CN1330333A - Chinese input transformation device and input transformation processing method and recording medium - Google Patents
Chinese input transformation device and input transformation processing method and recording medium Download PDFInfo
- Publication number
- CN1330333A CN1330333A CN 01122612 CN01122612A CN1330333A CN 1330333 A CN1330333 A CN 1330333A CN 01122612 CN01122612 CN 01122612 CN 01122612 A CN01122612 A CN 01122612A CN 1330333 A CN1330333 A CN 1330333A
- Authority
- CN
- China
- Prior art keywords
- input
- chinese
- string
- phonetic
- alphabetic string
- 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
Images
Landscapes
- Document Processing Apparatus (AREA)
- Machine Translation (AREA)
Abstract
When a character string expressing the reading of the KANJI of Chinese language is inputted through an input part 21, an accuracy checking processing part 25 checks whether or not the inputted character string can stand up as Pin-yin. With the timing of detecting that the inputted character string cannot stand up as Pin-yin, a prediction processing part 27 starts prediction processing to retrieve a Chinese dictionary 24 based on character strings inputted until just before then to predict a character string as Pin-yin including the inputted character string. Dictionary retrieval is carried out with this Pin-yin character string (predicted candidate) as the input of a dictionary retrieving part 23 and the candidate of the KANJI obtained by the dictionary retrieval is presented to a user by an output part 28.
Description
Transition processing device imported in the Chinese that the present invention relates to use in the file producing device of the word processor that can carry out the Chinese input and PC etc., be particularly related to and possess when transforming to Chinese character from phonetic as the Chinese pronunciation mark, when having imported phonetic alphabet strings a part of, predict Chinese input transition processing device, the input transform process method of the Chinese in same device and the recording medium of correct phonetic candidate function.
In the word production device that can carry out the Chinese input, possess and use the dictionary that the pronunciation mark (phonetic) of the Chinese character of Chinese and its pronunciation of expression is mapped, the pronunciation with phonetic input Chinese is converted to the function of Chinese character to it.It is called phonetic Chinese character change function (being equivalent to Japanese word processor Kana-Chinese character conversion function).
But, in pinyin input mode,, then have the problem of input spended time if must import the alphabetic string (it is called the input of spelling sound) of whole pronunciations of the Chinese (Chinese character) that becomes transforming object with letter.As the mode of omitting this phonetic input, following motion has been proposed.
(Japan's application)
1, the patent No.: P2624484 (registration on April 11st, 1997)
2, publication number: PH09-128376 (on May 16th, 1997 is open)
(China's Mainland application)
3, publication number: CN1026272 (application on June 19th, 1989)
4, the patent No.: ZL93116670 (registration on November 25th, 1998)
5, the patent No.: ZL91102940 (registration on Dec 31st, 1998)
6, the patent No.: ZL94105991 (registration on February 17th, 1999)
The mode of above-mentioned document 1 is, in 3 words (Chinese character) more than the letter, and 1 literal input spelling sound, the beginning letter of spelling sound imported later in the 2nd literal.
The mode of above-mentioned document 2 is to import the letter (quilt of the part of the beginning that is positioned at the spelling sound Be called " choosing is pieced together ").
The mode of above-mentioned document 3 is the beginning letter of combinatorial input spelling sound or the part of initial consonant and simple or compound vowel of a Chinese syllable.
The mode of above-mentioned document 4 is a kind of sound shape code input method of combinating Pinyin and font.Sound is to realize input by the beginning letter of phonetic, and shape is to realize input with radicals by which characters are arranged in traditional Chinese dictionaries (cutting apart with Roman capitals).For example, " people " input " rmpr "." r " and " m " is " people " and " " beginning letter separately, and " p " and " r " is the mark of expression " people " and " " radicals by which characters are arranged in traditional Chinese dictionaries separately.
The mode of above-mentioned document 5 uses the spelling sound to import a side of the word of 2 letters, imports the opposing party with the beginning letter.
The mode of above-mentioned document 6 is to carry out the conversion of 1 Chinese character by the basic code+input of selection code.Basic code is represented the beginning letter of a certain word, selects coded representation to want position in the basic code of the Chinese character imported.For example, input " rrqs3 " under the situation of wanting input " by force " this Chinese character.Basic code " rrqs " is the beginning letter of each Chinese character of " the weak are the prey of the strong ", selects code " 3 " expression the 3rd literal wherein.
In Chinese, the pronunciation of 1 Chinese character must be 1 syllable.1 syllable further is made of the beginning consonant part that is called as " initial consonant ", the part except " initial consonant " (vowel, diphthong, nasalization vowel etc. are arranged) that is called as " simple or compound vowel of a Chinese syllable ".In addition, represent the tone that is called as " four tones of standard Chinese pronunciation " that rises and falls (being similar to the stress of Japanese) of syllable in addition, 1 syllable has these 3 key elements of initial consonant, simple or compound vowel of a Chinese syllable and the four tones of standard Chinese pronunciation to constitute.
The example of initial consonant: b, p, m, f, d, t, n, l, zh, ch, sh,
The example of simple or compound vowel of a Chinese syllable: a, o, e, i, u, ai, en, ang, iong,
Different with vowel with the consonant of Japanese Roman capitals on mark, the length of the letter of phonetic alphabet string might not be one of feature.
The example of the phonetic mark of Chinese character as shown in Figure 1.
For example, " ba " of phonetic mark, wherein " b " is equivalent to initial consonant, and " a " is equivalent to simple or compound vowel of a Chinese syllable.Additional tone mark on this phonetic mark is if input " ba1 " then obtains belonging to the Chinese character of the 1st " eight ", " crust " etc.Equally, " shan ", wherein sh is an initial consonant, " an " is simple or compound vowel of a Chinese syllable, by " shan1 " this input, can obtain the Chinese character of " mountain ", " coral ", " inciting " etc." huang ", wherein " h " is initial consonant, " uang " is simple or compound vowel of a Chinese syllable, by " huang1 " this input, can obtain the Chinese character of " famine ", " unbearably " etc.
Like this, the length for each its alphabetic string of Chinese character is not certain in the phonetic mark.Thereby, as a kind of mode of carrying out the Chinese character conversion, beginning phonetic letter input mode is arranged by short alphabetic string input.
Beginning phonetic letter input mode, the beginning part of an input Pinyin (being mostly the consonant part usually) is realized and the spelling sound is imported same conversion.In a word, in consonant part (initial consonant) be under the situation of 1 letter this 1 letter as the input of beginning letter, (" zh ", " ch ", " sh ") imports 1 letter or 2 letters of its beginning as beginning is alphabetical under the situation that is 2 letters.
The example of beginning phonetic letter input mode as shown in Figure 2.
For example, under the situation that obtains " enduring hardships to accomplish some ambition " this Chinese character, in spelling sound input mode, must import " wo/xin/chang/dan " ("/" expression syllabication, do not have in the reality) this pronunciation, but in beginning phonetic letter input mode, import " wxcd " with the beginning letter of each syllable and get final product.Similarly, in " system of responsibility in production " this Chinese character, in spelling sound mode, need input " sheng/chan/ze/ren/zhi ", and input " sczrz " in beginning phonetic letter input mode.In addition, under the situation of input " People's Republic of China (PRC) " this Chinese character, in spelling sound mode, need input " zhong/hua/ren/min/gong/he/guo ", and input " zhrmghg " in beginning phonetic letter input mode.
From above-mentioned example as can be known, if with beginning phonetic letter input mode, then stroke seldom can be finished input, have can quicker input advantage.But, because be that pronunciation mark (phonetic alphabet string) with needed Chinese character all knows to be prerequisite, need to import, so exist when in use not knowing pronunciation and out of use problem when not knowing input mode according to corresponding input mode.
In addition, be recorded in each above-mentioned document the omission input mode too, just can not use if know the pronunciation mark (phonetic alphabet string) of whole Chinese characters, and then, exist and not know that these omit the out of use problem of user of input modes.
Thereby, the objective of the invention is to: a kind of input burden that alleviates when carrying out the phonetic input in common pinyin input mode is provided, can obtains Chinese input transition processing device, Chinese input transform process method and the recording medium of desirable Chinese character expeditiously.
The present invention is an alphabetic string of representing the Chinese-character pronunciation of Chinese with the pinyin input mode input, the alphabetic string of this input is transformed to the Chinese input transition processing device of suitable Chinese character, it is characterized in that: when each input, check alphabetic string as the pronunciation input, timing when satisfying defined terms, alphabetic string according to input is before this predicted the alphabetic string that exists as phonetic, carries out phonetic Chinese character change according to this predicted letters string and handles.
The condition of so-called afore mentioned rules is when having as the invalid input of phonetic when input, perhaps, and when the input alphabet number surpasses the alphabetical number of setting.
Under the former situation, when importing, each letter checks the alphabetic string that is transfused to, judge whether the input alphabet string is set up as phonetic.The phonetic composition rule of the initial consonant of the predefined phonetic of this judgement reference and the combination of simple or compound vowel of a Chinese syllable carries out.When being judged to be when being false as phonetic, that is, detecting as phonetic in input process is when not setting up the input state of (not finishing), as the correct alphabetic string of phonetic prediction of the alphabetic string that then is transfused to before this.
