Specific embodiment
Example embodiment is described more fully with reference to the drawings.However, example embodiment can be with a variety of shapesFormula is implemented, and is not understood as limited to example set forth herein；On the contrary, thesing embodiments are provided so that the present invention will moreFully and completely, and by the design of example embodiment comprehensively it is communicated to those skilled in the art.
In addition, described feature, structure or characteristic can be incorporated in one or more implementations in any suitable mannerIn example.In the following description, many details are provided to provide and fully understand to the embodiment of the present invention.However,It will be appreciated by persons skilled in the art that technical solution of the present invention can be practiced without one or more in specific detail,Or it can be using other methods, constituent element, device, step etc..In other cases, it is not shown in detail or describes known sideMethod, device, realization or operation are to avoid fuzzy each aspect of the present invention.
Block diagram shown in the drawings is only functional entity, not necessarily must be corresponding with physically separate entity.I.e., it is possible to realize these functional entitys using software form, or realized in one or more hardware modules or integrated circuitThese functional entitys, or these functional entitys are realized in heterogeneous networks and/or processor device and/or microcontroller device.
Flow chart shown in the drawings is merely illustrative, it is not necessary to including all content and operation/step,It is not required to execute by described sequence.For example, some operation/steps can also decompose, and some operation/steps can closeAnd or part merge, therefore the sequence actually executed is possible to change according to the actual situation.
Fig. 1 is shown can reciting the processing method of task or recite the processing unit of task using the embodiment of the present inventionExemplary system architecture 100 schematic diagram.
As shown in Figure 1, system architecture 100 may include one of terminal device 101,102,103 or a variety of, network104 and server 105.Network 104 between terminal device 101,102,103 and server 105 to provide communication linkMedium.Network 104 may include various connection types, such as wired communications links, wireless communication link etc..
It should be understood that the number of terminal device, network and server in Fig. 1 is only schematical.According to realization needIt wants, can have any number of terminal device, network and server.For example server 105 can be multiple server compositionsServer cluster etc..
User can be used terminal device 101,102,103 and be interacted by network 104 with server 105, to receive or send outSend message etc..Terminal device 101,102,103 can be the various electronic equipments with display screen, including but not limited to intelligent handMachine, tablet computer, portable computer and desktop computer etc..
Server 105 can be to provide the server of various services.Such as first user (such as teacher) utilize terminal device103 (being also possible to terminal device 101 or 102) issued the task of reciting for specified content, server to server 105105 after receiving this and reciting task, which can be sent to the terminal of second user (such as student), Jin ErThe speech concurrent of reciting that the terminal of two users can acquire second user gives the progress speech recognition of server 105.Server 105After it will recite voice and be converted to content of text, text content is sent to the terminal of second user, and then second userTerminal according to text content and can need the specified content recited and determine the executive condition for the task of reciting.
In one embodiment of the invention, the terminal of second user, can after the executive condition of task is recited in determinationThe executive condition for the task of reciting is sent to server 105, the terminal of the first user is then sent to by server 105, withIt is checked convenient for the first user.Meanwhile server 105 can also count the execution to the task of reciting that the terminal of multiple users is sentThen statistical result is sent to the terminal of the first user by situation, in order to which the first user checks.
Fig. 2 shows the structural schematic diagrams of the computer system of the electronic equipment suitable for being used to realize the embodiment of the present invention.
It should be noted that Fig. 2 shows the computer system 200 of electronic equipment be only an example, should not be to this hairThe function and use scope of bright embodiment bring any restrictions.
As shown in Fig. 2, computer system 200 includes central processing unit (CPU) 201, it can be read-only according to being stored inProgram in memory (ROM) 202 or be loaded into the program in random access storage device (RAM) 203 from storage section 208 andExecute various movements appropriate and processing.In RAM 203, it is also stored with various programs and data needed for system operatio.CPU201, ROM 202 and RAM 203 is connected with each other by bus 204.Input/output (I/O) interface 205 is also connected to bus204。
I/O interface 205 is connected to lower component: the importation 206 including keyboard, mouse etc.；It is penetrated including such as cathodeThe output par, c 207 of spool (CRT), liquid crystal display (LCD) etc. and loudspeaker etc.；Storage section 208 including hard disk etc.；And the communications portion 209 of the network interface card including LAN card, modem etc..Communications portion 209 via such as becauseThe network of spy's net executes communication process.Driver 210 is also connected to I/O interface 205 as needed.Detachable media 211, such asDisk, CD, magneto-optic disk, semiconductor memory etc. are mounted on as needed on driver 210, in order to read from thereonComputer program be mounted into storage section 208 as needed.
