CN110534093A - Rest method, server, client to speaking for children identification - Google Patents
Rest method, server, client to speaking for children identification Download PDFInfo
- Publication number
- CN110534093A CN110534093A CN201910789150.8A CN201910789150A CN110534093A CN 110534093 A CN110534093 A CN 110534093A CN 201910789150 A CN201910789150 A CN 201910789150A CN 110534093 A CN110534093 A CN 110534093A
- Authority
- CN
- China
- Prior art keywords
- information
- children
- speaking
- speech recognition
- child
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/02—Feature extraction for speech recognition; Selection of recognition unit
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/28—Constructional details of speech recognition systems
- G10L15/30—Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
Abstract
The present invention provides the rest method of a kind of pair of speaking for children identification, server, client, wherein the method applied to server includes: the current speaking for children information to be identified for receiving parent's client and sending, and is pre-processed to speaking for children information;Speech recognition is carried out to pretreated voice messaging using speech recognition modeling, obtains the essential information of current child;The standard semantic information in pretreated voice messaging is identified using semantics recognition algorithm;According to the essential information of current child and standard semantic information, generates asking for leave for current child and record information.It is provided by the invention that faster the task of asking for leave can be simply completed to the rest method of speaking for children identification, server and client side, strong operability, and false information is asked convenient for programming count and record, conducive to inquiry and verification from now on, reduce the occurrence probability of mistake.
Description
Technical field
The present invention relates to artificial intelligence fields, rest method, service in particular to the identification of a kind of pair of speaking for children
Device, client.
Background technique
Child's mode of asking for leave, which is generally in parent to garden, at present asks for leave, or is asked by social softwares such as phone, wechats
It is false and asked for leave by way of logging in educational system software and carrying out copy editor.
But existing mode of asking for leave is to be manually entered to ask false information, needs teacher to be operated manually and record, leads
Cause often will appear errors and omissions, can not achieve the programming count and record for asking false information, often results in child and ask false information
A series of problems, such as misregistration, attendance mistake.
Summary of the invention
In order to solve to can not achieve the programming count for asking false information and record in the prior art, and often results in child and ask
The problem of false information misregistration, the present invention provide the rest method of a kind of pair of speaking for children identification, client, server.
In a first aspect, the present invention provides the rest method of a kind of pair of speaking for children identification, method is applied to server, the party
Method includes:
The current speaking for children information to be identified that parent's client is sent is received, speaking for children information is located in advance
Reason;
Speech recognition is carried out to pretreated voice messaging using speech recognition modeling, obtains the basic letter of current child
Breath;
The standard semantic information in pretreated voice messaging is identified using semantics recognition algorithm;
According to the essential information of current child and standard semantic information, generates asking for leave for current child and record information.
Further, speech recognition is carried out to pretreated voice messaging using speech recognition modeling, obtains current children
Before the essential information of youngster further include:
All child's recording are received, voice data collection is established;
The modeling for carrying out speech recognition to voice data collection using deep learning algorithm, obtains speech recognition modeling.
Further, according to the essential information of current child and standard semantic information, generate current child asks false entry
After information further include:
Asking for leave for current child is recorded by information is formatted;
Information is recorded according to formatted ask for leave, counts attendance information and payment information.
Further, method further include:
Standard semantic information is sent to teacher's client;
It receives teacher's client and sends speech answering information;
Speech answering information is sent to parent's client.
Second aspect, the present invention provide the rest method of a kind of pair of speaking for children identification, and method is applied to parent's client,
This method comprises:
Obtain current speaking for children information to be identified;
Current speaking for children information to be identified is sent to server, so that server carries out in advance speaking for children information
Processing carries out speech recognition to pretreated voice messaging using speech recognition modeling, obtains the essential information of current child,
The standard semantic information in pretreated voice messaging is identified using semantics recognition algorithm, according to the basic letter of current child
Breath and standard semantic information, generate asking for leave for current child and record information.
