CN104035551A - Input method and electronic device - Google Patents
Input method and electronic device Download PDFInfo
- Publication number
- CN104035551A CN104035551A CN201310074783.3A CN201310074783A CN104035551A CN 104035551 A CN104035551 A CN 104035551A CN 201310074783 A CN201310074783 A CN 201310074783A CN 104035551 A CN104035551 A CN 104035551A
- Authority
- CN
- China
- Prior art keywords
- candidate target
- input
- candidate
- score
- display unit
- 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
Abstract
The invention provides an input method and an electronic device. The method is applied to the electronic device. The electronic device comprises a display unit. The method includes that first input information which is input by a first input mode is obtained; voice input information which is input by a voice input mode is obtained; the first input information is processed to determine M candidate objects; the voice input information is recognized to determine N candidate objects which are matched with the voice input information; M and N are integral numbers which are larger than or equal to 1; the same first candidate object is determined on the basis of the M candidate objects and the N candidate objects; the first candidate object serves as a first choice to be displayed on the display unit.
Description
Technical field
The present invention relates to electronic technology field, relate in particular to a kind of input method and electronic equipment.
Background technology
Along with the development of electronic device technology, various electronic equipments have entered user's life, and for example mobile phone, notebook computer, panel computer, bring great convenience to people's life.
For can be in the input of the enterprising style of writing word of these electronic equipments, electronic equipment has all been equipped with keyboard conventionally, the keyboard of some product is exactly simply software simulation to the keyboard interface on the display unit of respective electronic equipment, be applicable to the input method of keyboard, normally spelling input method or five-stroke input method.Along with scientific and technical development, input device is also in fast development, for allow not can phonetic and the user of five-stroke input method also can carry out word input, just developed the mode of handwriting input, on a touch pad, as writing on paper, input; Along with the development of speech recognition technology, developed again the mode of phonetic entry.
Yet, in the process of the technical scheme of the inventor in realizing the embodiment of the present invention, find, by keyboard, input and conventionally need to press many buttons and just can reach, although the input method of current a kind of association type prevailing, for example want input " patent " two words, if spelling input method, conventionally as long as just can there is " here " by " z " of lower keyboard and " l ", " patent ", candidate targets such as " instructions ", although but this mode has been simplified the program of input, most words can both be completed with less button, if but last possible combination is a lot, and during the candidate target that preference is not user to be wanted, also to choose one by one by upper and lower key, and for Chinese, English and digital different mode will manually switch.
And for handwriting input and phonetic entry, although do not need to carry out manual switchover different mode, but because the correct discrimination power of handwriting recognition and speech recognition is relatively low, so the quantity of candidate target is also larger, so also can exist preference be not user want candidate target time, the problem that also will choose one by one by upper and lower key.Therefore, input method of the prior art because preference be not user want candidate target time, also to manually choose one by one by upper and lower key, conventionally candidate target is more, candidate region is less, easily location is inaccurate, so input method of the prior art exists low, the awkward technical matters of efficiency.
Summary of the invention
The invention provides a kind of input method and electronic equipment, in order to solve the low and awkward technical matters of efficiency that input method of the prior art exists.
One aspect of the present invention provides a kind of input method, is applied in an electronic equipment, and described electronic equipment comprises a display unit, and described method comprises: obtain the first input message of being inputted with the first input mode; The speech input information that acquisition is inputted in phonetic entry mode; Process described the first input message and determine M candidate target; And described speech input information is identified, determine N the candidate target mating with described speech input information; Wherein, M, N are more than or equal to 1 integer; Based on a described M candidate target and a described N candidate target, determine identical the first candidate target; Described the first candidate target of usining is presented on described display unit as preference.
Optionally, described the first input mode is different from described phonetic entry mode.
Optionally, in a described M candidate target, there is L the second candidate target identical respectively with L the 3rd candidate object in a described N candidate target, wherein, L is more than or equal to 2 integer, describedly determine identical the first candidate target, specifically comprise: the first score of obtaining each the second candidate target in described L the second candidate target; Obtain the second score of each the 3rd candidate target in described L the 3rd candidate target; Based on described the first score and described the second score, determine the highest candidate target of score in described L the second candidate target and in described L the 3rd candidate target; Determine that the candidate target that described score is the highest is described identical the first candidate target.
Optionally, described determine identical the first candidate target after, described method also comprises: other same candidate objects except described the first candidate target in described L the second candidate target and in described L the 3rd candidate target are sorted successively according to score height; By described other same candidate objects according to described sequencing display after described preference.
The present invention also provides a kind of input method on the other hand, is applied to an electronic equipment, and described electronic equipment comprises a display unit, and described method comprises: obtain the first input message of being inputted with the first input mode; Process described the first input message and determine M candidate target; Wherein, M is more than or equal to 1 integer; The speech input information that acquisition is inputted in phonetic entry mode; Described speech input information is identified, from a described M candidate target, determined the first candidate target mating with described speech input information; On described display unit, show described the first candidate target.
Optionally, described the first input mode is different from described phonetic entry mode.
