Summary of the invention
The purpose of the present invention is to provide a kind of power performance test method of electric car, solve personal in the prior artFor computer in conference scenario activity, the function that may be implemented is very single, and only simply text is projected, the space accounted forAlso bigger, it is also not beautiful enough.It is difficult to meet current meeting personnel to conference scenario screen control and session information managementDemand, cause many many and diverse work or can only by it is traditional it is artificial complete, both waste of manpower or inefficent askedTopic.
Technical solution of the present invention is accomplished by
The present invention provides a kind of control method of conference scenario, comprising:
The audio-frequency information and image information for receiving user match the vocal print prestored according to the audio-frequency information, from the figureAs extracting face information in information, the face characteristic prestored, the matching knot according to the vocal print are matched according to the face informationThe matching result of fruit and the face characteristic confirms the identity information of the user；
The audio-frequency information for continuing to the user identifies the control command in the audio-frequency information, according to the controlOrder and the identity information control conference scenario screen；
The image information of the user is continued to, and extracts the first action command from described image information, according to instituteIt states the first action command and the identity information controls the conference scenario screen；
The limbs information for receiving user, according to second action command of limbs information extraction, according to second movementInstruction and the identity information control the conference scenario screen.
In power performance test method of the present invention, the audio-frequency information and image information for receiving user, according toThe vocal print prestored is matched according to the audio-frequency information, face information is extracted from described image information, according to the face informationWith the face characteristic prestored, confirm the user's according to the matching result of the vocal print and the matching result of the face characteristicIdentity information, comprising:
The registration information of user is received with the vocal print and face characteristic of user described in typing, the registration information includes describedThe identity information of user；
The audio-frequency information that the user is received by microphone judges whether it is the audio of the user according to the vocal printInformation, if so, voice print matching success, if it is not, then voice print matching fails；
The image information that the user is received by camera extracts face information from described image information, according to instituteThe face information that face characteristic judges whether it is the user is stated, if so, face successful match, if it is not, then face matching is lostIt loses；
If the voice print matching success or face successful match, confirm the identity information of the user so that active userIt logins successfully, and assigns active user's control authority.
In power performance test method of the present invention, the audio-frequency information for continuing to the user, identificationControl command in the audio-frequency information controls conference scenario screen according to the control command and the identity information, comprising:
The audio-frequency information of the user is continued to by microphone；
It stores the audio-frequency information and is converted into text information；
Extract the control instruction in the text information；
According to the identity information judge the user whether have control conference scenario screen permission, if so, then according toConference scenario screen is controlled according to the control command.
In power performance test method of the present invention, the image information for continuing to the user, and fromThe first action command is extracted in described image information, controls the meeting according to first action command and the identity informationScene screen, comprising:
The image information of the user is continued to by camera；
The first action command is extracted from described image information；
According to the identity information judge the user whether have control conference scenario screen permission, if so, then according toConference scenario screen is controlled according to first action command.
In power performance test method of the present invention, the limbs information for receiving user, according to the limbsThe second action command of information extraction controls the conference scenario screen according to second action command and the identity information,Include:
User's limbs information is acquired by limbs sensor；
According to second action command of limbs acquisition of information；
According to the identity information judge the user whether have control conference scenario screen permission, if so, then according toConference scenario screen is controlled according to second action command.
In power performance test method of the present invention, further includes:
The received audio-frequency information of translation.
In power performance test method of the present invention, audio-frequency information received by the translation, comprising:
Original text region and translational domain are set in the conference scenario screen；
Received audio-frequency information is shown in the original text region；
The translation translating the audio-frequency information and obtaining is shown in the translational domain.
In power performance test method of the present invention, further includes:
Type according to document carries out file management.
In power performance test method of the present invention, the type according to document carries out file management, comprising:
Type according to document stores corresponding document；
Type according to document generates one or more and selects frame；
One of them is selected in frame to obtain all documents of selected type from selecting described in one or more；
One of selection from all documents；
Selected document is shown in the conference scenario screen.
In power performance test method of the present invention, further includes:
The received audio-frequency information of storage, and the audio-frequency information is stored according to vocal print.
Therefore, the invention has the advantages that passing through audio and acting the control to conference screen, and motion capture usesImage procossing and limbs sense two ways, realize the diversification of session control function.
