CN101324806B - Input system and method for mobile search - Google Patents
Input system and method for mobile search Download PDFInfo
- Publication number
- CN101324806B CN101324806B CN2007101270046A CN200710127004A CN101324806B CN 101324806 B CN101324806 B CN 101324806B CN 2007101270046 A CN2007101270046 A CN 2007101270046A CN 200710127004 A CN200710127004 A CN 200710127004A CN 101324806 B CN101324806 B CN 101324806B
- Authority
- CN
- China
- Prior art keywords
- input
- words
- word
- order
- lexicon
- 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.)
- Expired - Fee Related
Links
Images
Abstract
The invention provides an input system used for mobile search and a method thereof. The input system comprises an input module, a database, a processing module and an output module, wherein the input module is used for inputting at least one character code corresponding to a specific word and inputting a speech corresponding to the word; the database comprises a vocabulary base and an acoustical model, and the vocabulary base comprises a plurality of pairs of words with different search weights based on an order list and the order list; the processing module uses an input algorithm for screening out a first number of alternative words in line with the corresponding character code from the vocabulary base, and uses a speech recognition algorithm to compare the speech with the first number of alternative words through an acoustical model, thus screening out a second number of alternative words arranged in a specific order based on the search weights; and the output module displays the second number of the alternative words arranged in the specific order so as to select out the specific word.
Description
Technical field
Relevant a kind of input method of the present invention and system thereof, more particularly, the present invention is relevant a kind of input method and system thereof that is used for mobile search.
Background technology
Present character input method on device for mobile communication, it is very not convenient to be still concerning the user.In traditional input method, the user can reach just press many buttons possibly in order to import an English alphabet or phonetic notation.
Recently association method such as T9 rather in vogue, for each English alphabet, phonetic notation or phonetic, only need by at least one button, last English words or the Chinese words that shows then is to utilize the method for dictionary search to find out all possible combination, and bar is listed again provides the user to select.Please refer to Fig. 1, it is the synoptic diagram of the input keyboard of an existing Nokia mobile phone.This input keyboard 10 is that numerical key is marked corresponding phonetic notation and phonetic just like Fig. 1 respectively, and can use these association methods by this input keyboard 10.For example, " me " chooses by 63+, and and for example, " sky (ㄊ ㄧ ㄢ ㄎ ㄨ ㄥ) " is to choose and choose by 309+ by 209+.And during " * " key in pressing this input keyboard 10, can show that then a plurality of special symbols commonly used are for choosing; As when pressing this " # " key, then changeable different input method, the switching of for example input in Chinese (phonetic symbol) and English input (English alphabet/arabic numeral).
Please refer to Fig. 2, it shows the process flow diagram of an existing association method.At first, first step is that button is once with input alphabet or phonetic notation (step 20), its the expression user just on a keyboard button import an English alphabet or a phonetic symbol, can import a words, this words can be a Chinese words or an English words, and the complete phonetic symbol of being keyed in is the prepare word that is used to search the Chinese words of this desire input.Secondly, second step of this input method is to confirm whether this first step has finished (step 21), if finished and then carried out third step, be that queries dictionary is to list prepare word (step 22), it is to pass through an association type Dictionary retrieval according to complete letter of keying in or phonetic notation, listing at least one prepare word of this desire input words, and these prepare words are to list by an ordering of choosing (a for example ordering that is produced according to the frequency of utilization of each words etc.); But, then get back to first step (step 21) if this second step (step 21) is not finished.The 4th step is then for choosing (step 23) by key up and down, its be expression when the prepare word of first ordering be not the user want prepare word the time, then need by by about key choose one by one.Certainly, if when the prepare word of first ordering is the prepare word that the user wants, then can directly choose.