The third aspect, the present invention provide the server of asking for leave of a kind of pair of speaking for children identification, and server includes:
Receiving module, for receiving the current speaking for children information to be identified of parent's client transmission, to speaking for children
Information is pre-processed;
Speech recognition module is obtained for carrying out speech recognition to pretreated voice messaging using speech recognition modeling
To the essential information of current child;
Semantics recognition module, for identifying the standard semantic in pretreated voice messaging using semantics recognition algorithm
Information;
Information generating module of asking for leave generates current children for the essential information and standard semantic information according to current child
Asking for leave for youngster records information.
Further, before speech recognition module further include:
Voice data collection establishes module, for receiving all child's recording, establishes voice data collection;
Speech recognition modeling determining module is built for carrying out speech recognition to voice data collection using deep learning algorithm
Mould obtains speech recognition modeling.
Fourth aspect, the present invention provide parent's client of asking for leave of a kind of pair of speaking for children identification, and parent's client includes:
Module is obtained, for obtaining current speaking for children information to be identified;
Sending module, for current speaking for children information to be identified to be sent to server, so that server is to child
Voice messaging is pre-processed, and is carried out speech recognition to pretreated voice messaging using speech recognition modeling, is obtained current
The essential information of child identifies the standard semantic information in pretreated voice messaging using semantics recognition algorithm, according to
The essential information and standard semantic information of current child, generates asking for leave for current child and records information.
5th aspect, the present invention provides a kind of electronic equipment, including memory, processor and storage are on a memory and can
The computer program run on a processor, the processor realize that first aspect provides when executing described program to baby talk
The step of rest method of sound identification.
6th aspect, the present invention provide a kind of non-transient computer readable storage medium, are stored thereon with computer program,
The step of rest method identified to speaking for children that first aspect provides is realized when the computer program is executed by processor.
It is provided by the invention to speaking for children identification rest method, server and client side can be faster simply complete
At the task of asking for leave, strong operability, and false information is asked convenient for programming count and record, conducive to inquiry and verification from now on, reduced
The occurrence probability of mistake.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is the flow diagram of the rest method provided in an embodiment of the present invention to speaking for children identification;
Fig. 2 be another embodiment of the present invention provides to speaking for children identification rest method flow diagram;
Fig. 3 is the structural block diagram of the server of asking for leave provided in an embodiment of the present invention to speaking for children identification;
Fig. 4 is the structural block diagram of parent's client of asking for leave provided in an embodiment of the present invention to speaking for children identification;
Fig. 5 is that entire voice provided in an embodiment of the present invention is asked for leave the flow diagram of business function;
Fig. 6 is electronic device block diagram provided in an embodiment 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 described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Child's mode of asking for leave, which is generally in parent to garden, at present asks for leave, is asked by social softwares such as phone or wechats
False, educational system software text is asked for leave.These modes of asking for leave have the following problems:
1. it is time-consuming and laborious to ask for leave in parent to garden.
2. the information of asking for leave of the social softwares such as phone, wechat needs teacher to be operated manually and record, often will appear
The problem of errors and omissions leads to child's attendance mistake, and payment calculates error.
3. the complexity and diversity of channel of asking for leave cause to ask false information that can not carry out automatic butt with kindergarten's operation system,
It can not achieve automatically statistics and record.
4. to child, old man is illiterate, dim eyesight or is inconvenient to for the people for inputting text, typewriting is a kind of burden.
In order to solve the above problem in the prior art, the embodiment of the present invention, which provides, a kind of asks for leave to speaking for children identification
Method, client, server.As shown in FIG. 1, FIG. 1 is the rest methods provided in an embodiment of the present invention to speaking for children identification
Flow diagram, in figure this method comprises:
Step S101 receives the current speaking for children information to be identified that parent's client is sent, to speaking for children information
It is pre-processed;
Step S102 carries out speech recognition to pretreated voice messaging using speech recognition modeling, obtains current children
The essential information of youngster;
Step S103 identifies the standard semantic information in pretreated voice messaging using semantics recognition algorithm;
Step S104, according to the essential information of current child and standard semantic information, generate current child asks false entry
Information.