Specific embodiment
For a clearer understanding of the technical characteristics, objects and effects of the present invention, will to compare attached drawing below detailedIllustrate a specific embodiment of the invention.It should be appreciated that following explanation is only being specifically described for the embodiment of the present invention, it should not be with thisIt limits the scope of the invention.
Referring to Fig. 1, Fig. 1 is a kind of flow chart of the control method for conference scenario that one embodiment of the invention provides, includingStep S1-S4:
S1, the audio-frequency information and image information for receiving user match the vocal print that prestores according to the audio-frequency information, from describedFace information is extracted in image information, and the face characteristic prestored, the matching according to the vocal print are matched according to the face informationAs a result and the matching result of the face characteristic confirms the identity information of the user；Step S1 includes step S11-S14:
S11, receive user registration information with the vocal print and face characteristic of user described in typing, the registration information includesThe identity information of the user；I.e. user needs in advance the vocal print and face characteristic of registration and typing oneself in systems, then underWhen secondary login the user could be matched to by vocal print and face characteristic.
S12, the audio-frequency information that the user is received by microphone judge whether it is the user's according to the vocal printAudio-frequency information, if so, voice print matching success, if it is not, then voice print matching fails.
S13, the image information that the user is received by camera, extract face information from described image information, according toThe face information of the user is judged whether it is according to the face characteristic, if so, face successful match, if it is not, then faceWith failure.
If the success of S14, the voice print matching or face successful match, the identity information of the user is confirmed so that currentUser logins successfully, and assigns active user's control authority.Control authority is also the generation in registration, by i.e. settable from the backgroundThe control authority of different user.
S2, the audio-frequency information for continuing to the user, identify the control command in the audio-frequency information, according to the controlSystem order and the identity information control conference scenario screen；Step S2 includes step S21-S24:
S21, the audio-frequency information that the user is continued to by microphone；Preferably, in order to ensure the standard of simultaneous interpretationTrue property, terminal device use dynamical microphone array and are used for front audio acquisition and noise processed, in addition cloud (afterEnd) powerful processing capacity and outstanding speech recognition algorithm, to guarantee the quick, real-time, accurate of final translation result.I.e.The video conference may be coupled to rear end.
S22, the storage audio-frequency information are simultaneously converted into text information；Such as: it records to user, supports TTS,Conference content can directly be changed into text, save many and diverse minutes manual sorting work.
Control instruction in S23, the extraction text information；Such as: during recording, user can pass through voice controlConference scenario screen processed.Control instruction include to the left, to the right, upwards, move down etc..
S24, judge whether the user has the permission of control conference scenario screen according to the identity information, if so,Then conference scenario screen is controlled according to the control command.Judge whether user can pass through voice control meeting according to permissionScene screen controls conference scenario screen without permission, but also can if lack of competence or the user of vocal print is not stored in advanceCollected voice messaging saves.Therefore the step prevents the interference of other voice messagings by verifying the permission of user.
S3, the image information for continuing to the user, and the first action command, foundation are extracted from described image informationFirst action command and the identity information control the conference scenario screen；Step S3 includes step S31-S33:
S31, the image information that the user is continued to by camera；Preferably, system supports two high-definition camerasHead, system identify user action, such as hand motion by high-definition camera, when user's hand makes specific movementAfterwards, camera captures this movement, and image is sent to primary processor, identifies containing for this movement by image recognition algorithmJustice, and specific instruction is generated, finally make specific feedback.
S32, the first action command is extracted from described image information；Such as: by high-definition camera, user can be doneSome movements out, such as arm stroke to the left, to the right stroke, upward stroke, downward stroke, may be implemented picture to the left, to the right,Upwards, move down etc..
S33, judge whether the user has the permission of control conference scenario screen according to the identity information, if so,Then conference scenario screen is controlled according to first action command.
S4, the limbs information for receiving user, it is dynamic according to described second according to second action command of limbs information extractionMake instruction and the identity information controls the conference scenario screen.Step S4 includes step S41-S43:
S41, user's limbs information is acquired by limbs sensor；Such as: this method support is known by nine axle sensorsThe movement of other user.