Particularly, according to an embodiment of the invention, may be implemented as computer below with reference to the process of flow chart descriptionSoftware program.For example, the embodiment of the present invention includes a kind of computer program product comprising be carried on computer-readable mediumOn computer program, which includes the program code for method shown in execution flow chart.In such realityIt applies in example, which can be downloaded and installed from network by communications portion 209, and/or from detachable media211 are mounted.When the computer program is executed by central processing unit (CPU) 201, executes and limited in the system of the applicationVarious functions.
It should be noted that computer-readable medium shown in the present invention can be computer-readable signal media or meterCalculation machine readable storage medium storing program for executing either the two any combination.Computer readable storage medium for example can be --- but notBe limited to --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor system, device or device, or any above combination.MeterThe more specific example of calculation machine readable storage medium storing program for executing can include but is not limited to: have the electrical connection, just of one or more conducting wiresTaking formula computer disk, hard disk, random access storage device (RAM), read-only memory (ROM), erasable type may be programmed read-only storageDevice (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic memory device,Or above-mentioned any appropriate combination.In the present invention, computer readable storage medium can be it is any include or storage journeyThe tangible medium of sequence, the program can be commanded execution system, device or device use or in connection.And at thisIn invention, computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including but unlimitedIn electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer canAny computer-readable medium other than storage medium is read, which can send, propagates or transmit and be used forBy the use of instruction execution system, device or device or program in connection.Include on computer-readable mediumProgram code can transmit with any suitable medium, including but not limited to: wireless, electric wire, optical cable, RF etc. are above-mentionedAny appropriate combination.
Flow chart and block diagram in attached drawing are illustrated according to the system of various embodiments of the invention, method and computer journeyThe architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generationA part of one module, program segment or code of table, a part of above-mentioned module, program segment or code include one or moreExecutable instruction for implementing the specified logical function.It should also be noted that in some implementations as replacements, institute in boxThe function of mark can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are practicalOn can be basically executed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.Also it wantsIt is noted that the combination of each box in block diagram or flow chart and the box in block diagram or flow chart, can use and execute ruleThe dedicated hardware based systems of fixed functions or operations is realized, or can use the group of specialized hardware and computer instructionIt closes to realize.
Being described in unit involved in the embodiment of the present invention can be realized by way of software, can also be by hardThe mode of part realizes that described unit also can be set in the processor.Wherein, the title of these units is in certain situationUnder do not constitute restriction to the unit itself.
As on the other hand, present invention also provides a kind of computer-readable medium, which be can beIncluded in electronic equipment described in above-described embodiment；It is also possible to individualism, and without in the supplying electronic equipment.Above-mentioned computer-readable medium carries one or more program, when the electronics is set by one for said one or multiple programsWhen standby execution, so that method described in electronic equipment realization as the following examples.For example, the electronic equipment can be realNow each step as shown in figs. 3 to 9.
The realization details of the technical solution of the embodiment of the present invention is described in detail below:
Fig. 3 diagrammatically illustrates the flow chart of the processing method according to an embodiment of the invention for reciting task, shouldThe processing method for reciting task is suitable for electronic equipment described in previous embodiment, which can be such as serverDeng the equipment with data-handling capacity.Referring to shown in Fig. 3, which includes at least step S310 to stepRapid S350, is described in detail as follows:
In step s310, obtain first terminal publication recites task for specified content.
In one embodiment of the invention, step S310 can specifically include: receive first terminal send search andSelection instruction；According to described search and selection instruction, determine that the needs of user's selection of the first terminal are recited specified interiorHold；According to the specified content, task is recited described in generation.I.e. in an embodiment of the present invention, user (such as teacher) can lead toFirst terminal is crossed to search for and select the content for needing to recite.Wherein, the specified content for needing to recite can be entire article, can alsoTo be a certain section or several sections in article, and this article can be the article of any language, such as Chinese articles, English wordsDeng.
In step s 320, the task of reciting is sent to second terminal.
In one embodiment of the invention, (server) receive first terminal transmission recite task after, canThe task of reciting is pushed to second terminal.
In step S330, receive that the second terminal is collected to recite voice.
In one embodiment of the invention, the user of second terminal, can be according to back after receiving the task of recitingThe task of reading aloud recites corresponding content, so second terminal can acquire user recite voice, be then sent to server.
In step S340, the voice of reciting is converted into content of text.
In one embodiment of the invention, server can use mould when that will recite voice and be converted to content of textThe matched method of type, the method that neural network can also be used.The method of Model Matching mainly passes through extraction phonetic feature, soAcoustic model is trained afterwards, and then speech recognition is carried out based on the acoustic model after training, voice conversion will be recitedFor content of text.The method of neural network is to carry out feature learning using neural network, to improve the accuracy of speech recognition.
In step S350, the content of text is sent to the second terminal, so that the second terminal is according to instituteState the executive condition that task is recited described in content of text and the specified content determination.
The technical solution of embodiment illustrated in fig. 3 recite task publisher (such as teacher) can by first terminal publicationThen task recites task by second terminal completion by performer (such as student), realizes and send out on the line for the task of recitingCloth and execution optimize the implementation procedure for the task of reciting, and are conducive to the experience for promoting each participant.
Fig. 4 diagrammatically illustrates the flow chart of the processing method for reciting task according to another embodiment of the invention,Further include following steps on the basis of this recites the step S310 to step S350 of the processing method of task shown in fig. 3:
Step S410 receives the executive condition for reciting task of second terminal feedback.
In one embodiment of the invention, the executive condition for reciting task includes reciting whether task executes completion, withAnd the concrete outcome executed, for example situation etc. is recited to needing to recite the specific of content.
The executive condition for reciting task is sent to the first terminal, so that the first terminal by step S420The executive condition of task is recited described in displaying.
The technical solution of embodiment illustrated in fig. 4 makes (server) executive condition for the task of reciting can be sent to firstTerminal, so that the user of first terminal can intuitively understand and grasp execution feelings of the user to the task of reciting of second terminalCondition is conducive to the experience for promoting first terminal user.
Fig. 5 diagrammatically illustrates the flow chart of the processing method for reciting task according to still another embodiment of the invention,Further include following steps on the basis of this recites processing method each step shown in Fig. 4 of task:
Step S510 receives the evaluation information for the executive condition that first terminal is sent.
In one embodiment of the invention, evaluation information can be the evaluation information of written form, be also possible to voiceThe evaluation information of form.
The evaluation information is sent to the second terminal by step S520, so that the second terminal shows institute's commentaryValence information.
The technical solution of embodiment illustrated in fig. 5 makes (server) can be by the user of first terminal to reciting task executionThe evaluation information of situation is sent to second terminal, and then can guarantee that the user of second terminal can view the evaluation information,Realize timely feedbacking for evaluation information.
Fig. 6 diagrammatically illustrates the flow chart of the processing method for reciting task of still another embodiment in accordance with the present invention,This recites the processing method of task on the basis of Fig. 3 scheme shown in any figure into Fig. 5, can also include the following steps:
Step S610 counts the executive condition for reciting task of at least one second terminal transmission, to obtain at leastThe user of one second terminal is to the overall implementing result for reciting task.
In one embodiment of the invention, overall implementing result of the user of at least one second terminal to the task of recitingMay include: complete recite task number of users, do not complete recite task number of users, recite task complete result be it is excellentElegant number of users recites task and completes that result is good number of users, to recite task to complete result be qualified number of usersMeasuring, reciting task to complete result is underproof number of users etc..
The overall implementing result is sent to the first terminal, so that the first terminal shows institute by step S620State overall implementing result.
The technical solution of embodiment illustrated in fig. 6 can unite executive condition of the user of second terminal to the task of recitingIt counts and timely feedbacks to the user of first terminal, so that the user of first terminal will appreciate that at least one second terminalUser to the overall implementing result of the task of reciting, be conducive to the experience for promoting first terminal user.
Fig. 3 to Fig. 6 is expounded the processing method for reciting task of the embodiment of the present invention from the angle of server, withUnder the processing method for reciting task of the embodiment of the present invention is further elaborated from the angle of above-mentioned second terminal.
Fig. 7 diagrammatically illustrates the flow chart of the processing method for reciting task of still another embodiment in accordance with the present invention,The executing subject for reciting the processing method of task can be terminal (such as above-mentioned second terminal).Referring to shown in Fig. 7, the backThe processing method for reading aloud task includes at least step S710 to step S740, is described in detail as follows:
In step S710, receive server transmission recites task for specified content, wherein described to recite taskIt is that the server is distributed to by first terminal.