Specifically, server receives the current speaking for children information to be identified that parent's client is sent, to received children
Childrenese sound carries out the pretreatment of alignment enhancing, using trained speech recognition modeling to alignment enhance pretreated voice into
Row identification, the essential information of the current child identified, wherein essential information includes the place class of child, corresponding religion
Teacher.The standard semantic information in pretreated voice messaging is identified further according to semantics recognition algorithm, can be said according to child
Words habit, speech logic and pronunciation understand the meaning of one's words, important information etc., learns child in identification recording by reading understanding means
Recording Plays it is semantic, such as: due to throat inflammation, need to ask for leave 1 day.Herein, standard semantic (the important letter in recording
Breath) are as follows: throat, inflammation, 1 day.Finally, by corresponding storage the asking to current child of information of asking for leave of the child of currently transmitted recording
In false entry.
Rest method provided in an embodiment of the present invention to speaking for children identification, which faster can be simply completed to ask for leave, appoints
Business, strong operability, and false information is asked convenient for programming count and record, conducive to inquiry and verification from now on, reduce the hair of mistake
Raw probability.
Content based on the various embodiments described above, as a kind of alternative embodiment: as shown in Fig. 2, utilizing speech recognition modeling
Speech recognition is carried out to pretreated voice messaging, before obtaining the essential information of current child further include:
Step S201 receives all child's recording, establishes voice data collection;
Step S202 is carried out the modeling of speech recognition to voice data collection using deep learning algorithm, obtains speech recognition
Model.
In Fig. 2, step S201, S202 before step S102, specifically: server receives the record of all school childs
Then sound is spoken mode using deep learning algorithm and in conjunction with child, is carried out to voice data collection for establishing voice data collection
The modeling of speech recognition, obtains speech recognition modeling.Herein, the voice data collection of foundation only stores the recording of this school child,
The voice of other childs other than this school is not stored.
Content based on the various embodiments described above, as a kind of alternative embodiment: according to the essential information and mark of current child
Quasi- semantic information, after generating the asking for leave and record information of current child further include:
Asking for leave for current child is recorded by information is formatted;
Information is recorded according to formatted ask for leave, counts attendance information and payment information.
Specifically, the information such as time and the origin of an incident of asking for leave in false entry will be asked to be formatted processing, and extracts and examine
Diligent information carries out the statistics of payment information, and the payment amount of money of statistics is sent to parent's client and reminds payment.
For the embodiment of the present invention by the directly synchronous kindergarten's office system of data, direct Intelligent statistical child attendance and payment are golden
Volume, it is intermediate without manual operation, it reduces statistics and calculates mistake.
Content based on the various embodiments described above, as a kind of alternative embodiment: method further include:
Standard semantic information is sent to teacher's client;
It receives teacher's client and sends speech answering information;
Speech answering information is sent to parent's client.
Specifically, the standard semantic information that server will identify that is sent to teacher's client, teacher's client is received
Child asks for leave after recording, may be selected to reply child by way of recording, server receives teacher's client and sends voice at this time
The speech answering information is sent to parent's client by return information.At this point, teacher's recording clicks directly on " reply " button and starts
Recording, if child calls in sick, replys the sentences such as child's " take a good rest, understand carefully, take medicine on time ".
It is understood that the corresponding voice for recording one or more this school childs of each parent's client, according to
The voice of child can identify the class corresponded to where finding it and the teacher that teaches, to complete voice provided in an embodiment of the present invention
The rest method of identification.
According to another aspect of the present invention, the embodiment of the present invention provides the rest method of a kind of pair of speaking for children identification,
This method is applied to parent's client, and method includes:
Obtain current speaking for children information to be identified;
Current speaking for children information to be identified is sent to server, so that server carries out in advance speaking for children information
Processing carries out speech recognition to pretreated voice messaging using speech recognition modeling, obtains the essential information of current child,
The standard semantic information in pretreated voice messaging is identified using semantics recognition algorithm, according to the basic letter of current child
Breath and standard semantic information, generate asking for leave for current child and record information.
