to sample；
It puts question to sample as training data using the target voice, is training knot with the corresponding subject type of the target voice sample
Fruit, training obtain subject identification model；
Receive the voice question information for problem of target user's input；
The voice question information is imported into the subject identification model, obtains the corresponding target subject of the problem.
2. the method according to claim 1, wherein in the language for problem of the reception target user input
It is after sound question information and described by the voice question information importing subject identification model, obtain the problem pair
Before the target subject answered, the method also includes:
The voice question information is identified to generate the text question information for being directed to the problem；
The text question information is exported in the display page and exports inquiry message；The inquiry message is for inquiring the text
Whether first content indicated by question information matches with the second content indicated by the problem；
Obtain the return information of target user's input；
If the return information shows second indicated by first content indicated by the text question information and the problem
Content matches, and execution is described to import the subject identification model for the voice question information, and it is corresponding to obtain the problem
Target family purpose step.
3. according to the method described in claim 2, it is characterized in that, the voice question information is imported the subject described
Identification model, after obtaining the corresponding target subject of the problem, the method also includes:
According to the target subject, the target search range of the problem is determined；
The corresponding answer of the problem is searched for from the target search range；
The answer is pushed to the target user.
4. according to the method described in claim 3, it is characterized in that, the method also includes:
The audio that search matches with the answer；
The target audio to match with the target subject is screened from the audio；
While pushing the answer to the target user, the target audio is played.
5. the method according to claim 3 or 4, which is characterized in that give the target user in the push answer
Later, the method also includes:
The vocal print feature of the target user is extracted from the voice question information；
According to the vocal print feature, the identity information of the target user is identified；
According to the identity information, the information of the teacher of class where determining the target user；
The information of the corresponding target teacher of the target subject is determined from the information of the teacher；
The voice question information for problem and the answer are sent to the instructional terminal of the target teacher, so as to described
Target teacher's specific aim readjusting operations topic.
6. a kind of private tutor's equipment characterized by comprising
First acquisition unit puts question to sample for the voice of multiple subject types for obtaining mass users；
Marking unit, for according to subject type, puing question to sample to be marked the voice to obtain target voice and put question to sample
This；
Training unit, for puing question to sample as training data using the target voice, with the corresponding section of the target voice sample
Mesh type is training result, and training obtains subject identification model；
Receiving unit, for receiving the voice question information for problem of target user's input；
It is corresponding to obtain the problem for the voice question information to be imported the subject identification model for second acquisition unit
Target subject.
7. private tutor's equipment according to claim 6, which is characterized in that private tutor's equipment further include:
First recognition unit, for the receiving unit receive target user input the voice question information for problem it
Afterwards and the second acquisition unit is by the voice question information importing subject identification model, obtains the problem pair
Before the target subject answered, the voice question information is identified to generate the text question information for being directed to the problem；
Inquiry unit, for exporting the text question information in the display page and exporting inquiry message；The inquiry message is used
Whether the first content indicated by the inquiry text question information matches with the second content indicated by the problem；
The first acquisition unit is also used to obtain the return information of target user's input；
The second acquisition unit, specifically for showing in first indicated by the text question information when the return information
When appearance matches with the second content indicated by the problem, the voice question information is imported into the subject identification model,
Obtain the corresponding target subject of the problem.
8. private tutor's equipment according to claim 7, which is characterized in that private tutor's equipment further include:
First determination unit identifies mould for the voice question information to be imported the subject in the second acquisition unit
Type after obtaining the corresponding target subject of the problem, according to the target subject, determines the target search model of the problem
It encloses；
Search unit, for searching for the corresponding answer of the problem from the target search range；
Push unit, for pushing the answer to the target user.
9. private tutor's equipment according to claim 8, which is characterized in that private tutor's equipment further include:
Described search unit is also used to search for the audio to match with the answer；
Screening unit, for screening the target audio to match with the target subject from the audio；
Broadcast unit, for playing the target while push unit pushes the answer to the target user
Audio.
10. private tutor's equipment according to claim 8 or claim 9, which is characterized in that private tutor's equipment further include:
Extraction unit, for being putd question to from the voice after the push unit pushes the answer to the target user
The vocal print feature of the target user is extracted in information；
Second recognition unit, for identifying the identity information of the target user according to the vocal print feature；
Second determination unit, for determining the information of the teacher of the target user place class according to the identity information；
Second determination unit is also used to determine the letter of the corresponding target teacher of the target subject from the information of the teacher
Breath；
Transmission unit, for sending the voice question information for problem and the answer to the teaching of the target teacher
Terminal, so as to target teacher specific aim readjusting operations topic.
11. a kind of private tutor's equipment characterized by comprising
It is stored with the memory of executable program code；
The processor coupled with the memory；
The processor calls the executable program code stored in the memory, requires 1-5 to appoint for perform claim
A kind of recognition methods of subject type described in one.
12. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage computer journey
Sequence, wherein the computer program makes computer perform claim require a kind of described in any item identifications of subject type of 1-5
Method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910061395.9A CN109545015A (en) | 2019-01-23 | 2019-01-23 | A kind of recognition methods and private tutor's equipment of subject type |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910061395.9A CN109545015A (en) | 2019-01-23 | 2019-01-23 | A kind of recognition methods and private tutor's equipment of subject type |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109545015A true CN109545015A (en) | 2019-03-29 |
Family
ID=65838155
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910061395.9A Pending CN109545015A (en) | 2019-01-23 | 2019-01-23 | A kind of recognition methods and private tutor's equipment of subject type |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109545015A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111081080A (en) * | 2019-05-29 | 2020-04-28 | 广东小天才科技有限公司 | Voice detection method and learning device |
| CN111079489A (en) * | 2019-05-28 | 2020-04-28 | 广东小天才科技有限公司 | Content identification method and electronic equipment |
| CN111091035A (en) * | 2019-05-05 | 2020-05-01 | 广东小天才科技有限公司 | Subject identification method and electronic equipment |
| CN112308511A (en) * | 2020-10-27 | 2021-02-02 | 北京字节跳动网络技术有限公司 | Task plan generation method and device, electronic equipment and storage medium |
| CN113870635A (en) * | 2019-10-25 | 2021-12-31 | 北京猿力教育科技有限公司 | Voice answering method and device |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1182259A (en) * | 1996-11-11 | 1998-05-20 | 李琳山 | Pronunciation training system and method |
| CN1787076A (en) * | 2005-12-13 | 2006-06-14 | 浙江大学 | Method for distinguishing speek person based on hybrid supporting vector machine |
| CN102324232A (en) * | 2011-09-12 | 2012-01-18 | 辽宁工业大学 | Method for recognizing sound-groove and system based on gauss hybrid models |
| CN105094717A (en) * | 2015-07-15 | 2015-11-25 | 百度在线网络技术（北京）有限公司 | Printing method, printing device and printer based on voice input |
| CN105930486A (en) * | 2016-04-29 | 2016-09-07 | 广东小天才科技有限公司 | Quick search method and apparatus for big data |
| CN106776760A (en) * | 2016-11-18 | 2017-05-31 | 广东小天才科技有限公司 | Be applied to intelligent terminal searches topic method and device |
| CN106959999A (en) * | 2017-02-06 | 2017-07-18 | 广东小天才科技有限公司 | A kind of method and device of phonetic search |
| CN107818168A (en) * | 2017-11-10 | 2018-03-20 | 广东小天才科技有限公司 | Topic searching method, device and equipment |
| CN107945599A (en) * | 2017-11-27 | 2018-04-20 | 淄博职业学院 | Timely answering system under a kind of class |
| CN109213856A (en) * | 2018-10-22 | 2019-01-15 | 广东小天才科技有限公司 | A kind of method for recognizing semantics and system |
-
2019
- 2019-01-23 CN CN201910061395.9A patent/CN109545015A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1182259A (en) * | 1996-11-11 | 1998-05-20 | 李琳山 | Pronunciation training system and method |