This mode has been simplified the program of input, most words can both be finished with less button, but if last possible combination is a lot, and during the prepare word that prepare word of its first ordering might not the person of being to use wants, still choose one by one by key up and down.For example: by 63 is " of, me... "; By 209 be " electricity, moving, day, take turns ... "; By 309 is " light changes, rod, sky ... ".Therefore, use this association method and during desire input " me ", press 63 keys, then once by key down.And during desire input " sky ", press 209 keys, by key down three times, press 309 keys again, by key down four times.And, as if carrying out Chinese, English simultaneously, when numeral is imported, still needing the manual switchover input method, also be very not convenient to Chinese pattern, English mode, figure pattern.
In addition, mobile search (mobile search) is that the online of very hot door in the present mobile communication is used, and certainly will be difficult to import fast key word (keyword) according to input mode now, therefore, the inventor is because above-mentioned existing input method is used the disappearance at mobile search, and invent out " input system and the method thereof that are used for mobile search " with better function, to use at mobile search, the button input mode of more diversification is provided, and further reduce the input key word required press bond number, and utilize voice to confirm to choose all possible prepare word, the more convenient keyword fast of user inputting interface can be provided.
Summary of the invention
Fundamental purpose of the present invention is to provide a kind of input system and method thereof that is used for mobile search, it is used at mobile search, the button input mode of more diversification is provided, and further reduce the input words required press bond number, and utilize voice to confirm to choose all possible prepare word, so as to the more convenient keyword fast of user inputting interface is provided.
Another object of the present invention is to provide a kind of input system and method thereof that is used for mobile search, can dynamically update up-to-date lexicon and order inventory, more meet the demand of user's mobile search according to the current popular vocabulary seniority among brothers and sisters of searching.
A kind of input system that is used for mobile search is provided according to an aspect of the present invention, in order to import a specific words, this system comprises: a load module, to voice that should words, and this at least one corresponding character code is the input method code of part word in this words in order at least one corresponding character code of importing this specific words respectively and input; One database has a lexicon and an acoustic model, and wherein this lexicon has a plural words and an order inventory, and these words are to divide according to this order inventory to have the different weights of searching; One processing module, use an input algorithm to filter out the prepare word of one first number that meets this correspondence character code in this lexicon certainly, and use a speech recognition algorithm and these voice are filtered out the prepare word of one second number by the prepare word comparison of this acoustic model and this first number, wherein the prepare word of this second number is based on it and searches weight and a particular sorted order is arranged; And an output module, the prepare word that shows this second number with this particular sorted order is for selecting this specific words.
According to above-mentioned conception, this order inventory is people's frequency of utilization statistics seniority among brothers and sisters, gives maximum search weight and is arranged in this order inventory foremost with the words of the most normal use.
According to above-mentioned conception, this order inventory also can be the popular statistics seniority among brothers and sisters of searching of network that a servomechanism is counted, be arranged in this order inventory foremost to give maximum search weight with the words that the most normal quilt is searched, therefore, this input system also comprises a update module, in order to upgrade database connections, so as to upgrading the words order inventory corresponding in this lexicon with it by one of a link network and this servomechanism.
According to above-mentioned conception, when this renewal data base set counts a plural words that upgrades and a pair of inventory in proper order different search weights with the plural words of giving this renewal respectively based on the Web search words kind during this servomechanism is between a given period with its frequency of utilization.
According to above-mentioned conception, this servomechanism also has a network lexicon, and when this words of importing is failed when this lexicon filters out, this processing module also can be searched by this link network connections to this network lexicon.
According to above-mentioned conception, the words system that this network lexicon is held is greater than this lexicon.
According to above-mentioned conception, this input algorithm is an association type input algorithm.
According to above-mentioned conception, this words is a key word of a literal.
According to above-mentioned conception, corresponding character code is wherein arbitrary for being selected from a phonetic symbol, a stroke symbol, a phonetic symbol, a radical symbol, a circumflex, an arabic numeral sign indicating number and plural number special symbol commonly used.
According to above-mentioned conception, it is wherein arbitrary that this article type families are selected from a Chinese, a Japanese, a Korean, an English, a German, a French, a Spanish, an Arabic, a Russian, an Italian, a Portuguese, a Dutch, a Greek, Czech literary composition and a Danish.
According to above-mentioned conception, this second number is to be equal to or less than this first number.
According to above-mentioned conception, this particular sorted order also consider in light of actual conditions this speech recognition algorithm relatively this first number the obtained similarity weight of prepare word and sort.
A kind of input method that is used for mobile search is provided according to a further aspect of the invention, be used to import a specific words, this method includes the following step: a database (A) is provided, has a lexicon, wherein this lexicon has a plural words and an order inventory, mutually should the order inventory and the difference of giving these words is respectively searched weight; (B) according to an input method importing at least one corresponding character code of this words, and this at least one corresponding character code is the input method code of word partly in this words; (C) mutually should at least one character code and from this lexicon, filter out the prepare word of one first number that meets this correspondence character code; (C) input one voice; (D) these voice of speech recognition and compare with the prepare word of this first number and filter out the prepare word of one second number, wherein the prepare word of this second number system based on its indivedual search weights and relatively this first number the obtained similarity weight of prepare word and a particular sorted order is arranged; And (E) show that with this particular sorted order the prepare word of this second number is for selecting this specific words.
According to above-mentioned conception, this input method also comprises a step (F) provides a network lexicon, when the prepare word of this second number does not have this specific words, also can search by link network connections to this network lexicon.
According to above-mentioned conception, this database chains network to upgrade the words order inventory corresponding with it in this lexicon by one.
This is according to above-mentioned conception, and this database also has an acoustic module, relatively produces its similarity weight respectively with the prepare word with these voice and this first number.
According to above-mentioned conception, this input method is an association method.
Provide a kind of input system that is used for mobile search according to another aspect of the invention, in order to import a specific words, this system comprises: a load module, to voice that should words, and this at least one corresponding character code is the input method code of part word in this words in order at least one corresponding character code of importing this specific words respectively and input; One lexicon has a plural words and an order inventory, and there are the different weights of searching in this order inventory system with these words according to this order inventory; One processing module, use an input algorithm to filter out the prepare word of one first number that meets this correspondence character code in this lexicon certainly, and the relatively prepare word of these voice and this first number and the similarity weight that filters out the prepare word of one second number and obtain these prepare words, wherein the prepare word of this second number system searches weight and similarity weight and a particular sorted order is arranged based on it; And an output module, the prepare word that shows this second number with this particular sorted order is for selecting this specific words.
A kind of disposal route that is used for the mobile search input is provided according to a further aspect of the present invention, be applicable in the device for mobile communication, in order to import a specific words, this method comprises following step at least: receive one first input, this first at least one character code that is input as this specific words, and this at least one corresponding character code is the input method code of word partly in this words; Determine the prepare word of one first number according to this first input; Reception one comprises second input of voice; Decide the prepare word of one second number according to this first input and this second input; Based on indivedual weights of the prepare word of this second number and with the prepare word ordering of a particular sorted order with this second number; And choose this specific words.
According to above-mentioned conception, this weight is a search weight and a similarity weight.
According to above-mentioned conception, this first input comprises that to be selected from touch-control input, a hand-written identification input and keyboard input wherein arbitrary.
According to above-mentioned conception, the prepare word of this second number system is determined under the restriction of this first input according to this second input.
According to above-mentioned conception, the prepare word of this first number system makes decision at the context of considering word according to this first input
Description of drawings
Effect of the present invention and purpose, can by below in conjunction with accompanying drawing to the detailed description of its embodiment and more deep understanding is arranged, wherein:
Fig. 1 is the synoptic diagram of the input keyboard of an existing mobile phone
Fig. 2 is the schematic flow sheet of an existing association method;
Fig. 3 is a kind of concise and to the point system configuration synoptic diagram that is used for the input system and the method thereof of mobile search of preferred embodiment of the present invention
Fig. 4 is a kind of schematic flow sheet that is used for the input system and the method thereof of mobile search of preferred embodiment of the present invention.
Fig. 5 is used for the schematic flow sheet of the disposal route of mobile search input in device for mobile communication for the present invention.