And then, if carry out the establishment judgement (phonetic is corrected errors and checked) of phonetic at the beginning part of pronunciation alphabetic string, then begin prediction processing immediately, because there is the prediction candidate a lot of possibilities to occur, so preferably do not carry out the establishment judgement of phonetic at least in the moment that 1 letter that starts is transfused to.
In the latter case, when each input, check the alphabetic string that is transfused to as pronunciation, judge whether the input alphabet number has surpassed the alphabetical number of setting.Above-mentioned setting letter number can be according to outside indication change arbitrarily.When being judged as the input alphabet number when surpass setting alphabetical number, that is,, when the input alphabet number of this moment has surpassed setting letter number before the prediction beginning, predict correct alphabetic string as the phonetic of the alphabetic string that then is transfused to before this when in input process.
By using such input forecast function, phonetic is imported when the pronunciation in common pinyin input mode, even do not import whole phonetic alphabet strings of the pronunciation that becomes transforming object, also can in its input process, obtain transformation results, can alleviate user's input burden.In addition,, just can dwindle prediction candidate number, can avoid because the decline of the conversion efficiency that a plurality of prediction candidates cause by when satisfying defined terms, beginning prediction.
In addition, also can satisfy above-mentioned the former condition and begin prediction processing during the above-mentioned latter's condition.
That is, when each letter input, check alphabetic string, judge whether input alphabet string number surpasses to set alphabetical number, surpass when setting alphabetical number being judged as the input alphabet number, whether the alphabetic string judgement of later input is set up as phonetic as the pronunciation input.Then, be judged as the input alphabet string when being false, the alphabetic string that exists as phonetic according to the alphabetic string prediction of input before this as phonetic.
Like this, if subsidiary condition are carried out the establishment judgement (phonetic is corrected errors and checked) of phonetic on the alphabetical number before the input prediction beginning, then for example in using the pronunciation mark of the Chinese character that constitutes by a plurality of syllables, for the input of the such pronunciation alphabetic string of check and correction of after the 1st syllable, correcting errors immediately, the moment that can delay prediction begins.Thus, can prevent to cause a lot of candidate of appearance owing to import prediction in early days.
Accompanying drawing below is described simply.
Fig. 1 is the figure that is used to illustrate the phonetic mark of Chinese.
Fig. 2 is the figure that is used to illustrate beginning phonetic letter input mode.
Fig. 3 is a block scheme of showing system's formation of Chinese input transition processing device of the present invention.
Fig. 4 is that the function of showing the embodiment 1 of above-mentioned Chinese input transition processing device constitutes block scheme.
Fig. 5 is the figure that is illustrated in the formation of the Chinese dictionary that possesses in the above-mentioned Chinese input transition processing device.
Fig. 6 is the figure of kind that shows the initial consonant of Chinese.
Fig. 7 is the figure of kind that shows the simple or compound vowel of a Chinese syllable of Chinese.
Fig. 8 is the figure of an example that shows the combination (phonetic composition rule) of initial consonant and simple or compound vowel of a Chinese syllable.
Fig. 9 shows and moves the figure of picture state of the 1st corresponding program from the processing that is input to conversion of embodiment 1.
Figure 10 shows and moves the figure of picture state of the 2nd corresponding program from the processing that is input to conversion of embodiment 1.
Figure 11 shows and moves the figure of picture state of the 3rd corresponding program from the processing that is input to conversion of embodiment 1.
Figure 12 shows and moves the figure of picture state of the 4th corresponding program from the processing that is input to conversion of embodiment 1.
Figure 13 is a process flow diagram of showing the conversion process action in the embodiment 1.
Figure 14 is the block scheme of displaying as the function formation of the embodiment 2 of above-mentioned Chinese transition processing device.
Figure 15 shows and moves the figure of picture state of the 1st corresponding program from the processing that is input to conversion of embodiment 2.
Figure 16 shows and moves the figure of picture state of the 2nd corresponding program from the processing that is input to conversion of embodiment 2.
Figure 17 is a process flow diagram of showing the conversion process action of embodiment 2.
Figure 18 is the presentation group process flow diagram of the conversion process action under the situation of stating embodiment 2 and above-mentioned embodiment 1 that closes.
Below, with reference to description of drawings embodiment of the present invention.
(embodiment 1)
Fig. 3 shows the block scheme that the system of Chinese input transition processing device of the present invention constitutes.This device is the device that the phonetic (alphabetic string) of input expression Chinese pronunciation afterwards is transformed to this phonetic Chinese character, possesses the function of the alphabetic string prediction subsequent character string of importing relatively now with defined terms when phonetic is imported especially.In embodiment 1, the condition of so-called afore mentioned rules is meant the invalid situation of phonetic of input.In other words, do not set up the input state of (not finishing), predict the phonetic of correct alphabetic string as the follow-up alphabetic string that is transfused to before this by in input process, detecting phonetic.
And then this device for example reads in the program on the recording medium that is recorded in disk etc., by the computer realization by this programmed control action.
As shown in Figure 3, the Chinese input processing device in the present embodiment is made of CPU11, storer 12, input media 13, display device 14, external memory 15, printing equipment 16, communicator 17.
CPU11 is all parts of action of this device of control, moves by the starting that is stored in program in the storer 12.And then, as the function that realizes according to the program that is stored in the storer 12, the word processor of employing application program etc. is arranged.
Storer 12 for example is made of ROM and RAM, is stored in this device the data of the various programs used and font (comprising the Chinese font) etc.In this storer 12, except the program area 12a of the routine data that is used to store the application program that realizes word processing etc., also be provided with input buffer 12b, candidate impact damper 12c, archive buffer 12d etc.
Input buffer 12b storage representation is used for documenting and the phonetic alphabet string of the pronunciation of the Chinese character imported.Candidate impact damper 12c stores the conversion candidate of the Chinese character that obtains by the phonetic Chinese character change according to the input alphabet string.The file data that archive buffer 12d storage constitutes with Chinese character.
Input media 13 for example is made of keyboard, be that this device is shown device with data inputs, be used to carry out as the phonetic of the pronunciation mark of Chinese input, this phonetic that is transfused to is carried out phonetic Chinese character change indication (by the indication of " conversion " key operation) etc.
Display device 14 for example is made up of CRT (cathode-ray tube (CRT)) and LCD (LCD), shows alphabetic string by input media 13 inputs and transformation results etc.
External memory 15 for example is made up of HDD (hard disk drive) and CD-ROM (compact disc read-only memory) etc., preserves the data of various programs and file etc.In addition, can also be provided for realizing program of the present invention by the storage medium of this external memory 15.And then the method that provides of program is not limited to recording medium, can also provide via the communication media of network etc.
Printing equipment 16 is used to printing of carrying out by file etc.As this printing equipment 16, can be built in this device, also can be external.In addition, communicator 17 for example carries out receiving control with the transmission of the data of external device (ED) via dedicated lan (LAN (Local Area Network)) and communication network etc.
Then, illustrate that the function that constitutes the Chinese input transition processing device of realization by system shown in Figure 3 constitutes.
Fig. 4 shows that system by Fig. 3 constitutes the block scheme that the function of embodiment 1 of the Chinese input transition processing device of realization constitutes.As shown in Figure 4, this device has: importation 21, control section 22, dictionary retrieving portion 23, Chinese dictionary 24, the collation process of correcting errors part 25, phonetic composition rule table 26, prediction processing section 27, output 28.
In Chinese dictionary 24, relate to the various Chinese characters of Chinese, login the entry of pronunciation that useful phonetic mark records and narrates, the Chinese character corresponding, in addition the information (with reference to Fig. 5) of part of speech etc. with this pronunciation.This Chinese dictionary 24 is stored in the external memory 15 of Fig. 3.
The collation process of correcting errors part 25 when phonetic is imported according to being stored in phonetic composition rule in the phonetic composition rule table 26, checking the processing whether alphabetic string that is transfused to as pronunciation is set up as phonetic.In phonetic composition rule table 26, store combination as predefined initial consonant of phonetic (consonant part) and simple or compound vowel of a Chinese syllable (vowel part) with sheet form.
Fig. 5 shows the formation of Chinese dictionary 24.
In Chinese dictionary 24, login has needed information in the phonetic Chinese character change of pronunciation and entry, part of speech etc. is handled.Pronunciation is with the login of phonetic mark, and the Chinese character with this pronunciation is used as the entry login.And then in practice, also login the information that part of speech and tone etc. are arranged accordingly with pronunciation and entry.
At this, for easy to understand, the phonetic of Framingham language briefly.
In Chinese, for the expression Chinese speech has used the phonetic symbol that is called as phonetic.Phonetic is to use the symbol of 26 letters and specific 2 whole syllables of letter representation Chinese.1 syllable is made up of " initial consonant " and " simple or compound vowel of a Chinese syllable " basically.So-called " initial consonant " is at the consonant of syllable beginning, defined 21 kinds as shown in Figure 6.So-called " simple or compound vowel of a Chinese syllable " is the part except the initial consonant in the syllable, has been defined 35 kinds (er etc. is arranged in fact, in addition) as shown in Figure 7.
In Chinese speech, general 1 syllable is constituted by 1 initial consonant and 1 simple or compound vowel of a Chinese syllable, but because also have cannot stand combination in the reality, so there are 400 kinds approximately.Fig. 8 has showed the part by the syllable kind that constitutes of initial consonant and simple or compound vowel of a Chinese syllable.The combination of representing with " O " among the figure is used as the standard pronunciation of Modern Chinese.And then Fig. 8 only shows the combination of a part, and also has a lot of combinations in practice.In above-mentioned phonetic composition rule table 26, the combination of such initial consonant and simple or compound vowel of a Chinese syllable is stored as the phonetic composition rule.
In pinyin input mode,,, in addition, in input process, do not know the situation of the pronunciation (phonetic alphabet string) that will import in addition so import loaded down with trivial detailsly because the phonetic alphabet string that is constituted by above-mentioned initial consonant and simple or compound vowel of a Chinese syllable is imported as pronunciation.Therefore, in embodiment of the present invention 1, by being that condition is carried out prediction processing when having as the invalid input of phonetic, the input burden that realizes alleviating the user obtains the purpose of desirable Chinese character expeditiously.
Below, the processing action of this device in embodiment 1 is described.
When the alphabetic string of the pronunciation of having imported the Chinese character of representing Chinese by the importation 21 of Fig. 4, in the collation process part 25 of correcting errors, check this input alphabet string and whether set up as phonetic.Then, when detecting when being false as phonetic, promptly, the moment when in input process, detecting the input state of not setting up (not finishing), begin to carry out prediction processing by prediction processing section 27, according to the alphabetic string retrieval Chinese dictionary 24 that is transfused to before this, prediction comprises the alphabetic string of the phonetic existence of above-mentioned input alphabet string.And then, this phonetic alphabet string (prediction candidate) is carried out the dictionary retrieval as the input of dictionary retrieving portion 23, the candidate of the Chinese character that obtains by this dictionary retrieval is prompted to the user by output 28.
In addition, in when input, under situation about having, carry out common conversion process according to the alphabetic string that be transfused to this moment from user's conversion indication (pressing transfer key 21a etc.).
At this, with the concrete example explanation.
Fig. 9 to Figure 12 shows and moves the figure of picture state of each corresponding program from the processing that is input to conversion of embodiment 1, Fig. 9 is the picture state of the 1st program, Figure 10 is the picture state of the 2nd program, and Figure 11 is the picture state of the 3rd program, and Figure 12 is the picture state of the 4th program.
Suppose that phonetic input is called the Chinese-character pronunciation of being made up of 1 syllable of " teng ".At first, as shown in Figure 9, under the state of having set the phonetic input pattern, accept input from the user.In the example of Fig. 9, input is called the letter of " t ".Remained on input sequence among the input buffer 12b shown in Figure 3 at this letter that is transfused to.And then the CL among the figure is a cursor, represents present input position.UB is a underscore, represents present transforming object scope.In addition, the 31st, present input pattern is represented in the input pattern display part.
For this initial input alphabet (the 1st letter), also can correct errors and check according to the phonetic composition rule.But, in the input of the 1st letter that starts, be false as phonetic mostly, start to correct errors immediately and check function, begin the input prediction.In this early stage input prediction, because a lot of prediction candidates occur, so preferably control is corrected errors and checked function and do not start in the 1st letter input at least.
Then, as shown in figure 10, suppose to have carried out being called the input of " te ".This input alphabet string is delivered to the collation process part 25 of the correcting errors collation process of correcting errors.In this case, in phonetic composition rule shown in Figure 8, exist, set up inoperative prediction processing as phonetic so be judged as the input alphabet string this moment because be called the phonetic (t is an initial consonant, and e is a simple or compound vowel of a Chinese syllable) of " te ".
Then, as shown in figure 11, suppose to have carried out " ten " this input.If this input alphabet string is delivered to the collation process part 25 of the correcting errors collation process of correcting errors,, is false as phonetic so be judged as the input alphabet string because " ten " this phonetic does not exist in phonetic composition rule shown in Figure 8.Therefore, this input alphabet string is delivered to prediction processing section 27 and carry out prediction processing.In this case, in Chinese dictionary 24 shown in Figure 5, " teng " arranged as comprising " ten " this phonetic alphabet string.Therefore, " teng " delivered to dictionary retrieving portion 23 as the prediction candidate corresponding with this input alphabet string carry out the dictionary retrieval process, its result is prompted to the user by output 28.
Figure 12 is a picture of showing the transformation results that obtains by the input prediction.Among the figure 32 is candidate guide look pictures, showed the guide look of the conversion candidate when being pronunciation with " teng ".And then, also can be included in " teng " as the phonetic alphabet string that obtain as the prediction candidate in this conversion candidate.
In addition, the user also can carry out common conversion process, promptly by under the situation of pushing transfer key 21a indication conversion when in input, the alphabetic string of input before carving is at this moment delivered to dictionary retrieving portion 23 retrieval dictionaries as transforming object, its result is prompted to the user as the conversion candidate.
Figure 13 is a process flow diagram of showing the conversion process action in the embodiment 1.
By the importation 21 of Fig. 4, when having imported the alphabetic string of the pronunciation that becomes transforming object (steps A 11), control section 22 judges whether conversion indication (steps A 12) is arranged after the input of this pronunciation alphabetic string.Under the situation that the conversion indication is arranged, promptly, clearly indicate under the situation of phonetic Chinese character change (Yes of steps A 12) by pushing the transfer key 21a that is set on the importation 21 the user, control section 22 is carried out common conversion process (steps A 12 → A16, A17) by this input alphabet string being delivered to dictionary retrieving portion 23.
At this, under the situation that conversion indication is being arranged after the input of pronunciation alphabetic string (No of steps A 12), control section 22 is delivered to the collation process part 25 of correcting errors to this input alphabet string and is carried out the phonetic processing (steps A 13) of correcting errors.In this case, as mentioned above,, correct errors and check so be arranged to not carry out phonetic because many prediction candidates in the 1st initial letter, occur.
In the collation process part 25 of correcting errors, when importing, per 1 letter of the input alphabet string that gives from control section 22, judges whether this input alphabet string is set up as phonetic with the phonetic composition rule contrast that is stored in the phonetic composition rule table 26.That is, judge that whether the alphabetic string that is transfused to now exists, and is transmitted back to control section 22 to this judged result in the phonetic composition rule.If control section 22 receives the result (Yes of steps A 14) that the input alphabet string is set up as phonetic from the collation process part 25 of correcting errors, then wait for next input and carry out above-mentioned same processing (steps A 14 → A11).
On the other hand, if control section 22 receives the input alphabet string as the invalid result of phonetic (No of steps A 14) from the collation process part 25 of correcting errors, then this input alphabet string is delivered to prediction processing section 27 and carry out prediction processing (steps A 15).In prediction processing section 27, by according to the input alphabet string retrieval Chinese dictionary 24 that gives from control section 22, behind this input alphabet string, make the letter of additional suitable or the prediction candidate of alphabetic string, it is returned to control section 22.Specifically, for example for " ten " this input alphabet string,, make " teng " this alphabetic string as the prediction candidate in " ten " back additional " g "." teng " logined the pronunciation mark of the Chinese character on Chinese dictionary 24 in advance.
If control section 22 receives the alphabetic string that obtains as the prediction candidate from prediction processing section 27, then it is delivered to dictionary retrieving portion 23 as transforming object and carry out dictionary retrieval process (steps A 16).In dictionary retrieving portion 23, retrieve Chinese dictionary 24 according to the alphabetic string that obtains as above-mentioned prediction candidate, this alphabetic string is extracted out from Chinese dictionary 24 as the entry (Chinese character) that pronunciation had be transmitted back to control section 22.Control section 22 is exported (steps A 17) to the entry that obtains by dictionary retrieving portion 23 as the conversion candidate from output 28.In this case, as the conversion candidate that obtains by prediction processing, for example guide look is showed on candidate shown in Figure 12 guide look picture 32, by the user from wherein selecting.
Like this, when being false as phonetic in when input, prediction comprises the phonetic alphabet string of the alphabetic string that is transfused to before this, by predict candidate output transform result according to this, just can be for example have " ... ng " like this during the pronunciation of the Chinese character of the phonetic alphabet string of length at input suffix (simple or compound vowel of a Chinese syllable part), whole alphabetic string of input Pinyin not, and in this input process, obtain transformation results.Thus, can alleviate user's input burden, in addition, even can not obtain desirable Chinese character as transformation results under the situation of whole pronunciation knowing yet.
And then, the method for the time unconditionally carrying out prediction processing in input is also arranged, if but unconditionally carry out prediction processing down this, then for example import 1 letter and constantly begin to predict (being called as association) the user.Therefore, this candidate occurs many, instead conversion efficiency is reduced.In contrast, be that condition begins prediction (except the 1st letter of suppose to start) under situation of the present invention because when being false as phonetic, so can the alphabetic string that narrow down to a certain degree be enumerated as the prediction candidate according to this alphabetic string of importing constantly.Thereby, in output during with the corresponding transformation results of this prediction candidate, the desired Chinese character of selection from this transformation results rapidly.
In addition, in above-mentioned embodiment 1, illustrate, but under the situation of the Chinese-character pronunciation that input is made up of a plurality of syllables, also can be suitable for the example under the situation of importing 1 Chinese-character pronunciation of 1 syllable.In this case, differentiate the syllable-boundary limit of input alphabet and handle each letter, just can avoid and when the 1st syllable, begin to predict if be arranged to the limit.
Specifically, for example, suppose the pronunciation of input by the Chinese character of these 2 syllables compositions of " jia/ting " (separation of "/" expression syllable does not have in practice).In the input of " jia " of the 1st syllable, " j " of beginning letter by way of exception, " ji " that follows is because set up (because existing) as phonetic, so do not begin prediction in the phonetic composition rule." ji " then is because also set up as phonetic, so also do not begin prediction.
At this, when the user had imported " a " of " jia ", can be judged as was the separation (syllable-boundary) of 1 syllable.At this, then the 1st syllable, specifically since the input alphabet of the 2nd syllable carry out again phonetic correct errors check.In this case, being judged as " tin " when user input " ... tin " is false as phonetic and begins prediction.Thus, import last letter " g " before, from Chinese dictionary 24, obtain " jiating " this alphabetic string as the prediction candidate the user.Can export suitable with it Chinese character as transformation results.
And then so-called " being false as phonetic " be that expression is not being set up in the input process of (not finishing) as phonetic, but it also comprises the situation that the user violates the mistake input of phonetic composition rule.Like this, import at user error under the situation of pronunciation alphabetic string, correct errors with above-mentioned the same phonetic and check function operation, begin prediction, but because can not obtain this candidate, so can be used as fault processing.
(embodiment 2)
Below, embodiment of the present invention 2 are described.
In above-mentioned embodiment 1, be that condition begins prediction when being false as phonetic in when input.In contrast, in embodiment 2, it is characterized in that: as the basis, is a certain alphabetical number that is set (user can set arbitrarily) that condition begins prediction when surpassing the alphabetical number of setting with the input alphabet string.
Figure 14 shows as the system by Fig. 3 to constitute the block scheme that the function of embodiment 2 of the Chinese input transition processing device of realization constitutes.And then, on the part identical, mark same-sign, at this explanation difference with Fig. 4 (formation of embodiment 1).
In Figure 14 and Fig. 4 difference be that the collation process part 25 that replaces correcting errors is provided with alphabetical number and sets processing section 29 and append alphabetical number setting key 21b on importation 21.The letter number is set processing section 29, sets the processing of the alphabetical number of the condition that becomes the prediction beginning.This letter number is except the value that is set as default value in advance, and by pushing of above-mentioned alphabetical number setting key 21b, the user can set arbitrarily.
Below, the processing action of this device in the embodiment 2 is described.
When the alphabetic string of the Chinese-character pronunciation of representing Chinese by importation 21 inputs of Figure 14, in alphabetical number setting processing section 29, whether check present input alphabet number above setting alphabetical number.Surpass under the situation of setting alphabetical number at the input alphabet number, by prediction processing section 27 beginning prediction processing, according to the alphabetic string retrieval Chinese dictionary 24 of input before this, the alphabetic string that prediction exists as the phonetic that comprises above-mentioned input alphabet string.And then, this phonetic alphabet string (prediction candidate) is carried out the dictionary retrieval as the input of dictionary retrieving portion 23, the candidate of the Chinese character that is obtained by this dictionary retrieval is prompted to the user with output 28.
In addition, in when input, under the situation that conversion indication from the user (transfer key 21a push etc.) is arranged, suppose to carry out common conversion process according to the alphabetic string that import this moment.At this, lift the concrete example explanation.
Figure 15 and Figure 16 be and figure from the picture state of each corresponding program of the processing action that inputs to conversion of embodiment 2, and Figure 15 shows the 1st program picture state, and Figure 16 shows the picture state of the 2nd program.
Now, suppose the pronunciation of phonetic input by the Chinese character of " huang " this syllable formation.At first, as shown in figure 15, under the state of having set the phonetic input pattern, accept input from the user.In the example of Figure 15, input " hua " this alphabetic string.Here the alphabetic string that is transfused to keeps each letter according to input sequence in input buffer 12b shown in Figure 3.And then the CL among the figure is a cursor, represents present input position.UB is a underscore, represents present transforming object scope.In addition, the 31st, present input pattern is represented in the input pattern display part.
At this,, set the alphabetical number of regulation at first as the default value of system.For example set " 3 letters of letter ".At this, when importing, in alphabetical number setting processing section 29, check the input alphabet number and whether surpass the alphabetical number of setting, when the input alphabet number surpasses the alphabetical number of setting, this input alphabet string is delivered to prediction processing section 27 carry out prediction processing.
For example, be under the situation of 3 letters when setting alphabetical number, the moment when being input as " hua " → " huan " (having imported the 4th when alphabetical), starting prediction processing.In this case, in Chinese dictionary 24 as shown in Figure 5,, " huan " and " huang " arranged as the phonetic alphabet string that comprises " huan ".At this, they are delivered to dictionary retrieving portion 23 as the prediction candidate corresponding with this input alphabet string carry out the dictionary retrieval process, its result is prompted to the user by output 28.
Figure 16 is a picture of predicting the transformation results that obtains by input.Among the figure 33 is candidate guide look pictures, and guide look is showed " huan " and " huang " as the conversion candidate under the situation of pronunciation.And then also can be included in this conversion candidate what obtain as the prediction candidate is " huan " and " huang " of phonetic alphabet string.
In addition, under the situation of thinking change setting letter number, can use the user to control the alphabetical arbitrarily number of such function setting.
In addition, also can carry out common conversion process, that is, when input, work as the user by under the situation of pushing transfer key 21a indication conversion, the alphabetic string of input before carving is at this moment delivered to dictionary retrieving portion 23 retrieval dictionaries as transforming object, its result is prompted to the user as the conversion candidate.
Figure 17 is the process flow diagram that is illustrated in the conversion process action in the embodiment 2.
When importation 21 inputs by Fig. 4 become the pronunciation alphabetic string of transforming object (step B11), control section 22 judges whether conversion indication (step B12) is arranged after the input of this pronunciation alphabetic string.Under the situation that the conversion indication is arranged, promptly, by being set at push (Yes of step B12) under the situation of clearly indicating phonetic Chinese character change of transfer key 21a on the importation 21, control section 22 is carried out common conversion process (step B12 → B17, B18) by this input alphabet string being delivered to dictionary retrieving portion 23 the user.
At this, when under the situation that does not have the conversion indication after the input of pronunciation alphabetic string (No of step B12), control section 22 judges whether to set indication (step B13) by the alphabetical number of pushing generation of alphabetical number setting key 21b.Having alphabetical number to set under the situation of indication (Yes of step B13), control section 22 is delivered to alphabetical number to the alphabetical number of user's appointment and is set the change processing (step B14) that alphabetical number is set in processing section 29.
In addition, in alphabetical number setting processing section 29, receive the alphabetic string of input now from control section 22, relatively this input alphabet number and the alphabetical number of setting are transmitted back to control section 22 to its result.If control section 22 is set processing section 29 from alphabetical number and is received the input alphabet number in the result (No of step B15) who sets below the alphabetical number, and the then above-mentioned same processing of wait next one input carrying out (step B15 → B11).
On the other hand, receive the result (Yes of step B15) that the input alphabet number surpasses the alphabetical number of setting, just this input alphabet string is delivered to prediction processing section 27 and carry out prediction processing (step B16) if control section 22 is set processing section 29 from alphabetical number.In prediction processing section 27, according to the input alphabet string that gives from control section 22 retrieval Chinese dictionary 24, this input alphabet string after, make and added the letter that suits or the prediction candidate of alphabetic string as phonetic, he is transmitted back to control section 22.Specifically, for example for " huan " this input alphabet string, except " huan ", be formed in " huang " this alphabetic string of having added " g " after this " huan "." huan " and " huang " is the pronunciation mark that is logged the Chinese character in Chinese dictionary 24 in advance.
If control section 22 is obtained the alphabetic string that obtains as the prediction candidate from prediction processing section 27, then it is delivered to dictionary retrieving portion 23 as transforming object and carry out dictionary retrieval process (step B17).In dictionary retrieving portion 23, the alphabetic string retrieval Chinese dictionary 24 according to obtaining as above-mentioned prediction candidate is transmitted back to control section 22 extracting out as the entry (Chinese character) of pronunciation with this alphabetic string from Chinese dictionary 24.Control section 22 is exported (step B18) to the entry that obtains by dictionary retrieving portion 23 as the conversion candidate with output 28.In this case, as being the conversion candidate that obtains by prediction processing, for example guide look is showed on candidate guide look picture 33 shown in Figure 16, allows the user from wherein selecting.
Like this, by the input alphabet number is carried out prediction processing as condition, just can adjust the moment of prediction.Thereby, if the moment that the alphabetical number that begins to predict is increased make prediction postpones, just can obtain having dwindled the prediction candidate of certain limit, just can improve conversion efficiency by carrying out phonetic Chinese character change according to this prediction candidate.
And then, in above-mentioned embodiment 2, be the change of in the input process of pronunciation alphabetic string, setting alphabetical number, but also can be before input pronunciation alphabetic string, by pushing change setting letter number such as alphabetical number setting key 21b.At this moment the setting letter number that is changed is maintained at alphabetical number and sets in the processing section 29, reference when being imported each letter of pronunciation alphabetic string by the user.
In addition, also can make up above-mentioned embodiment 2 and above-mentioned embodiment 1.
That is, constitute, can in the formation of Fig. 4, append the alphabetical number of Figure 14 and set processing section 29 as device.In this formation, shown in the process flow diagram of Figure 18, at first, set processing section 29 by alphabetical number and judge whether the alphabetical number of the pronunciation alphabetic strings of user's input when the input has surpassed and set alphabetical number (step C11～C15).Above-mentioned setting letter number can be by the user by outside indication change (step C13, C14) arbitrarily.Surpass under the situation of setting alphabetical number (Yes of step C15) when the input alphabet number, start the collation process of correcting errors (step C16) of the phonetic that is undertaken by the collation process part 25 of correcting errors.In the collation process part 25 of correcting errors,, the later input alphabet of above-mentioned setting letter number is judged whether set up as phonetic with reference to the phonetic composition rule table that is stored in the phonetic composition rule table 26.Then, under invalid situation (No of step C17),, begin prediction processing (step C18) according to the alphabetic string that is transfused to before this by prediction processing section 27 as phonetic.The prediction candidate that is obtained by this prediction processing is sent to dictionary retrieving portion 23 as transforming object, from Chinese dictionary 24, corresponding Chinese character is extracted out as transformation results, by output 28 outputs (step C19, C20).
Like this, if subsidiary condition are carried out correcting errors of phonetic and are checked on the alphabetical number before the input prediction beginning, then, check the input of such pronunciation alphabetic string for behind the 1st syllable, correcting errors immediately, the moment that can delay prediction begins at the pronunciation mark of the Chinese character of forming by a plurality of syllables.Thereby, can prevent to cause the many of candidate number appearance owing to import prediction in early days.
In addition, in above-mentioned embodiment, the situation of the collation process of stipulating has been described, but the unit of this collation process is not limited to import 1 letter at every turn, also can carry out at every turn when each letter of input pronunciation alphabetic string when importing the pronunciation alphabetic string.
The present invention is not limited to above-mentioned each embodiment, the implementation phase in the scope that does not break away from its purport, various distortion can be arranged.And then, in above-mentioned each embodiment, include the invention in each stage, by the suitable combination of disclosed a plurality of inscapes, can extract various inventions out.For example, even eliminate several inscapes the whole inscapes shown in embodiments, also can solve in the effect described in " problem that invention will solve ", can obtain under the situation of the effect described in " effect of invention " hurdle, can extract the formation of having eliminated its inscape out as invention.
And then, in the method described in each above-mentioned embodiment, as the program that can carry out by computing machine, for example be written in the recording medium of disk (floppy disk, hard disk etc.), CD (CD-ROM, DVD etc.), semiconductor memory etc., be applicable to various devices, also can transmit and be applicable to various devices by communication media.Realize the computing machine of this device, read in the program that is recorded in the recording medium,, carry out above-mentioned processing by by this programmed control action.
If adopt the present invention as mentioned above, because check alphabetic string when being arranged in each the input as the pronunciation input, the moment when satisfying rated condition, alphabetic string according to input is before this predicted the alphabetic string that exists as phonetic, carrying out phonetic Chinese character change according to this predicted letters string handles, so when importing, can alleviate its input burden, can obtain desirable Chinese character expeditiously with common pinyin input mode.
Claims (17)
1, a kind of Chinese input transition processing device, it is alphabetic string with the Chinese-character pronunciation of pinyin input mode input expression Chinese, the alphabetic string of this input is transformed to the Chinese input transition processing device of corresponding Chinese character, it is characterized in that comprising: input block (21) is used to import the alphabetic string that becomes transforming object; The alphabetic string by this input block (21) input is checked in condition judgment unit (25) when each input, judge whether to satisfy defined terms; Predicting unit (27) in the moment when being judged as the condition that satisfies afore mentioned rules by this condition judgment unit (25), is predicted the alphabetic string that exists as phonetic according to the alphabetic string of input before this; Converter unit (23) is transformed to corresponding Chinese character to the predicted letters string that is obtained by this predicting unit (27); Output unit (28) is exported the Chinese character that is obtained by this converter unit (23) as transformation results.
2, a kind of Chinese input transition processing device, it is alphabetic string with the Chinese-character pronunciation of pinyin input mode input expression Chinese, the alphabetic string of this input is transformed to the Chinese input transition processing device of corresponding Chinese character, it is characterized in that comprising: input block (21) is used to import the alphabetic string that becomes transforming object; Phonetic is corrected errors and is checked unit (25), checks the alphabetic string by this input block (21) input when each input alphabet, judges whether the input alphabet string is set up as phonetic; Predicting unit (27) is checked unit (25) and is judged as the input alphabet string when being false as phonetic being corrected errors by this phonetic, the alphabetic string that exists as phonetic according to the alphabetic string prediction of input before this; Converter unit (23) is transformed to corresponding Chinese character to the predicted letters string that is obtained by this predicting unit (27); Output unit (28) is exported the Chinese character that is obtained by this converter unit (23) as transformation results.
3, Chinese input transition processing device as claimed in claim 2, it is characterized in that: above-mentioned phonetic is corrected errors and is checked unit (25), according to the phonetic composition rule of the combination of the initial consonant of pre-defined phonetic and simple or compound vowel of a Chinese syllable, judge whether the input alphabet string is set up as phonetic.
4, Chinese input transition processing device as claimed in claim 2, it is characterized in that: above-mentioned phonetic is corrected errors and is checked unit (25), is controlled so as to the establishment judgement of not carrying out phonetic at least in the moment that 1 letter that starts is transfused to.
5, Chinese input transition processing device as claimed in claim 2, it is characterized in that: above-mentioned predicting unit (27), obtain the candidate with the corresponding predicted letters string of the alphabetic string that is transfused to before this from the dictionary of the entry of logining pronunciation that useful phonetic mark records and narrates and the Chinese character corresponding with its pronunciation.
6, a kind of Chinese input transition processing device, it is alphabetic string with the Chinese-character pronunciation of pinyin input mode input expression Chinese, the alphabetic string of this input is transformed to the Chinese input transition processing device of corresponding Chinese character, it is characterized in that comprising: input block (21) is used to import the alphabetic string that becomes transforming object; The letter number is checked unit (29), checks the alphabetic string by this input block (21) input when each input alphabet, judges whether the input alphabet number has surpassed the alphabetical number of setting; Predicting unit (27) is judged as the input alphabet number and has surpassed when setting alphabetical number being checked unit (29) by this letter number, the alphabetic string that exists as phonetic according to the alphabetic string prediction of input before this; Converter unit (23) is transformed to corresponding Chinese character to the predicted letters string that is obtained by this predicting unit (27); Output unit (28) is exported the Chinese character that is obtained by this converter unit (23) as transformation results.
7, Chinese input transition processing device as claimed in claim 6 is characterized in that: above-mentioned alphabetical number is checked the setting letter number of unit (29), can be by outside indication change arbitrarily.
8, Chinese input transition processing device as claimed in claim 6, it is characterized in that: above-mentioned predicting unit (27), obtain the candidate with the corresponding predicted letters string of the alphabetic string that is transfused to before this from the dictionary of the entry of logining pronunciation that useful phonetic mark records and narrates and the Chinese character corresponding with this pronunciation.
9, a kind of Chinese input transition processing device, it is alphabetic string with the Chinese-character pronunciation of pinyin input mode input expression Chinese, the alphabetic string of this input is transformed to the Chinese input transition processing device of corresponding Chinese character, it is characterized in that comprising: input block (21) is used to import the alphabetic string that becomes transforming object; The letter number is checked unit (29), checks the alphabetic string by this input block (21) input when each input alphabet, judges whether the input alphabet number has surpassed the alphabetical number of setting; Phonetic is corrected errors and is checked unit (25), is judged as the input alphabet number and has surpassed when setting alphabetical number being checked unit (29) by this letter number, judges whether set up as phonetic for the alphabetic string of later input; Predicting unit (27) is checked unit (25) and is judged as the input alphabet string when being false as phonetic being corrected errors by this phonetic, the alphabetic string that exists as phonetic according to the alphabetic string prediction of input before this; Converter unit (23) is transformed to corresponding Chinese character to the predicted letters string that is obtained by this predicting unit (27); Output unit (28) is exported the Chinese character that is obtained by this converter unit (23) as transformation results.
10, a kind of Chinese input transform process method, it is the alphabetic string that is used for the Chinese-character pronunciation of pinyin input mode input expression Chinese, the alphabetic string of this input is transformed to the Chinese input transform process method of corresponding Chinese character, it is characterized in that comprising: when each input alphabet, check alphabetic string, judge whether to satisfy rated condition (A11～A14) as the pronunciation input; In the moment that is judged as when satisfying the afore mentioned rules condition, the alphabetic string (A15) that exists as phonetic according to the alphabetic string prediction that is transfused to before this; The predicted letters string that obtains predicting the outcome as this is transformed to corresponding Chinese character (A16, A17).
11, a kind of Chinese input transform process method, it is the alphabetic string that is used for the Chinese-character pronunciation of pinyin input mode input expression Chinese, the alphabetic string of this input is transformed to the Chinese input transform process method of corresponding Chinese character, it is characterized in that comprising: when each input alphabet, check alphabetic string, judge whether the input alphabet string sets up (A11～A14) as phonetic as the pronunciation input; Be judged as the input alphabet string when being false, the alphabetic string (A15) that exists as phonetic according to the alphabetic string prediction that is transfused to before this as phonetic; The predicted letters string that obtains predicting the outcome as it is transformed to corresponding Chinese character (A16, A17).
12, a kind of Chinese input transform process method, it is the alphabetic string that is used for the Chinese-character pronunciation of pinyin input mode input expression Chinese, the alphabetic string of this input is transformed to the Chinese input transform process method of corresponding Chinese character, it is characterized in that comprising: when each input alphabet, check alphabetic string, judge whether the input alphabet number has surpassed the alphabetical number of setting (B11～B15) as the pronunciation input; When being judged as the input alphabet number, according to the alphabetic string (B16) of the alphabetic string prediction that is transfused to before this as the phonetic existence above the alphabetical number of setting; The predicted letters string that obtains predicting the outcome as it is transformed to corresponding Chinese character (B17, B18).
13, a kind of Chinese input transform process method, it is the alphabetic string that is used for the Chinese-character pronunciation of pinyin input mode input expression Chinese, the alphabetic string of this input is transformed to the Chinese input transform process method of corresponding Chinese character, it is characterized in that comprising: when each input alphabet, check alphabetic string, judge whether the input alphabet number surpasses the alphabetical number of setting (C11～C15) as the pronunciation input; Surpassed when setting alphabetical number being judged as the input alphabet number, to judging whether set up (C16, C17) as phonetic with the alphabetic string of later input; Be judged as the input alphabet string when being false, the alphabetic string (C18) that exists as phonetic according to the alphabetic string prediction that is transfused to before this as phonetic; The predicted letters string that obtains predicting the outcome as it is transformed to corresponding Chinese character (C19, C20).
14, a kind of computer readable recording medium storing program for performing that has program recorded thereon, make the alphabetic string that possesses with the Chinese-character pronunciation of pinyin input mode input expression Chinese, the computing machine that the alphabetic string of this input is transformed to the function of corresponding Chinese character is carried out following the processing: check the alphabetic string that is transfused to as pronunciation when each input alphabet, judge whether to satisfy defined terms (A11～A14); The moment when being judged as the condition that satisfies afore mentioned rules is according to the alphabetic string (A15) of the alphabetic string prediction that is transfused to before this as the phonetic existence; The predicted letters string that obtains predicting the outcome as it is transformed to suitable Chinese character (A16, A17).
15, a kind of computer readable recording medium storing program for performing that has program recorded thereon, make the alphabetic string that possesses with the Chinese-character pronunciation of pinyin input mode input expression Chinese, the computing machine that the alphabetic string of this input is transformed to the function of corresponding Chinese character is carried out following the processing: check the alphabetic string that is transfused to as pronunciation when each input, judge whether the input alphabet string sets up (A11～A14) as phonetic; Be judged as the input alphabet string when being false, the alphabetic string (A15) that exists as phonetic according to the alphabetic string prediction that is transfused to before this as phonetic; The predicted letters string that obtains predicting the outcome as it is transformed to suitable Chinese character (A16, A17).
16, a kind of computer readable recording medium storing program for performing that has program recorded thereon, make the alphabetic string that possesses with the Chinese-character pronunciation of pinyin input mode input expression Chinese, the computing machine that the alphabetic string of this input is transformed to the function of corresponding Chinese character is carried out following the processing: check the alphabetic string that is transfused to as pronunciation when each input alphabet, judge whether the input alphabet number has surpassed the alphabetical number of setting (B11～B15); When being judged as the input alphabet number, according to the alphabetic string (B16) of the alphabetic string prediction that is transfused to before this as the phonetic existence above the alphabetical number of setting; The predicted letters string that obtains predicting the outcome as it is transformed to suitable Chinese character (B17, B18).
17, a kind of computer readable recording medium storing program for performing that has program recorded thereon, make the alphabetic string that possesses with the Chinese-character pronunciation of pinyin input mode input expression Chinese, the alphabetic string of this input is transformed to the computing machine of the function of corresponding Chinese character, carry out following the processing: when each input alphabet, check the alphabetic string that is transfused to as pronunciation, judge whether the input alphabet number surpasses the alphabetical number of setting (C11～C15); When being judged as the input alphabet number, judge whether set up (C16, C17) as phonetic for the alphabetic string of later input above the alphabetical number of setting; Be judged as the input alphabet string when being false, the alphabetic string (C18) that exists as phonetic according to the alphabetic string prediction of input before this as phonetic; The predicted letters string that obtains predicting the outcome as it is transformed to suitable Chinese character (C19, C20).
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP194739/2000 | 2000-06-28 | ||
| JP2000194739A JP2002014954A (en) | 2000-06-28 | 2000-06-28 | Chinese language inputting and converting processing device and method, and recording medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN1330333A true CN1330333A (en) | 2002-01-09 |
Family
ID=18693512
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 01122612 Pending CN1330333A (en) | 2000-06-28 | 2001-06-26 | Chinese input transformation device and input transformation processing method and recording medium |
Country Status (2)
| Country | Link |
|---|---|
| JP (1) | JP2002014954A (en) |
| CN (1) | CN1330333A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100342373C (en) * | 2002-12-27 | 2007-10-10 | 欧姆龙株式会社 | Language input method and system |
| CN108427508A (en) * | 2017-02-15 | 2018-08-21 | 北京搜狗科技发展有限公司 | Input method and device, the method and apparatus for establishing LAN dictionary |
| CN108700953A (en) * | 2016-03-15 | 2018-10-23 | 雅马哈株式会社 | Auxiliary input device, smart phone and input aiding method |
Families Citing this family (122)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8645137B2 (en) | 2000-03-16 | 2014-02-04 | Apple Inc. | Fast, language-independent method for user authentication by voice |
| US7395203B2 (en) | 2003-07-30 | 2008-07-01 | Tegic Communications, Inc. | System and method for disambiguating phonetic input |
| US8677377B2 (en) | 2005-09-08 | 2014-03-18 | Apple Inc. | Method and apparatus for building an intelligent automated assistant |
| US9318108B2 (en) | 2010-01-18 | 2016-04-19 | Apple Inc. | Intelligent automated assistant |
| US8977255B2 (en) | 2007-04-03 | 2015-03-10 | Apple Inc. | Method and system for operating a multi-function portable electronic device using voice-activation |
| US9330720B2 (en) | 2008-01-03 | 2016-05-03 | Apple Inc. | Methods and apparatus for altering audio output signals |
| US8996376B2 (en) | 2008-04-05 | 2015-03-31 | Apple Inc. | Intelligent text-to-speech conversion |
| US10496753B2 (en) | 2010-01-18 | 2019-12-03 | Apple Inc. | Automatically adapting user interfaces for hands-free interaction |
| US20100030549A1 (en) | 2008-07-31 | 2010-02-04 | Lee Michael M | Mobile device having human language translation capability with positional feedback |
| WO2010067118A1 (en) | 2008-12-11 | 2010-06-17 | Novauris Technologies Limited | Speech recognition involving a mobile device |
| US9858925B2 (en) | 2009-06-05 | 2018-01-02 | Apple Inc. | Using context information to facilitate processing of commands in a virtual assistant |
| US20120309363A1 (en) | 2011-06-03 | 2012-12-06 | Apple Inc. | Triggering notifications associated with tasks items that represent tasks to perform |
| US10241752B2 (en) | 2011-09-30 | 2019-03-26 | Apple Inc. | Interface for a virtual digital assistant |
| US10241644B2 (en) | 2011-06-03 | 2019-03-26 | Apple Inc. | Actionable reminder entries |
| US9431006B2 (en) | 2009-07-02 | 2016-08-30 | Apple Inc. | Methods and apparatuses for automatic speech recognition |
| US10705794B2 (en) | 2010-01-18 | 2020-07-07 | Apple Inc. | Automatically adapting user interfaces for hands-free interaction |
| US10276170B2 (en) | 2010-01-18 | 2019-04-30 | Apple Inc. | Intelligent automated assistant |
| US10553209B2 (en) | 2010-01-18 | 2020-02-04 | Apple Inc. | Systems and methods for hands-free notification summaries |
| US10679605B2 (en) | 2010-01-18 | 2020-06-09 | Apple Inc. | Hands-free list-reading by intelligent automated assistant |
| US8977584B2 (en) | 2010-01-25 | 2015-03-10 | Newvaluexchange Global Ai Llp | Apparatuses, methods and systems for a digital conversation management platform |
| US8682667B2 (en) | 2010-02-25 | 2014-03-25 | Apple Inc. | User profiling for selecting user specific voice input processing information |
| US10762293B2 (en) | 2010-12-22 | 2020-09-01 | Apple Inc. | Using parts-of-speech tagging and named entity recognition for spelling correction |
| US9262612B2 (en) | 2011-03-21 | 2016-02-16 | Apple Inc. | Device access using voice authentication |
| JP5505360B2 (en) * | 2011-04-20 | 2014-05-28 | カシオ計算機株式会社 | Information display control device and program |
| US10057736B2 (en) | 2011-06-03 | 2018-08-21 | Apple Inc. | Active transport based notifications |
| US8706472B2 (en) * | 2011-08-11 | 2014-04-22 | Apple Inc. | Method for disambiguating multiple readings in language conversion |
| US8994660B2 (en) | 2011-08-29 | 2015-03-31 | Apple Inc. | Text correction processing |
| US10134385B2 (en) | 2012-03-02 | 2018-11-20 | Apple Inc. | Systems and methods for name pronunciation |
| US9483461B2 (en) | 2012-03-06 | 2016-11-01 | Apple Inc. | Handling speech synthesis of content for multiple languages |
| US9280610B2 (en) | 2012-05-14 | 2016-03-08 | Apple Inc. | Crowd sourcing information to fulfill user requests |
| US9721563B2 (en) | 2012-06-08 | 2017-08-01 | Apple Inc. | Name recognition system |
| US9495129B2 (en) | 2012-06-29 | 2016-11-15 | Apple Inc. | Device, method, and user interface for voice-activated navigation and browsing of a document |
| US9576574B2 (en) | 2012-09-10 | 2017-02-21 | Apple Inc. | Context-sensitive handling of interruptions by intelligent digital assistant |
| US9547647B2 (en) | 2012-09-19 | 2017-01-17 | Apple Inc. | Voice-based media searching |
| CN104969289B (en) | 2013-02-07 | 2021-05-28 | 苹果公司 | Voice trigger of digital assistant |
| US9368114B2 (en) | 2013-03-14 | 2016-06-14 | Apple Inc. | Context-sensitive handling of interruptions |
| US10652394B2 (en) | 2013-03-14 | 2020-05-12 | Apple Inc. | System and method for processing voicemail |
| WO2014144579A1 (en) | 2013-03-15 | 2014-09-18 | Apple Inc. | System and method for updating an adaptive speech recognition model |
| US9922642B2 (en) | 2013-03-15 | 2018-03-20 | Apple Inc. | Training an at least partial voice command system |
| WO2014197334A2 (en) | 2013-06-07 | 2014-12-11 | Apple Inc. | System and method for user-specified pronunciation of words for speech synthesis and recognition |
| US9582608B2 (en) | 2013-06-07 | 2017-02-28 | Apple Inc. | Unified ranking with entropy-weighted information for phrase-based semantic auto-completion |
| WO2014197336A1 (en) | 2013-06-07 | 2014-12-11 | Apple Inc. | System and method for detecting errors in interactions with a voice-based digital assistant |
| WO2014197335A1 (en) | 2013-06-08 | 2014-12-11 | Apple Inc. | Interpreting and acting upon commands that involve sharing information with remote devices |
| EP3937002A1 (en) | 2013-06-09 | 2022-01-12 | Apple Inc. | Device, method, and graphical user interface for enabling conversation persistence across two or more instances of a digital assistant |
| US10176167B2 (en) | 2013-06-09 | 2019-01-08 | Apple Inc. | System and method for inferring user intent from speech inputs |
| CN105265005B (en) | 2013-06-13 | 2019-09-17 | 苹果公司 | System and method for the urgent call initiated by voice command |
| WO2015020942A1 (en) | 2013-08-06 | 2015-02-12 | Apple Inc. | Auto-activating smart responses based on activities from remote devices |
| US9620105B2 (en) | 2014-05-15 | 2017-04-11 | Apple Inc. | Analyzing audio input for efficient speech and music recognition |
| US10592095B2 (en) | 2014-05-23 | 2020-03-17 | Apple Inc. | Instantaneous speaking of content on touch devices |
| US9502031B2 (en) | 2014-05-27 | 2016-11-22 | Apple Inc. | Method for supporting dynamic grammars in WFST-based ASR |
| US10170123B2 (en) | 2014-05-30 | 2019-01-01 | Apple Inc. | Intelligent assistant for home automation |
| US9734193B2 (en) | 2014-05-30 | 2017-08-15 | Apple Inc. | Determining domain salience ranking from ambiguous words in natural speech |
| US10078631B2 (en) | 2014-05-30 | 2018-09-18 | Apple Inc. | Entropy-guided text prediction using combined word and character n-gram language models |
| US9842101B2 (en) | 2014-05-30 | 2017-12-12 | Apple Inc. | Predictive conversion of language input |
| US9715875B2 (en) | 2014-05-30 | 2017-07-25 | Apple Inc. | Reducing the need for manual start/end-pointing and trigger phrases |
| US10289433B2 (en) | 2014-05-30 | 2019-05-14 | Apple Inc. | Domain specific language for encoding assistant dialog |
| US9785630B2 (en) | 2014-05-30 | 2017-10-10 | Apple Inc. | Text prediction using combined word N-gram and unigram language models |
| WO2015184186A1 (en) | 2014-05-30 | 2015-12-03 | Apple Inc. | Multi-command single utterance input method |
| US9760559B2 (en) | 2014-05-30 | 2017-09-12 | Apple Inc. | Predictive text input |
| US9633004B2 (en) | 2014-05-30 | 2017-04-25 | Apple Inc. | Better resolution when referencing to concepts |
| US9430463B2 (en) | 2014-05-30 | 2016-08-30 | Apple Inc. | Exemplar-based natural language processing |
| US9338493B2 (en) | 2014-06-30 | 2016-05-10 | Apple Inc. | Intelligent automated assistant for TV user interactions |
| US10659851B2 (en) | 2014-06-30 | 2020-05-19 | Apple Inc. | Real-time digital assistant knowledge updates |
| US10446141B2 (en) | 2014-08-28 | 2019-10-15 | Apple Inc. | Automatic speech recognition based on user feedback |
| US9818400B2 (en) | 2014-09-11 | 2017-11-14 | Apple Inc. | Method and apparatus for discovering trending terms in speech requests |
| US10789041B2 (en) | 2014-09-12 | 2020-09-29 | Apple Inc. | Dynamic thresholds for always listening speech trigger |
| US9886432B2 (en) | 2014-09-30 | 2018-02-06 | Apple Inc. | Parsimonious handling of word inflection via categorical stem + suffix N-gram language models |
| US9668121B2 (en) | 2014-09-30 | 2017-05-30 | Apple Inc. | Social reminders |
| US10127911B2 (en) | 2014-09-30 | 2018-11-13 | Apple Inc. | Speaker identification and unsupervised speaker adaptation techniques |
| US9646609B2 (en) | 2014-09-30 | 2017-05-09 | Apple Inc. | Caching apparatus for serving phonetic pronunciations |
| US10074360B2 (en) | 2014-09-30 | 2018-09-11 | Apple Inc. | Providing an indication of the suitability of speech recognition |
| US10552013B2 (en) | 2014-12-02 | 2020-02-04 | Apple Inc. | Data detection |
| US9711141B2 (en) | 2014-12-09 | 2017-07-18 | Apple Inc. | Disambiguating heteronyms in speech synthesis |
| US9865280B2 (en) | 2015-03-06 | 2018-01-09 | Apple Inc. | Structured dictation using intelligent automated assistants |
| US9886953B2 (en) | 2015-03-08 | 2018-02-06 | Apple Inc. | Virtual assistant activation |
| US9721566B2 (en) | 2015-03-08 | 2017-08-01 | Apple Inc. | Competing devices responding to voice triggers |
| US10567477B2 (en) | 2015-03-08 | 2020-02-18 | Apple Inc. | Virtual assistant continuity |
| US9899019B2 (en) | 2015-03-18 | 2018-02-20 | Apple Inc. | Systems and methods for structured stem and suffix language models |
| US9842105B2 (en) | 2015-04-16 | 2017-12-12 | Apple Inc. | Parsimonious continuous-space phrase representations for natural language processing |
| US10083688B2 (en) | 2015-05-27 | 2018-09-25 | Apple Inc. | Device voice control for selecting a displayed affordance |
| US10127220B2 (en) | 2015-06-04 | 2018-11-13 | Apple Inc. | Language identification from short strings |
| US9578173B2 (en) | 2015-06-05 | 2017-02-21 | Apple Inc. | Virtual assistant aided communication with 3rd party service in a communication session |
| US10101822B2 (en) | 2015-06-05 | 2018-10-16 | Apple Inc. | Language input correction |
| US11025565B2 (en) | 2015-06-07 | 2021-06-01 | Apple Inc. | Personalized prediction of responses for instant messaging |
| US10255907B2 (en) | 2015-06-07 | 2019-04-09 | Apple Inc. | Automatic accent detection using acoustic models |
| US10186254B2 (en) | 2015-06-07 | 2019-01-22 | Apple Inc. | Context-based endpoint detection |
| US10747498B2 (en) | 2015-09-08 | 2020-08-18 | Apple Inc. | Zero latency digital assistant |
| US10671428B2 (en) | 2015-09-08 | 2020-06-02 | Apple Inc. | Distributed personal assistant |
| US9697820B2 (en) | 2015-09-24 | 2017-07-04 | Apple Inc. | Unit-selection text-to-speech synthesis using concatenation-sensitive neural networks |
| US10366158B2 (en) | 2015-09-29 | 2019-07-30 | Apple Inc. | Efficient word encoding for recurrent neural network language models |
| US11010550B2 (en) | 2015-09-29 | 2021-05-18 | Apple Inc. | Unified language modeling framework for word prediction, auto-completion and auto-correction |
| US11587559B2 (en) | 2015-09-30 | 2023-02-21 | Apple Inc. | Intelligent device identification |
| US10691473B2 (en) | 2015-11-06 | 2020-06-23 | Apple Inc. | Intelligent automated assistant in a messaging environment |
| US10049668B2 (en) | 2015-12-02 | 2018-08-14 | Apple Inc. | Applying neural network language models to weighted finite state transducers for automatic speech recognition |
| US10223066B2 (en) | 2015-12-23 | 2019-03-05 | Apple Inc. | Proactive assistance based on dialog communication between devices |
| US10446143B2 (en) | 2016-03-14 | 2019-10-15 | Apple Inc. | Identification of voice inputs providing credentials |
| US9934775B2 (en) | 2016-05-26 | 2018-04-03 | Apple Inc. | Unit-selection text-to-speech synthesis based on predicted concatenation parameters |
| US9972304B2 (en) | 2016-06-03 | 2018-05-15 | Apple Inc. | Privacy preserving distributed evaluation framework for embedded personalized systems |
| US10249300B2 (en) | 2016-06-06 | 2019-04-02 | Apple Inc. | Intelligent list reading |
| US10049663B2 (en) | 2016-06-08 | 2018-08-14 | Apple, Inc. | Intelligent automated assistant for media exploration |
| DK179309B1 (en) | 2016-06-09 | 2018-04-23 | Apple Inc | Intelligent automated assistant in a home environment |
| US10490187B2 (en) | 2016-06-10 | 2019-11-26 | Apple Inc. | Digital assistant providing automated status report |
| US10509862B2 (en) | 2016-06-10 | 2019-12-17 | Apple Inc. | Dynamic phrase expansion of language input |
| US10586535B2 (en) | 2016-06-10 | 2020-03-10 | Apple Inc. | Intelligent digital assistant in a multi-tasking environment |
| US10067938B2 (en) | 2016-06-10 | 2018-09-04 | Apple Inc. | Multilingual word prediction |
| US10192552B2 (en) | 2016-06-10 | 2019-01-29 | Apple Inc. | Digital assistant providing whispered speech |
| DK179415B1 (en) | 2016-06-11 | 2018-06-14 | Apple Inc | Intelligent device arbitration and control |
| DK201670540A1 (en) | 2016-06-11 | 2018-01-08 | Apple Inc | Application integration with a digital assistant |
| DK179343B1 (en) | 2016-06-11 | 2018-05-14 | Apple Inc | Intelligent task discovery |
| DK179049B1 (en) | 2016-06-11 | 2017-09-18 | Apple Inc | Data driven natural language event detection and classification |
| US10664157B2 (en) | 2016-08-03 | 2020-05-26 | Google Llc | Image search query predictions by a keyboard |
| US10043516B2 (en) | 2016-09-23 | 2018-08-07 | Apple Inc. | Intelligent automated assistant |
| US20180173692A1 (en) * | 2016-12-19 | 2018-06-21 | Google Inc. | Iconographic symbol predictions for a conversation |
| US10593346B2 (en) | 2016-12-22 | 2020-03-17 | Apple Inc. | Rank-reduced token representation for automatic speech recognition |
| DK201770439A1 (en) | 2017-05-11 | 2018-12-13 | Apple Inc. | Offline personal assistant |
| DK179496B1 (en) | 2017-05-12 | 2019-01-15 | Apple Inc. | USER-SPECIFIC Acoustic Models |
| DK179745B1 (en) | 2017-05-12 | 2019-05-01 | Apple Inc. | SYNCHRONIZATION AND TASK DELEGATION OF A DIGITAL ASSISTANT |
| DK201770431A1 (en) | 2017-05-15 | 2018-12-20 | Apple Inc. | Optimizing dialogue policy decisions for digital assistants using implicit feedback |
| DK201770432A1 (en) | 2017-05-15 | 2018-12-21 | Apple Inc. | Hierarchical belief states for digital assistants |
| DK179560B1 (en) | 2017-05-16 | 2019-02-18 | Apple Inc. | Far-field extension for digital assistant services |
| CN107329585A (en) * | 2017-06-28 | 2017-11-07 | 北京百度网讯科技有限公司 | Method and apparatus for inputting word |
| CN117875267B (en) * | 2024-03-11 | 2024-05-24 | 江西曼荼罗软件有限公司 | Method and system for converting Chinese characters into pinyin |
-
2000
- 2000-06-28 JP JP2000194739A patent/JP2002014954A/en active Pending
-
2001
- 2001-06-26 CN CN 01122612 patent/CN1330333A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100342373C (en) * | 2002-12-27 | 2007-10-10 | 欧姆龙株式会社 | Language input method and system |
| CN108700953A (en) * | 2016-03-15 | 2018-10-23 | 雅马哈株式会社 | Auxiliary input device, smart phone and input aiding method |
| CN108700953B (en) * | 2016-03-15 | 2024-02-06 | 雅马哈株式会社 | Input assisting device, smart phone, and input assisting method |
| CN108427508A (en) * | 2017-02-15 | 2018-08-21 | 北京搜狗科技发展有限公司 | Input method and device, the method and apparatus for establishing LAN dictionary |
| CN108427508B (en) * | 2017-02-15 | 2024-01-19 | 北京搜狗科技发展有限公司 | Input method and device, and method and device for establishing local area network word stock |
Also Published As
| Publication number | Publication date |
|---|---|
| JP2002014954A (en) | 2002-01-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN1330333A (en) | Chinese input transformation device and input transformation processing method and recording medium | |
| CN1113305C (en) | Language processing apparatus and method | |
| CN1288581C (en) | Document retrieval by minus size index | |
| CN1180369C (en) | Equipment and method for input of character string | |
| CN86105610A (en) | Use the character data processing of the Chinese phonetic alphabet and the method and apparatus of word processing | |
| CN1232226A (en) | Sentence processing apparatus and method thereof | |
| CN101079301A (en) | Device and method for text to audio mapping, and animation of the text | |
| CN1993692A (en) | A character display system | |
| CN101067766A (en) | Method for cancelling character string in inputting method and word inputting system | |
| CN101038508A (en) | GB phoneticize input method | |
| CN1254786C (en) | Method for synthetic output with prompting sound and text sound in speech synthetic system | |
| CN1106619C (en) | Chinese input transition processing device and Chinese input transition processing method | |
| CN1144141C (en) | Change-over processor for Chinese input and method of change-over processing for Chinese input | |
| CN1309369A (en) | Chinese input transformation processing device and method, and recording medium | |
| CN1133996A (en) | Apparatus and method for inserting specified character codes between characters | |
| CN1379342A (en) | Chinese language input translation processing device and Chinese language translation processing method | |
| CN1287321A (en) | Text processor, transfer processing method and recording medium for recording conversion processing program | |
| CN1102768C (en) | Chinese character sound-shape coding input method for electronic computer | |
| CN1156744C (en) | Chinese-character 'meta-root code' input method | |
| CN1399191A (en) | Processing method for Chinese phonetic recognition word library | |
| CN1573662A (en) | Method and system for input and output of chinese character | |
| CN1187677C (en) | Method for inputting Chinese holophrase into computers by using partial stroke | |
| CN1178123C (en) | Input device for characters and data by pronunciation | |
| CN1295290A (en) | Chinese input transition processing device, method and recording medium | |
| CN1455323A (en) | Alphabetic writing coding and abbreviation input method and its confirming code |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C06 | Publication | ||
| PB01 | Publication | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |