CN110444206A - Voice interactive method and device, computer equipment and readable medium - Google Patents
Voice interactive method and device, computer equipment and readable medium Download PDFInfo
- Publication number
- CN110444206A CN110444206A CN201910699941.1A CN201910699941A CN110444206A CN 110444206 A CN110444206 A CN 110444206A CN 201910699941 A CN201910699941 A CN 201910699941A CN 110444206 A CN110444206 A CN 110444206A
- Authority
- CN
- China
- Prior art keywords
- phonetic order
- cloud
- user
- needs
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/28—Constructional details of speech recognition systems
- G10L15/30—Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/225—Feedback of the input speech
Abstract
The present invention provides a kind of voice interactive method and device, computer equipment and readable medium.Its method includes: the phonetic order for receiving user；According to preset rules, detect whether the phonetic order needs cloud to be handled；If not needing, the phonetic order is executed by local control module, is generated and to the user feedback response message.In technical solution of the present invention, smart machine has certain computing capability, it is detected by the phonetic order to user, for the phonetic order without cloud processing, directly can locally be completed in smart machine, even if when network environment is unstable, smart machine can be performed locally phonetic order, and engage in the dialogue in time with user, it not will cause dialogue time delay, so as to effectively improve the dialogue ability of smart machine and user.Moreover, directly being locally executed in smart machine, additionally it is possible to further shorten processing delay, enhance the usage experience of user for the phonetic order without cloud processing.
Description
[technical field]
The present invention relates to computer application technologies more particularly to a kind of voice interactive method and device, computer to set
Standby and readable medium.
[background technique]
Intelligent dialogue based on semantic understanding, has been applied to all trades and professions at present.This intelligent interactive side
Formula had both reduced the cost of every profession and trade, also improved the efficiency of communication, the user experience is improved.In artificial intelligence Internet of Things
(Artificial Intelligence&Internet of Things；AIoT it in), has permeated in multiple industry scenes,
It is intelligent as major traditional industries such as medical instrument, smart home, wisdom game, intelligent vehicle-carried, intelligent Community/industrial circle
Change the optimal channel of upgrading, it has also become the inexorable trend of Internet of Things development.Wherein AIoT, as artificial intelligence (Artificial
Intelligence；AI) technology and Internet of Things (Internet of Things；IoT) landing fusion in practical applications.
The landing of AIoT realizes that in the scene of [waking up all things on earth], equipment will interconnect with equipment room, forms data and hands over
Mutually, shared ecology.For example, user directly can carry out voice with smart machine in the scenes such as smart home and car networking
The exchange of dialogue.In detailed process, user issues phonetic order against smart machine, and smart machine will be under the audio recording of user
Come, and cloud be sent to by network, realized by cloud the processing of speech recognition, natural language understanding, semanteme and dialogue with
And the work such as speech synthesis, then the words of the reply for responding user art, audio and control instruction are issued to smart machine.By
Smart machine plays reply voice according to reply words art and audio, and executes control instruction as required.It is set from actual use intelligence
From the point of view of standby user perspective, user wish with smart machine carry out voice dialogue exchange when, smart machine when what
Ground should can all respond, it is also desirable to which this response is quickly, it is natural to reach the response speed exchanged between people
It is best.
But according to above-mentioned existing scheme, if it is unstable to occur network environment between smart machine and cloud, even if user
Requested service is also able to carry out without cloud, and also resulting in smart machine can not engage in the dialogue with user, or dialogue
It is delayed larger.
[summary of the invention]
The present invention provides a kind of voice interactive method and devices, computer equipment and readable medium, for improving network
When environment is unstable, the dialogue ability of smart machine and user shortens dialogue time delay.
The present invention provides a kind of voice interactive method, which comprises
Receive the phonetic order of user；
According to preset rules, detect whether the phonetic order needs cloud to be handled；
If not needing, the phonetic order is executed by local control module, generates and is responded to the user feedback and believed
Breath.
The present invention provides a kind of smart machine, and the smart machine includes:
Receiving module, for receiving the phonetic order of user；
Detection module, for detecting whether the phonetic order needs cloud to be handled according to preset rules；
Control module is performed locally the phonetic order if the detection module, which determines, does not need the cloud processing,
It generates and to the user feedback response message.
The present invention also provides a kind of computer equipment, the equipment includes:
One or more processors；
Memory, for storing one or more programs；
When one or more of programs are executed by one or more of processors, so that one or more of processing
Device realizes voice interactive method as described above.
The present invention also provides a kind of computer-readable mediums, are stored thereon with computer program, which is held by processor
Voice interactive method as described above is realized when row.
Voice interactive method and device of the invention, computer equipment and readable medium have certain for smart machine
Computing capability is detected by the phonetic order to user, can be directly in intelligence for the phonetic order without cloud processing
Energy equipment is locally completed, though smart machine can be performed locally phonetic order when network environment is unstable, and
It engages in the dialogue in time with user, not will cause dialogue time delay, so as to effectively improve the dialogue energy of smart machine and user
Power.Moreover, directly being locally executed in smart machine for the phonetic order without cloud processing, additionally it is possible at further shortening
Time delay is managed, the usage experience of user is enhanced.