Embodiment
Will be in the present invention hereinafter be described, being familiar with present technique person must understanding explanation hereinafter only be as illustration usefulness, and is not used in restriction the present invention.
Below be described at a kind of input system and method thereof that is used for mobile search of preferred embodiment of the present invention, but actual framework and the method that is adopted must not meet the framework and the method for description fully, person skilled in the art person is when making many variations and modification under the situation that does not break away from practicalness of the present invention and scope.
See also Fig. 3, it is the disclosed a kind of input system of mobile search and enforcement configuration diagram of method thereof of being used for.This input system comprises a load module 30, a database 31, a processing module 32 and an output module 33.
These load module 30 usefulness are imported at least one corresponding character code of a specific words and input to voice that should words successively for a user, and this database 31, have a lexicon 311 and an acoustic model 312, wherein this lexicon 311 has a plural words and an order inventory, and these words are to divide according to this order inventory to have the different weights of searching.32 of this processing modules have an input algorithm and a speech recognition algorithm, by this input algorithm can be mutually should corresponding character code and from this lexicon 311, filter out the prepare word of first number that meets this correspondence character code, and these voice are compared to filter out the prepare word of one second number by the prepare word of this acoustic model 312 with this first number by this speech recognition algorithm.Simultaneously, with this speech recognition algorithm relatively the prepare word of these voice and this first number when obtaining the prepare word of this second number, also can give the similarity weight of indivedual words in the prepare word of this second number respectively, and corresponding these prepare words have the similarity weight and search weight (originally promptly giving each words different search weights at this lexicon 311), two kinds of weights with the proper proportion collocation (for example:, ordering is based on the similarity weight, and when after speech recognition, having a plurality of prepare word of identical similarity weight, then be arranged in front end with prepare word with higher search weight) and the prepare word of this second number can be sorted with a particular sorted order, promptly can pass through this output module 33 at last, show that with this particular sorted order the prepare word of this second number selects this specific words for this user.
Wherein, this order inventory can be people's frequency of utilization statistics seniority among brothers and sisters, give maximum search weight and be arranged in this order inventory foremost with the words of the most normal use, in addition, this order inventory also can be the popular statistics seniority among brothers and sisters of searching of a network, is arranged in this order inventory foremost to give maximum search weight with the words that the most normal quilt is searched.In addition, this order inventory also can be integrated above-mentioned individual frequency of utilization statistics seniority among brothers and sisters and the popular statistics seniority among brothers and sisters of searching of network simultaneously, and the candidate vocabulary that makes this second number can also be arranged according to specific sortord after having put in order the similarity weight and having searched weight, for example: show the highest the first five prepare word of individual frequency of utilization earlier, display network is popular subsequently searches the highest the first five the individual prepare word of statistics, or intersection shows individual frequency of utilization and the popular prepare word of adding up of searching of network.
Therefore, input system of the present invention also can comprise a communication module 34, in order to link by a link network 35 and a servomechanism 36, this servomechanism 36 has more a new database 361 and a network lexicon 362, this more new database 361 be based on the Web search words kind of this servomechanism 36 between a given period count with its frequency of utilization a plural words that upgrades with a pair of should the order inventory (network that is counted is popular search statistics rank) with the different search weights of the plural words of giving this renewal respectively, therefore, this processing module 32 can also link by the more new database 361 of this communication module 34 with this servomechanism 36, so as to upgrading the words order inventory corresponding with it in this lexicon 311.
In addition, this servomechanism 36 also has a network lexicon 362, the words that this network lexicon 362 is held is more greater than this lexicon 311, when the words that the user imported is failed when this lexicon 311 filters out, this processing module 32 also can be linked to this network lexicon 362 by this link network 35 by this communication module 34 and search.
Moreover, this input algorithm is an association type input algorithm, therefore importing different corresponding character codes can show the plural words of providing relevance, and this words is a key word of a literal, and this at least one corresponding code promptly is the input method code of part word in this key word, and this correspondence character code is wherein arbitrary for being selected from a phonetic symbol, a stroke symbol, a phonetic symbol, a radical symbol, a circumflex, an arabic numeral sign indicating number and plural number special symbol commonly used.This literal then can be the literal of any country, as: Chinese, Japanese, Korean, English, German, French, Spanish, Arabic, Russian, Italian, Portuguese, Dutch, Greek, Czech's literary composition or Danish.