Specifically, the embodiment of the present invention is based on parent's client, in detail are as follows: parent's client obtains current children to be identified
Youngster's voice messaging, then the current speaking for children information to be identified that will acquire are sent to server end, so that server is to child
Voice messaging is pre-processed, and is carried out speech recognition to pretreated voice messaging using speech recognition modeling, is obtained current
The essential information of child identifies the standard semantic information in pretreated voice messaging using semantics recognition algorithm, according to
The essential information and standard semantic information of current child, generates asking for leave for current child and records information.
Rest method provided in an embodiment of the present invention to speaking for children identification, which faster can be simply completed to ask for leave, appoints
Business, strong operability, and false information is asked convenient for programming count and record, conducive to inquiry and verification from now on, reduce the hair of mistake
Raw probability.
According to a further aspect of the invention, the embodiment of the present invention provides the service of asking for leave of a kind of pair of speaking for children identification
Device, referring to Fig. 3, Fig. 3 is the structural block diagram of the server of asking for leave provided in an embodiment of the present invention to speaking for children identification.The device
It is provided in an embodiment of the present invention to speaking for children identification for being completed in foregoing embodiments.Therefore, in foregoing embodiments
In the rest method provided in an embodiment of the present invention to speaking for children identification in description and definition, can be used for of the invention real
Apply the understanding of each execution module in example.
The server includes:
Receiving module 301, for receiving the current speaking for children information to be identified of parent's client transmission, to baby talk
Message breath is pre-processed;
Speech recognition module 302, for carrying out speech recognition to pretreated voice messaging using speech recognition modeling,
Obtain the essential information of current child;
Semantics recognition module 303, for identifying the standard in pretreated voice messaging using semantics recognition algorithm
Semantic information;
Information generating module of asking for leave 304 generates current for the essential information and standard semantic information according to current child
Asking for leave for child records information.
Rest method provided in an embodiment of the present invention to speaking for children identification, which faster can be simply completed to ask for leave, appoints
Business, strong operability, and false information is asked convenient for programming count and record, conducive to inquiry and verification from now on, reduce the hair of mistake
Raw probability.
According to a further aspect of the invention, the embodiment of the present invention provides a long-traveller of asking for leave for a kind of pair of speaking for children identification
Family end, referring to fig. 4, Fig. 4 are the structural block diagram of parent's client of asking for leave provided in an embodiment of the present invention to speaking for children identification.
The device is provided in an embodiment of the present invention to speaking for children identification for completing in foregoing embodiments.Therefore, aforementioned each
The description and definition in the rest method provided in an embodiment of the present invention to speaking for children identification in embodiment, can be used for this
The understanding of each execution module in inventive embodiments.
Parent's client includes:
Module 401 is obtained, for obtaining current speaking for children information to be identified;
Sending module 402, for current speaking for children information to be identified to be sent to server, so that server is to children
Youngster's voice messaging pre-processes, and carries out speech recognition to pretreated voice messaging using speech recognition modeling, is worked as
The essential information of preceding child identifies the standard semantic information in pretreated voice messaging, root using semantics recognition algorithm
According to the essential information and standard semantic information of current child, generates asking for leave for current child and record information.
Rest method provided in an embodiment of the present invention to speaking for children identification, which faster can be simply completed to ask for leave, appoints
Business, strong operability, and false information is asked convenient for programming count and record, conducive to inquiry and verification from now on, reduce the hair of mistake
Raw probability.
Content based on the various embodiments described above, as a kind of alternative embodiment: as shown in figure 5, Fig. 5 is the embodiment of the present invention
The entire voice provided is asked for leave the flow diagram of business function, is described in detail as follows:
The recording 1. child asks for leave:
The module 1. opening " parent end APP " entrance " is asked for leave ", clicks " voice is asked for leave " icon and enters recording module of asking for leave.
2. clicking " starting to record " button carries out recorded speech.
3. the contents such as explanation " asking for leave the time ", " origin of an incident of asking for leave " when recording.
4. recording can be suspended in recording process.
