CN109087643A

CN109087643A - Sound control method, device and electronic equipment

Info

Publication number: CN109087643A
Application number: CN201811138659.8A
Authority: CN
Inventors: 杨琳; 徐培来; 汪俊杰
Original assignee: Lenovo Beijing Ltd
Current assignee: Lenovo Beijing Ltd
Priority date: 2018-09-28
Filing date: 2018-09-28
Publication date: 2018-12-25

Abstract

The present invention provides a kind of sound control methods, device and electronic equipment, when the first electronic equipment is communicated with the second electronic equipment, after second electronic equipment user sends the first voice messaging (such as tell by telephone the first electronic equipment user operating procedure or demand) to the first electronic equipment, first electronic equipment exports first voice messaging, while so that its user hears second electronic equipment user's dialog context, first electronic equipment also can carry out semantic analysis to the first voice messaging, obtain the first operational order for controlling the first electronic equipment, so that the first electronic equipment can be directly based upon the voice content of communication counterpart, directly execute corresponding operation, do not need the first electronic equipment user terminate with after counterparting communications, voice control is initiated to the first electronic equipment again according to memory, i.e. in voice communication While realize electronic equipment voice control, improve the first electronic equipment voice control flexibility and diversity.

Description

Sound control method, device and electronic equipment

Technical field

Present application relates generally to fields of communication technology, more particularly to a kind of sound control method, device and electricity Sub- equipment.

Background technique

In recent years, with the development of computer communication technology, such as the function of mobile phone, computer, home equipment electronic equipment More and more, also more and more intelligent, especially artificial intelligence (Artificial Intelligence, AI) is in electronic equipment In application be also able to respond some simple phonetic control commands so that electronic equipment can not only receive manual operation, mention High electronic device convenience.

In practical applications, often limited because grasping knowledge for this types of populations such as such as children, the elderly, lead to this A little users do not know how using electronic equipment, it usually needs make a phone call to seek help to other people, tell by telephone the user such as by other people What operation electronic equipment, to meet the user demand.

However, the voice control mode due to electronic equipment is single, the phonetic control command that user initiates only is received, this The operating procedure for just needing user first to remember that other people explain in the phone after hanging up the telephone, is initiated according to remembering to electronic equipment Corresponding phonetic control command will be unable to the operational requirements for meeting user to electronic equipment once user forgets or remember error.

Summary of the invention

In view of this, the present invention provides a kind of sound control method, device and electronic equipment, it is logical in both sides' electronic equipment During letter, both sides can voice communication while, additionally it is possible to voice control counterpart device, communication counterpart can not remember this user Voice control content, directly can execute this Client-initiated phonetic control command using its voice assistant, meet electronics and set Standby demand for control.

To achieve the goals above, this application provides following technical schemes:

The embodiment of the invention provides a kind of sound control methods, are applied to the first electronic equipment, which comprises

When communicating with the second electronic equipment, the first voice messaging of the second electronic equipment user is obtained；

First voice messaging is exported, and semantic analysis is carried out to first voice messaging, the first operation is obtained and refers to It enables；

Execute first operational order.

Optionally, when being communicated with the second electronic equipment, the method also includes:

Acquire the second voice messaging of the first electronic equipment user；

Second voice messaging is sent to the second electronic equipment, so that second electronic equipment output described second Voice messaging, and execute the second operational order that second voice messaging includes；

The voice service for waking up first electronic equipment carries out semantic analysis to second voice messaging, obtains needle To the third operational order of first electronic equipment, the third operational order is executed.

It is optionally, described to execute first operational order, comprising:

Triggering enters working condition with the associated target application of the first operational order, and is executed by the target application First operational order；

If receiving the response message of first operational order, the response message is fed back into second electronics and is set It is standby.

Optionally, the method also includes:

Voice control prompt information is exported, the voice control prompt information is for prompting first electronic equipment to use Person is confirmed whether to allow first electronic equipment by the second electronic equipment voice control；

It receives the first electronic equipment user to instruct the confirmation of the voice control prompt information, described in wake-up The voice service of first electronic equipment, it is described to first voice messaging progress semantic analysis to execute, obtain the first operation Instruct step.

Optionally, the method also includes:

It determines the first operational order described in successful execution, or receives the response message of the second electronic equipment feedback, institute Response message is stated for characterizing the second operational order of the second electronic equipment successful execution；

Terminate the communication with second electronic equipment, or terminates the voice service of first electronic equipment.

The embodiment of the invention also provides a kind of phonetic controllers, are applied to the first electronic equipment, and described device includes:

Voice messaging obtains module, for the second electronic equipment communication process, the second electronic equipment of acquisition to be used The first voice messaging of person；

Voice messaging output module, for exporting first voice messaging；

Voice messaging analysis module obtains the first operational order for carrying out semantic analysis to first voice messaging；

Operational order execution module, for executing first operational order.

Optionally, described device further include:

Voice messaging acquisition module, for acquiring the second voice messaging of the first electronic equipment user；

Transmission of speech information module, for second voice messaging to be sent to the second electronic equipment, so that described Two electronic equipments export second voice messaging, and execute the second operational order that second voice messaging includes；

Voice service wake-up module believes second voice for waking up the voice service of first electronic equipment Breath carries out semantic analysis, obtains the third operational order for first electronic equipment, executes the third operational order.

Optionally, the operational order execution module includes:

Applications trigger and running unit enter work shape with the associated target application of the first operational order for triggering State, and first operational order is executed by the target application；

Response message feedback unit believes the response if the response message for receiving first operational order Breath feeds back to second electronic equipment.

Optionally, described device further include:

Cue module, for exporting voice control prompt information, the voice control prompt information is for prompting described the One electronic equipment user is confirmed whether to allow first electronic equipment by the second electronic equipment voice control；

Voice service wake-up module prompts to believe for receiving the first electronic equipment user to the voice control The confirmation of breath instructs, and the voice service of first electronic equipment is waken up, to trigger the voice messaging analysis module to described First voice messaging carries out semantic analysis, obtains the first operational order.

The embodiment of the invention also provides a kind of electronic equipment, the electronic equipment includes:

Communication module；Display；

Memory, for storing the program for realizing sound control method as described above；

Processor, for loading and executing the program of the memory storage, described program is used for:

Execute first operational order.

It can be seen that compared with prior art, this application provides a kind of sound control method, device and electronic equipment, When the first electronic equipment is communicated with the second electronic equipment, the second electronic equipment user sends the first language to the first electronic equipment Message cease (such as tell by telephone the first electronic equipment user operating procedure or demand) after, the first electronic equipment export this first Voice messaging, while so that its user hears second electronic equipment user's dialog context, which also can Semantic analysis is carried out to the first voice messaging, the first operational order for controlling the first electronic equipment is obtained, so that first Electronic equipment can be directly based upon the voice content of communication counterpart, directly execution corresponding operation, not need the first electronic equipment User terminates to initiate voice control to the first electronic equipment again according to memory, i.e., in the same of voice communication with after counterparting communications The voice control of Shi Shixian electronic equipment improves the first electronic equipment voice control flexibility and diversity.

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 The embodiment of invention for those of ordinary skill in the art without creative efforts, can also basis The attached drawing of offer obtains other attached drawings.