Therefore, because the present invention is useful in the key word input in the mobile search, and the words limited amount of this lexicon 311 and this network lexicon 362, therefore can simplify the number of times of user's input code, need not remove to import one by one the complete corresponding code of all words in this key word by the user, only need the initial code of each word or the partial code of this key word and can filter out the prepare word of first number, import the voice of this key word at last and confirm, can demonstrate the prepare word of the second the most close number via the processing of system of the present invention.More prepare word can be produced though simplify input code,, can't increase the degree of difficulty that selects speech, and speech recognition also certain accuracy can be kept because the mode that then can use voice to confirm is chosen.In addition, indivedual search weights of this prepare word can also be applied in the above-mentioned speech recognition process, search the bigger words of weight and can increase the weight of score,, use required more to meet mobile search so that the keyword that the most normal quilt is searched can just identify easilier at speech recognition process.
Therefore, the present invention illustrates with the input keyboard 10 of Fig. 1, when the user uses the phonetic notation input and during desire input " sky ", as long as press 23 keys (ㄊ ㄎ), say " sky " again, can demonstrate this words, and the present invention can also use other input form, as: stroke symbol, phonetic symbol, radical symbol, circumflex, arabic numeral sign indicating number or other special symbols commonly used.Therefore when user's desire input " sky ", if when importing, then press 11 keys () with tone, say " sky " again, and when importing, press 85 keys (T K) with phonetic, say " sky " again.The present invention can also provide part button input mode, only need import two keys as five character word and get final product.For example: when user's desire input " Taibei 1 ", press 21 keys (ㄊ ㄅ), say " Taibei 1 " again.When user's desire input " delta ", press 33 keys (D E), say " delta " again.
Refer again to Fig. 4, it is a kind of schematic flow sheet that is used for the input system and the method thereof of mobile search of the present invention.At first, import at least one corresponding character code (step 40) of a words according to an input method by a user, confirm whether input finishes (step 41), then mutually should corresponding character code and from a lexicon, filter out prepare word (step 42) to one first number that should character code, import the voice (step 43) of this words by this user, utilize speech recognition to remove these voice relatively and filter out the prepare word (step 44) of one second number with the prepare word of this first number, then list the prepare word of second number and choose this words (step 45) of affirmation, promptly finish at last (step 46) for this user.
Wherein, if in step 45, the user fails to select required words from the prepare word of second number, then filter out a new prepare word (step 47) to the network lexicon by the link network connections, repeating step 43, step 44 and step 45 more subsequently, and can allow the user therefrom reselect this words.
Moreover, narrate according to the front, each prepare word all has its different search weight, and its different similarity weights behind speech recognition program, have also been given, based on its similarity weight and search weight, and can rearrange the prepare word of this second number, so that the tabulation that the words that the most normal quilt searches can be arranged in last demonstration easilier is foremost, properer user is required when carrying out mobile search.
Please with reference to figure 5, it is used for the schematic flow sheet of the disposal route of mobile search input in device for mobile communication for the present invention.The present invention is applicable in the device for mobile communication, be to receive first input (step 50) that includes at least one character code earlier in this device for mobile communication, determine the prepare word (step 51) of one first number according to this first input, then receive one include voice second the input (step 52), and decide the prepare word (step 53) of one second number according to this first input and this second input, and, and remove to choose wherein required words (step 55) by the user at last based on indivedual weights (searching weight and similarity weight) of the prepare word of this second number and with the prepare word ordering (step 54) of a particular sorted order with this second number.
Wherein, this first input system can be touch-control input, one hand-written identification input, the input of one keyboard or other can be imported the input mode of at least one code of this words, and the prepare word of this second number system is determined under the restriction of this first input according to this second input, promptly be this second input of speech recognition and compare with the prepare word of this first number, and because this program system is based on a habitual association method, so the prepare word of this first number determines according to this first input and considering under the context of word (context).