5. recording pause after the completion can audition.
It records 6. recording and completing to send to ask for leave to background server.
The recording 2. background server processing child asks for leave:
1. background server receives the recording of asking for leave of transmission, reception processing is carried out, if the phonetic incepting success sent,
" parent end APP " prompt " sending successfully " is fed back to immediately.
2. after background query failure cause, feeding back to " parent end APP " prompt immediately if the phonetic incepting failure sent
" sending failure, " simultaneously prompts failure cause, and user can retransmit again.
3. after background server receives voice success, passing through the currently transmitted people's essential information of the automatic recognition of speech, place class
Grade, teach teacher's information.
4. recording is pushed in the corresponding teacher of " child-care center end APP " and the account of dining room relevant station.
3. teacher listens to recording and replys:
1. child can be received and ask dummy message after teacher's account of background server push is logged in by " child-care center end APP "
It reminds.
2. teacher opens " child-care center end APP " or clicks directly on PUSH message and enter child and asks for leave details, can directly listen to
Child asks for leave recording.
3. teacher may be selected to reply child by way of recording.
4. teacher's recording clicks directly on " reply " button and starts to record, as child call in sick reply child " take a good rest, it is good
Holiday speech is taken medicine on time " etc..
5. sending back copy back sound to background server after the completion of recording.
4. background server handles teacher response's recording:
1. after background query failure cause, feeding back to " child-care center end immediately if replying recording background server reception failure
APP " prompt " sending failure, " simultaneously prompts failure cause, and user can retransmit again.
2. if the recording of reply is pushed to parent end by background server after reply recording background server receives successfully
APP。
5. child listens to teacher response:
1. background server is pushed to the recording of infant teacher's reply, child, which logs in " parent end APP ", can receive teacher
Reply recording.
2. child clicks and is directly entered details page of asking for leave, carry out listening to recording.
6. pair speaking for children intelligent recognition is handled:
After 1. child's recording is sent successfully, by constructing special children speech data set using AI technology.
2. using depth learning technology combine to children speak mode immediately carry out children speech identification modeling.
3. system automatically identifies the voice content of child's recording, logical according to speak habit, speech logic and pronunciation of child
It crosses reading understanding means and carries out algorithm analysis, understand the meaning of one's words, important information in identification recording.
4. the information such as time and the origin of an incident of asking for leave that will identify that are formatted processing, and extract and be sent to backstage
Server is saved.
7. background server saves statistical data
1. background server receive formatted ask false entry after automatically save record.
2. according to the records such as asking false entry and turning out for work carry out work attendance statistics.
3. Intelligent statistical payment amount of money is sent to parent and reminds payment by work attendance statistics.
Fig. 6 is electronic device block diagram provided in an embodiment of the present invention, as shown in fig. 6, the equipment includes: processor 601, deposits
Reservoir 602 and bus 603;
Wherein, processor 601 and storage 602 complete mutual communication by bus 603 respectively;Processor 601 is used for
The program instruction in memory 602 is called, to execute provided by above-described embodiment to the rest method of speaking for children identification, example
Such as include: the current speaking for children information to be identified for receiving parent's client and sending, speaking for children information is pre-processed;
Speech recognition is carried out to pretreated voice messaging using speech recognition modeling, obtains the essential information of current child;It utilizes
Semantics recognition algorithm identifies the standard semantic information in pretreated voice messaging;According to the essential information of current child and
Standard semantic information generates asking for leave for current child and records information.
The embodiment of the present invention provides a kind of non-transient computer readable storage medium, is stored thereon with computer program, should
The step of rest method that realization identifies speaking for children when computer program is executed by processor.For example, receive parent
The current speaking for children information to be identified that client is sent, pre-processes speaking for children information;Utilize speech recognition mould
Type carries out speech recognition to pretreated voice messaging, obtains the essential information of current child;Known using semantics recognition algorithm
It Chu not standard semantic information in pretreated voice messaging;According to the essential information of current child and standard semantic information,
It generates asking for leave for current child and records information.