In one embodiment of the invention, the user of first terminal can be selected by searching for need recite inHold, server is then distributed to by first terminal.Wherein, the specified content for needing to recite can be entire article, be also possible toA certain section in article or several sections, and this article can be the article of any language, such as Chinese articles, English words.
In step S720, voice is recited if collecting, the voice of reciting is sent to the server.
In one embodiment of the invention, the task of reciting can be presented to by terminal after receiving the task of recitingUser, and then acquire user and recite voice, and be sent to server.
In step S730, reciting described in the text that voice is converted to for the server return is receivedHold.
In one embodiment of the invention, if reciting voice is Chinese speech, voice will be recited and convertTo content of text can be Chinese and/or the corresponding phonetic of Chinese；If reciting voice as English voice, voice will be recitedThe content of text being converted to can be English.
In step S740, according to the content of text and the specified content, the execution feelings of task are recited described in determinationCondition.
The technical solution of embodiment illustrated in fig. 7 makes the executor (such as student) for the task of reciting can be by terminal and serviceInteraction between device is completed to recite task on line, optimizes the implementation procedure for the task of reciting, and is conducive to the experience for promoting user.
On the basis of the embodiment shown in fig. 7, as shown in figure 8, in one embodiment of the invention, according to the textContent and the specified content, determine described in recite the executive condition of task, include the following steps:
Step S810, will correspond in the content of text and the specified content object content for reciting voice intoRow matching.
Step S820, judges whether the content of text matches with the object content, if so, reciting language described in determiningSound is errorless；If not, it is determined that described to recite voice wrong.
Since speech recognition process may have the Chinese text that identification is not accurate, such as identical pronunciation,May there is a situation where identification mistake, therefore propose corresponding prioritization scheme in another embodiment of the present invention, haveBody recites the executive condition of task, including such as shown in figure 9, according to the content of text and the specified content described in determinationLower step:
Step S810, will correspond in the content of text and the specified content object content for reciting voice intoRow matching.
Step S820, judges whether the content of text matches with the object content, if so, reciting language described in determiningSound is errorless；If it is not, thening follow the steps S910.
Step S910, there are the associated texts of incidence relation with the content of text for acquisition.
In one embodiment of the invention, with content of text there are the associated text of incidence relation can be in textHold approximate text, such as phonetically similar word.Specifically, can will be recognized if the content of text that speech recognition is arrived is ChineseChinese be converted to phonetic, then obtain the other Chinese to match with the phonetic, and/or obtain phonetic approximate with the phoneticThe Chinese to match, and the Chinese that will acquire is as above-mentioned associated text.
Step S920 matches the associated text with the object content.
Step S930, judges whether the associated text matches with the object content, if so, reciting language described in determiningSound is errorless；If it is not, it is wrong to recite voice described in determining.
The technical solution of embodiment illustrated in fig. 9 makes in the target that the content of text and needs that voice is converted to are recitedWhen holding mismatch, it can be matched again by the associated text of content of text, improve the robustness and fault-tolerance of system.
It can also be shown in one embodiment of the invention based on Fig. 7 to the processing method shown in Fig. 9 for reciting taskShow the object content for corresponding in specified content that needs are recited and reciting voice, is then marked in the object content describedContent of text and the unmatched place of the object content.
In this embodiment, need to correspond in the specified content recited the object content for reciting voice by showing, andContent of text and the unmatched place of object content are marked in object content, allow to remind reciter to recite in timePlace accidentally, to cause the attention of reciter.In one embodiment of the invention, mark unmatched place can be by notSame color (be such as highlighted, change font color), different fonts, different fonts size mode are marked.
It in one embodiment of the invention can be with root based on Fig. 7 to the processing method shown in Fig. 9 for reciting taskAccording to the executive condition for reciting task, the report that executes of task is recited described in generation, and is shown and described executed report.
The technical solution of the embodiment allows users to intuitively be recognized according to the execution report shown in recitingThat holds specifically recites situation.Wherein, the execution report for reciting task may include: the place for reciting error, recite the used time, reciteScoring etc..
Figure 10 diagrammatically illustrates the structure chart of the processing system according to an embodiment of the invention for reciting task, shouldThe processing system for reciting task specifically includes that first terminal 1001, server 1002 and second terminal 1003.
In one embodiment of the invention, first terminal 1001 can be issued to server 1002 for specified contentRecite task；Fig. 3 may be implemented in above-described embodiment to the processing method shown in fig. 6 for reciting task in server 1002；SecondFig. 7 may be implemented in above-described embodiment to the processing method shown in Fig. 9 for reciting task in terminal 1003.