[Detailed description of the invention]
Fig. 1 is the flow chart of voice interactive method embodiment of the invention.
Fig. 2 is the structure chart of smart machine embodiment one of the invention.
Fig. 3 is the structure chart of smart machine embodiment two of the invention.
Fig. 4 is the structure chart of computer equipment embodiment of the invention.
Fig. 5 is a kind of exemplary diagram of computer equipment provided by the invention.
[specific embodiment]
To make the objectives, technical solutions, and advantages of the present invention clearer, right in the following with reference to the drawings and specific embodiments
The present invention is described in detail.
Fig. 1 is the flow chart of voice interactive method embodiment of the invention.As shown in Figure 1, the interactive voice of the present embodiment
Method can specifically include following steps:
S100, the phonetic order for receiving user；
The executing subject of the voice interactive method of the present embodiment is for realizing interactive smart machine with user.Example
Such as, the voice interactive method of the present embodiment can be adapted in the scenes such as smart home and car networking.For example, user can lead to
It crosses to intelligent sound box, intelligent appliance, intelligent electric lamp, Intelligent extension socket, the sweeping robot etc. in smart home product, using language
The mode of sound interaction, which is realized, to be controlled it, such as switch control, adjusting control and information inquiry.Similarly, join in vehicle
In net, user can control switch air-conditioning, switch broadcast, adjusting temperature, handoff radio and official communication by way of interactive voice
Interrogate etc..In all interactive voices, user issues phonetic order, and smart machine receives the phonetic order of user, and
Phonetic order based on user realizes the control to smart machine.
S101, according to preset rules, detect whether phonetic order needs cloud to be handled；If not needing, step is executed
S102；Otherwise, if desired, execute step S103；
In conjunction with above-mentioned various forms of controls, it can analyze and obtain, the control to be realized of some phonetic orders does not need to send out
Send to cloud, certain computing capability assigned if smart machine, which also can voluntarily be handled, such as switch control and
Adjust control.And the control to be realized of some phonetic orders such as information inquiry etc., then it has to be sent to cloud and is handled.Base
In above-mentioned thought, the present embodiment, it can detect whether phonetic order needs cloud to be handled according to preset rules.Without
With as the prior art, all phonetic order unifications are all sent to cloud and are handled, to overcome smart machine and cloud
Between Network status it is bad when, smart machine still be able to provide part of speech interactive service.
For example, step S101 detects whether phonetic order needs at cloud according to preset rules in the present embodiment
Reason, can specifically include the following two kinds implementation:
The first implementation, may include steps of:
(a) using intention assessment model trained in advance, the corresponding intention of identification phonetic order；
(b) rule is handled according to pre-set intention and be intended to, whether identification phonetic order needs cloud to handle.
In the first implementation, an intention assessment model can be trained in advance, which can know
The intention of the phonetic order of other user.In the present embodiment, intentional processing rule is also preset.It according to demand, specifically can be with
A plurality of intention processing rule is set.It may include the phonetic order for being intended to and handling the intention in every intention processing rule
Actuating station.In actual scene, handle the phonetic order of intention actuating station can for cloud, or smart machine end,
It can also be jointly processed by for cloud+smart machine end.For example, for today weather how etc information inquiry, need cloud
End is individually handled；Control, radio station switching control etc. are adjusted for the switch control, volume control, temperature of smart machine side
It is individually handled at smart machine end；For needing to inquire the navigation with road conditions, smart machine side is not only needed
Electronic map is supported, it is also necessary to which the road conditions that front is obtained from cloud need cloud+smart machine end to be jointly processed by this time.
When specifically used, by voice command input to being intended to extract in model, which extracts model can be from the voice
Its intention is extracted in instruction.Then rule, the corresponding phonetic order of the available intention are handled according to pre-set intention
Actuating station, and then can identify whether corresponding phonetic order needs cloud to handle based on the identification end got.
Or in the present embodiment, it is intended that extracting model can also be based on literal order training.It specifically, can be with when use
Speech recognition first is carried out to the phonetic order received in smart machine side, corresponding literal order is obtained, then again by text
Instruction input, by being intended to extract model according to literal order, extracts corresponding intention to being intended to extract in model.
In the present embodiment, several training datas can be acquired in advance, may include the training of acquisition in every training data
Phonetic order and the corresponding intention marked.It, should by every trained voice command input to being intended to extract in model when training
Intention lifts model prediction and exports the corresponding intention of training phonetic order.Then the intention and the intention of mark of prediction are compared
Whether consistent, if inconsistent, adjustment is intended to extract the parameter of model, so that the intention of prediction is consistent with the intention of mark.Using
Several training datas constantly extract model to intention and are trained in the manner described above, until frequency of training reaches preset
In frequency threshold value or again continuous preset times training, the intention of prediction is consistent with the intention of mark always, and training terminates,
It determines the parameter for being intended to extract model, and then determines and be intended to extract model.
The item number of training data in the present embodiment can achieve million orders of magnitude or more, including training data it is more,
It is more accurate that trained intention extracts model.
Similarly, it is realized if being intended to extraction model using literal order, speech recognition is carried out to every trained phonetic order,
Be converted to literal order.Remaining training method is the same, and details are not described herein.
Second of implementation, may include steps of:
(1) speech recognition is carried out to phonetic order, obtains corresponding literal order；
(2) table and literal order are handled according to preset rules, and whether identification literal order needs cloud to handle.
Unlike the first above-mentioned implementation, in this implementation, rule process table can be preset, such as
Literal order and the corresponding actuating station of literal order can be set in the rule process table.Text in rule process table refers to
It enables as by acquiring existing all phonetic orders, row text of going forward side by side is converted to.The wherein corresponding actuating station of literal order
It is identical with the first above-mentioned implementation, it can be cloud or smart machine end, can also be that cloud+intelligence is set
Standby end is jointly processed by.Remaining is identical as the first above-mentioned implementation, in detail can be with reference in the first above-mentioned implementation
It records, details are not described herein.
One of implementation can be selected to execute in a manner of selecting one in practical application.Alternatively, optionally, it can also
Based on second of implementation, supplemented by the first implementation.Specifically, it can first be held according to second of implementation
Row, if there is no the corresponding literal order of corresponding phonetic order in rule process table in second of implementation, according still further to
The first implementation is handled.
S102, phonetic order is executed by local control module, generated and to user feedback response message；Terminate.
In the present embodiment, the control module with computing capability can be set in smart machine, for smart machine tax
Computing capability is given, enables smart machine that there is computing capability.In this way, smart machine can pass through local control module pair
Phonetic order carries out speech recognition, natural language understanding and semantic analysis etc., so as to identify and further execute voice
Instruction.And corresponding response message can also be generated；Then to the user feedback response message.
For example, phonetic order is to turn on the switch, improve volume, open vehicle window, open radio station etc. instruction, these are similar
Phonetic order can be identified and be executed by the control module of smart machine local, and generate corresponding response message, concurrently
Give user.In the present embodiment, the response message of generation, which is mainly used for responding in implementing result, such as response message, may include
The result for the phonetic order that the responses such as switch has been opened, volume has been turned up, vehicle window has been opened, radio station has been opened execute.
S103, the intensity for obtaining network signal；
S104, according to the intensity of pre-set signal strength recognition rule and network signal, whether identify network signal
By force；If network signal is strong, step S105 is executed；If network signal is weak, step S111 is executed；
In the present embodiment, if desired when cloud processing phonetic order, the net that smart machine is communicated with cloud can be first obtained
The intensity of network signal.It is then based on pre-set signal strength recognition rule, judges that network signal is strong or weak.For example, can
A signal strength threshold is arranged, it is greater than the signal strength threshold, then it is assumed that signal strength is strong, otherwise it is assumed that signal strength
It is weak.
S105, directly to cloud send phonetic order；Execute step S106；
S106, the feedback information that cloud is sent is received；Execute step S107；
If network signal is strong, phonetic order directly can be sent to cloud, at this point it is possible to according to the place in existing cloud
Reason mode, such as the processing and speech synthesis work of speech recognition, natural language understanding, semanteme and dialogue are carried out to phonetic order
Make, then issues the feedback informations such as the words of the reply for responding user art, audio and control instruction to smart machine.
Whether S107, detection phonetic order also need processing locality；If it remains desirable that executing step S108；If not needing, hold
Row step S110；
S108, phonetic order is executed by local control module, generates corresponding response message；
S109, by feedback information that cloud is sent and locally the response message that returns merges together, returns to user, ties
Beam.
As can be seen from the above embodiments, the phonetic order of the present embodiment is it is also possible to need smart machine and cloud while locating
Reason.Therefore, after the feedback information for receiving cloud return, further according to the same detection mode of above-mentioned steps S101,
Whether detection phonetic order also needs processing locality.If desired, phonetic order is executed by local control module, generated corresponding
Response message；And by feedback information that cloud is sent and locally the response message that returns merges together, returns to user.
S110, the feedback information that cloud is sent is returned to user, terminated.
If detecting that phonetic order does not need processing locality for step S107, at this point it is possible to directly return to cloud to user
Hold the feedback information sent.For example, smart machine is after testing and true after the phonetic order of user's sending " today, how much is temperature "
The fixed phonetic order needs cloud individually to handle, and when network signal is preferable, the phonetic order is directly sent to cloud, by
Cloud gets answer, and returns to smart machine.Handled at this time due to only needing cloud, smart machine can directly to
Family returns to the feedback information that cloud is sent.
Whether S111, detection phonetic order only need cloud to handle；If so, executing step S112；Otherwise, step is executed
S113；
S112, carrying Network Abnormal is generated, the prompt information of result can not be obtained, and return to user, terminated；
If S113, phonetic order also need to locally execute, the sound returned after phonetic order is executed by local control module
Information is answered, and returns to user, is terminated.
It, at this time can be directly to user if the phonetic order only needs cloud to handle when weak for network signal
Network Abnormal is returned, the prompt information of result can not be obtained.And if also need local smart machine to execute, at this time can only by
Local control module executes phonetic order, generates and to user's returning response information.
The voice interactive method of the present embodiment, by using above-mentioned technical proposal, smart machine has certain calculating energy
Power is detected by the phonetic order to user, can be directly in smart machine for the phonetic order without cloud processing
Locally complete, in this way, even if when network environment is unstable smart machine can be performed locally phonetic order, and
It engages in the dialogue in time with user, not will cause dialogue time delay, so as to effectively improve the dialogue energy of smart machine and user
Power.Moreover, directly being locally executed in smart machine for the phonetic order without cloud processing, additionally it is possible at further shortening
Time delay is managed, the usage experience of user is enhanced.
Fig. 2 is the structure chart of smart machine embodiment one of the invention.As shown in Fig. 2, the smart machine of the present embodiment, tool
Body may include:
Receiving module 10 is used to receive the phonetic order of user；
Detection module 11 is used for according to preset rules, detect the received phonetic order of receiving module 10 whether need cloud into
Row processing；
If 12 detection module 11 of control module, which determines, does not need cloud processing, be performed locally phonetic order, generate and to
User feedback response message.
The smart machine of the present embodiment realizes the realization principle and technical effect of interactive voice by using above-mentioned module
It is identical as the realization of above-mentioned related method embodiment, the record of above-mentioned related method embodiment can be referred in detail, herein no longer
It repeats.
Fig. 3 is the structure chart of smart machine embodiment two of the invention.As shown in figure 3, the smart machine of the present embodiment, In
On the basis of the technical solution of embodiment described in above-mentioned Fig. 2, technical solution of the present invention is further introduced in further detail.
In the smart machine of the present embodiment, detection module 11 is specifically used for:
Using intention assessment model trained in advance, the corresponding intention of identification phonetic order；
Rule is handled according to pre-set intention and is intended to, and whether identification phonetic order needs cloud to handle.
Or optionally, in the smart machine of the present embodiment, detection module 11 is specifically used for:
Speech recognition is carried out to phonetic order, obtains corresponding literal order；
Table and literal order are handled according to preset rules, and whether identification literal order needs cloud to handle.
As shown in figure 3, further including obtaining module 13 and transmission mould in the smart machine of the present embodiment still optionally further
Block 14；
It needs cloud to handle for the determination of detection module 11 if obtaining module 13, obtains the intensity of network signal；
Detection module 11 is also used to according to pre-set signal strength recognition rule and obtains the network of the acquisition of module 13
Whether the intensity of signal, identification network signal are strong；
If sending module 14 detects that network signal is strong for detection module 11, the triggering of examined module 11, directly to
Cloud sends phonetic order；
Receiving module 10 is also used to receive the feedback information of cloud transmission.
As shown in figure 3, further including Fusion Module 15 in the smart machine of the present embodiment still optionally further；
Detection module 11 is also used to detect whether the received phonetic order of receiving module 10 also needs processing locality；
If control module 12 also needs processing locality for the determination of detection module 11, it is performed locally phonetic order, is generated
Corresponding response message；
Fusion Module 15 is used to obtain feedback information and control module 12 that the cloud that receiving module 10 receives is sent
The response message locally returned merge together, return to user；
If sending module 14 is also used to detection module 11, determination does not need processing locality, returns to the anti-of cloud transmission to user
Feedforward information.
Still optionally further, in the smart machine of the present embodiment:
If detection module 11 is also used to detect that network signal is weak, whether detection phonetic order only needs cloud to handle；
If control module 12 is also used to detection module 11, determination is only cloud to be needed to handle, and generates and carries Network Abnormal, nothing
Method obtains the prompt information of result, and returns to user；
If control module 12 also needs to locally execute for detecting the received phonetic order of receiving module 10, it is performed locally
Phonetic order generates and to user's returning response information.
The smart machine of the present embodiment realizes the realization principle and technical effect of interactive voice by using above-mentioned module
It is identical as the realization of above-mentioned related method embodiment, the record of above-mentioned related method embodiment can be referred in detail, herein no longer
It repeats.
The smart machine of the present embodiment can be any smart machine in smart home, intelligent vehicle net, herein no longer
Citing repeats one by one.
Fig. 4 is the structure chart of computer equipment embodiment of the invention.As shown in figure 4, the computer equipment of the present embodiment,
It include: one or more processors 30 and memory 40, memory 40 works as memory for storing one or more programs
The one or more programs stored in 40 are executed by one or more processors 30, so that one or more processors 30 are realized such as
The voice interactive method of figure 1 above illustrated embodiment.In embodiment illustrated in fig. 4 for including multiple processors 30.
For example, Fig. 5 is a kind of exemplary diagram of computer equipment provided by the invention.Fig. 5, which is shown, to be suitable for being used to realizing this
The block diagram of the exemplary computer device 12a of invention embodiment.The computer equipment 12a that Fig. 5 is shown is only an example,
Should not function to the embodiment of the present invention and use scope bring any restrictions.
As shown in figure 5, computer equipment 12a is showed in the form of universal computing device.The component of computer equipment 12a can
To include but is not limited to: one or more processor 16a, system storage 28a connect different system components (including system
Memory 28a and processor 16a) bus 18a.
Bus 18a indicates one of a few class bus structures or a variety of, including memory bus or Memory Controller,
Peripheral bus, graphics acceleration port, processor or the local bus using any bus structures in a variety of bus structures.It lifts
For example, these architectures include but is not limited to industry standard architecture (ISA) bus, microchannel architecture (MAC)
Bus, enhanced isa bus, Video Electronics Standards Association (VESA) local bus and peripheral component interconnection (PCI) bus.
Computer equipment 12a typically comprises a variety of computer system readable media.These media can be it is any can
The usable medium accessed by computer equipment 12a, including volatile and non-volatile media, moveable and immovable Jie
Matter.
System storage 28a may include the computer system readable media of form of volatile memory, such as deposit at random
Access to memory (RAM) 30a and/or cache memory 32a.Computer equipment 12a may further include it is other it is removable/
Immovable, volatile/non-volatile computer system storage medium.Only as an example, storage system 34a can be used for reading
Write immovable, non-volatile magnetic media (Fig. 5 do not show, commonly referred to as " hard disk drive ").Although being not shown in Fig. 5,
The disc driver for reading and writing to removable non-volatile magnetic disk (such as " floppy disk ") can be provided, and non-easy to moving
The CD drive that the property lost CD (such as CD-ROM, DVD-ROM or other optical mediums) is read and write.In these cases, each
Driver can be connected by one or more data media interfaces with bus 18a.System storage 28a may include at least
One program product, the program product have one group of (for example, at least one) program module, these program modules are configured to hold
The function of the above-mentioned each embodiment of Fig. 1-Fig. 3 of the row present invention.
Program with one group of (at least one) program module 42a/utility 40a, can store and deposit in such as system
In reservoir 28a, such program module 42a include --- but being not limited to --- operating system, one or more application program,
It may include the reality of network environment in other program modules and program data, each of these examples or certain combination
It is existing.Program module 42a usually executes the function and/or method in above-mentioned each embodiment of Fig. 1-Fig. 3 described in the invention.
Computer equipment 12a can also be with one or more external equipment 14a (such as keyboard, sensing equipment, display
24a etc.) communication, the equipment interacted with computer equipment 12a communication can be also enabled a user to one or more, and/or
(such as network interface card is adjusted with any equipment for enabling computer equipment 12a to be communicated with one or more of the other calculating equipment
Modulator-demodulator etc.) communication.This communication can be carried out by input/output (I/O) interface 22a.Also, computer equipment
12a can also by network adapter 20a and one or more network (such as local area network (LAN), wide area network (WAN) and/or
Public network, such as internet) communication.As shown, network adapter 20a passes through its of bus 18a and computer equipment 12a
The communication of its module.It should be understood that although not shown in the drawings, other hardware and/or software can be used in conjunction with computer equipment 12a
Module, including but not limited to: microcode, device driver, redundant processor, external disk drive array, RAID system, tape
Driver and data backup storage system etc..
Processor 16a by the program that is stored in system storage 28a of operation, thereby executing various function application and
Data processing, such as realize voice interactive method shown in above-described embodiment.
The present invention also provides a kind of computer-readable mediums, are stored thereon with computer program, which is held by processor
The voice interactive method as shown in above-described embodiment is realized when row.
The computer-readable medium of the present embodiment may include in the system storage 28a in above-mentioned embodiment illustrated in fig. 5
RAM30a, and/or cache memory 32a, and/or storage system 34a.
With the development of science and technology, the route of transmission of computer program is no longer limited by tangible medium, it can also be directly from net
Network downloading, or obtained using other modes.Therefore, the computer-readable medium in the present embodiment not only may include tangible
Medium can also include invisible medium.
The computer-readable medium of the present embodiment can be using any combination of one or more computer-readable media.
Computer-readable medium can be computer-readable signal media or computer readable storage medium.Computer-readable storage medium
Matter for example may be-but not limited to-system, device or the device of electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, or
Any above combination of person.The more specific example (non exhaustive list) of computer readable storage medium includes: with one
Or the electrical connections of multiple conducting wires, portable computer diskette, hard disk, random access memory (RAM), read-only memory (ROM),
Erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light
Memory device, magnetic memory device or above-mentioned any appropriate combination.In this document, computer readable storage medium can
With to be any include or the tangible medium of storage program, the program can be commanded execution system, device or device use or
Person is in connection.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including --- but
It is not limited to --- electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be
Any computer-readable medium other than computer readable storage medium, which can send, propagate or
Transmission is for by the use of instruction execution system, device or device or program in connection.
The program code for including on computer-readable medium can transmit with any suitable medium, including --- but it is unlimited
In --- wireless, electric wire, optical cable, RF etc. or above-mentioned any appropriate combination.
The computer for executing operation of the present invention can be write with one or more programming languages or combinations thereof
Program code, described program design language include object oriented program language-such as Java, Smalltalk, C++,
Further include conventional procedural programming language-such as " C " language or similar programming language.Program code can be with
It fully executes, partly execute on the user computer on the user computer, being executed as an independent software package, portion
Divide and partially executes or executed on a remote computer or server completely on the remote computer on the user computer.In
Be related in the situation of remote computer, remote computer can pass through the network of any kind --- including local area network (LAN) or
Wide area network (WAN)-be connected to subscriber computer, or, it may be connected to outer computer (such as mentioned using Internet service
It is connected for quotient by internet).
In several embodiments provided by the present invention, it should be understood that disclosed system, device and method can be with
It realizes by another way.For example, the apparatus embodiments described above are merely exemplary, for example, the unit
It divides, only a kind of logical function partition, there may be another division manner in actual implementation.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of hardware adds SFU software functional unit.
The above-mentioned integrated unit being realized in the form of SFU software functional unit can store and computer-readable deposit at one
In storage media.Above-mentioned SFU software functional unit is stored in a storage medium, including some instructions are used so that a computer
It is each that equipment (can be personal computer, server or the network equipment etc.) or processor (processor) execute the present invention
The part steps of embodiment the method.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (Read-
Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic or disk etc. it is various
It can store the medium of program code.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention
Within mind and principle, any modification, equivalent substitution, improvement and etc. done be should be included within the scope of the present invention.
Claims (14)
1. a kind of voice interactive method, which is characterized in that the described method includes:
Receive the phonetic order of user；
According to preset rules, detect whether the phonetic order needs cloud to be handled；
If not needing, the phonetic order is executed by local control module, is generated and to the user feedback response message.
2. the method according to claim 1, wherein detecting whether the phonetic order needs according to preset rules
Cloud is wanted to be handled, comprising:
Using intention assessment model trained in advance, the corresponding intention of the phonetic order is identified；
Rule and the intention are handled according to pre-set intention, identifies whether the phonetic order needs at the cloud
Reason.
3. the method according to claim 1, wherein detecting whether the phonetic order needs according to preset rules
Cloud is wanted to be handled, comprising:
Speech recognition is carried out to the phonetic order, obtains corresponding literal order；
Table and the literal order are handled according to preset rules, identify whether the literal order needs at the cloud
Reason.
4. the method according to claim 1, wherein if desired cloud processing, the method also includes:
Obtain the intensity of network signal；
According to the intensity of pre-set signal strength recognition rule and the network signal, whether the network signal is identified
By force；
If the network signal is strong, the phonetic order directly is sent to the cloud；
And receive the feedback information that the cloud is sent.
5. according to the method described in claim 4, it is characterized in that, and after receiving the feedback information that the cloud is sent, institute
State method further include:
Detect whether the phonetic order also needs processing locality；
If generating the corresponding response message it remains desirable that executing the phonetic order by the local control module；
The response message by the feedback information that the cloud is sent and locally returned merges together, returns to the use
Family；
If not needing, Xiang Suoshu user returns to the feedback information that the cloud is sent.
6. according to the method described in claim 4, it is characterized in that, if the network signal is weak, the method also includes:
Detect whether the phonetic order only needs the cloud to handle；
Network Abnormal is carried if so, generating, the prompt information of result can not be obtained, and return to the user；
Otherwise, if the phonetic order also needs to locally execute, the phonetic order is executed by the local control system, it is raw
User described in Cheng Bingxiang returns to the response message.
7. a kind of smart machine, which is characterized in that the smart machine includes:
Receiving module, for receiving the phonetic order of user；
Detection module, for detecting whether the phonetic order needs cloud to be handled according to preset rules；
Control module is performed locally the phonetic order, generates if the detection module, which determines, does not need the cloud processing
And to the user feedback response message.
8. equipment according to claim 7, which is characterized in that the detection module is used for:
Using intention assessment model trained in advance, the corresponding intention of the phonetic order is identified；
Rule and the intention are handled according to pre-set intention, identifies whether the phonetic order needs at the cloud
Reason.
9. equipment according to claim 7, which is characterized in that the detection module is used for:
Speech recognition is carried out to the phonetic order, obtains corresponding literal order；
Table and the literal order are handled according to preset rules, identify whether the literal order needs at the cloud
Reason.
10. equipment according to claim 7, which is characterized in that the equipment further includes obtaining module and sending module；
The acquisition module needs the cloud processing if determining for the detection module, obtains the intensity of network signal；
The detection module is also used to the intensity according to pre-set signal strength recognition rule and the network signal, knows
Whether the not described network signal is strong；
The sending module directly sends the phonetic order to the cloud if strong for the network signal；
The receiving module is also used to receive the feedback information that the cloud is sent.
11. equipment according to claim 10, which is characterized in that the equipment further includes Fusion Module；
The detection module, is also used to detect whether the phonetic order also needs processing locality；
The control module generates the corresponding sound if being performed locally the phonetic order for also needing processing locality
Answer information；
The Fusion Module, the feedback information for sending the cloud and the response message locally returned are together
Fusion, returns to the user；
The sending module, if being also used to not need processing locality, Xiang Suoshu user returns to the feedback that the cloud is sent
Information.
12. equipment according to claim 10, it is characterised in that:
The detection module detects whether the phonetic order only needs at the cloud if it is weak to be also used to the network signal
Reason；
The control module generates if being also used to that the cloud is only needed to handle and carries Network Abnormal, can not obtain result
Prompt information, and return to the user；
The control module is performed locally the phonetic order if also needing to locally execute for the phonetic order, generates
And the response message is returned to the user.
13. a kind of computer equipment, which is characterized in that the equipment includes:
One or more processors；
Memory, for storing one or more programs；
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
Now such as method as claimed in any one of claims 1 to 6.
14. a kind of computer-readable medium, is stored thereon with computer program, which is characterized in that the program is executed by processor
Shi Shixian method for example as claimed in any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910699941.1A CN110444206A (en) | 2019-07-31 | 2019-07-31 | Voice interactive method and device, computer equipment and readable medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910699941.1A CN110444206A (en) | 2019-07-31 | 2019-07-31 | Voice interactive method and device, computer equipment and readable medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110444206A true CN110444206A (en) | 2019-11-12 |
Family
ID=68432365
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910699941.1A Pending CN110444206A (en) | 2019-07-31 | 2019-07-31 | Voice interactive method and device, computer equipment and readable medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110444206A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111404998A (en) * | 2020-02-27 | 2020-07-10 | 北京三快在线科技有限公司 | Voice interaction method, first electronic device and readable storage medium |
| CN111581919A (en) * | 2020-04-02 | 2020-08-25 | 联想(北京)有限公司 | Task processing method and device |
| CN112309399A (en) * | 2020-10-30 | 2021-02-02 | 上海淇玥信息技术有限公司 | Method and device for executing task based on voice and electronic equipment |
| CN112992145A (en) * | 2021-05-10 | 2021-06-18 | 湖北亿咖通科技有限公司 | Offline online semantic recognition arbitration method, electronic device and storage medium |
| CN113270098A (en) * | 2021-06-22 | 2021-08-17 | 广州小鹏汽车科技有限公司 | Voice control method, vehicle, cloud and storage medium |
| CN113674742A (en) * | 2021-08-18 | 2021-11-19 | 北京百度网讯科技有限公司 | Man-machine interaction method, device, equipment and storage medium |
| CN114005448A (en) * | 2021-12-29 | 2022-02-01 | 广州小鹏汽车科技有限公司 | Voice interaction method and device, model training method, vehicle and storage medium |
| CN114005449A (en) * | 2021-12-29 | 2022-02-01 | 广州小鹏汽车科技有限公司 | Voice interaction method and device, model training method, vehicle and storage medium |
| WO2022143258A1 (en) * | 2020-12-31 | 2022-07-07 | 华为技术有限公司 | Voice interaction processing method and related apparatus |
| WO2022217621A1 (en) * | 2021-04-17 | 2022-10-20 | 华为技术有限公司 | Speech interaction method and apparatus |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150331666A1 (en) * | 2014-05-15 | 2015-11-19 | Tyco Safety Products Canada Ltd. | System and Method for Processing Control Commands in a Voice Interactive System |
| CN105913847A (en) * | 2016-06-01 | 2016-08-31 | 北京灵隆科技有限公司 | Voice control system, user end device, server and central control unit |
| CN106560892A (en) * | 2015-09-30 | 2017-04-12 | 深圳光启合众科技有限公司 | Intelligent robot and cloud side interactive method and cloud side interactive system thereof |
| CN106817144A (en) * | 2017-01-18 | 2017-06-09 | 上海洪洋通信科技有限公司 | Various dimensions robot system |
| CN106992009A (en) * | 2017-05-03 | 2017-07-28 | 深圳车盒子科技有限公司 | Vehicle-mounted voice exchange method, system and computer-readable recording medium |
| CN107430852A (en) * | 2015-05-27 | 2017-12-01 | 谷歌公司 | The selectivity of the online processing of phonetic entry is stopped in the electronic equipment for supporting voice |
| CN107785019A (en) * | 2017-10-26 | 2018-03-09 | 西安Tcl软件开发有限公司 | Mobile unit and its audio recognition method, readable storage medium storing program for executing |
-
2019
- 2019-07-31 CN CN201910699941.1A patent/CN110444206A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150331666A1 (en) * | 2014-05-15 | 2015-11-19 | Tyco Safety Products Canada Ltd. | System and Method for Processing Control Commands in a Voice Interactive System |
| CN107430852A (en) * | 2015-05-27 | 2017-12-01 | 谷歌公司 | The selectivity of the online processing of phonetic entry is stopped in the electronic equipment for supporting voice |
| CN106560892A (en) * | 2015-09-30 | 2017-04-12 | 深圳光启合众科技有限公司 | Intelligent robot and cloud side interactive method and cloud side interactive system thereof |
| CN105913847A (en) * | 2016-06-01 | 2016-08-31 | 北京灵隆科技有限公司 | Voice control system, user end device, server and central control unit |
| CN106817144A (en) * | 2017-01-18 | 2017-06-09 | 上海洪洋通信科技有限公司 | Various dimensions robot system |
| CN106992009A (en) * | 2017-05-03 | 2017-07-28 | 深圳车盒子科技有限公司 | Vehicle-mounted voice exchange method, system and computer-readable recording medium |
| CN107785019A (en) * | 2017-10-26 | 2018-03-09 | 西安Tcl软件开发有限公司 | Mobile unit and its audio recognition method, readable storage medium storing program for executing |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111404998A (en) * | 2020-02-27 | 2020-07-10 | 北京三快在线科技有限公司 | Voice interaction method, first electronic device and readable storage medium |
| CN111581919A (en) * | 2020-04-02 | 2020-08-25 | 联想(北京)有限公司 | Task processing method and device |
| CN111581919B (en) * | 2020-04-02 | 2023-07-21 | 联想(北京)有限公司 | Task processing method and device |
| CN112309399A (en) * | 2020-10-30 | 2021-02-02 | 上海淇玥信息技术有限公司 | Method and device for executing task based on voice and electronic equipment |
| CN112309399B (en) * | 2020-10-30 | 2023-02-24 | 上海淇玥信息技术有限公司 | Method and device for executing task based on voice and electronic equipment |
| WO2022143258A1 (en) * | 2020-12-31 | 2022-07-07 | 华为技术有限公司 | Voice interaction processing method and related apparatus |
| EP4318464A4 (en) * | 2021-04-17 | 2024-05-08 | Huawei Tech Co Ltd | Speech interaction method and apparatus |
| WO2022217621A1 (en) * | 2021-04-17 | 2022-10-20 | 华为技术有限公司 | Speech interaction method and apparatus |
| CN112992145A (en) * | 2021-05-10 | 2021-06-18 | 湖北亿咖通科技有限公司 | Offline online semantic recognition arbitration method, electronic device and storage medium |
| CN112992145B (en) * | 2021-05-10 | 2021-08-06 | 湖北亿咖通科技有限公司 | Offline online semantic recognition arbitration method, electronic device and storage medium |
| CN113270098A (en) * | 2021-06-22 | 2021-08-17 | 广州小鹏汽车科技有限公司 | Voice control method, vehicle, cloud and storage medium |
| CN113674742A (en) * | 2021-08-18 | 2021-11-19 | 北京百度网讯科技有限公司 | Man-machine interaction method, device, equipment and storage medium |
| CN114005449A (en) * | 2021-12-29 | 2022-02-01 | 广州小鹏汽车科技有限公司 | Voice interaction method and device, model training method, vehicle and storage medium |
| CN114005448A (en) * | 2021-12-29 | 2022-02-01 | 广州小鹏汽车科技有限公司 | Voice interaction method and device, model training method, vehicle and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110444206A (en) | Voice interactive method and device, computer equipment and readable medium | |
| JP2021086154A (en) | Method, device, apparatus, and computer-readable storage medium for speech recognition | |
| CN107612968B (en) | The method, equipment and system of its connected device are controlled by intelligent terminal | |
| CN108470034B (en) | A kind of smart machine service providing method and system | |
| CN108133707A (en) | A kind of content share method and system | |
| CN108681440A (en) | A kind of smart machine method for controlling volume and system | |
| EP3564950A1 (en) | Method and apparatus for voiceprint creation and registration | |
| CN108683937A (en) | Interactive voice feedback method, system and the computer-readable medium of smart television | |
| CN107591152B (en) | Voice control method, device and equipment based on earphone | |
| CN108520743A (en) | Sound control method, smart machine and the computer-readable medium of smart machine | |
| CN109918975A (en) | A kind of processing method of augmented reality, the method for Object identifying and terminal | |
| CN107808670A (en) | Voice data processing method, device, equipment and storage medium | |
| CN107516510A (en) | A kind of smart machine automated voice method of testing and device | |
| CN107478237A (en) | Real scene navigation method, device, equipment and computer-readable recording medium | |
| CN110235132A (en) | The mobile device continuously verified is provided based on context aware | |
| CN108459510A (en) | Control method, equipment, system and the computer-readable medium of intelligent appliance | |
| CN110248021A (en) | A kind of smart machine method for controlling volume and system | |
| CN108874895A (en) | Interactive information method for pushing, device, computer equipment and storage medium | |
| CN109346074A (en) | A kind of method of speech processing and system | |
| CN109872723A (en) | Building information processing method and device based on artificial intelligence | |
| CN113436611B (en) | Test method and device for vehicle-mounted voice equipment, electronic equipment and storage medium | |
| CN108564944A (en) | Intelligent control method, system, equipment and storage medium | |
| CN109785846A (en) | The role recognition method and device of the voice data of monophonic | |
| CN109597996A (en) | A kind of semanteme analytic method, device, equipment and medium | |
| CN110110236A (en) | A kind of information-pushing method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191112 |
|
| RJ01 | Rejection of invention patent application after publication |