Optionally, when described the first candidate target is the candidate target the highest with described speech input information matching degree, describedly on described display unit, show described the first candidate target, be specially: described the first candidate target of usining is presented on described display unit as preference.
Optionally, when described the first candidate target is during as preference, describedly on described display unit, show described the first candidate target, be specially: in the content input field on described display unit, show described the first candidate target.
Yet another embodiment of the invention also provides a kind of electronic equipment, comprising: display unit; The first input block, for obtaining the first input message with the first input mode input; Voice-input unit, for obtaining the speech input information of being inputted in phonetic entry mode; The first processing unit, determines M candidate target for the treatment of described the first input message; The second processing unit, for described speech input information is identified, determines N the candidate target mating with described speech input information; Wherein, M, N are more than or equal to 1 integer; The 3rd processing unit, for determining identical the first candidate target based on a described M candidate target and a described N candidate target; Control module, is presented at described display unit for usining described the first candidate target as preference.
Optionally, described the first input mode is different from described phonetic entry mode.
Optionally, in a described M candidate target, there is L the second candidate target identical respectively with L the 3rd candidate object in a described N candidate target, wherein, L is more than or equal to 2 integer, and described the 3rd processing unit is specifically for obtaining the first score of each the second candidate target in described L the second candidate target; Obtain the second score of each the 3rd candidate target in described L the 3rd candidate target; Based on described the first score and described the second score, determine the highest candidate target of score in described L the second candidate target and in described L the 3rd candidate target; Determine that the candidate target that described score is the highest is described identical the first candidate target.
Optionally, described the 3rd processing unit is concrete also for other same candidate objects except described the first candidate target in described L the second candidate target and described L the 3rd candidate target are just sorted successively according to score; Described control module specifically also for by described other same candidate objects according to described sequencing display after described preference.
Further embodiment of this invention also provides a kind of electronic equipment, comprising: display unit; The first input block, for obtaining the first input message of being inputted with the first input mode; The first processing unit, determines M candidate target for the treatment of described the first input message; Wherein, M is more than or equal to 1 integer; Voice-input unit, for obtaining the speech input information of being inputted in phonetic entry mode; The second processing unit, for described speech input information is identified, from a described M candidate target, determines the first candidate target mating with described speech input information; Control module, shows described the first candidate target for being controlled on described display unit.
Optionally, described the first input mode is different from described phonetic entry mode.
Optionally, when described the first candidate target is the candidate target the highest with described speech input information matching degree, described control module is usingd described the first candidate target and is presented on described display unit as preference specifically for controlling.
Optionally, when described the first candidate target is during as preference, described control module shows described the first candidate target specifically for being controlled in the content input field on described display unit.
The one or more technical schemes that provide in the embodiment of the present invention, at least have following technique effect or advantage:
In one embodiment of the invention, by the first input mode, input the first input message, by the mode of phonetic entry, input speech input information, then process the first input message and determine each candidate target of M; And speech input information is identified, determine N the candidate target mating with speech input information; Then based on M candidate target and N candidate target, determine identical the first candidate target; First candidate target of usining is again presented on display unit as preference.Method in the present embodiment is simultaneously by the first input mode and phonetic entry mode, input a content to be entered, under two kinds of input modes, obtain respectively two Candidate Sets, then select the first candidate target identical in two Candidate Sets, then using the first candidate target as preference, so preference of determining like this, the first candidate target is exactly that the probability wanted of user has just improved, so just can directly confirm input under more susceptible condition, do not need as in prior art, by upper and lower key going one by one, ransack again, choose, therefore, input method efficiency in the present embodiment is high, easy to use.
Accompanying drawing explanation
Fig. 1 is the process flow diagram of the input method in first embodiment of the invention;
Fig. 2 a-Fig. 2 c is the schematic diagram of the input method in first embodiment of the invention;
Fig. 3 is the process flow diagram of the input method in second embodiment of the invention;
Fig. 4 is the functional block diagram of the electronic equipment in first embodiment of the invention;
Fig. 5 is the functional block diagram of the electronic equipment in second embodiment of the invention.
Embodiment
The invention provides a kind of input method and electronic equipment, in order to solve the low and awkward technical matters of efficiency that the input method that exists in prior art exists.
Technical scheme in the embodiment of the present invention is for solving above-mentioned technical matters, and general thought is as follows:
By the first input mode, input the first input message, by the mode of phonetic entry, input speech input information, then process the first input message and determine each candidate target of M; And speech input information is identified, determine N the candidate target mating with speech input information; Then based on M candidate target and N candidate target, determine identical the first candidate target; First candidate target of usining is again presented on display unit as preference.Method in the present embodiment is simultaneously by the first input mode and phonetic entry mode, input a content to be entered, under two kinds of input modes, obtain respectively two Candidate Sets, then select the first candidate target identical in two Candidate Sets, then using the first candidate target as preference, so preference of determining like this, the first candidate target is exactly that the probability wanted of user has just improved, so just can directly confirm input under more susceptible condition, do not need as in prior art, by upper and lower key going one by one, ransack again, choose, therefore, input method efficiency in the present embodiment is high, easy to use.
In order better to understand technique scheme, below in conjunction with Figure of description and concrete embodiment, technique scheme is described in detail.
Embodiment mono-
First embodiment of the invention provides a kind of input method, is applied on the electronic equipment of a support voice input, and this electronic equipment is such as being the electronic equipments such as mobile phone, panel computer, notebook computer, and this electronic equipment comprises a display unit.
Please refer to Fig. 1, the method comprises:
Step 101: obtain the first input message of being inputted with the first input mode;
Step 102: obtain the speech input information of being inputted in phonetic entry mode;
Step 103: process the first input message and determine M candidate target; And speech input information is identified, determine N the candidate target mating with speech input information; Wherein, M, N are more than or equal to 1 integer;
Step 104: determine identical the first candidate target based on M candidate target and N candidate target;
Step 105: first candidate target of usining is presented on display unit as preference.
Wherein, the first input mode is identical with phonetic entry mode, also can be not identical.
Wherein, in step 101, the first input message that acquisition is inputted with the first input mode, concrete example is inputted by the keyboard of electronic equipment in this way, also can be the handwriting pad handwriting input that is connected in electronic equipment by, also can be phonetic entry, in the present embodiment, by handwriting pad handwriting input, be specifically that example describes, as shown in Figure 2 a, if user is now using mobile phone 20 to write short message, on the display unit of mobile phone, show a content input field 201, also has a hand-written input area 202, currently in content input field 201, inputted " a you " word, next, user utilizes finger or pointer in handwriting input region 202, to write " early " word.
In step 102, the speech input information that acquisition is inputted in phonetic entry mode, concrete example for example, collects the speech input information of user's input in this way by the sound collection unit on electronic equipment (microphone), continue to continue to use above-mentioned example, and user has said " zao ".
Wherein, step 101 and step 102 can be carried out simultaneously, for example user can be while writing, also can be asynchronous execution, can be first by the first input mode, to input, then in predetermined time interval, input speech input information, for example, after first having write, in 2s, whether detection receives speech input information, if had, just perform step 103, if do not receive speech input information in 2s, so just represent to only have handwriting input a kind of, so just continue down to continue according to the flow process of handwriting input; Also or first input speech input information, then detect the first input message whether having with the first input mode in predetermined time interval, for example first use phonetic entry, then detect and in 2s, whether have keyboard input or handwriting input, if had, just perform step 103, if do not had, so just according to the flow process of phonetic entry, down continue.Also can be when surpassing a schedule time during scope, providing information, allow user carry out phonetic entry or with the first input mode input, or provide option, allow user select to finish input, or select to carry out phonetic entry or with the first input mode input; Certainly, can be also when electronic equipment is adjusted in conjunction with input pattern, no matter how long cross after step 101, if do not perform step 102, will be parked in so in this step waiting voice input.
In the present embodiment, when user has write " early " by handwriting input, and by phonetic entry, also inputted " zao " simultaneously, so next just perform step 103: process the first input message and determine M candidate target, and speech input information is identified, determine N the candidate target mating with speech input information.
First, process the first input message and determine M candidate target, specifically, can be slightly different according to the first input mode difference, if for example the first input mode is the mode of keyboard input, process so the first input message and determine M candidate target, will be that the code that produces according to the key being pressed on keyboard and the words in a character library are compared, find the words matching, obtain M candidate target; And if the first input mode is handwriting input, this step is exactly that coordinate sequence by handwriting tracks is to a mapping process of the ISN of Chinese character so, find M the candidate target mating with handwriting tracks, no matter be that keyboard input might as well, handwriting input might as well, the content that this part content is well known to those skilled in the art, so do not repeat them here.
Continue to continue to use above-mentioned example, the M a determining candidate target just sorts by matching degree and is for example " drought, early, seldom ", certainly, just enumerate herein, and be not exhaustive, so in practice, may also comprise other candidate target.
Then, voice messaging is identified, determine N candidate target mating with speech input information, concrete example is in this way first by the extraction of acoustic feature, for example calculating of linear predictor coefficient LPC, cepstrum coefficient CEP, Mel cepstrum coefficient MFCC and perception linear prediction PLP and MFCC; By acoustic model, mate again, for example, utilize hidden Markov model; By language model, mate, the content that this part is well known to those skilled in the art, so be not described in detail in this again.
Continue to continue to use above-mentioned example, the N determining an in this step candidate target just sorts according to matching degree and is for example " early, bath, jujube ", certainly, just enumerate herein, and be not exhaustive, so in practice, may also comprise other candidate target.
It should be noted that, determine that the order of M candidate target and N candidate target is synchronously carried out, can synchronously not carry out yet, for example, no matter step 101 and step 102 are synchronous or tandem, after can waiting until in step 103 that the first input message and speech input information all obtain, process simultaneously; Also can be the order according to step 101 and step 102, first obtain the first input message, just first determine M candidate target, if first obtain speech input information, so just first determine N candidate target.
Next, just perform step 104, based on M candidate target and N candidate target, determine identical the first candidate target.
In specific implementation process, be for example that each candidate target in each candidate target in M candidate target and N candidate target is compared, find out in M candidate target with N candidate target in the first candidate target of having.Specifically, continue to continue to use above-mentioned example, after comparison, in " drought, early, seldom " neutralization " early, bath, jujube ", the first identical candidate target is " early ".
Then perform step 105, first candidate target of usining is presented on display unit as preference, specifically as shown in Figure 2 b, in a sub regions in handwriting input region 202, demonstrated and usingd the candidate list of the first candidate target as preference, because now preference is exactly the word that user wants, as long as so user carries out directly confirmation, and do not need to select with right and left key, upper and lower key.
Certainly, in another embodiment, because the first candidate target is confirmed as preference, so step 105 can also be specifically that the first candidate target is directly presented in content input field, specifically please refer to shown in Fig. 2 c, has directly been transfused to " early " word in content input field 201, in an embodiment, user does not even need the action of determining, has reduced the number of times of button, so further improved the efficiency of input in the situation that guaranteeing accuracy rate.
In the above-described embodiments, the first input mode be take handwriting input and is described as example, because the M that handwriting input an is determined candidate target is all similar on font conventionally, and word tone is different, so input again one time by the mode of phonetic entry, so just can select very soon the candidate target needing, and the quantity of the first candidate target is also one conventionally, so the probability of the words that the first candidate target is user to be needed is higher.Yet, when the first input mode is other modes, for example, while inputting with the spelling input method of keyboard, M candidate target is also the same or similar of word tone conventionally, and be also the identical of word tone in the N that the mode of phonetic entry an is determined candidate target, so the quantity of identical the first candidate target of determining in step 104 may be more than or equal to 2, suppose to have in M candidate target L the second candidate target, identical respectively with L the 3rd candidate object in N candidate target, L is more than or equal to 2 integer, so in this case, the embodiment of the step 104 in the present embodiment is as follows:
Obtain the first score of each the second candidate target in L the second candidate target; Obtain the second score of each the 3rd candidate target in L the 3rd candidate target; Based on the first score and the second score, determine the highest candidate target of score in L the second candidate target and in L the 3rd candidate target; Determine that the candidate target that score is the highest is identical the first candidate target.
For example user wants input " morning ", so just perform step 101, by keyboard, utilize predictive input mode input " zs ", and perform step 102 simultaneously, be phonetic entry " zaoshang ", then perform step 103, determine that M candidate target is for example " integer, morning, at least, on jujube, on algae ", and determine that N candidate target is for example " on morning, algae, on kitchen range, on jujube ", wherein, 3 the second candidate targets are respectively " on morning, jujube, on algae ", and 3 the 3rd candidate targets are respectively " on morning, jujube, on algae ".
So, next perform step 104, obtain the first score of L each the second candidate target in the second candidate target, concrete example in this way the first score of the second candidate target " morning " is 80 minutes, the first score of the second candidate target " on jujube " is 60 minutes, and the first score of the second candidate target " on algae " is 50 minutes; Obtain the second score of each the 3rd candidate target in L the 3rd candidate target, concrete example in this way the second score of the 3rd candidate target " morning " is 90 minutes, the second score of the 3rd candidate target " on algae " is 80 minutes, and the second score of the 3rd candidate target " on jujube " is 60 minutes.
Then next, based on the first score and the second score, determine the highest candidate target of score in L the second candidate target and in L the 3rd candidate target, concrete example is added the first score of identical candidate target and the second score in this way, or further averages again; Or the weight of the first score is higher than the weight of the second score, or the weight of the second score is higher than the weight of the first score; In the present embodiment, for example that the first score and the second score are added, in so above-mentioned example, " morning " must be divided into 170, the score of " on jujube " is 120, " on algae " must be divided into 130 minutes, so the highest candidate target of score is " morning ", so just determine that " morning " is identical the first candidate target.
In a further embodiment, also other same candidate objects except the first candidate target in L the second candidate target and in L the 3rd candidate target are sorted successively according to score height; And by other same candidate objects according to sequencing display after preference.Continue to use above-mentioned example, so just " on algae " and " on jujube " just sorted according to score, and be presented at according to this " morning " afterwards.
In a further embodiment, for other the mutually different candidate targets in M candidate target and N candidate target, also can be according to score height successively sequencing display after an identical demonstration object of most end, can not show yet, or preferentially show in N candidate target, show again in M candidate target, or show conversely.
Embodiment bis-
The present embodiment also provides a kind of input method, is applied to an electronic equipment, and this electronic equipment comprises a display unit and support voice input, and this electronic equipment is such as being the electronic equipments such as mobile phone, panel computer, notebook computer.
Please refer to Fig. 3, the method comprises:
Step 301: obtain the first input message of being inputted with the first input mode;
Step 302: process the first input message and determine M candidate target; Wherein, M is more than or equal to 1 integer;
Step 303: obtain the speech input information of inputting in phonetic entry mode;
Step 304: speech input information is identified, from M candidate target, determined the first candidate target mating with speech input information;
Step 305: show the first candidate target on display unit.
Wherein, the first input mode and phonetic entry mode can identical can be not identical yet.
Wherein, step 301 is similar with the implementation process of step 101, in step 302, process the first input message and determine that in the embodiment of M candidate target and step 103, processing the first input message determines that the embodiment of M candidate target is similar, step 303 and step 102 are similar, so do not repeat them here.
Especially, in actual implementation process, if also do not perform step 303 within the scope of the schedule time after step 302, so just represent only need to, with the first input mode input, so just can directly show M candidate target; Also can be when surpassing a schedule time during scope, provide information, allow user carry out phonetic entry, or provide option, allowing user select to finish input, or select to carry out phonetic entry; Certainly, can be also when electronic equipment is adjusted in conjunction with input pattern, no matter how long cross after step 302, if do not perform step 303, will be parked in so in this step waiting voice input.
Next perform step 304, speech input information is identified, from M candidate target, determine the first candidate target mating with speech input information; Concrete example is in this way to after speech input information identification, in M candidate target, compare one by one the pronunciation of each candidate target and the similarity of speech input information, the first candidate target can be M candidate target after M candidate target rearranges according to the height of similarity; Also can be that the highest candidate target of similarity in M candidate target; Also can be that similarity is greater than the corresponding candidate target of certain threshold value.
Then perform step 305, on display unit, show the first candidate target, in specific implementation process, when the first candidate target is the candidate target the highest with speech input information matching degree, first candidate target of just usining is presented on display unit as preference, shown in similar Fig. 2 b; Further, if the first candidate target during as preference, is specially in the content input field on display unit and shows the first candidate target, be similar to shown in Fig. 2 c.
Use the input method in the present embodiment, than directly using phonetic entry, in character library, compare, in M candidate target, compare, because quantity is far less than character library, so the efficiency of phonetic entry is higher, and accuracy rate is higher, the accuracy that preference is the words that user will input can reach more than 95%, even in 5% mistake, still have most correct words to there will be at the second cis-position or the 3rd cis-position, also can allow easily user press upper and lower key or right and left key is chosen.
Embodiment tri-
A kind of electronic equipment is also provided in one embodiment of the invention, and this electronic equipment is such as being the electronic equipments such as mobile phone, panel computer, notebook computer, and this electronic equipment support voice input, for realizing for example input method of embodiment mono-.
As shown in Figure 4, this electronic equipment comprises: display unit 401; The first input block 402, for obtaining the first input message with the first input mode input; Voice-input unit 403, for obtaining the speech input information of being inputted in phonetic entry mode; The first processing unit 404, determines M candidate target for the treatment of the first input message; The second processing unit 405, for speech input information is identified, determines N the candidate target mating with speech input information; Wherein, M, N are more than or equal to 1 integer; The 3rd processing unit 406, for determining identical the first candidate target based on M candidate target and N candidate target; Control module 407, is presented at display unit 401 for usining the first candidate target as preference.
Wherein, the first input mode can be identical with phonetic entry mode, also can be different.
In one embodiment, in M candidate target, there is L the second candidate target identical respectively with L the 3rd candidate object in N candidate target, wherein, L is more than or equal to 2 integer, and the 3rd processing unit 406 is specifically for obtaining the first score of each the second candidate target in L the second candidate target; Obtain the second score of each the 3rd candidate target in L the 3rd candidate target; Based on the first score and the second score, determine the highest candidate target of score in L the second candidate target and in L the 3rd candidate target; Determine that the candidate target that score is the highest is identical the first candidate target.
Further, the 3rd processing unit 406 is concrete also for other same candidate objects except the first candidate target in L the second candidate target and L the 3rd candidate target are sorted successively according to score height; Control module 407 specifically also for by other same candidate objects according to this sequencing display after preference.
In practice, the first input block 402 concrete examples are keyboard in this way, and voice-input unit 403 concrete examples are microphone, microphone array in this way.
Further, the first processing unit 404 can be integrated in the central processing unit of electronic equipment, can be also independent process chip, is arranged on the circuit board of electronic equipment
Further, the second processing unit 405, concrete example is an integrated in this way chip of pronounciation processing chip, can carry out speech recognition, and according to recognition result, determine the candidate target matching, and is arranged on the circuit board of electronic equipment.
Further, the first processing unit 404, the second processing unit 405 and the 3rd processing unit 406 can be specifically different between two chips, can be also identical chips.
Further, control module 407 can be to be integrated in central processing unit, can be also independent control chip, arranges on circuit board.
Each embodiment can implement separately above, also can be in conjunction with enforcement, and technician can select according to actual needs.
The electronic equipment that various variation patterns in input method in previous embodiment one and instantiation are equally applicable to the present embodiment, by the aforementioned detailed description to input method, those skilled in the art can clearly know the implementation method of electronic equipment in the present embodiment, so succinct for instructions, is not described in detail in this.
Embodiment tetra-
A kind of electronic equipment is also provided in one embodiment of the invention, and this electronic equipment is such as being the electronic equipments such as mobile phone, panel computer, notebook computer, and this electronic equipment support voice input, for realizing for example input method of embodiment bis-.
As shown in Figure 5, this electronic equipment comprises: display unit 501; The first input block 502, for obtaining the first input message with the first input mode input; The first processing unit 503, determines M candidate target for the treatment of the first input message; Wherein, M is more than or equal to 1 integer; Voice-input unit 504, for obtaining the speech input information of being inputted in phonetic entry mode; The second processing unit 505, for speech input information is identified, from M candidate target, determines the first candidate target mating with speech input information; Control module 506, shows the first candidate target for being controlled on display unit 501.
Wherein, the first input mode can be identical with phonetic entry mode, also can be different.
In one embodiment, when the first candidate target is the candidate target the highest with speech input information matching degree, control module 506 is usingd the first candidate target and is presented on display unit 501 as preference specifically for controlling.
Further, when the first candidate target is during as preference, control module 506 shows the first candidate target specifically for being controlled in the content input field on display unit 501.
In practice, the first input block 502 concrete examples are keyboard in this way, and voice-input unit 504 concrete examples are microphone, microphone array in this way.
Further, the first processing unit 503 can be integrated in the central processing unit of electronic equipment, can be also independent process chip, is arranged on the circuit board of electronic equipment.
Further, the second processing unit 505, concrete example is an integrated in this way chip of pronounciation processing chip, can carry out speech recognition, is arranged on the circuit board of electronic equipment.
Further, the first processing unit 503 and the second processing unit 505 can be specifically different chips, can be also identical chips.
Further, control module 506 can be to be integrated in central processing unit, can be also independent control chip, arranges on circuit board.
Each embodiment can implement separately above, also can be in conjunction with enforcement, and technician can select according to actual needs.
The electronic equipment that various variation patterns in input method in previous embodiment two and instantiation are equally applicable to the present embodiment, by the aforementioned detailed description to input method, those skilled in the art can clearly know the implementation method of electronic equipment in the present embodiment, so succinct for instructions, is not described in detail in this.
The one or more technical schemes that provide in the embodiment of the present invention, at least have following technique effect or advantage:
In one embodiment of the invention, by the first input mode, input the first input message, by the mode of phonetic entry, input speech input information, then process the first input message and determine each candidate target of M; And speech input information is identified, determine N the candidate target mating with speech input information; Then based on M candidate target and N candidate target, determine identical the first candidate target; First candidate target of usining is again presented on display unit as preference.Method in the present embodiment is simultaneously by the first input mode and phonetic entry mode, input a content to be entered, under two kinds of input modes, obtain respectively two Candidate Sets, then select the first candidate target identical in two Candidate Sets, then using the first candidate target as preference, so preference of determining like this, the first candidate target is exactly that the probability wanted of user has just improved, so just can directly confirm input under more susceptible condition, do not need as in prior art, by upper and lower key going one by one, ransack again, choose, therefore, input method efficiency in the present embodiment is high, easy to use.
Those skilled in the art should understand, embodiments of the invention can be provided as method, system or computer program.Therefore, the present invention can adopt complete hardware implementation example, implement software example or in conjunction with the form of the embodiment of software and hardware aspect completely.And the present invention can adopt the form that wherein includes the upper computer program of implementing of computer-usable storage medium (including but not limited to magnetic disk memory and optical memory etc.) of computer usable program code one or more.
The present invention is with reference to describing according to process flow diagram and/or the block scheme of the method for the embodiment of the present invention, equipment (system) and computer program.Should understand can be in computer program instructions realization flow figure and/or block scheme each flow process and/or the flow process in square frame and process flow diagram and/or block scheme and/or the combination of square frame.Can provide these computer program instructions to the processor of multi-purpose computer, special purpose computer, Embedded Processor or other programmable data processing device to produce a machine, the instruction of carrying out by the processor of computing machine or other programmable data processing device is produced for realizing the device in the function of flow process of process flow diagram or a plurality of flow process and/or square frame of block scheme or a plurality of square frame appointments.
These computer program instructions also can be stored in energy vectoring computer or the computer-readable memory of other programmable data processing device with ad hoc fashion work, the instruction that makes to be stored in this computer-readable memory produces the manufacture that comprises command device, and this command device is realized the function of appointment in flow process of process flow diagram or a plurality of flow process and/or square frame of block scheme or a plurality of square frame.
These computer program instructions also can be loaded in computing machine or other programmable data processing device, make to carry out sequence of operations step to produce computer implemented processing on computing machine or other programmable devices, thereby the instruction of carrying out is provided for realizing the step of the function of appointment in flow process of process flow diagram or a plurality of flow process and/or square frame of block scheme or a plurality of square frame on computing machine or other programmable devices.
Obviously, those skilled in the art can carry out various changes and modification and not depart from the spirit and scope of the present invention the present invention.Like this, if within of the present invention these are revised and modification belongs to the scope of the claims in the present invention and equivalent technologies thereof, the present invention is also intended to comprise these changes and modification interior.
Claims (16)
1. an input method, is applied to an electronic equipment, and described electronic equipment comprises a display unit, it is characterized in that, described method comprises:
The first input message that acquisition is inputted with the first input mode;
The speech input information that acquisition is inputted in phonetic entry mode;
Process described the first input message and determine M candidate target; And described speech input information is identified, determine N the candidate target mating with described speech input information; Wherein, M, N are more than or equal to 1 integer;
Based on a described M candidate target and a described N candidate target, determine identical the first candidate target;
Described the first candidate target of usining is presented on described display unit as preference.
2. the method for claim 1, is characterized in that, described the first input mode is different from described phonetic entry mode.
3. the method for claim 1, is characterized in that, has L the second candidate target identical respectively with L the 3rd candidate object in a described N candidate target in a described M candidate target, wherein, L is more than or equal to 2 integer, described in determine identical the first candidate target, specifically comprise:
Obtain the first score of each the second candidate target in described L the second candidate target;
Obtain the second score of each the 3rd candidate target in described L the 3rd candidate target;
Based on described the first score and described the second score, determine the highest candidate target of score in described L the second candidate target and in described L the 3rd candidate target;
Determine that the candidate target that described score is the highest is described identical the first candidate target.
4. method as claimed in claim 3, is characterized in that, described determine identical the first candidate target after, described method also comprises:
Other same candidate objects except described the first candidate target in described L the second candidate target and in described L the 3rd candidate target are sorted successively according to score height;
By described other same candidate objects according to described sequencing display after described preference.
5. an input method, is applied to an electronic equipment, and described electronic equipment comprises a display unit, it is characterized in that, described method comprises:
The first input message that acquisition is inputted with the first input mode;
Process described the first input message and determine M candidate target; Wherein, M is more than or equal to 1 integer;
The speech input information that acquisition is inputted in phonetic entry mode;
Described speech input information is identified, from a described M candidate target, determined the first candidate target mating with described speech input information;
On described display unit, show described the first candidate target.
6. method as claimed in claim 5, is characterized in that, described the first input mode is different from described phonetic entry mode.
7. method as claimed in claim 5, is characterized in that, when described the first candidate target is the candidate target the highest with described speech input information matching degree, describedly on described display unit, shows described the first candidate target, is specially:
Described the first candidate target of usining is presented on described display unit as preference.
8. method as claimed in claim 7, is characterized in that, when described the first candidate target is during as preference, describedly on described display unit, shows described the first candidate target, is specially:
In content input field on described display unit, show described the first candidate target.
9. an electronic equipment, is characterized in that, comprising:
Display unit;
The first input block, for obtaining the first input message with the first input mode input;
Voice-input unit, for obtaining the speech input information of being inputted in phonetic entry mode;
The first processing unit, determines M candidate target for the treatment of described the first input message;
The second processing unit, for described speech input information is identified, determines N the candidate target mating with described speech input information; Wherein, M, N are more than or equal to 1 integer;
The 3rd processing unit, for determining identical the first candidate target based on a described M candidate target and a described N candidate target;
Control module, is presented at described display unit for usining described the first candidate target as preference.
10. electronic equipment as claimed in claim 9, is characterized in that, described the first input mode is different from described phonetic entry mode.
11. electronic equipments as claimed in claim 9, it is characterized in that, in a described M candidate target, there is L the second candidate target identical respectively with L the 3rd candidate object in a described N candidate target, wherein, L is more than or equal to 2 integer, and described the 3rd processing unit is specifically for obtaining the first score of each the second candidate target in described L the second candidate target; Obtain the second score of each the 3rd candidate target in described L the 3rd candidate target; Based on described the first score and described the second score, determine the highest candidate target of score in described L the second candidate target and in described L the 3rd candidate target; Determine that the candidate target that described score is the highest is described identical the first candidate target.
12. electronic equipments as claimed in claim 11, it is characterized in that, described the 3rd processing unit is concrete also for other same candidate objects except described the first candidate target in described L the second candidate target and described L the 3rd candidate target are sorted successively according to score height;
Described control module specifically also for by described other same candidate objects according to described sequencing display after described preference.
13. 1 kinds of electronic equipments, is characterized in that, comprising:
Display unit;
The first input block, for obtaining the first input message of being inputted with the first input mode;
The first processing unit, determines M candidate target for the treatment of described the first input message; Wherein, M is more than or equal to 1 integer;
Voice-input unit, for obtaining the speech input information of being inputted in phonetic entry mode;
The second processing unit, for described speech input information is identified, from a described M candidate target, determines the first candidate target mating with described speech input information;
Control module, shows described the first candidate target for being controlled on described display unit.
14. electronic equipments as claimed in claim 13, is characterized in that, described the first input mode is different from described phonetic entry mode.
15. electronic equipments as claimed in claim 13, it is characterized in that, when described the first candidate target is the candidate target the highest with described speech input information matching degree, described control module is usingd described the first candidate target and is presented on described display unit as preference specifically for controlling.
16. electronic equipments as claimed in claim 15, is characterized in that, when described the first candidate target is during as preference, described control module shows described the first candidate target specifically for being controlled in the content input field on described display unit.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310074783.3A CN104035551A (en) | 2013-03-08 | 2013-03-08 | Input method and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310074783.3A CN104035551A (en) | 2013-03-08 | 2013-03-08 | Input method and electronic device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104035551A true CN104035551A (en) | 2014-09-10 |
Family
ID=51466353
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310074783.3A Pending CN104035551A (en) | 2013-03-08 | 2013-03-08 | Input method and electronic device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104035551A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105719645A (en) * | 2014-12-17 | 2016-06-29 | 现代自动车株式会社 | Speech recognition apparatus, vehicle including the same, and method of controlling the same |
| CN106445100A (en) * | 2015-08-06 | 2017-02-22 | 大众汽车有限公司 | Method and system for processing multimodal input signals |
| CN106843523A (en) * | 2016-12-12 | 2017-06-13 | 百度在线网络技术（北京）有限公司 | Character input method and device based on artificial intelligence |
| CN110192242A (en) * | 2017-01-20 | 2019-08-30 | 森兰信息科技（上海）有限公司 | Key for piano system assists user input systems and method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1470975A (en) * | 2002-07-22 | 2004-01-28 | 北京大学 | Chinese character input method and system by using said method |
| US20060190256A1 (en) * | 1998-12-04 | 2006-08-24 | James Stephanick | Method and apparatus utilizing voice input to resolve ambiguous manually entered text input |
| CN1996206A (en) * | 2005-12-31 | 2007-07-11 | 北京三星通信技术研究有限公司 | Conversion input device based on offline input mode and method therefor |
-
2013
- 2013-03-08 CN CN201310074783.3A patent/CN104035551A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060190256A1 (en) * | 1998-12-04 | 2006-08-24 | James Stephanick | Method and apparatus utilizing voice input to resolve ambiguous manually entered text input |
| CN1470975A (en) * | 2002-07-22 | 2004-01-28 | 北京大学 | Chinese character input method and system by using said method |
| CN1996206A (en) * | 2005-12-31 | 2007-07-11 | 北京三星通信技术研究有限公司 | Conversion input device based on offline input mode and method therefor |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105719645A (en) * | 2014-12-17 | 2016-06-29 | 现代自动车株式会社 | Speech recognition apparatus, vehicle including the same, and method of controlling the same |
| CN105719645B (en) * | 2014-12-17 | 2020-09-18 | 现代自动车株式会社 | Voice recognition apparatus, vehicle including the same, and method of controlling voice recognition apparatus |
| CN106445100A (en) * | 2015-08-06 | 2017-02-22 | 大众汽车有限公司 | Method and system for processing multimodal input signals |
| CN106445100B (en) * | 2015-08-06 | 2019-08-02 | 大众汽车有限公司 | For handling the method and system of multimode input signal |
| CN106843523A (en) * | 2016-12-12 | 2017-06-13 | 百度在线网络技术（北京）有限公司 | Character input method and device based on artificial intelligence |
| CN106843523B (en) * | 2016-12-12 | 2020-09-22 | 百度在线网络技术（北京）有限公司 | Character input method and device based on artificial intelligence |
| CN110192242A (en) * | 2017-01-20 | 2019-08-30 | 森兰信息科技（上海）有限公司 | Key for piano system assists user input systems and method |
| CN110192242B (en) * | 2017-01-20 | 2021-11-30 | 森兰信息科技（上海）有限公司 | Piano key assisting user input system and method for piano system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9026428B2 (en) | Text/character input system, such as for use with touch screens on mobile phones | |
| US9123341B2 (en) | System and method for multi-modal input synchronization and disambiguation | |
| US7719521B2 (en) | Navigational interface providing auxiliary character support for mobile and wearable computers | |
| US9552080B2 (en) | Incremental feature-based gesture-keyboard decoding | |
| JP4416643B2 (en) | Multimodal input method | |
| CN100587660C (en) | Method and device for forecasting and discriminating hand-written characters | |
| CN105810188B (en) | Information processing method and electronic equipment | |
| KR101474854B1 (en) | Apparatus and method for selecting a control object by voice recognition | |
| WO2014055762A1 (en) | Incremental multi-touch gesture recognition | |
| CN103870192B (en) | Input method and device based on touch screen, Chinese pinyin input method and system | |
| US10082952B2 (en) | System and method for text input by a continuous sliding operation | |
| WO2014062588A2 (en) | Incremental multi-word recognition | |
| JPH07295784A (en) | Information processor by voice | |
| CN1777858A (en) | Unambiguous text input method for touch screens and reduced keyboard systems | |
| CN103903618B (en) | A kind of pronunciation inputting method and electronic equipment | |
| CN104267922B (en) | A kind of information processing method and electronic equipment | |
| KR20180115699A (en) | System and method for multi-input management | |
| CN102937837A (en) | Method for inputting words on the basis of incomplete recognition quickly | |
| CN104035551A (en) | Input method and electronic device | |
| US20080095444A1 (en) | Information recognition device operating with low power consumption | |
| CN105786204A (en) | Information processing method and electronic equipment | |
| CN102063282A (en) | Chinese speech input system and method | |
| KR101385012B1 (en) | Multi-modal input device using handwriting and voice recognition and control method thereof | |
| CN102207824B (en) | Sliding pinyin input method based on touch screen device | |
| CN105404624A (en) | Chinese character recognition method, device and terminal |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140910 |
|
| RJ01 | Rejection of invention patent application after publication |