The apparatus embodiments described above are merely exemplary, wherein unit can be as illustrated by the separation member
Or may not be and be physically separated, component shown as a unit may or may not be physical unit, i.e.,
It can be located in one place, or may be distributed over multiple network units.It can select according to the actual needs therein
Some or all of the modules achieves the purpose of the solution of this embodiment.Those of ordinary skill in the art are not paying creative labor
In the case where dynamic, it can understand and implement.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
It realizes by means of software and necessary general hardware platform, naturally it is also possible to pass through hardware.Based on this understanding, on
Stating technical solution, substantially the part that contributes to existing technology can be embodied in the form of software products in other words, should
Computer software product may be stored in a computer readable storage medium, such as ROM/RAM, magnetic disk, CD, including several fingers
It enables and using so that a computer equipment (can be personal computer, server or the network equipment etc.) executes each implementation
The method of certain parts of example or embodiment.
Finally, applying specific embodiment in the present invention, principle and implementation of the present invention are described, above
The explanation of embodiment is merely used to help understand method and its core concept of the invention;Meanwhile for the general skill of this field
Art personnel, according to the thought of the present invention, there will be changes in the specific implementation manner and application range, in conclusion this
Description should not be construed as limiting the invention.
Claims (10)
1. the rest method of a kind of pair of speaking for children identification, which is characterized in that the method is applied to server, the method packet
It includes:
The current speaking for children information to be identified that parent's client is sent is received, the speaking for children information is located in advance
Reason;
Speech recognition is carried out to pretreated voice messaging using speech recognition modeling, obtains the essential information of current child;
The standard semantic information in pretreated voice messaging is identified using semantics recognition algorithm;
According to the essential information and standard semantic information of the current child, generates asking for leave for current child and record information.
2. the method according to claim 1, wherein described utilize speech recognition modeling to pretreated voice
Information carries out speech recognition, before obtaining the essential information of current child further include:
All child's recording are received, voice data collection is established;
The modeling for carrying out speech recognition to the voice data collection using deep learning algorithm, obtains speech recognition modeling.
3. the method according to claim 1, wherein the essential information and standard according to the current child
Semantic information, after generating the asking for leave and record information of current child further include:
Asking for leave for current child is recorded by information is formatted;
Information is recorded according to formatted ask for leave, counts attendance information and payment information.
4. the method according to claim 1, wherein the method also includes:
The standard semantic information is sent to teacher's client;
It receives teacher's client and sends speech answering information;
The speech answering information is sent to parent's client.
5. the rest method of a kind of pair of speaking for children identification, which is characterized in that the method is applied to parent's client, the side
Method includes:
Obtain current speaking for children information to be identified;
Current speaking for children information to be identified is sent to server so that the server to the speaking for children information into
Row pretreatment carries out speech recognition to pretreated voice messaging using speech recognition modeling, obtains the basic of current child
Information identifies the standard semantic information in pretreated voice messaging using semantics recognition algorithm, according to the current children
The essential information and standard semantic information of youngster, generates asking for leave for current child and records information.
6. the server of asking for leave of a kind of pair of speaking for children identification, which is characterized in that the server includes:
Receiving module, for receiving the current speaking for children information to be identified of parent's client transmission, to the speaking for children
Information is pre-processed;
Speech recognition module is worked as carrying out speech recognition to pretreated voice messaging using speech recognition modeling
The essential information of preceding child;
Semantics recognition module, for identifying that the standard semantic in pretreated voice messaging is believed using semantics recognition algorithm
Breath;
Information generating module of asking for leave generates current children for the essential information and standard semantic information according to the current child
Asking for leave for youngster records information.
7. server according to claim 6, which is characterized in that before the speech recognition module further include:
Voice data collection establishes module, for receiving all child's recording, establishes voice data collection;
Speech recognition modeling determining module is built for carrying out speech recognition to the voice data collection using deep learning algorithm
Mould obtains speech recognition modeling.
8. parent's client of asking for leave of a kind of pair of speaking for children identification, which is characterized in that parent's client includes:
Module is obtained, for obtaining current speaking for children information to be identified;
Sending module, for current speaking for children information to be identified to be sent to server, so that the server is to described
Speaking for children information is pre-processed, and is carried out speech recognition to pretreated voice messaging using speech recognition modeling, is obtained
The essential information of current child, identifies the standard semantic information in pretreated voice messaging using semantics recognition algorithm,
According to the essential information and standard semantic information of the current child, generates asking for leave for current child and record information.
9. a kind of electronic equipment including memory, processor and stores the calculating that can be run on a memory and on a processor
Machine program, which is characterized in that the processor is realized as described in any one of Claims 1-4 when executing described program to child
The step of rest method of speech recognition.
10. a kind of non-transient computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer
The step of rest method as described in any one of Claims 1-4 to speaking for children identification is realized when program is executed by processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910789150.8A CN110534093A (en) | 2019-08-26 | 2019-08-26 | Rest method, server, client to speaking for children identification |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910789150.8A CN110534093A (en) | 2019-08-26 | 2019-08-26 | Rest method, server, client to speaking for children identification |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110534093A true CN110534093A (en) | 2019-12-03 |
Family
ID=68662853
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910789150.8A Pending CN110534093A (en) | 2019-08-26 | 2019-08-26 | Rest method, server, client to speaking for children identification |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110534093A (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105070288A (en) * | 2015-07-02 | 2015-11-18 | 百度在线网络技术(北京)有限公司 | Vehicle-mounted voice instruction recognition method and device |
CN108563633A (en) * | 2018-03-29 | 2018-09-21 | 腾讯科技(深圳)有限公司 | A kind of method of speech processing and server |
-
2019
- 2019-08-26 CN CN201910789150.8A patent/CN110534093A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105070288A (en) * | 2015-07-02 | 2015-11-18 | 百度在线网络技术(北京)有限公司 | Vehicle-mounted voice instruction recognition method and device |
CN108563633A (en) * | 2018-03-29 | 2018-09-21 | 腾讯科技(深圳)有限公司 | A kind of method of speech processing and server |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101010934B (en) | Method for machine learning | |
CN106328166B (en) | Human-computer dialogue abnormality detection system and method | |
EP1277201B1 (en) | Web-based speech recognition with scripting and semantic objects | |
Skantze | Exploring human error handling strategies: Implications for spoken dialogue systems | |
CN105512228A (en) | Bidirectional question-answer data processing method and system based on intelligent robot | |
CN108777751A (en) | A kind of call center system and its voice interactive method, device and equipment | |
CN101834809B (en) | Internet instant message communication system | |
CN111182162A (en) | Telephone quality inspection method, device, equipment and storage medium based on artificial intelligence | |
CN108763548A (en) | Collect method, apparatus, equipment and the computer readable storage medium of training data | |
CN109271503A (en) | Intelligent answer method, apparatus, equipment and storage medium | |
Wu et al. | Harpervalleybank: A domain-specific spoken dialog corpus | |
CN111933118B (en) | Method and device for optimizing voice recognition and intelligent voice dialogue system applying same | |
CN114064943A (en) | Conference management method, conference management device, storage medium and electronic equipment | |
CN109147792A (en) | A kind of voice resume system | |
Wallis | A robot in the kitchen | |
CN110047473B (en) | Man-machine cooperative interaction method and system | |
CN117056481A (en) | Cloud service industry dialogue help system based on large model technology and implementation method | |
US20020002463A1 (en) | Web-based speech recognition with scripting and semantic objects | |
Kumar et al. | Speech to text community application using natural language processing | |
CN110534093A (en) | Rest method, server, client to speaking for children identification | |
WO2017000786A1 (en) | System and method for training robot via voice | |
CN114328867A (en) | Intelligent interruption method and device in man-machine conversation | |
KR20000036769A (en) | Foreign language learning system using mobile station(or PC & telephone) | |
CN113053186A (en) | Interaction method, interaction device and storage medium | |
CN113539245B (en) | Language model automatic training 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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191203 |