| CN1787076A (en) * | 2005-12-13 | 2006-06-14 | 浙江大学 | Method for distinguishing speek person based on hybrid supporting vector machine |
| CN102324232A (en) * | 2011-09-12 | 2012-01-18 | 辽宁工业大学 | Method for recognizing sound-groove and system based on gauss hybrid models |
| CN105094717A (en) * | 2015-07-15 | 2015-11-25 | 百度在线网络技术（北京）有限公司 | Printing method, printing device and printer based on voice input |
| CN105930486A (en) * | 2016-04-29 | 2016-09-07 | 广东小天才科技有限公司 | Quick search method and apparatus for big data |
| CN106776760A (en) * | 2016-11-18 | 2017-05-31 | 广东小天才科技有限公司 | Be applied to intelligent terminal searches topic method and device |
| CN106959999A (en) * | 2017-02-06 | 2017-07-18 | 广东小天才科技有限公司 | A kind of method and device of phonetic search |
| CN107818168A (en) * | 2017-11-10 | 2018-03-20 | 广东小天才科技有限公司 | Topic searching method, device and equipment |
| CN107945599A (en) * | 2017-11-27 | 2018-04-20 | 淄博职业学院 | Timely answering system under a kind of class |
| CN109213856A (en) * | 2018-10-22 | 2019-01-15 | 广东小天才科技有限公司 | A kind of method for recognizing semantics and system |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111091035A (en) * | 2019-05-05 | 2020-05-01 | 广东小天才科技有限公司 | Subject identification method and electronic equipment |
| CN111079489A (en) * | 2019-05-28 | 2020-04-28 | 广东小天才科技有限公司 | Content identification method and electronic equipment |
| CN111079489B (en) * | 2019-05-28 | 2023-04-28 | 广东小天才科技有限公司 | Content identification method and electronic equipment |
| CN111081080A (en) * | 2019-05-29 | 2020-04-28 | 广东小天才科技有限公司 | Voice detection method and learning device |
| CN111081080B (en) * | 2019-05-29 | 2022-05-03 | 广东小天才科技有限公司 | Voice detection method and learning device |
| CN113870635A (en) * | 2019-10-25 | 2021-12-31 | 北京猿力教育科技有限公司 | Voice answering method and device |
| CN112308511A (en) * | 2020-10-27 | 2021-02-02 | 北京字节跳动网络技术有限公司 | Task plan generation method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109545015A (en) | A kind of recognition methods and private tutor's equipment of subject type | |
| US20190108273A1 (en) | Data Processing Method, Apparatus and Electronic Device | |
| Shawai et al. | Malay language mobile learning system (MLMLS) using NFC technology | |
| Erickson | Demystifying data construction and analysis | |
| CN102842306B (en) | Sound control method and device, voice response method and device | |
| KR101605430B1 (en) | SYSTEM AND METHOD FOR BUINDING QAs DATABASE AND SEARCH SYSTEM AND METHOD USING THE SAME | |
| US7143037B1 (en) | Spelling words using an arbitrary phonetic alphabet | |
| CN107992195A (en) | A kind of processing method of the content of courses, device, server and storage medium | |
| CN107291343A (en) | Recording method, device and the computer-readable recording medium of notes | |
| CN101739437A (en) | Implementation method for network sound-searching unit and specific device thereof | |
| CN104361132B (en) | A kind of language data processing method and processing device | |
| CN112685550B (en) | Intelligent question-answering method, intelligent question-answering device, intelligent question-answering server and computer readable storage medium | |
| CN111107442A (en) | Method and device for acquiring audio and video files, server and storage medium | |
| Finnegan | Communication and technology | |
| CN114401431A (en) | Virtual human explanation video generation method and related device | |
| CN113360598A (en) | Matching method and device based on artificial intelligence, electronic equipment and storage medium | |
| CN116821290A (en) | Multitasking dialogue-oriented large language model training method and interaction method | |
| KR100593589B1 (en) | Multilingual Interpretation / Learning System Using Speech Recognition | |
| CN106709018A (en) | Method and device for hitting preset problems | |
| CN109920285B (en) | Foreign language teaching system and method based on word corresponding translation | |
| CN114390331B (en) | Video teaching method, system, equipment and medium | |
| CN109002454B (en) | Method and electronic equipment for determining spelling partition of target word | |
| CN114297450A (en) | Deep learning-based dialogue system and dialogue method thereof | |
| KR20190070682A (en) | System and method for constructing and providing lecture contents | |
| KR102105882B1 (en) | Apparatus for Providing Learning Service and Driving Method Thereof |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190329 |