In one embodiment of the invention, first terminal 1001 can be also used for: receiving and shows that server 1002 is sent outThe executive condition for reciting task sent；And/or receive and show at least one second terminal that server 1002 is sentOverall implementing result of 1003 user to the task of reciting.
In one embodiment of the invention, first terminal 1001 can also receive the execution feelings that user is directed to task of recitingThe evaluation information of condition, and the evaluation information is sent to server 1002, so that the evaluation information is sent to by server 1002Second terminal 1003 is shown.
It is below terminal used in teacher with first terminal, second terminal is terminal used in student, recites taskFor teacher selection recite operation for, the technical solution of one embodiment of the present of invention is described in detail.
The function that terminal used in teacher is realized is as follows:
As shown in figure 11, teacher can select the article for needing to recite by searching at the terminal, such as in search box" spring " is inputted in 1101, then may search out article relevant to " spring ", certainly such as " spring rain " of Tu Fu, " springtime " of Zhu Xi, ZhuClear " spring " etc..
After searching out the article for needing to recite, it can choose entire chapter and recite (as the entire chapter of selection classic poetry is carried on the backRead aloud) or paragraph is selected to recite (as certain paragraphs in selection text are recited).It is specific as shown in figure 12, it is a certain when selectingWhen article, can show each paragraph of article, and show before paragraph choice box 1201 in order to select, and then teacherIt can choose part paragraph therein and recite operation to arrange.
As shown in figure 13, after teacher selects the content for needing to recite, " publication " control 1301 can be clicked to issueOperation is recited, and then student can receive in the terminal that oneself is used and recite operation, and recite operation based on what is receivedRecite corresponding content.
As shown in figure 14, after student completes to recite operation and submit, terminal used in teacher can receiveThe raw operation submitted, and evaluation information can be filled in corresponding position (region 1401 as shown in Figure 14), the evaluationInformation can be text information, be also possible to voice messaging.
In addition, as shown in figure 15, teacher can also check student to the situation that is performed integrally for reciting operation, pole by terminalThe earth improves the experience of teacher's students ' study situation.
The function that terminal used in student is realized is as follows:
As shown in figure 16, after teacher arranges operation, student can see the operation of teacher's arrangement at the terminal, and canTo recite the content of teacher's arrangement by clicking " starting to recite " control 1601.
As shown in figure 17, student is during reciting, the progress that terminal meeting real-time display student recites, and can markStudent recites the place of error out, and as shown in Figure 17 1701 and 1702 recite the place of error for student, passes through this sideFormula can play suggesting effect, to cause the attention of student.Meanwhile student " can carry on the back " control 1703 again by click come againIt recites；" prompt " control 1704 can also be clicked to obtain prompt, can show and connect after such as click " prompt " control 1704Get off several words etc. for needing to recite.In addition, student can also click " exit and recite " control 1705 to terminate to recite.
As shown in figure 18, after student recites completion, terminal can generate and show student to the completion report for reciting operationIt accuses, such as shows and recite the quantity of error, prompt number, recite the used time and marking situation.Meanwhile student can pass through click" submission " control 1801 submits operation, and " can also carry on the back " control 1802 again by click to recite again.
In an embodiment of the present invention, terminal used in terminal used in teacher and student can by server intoThe operation of reciting that teacher is arranged in row interaction, i.e. terminal used in teacher is sent to used in student eventually by serverEnd；After completing to recite operation and submit, terminal used in student can be sent operation performance by server studentTo terminal used in teacher；Teacher is receiving the case where student recites, and after being evaluated, terminal used in teacherEvaluation information can be sent to terminal used in student by server, in order to which student checks.Meanwhile used in studentTerminal collect student recite voice after, can will recite voice be sent to server carry out speech recognition, such energyThe high treatment capacity by server is reached to improve audio identification efficiency.
Based on above-mentioned introduction, in one embodiment of the invention, the system architecture of server is as shown in figure 19, usesThree-tier architecture, from top to bottom respectively access layer 1901, logical layer (or field layer) 1902 and accumulation layer 1903.Such areaWith different levels purpose is for " high cohesion lower coupling ".Each layer of main function difference is as follows:
Access layer 1901: mainly to be external such as APP (Application, application program), WEB (i.e. World WideWeb, global wide area network), PC (personal computer, personal computer) end etc. showing interfaces form provide API(Application Programming Interface, application programming interface) access service, API can be HTTP(Hyper Text Transfer Protocol, hypertext transfer protocol) mode, is also possible to TCP (TransmissionControl Protocol, transmission control protocol) long connection type.
Logical layer 1902: mainly the data service logic and affairs such as being handled, for example carries out text typing, textSearch, job management, speech recognition etc..
Accumulation layer 1903: also referred to as persistent layer, function are mainly responsible for the access of database, including relevant databaseWith non-relational database etc..
Meanwhile in order to preferably cope with the request of the high concurrent for the mass users that may occur in the future, server system can be withUsing micro services framework, micro services are a kind of framework styles, and general thought is that a large-scale complex software is divided into oneA or multiple micro services compositions, and each micro services can be disposed independently, i.e., be loose coupling, Mei Gewei between each micro servicesService, which only focuses on, to be completed a task and can complete the task well.In all cases, each Charge-de-Mission oneSmall professional ability.Micro services framework also can solve team's co-development while solving the problem of high load, itComplicated project is decomposed into many independent small services, each team can only focus on the service oneself being responsible for, thus moreGood collaboration.
Based on micro services framework, the functions such as text typing, text search, job management, speech recognition for stating in realizationWhen, it can be realized by several different module/services.Wherein, modules/service effect difference is as follows:
Text typing: mainly text data are saved in database by typing or crawler mode；
Text search: mainly when teacher's arrangement recites operation, text function of search is provided；
Job management: the functions such as preservation, modification, the list displaying of operation are provided；
Speech recognition: efficient, high quality recording data is provided and is identified as the functions such as text.
In one embodiment of the invention, the system of terminal (terminal that the terminal and student used including teacher uses)Framework is as shown in figure 20, also uses three-tier architecture, from top to bottom respectively presentation layer 2001, field layer (or logical layer)2002, data Layer 2003.Each layer of main function difference is as follows:
Presentation layer 2001: major responsibility is to show UI (User Interface, user interface), animation etc., does not handle and removesAny logic except UI logic has used MVP (Model-View-Presenter) mode in this embodiment, certainly at thisAlso MVC (Model View Controller), MVVM (Model-View- can be used in the other embodiments of inventionViewModel) etc..
Field layer 2002, major responsibility is processing business logic.In some cases, logical layer needs directly and UI is interactive,If being introduced directly into UI interrelated logic, it will become not enough purely, so Event Bus or similar incidents can be introduced at this timePub/sub mechanism decouples.
Data Layer 2003, major responsibility are external offer data source and data storage.Data source is for outsideIt is bright, outside do not need to be concerned about it be from memory, SD card (Secure Digital Memory Card, safe digital card) orThe data that server is taken.For example, when obtaining a user by ID, if this user is not present in the buffer, thatSD card caching can be selected as data source, if SD card caching is also not present, data can be obtained by server interface, andIt is stored in local cache.
In one embodiment of the invention, the process of speech recognition is completed in the cooperation of terminal and server used in studentIt is specific as shown in figure 21, include the following steps:
Step S2101, terminal used in student start to record.
Step S2102, sub thread work thread poll read recording data, and by PCM (Pulse CodeModulation, pulse code modulation) recording data of format is converted into SILK format, then it is stored in local.
In one embodiment of the invention, in order to improve phonetic recognization rate, recording data can be carried out after recordingOptimization processing, such as carry out gain, denoising processing.
Step S2103, will be in recording data deposit caching.
Step S2104, another sub thread work thread read out recording data from caching, then to recordSound data such as are compressed, are encrypted at the encapsulation packaging operation, and the recording data after encapsulation is then sent to clothes by TCP long connectionIt is engaged on device (i.e. speech recognition backstage).
Speech recognition result is notified terminal by push by step S2105, server.
In one embodiment of the invention, in order to support the identification of more character sets multiple, user can also dynamically add fromDefine character library, rarely used word etc..Server will be when that will recite voice and be converted to content of text, the method that can use Model Matching,The method that neural network can also be used.
Step S2106, a sub thread work thread in terminal unpack data after receiving push notice,The text of speech recognition is obtained after unpacking, reconvert finally acquires the text and phonetic of identification at phonetic.
In one embodiment of the invention, terminal used in student the text and phonetic for getting speech recognition itMatching process afterwards is as shown in figure 22, includes the following steps:
Step S2201 obtains speech recognition text.
Step S2202, converts text to phonetic.
Step S2203, judges whether the phonetic (being also possible to speech recognition text) being converted to matches with model answer,It is recited correctly if so, determining；Otherwise, step S2204 is executed.
Step S2204, judge the phonetic (being also possible to speech recognition text) being converted to and other approximate sounds whetherMatch, is recited correctly if so, determining；Otherwise, it determines reciting mistake.
The technical solution of the above embodiment of the present invention can allow teacher, and choice arrangement specifically recites content on line, thenIt is recited in oneself or the mobile phone of parent by student, and then by speech recognition technology, it is automatic that student's inspection is helped to reciteWhether content is correct and provides prompt, and auxiliary is completed to recite, and can see achievement that this is recited after student completes to recite simultaneouslyIt submits, reciting achievement and can evaluating for student can be seen in teacher after submission.In this way, child can be helped moreOperation is recited in good completion, alleviates the burden of parent, while providing student's statistics feedback for reciting situation to teacher in time, fromAnd it greatly improves student and completes to recite the overall experience of operation.
The technical solution of the embodiment of the present invention can be applied in instant message applications, for example be added in QQ or wechatThe function of stating, and then academics and students realize the arrangement and completion for reciting operation in which can be convenient using QQ or wechat, greatlyImprove user experience.
The device of the invention embodiment introduced below can be used for executing the task of reciting in the above embodiment of the present inventionProcessing method.For undisclosed details in apparatus of the present invention embodiment, the above-mentioned processing for reciting task of the present invention is please referred toThe embodiment of method.
Figure 23 diagrammatically illustrates the block diagram of the processing unit according to an embodiment of the invention for reciting task, at thisReason device can be set in server.
Referring to shown in Figure 23, the processing unit 230 according to an embodiment of the invention for reciting task, comprising: obtainUnit 231, transmission unit 232, receiving unit 233, converting unit 234.
Wherein, what acquiring unit 231 was used to obtain first terminal publication recites task for specified content；Transmission unit232 for being sent to second terminal for the task of reciting；Receiving unit 233 is for receiving the collected back of the second terminalRead aloud voice；Converting unit 234 is used to the voice of reciting being converted to content of text；Wherein, the transmission unit 232 is also used toThe content of text is sent to the second terminal so that the second terminal according to the content of text and it is described it is specified inHold the executive condition that task is recited described in determining.
Figure 24 diagrammatically illustrates the block diagram of the processing unit for reciting task according to another embodiment of the invention, shouldProcessing unit can be set in server.
Referring to shown in Figure 24, the processing unit 240 for reciting task according to another embodiment of the invention, in Figure 23 instituteOn the basis of the processing unit for reciting task shown, further includes: statistic unit 235.
Wherein, receiving unit 233 is also used to receive the executive condition for reciting task of the second terminal feedback；SystemMeter unit 235 is used to count the executive condition for reciting task that at least one described second terminal is sent, to obtain at leastThe user of one second terminal is to the overall implementing result for reciting task；The transmission unit 232 is also used to instituteIt states overall implementing result and is sent to the first terminal, so that the first terminal shows the overall implementing result.
In some embodiments of the invention, aforementioned schemes are based on, the receiving unit 233 is also used to receive described secondThe executive condition for reciting task of terminal feedback；The transmission unit 232 is also used to the execution feelings for reciting taskCondition is sent to the first terminal, so as to recite the executive condition of task described in first terminal displaying.In this embodiment,Receiving unit 233 and transmission unit 232, which can be connected directly, (is omitted receiving unit 233 and transmission unit in Figure 23 and Figure 24Connecting line between 232).
In some embodiments of the invention, aforementioned schemes are based on, the receiving unit 233 is also used to receive described firstThe evaluation information for the executive condition that terminal is sent；The transmission unit 232 is also used to send the evaluation informationTo the second terminal, so that the second terminal shows the evaluation information.In this embodiment, receiving unit 233 and hairIt send unit 232 that can be connected directly and (connection between receiving unit 233 and transmission unit 232 is omitted in Figure 23 and Figure 24Line).
In one embodiment of the invention, as shown in figure 25, acquiring unit 231 shown in Figure 23 and Figure 24 includes:Instruction receiving unit 2311, determination unit 2312 and generation unit 2313.
Wherein, instruction receiving unit 2311 is used to receive search and selection instruction that the first terminal is sent；It determines singleMember 2312 is for determining that the needs of user's selection of the first terminal are recited specified interior according to described search and selection instructionHold；Generation unit 2313 is used to recite task described in generation according to the specified content.
Figure 26 diagrammatically illustrates the block diagram of the processing unit for reciting task according to still another embodiment of the invention, shouldProcessing unit can be set in terminal.
Referring to shown in Figure 26, the processing unit 260 for reciting task according to still another embodiment of the invention, comprising: backRead aloud task receiving unit 261, acquisition unit 262, transmission unit 263, content of text receiving unit 264, processing unit 265.
Wherein, it recites task receiving unit 261 and recites task for specified content for receive server transmission,In, the task of reciting is that the server is distributed to by first terminal；Acquisition unit 262 recites voice for acquiring；HairSend unit 263 for when the acquisition unit 262 collects and recites voice, the voice of reciting to be sent to the serviceDevice；Content of text receiving unit 264 is used to receive that the server to return by the text reciting voice and being converted toThis content；Processing unit 265 recites the execution feelings of task described in being used to determine according to the content of text and the specified contentCondition.
In Figure 26, reciting can be directly electrically connected between task receiving unit 261 and acquisition unit 262, such as recited and appointedBusiness receiving unit 261 receive recite task when, triggering collection unit 262 acquisition recite voice；Certainly, task reception is recitedIt can also be directly electrically connected by not between unit 261 and acquisition unit 262.
In one embodiment of the invention, as shown in figure 27, processing unit 265 may include: 2651 He of matching unitDetermination unit 2652.
Wherein, matching unit 2651 described recites voice for that will correspond in the content of text and the specified contentObject content matched；Determination unit 2652 is used to determine when the content of text and the object content matchThe voice of reciting is errorless, and for reciting voice described in determination when the content of text and the object content mismatchIt is wrong.
In another embodiment of the present invention, as shown in figure 28, processing unit 265 is on the basis of Figure 27, can be withIt include: acquiring unit 2653.
Wherein, there are the associated texts of incidence relation with the content of text for obtaining for acquiring unit 2653；DescribedIt is also used to unit 2651 when the content of text and the object content mismatch, by the associated text and the targetContent is matched；The determination unit 2652 is also used to: when the associated text and the object content match, being determinedThe voice of reciting is errorless, and for reciting voice described in determination when the associated text and the object content mismatchIt is wrong.
In some embodiments of the invention, aforementioned schemes are based on, the acquiring unit 2653 is used for: in the textWhen appearance is Chinese, the Chinese is converted into phonetic；Obtain the other Chinese to match with the phonetic, and/or acquisition and instituteThe Chinese that the approximate phonetic of phonetic matches is stated, and the Chinese that will acquire is as the associated text.
In some embodiments of the invention, aforementioned schemes are based on, the processing unit 260 of task is recited shown in Figure 26 alsoIt may include: display unit, correspond to the object content for reciting voice in the specified content for showing；Label is singleMember, for marking the content of text and the unmatched place of the object content in the object content.
In some embodiments of the invention, aforementioned schemes are based on, the processing unit 260 of task is recited shown in Figure 26 alsoIt may include: generation unit, for reciting the executive condition of task according to, that task is recited described in generation executes report；Display unit described executes report for showing.
It should be noted that although being referred to several modules or list for acting the equipment executed in the above detailed descriptionMember, but this division is not enforceable.In fact, embodiment according to the present invention, it is above-described two or moreModule or the feature and function of unit can embody in a module or unit.Conversely, an above-described mouldThe feature and function of block or unit can be to be embodied by multiple modules or unit with further division.
Through the above description of the embodiments, those skilled in the art is it can be readily appreciated that example described herein is implementedMode can also be realized by software realization in such a way that software is in conjunction with necessary hardware.Therefore, according to the present inventionThe technical solution of embodiment can be embodied in the form of software products, which can store non-volatile at oneProperty storage medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) in or network on, including some instructions are so that a calculatingEquipment (can be personal computer, server, touch control terminal or network equipment etc.) executes embodiment according to the present inventionMethod.
Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to of the invention itsIts embodiment.This application is intended to cover any variations, uses, or adaptations of the invention, these modifications, purposes orPerson's adaptive change follows general principle of the invention and including the undocumented common knowledge in the art of the present inventionOr conventional techniques.The description and examples are only to be considered as illustrative, and true scope and spirit of the invention are by followingClaim is pointed out.
It should be understood that the present invention is not limited to the precise structure already described above and shown in the accompanying drawings, andAnd various modifications and changes may be made without departing from the scope thereof.The scope of the present invention is limited only by the attached claims.