CN105718239A - Voice input method and device - Google Patents
Voice input method and device Download PDFInfo
- Publication number
- CN105718239A CN105718239A CN201610054745.5A CN201610054745A CN105718239A CN 105718239 A CN105718239 A CN 105718239A CN 201610054745 A CN201610054745 A CN 201610054745A CN 105718239 A CN105718239 A CN 105718239A
- Authority
- CN
- China
- Prior art keywords
- input text
- phonetic entry
- input
- user
- recognition result
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/16—Sound input; Sound output
- G06F3/167—Audio in a user interface, e.g. using voice commands for navigating, audio feedback
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0481—Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
- G06F3/0482—Interaction with lists of selectable items, e.g. menus
-
- 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
Abstract
The invention provides a voice input method and device.The method includes the step of displaying an input text recommend list on a voice input function interface after entering the voice input function interface, wherein the input text recommend list is generated according to a recognition result of user historical voice input.A user can directly select an input text from the input text recommend list after entering the voice input function interface.If the content input by the user through voice already exists in the input text recommend list, voice input does not need to be repeated, and input efficiency is improved; in addition, the method and device can be conveniently used in some non-private environments or environments where speaking is inconvenient.
Description
[technical field]
The present invention relates to Computer Applied Technology field, particularly to the method and apparatus of a kind of phonetic entry.
[background technology]
Along with developing rapidly of smart machine, text input gradually can not meet people and liberate the demand of both hands, phonetic entry and the phonetic search based on phonetic entry and become for one of mutual important way of people and smart machine.
At present, when user needs to carry out phonetic entry, it is necessary to be introduced into speech voice input function interface, as shown in fig. 1, record voice content by long by speech voice input function button, after release button, voice content be identified or further search for.But, when user carries out phonetic entry every time, it is required for saying voice content accurately, even if user had inputted identical voice content in the past, the voice content that even often input is identical, it is still necessary to again by growing the function button by phonetic entry and inputting voice content.On the one hand, this input mode is inefficient, it is necessary to user repeatedly inputs identical voice content；On the other hand, also the use environment of speech voice input function is brought restriction, for instance at non-secret environment such as some bus, coffee-houses etc., or in a meeting, the first-class environment being inconvenient to speak in classroom, just cannot be carried out phonetic entry effectively.
[summary of the invention]
In view of this, the method and apparatus that the invention provides a kind of phonetic entry, in order to improve input efficiency, and reduce the restriction using environment to speech voice input function.
Concrete technical scheme is as follows:
A kind of method that the invention provides phonetic entry, the method includes:
After entering speech voice input function interface, described speech voice input function interface represents input text recommendation list；Wherein said input text recommendation list is that the recognition result according to user's history phonetic entry generates.
According to the present invention one preferred implementation, the method also includes:
Recognition result according to user's history phonetic entry, generates input text recommendation list；Or,
The input text recommendation list that the recognition result according to user's history phonetic entry generates is obtained from service end.
According to the present invention one preferred implementation, the recognition result according to user's history phonetic entry, generate input text recommendation list and include:
Obtain the recognition result record of history phonetic entry；
According to the described user recognition result occurrence number in the history phonetic entry of nearest a period of time, described user is in the recognition result occurrence number of the history phonetic entry of current same period, described user is in the recognition result occurrence number of the history phonetic entry in current same place, all users are in the popular degree of the recognition result of the history phonetic entry of nearest a period of time, in the popular degree of recognition result of history phonetic entry of the current all users in same place and at least one factor in the popular degree of the recognition result of the history phonetic entry of current all users of same period, the recognition result of history phonetic entry is ranked up；
Choosing the recognition result of the history phonetic entry coming front M, constitute described input text recommendation list, wherein M is default positive integer.
According to the present invention one preferred implementation, the method also includes:
One of them input text in described input text recommendation list is in selected state.
According to the present invention one preferred implementation, the method also includes:
When getting the operation that user switches input text, another input text switched in described input text recommendation list is in selected state；
Wherein, input text recommendation list described in the same time can only exist an input text and be in selected state.
According to the present invention one preferred implementation, described in when getting the operation that user switches input text, switch another input text in described input text recommendation list and be in selected state and include:
Get to trigger and be in the user operation of phonetic entry state and the voice quality of input not up to identifying that the duration required reaches preset duration, then the next one input text in order or in the described input text recommendation list of random switching is in selected state；Or,
Get user and click the input text being in unselected state in described input text recommendation list, then the input text that switching user clicks is in selected state.