Fig. 1 is a kind of flow diagram of sound control method provided in an embodiment of the present invention；

Fig. 2 a is a kind of speech control system structural schematic diagram for realizing sound control method provided in an embodiment of the present invention；

Fig. 2 b is another speech control system structural representation for realizing sound control method provided in an embodiment of the present invention Figure；

Fig. 3 is the flow diagram of another sound control method provided in an embodiment of the present invention；

Fig. 4 is a kind of schematic diagram of a scenario of sound control method provided in an embodiment of the present invention；

Fig. 5 is the flow diagram of another sound control method provided in an embodiment of the present invention；

Fig. 6 is the flow diagram of another sound control method provided in an embodiment of the present invention；

Fig. 7 is the flow diagram of another sound control method provided in an embodiment of the present invention；

Fig. 8 is a kind of signaling process schematic diagram of sound control method provided in an embodiment of the present invention；

Fig. 9 is a kind of scene flow diagram of sound control method provided in an embodiment of the present invention；

A kind of Figure 10 structural schematic diagram of phonetic controller provided in an embodiment of the present invention；

The structural schematic diagram of Figure 11 another phonetic controller provided in an embodiment of the present invention；

The structural schematic diagram of Figure 12 another phonetic controller provided in an embodiment of the present invention；

The hardware structural diagram of Figure 13 a kind of electronic equipment provided in an embodiment of the present invention.

Specific embodiment

The inventors found that: for being able to use the electricity of voice assistant in the market with speech identifying function Sub- equipment, such as current most smart phone, voice assistant have a single function, and can only often identify electronic equipment user The phonetic control command of sending.In order to improve the problem, the ability of voice assistant is improved, the present inventor proposes to utilize AI Speech recognition and natural language processing function in (Artificial Intelligence, artificial intelligence) technology, to extend electricity Sub- equipment voice assistant can, make it that can not only respond the phonetic control command of local user, additionally it is possible to response call pair The phonetic control command of Fang Faqi controls local use by the voice assistant of partner user's control local user's electronic equipment Family electronic equipment executes various operations, meets actual demand, improves electronic equipment control diversity and flexibility, solves this Ground user is ignorant of the problems such as how operating its electronic equipment,

In order to make the foregoing objectives, features and advantages of the present invention clearer and more comprehensible, implement below in conjunction with the present invention Attached drawing in example, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment Only a part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, the common skill in this field Art personnel every other embodiment obtained without making creative work belongs to the model that the present invention protects It encloses.

It referring to Fig.1, is a kind of flow diagram of sound control method provided in an embodiment of the present invention, this method can answer It is able to carry out the user equipment of interactive voice for the first electronic equipment, such as mobile phone, laptop, tablet computer, and should First electronic equipment can install voice assistant (i.e. a kind of application program), identify the control of Client-initiated voice by voice assistant System instruction, the first electronic equipment of control execute corresponding operation, and the present embodiment is not detailed the working principle of the voice assistant.

As shown in Figure 1, the sound control method provided in this embodiment may include but be not limited to following steps:

Step S11 obtains the first voice of the second electronic equipment user with the second electronic equipment communication process Information；

It in the present embodiment, can be by the first electricity after the first electronic equipment receives the communication request of the second electronic equipment Sub- equipment user manual operation, receives the communication request, so that the first electronic equipment is communicated with the foundation of the second electronic equipment Connection, the first electronic equipment user and the second electronic equipment user can carry out voice friendship by the communication channel of foundation Mutually.

Alternatively, the present invention can also start voice assistant, user's selection or process in the call interface of the first electronic equipment Preset time automatically determines, if is handled and is sent a telegram here by the voice assistant, that is, the first electronic equipment is selected to enter voice service processing Mode, later, the communication request that the second electronic equipment of response is initiated.

It is to be appreciated that about when, how to establish logical between the first electronic equipment and the second electronic equipment Letter connection specifically can be with so that the two electronic equipments user is able to carry out the implementation method of voice communication without limitation Referring to the description of hereafter corresponding embodiment.

Wherein, the voice messaging for the second electronic equipment user that the present embodiment obtains can be denoted as the first voice messaging, First voice messaging can be the voice signal of the second electronic equipment user Yu first electronic equipment user's speech exchange, It may include the common exchange content for actualite, also may include that the second electronic equipment user instructs the first equipment to make How user completes the operational order of certain operation, second electronic equipment of the present invention to above-mentioned acquisition using the first electronic equipment The first speech information content of user is without limitation.

Step S12 exports first voice messaging, and carries out semantic analysis to first voice messaging, obtains the first behaviour It instructs；

In the present embodiment, after the first electronic equipment obtains the first voice messaging of the second electronic equipment user, in order to keep away Exempt to omit the phonetic control command that the second electronic equipment user initiates, it will usually carry out semantic point to first voice messaging Analysis, to obtain corresponding first operational order (i.e. voice messaging cover phonetic control command).The present invention is to the semantic analysis Concrete methods of realizing without limitation, can be using the voice in artificial intelligence (Artificial Intelligence, AI) technology Identification and natural language processing function are realized.

It optionally, may include knowing first with speech recognition technology about the semantic analysis process to the first voice messaging Not Chu the first voice messaging the information content, recycle natural language technology to the information content carry out semantic understanding, so as to evidence This provides the content to be replied, or the certain operations (such as transmission photo checks calendar, plays XX video) for needing to carry out, For the content of reply, it usually needs other side's output will be fed back to again after its synthetic speech signal, the present invention is related to above-mentioned The concrete methods of realizing of the operations such as speech recognition, semantic analysis, speech synthesis be not detailed, can be according to AI technology in intelligence Application principle in terms of interactive voice determines.

Semantic analysis is carried out by the first voice messaging to the second electronic equipment user, can accurately learn the second electricity Sub- equipment user wishes what operation the first electronic equipment executes, and will obtain corresponding first operational order, first operation Instruction is actually the phonetic control command that the second electronic equipment user initiates the first electronic equipment, and the present embodiment is to it The content for including is without limitation.

Optionally, the present embodiment executes first operational order directly in order to avoid the first electronic equipment, causes the first electricity The leakage of sub- equipment important information, or interfere to current scene, the present embodiment can execute the with the first electronic equipment One operational order straight line exports prompt information, to inform the first electronic equipment user, the second electronic equipment user control the One electronic equipment executes any operation, and decides whether to execute the first operational order accordingly.

Wherein, prompt information may include the first operational order or the operation indicating content performed by it, and include " really Recognize ", the printed words content such as " cancellation ", the voice control for whether responding the second electronic equipment user initiation for selection by the user refers to It enables.The present embodiment to the content of the prompt information without limitation.In conjunction with above description, the first electronic equipment receives communication counterpart The first voice messaging after, export first voice messaging so that the first electronic equipment user hears other side's voice content While, further the first voice messaging can also be analyzed using AI technology, to determine the second electronic equipment user The control of first electronic equipment is intended to.As it can be seen that carrying out voice in the first electronic equipment and the second electronic equipment communication process Also it can be realized the voice control to other side's electronic equipment while call, solve in traditional call scene, communicating pair is only It can be carried out voice communication, counterpart device can not be controlled by voice content and execute operation, and then be unable to satisfy actual scene demand The problem of.

Such as, it can use sound control method provided in this embodiment, during double-talk, field as shown in Figure 2 a Scape schematic diagram, user B can be by exporting to user A, " playing video C using your mobile phone " this voice messaging, user's A hand Machine A will play this voice messaging, while through semantic analysis, the operational order for playing video C can be obtained, so that mobile phone A It is able to respond the operational order and plays video C, in this way, when user A does not know how to search and play video C, user B can be During making a phone call with it, the voice messaging of content as above is exported, sends corresponding operation instruction to the mobile phone A of user A, It does not need to hold mobile phone A in person and be operated.

Step S13 executes the first operational order.

In the present embodiment practical application, the application scenarios schematic diagram of the method in conjunction with shown in Fig. 2 a and Fig. 2 b, by right The first voice messaging of second electronic equipment user is analyzed, and the first obtained operational order may include the first electricity of starting Certain application of sub- equipment, and control instruction (such as the second electronic equipment user voice control that the application exports specific information One electronic equipment starts music software, plays certain music), or the specific information of the application memory is searched, and feed back to the second electricity (such as second electronic equipment user the first electronic equipment of voice control searches some or class photo, and feeds back for the instruction of sub- equipment To the second electronic equipment), or configuration specific information can also include the instruction (such as the of the configuration information of the first electronic equipment of adjustment The setting of two electronic equipment user the first electronic equipments of voice control completion alarm clock), or downloading and the instruction applied according to certain, It can also include triggering certain control program, to realize instruction (such as second electronic equipment user's voice controlled other equipment The first electronic equipment is controlled, the control to the smart home device of the first electronic device association is realized, it is bright such as to reconcile indoor lamp Degree, control intelligent sound box play broadcast etc.) etc..

Therefore, the first electronic equipment executes the first operational order, can be the first electronic equipment and itself executes certain operation, only The first electronic equipment itself is acted on, can also be further realized to the other equipment with first electronic device association, for The latter, the first electronic equipment are equivalent to the control equipment that can control at least one other equipment, which receives The control signal arrived derives from the voice messaging of the second electronic equipment user, certainly, can also set from the first electronics Standby user's voice messaging, the present embodiment is mainly to the second electronic equipment user how in communication process, voice control the The scheme of one electronic equipment or associated other equipment is described.

Thus, the difference for the first operational order that the present embodiment obtains in the manner described above, the first electronic equipment execute First operational order, the operation of realization also can difference, can specifically be determined based on the Content of Communication of communicating pair, not office It is limited to content listed above.

Based on above-mentioned analysis, step S13 can specifically include but be not limited to following steps:

Triggering enters working condition with the associated target application of the first operational order, and executes described the by the target application One operational order；

Wherein, target application can be the application program in the installation of the first electronic equipment, such as pictures management application, audio-video Player, alarm clock, memorandum, calendar etc., specifically can be according to the second electronic equipment user to the language of the first electronic equipment Sound control system requires to determine.

It is not limited in the operation of the present embodiment description it is to be appreciated that the first electronic equipment executes the first operational order Hold, such as analysis above, can be determined according to specific communication speech content.

If receiving the response message of the first operational order, which is fed back into the second electronic equipment.

In the present embodiment, in conjunction with the analysis above to the first operational order content, the second electronic equipment user is to first The voice control of electronic equipment may include the setting content of the first electronic equipment, function, configuration, installation application or based on the Further control etc. of one electronic equipment to other equipment, can not be to the second electronic equipment feedback information for these, can also With feedback, successful response message is set；In addition, above-mentioned voice control is also possible that the photo etc. shot before transmission, it is this In the case of, need the first electronic equipment by the photo feedback found to the second electronic equipment.

Thus, the response message of the present embodiment the first operational order above may is that whether the first electronic equipment succeeds Execute the first operational order as a result, is also possible to the data etc. to match with the first operational order searched, specifically can root During current intercommunication, the content of both sides' interactive voice is determined, response message of the present embodiment to the first operational order Content be not construed as limiting.

Optionally, in conjunction with to the analysis of prompt information, the first electronic equipment user can select according to actual needs above The voice control for receiving or not receiving the second electronic equipment user is selected, if selection receives, such as user's Response to selection prompt information " confirmation " button in the prompting interface of place (is also possible to other words for indicating to receive second electronic equipment user's voice control The button of sample), it can produce the first electronic equipment user and the confirmation of the response prompt information instructed, the first electronic equipment connects Confirmation instruction is received, then triggers step S13 and executes the first operational order, so that the first electronic equipment completes corresponding operation.

The speech information content sent such as the second electronic equipment user to the first equipment is " the first electronic equipment to be asked to use Person sends one and attends certain movable photo ", process, carries out semantic analysis to the voice messaging, can obtain according to the above analysis Know the word content of the voice messaging, and its operational order that may cover, such as searches the instruction of certain photo, and will search The photo feedback arrived to the second electronic equipment instruction.Therefore, above-mentioned first operational order of the present embodiment can not be Dan Zhiyi Instruction, also may include multiple instructions continuously performed.

Such as the example above, after obtaining the first operational order, learn the second electronic equipment user requirement acquisition is to shine Piece has been related to individual privacy, can export prompt information in the manner described above.Such as, if allow to inquire and feed back certain work Dynamic photo, if it is allowed, the first electronic equipment can respond the first operational order of above content, by the first electronic equipment It is defeated to be sent to the second electronic equipment later by voice assistant, the photo that lookup meets the requirement from its memory for the photo Out.

If not allowing to inquire and feed back certain photo, the first electronic equipment voice assistant can be from the default response prestored In information, searches and feed back to the second electronic equipment with the associated default response message of first voice messaging, cannot such as send photograph Piece can reply the information of contents such as " sorry, since certain photo maintains secrecy, it has not been convenient to open ".The present embodiment is to default sound Answer the content of information without limitation.

Further, the present invention can also export the first electronic equipment to the implementation procedure of the first operational order.

It is that the voice assistant of the first electronic equipment is allowed to carry out voice in the case where each step describes the present embodiment above The trustship of control substitutes the first electronic equipment user and the first electronic equipment is manually operated in person, directly rung by voice assistant The phonetic control command that should be received comprising above-mentioned first operational order and the voice of the first electronic equipment user sending Control instruction.

Wherein, the first electronic equipment is during executing the first operational order, and the first electronic equipment display screen can be with Operation progress export corresponding operation interface or query result etc., that is to say, that the first electronic equipment executes the first operation and refers to When enabling, the voice assistant response of the first electronic equipment with its implementation procedure to the first operational order of synchronism output, that is, can be monitored The process of second electronic equipment user's phonetic control command, so that the first electronic equipment user be enable intuitively to learn second Electronic equipment user has what control requires and the first electronic equipment performs what operation etc..

Optionally, it is watched in implementation procedure of the first electronic equipment output to the first operational order in user, if operation has Accidentally, misoperation or because of reasons such as temporary changes demands, needs to interrupt or change the implementation procedure, the first electronic equipment user Can be with being intervened manually the first electronic equipment, such as incoming call of the second electronic equipment of manual adapter tube is set by the first electronics Standby user in propria persona replys, and operates manually to the first equipment, certain work that the second electronic equipment user is required Dynamic photo is sent to the second electronic equipment.

Further, the present embodiment can also lead to above-described first electronic equipment with the second electronic equipment During letter, the voice messaging and both sides' electronic equipment of both sides records the implementation procedure of obtained operational order.It can See, this is recorded relative to traditional incoming call history, i.e., only recording incoming number and send a telegram here the time history message registration, the present embodiment The first electronic equipment user can according to record content, can not only learn its not the first electronic equipment at one's side during, First electronic equipment receives the communication request of which the second electronic equipment, additionally it is possible to learn that each second electronic equipment user is logical Voice control mode is crossed, which operation the first electronic equipment of control performs, so that the first electronic equipment carries out subsequent place accordingly Reason.

In conclusion in the first electronic equipment and the second electronic equipment communication process, the first electronics is set in the present embodiment After standby the first voice messaging for receiving the second electronic equipment user, the first electronic equipment exports the first voice messaging, so that While first electronic equipment user learns other side's voice content, additionally it is possible to using AI technology in speech recognition and natural language Application in processing carries out semantic analysis to the voice messaging, obtains showing that the second electronic equipment user sets the first electronics The first operational order that standby control is intended to executes first operational order, and the second electronic equipment user is during call for realization, To the voice control of the first electronic equipment, the diversity and flexibility of electronic equipment voice control function are improved, can satisfy The electronic equipment use demand of more scenes.

The core idea of the sound control method of the present invention described based on the above embodiment shows the present invention referring to Fig. 3 The signaling process schematic diagram for the sound control method that another embodiment provides, as shown in figure 3, this method may include but not office It is limited to following steps:

Step S21, with the second electronic equipment communication process, the first electronic equipment acquires the first electronic equipment user The second voice messaging；In the present embodiment, it can be made by the sound collector of the first electronic equipment to acquire the first electronic equipment The second voice messaging of user, concrete methods of realizing are not detailed.

Wherein, the communication of the first electronic equipment and the second electronic equipment can be the two user and carry out telephone communication, It can be the voice communication realized using respective social software or video communication etc., the present embodiment is set to the first electronics is established The implementation method of the standby communication connection between the second electronic equipment is not construed as limiting.

Second voice messaging is sent to the second electronic equipment by step S22, the first electronic equipment；

It, can be by with second after the first electronic equipment collects the second voice messaging of its user after above description Second voice messaging is sent to the second voice messaging, to realize the interactive voice of communicating pair by electronic equipment communication channel.

Wherein, the content of the first voice messaging and the second voice messaging can be associated with, and the present embodiment is to speech information content Without limitation.And realize that the mode of communication connection is different between the first electronic device and the second electronic device, the two user The transmission mode of voice messaging can also accordingly change.

Step S23, the second electronic equipment exports the second voice messaging, and carries out semantic analysis to the second voice messaging, obtains To the second operational order；

Step S24, the second electronic equipment execute the second operational order；

About the realization process of step S23 and step S24, it is referred to above-mentioned steps S12 and step S13 corresponding portion Description.

Step S25, the first electronic equipment wake up the voice service of the first electronic equipment, carry out to the second voice messaging semantic Analysis obtains the third operational order for the first electronic equipment；

Step S26, the first electronic equipment execute third operational order.

It is logical in addition to being sent to after electronic equipment collects the voice messaging of local user in conjunction with the description of foregoing embodiments Believe counterpart device, the voice service of itself, such as voice assistant can also be waken up, the voice messaging of local user is carried out semantic Analysis, obtains the operational order for controlling local electronic equipment.

Wherein, the realization about the first electronic equipment to the semantic analysis of the second voice messaging is referred to above-mentioned implementation The description of example corresponding portion, it can realize that details are not described herein for the present embodiment using AI technology.

And the content and its control object of the third operational order for obtaining, the first operation is referred to above-described embodiment The description of order is similar, and the voice control to the first electronic equipment may be implemented, and also may be implemented to other electricity associated with it The voice control of sub- equipment is specifically referred to the description of foregoing embodiments corresponding portion, and details are not described herein for the present embodiment.

As it can be seen that scene flow diagram as shown in connection with fig. 4, during intercommunication, for the either side of communication For, the voice messaging of output can not only be sent to counterpart device, realize the voice control to counterpart device, additionally it is possible to The voice control to local user is realized accordingly, and relative in traditional scheme, electronic equipment is only capable of the voice of acquisition local user Information realizes that the voice control to local device, sound control method provided in this embodiment improve electronic equipment voice control The flexibility and diversity of system.

In conjunction with the description for the related content prompted the first electronic equipment that foregoing embodiments describe, the present invention is provided The another embodiment of sound control method, as shown in figure 5, this method may include:

Step S31 obtains the first voice letter of the second electronic equipment user when communicating with the second electronic equipment Breath；

Step S32 exports first voice messaging and voice control prompt information；

Wherein, the voice control prompt information is for prompting the first electronic equipment user confirmation, if allows the first electricity Sub- equipment is by the second electronic equipment voice control.That is, the second electronic equipment user uses with the first electronic equipment Person carries out having initiated voice control to the first electronic equipment, the first electronic equipment can't be directly by it in voice call process Voice assistant can remind the control content of the first electronic equipment user other side directly in response to phonetic control command herein.

Optionally, above-mentioned voice control prompt information can be in the pop-up of the first electronic equipment display screen, voice control Request, such as request carry out voice control to the first electronic equipment by the second electronic equipment user, " permit at this point, can also export Perhaps ", the select button for the printed words such as " not allowing ", selects for the first electronic equipment user.

As an alternate embodiment of the present invention, the present embodiment can be by detecting whether the voice messaging includes preset peace Contents, the phonetic control commands to judge that the voice messaging that the second electronic equipment uses includes such as full hidden danger, harassing and wrecking keyword are No safety, the first electronic equipment respond the phonetic control command with the presence or absence of security risk etc..If it is determined that there are security risk, it can To export voice control prompt information.

Optionally, the above-mentioned detection to the voice messaging received can converse according to the history of the first electronic equipment and remember Record, the call mark information of third party's acquisition, the first electronic equipment are for contents such as the processing rules of separate sources communication request It determines, specific implementation process the present embodiment is not detailed.

Step S33 receives the first electronic equipment user and instructs to the confirmation of voice control prompt information, wakes up first The voice service of electronic equipment；

In conjunction with the analysis of the above-mentioned confirmation instruction to voice control prompt information, the present embodiment is selected in the first electronic equipment After phonetic control command by its voice assistant voice responsive information, just the first electronic equipment voice assistant is allowed to believe the voice Breath is handled.

Therefore, the present embodiment can monitor whether that the first electronic equipment receives the first electronic equipment user to voice control The confirmation of prompt information processed instructs, and specific available first electronic equipment user is to the response prompt information currently shown The instruction that selection operation generates to judge whether the instruction is confirmation instruction, but is not limited to a kind of this mode.

If the first electronic equipment user does not allow the second electronic equipment user to control the first electronic equipment, that is, receive First electronic equipment user denies instructing to the voice control prompt information, can believe from pre-stored default response In breath, the default response message that the voice messaging searched and be currently received matches, and feed back to the second electronic equipment.

Wherein, default response message may include the voice messaging for different content type, the response content of setting, such as Sorry, I calls back to you later；Sorry, I am just in session；I just in session, please wait a moment calls me again；My road Zheng On；Thank very much etc..The present embodiment presets response message content without limitation to this.

Step S34 carries out semantic analysis to first voice messaging, obtains the first operational order；

Step S35 executes first operational order；

In the present embodiment, the first operational order is really analyzed from the voice messaging of the second electronic equipment user and is obtained , the phonetic control command that as the second electronic equipment user initiates the first electronic equipment or its associate device, this implementation Example to the acquisition modes of first operational order without limitation.Specific implementation is referred to retouching for above-described embodiment corresponding portion It states.

Optionally, the present embodiment can also export the first electronic equipment to the implementation procedure of first operational order, and The contents such as the voice messaging of the second electronic equipment user obtained, so that the first electronic equipment user monitors its voice assistant Action.

Step S36 determines the first operational order of successful execution, or receives the response message of the second electronic equipment feedback；

Wherein, which can be used for characterizing the second operational order of the second electronic equipment successful execution, this reality Example is applied to the content of the response message without limitation.

Step S37 terminates the communication with the second electronic equipment.

Optionally, in the condition for meeting step S36 record, the voice service of the first electronic equipment can also be terminated, by the One electronic equipment user continues to be manually operated.

Optionally, since the present embodiment can just record first receiving the communication request that the second electronic equipment is initiated Interactive voice content and the first electronic equipment between electronic equipment and the second electronic equipment respond the second electronic equipment and use The process of the voice messaging of person is inquired so that the first electronic equipment user is subsequent.

It is to be appreciated that above-mentioned first electronic equipment can be communication request initiator, it is also possible to recipient, that is, It says, double for communication to send, after the voice messaging for receiving other side, the method that can be described according to above-described embodiment is carried out Processing, i.e. communicating pair can execute corresponding operating by voice operating counterpart device, while the equipment operated can be shown Its process for executing the phonetic control command that other side sends, i.e. operation of the displaying other side to this equipment, so that this equipment user couple Operating process is monitored, and according to the actual situation, carries out manual intervention at any time.

To sum up, it in the present embodiment, is carried out in communication process in the first electronic equipment and the second electronic equipment, both sides are in addition to energy Voice communication is enough carried out, while voice control can also be carried out to own electronic equipment or other side's electronic equipment, wherein is being controlled Before counterpart device, counterpart device can remind counterpart device user to control content, decide whether to connect by counterpart device user It is controlled, is determined after receiving, counterpart device will carry out semantic analysis to the voice messaging received by voice assistant, and execute The operational order arrived meets actual needs.

The voice assistant that above-described embodiment is mentioned to can actually be that the intelligent sound interaction realized using AI technology is answered With, can be identified in real time by the voice to communication counterpart, intelligent Understanding, synthesis response voice come and other side carry out language Sound interaction, local user can different sounding also can be realized the voice communication with other side, how sharp the present invention is to voice assistant Realize that the concrete methods of realizing of both sides' interactive voice is not described further with AI technology.

As it can be seen that the voice assistant of the first electronic equipment of the present embodiment, which can substitute user, executes the second electronic equipment user The phonetic control command of sending, or response is carried out to the speech information content of the second electronic equipment user, even if in this way, first Electronic equipment user is inconvenient to speak or not near the first electronic equipment, or the first electronic equipment of not knowing that how to operate In the case of, the first electronic equipment voice assistant can control the first electronics based on the voice messaging of the second electronic equipment user Equipment executes operation, meets control requirement of the second electronic equipment user to the first electronic equipment.

Moreover, the first electronic equipment can remind the first electronic equipment before the voice messaging that voice assistant responds other side What the speech information content of user other side is, if to respond corresponding operation instruction, if allowing to respond, the first electronics Equipment can just execute the operational order, avoid and do not make any prompt, be sent by the first electronic equipment directly in response to communication counterpart Voice messaging, cause the first electronic equipment important information reveal, or execute it is improper operation and so on.That is, The present embodiment ensure that the safety that electronic equipment uses while improving electronic equipment ease of use.

In an alternate embodiment of the present invention, the voice assistant in electronic equipment can receive other electronic equipments hair It in the communication request risen, determines starting or does not start, specific implementation process is referred to the offer of the alternative embodiment described in Fig. 3 Sound control method flow chart, this method still can apply the first electronic equipment, as shown in fig. 6, this method may include But it is not limited to following steps:

Step S41 receives the communication request that the second electronic equipment is initiated；

In practical applications, the voice communication which can be incoming call requests, initiated using social application software Request or video calling request etc., which may include the attribute information of the second electronic equipment, and such as the second electronics is set The name of standby user, the second electronic equipment initiate the telephone number that the communication request uses, social software are used to initiate communication Account information of request etc. communicates boundary in request so that the first electronic equipment shows the information carried in the communication request Face, i.e. call interface, voice request interface, video request interface etc..

Optionally, after the first electronic equipment receives the communication request that the second electronic equipment is initiated, it will usually which output phase is answered Request interface the first electricity can also be shown by second electronic equipment of request showing interface and its user's relevant information The mark information that sub- equipment user sets second electronic equipment or its user, such as distribution, advertisement, express delivery.

Step S42 analyzes the communication request, obtains analysis result；

In conjunction with the description of content and its way of output above to the communication request received, analyze it Analyzing result may include: the second electronic equipment and/or the attribute information of its user, such as mark information, account information, incoming call Number, remarks pet name etc..

Optionally, above-mentioned analysis result can also include the security even analysis carried out to these contents, i.e., according to communication The content carried is requested, determines whether the communication request that second electronic equipment is initiated is harassing and wrecking or swindle request etc..

Step S43 exports communication prompt information based on the analysis result；

Such as the description above to communication request content and its analysis result, it is known that the analysis result that the present embodiment obtains can The communication request for characterizing the initiation of the second electronic equipment is harassing and wrecking/distribution type customer service incoming call requests, or is preset important Client-initiated communication request, perhaps for regular friend initiate communication request or be strange Client-initiated communication request Etc., therefore, whether the first electronic equipment can be based on the analysis and set the communication request trustship to the first electronics as a result, exporting The communication prompt information of standby voice assistant.

As it can be seen that the communication prompt information of the present embodiment output can be used for that the first electronic equipment user is prompted to determine, it is The no voice service (i.e. the service of voice assistant offer) by the first electronic equipment handles the communication request.

Further, the history note that the present embodiment can be combined with the address list of the first electronic equipment, respond communication request The information such as record, the processing rule based on different type communication request, providing this communication request, whether trustship is to voice assistant It is recommended that.Such as service calls listed above, it can suggest that voice assistant response is given in the first electronic equipment user trustship；It is right In the incoming call of responsible consumer, it can suggest that voice assistant response is given in not trustship, and it is in person manual by the first electronic equipment user Response；For ordinary user (such as regular friend, colleague), can be accustomed to according to the previous response of the first electronic equipment user Suggestion is provided, determines the first electronic equipment using what mode response communication request.

Optionally, the display screen of the first electronic equipment can be directly displayed at for above-mentioned communication prompt information, it can also be with Be shown using default prompt tone, or using voice broadcast mode export, the present embodiment to its way of output without limitation.

Step S44 receives the first electronic equipment user and instructs to the confirmation of communication prompt information, controls the first electronics Equipment enters voice service tupe, and responds the communication request.

It is similar with the confirmation instruction generation process of foregoing embodiments description, it, can also be defeated when exporting above-mentioned communication prompt Out for the button of the printed words such as "Yes", "No" of the first electronic equipment user selection, when user selects this button of "Yes", i.e., the One electronic equipment is determined this communication request trustship to voice assistant, corresponding confirmation instruction can be generated, so that first After electronic equipment receives confirmation instruction, the first electronic equipment of control enters voice service tupe, i.e. starting voice helps Hand responds the communication request that the second electronic equipment that this is received is initiated.

It is to be appreciated that how the present embodiment responds the implementation method of the communication request without limitation to voice assistant, voice After assistant responds the communication request, it will, during this period, can be with so that the first electronic equipment is communicated with the second electronic equipment The voice messaging of the second electronic equipment user is identified in real time by the voice assistant of the first electronic equipment, semantic understanding, And response voice feedback is synthesized to the second electronic equipment.

Thus, for the first electronic equipment by communication request trustship to voice assistant, that is, enter voice service and handle First electronic equipment of mode does not need the first electronic equipment user and carries out voice friendship with the second electronic equipment user in person Stream, in this way, near the first electronic equipment user no longer the first electronic equipment, or the inconvenient, reasons such as be unwilling, Bu Nengqin In the case where the manual communication request for receiving the second electronic equipment, it can be located in time using the voice assistant of the first electronic equipment The communication request is managed, the second electronic equipment user is avoided to fall into a long wait because of no response.

And the description in conjunction with foregoing embodiments to the processing method of voice assistant in communication process, the first of the present embodiment Electronic equipment can also export answering of the voice assistant to communication request of the first electronic equipment in real time, and its to the second electricity The response process of the voice messaging of sub- equipment user protects it that can carry out manual intervention to this voice communication in time.

It is to be appreciated that first electricity can be established after the first electronic equipment responds the communication request that the second electronic equipment is initiated Communication connection between sub- equipment and the second electronic equipment, so that the user of the two carries out voice friendship by the communication connection Mutually, about the communication control method in the first electronic equipment and the second electronic equipment communication process, it is referred to above-described embodiment Description.

The first electronic equipment of determination and the in another alternative embodiment provided by the invention, with foregoing embodiments description The method that two electronic equipments are communicated is different, and the present embodiment can automatically determine whether the communication request support for receiving this Pipe is to voice assistant, as shown in fig. 7, the specific implementation steps are as follows:

Step S51 receives the communication request that the second electronic equipment is initiated；

Wherein, the implementation method of step S51 can be similar with the above-mentioned steps S41 acquisition implementation method of communication request, this Embodiment repeats no more.

Step S52 does not receive the first electronic equipment user within a preset period of time and instructs to the response of communication request, The voice service of the first electronic equipment is waken up, so that the first electronic equipment enters voice service tupe；

In the present embodiment practical application, especially in the first electronic equipment user not near the first electronic equipment, nothing In the case that method in person operates the first electronic equipment, the present embodiment can preset it and set receiving the second electronics After the signal intelligence that preparation rises, the communication request is not operated in first electronic equipment user's preset time period, is such as connect The responses instructions such as logical/refusal incoming call, the first electronic equipment can directly initiate the first electronic equipment voice assistant, to handle this The communication request received.

Wherein, the first electronic equipment voice assistant of starting is to wake up the voice service of the first electronic equipment, is made it into Voice service tupe, later, the first electronic equipment by functions such as speech recognition, natural language processings based on AI technology, The voice messaging of second electronic equipment user is handled, so that the communication request that the second electronic equipment user initiates It can be handled in time.

It is to be appreciated that after the present embodiment enters voice service tupe to the first electronic equipment, how to receiving The implementation method that voice messaging is handled without limitation, can be in conjunction with function such as speech recognition, the natural language processings of AI technology The working principle of energy determines.

Step S53 responds the communication request, establishes the communication connection with second electronic equipment.

As it can be seen that the first electronic equipment receives the communication request of the second electronic equipment initiation, it has not been convenient to or do not know how When responding the communication request, the voice service of the first electronic equipment can be waken up, timely responds to the communication request, so that the Communication channel is generated between one electronic equipment and the second electronic equipment, so that the first electronic equipment and the second electronic equipment carry out Voice communication specifically can be voice assistant or its user of the first electronic equipment, the voice assistant with the second electronic equipment Or its user carries out interactive voice, will pass through interactive speech information content, controls counterpart device or associated equipment It realizes specified function, meets this communicating requirement.

In conclusion the phonetic control command of its user can only be handled relative to the voice assistant of conventional electronic devices, The present invention can utilize AI technology speech recognition and natural language processing function, help electronic equipment user intelligent response, The application for the communication request that management and processing receive, so that the voice assistant function of electronic equipment is more diversified, Neng Gougeng It is serviced for electronic equipment user well, improves the electronic equipment with the voice assistant and promote market.

Optionally, on the basis of the various embodiments described above, the first electronic equipment enters voice service tupe, by its language During sound assistant automatically processes and manages the voice messaging of the second electronic equipment user, it can synchronize and show the processing and management Process, the first electronic equipment user see that current operation is improper, can operate at any time to the first electronic equipment, to interrupt Or the current operation that change voice assistant is realized, the first electronic equipment receive its user and operate the control instruction generated (i.e. The instruction generated for the implementation procedure of the first operational order of output), the control instruction is responded, the first electronics is can control and sets It is standby to be switched to artificial treatment mode from voice service tupe, and stop executing the first operational order (or third operation refers to Enable), the 4th operational order that the first electronic equipment user is inputted based on voice messaging is received, the 4th operational order is executed.

Wherein, after the first electronic equipment receives voice messaging, it can be converted corresponding word content, and show On first electronic equipment display screen, for the first electronic equipment user reading, and judge what current speech assistant executed accordingly Whether operation meets the requirement of text content.

It can be seen that waking up voice service in the first electronic equipment uses voice assistant into voice service tupe The voice messaging of second electronic equipment user is treated in journey, the first electronic equipment user can be based on displaying The content of operating process and voice messaging finds in time and prevents the operation dealt with improperly, guarantees the second electronic equipment user Voice control can reliably realize.

In conjunction with the communication control method that the various embodiments described above describe, in order to more clearly illustrate the core idea of this method, During this implementation is conversed herein with user A and user B, user B to user A take individual after year on photo scene for It is illustrated, is specifically referred to flow diagram shown in Fig. 8, the realization step of communication control method is such as under the scene Under:

User B initiates call request to the mobile phone A of user A using mobile phone B, and the display screen of mobile phone A can be with output incoming circle Face, if the incoming call of user B is seen in user A prompt, oneself can select to answer or connect absolutely or open to export active user B incoming call The voice assistant of dynamic mobile phone A handles (this mode is denoted as trustship by the present embodiment), can be with when user A selects entrusted management model Without receiving calls manually and carrying out speech exchange with user B in person.

Certainly, after mobile phone A receives the incoming call of mobile phone B, mobile phone A usually can learn the device attribute information of mobile phone B (such as Mobile phone model, illegal mobile phone mark information (such as mobile phone B is stolen mobile phone) etc.), user, that is, user B use of mobile phone B (such as phone number of user B, user A are to the remarks title of user B, strange number/people, distribution/harassing and wrecking number for family attribute information Etc. mark information), in this way, mobile phone A can according to preset rules, export to mobile phone B incoming call whether the suggestion of trustship.

Wherein, which, which can be, answers the information such as habit to all types of user/equipment incoming call history based on user A It determines.All kinds of customer service incoming calls of such as distribution/harassing and wrecking, can suggest that user A trustship is handled to the voice assistant of mobile phone A, important friend Friend/client/household incoming call further can also answer habit according to user A in the past and provide corresponding suggestion, and the present embodiment is to giving The content of suggestion content and preset rules out is without limitation.

The incoming call that mobile phone B is handled by the voice assistant of mobile phone A, i.e. mobile phone A processing entrusted management model are selected in user A (i.e. The voice service tupe of foregoing embodiments), can with the incoming call of listening user B, and in the communication process of user B, language Sound assistant will utilize AI technology, the voice of user B will be identified in real time, intelligent semantic understanding, synthesis response voice come with user B into Row intelligent interaction, that is to say, that in this process, the mobile phone A for starting voice assistant is equivalent to an intelligent robot, come with make Interactive voice is carried out with the user B of mobile phone B.During this period, user A can without reference to the interactive voice process, user A can be with It is left or other busy things with vertical, the interactive voice with user B can't be delayed.

Certainly, in order to avoid user B requires the improper operation of mobile phone A execution or mobile phone A voice assistant to respond user B's The display screen of voice messaging, performed misoperation, mobile phone A can be held with real-time display both sides' interactive voice content and mobile phone A The process of row operational order, in this way, user's A direct viewing display screen shows content, even without coming for listening user B in person Electricity can also learn user B to the control content of mobile phone A.In this way, when there is improper behaviour in the operating process of user A discovery mobile phone A Make, manual intervention can be carried out in time, if user A triggers the display screen of mobile phone A manually, stop the work of voice assistant, by with Family A manually completes subsequent operation.

And when the user B controlling mobile phone through speech A operation completed is related to security, as the voice messaging of user B is " by wechat to I send out several I after year on photo ", after the voice assistant according to above-mentioned treatment process starting mobile phone A, warp Semantic analysis to the voice messaging determines that mobile phone A needs to inquire photo and is sent to mobile phone B, which is related in mobile phone A Preset security privacy content, mobile phone A can be with output response prompt informations, as whether PLSCONFM to mobile phone B sends photo, if The photo of user B and it is sent to the prompt informations of the contents such as mobile phone B in inquiry mobile phone A, after user A selection confirmation, mobile phone A just meeting The photo this operation instruction for sending user B is executed, specifically, mobile phone A will start this application of wechat, finds user B's Social account, and the photo of user B is sent to user B.

At the same time, mobile phone B it can also be sent " by wechat to I send out several I after year on photo " this Voice messaging carries out semantic analysis, obtains the operational order of the wechat application of starting mobile phone B, will start the wechat of mobile phone B, wait The photo that the user A of mobile phone A is sent.As it can be seen that user A and user B is carried out in communication process, both sides can not only carry out voice friendship Stream, while itself and/or counterpart device can also be controlled according to exchange content, content is exchanged with assistant voice, is not required to It wants user to exchange content further according to call, is indicated according to other side's voice, manual function operates equipment of itself.

In addition, voice assistant can search and work as from the default response message prestored if user B selection receives and sends absolutely The default response message that preceding scene matches feeds back to mobile phone B output, such as reply " it is sorry, be inconvenient to search now, having time meeting Issue you as early as possible " etc. contents.It is to be appreciated that the content that the voice assistant of mobile phone A is replied at this time is obtained there is still a need for AI technology is utilized Mobile phone B output is fed back to corresponding voice messaging, so that user B hears the content.Certainly, the mobile phone B of user B is come It says, can also be handled according to the communication control method of above-mentioned mobile phone A using the voice assistant of mobile phone B.That is, logical The voice messaging that the mobile phone of both sides can use voice assistant processing other side to send is talked about, the various embodiments described above of the present invention are only to connect It is illustrated for the treatment process of the first electronic equipment of debit, the second electronic equipment handles the language of the first electronic equipment user The implementation method of message breath is similar, and the present invention repeats no more.

To in this present embodiment, confirmation of the user A to response prompt information can directly select ACK button, can also be with Input password executes photo triggering mobile phone A and sends operation, specifically can according to the way of output of the response prompt information and Preset user's validation testing determines which is not limited by the present invention.

It can be seen that being helped in the communication process of user A and user B even with the voice of respective mobile phone in the present embodiment Hand handles the voice messaging of other side, security protection can also be arranged to this, specifically can in conjunction with user communication record, to being related to using The information etc. of family privacy class, is arranged the processing authority of voice assistant, when the speech information content received is managed in permission at which, Directly it can be handled by voice assistant, not need user and cooperate；For exceeding mobile phone speech assistant disposal right The voice messaging of limit can further be determined whether that voice assistant processing should with output response prompt information by user Voice messaging improves the safety that mobile phone uses, especially in mobile phone during user's communication, by partner voice control In the application of system, other side is avoided by voice control and carries out illegal or improper operation, leads to the important information of user in mobile phone Leakage or other side pass through this user mobile phone of voice control and carry out illegal operation etc. to other equipment.

It is to be appreciated that the dialog context of corresponding user A and user B both sides, especially in one party starting voice assistant processing In the case where other side's voice messaging, double-talk content and other side can recorde to the operation content etc. of local user's mobile phone, For this user's subsequent query, and improper operation of timely correction etc..

Figure 8 above only the communication control process for receiving voice messaging is described in detail the mobile phone A of user A, and The communication control process of the mobile phone B of user B is similar, i.e. the control process class of user A controlling mobile phone through speech B or its associate device Seemingly, Fig. 8 is not showed that.

In addition, describing in conjunction with each embodiment of above-mentioned communication control method it is found that the application that the communication control method is applicable in Scene is not limited to above-described user's double-talk process, can be applicable to other voice communication scenes, and double In square communication process, it is also not limited to the concrete scene of above-described voice control counterpart device feedback photo, the present invention Above-mentioned communication control method can also be utilized, in communication process, helps other side that counterpart device or the function of its associate device are set.

Referring to schematic diagram of a scenario shown in Fig. 9, such as old man, children children under guardianship, guardian can with quilt In the communication process of guardian, by way of voice control, help children under guardianship be arranged its cell-phone function, content, configuration or Certain operation is executed, the old man of family is such as helped to start the broadcast software of its mobile phone, plays broadcast etc., or open flashlight, or beat Positioning software is opened, or according to certain software etc..If older mobile phone is associated with other smart home devices of family, guardian may be used also By the voice messaging sent to the mobile phone of children under guardianship, to start the voice of children under guardianship with by monitoring communication process Assistant, to start or adjust specified smart home device, is such as adjusted to be analyzed to obtain corresponding operation instruction using AI technology Bright indoor light brightness etc..Specific implementation process of the present embodiment to communication control method under each application scenarios listed above It is no longer described in detail one by one, and for the application scenarios that the communication control method is applicable in, is also not limited to multiple fields listed above Scape.

As it can be seen that this communication control method provided in this embodiment, can help other side in double hair voice call process (being especially ignorant of the individual that operates or can not operate) carries out voice control to its equipment, and counterpart device is made to complete this user speech It is required that operational order, do not need user and take action on one's own to operate to counterpart device, it is more convenient.

Referring to Fig.1 0, it is a kind of structural schematic diagram of phonetic controller provided in an embodiment of the present invention, which can be with Applied to the first electronic equipment, the apparatus may include:

Voice messaging obtains module 11, for the second electronic equipment communication process, the second electronic equipment of acquisition to make The first voice messaging of user；

Voice messaging output module 12, for exporting first voice messaging；

Voice messaging analysis module 13 obtains the first operation and refers to for carrying out semantic analysis to first voice messaging It enables；

Operational order execution module 14, for executing first operational order.

Optionally, as shown in figure 11, which may include:

Applications trigger and running unit 141 enter work with the associated target application of the first operational order for triggering Make state, and first operational order is executed by the target application；

Response message feedback unit 142, if the response message for receiving first operational order, by the response Information feeds back to second electronic equipment.

Analysis in conjunction with embodiment of the method above to above-mentioned each Implement of Function Module function, the present embodiment are set in the first electronics Standby and the second electronic equipment carries out in communication process, and the first electronic equipment voice assistant receives the second electronic equipment user's After voice messaging, while exporting the voice messaging, also semantic analysis can be carried out using AI technology, and by the first electronic equipment Execute obtained operational order, that is to say, that in both devices communication process, both sides user carries out the same of voice communication When, it also can be realized the voice control to counterpart device, improve the flexibility and diversity of electronic equipment voice control.

Optionally, referring to Fig.1 2, on the basis of the above embodiments, which can also include:

Voice messaging acquisition module 15, for acquiring the second voice messaging of the first electronic equipment user；

Transmission of speech information module 16, for second voice messaging to be sent to the second electronic equipment, so that described Second electronic equipment exports second voice messaging, and executes the second operational order that second voice messaging includes；

Voice service wake-up module 17, for waking up the voice service of first electronic equipment, to second voice Information carries out semantic analysis, obtains the third operational order for first electronic equipment, executes the third operational order.

The specific implementation for closing each functional module in this present embodiment, is referred to the description of above method embodiment.

On the basis of the various embodiments described above, above-mentioned apparatus can also include:

It is to be appreciated that about the prompting to the first electronic equipment user, it is not limited in the prompt of the cue module Hold, other suggestion contents are referred to the description of above method embodiment corresponding portion, and the present embodiment does not repeat them here.

Optionally, on the basis of the above embodiments, phonetic controller can also include:

First communication request receiving module, the communication request initiated for receiving second electronic equipment；

Communication prompt output module, for based on the analysis to the communication request as a result, output communication prompt information；

Wherein, which can be used for that the first electronic equipment user is prompted to determine whether by first electricity It may include being that the voice service of sub- equipment, which handles the communication request such as the description of above method embodiment corresponding portion, The suggestion etc. of the first electronic equipment voice assistant is given in no trustship.

First communication request respond module believes the communication prompt for receiving the first electronic equipment user The confirmation of breath instructs, and controls first electronic equipment and enters voice service tupe, and responds the communication request.

As it can be seen that the first electronic equipment can not be directly after the second electronic equipment initiates communication request to the first electronic equipment Starting voice assistant can independently be selected to be by voice assistant support by the first electronic equipment user to respond the communication request Pipe, or receive the communication request manually by oneself, improve the processing flexibility and multiplicity of electronic equipment response communication request Property.

In another alternative embodiment of the present invention, it is different from the processing side of the response communication request of above-described embodiment description Formula, the device can also include:

Second communication request receiving module, the communication request initiated for receiving second electronic equipment；

Voice service wake-up module, for not receiving the first electronic equipment user within a preset period of time to institute The response instruction for stating communication request, wakes up the voice service of first electronic equipment, so that first electronic equipment enters Voice service tupe；

Second communication request respond module responds the communication request for passing through the voice service of the first electronic equipment.

It is to be appreciated that the response mode about the communication request initiated the second electronic equipment, it is not limited to above two The mode that a alternative embodiment is recorded.

In addition, the first electronic equipment user can be at any time to the behaviour of voice assistant on the basis of the various embodiments described above Make carry out manual intervention, therefore, which can also include:

Tupe switching module is instructed for response control, is controlled first electronic equipment and is handled by voice service Pattern switching stops executing first operational order to artificial treatment mode；

Wherein, which generated for the implementation procedure of first operational order of output；

Second operational order execution module, it is defeated based on the voice messaging for receiving the first electronic equipment user The 4th operational order entered executes the 4th operational order.

As it can be seen that the first electronics is set during the voice messaging that the voice assistant of the first electronic equipment response other side sends It is standby can with the operating process of the synchronism output voice messaging and voice assistant, once the first electronic equipment user has found behaviour It is improper to make, and can carry out manual intervention to current operation in time, be switched to manually from the voice service tupe of voice assistant Processing module is operated according to the content of voice messaging in person by the first electronic equipment user.

Referring to Fig.1 3, it is the hardware structural diagram of a kind of electronic equipment provided in an embodiment of the present invention, the electronic equipment It may include but be not limited to lower component:

Communication module 21；

In the present embodiment, which may include wireless communication module and/or wire communication module, specifically can be with It is GPRS module, WIFI module, bluetooth module, radio-frequency module etc., can be specifically determined according to practical communication demand, this implementation Example is not construed as limiting the concrete composition structure of the communication module 21.

Display 22；

Wherein, display 22 can be liquid crystal display or touch display etc..

Memory 23, for storing the program for realizing the voice information processing method of embodiment description as above；

In the present embodiment, memory 23 may include the non-volatile memory in computer-readable medium, arbitrary access The forms such as memory (RAM) and/or Nonvolatile memory, such as read-only memory (ROM) or flash memory (flash RAM), memory Including at least one storage chip.

Processor 24, for loading and executing the program of memory storage, which is mainly used for:

Execute first operational order.

It is to be appreciated that executing each step for the communication control method that program is realized about processor, it is referred to above-mentioned side The description of method embodiment corresponding portion, details are not described herein for the present embodiment.

In practical applications, which can be used as communication request and sends hair, can also be used as communication request reception Side, specifically can be the product types such as mobile phone, tablet computer.

The embodiment of the invention also provides a kind of storage mediums, are stored thereon with program, which is executed by processor, real Each step of existing above-mentioned communication control method.

The embodiment of the invention also provides a kind of communication control systems, referring to figure 2 above a, Fig. 2 b, Fig. 4 and knot shown in Fig. 9 Structure, system may include the first electronic equipment (such as mobile phone A) and the second electronic equipment (such as mobile phone B), set about the two electronics Communication control process between standby is referred to each step of communication control method of above method embodiment description, the present embodiment It repeats no more.

Wherein, since the hardware configuration of the first electronic equipment and the second electronic equipment is similar, and the communication control side realized Method is also similar, and the present invention no longer describes respectively, and specific hardware structure is referred to the hardware of above-mentioned electronic equipment embodiment description Structure, the communication control method of realization are referred to the content of above method embodiment description.

Optionally, which can also include other electronics with the first electronic equipment and/or the second electronic device association Equipment, intelligence printer as shown in Figure 2 b, computer, intelligent sound box or other smart home devices etc., in this way, logical in both sides During letter, it can further can also not only be controlled by counterpart device associated with it by voice control counterpart device Other equipment improve the control function of voice assistant.

Finally, it should be noted that about in the various embodiments described above, such as first, second or the like relational terms are only Only it is used to an operation, unit or module and another is operated, unit or module distinguish, and not necessarily requires or secretly Show that there are any actual relationship or orders between these units, operation or module.Moreover, term " includes ", " packet Containing " or any other variant thereof is intended to cover non-exclusive inclusion, so that including the process, method of a series of elements Or system not only includes those elements, but also including other elements that are not explicitly listed, or it is this for further including Process, method or the intrinsic element of system.In the absence of more restrictions, being limited by sentence "including a ..." Element, it is not excluded that include the element process, method or system in there is also other identical elements.

Each embodiment in this specification is described in a progressive manner, the highlights of each of the examples are with other The difference of embodiment, the same or similar parts in each embodiment may refer to each other.For device disclosed in embodiment, For electronic equipment, since it is corresponding with method disclosed in embodiment, so being described relatively simple, related place is referring to method Part illustrates.

The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, as defined herein General Principle can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, of the invention It is not intended to be limited to the embodiments shown herein, and is to fit to and the principles and novel features disclosed herein phase one The widest scope of cause.

Claims

1. a kind of sound control method, which is characterized in that be applied to the first electronic equipment, which comprises

First voice messaging is exported, and semantic analysis is carried out to first voice messaging, obtains the first operational order；

Execute first operational order.

2. the method according to claim 1, wherein the method is also wrapped when communicating with the second electronic equipment It includes:

Acquire the second voice messaging of the first electronic equipment user；

Second voice messaging is sent to the second electronic equipment, so that second electronic equipment exports second voice Information, and execute the second operational order that second voice messaging includes；

The voice service for waking up first electronic equipment carries out semantic analysis to second voice messaging, obtains for institute The third operational order for stating the first electronic equipment executes the third operational order.

3. the method according to claim 1, wherein described execute first operational order, comprising:

Triggering enters working condition with the associated target application of the first operational order, and as described in target application execution First operational order；

If receiving the response message of first operational order, the response message is fed back into second electronic equipment.

4. method according to any one of claims 1 to 3, which is characterized in that the method also includes:

Voice control prompt information is exported, the voice control prompt information is for prompting the first electronic equipment user true Whether recognize allows first electronic equipment by the second electronic equipment voice control；

It receives the first electronic equipment user to instruct the confirmation of the voice control prompt information, wakes up described first The voice service of electronic equipment, it is described to first voice messaging progress semantic analysis to execute, obtain the first operational order Step.

5. according to the method described in claim 4, it is characterized in that, the method also includes:

It determines the first operational order described in successful execution, or receives the response message of the second electronic equipment feedback, the sound Answer information for characterizing the second operational order of the second electronic equipment successful execution；

6. a kind of phonetic controller, which is characterized in that be applied to the first electronic equipment, described device includes:

Voice messaging obtains module, for obtaining the second electronic equipment user's with the second electronic equipment communication process First voice messaging；

Voice messaging output module, for exporting first voice messaging；

Operational order execution module, for executing first operational order.

7. device according to claim 6, which is characterized in that described device further include:

Transmission of speech information module, for second voice messaging to be sent to the second electronic equipment, so that second electricity Sub- equipment exports second voice messaging, and executes the second operational order that second voice messaging includes；

Voice service wake-up module, for waking up the voice service of first electronic equipment, to second voice messaging into Row semantic analysis obtains the third operational order for first electronic equipment, executes the third operational order.

8. device according to claim 6, which is characterized in that the operational order execution module includes:

Applications trigger and running unit enter working condition with the associated target application of the first operational order for triggering, And first operational order is executed by the target application；

Response message feedback unit, if the response message for receiving first operational order, anti-by the response message It is fed to second electronic equipment.

9. device according to any one of claims 6 to 8, which is characterized in that described device further include:

Cue module, for exporting voice control prompt information, the voice control prompt information is for prompting first electricity Sub- equipment user is confirmed whether to allow first electronic equipment by the second electronic equipment voice control；

Voice service wake-up module, for receiving the first electronic equipment user to the voice control prompt information Confirmation instruction, wakes up the voice service of first electronic equipment, to trigger the voice messaging analysis module to described first Voice messaging carries out semantic analysis, obtains the first operational order.

10. a kind of electronic equipment, which is characterized in that the electronic equipment includes:

Communication module；Display；

Memory, for storing the program for realizing sound control method as claimed in any one of claims 1 to 5, wherein；

Execute first operational order.