In sum, the present invention can provide a kind of input system and method thereof that is used for mobile search really, it has broken through the complete corresponding code that still needs to import one by one required words at existing association method, and still need to choose one by one respectively suitable prepare word, and the inputting interface that can provide less code input and correctness also can effectively promote, be particularly useful in the application of existing mobile search, and can search the vocabulary seniority among brothers and sisters according to hot topic fast changing in the current network, dynamically update up-to-date lexicon and its search weight, and more meet the demand of user's mobile search, this technology need not increase many complicated software and hardware equipment, and implementation cost is very cheap.Therefore, the present invention is used for the input system and the method thereof of mobile search, but the user need not special training or study but high convenience is provided, and can effectively promote the progress of industry, and the technology of the present invention is simple, can use the field extensive, the value of real tool industry
The above is to utilize preferred embodiment to describe the present invention in detail, but not limit the scope of the invention, therefore the personage who knows present technique should be able to understand, suitably do slightly change and adjustment, will not lose main idea of the present invention place, also do not break away from the spirit and scope of the present invention, the former capital should be considered as further enforcement situation of the present invention.
Claims (13)
1. input system that is used for mobile search, in order to import a specific words, it comprises:
One load module, to voice that should words, and this at least one corresponding character code is the input method code of part word in this words in order at least one corresponding character code of importing this specific words respectively and input;
One database has a lexicon and an acoustic model, and wherein this lexicon has a plural words and an order inventory, and these words are to divide according to this order inventory to have the different weights of searching;
One processing module, use an input algorithm to filter out the prepare word of one first number that meets this correspondence character code in this lexicon certainly, and use a speech recognition algorithm and these voice are filtered out the prepare word of one second number by the prepare word comparison of this acoustic model and this first number, wherein the prepare word of this second number is based on it and searches weight and a particular sorted order is arranged; And
One output module, the prepare word that shows this second number with this particular sorted order is for selecting this specific words.
2. input system according to claim 1 is characterized in that this order inventory is people's frequency of utilization statistics seniority among brothers and sisters, gives maximum search weight and is arranged in this order inventory foremost with the words of the most normal use.
3. input system according to claim 1 is characterized in that this order inventory is the popular statistics seniority among brothers and sisters of searching of network that a servomechanism is counted, and is arranged in this order inventory foremost to give maximum search weight with the words that the most normal quilt is searched.
4. input system according to claim 3 is characterized in that also comprising a communication module, in order to upgrade database connections, so as to upgrading the words order inventory corresponding in this lexicon, wherein with it by one of a link network and this servomechanism:
This more new database be based on the Web search words kind of this servomechanism between a given period and count a plural words that upgrades and a pair of inventory in proper order different search weights with its frequency of utilization with the plural words of giving this renewal respectively; Or
This servomechanism also has a network lexicon, and fail when this lexicon filters out when this words of importing, this processing module also can be searched by this link network connections to this network lexicon by this communication module, and the words that this network lexicon is held is greater than this lexicon.
5. input system according to claim 1 is characterized in that:
This input algorithm is an association type input algorithm;
This words is a key word of a literal;
This correspondence character code is wherein arbitrary for being selected from a phonetic symbol, a stroke symbol, a phonetic symbol, a radical symbol, a circumflex, an arabic numeral sign indicating number and plural number special symbol commonly used; And
This literal is that to be selected from a Chinese, a Japanese, a Korean, an English, a German, a French, a Spanish, an Arabic, a Russian, an Italian, a Portuguese, a Dutch, a Greek, Czech literary composition and a Danish wherein arbitrary.
6. input system according to claim 1 is characterized in that:
This second number is to be equal to or less than this first number; And/or
This particular sorted order also consider in light of actual conditions this speech recognition algorithm relatively this first number the obtained similarity weight of prepare word and sort.
7. an input method that is used for mobile search is used to import a specific words, and this method includes the following step:
(A) provide a database, have a lexicon, wherein this lexicon has a plural words and an order inventory, gives the difference of these words in response to this order inventory respectively and searches weight;
(B) according to an input method importing at least one corresponding character code of this words, and this at least one corresponding character code is the input method code of word partly in this words;
(C) mutually should at least one character code and from this lexicon, filter out the prepare word of one first number that meets this correspondence character code;
(C) input one voice;
(D) these voice of speech recognition and compare with the prepare word of this first number and filter out the prepare word of one second number, wherein the prepare word of this second number be based on its indivedual search weights and relatively this first number the obtained similarity weight of prepare word and a particular sorted order is arranged; And
(E) show that with this particular sorted order the prepare word of this second number is for selecting this specific words.
8. input method according to claim 7, it is characterized in that also comprising a step (F) provides a network lexicon, when the prepare word of this second number does not have this specific words, also can search by link network connections to this network lexicon.
9. input method according to claim 7 is characterized in that:
This database chains network to upgrade the words order inventory corresponding with it in this lexicon by one;
This database also has an acoustic module, relatively produces its similarity weight respectively with the prepare word with these voice and this first number; Or
This input method is an association method.
10. input system that is used for mobile search, in order to import a specific words, this system comprises:
One load module, to voice that should words, and this at least one corresponding character code is the input method code of part word in this words in order at least one corresponding character code of importing this specific words respectively and input;
One lexicon has a plural words and an order inventory, and there are the different weights of searching in this order inventory system with these words according to this order inventory;
One processing module, use an input algorithm to filter out the prepare word of one first number that meets this correspondence character code in this lexicon certainly, and the relatively prepare word of these voice and this first number and the similarity weight that filters out the prepare word of one second number and obtain these prepare words, wherein the prepare word of this second number system searches weight and similarity weight and a particular sorted order is arranged based on it; And
One output module, the prepare word that shows this second number with this particular sorted order is for selecting this specific words.
11. the disposal route of a mobile search input is applicable in the device for mobile communication that in order to import a specific words, this method comprises following step at least:
Receive one first input, this first at least one character code that is input as this specific words, and this at least one corresponding character code is the input method code of part word in this words;
Determine the prepare word of one first number according to this first input;
Reception one comprises second input of voice;
Decide the prepare word of one second number according to this first input and this second input;
Based on indivedual weights of the prepare word of this second number and with the prepare word ordering of a particular sorted order with this second number; And
Choose this specific words.
12. disposal route according to claim 11 is characterized in that:
This weight is a search weight and a similarity weight; And/or
This first input comprises that to be selected from touch-control input, a hand-written identification input and keyboard input wherein arbitrary.
13. disposal route according to claim 11 is characterized in that:
The prepare word of this second number is to determine under the restriction of this first input according to this second input;
The prepare word of this first number is to make decision at the context of considering word according to this first input.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2007101270046A CN101324806B (en) | 2007-06-14 | 2007-06-14 | Input system and method for mobile search |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2007101270046A CN101324806B (en) | 2007-06-14 | 2007-06-14 | Input system and method for mobile search |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101324806A CN101324806A (en) | 2008-12-17 |
| CN101324806B true CN101324806B (en) | 2010-06-23 |
Family
ID=40188368
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2007101270046A Expired - Fee Related CN101324806B (en) | 2007-06-14 | 2007-06-14 | Input system and method for mobile search |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101324806B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI459224B (en) * | 2012-09-06 | 2014-11-01 | Shuttle Inc | Searching method for content of electronic device and application program using for the same |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102591472B (en) * | 2011-01-13 | 2014-06-18 | 新浪网技术(中国)有限公司 | Method and device for inputting Chinese characters |
| WO2013000136A1 (en) * | 2011-06-29 | 2013-01-03 | 宇龙计算机通信科技(深圳)有限公司 | Mobile terminal and method, system for inputting network hot words into mobile terminal |
| CN103177721B (en) * | 2011-12-26 | 2015-08-19 | 中国电信股份有限公司 | Audio recognition method and system |
| CN103677297B (en) * | 2012-09-03 | 2017-03-01 | 萧吉利 | The input method of digital conversion phonetic notation electronic device |
| CN103678377A (en) * | 2012-09-18 | 2014-03-26 | 浩鑫股份有限公司 | Content search method of electronic device |
| US8589164B1 (en) * | 2012-10-18 | 2013-11-19 | Google Inc. | Methods and systems for speech recognition processing using search query information |
| US9672202B2 (en) * | 2014-03-20 | 2017-06-06 | Microsoft Technology Licensing, Llc | Context-aware re-formating of an input |
| CN107463272A (en) * | 2016-06-06 | 2017-12-12 | 林政宏 | Associate advertisement input method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1277375A (en) * | 2000-07-19 | 2000-12-20 | 孙万勋 | Chinese character input method combining pronunciation and initial and its keyboard |
| CN1397866A (en) * | 2002-08-02 | 2003-02-19 | 北京南山高科技有限公司 | Method and device for inputting Chinese characters by speech and equipment with simplified keyboard |
| CN1752900A (en) * | 2004-09-24 | 2006-03-29 | 北京中星微电子有限公司 | Chinese character input method combined with speech sound identification |
-
2007
- 2007-06-14 CN CN2007101270046A patent/CN101324806B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1277375A (en) * | 2000-07-19 | 2000-12-20 | 孙万勋 | Chinese character input method combining pronunciation and initial and its keyboard |
| CN1397866A (en) * | 2002-08-02 | 2003-02-19 | 北京南山高科技有限公司 | Method and device for inputting Chinese characters by speech and equipment with simplified keyboard |
| CN1752900A (en) * | 2004-09-24 | 2006-03-29 | 北京中星微电子有限公司 | Chinese character input method combined with speech sound identification |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI459224B (en) * | 2012-09-06 | 2014-11-01 | Shuttle Inc | Searching method for content of electronic device and application program using for the same |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101324806A (en) | 2008-12-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101324806B (en) | Input system and method for mobile search | |
| TWI336048B (en) | Input system for mobile search and method therefor | |
| KR100891358B1 (en) | System and its method for inputting character by predicting character sequence of user's next input | |
| CN101398717A (en) | Display variable keyboard and input method | |
| CN1184969A (en) | Method and device for input of text messages from keypad | |
| JP2009501963A (en) | How to input kanji using 3 columns 4 rows keypad | |
| CN101644961A (en) | Encoded string sequencing method, device and character input method and device | |
| CN101170757A (en) | A method and device for controlling text input in mobile device | |
| CN101398718B (en) | keyboard and Chinese character input method thereof | |
| CN100561411C (en) | The input device of combining association formula input method and sound identification method and method | |
| US6799914B2 (en) | Arabic-persian alphabeth input apparatus | |
| CN102682045A (en) | Recommendation Method and Recommendation System Based on Dynamic Language Model | |
| CN1129838C (en) | Free-type Chinese-character enter method using keypad and its device | |
| CN101577115A (en) | Voice input system and voice input method | |
| CN102541278A (en) | Method and system for character selection in word input interface | |
| CN101661335A (en) | Chinese character input method applicable to embedded type platform and system | |
| CN100520684C (en) | Chinese phonetic notation input method and device thereof | |
| CN101114196B (en) | Method for inputting chinese phrase and equipment | |
| KR0154150B1 (en) | Inputing method of korean alphabet array in communication terminals | |
| CN1752906A (en) | Cell phone Chinese character input method | |
| CN1854997A (en) | Numbers and alphabets inputting method | |
| KR20000024794A (en) | Method for searching korean language data | |
| KR100434668B1 (en) | Apparatus for inputting korean letters | |
| CN101498965B (en) | Chinese character Pinyin input method by numeric keyboard | |
| KR20130097888A (en) | System and method for recommending words and completing sentences in touch screen devices |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20100623 Termination date: 20160614 |