According to the present invention one preferred implementation, the method also includes:
When getting the operation triggering input text input, input is currently at the input text of selected state.
According to the present invention one preferred implementation, described in get the operation triggering input text input and include:
The voice quality inputted when getting the user operation terminating to be in phonetic entry state is still not up to identifying requirement.
According to the present invention one preferred implementation, the method also includes:
Get the voice quality triggering the user operation and input that are in phonetic entry state to reach to identify requirement, then, when getting the user operation terminating to be in phonetic entry state, the voice of input is identified and inputs recognition result.
According to the present invention one preferred implementation, trigger the user operation being in phonetic entry state and include: pin the speech voice input function button on described speech voice input function interface；
The user operation terminating to be in phonetic entry state includes: unclamp described speech voice input function button.
Present invention also offers the device of a kind of phonetic entry, this device includes:
Recommendation unit, after being used for entering speech voice input function interface, represents input text recommendation list on described speech voice input function interface；
Wherein said input text recommendation list is that the recognition result according to user's history phonetic entry generates.
According to the present invention one preferred implementation, this device also includes: generate unit or acquiring unit；
Described generation unit, for the recognition result according to user's history phonetic entry, generates input text recommendation list；
Described acquiring unit, for obtaining the input text recommendation list that the recognition result according to user's history phonetic entry generates from service end.
According to the present invention one preferred implementation, described generation unit, specifically for:
Obtain the recognition result record of history phonetic entry；
According to the described user recognition result occurrence number in the history phonetic entry of nearest a period of time, described user is in the recognition result occurrence number of the history phonetic entry of current same period, described user is in the recognition result occurrence number of the history phonetic entry in current same place, all users are in the popular degree of the recognition result of the history phonetic entry of nearest a period of time, in the popular degree of recognition result of history phonetic entry of the current all users in same place and at least one factor in the popular degree of the recognition result of the history phonetic entry of current all users of same period, the recognition result of history phonetic entry is ranked up；
Choosing the recognition result of the history phonetic entry coming front M, constitute described input text recommendation list, wherein M is default positive integer.
According to the present invention one preferred implementation, this device also includes:
Selected cell, for making one of them the input text in described input text recommendation list be in selected state.
According to the present invention one preferred implementation, described selected cell, when being additionally operable to get the operation that user switches input text, another input text switched in described input text recommendation list is in selected state；
Wherein, input text recommendation list described in the same time can only exist an input text and be in selected state.
According to the present invention one preferred implementation, described selected cell, specifically for:
Get to trigger and be in the user operation of phonetic entry state and the voice quality of input not up to identifying that the duration required reaches preset duration, then the next one input text in order or in the described input text recommendation list of random switching is in selected state；Or,
Get user and click the input text being in unselected state in described input text recommendation list, then the input text that switching user clicks is in selected state.
According to the present invention one preferred implementation, this device also includes:
First input block, for when getting the operation triggering input text input, input is currently at the input text of selected state.
According to the present invention one preferred implementation, when described first input block gets the user operation terminating to be in phonetic entry state, the voice quality of input is still not up to identifying requirement, it is determined that get the operation triggering input text input.
According to the present invention one preferred implementation, this device also includes:
Second input block, reaches to identify requirement for getting the voice quality triggering the user operation and input that are in phonetic entry state, then, when getting the user operation terminating to be in phonetic entry state, the voice of input is identified and inputs recognition result.
According to the present invention one preferred implementation, trigger the user operation being in phonetic entry state and include: pin the speech voice input function button on described speech voice input function interface；
The user operation terminating to be in phonetic entry state includes: unclamp described speech voice input function button.
As can be seen from the above technical solutions, the present invention utilizes the recognition result of the history phonetic entry of user to generate input text recommendation list, and represent on speech voice input function interface, allow users to after entering speech voice input function interface, from input text recommendation list, directly select input text.If input text recommendation list has existed user originally by the content of phonetic entry, then need not repeat phonetic entry, improve input efficiency；Use it addition, be also convenient in the environment that some non-secret environment or be inconvenient to are spoken.
[accompanying drawing explanation]
The schematic diagram at the speech voice input function interface that Fig. 1 provides for prior art；
A kind of method flow diagram that Fig. 2 provides for the embodiment of the present invention；
The schematic diagram at a kind of speech voice input function interface that Fig. 3 a provides for the embodiment of the present invention；
The schematic diagram of a kind of selected state that Fig. 3 b provides for the embodiment of the present invention；
Fig. 3 c is in the schematic diagram of the input text of selected state for a kind of switching that the embodiment of the present invention provides；
The result schematic diagram of a kind of phonetic entry that Fig. 3 d provides for the embodiment of the present invention；
The result schematic diagram of the another kind of phonetic entry that Fig. 3 e provides for the embodiment of the present invention；
The structure drawing of device that Fig. 4 provides for the embodiment of the present invention.