S42, according to second action command of limbs acquisition of information；Such as: user holds Digiplex and (includes nine axisSensor), when user makes various limb actions, sensor will recognize corresponding limb action, and be parsed into correspondingInstruction code is wirelessly transferred to host by certain communication protocol, and primary processor finally makes specific feedback.FromAnd it realizes gesture interaction and manipulates.
S43, judge whether the user has the permission of control conference scenario screen according to the identity information, if so,Then conference scenario screen is controlled according to second action command.
By recognition of face and Application on Voiceprint Recognition, intelligent personal management is may be implemented, accurately in two kinds of personnel identity validation testingsThe identity information for identifying current speaker person, may be implemented language automatically switch, speech automatic arranging, filing etc., can be withNeed to expand more utility functions according to meeting.
Referring to fig. 2, Fig. 2 is the schematic diagram for the main interface that one embodiment of the invention provides；Main interface includes five big contents, farCheng Huiyi, translation, file management, recording turn text and setting.By corresponding voice control or action control or click controlSome function space of a whole page can be entered.
Preferably, further include step S5 in the power performance test method:
Audio-frequency information received by S5, translation.Step S5 includes step S51-S53:
S51, original text region and translational domain are set in the conference scenario screen；It is the present invention one referring to Fig. 3, Fig. 3The schematic diagram for the translation interface that embodiment provides；For example, " translation " icon clicked in main interface will enter translation interface, translationInterface is using double screen with aobvious interface.
S52, received audio-frequency information is shown in the original text region；Such as: upper half screen display Chinese.
S53, the translation translating the audio-frequency information and obtaining is shown in the translational domain.Such as:, lower half screen is shownEnglish, specific language can be selected in setting.If it is two separate display, will one piece of screen display Chinese wherein, in addition oneBlock screen display English, specific language can equally be selected in setting.
Preferably, which further includes S6:
Type according to document carries out file management.Step S6 includes step S61-S65:
S61, the corresponding document of type storage according to document；Such as: system can automatically set internal and peripheral hardware storageVarious files in standby (USB flash disk, mobile hard disk, T card etc.) are classified by file format, and respective file will be entered by clicking corresponding iconThen the browser interface of format selectes the particular content for needing the file browsed that can show this document on the screen.
S62, it generates one or more according to the type of document and selects frame；Referring to fig. 4, Fig. 4 is what one embodiment of the invention providedThe schematic diagram of file management interface.Such as: " file management " icon for clicking main interface will enter file management interface.Files classesType includes: PPT/WORD/pdf/excel/ photo etc..
S63, from selecting in frame one of them all document to obtain selected type of selection described in one or more；Such as: choosingIt selects PPT and then shows PPT file all in current device.
S64, one of selection from all documents；Such as: one of selection from all PPT files.
S65, selected document is shown in the conference scenario screen.Such as: selected PPT file is projected toIn conference scenario screen, in this way, meeting can be carried out to PPT.
Preferably, which further includes S7:
Audio-frequency information received by S7, storage, and the audio-frequency information is stored according to vocal print.I.e. system will be carried outIntelligent personal management identifies it is who is speaking, can intelligently be switched to relational language, while being able to achieve intelligence and recording everyoneSpeech content, carry out intelligent sorting and file and simultaneously save, such as: the user that vocal print is stored in advance has corresponding ID, does not storeThe user of vocal print can recorde as user A, user B ... and be converted to text in this way, can record to whole process and carry out TTS, storeContent will not ignore any one received sound.
The present invention can replace traditional PC, while various voices and moving control function completely, realize quickly,In real time, it accurately controls, record and simultaneous interpretation, business meetings are participated in without translator；By TTS function, conference contentText can be directly changed into, the work of many and diverse manual sorting minutes is saved；Equipment operation, intelligence easy to control usePerson can manipulate conference facility by interactive modes such as touch, voice, gesture, Digiplexs.The recording of terminal device whole process,Recording function records conference content, convenient to consult from now on.
In conclusion although the present invention has been disclosed above in the preferred embodiment, but above preferred embodiment is not to limitThe system present invention, those skilled in the art can make various changes and profit without departing from the spirit and scope of the present inventionDecorations, therefore protection scope of the present invention subjects to the scope of the claims.