[detailed description of the invention]
In order to make the object, technical solutions and advantages of the present invention clearly, describe the present invention below in conjunction with the drawings and specific embodiments.
The term used in embodiments of the present invention is only merely for the purpose describing specific embodiment, and is not intended to be limiting the present invention." one ", " described " and " being somebody's turn to do " of the singulative used in the embodiment of the present invention and appended claims is also intended to include most form, unless context clearly shows that other implications.
Should be appreciated that term "and/or" used herein is only a kind of incidence relation describing affiliated partner, can there are three kinds of relations in expression, for instance, A and/or B, it is possible to represent: individualism A, there is A and B, individualism B these three situation simultaneously.It addition, character "/" herein, typically represent forward-backward correlation to as if the relation of a kind of "or".
Depend on linguistic context, word as used in this " if " can be construed to " ... time " or " when ... " or " in response to determining " or " in response to detection ".Similarly, depend on linguistic context, phrase " if it is determined that " or " if detection (condition of statement or event) " " when determining " or " in response to determining " or " when detecting (condition of statement or event) " or " in response to detection (condition of statement or event) " can be construed to.
In the present invention, in order to improve the phonetic entry efficiency of user and carry out the environment of phonetic entry suitable in not aspect, after entering speech voice input function interface, representing input text recommendation list on speech voice input function interface, wherein this input text recommendation list is that the recognition result according to user's history phonetic entry generates.So that user can select the input text in input text recommendation list to input.
Below in conjunction with an embodiment, said method is described in detail.A kind of method flow diagram that Fig. 2 provides for the embodiment of the present invention, as in figure 2 it is shown, the method may comprise steps of:
In 201, the recognition result according to user's history phonetic entry, generate input text recommendation list.
It should be noted that this step can be the step first carried out in advance, it is also possible to be the step performed in real time after entering speech voice input function interface, in the present embodiment to first carry out in advance.
It addition, this step can exist but be not limited to two kinds of implementations:
The first implementation: generated input text recommendation list by the client of phonetic entry.
Client in phonetic entry, it is possible to perform following process:
First, the recognition result record of history phonetic entry is obtained.This record can be the record that client carries out, it is also possible to being the record that carries out of service end, then client obtains to service end.Can also being the recognition result of the history phonetic entry of this user of client records, all users' of service end record be the recognition result of phonetic entry.In record except the recognition result information including ID and phonetic entry, it is also possible to include the attribute information such as such as input time, input place.
Then, according to some factors, the recognition result of history phonetic entry is ranked up.The factor considered when sequence can include but not limited to the one in following factor or combination in any:
Factor 1: this user is in the recognition result occurrence number of the history phonetic entry of nearest a period of time.By this factor, it is possible to the recognition result of voice user frequently entered in nearest a period of time recommends user.It should be noted that what comprise in input text recommendation list is the recognition result of input voice, it is the form of text, so can check to user intuitively.Described a period of time can be one week, one month, 1 year etc., it is possible to arranges flexibly according to demand.Such as user travelled frequently over the mode of phonetic entry in nearest one week and inputs " Beijing weather " and check Pekinese's weather conditions, then " Beijing weather " can put into input text recommendation list.
Factor 2: this user is in the recognition result occurrence number of the history phonetic entry of current same period.By this factor, it is possible to the recognition result of voice user frequently entered in the same period recommends user.Such as, user every morning 8:00～9:00 all can be inputted " Shui Mu community " by the mode of phonetic entry and browse forum, when opening speech voice input function interface within the period of this user 8:00～9:00 in the morning, it is possible to " Shui Mu community " is put into input text recommendation list.
Factor 3: this user is in the recognition result occurrence number of the history phonetic entry in current same place, and the location information that wherein user is currently located can obtain by calling the position location API of subscriber equipment.By this factor, it is possible to the recognition result of voice user frequently entered in same place recommends user.Such as, when user arrives a certain high speed charge station entrance, input " Baidu's map " often through the mode of phonetic entry and check high speed congestion, so when this user arrives this high speed charge station entrance and opens speech voice input function interface, it is possible to " Baidu's map " is put into input text recommendation list.
Factor 4: all users are in the popular degree of the recognition result of the history phonetic entry of nearest a period of time.Client can obtain the recognition result of the popular phonetic entry of comparison that all users input in nearest a period of time from service end, and one or more recognition result is put into input text recommendation list.Such as, in a period of time recently, " the Mi month passes " is relatively popular, and a lot of users input " the Mi month passes " by the mode of phonetic entry and check video, then when user opens speech voice input function interface, it is possible to " the Mi month passes " puts into input text recommendation list.
Factor 5: in the popular degree of recognition result of the history phonetic entry of the current all users in same place.Client can obtain the recognition result of the popular phonetic entry of comparison that all users input in same place from service end, and one or more recognition result is put into input text recommendation list.Equally, the location information that user is currently located can obtain by calling the position location API of subscriber equipment.Such as a certain place is remoter, usual user can input " * * calls a taxi " and use software of calling a taxi when this place carries out phonetic entry, so when user opens speech voice input function interface in this place, it is possible to " * * calls a taxi " is put into input text recommendation list.
Factor 6: in the popular degree of recognition result of the history phonetic entry of current all users of same period.Client can obtain, from service end, the recognition result that comparison that all users input in the same period is popular, and one or more recognition result is put into input text recommendation list.Such as a lot of users can input " weather forecast " when carrying out phonetic entry in the morning between 7:00～8:00 and check weather conditions, so when user opens speech voice input function interface within this time period, it is possible to " weather forecast " is put into input text recommendation list.
Certainly, the present invention is not limited to factor in above-mentioned 6, it is also possible to adopt other because usually the recognition result of history phonetic entry being ranked up, exhaustive no longer one by one at this.It addition, when adopting more than one factor to be ranked up, it is possible to the mode of employing weighting calculates the score value of the recognition result of each history phonetic entry, is ranked up according to score value.
Finally, the recognition result of the history phonetic entry coming front M being constituted input text recommendation list, M is default positive integer.
The second implementation, is generated input text recommendation list by service end, is then handed down to the client of phonetic entry, for client when presenting speech voice input function interface.The method that this implementation adopts is similar with the first implementation with the factor of consideration, is different in that, when considering locality factors, service end needs to obtain the positional information of user from client.
In 202, after getting the instruction entering speech voice input function interface, speech voice input function interface represents input text recommendation list.
Such as shown in Fig. 3 a, after user enters into speech voice input function interface, speech voice input function interface shows the input text of several recommendation: " weather forecast ", " Shui Mu community ", " * * calls a taxi ", " PM2.5 ".
User can select an input text to complete input from input text recommendation list, and user can select input text by long by the mode of certain input text.But in order to adapt with the function on existing phonetic entry interface better, the invention provides a kind of preferred selection mode, detailed below.
In order to facilitate user to select input text, it is possible to when representing, acquiescence makes one of them the input text in input text recommendation list be in selected state.Such as acquiescence first input text is in selected state.When indicating selected state, it is possible to adopt and multiple highlight mode, for instance add boldface type, add big font, add frame etc..As shown in figure 3b, when user enters speech voice input function interface, giving tacit consent to first input text " weather forecast " and be in selected state, the mode of instruction selected state is for adding frame.
But in a lot of situations, user can't select to give tacit consent to the input text being in selected state and input, the demand of switching input text therefore can be produced.In 203, when getting the operation that user switches input text, another input text in switching input text recommendation list is in selected state, can only there is an input text and be in selected state in input of same time text recommendation list.
Wherein user switch input text mode of operation can be varied, enumerate following two at this:
First kind of way: get user and click in input text recommendation list and be in the input text of unselected state, then switch to the input text that user clicks and be in selected state.This mode is easier to understand.But in order to adapt with existing voice input function interface better, it is preferable that the second way.
The second way: get triggering and be in the user operation of phonetic entry state and the voice quality of input not up to identifying that the duration required reaches preset duration, then the next one input text that switching inputs in text recommendation list in order or at random is in selected state.Such as user pins speech voice input function button, thus trigger clients is in phonetic entry state, but the voice quality included and not up to identify requirement, such as voice intensity deficiency or speech intelligibility are not enough, illustrate that user does not input voice, when this situation reaches certain preset duration, such as 1s, then switching next one input text is in selected state, and as illustrated in figure 3 c, switching " Shui Mu community " is in selected state.If the voice quality that user's sustained hold speech voice input function button is not put and inputted is not up to identifying that the duration required reaches 1s again, namely user pins 2s altogether, then continues switching next one input text and is in selected state.
In 204, when getting the operation triggering input text input, input is currently at the input text of selected state.Wherein trigger the voice quality inputted when the operation inputting text input can be the user operation terminating to be in phonetic entry state still not up to identifying requirement.Such as, user pins the voice quality of speech voice input function button and input not up to identifying requirement, just can trigger input when user unclamps speech voice input function button and be currently at the input text of selected state.
Difference according to client kind, inputs the function triggered after being currently at the input text of selected state and differs.Such as, for instant messaging class client, this client can comprise speech voice input function, by the way, if user unclamps speech voice input function button on opportunity shown in Fig. 3 c, just going to the interface shown in Fig. 3 d, namely " Shui Mu community " inputs message as one.
Again such as, for searching class client, this client can comprise speech voice input function, by the way, if user unclamps speech voice input function button on opportunity shown in Fig. 3 c, just going to the interface shown in Fig. 3 e, namely " Shui Mu community " is as the Search Results obtained after query.
It is above the detailed description that method provided by the present invention is carried out, below in conjunction with embodiment, device provided by the present invention is described.
The structure drawing of device that Fig. 4 provides for the embodiment of the present invention, as shown in Figure 4, this device may include that recommendation unit 01, it is also possible to includes generating unit 02 or acquiring unit (not shown)；Can further include selected cell the 03, first input block 04 and the second input block 05.The major function of each component units is as follows:
After recommendation unit 01 is responsible for entrance speech voice input function interface, speech voice input function interface represents input text recommendation list；Wherein input text recommendation list is that the recognition result according to user's history phonetic entry generates.
Wherein, input text recommendation list can be that this device generates, it is also possible to is be handed down to this device after service end generates.It addition, input text recommendation list can previously generate, it is also possible to generate in real time after entering speech voice input function interface.
Generate if input text recommendation list is device, then the generation unit 02 recognition result according to user's history phonetic entry in this device, generate input text recommendation list.
Specifically, generate unit 02 and can obtain the recognition result record of history phonetic entry；Foundation user is in the recognition result occurrence number of the history phonetic entry of nearest a period of time, user is in the recognition result occurrence number of the history phonetic entry of current same period, user is in the recognition result occurrence number of the history phonetic entry in current same place, all users are in the popular degree of the recognition result of the history phonetic entry of nearest a period of time, in the popular degree of recognition result of history phonetic entry of the current all users in same place and at least one factor in the popular degree of the recognition result of the history phonetic entry of current all users of same period, the recognition result of history phonetic entry is ranked up；Choosing the recognition result of the history phonetic entry coming front M, constitute input text recommendation list, wherein M is default positive integer.
Generate if input text recommendation list is service end, then acquiring unit obtains, from service end, the input text recommendation list that the recognition result according to user's history phonetic entry generates.It is similar with the mode of above-mentioned generation unit 02 generation input text recommendation list that service end generates the mode of input text recommendation list, does not repeat them here.
In order to facilitate user to select input text, selected cell 03 can make one of them the input text in input text recommendation list be in selected state.Such as can give tacit consent to first input text when entering speech voice input function interface and be in selected state.When indicating selected state, it is possible to adopt and multiple highlight mode, for instance add boldface type, add big font, add frame etc..
But in a lot of situations, user can't select to give tacit consent to the input text being in selected state and input, the demand of switching input text therefore can be produced.When selected cell 03 gets the operation that user switches input text, it is possible to another input text in switching input text recommendation list is in selected state；Wherein, input of same time text recommendation list can only exist an input text and be in selected state.
Wherein user switch input text mode of operation can be varied, enumerate two kinds at this:
First kind of way: selected cell 03 gets to trigger and is in the user operation of phonetic entry state and the voice quality of input not up to identifying that the duration required reaches preset duration, then the next one input text in order or in random switching input text recommendation list is in selected state.
The second way: selected cell 03 gets user and clicks the input text being in unselected state in input text recommendation list, then the input text that switching user clicks is in selected state.
Preferred above-mentioned first kind of way.
When getting the operation triggering input text input, the first input block 04, input is currently at the input text of selected state.Wherein the first input block 04 gets the voice quality of input during the user operation terminating to be in phonetic entry state and still not up to identifying requirement, then may determine that the operation getting triggering input text input.
If getting the voice quality triggering the user operation and input that are in phonetic entry state to reach to identify requirement, then the second input block 05 can confirm that user has phonetic entry demand really, it is at input voice, therefore, when getting the user operation terminating to be in phonetic entry state, the voice of input is identified and inputs recognition result.
Above-mentioned triggering is in the user operation of phonetic entry state and may include that the speech voice input function button pinned on speech voice input function interface；Terminate to be in the user operation of phonetic entry state to may include that and unclamp speech voice input function button.
The said apparatus that the embodiment of the present invention provides can be in the application of user terminal, or can also be plug-in unit or the SDK (SoftwareDevelopmentKit of the application being arranged in user terminal, the functional unit such as SDK), this is not particularly limited by the embodiment of the present invention.
By above description it can be seen that method and apparatus provided by the invention can possess advantages below:
1) present invention utilizes the recognition result of the history phonetic entry of user to generate input text recommendation list, and represent on speech voice input function interface, allow users to after entering speech voice input function interface, from input text recommendation list, directly select input text.If input text recommendation list has existed user originally by the content of phonetic entry, then need not repeat phonetic entry, improve input efficiency；Use it addition, be also convenient in the environment that some non-secret environment or be inconvenient to are spoken.
2) can be in voice mode in the present invention, according to the nearest phonetic entry record of user, the phonetic entry record of user's specific time period, the phonetic entry record of user locality, current device some popular phonetic entries etc. generate input text recommendation list, cater to the phonetic entry demand of user as much as possible.
In several embodiments provided by the present invention, it should be understood that disclosed apparatus and method, it is possible to realize by another way.Such as, device embodiment described above is merely schematic, for instance, the division of described unit, it is only a kind of logic function and divides, actual can have other dividing mode when realizing.
The described unit illustrated as separating component can be or may not be physically separate, and the parts shown as unit can be or may not be physical location, namely may be located at a place, or can also be distributed on multiple NE.Some or all of unit therein can be selected according to the actual needs to realize the purpose of the present embodiment scheme.
It addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, it is also possible to be that unit is individually physically present, it is also possible to two or more unit are integrated in a unit.Above-mentioned integrated unit both can adopt the form of hardware to realize, it would however also be possible to employ hardware adds the form of SFU software functional unit and realizes.
The above-mentioned integrated unit realized with the form of SFU software functional unit, it is possible to be stored in a computer read/write memory medium.Above-mentioned SFU software functional unit is stored in a storage medium, including some instructions with so that a computer equipment (can be personal computer, server, or the network equipment etc.) or processor (processor) perform the part steps of method described in each embodiment of the present invention.And aforesaid storage medium includes: USB flash disk, portable hard drive, read only memory (Read-OnlyMemory, ROM), the various media that can store program code such as random access memory (RandomAccessMemory, RAM), magnetic disc or CD.
The foregoing is only presently preferred embodiments of the present invention, not in order to limit the present invention, all within the spirit and principles in the present invention, any amendment of making, equivalent replacement, improvement etc., should be included within the scope of protection of the invention.
Claims (20)
1. the method for a phonetic entry, it is characterised in that the method includes:
After entering speech voice input function interface, described speech voice input function interface represents input text recommendation list；Wherein said input text recommendation list is that the recognition result according to user's history phonetic entry generates.
2. method according to claim 1, it is characterised in that the method also includes:
Recognition result according to user's history phonetic entry, generates input text recommendation list；Or,
The input text recommendation list that the recognition result according to user's history phonetic entry generates is obtained from service end.
3. method according to claim 2, it is characterised in that the recognition result according to user's history phonetic entry, generates input text recommendation list and includes:
Obtain the recognition result record of history phonetic entry；
According to the described user recognition result occurrence number in the history phonetic entry of nearest a period of time, described user is in the recognition result occurrence number of the history phonetic entry of current same period, described user is in the recognition result occurrence number of the history phonetic entry in current same place, all users are in the popular degree of the recognition result of the history phonetic entry of nearest a period of time, in the popular degree of recognition result of history phonetic entry of the current all users in same place and at least one factor in the popular degree of the recognition result of the history phonetic entry of current all users of same period, the recognition result of history phonetic entry is ranked up；
Choosing the recognition result of the history phonetic entry coming front M, constitute described input text recommendation list, wherein M is default positive integer.
4. method according to claim 1, it is characterised in that the method also includes:
One of them input text in described input text recommendation list is in selected state.
5. method according to claim 4, it is characterised in that the method also includes:
When getting the operation that user switches input text, another input text switched in described input text recommendation list is in selected state；
Wherein, input text recommendation list described in the same time can only exist an input text and be in selected state.
6. method according to claim 5, it is characterised in that described in when getting the operation that user switches input text, another input text switched in described input text recommendation list is in selected state and includes:
Get to trigger and be in the user operation of phonetic entry state and the voice quality of input not up to identifying that the duration required reaches preset duration, then the next one input text in order or in the described input text recommendation list of random switching is in selected state；Or,
Get user and click the input text being in unselected state in described input text recommendation list, then the input text that switching user clicks is in selected state.
7. method according to claim 4, it is characterised in that the method also includes:
When getting the operation triggering input text input, input is currently at the input text of selected state.
8. method according to claim 7, it is characterised in that described in get trigger input text input operation include:
The voice quality inputted when getting the user operation terminating to be in phonetic entry state is still not up to identifying requirement.
9. method according to claim 1, it is characterised in that the method also includes:
Get the voice quality triggering the user operation and input that are in phonetic entry state to reach to identify requirement, then, when getting the user operation terminating to be in phonetic entry state, the voice of input is identified and inputs recognition result.
10. the method according to claim 6,8 or 9, it is characterised in that trigger the user operation being in phonetic entry state and include: pin the speech voice input function button on described speech voice input function interface；
The user operation terminating to be in phonetic entry state includes: unclamp described speech voice input function button.
11. the device of a phonetic entry, it is characterised in that this device includes:
Recommendation unit, after being used for entering speech voice input function interface, represents input text recommendation list on described speech voice input function interface；
Wherein said input text recommendation list is that the recognition result according to user's history phonetic entry generates.
12. device according to claim 11, it is characterised in that this device also includes: generate unit or acquiring unit；
Described generation unit, for the recognition result according to user's history phonetic entry, generates input text recommendation list；
Described acquiring unit, for obtaining the input text recommendation list that the recognition result according to user's history phonetic entry generates from service end.
13. device according to claim 12, it is characterised in that described generation unit, specifically for:
Obtain the recognition result record of history phonetic entry；
According to the described user recognition result occurrence number in the history phonetic entry of nearest a period of time, described user is in the recognition result occurrence number of the history phonetic entry of current same period, described user is in the recognition result occurrence number of the history phonetic entry in current same place, all users are in the popular degree of the recognition result of the history phonetic entry of nearest a period of time, in the popular degree of recognition result of history phonetic entry of the current all users in same place and at least one factor in the popular degree of the recognition result of the history phonetic entry of current all users of same period, the recognition result of history phonetic entry is ranked up；
Choosing the recognition result of the history phonetic entry coming front M, constitute described input text recommendation list, wherein M is default positive integer.
14. device according to claim 11, it is characterised in that this device also includes:
Selected cell, for making one of them the input text in described input text recommendation list be in selected state.
15. device according to claim 14, it is characterised in that described selected cell, when being additionally operable to get the operation that user switches input text, another input text switched in described input text recommendation list is in selected state；
Wherein, input text recommendation list described in the same time can only exist an input text and be in selected state.
16. device according to claim 15, it is characterised in that described selected cell, specifically for:
Get to trigger and be in the user operation of phonetic entry state and the voice quality of input not up to identifying that the duration required reaches preset duration, then the next one input text in order or in the described input text recommendation list of random switching is in selected state；Or,
Get user and click the input text being in unselected state in described input text recommendation list, then the input text that switching user clicks is in selected state.
17. device according to claim 14, it is characterised in that this device also includes:
First input block, for when getting the operation triggering input text input, input is currently at the input text of selected state.
18. device according to claim 17, it is characterised in that when described first input block gets the user operation terminating to be in phonetic entry state, the voice quality of input is still not up to identifying requirement, it is determined that get the operation triggering input text input.
19. device according to claim 11, it is characterised in that this device also includes:
Second input block, reaches to identify requirement for getting the voice quality triggering the user operation and input that are in phonetic entry state, then, when getting the user operation terminating to be in phonetic entry state, the voice of input is identified and inputs recognition result.
20. according to the device described in claim 16,18 or 19, it is characterised in that trigger the user operation being in phonetic entry state and include: pin the speech voice input function button on described speech voice input function interface；
The user operation terminating to be in phonetic entry state includes: unclamp described speech voice input function button.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610054745.5A CN105718239B (en) | 2016-01-27 | 2016-01-27 | A kind of method and apparatus of voice input |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610054745.5A CN105718239B (en) | 2016-01-27 | 2016-01-27 | A kind of method and apparatus of voice input |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105718239A true CN105718239A (en) | 2016-06-29 |
| CN105718239B CN105718239B (en) | 2019-03-08 |
Family
ID=56154304
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610054745.5A Active CN105718239B (en) | 2016-01-27 | 2016-01-27 | A kind of method and apparatus of voice input |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105718239B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107093426A (en) * | 2017-04-26 | 2017-08-25 | 医惠科技有限公司 | The input method of voice, apparatus and system |
| CN107168676A (en) * | 2017-03-29 | 2017-09-15 | 联想(北京)有限公司 | A kind of information output method and its device |
| CN109471537A (en) * | 2017-09-08 | 2019-03-15 | 腾讯科技（深圳）有限公司 | Pronunciation inputting method, device, computer equipment and storage medium |
| CN110347996A (en) * | 2019-07-15 | 2019-10-18 | 北京百度网讯科技有限公司 | Amending method, device, electronic equipment and the storage medium of text |
| CN113220175A (en) * | 2016-12-30 | 2021-08-06 | 谷歌有限责任公司 | Virtual assistant generation of group recommendations |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090327263A1 (en) * | 2008-06-25 | 2009-12-31 | Yahoo! Inc. | Background contextual conversational search |
| CN104462262A (en) * | 2014-11-21 | 2015-03-25 | 北京奇虎科技有限公司 | Method and device for achieving voice search and browser client side |
| CN105117195A (en) * | 2015-09-09 | 2015-12-02 | 百度在线网络技术（北京）有限公司 | Method and device for guiding voice input |
| CN105159930A (en) * | 2015-08-05 | 2015-12-16 | 百度在线网络技术（北京）有限公司 | Search keyword pushing method and apparatus |
-
2016
- 2016-01-27 CN CN201610054745.5A patent/CN105718239B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090327263A1 (en) * | 2008-06-25 | 2009-12-31 | Yahoo! Inc. | Background contextual conversational search |
| CN104462262A (en) * | 2014-11-21 | 2015-03-25 | 北京奇虎科技有限公司 | Method and device for achieving voice search and browser client side |
| CN105159930A (en) * | 2015-08-05 | 2015-12-16 | 百度在线网络技术（北京）有限公司 | Search keyword pushing method and apparatus |
| CN105117195A (en) * | 2015-09-09 | 2015-12-02 | 百度在线网络技术（北京）有限公司 | Method and device for guiding voice input |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113220175A (en) * | 2016-12-30 | 2021-08-06 | 谷歌有限责任公司 | Virtual assistant generation of group recommendations |
| CN107168676A (en) * | 2017-03-29 | 2017-09-15 | 联想(北京)有限公司 | A kind of information output method and its device |
| CN107093426A (en) * | 2017-04-26 | 2017-08-25 | 医惠科技有限公司 | The input method of voice, apparatus and system |
| CN109471537A (en) * | 2017-09-08 | 2019-03-15 | 腾讯科技（深圳）有限公司 | Pronunciation inputting method, device, computer equipment and storage medium |
| CN110347996A (en) * | 2019-07-15 | 2019-10-18 | 北京百度网讯科技有限公司 | Amending method, device, electronic equipment and the storage medium of text |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105718239B (en) | 2019-03-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9195645B2 (en) | Generating string predictions using contexts | |
| US8037070B2 (en) | Background contextual conversational search | |
| CN105718239A (en) | Voice input method and device | |
| US8238528B2 (en) | Automatic analysis of voice mail content | |
| US20120290303A1 (en) | Speech recognition system and method based on word-level candidate generation | |
| WO2017036047A1 (en) | Information extraction method and information extraction device | |
| CN102945243B (en) | A kind of contact details recognition methods based on browsing content | |
| US9298274B2 (en) | String predictions from buffer | |
| KR20200006107A (en) | Obtain response information from multiple corpus | |
| CN110888990A (en) | Text recommendation method, device, equipment and medium | |
| CN102984050A (en) | Method, client and system for searching voices in instant messaging | |
| US20100114930A1 (en) | Situation-aware, interest based search query generation | |
| CN107168599B (en) | Instant messaging method and device | |
| CN108334388B (en) | Session background process method, apparatus, computer equipment and storage medium | |
| CN108108249A (en) | Data inputting method and device | |
| CN108710682B (en) | Object recommendation method, device and equipment | |
| CN113011169A (en) | Conference summary processing method, device, equipment and medium | |
| CN109521888A (en) | A kind of input method, device and medium | |
| CN110659406B (en) | Searching method and device | |
| CN116541114A (en) | Information display method, device, computer equipment and storage medium | |
| CN104202482B (en) | A kind of communications records treatment facility, method and mobile terminal | |
| CN104965633A (en) | Service jumping method and apparatus | |
| CN113535940A (en) | Event abstract generation method and device and electronic equipment | |
| CN105450510A (en) | Friend management method, device and server for social network platform | |
| CN109815277B (en) | Retrieval display method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |