CN107870677A - A kind of input method, device and the device for input - Google Patents

A kind of input method, device and the device for input Download PDF

Info

Publication number
CN107870677A
CN107870677A CN201610849668.2A CN201610849668A CN107870677A CN 107870677 A CN107870677 A CN 107870677A CN 201610849668 A CN201610849668 A CN 201610849668A CN 107870677 A CN107870677 A CN 107870677A
Authority
CN
China
Prior art keywords
error correction
string
word
group
input
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201610849668.2A
Other languages
Chinese (zh)
Other versions
CN107870677B (en
Inventor
陈小帅
马尔胡甫·曼苏尔
张扬
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Sogou Technology Development Co Ltd
Original Assignee
Beijing Sogou Technology Development Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Sogou Technology Development Co Ltd filed Critical Beijing Sogou Technology Development Co Ltd
Priority to CN201610849668.2A priority Critical patent/CN107870677B/en
Publication of CN107870677A publication Critical patent/CN107870677A/en
Application granted granted Critical
Publication of CN107870677B publication Critical patent/CN107870677B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/02—Input arrangements using manually operated switches, e.g. using keyboards or dials
    • G06F3/023—Arrangements for converting discrete items of information into a coded form, e.g. arrangements for interpreting keyboard generated codes as alphanumeric codes, operand codes or instruction codes
    • G06F3/0233—Character input methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Human Computer Interaction (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Machine Translation (AREA)
  • Document Processing Apparatus (AREA)

Abstract

The embodiments of the invention provide a kind of input method, device and device for input.Method therein includes：Error correction is carried out to input string, obtains error correction string corresponding to the input string；When the error correction string meets preset group entry part, intelligent word is carried out to the error correction string, obtains first group of word result corresponding to the error correction string；First group of word result is showed as candidate item.A group accuracy for word result can be improved, and then can solve in the prior art, user just recognizes oneself to have input wrong pinyin string, it is necessary to the input string of deletion error and re-start input when seeing the group word result of mistake, the problem of causing input efficiency relatively low, to improve input efficiency.

Description

A kind of input method, device and the device for input
Technical field
The present invention relates to communication technical field, more particularly to a kind of input method, device and the device for input.
Background technology
For the users such as Chinese, Japanese, Korean, it is typically necessary and is handed over by input method procedure and computer Mutually.For example, user can input string by a keyboard entry, then will by the input method procedure Standard Map rule preset according to its The input string is converted to the candidate item of corresponding language and displaying, and then will shield in the candidate item of user's selection.
When user inputs Chinese using input method procedure, the input string that input method procedure inputs to user parses, Input string as user inputs is pinyin string, then can obtain entry corresponding to the pinyin string by inquiring about dictionary, then will look into Ask obtained entry and show user as candidate item.If the word corresponding with the pinyin string of user's input is not present in dictionary During bar, the intelligent word function of input method can be triggered.For example, the pinyin string of user's input is " chifanlema ", in dictionary In the presence of entry " having a meal " corresponding with pinyin string " chifan ", and entry corresponding with pinyin string " lema " " ", still In the absence of complete entry " having had a meal " corresponding with pinyin string " chifanlema ", therefore, input method procedure can be triggered Intelligent word function, input method procedure carry out contrast sequence according to language model to a variety of groups of word results.For example, input method procedure Contrast sequence is carried out to a group word result " eating "+" anti-", " having a meal "+" " etc., most language model preferably organizes word at last As a result " have a meal "+" " come the first place of candidate item.
But in actual applications, if mistake be present in the pinyin string of user's input, often obtain the group word of mistake As a result.For example, user is intended to input Pinyin string " chifanlema ", as a result erroneous input is " chianlema ", then input method procedure meeting Intelligent word is carried out according to the input string of mistake, finally gives the candidate items such as " eat and pacified ", " red bank ".User is seeing It may just recognize oneself to have input wrong pinyin string during the candidate item of mistake, now need the pinyin string of backspace deletion error And input is re-started, modification process is not only relatively complicated, is made troubles for user, and it is relatively low to also result in input efficiency.
The content of the invention
The embodiment of the present invention provides a kind of input method, device and the device for input, to solve intelligence in the prior art The problem of causing input efficiency relatively low, can be organized when word occurs wrong.
In order to solve the above problems, the invention discloses a kind of input method, including：
Error correction is carried out to input string, obtains error correction string corresponding to the input string；
When the error correction string meets preset group entry part, intelligent word is carried out to the error correction string, obtains the error correction First group of word result corresponding to string；
First group of word result is showed as candidate item.
Optionally it is determined that the error correction string meets the step of preset group entry part, including：
Cutting is carried out according to syllable to the error correction string；
When the number of syllables that cutting obtains exceeds preset group word threshold value, determine that the error correction string meets preset group entry Part.
Optionally it is determined that the error correction string meets the step of preset group entry part, including：
According to the error correction string inquiry system dictionary；
The system word to match with the error correction string in the system dictionary be present, and the word frequency of the system word is less than During default word frequency threshold value, determine that the error correction string meets preset group entry part.
Optionally it is determined that the error correction string meets the step of preset group entry part, including：
According to the error correction string inquiry system dictionary；
The system word to match with the error correction string in the system dictionary be present, and the error correction string has a plurality of group During word path, determine that the error correction string meets preset group entry part.
Alternatively, it is described that intelligent word is carried out to the error correction string, obtain first group of word result corresponding to the error correction string The step of, including：
Cutting is carried out according to syllable to the error correction string, obtains a plurality of group of word path corresponding to the error correction string；
By inquiry system dictionary and user thesaurus, a group word is carried out to every group word path；
According to preset binary storehouse, path score corresponding to the Zu Ci roads warp is determined；
Acquisition approach score meets first group of word result corresponding to the group word path of predetermined threshold value.
Alternatively, it is described to carry out error correction to input string, the step of obtaining error correction string corresponding to the input string, including：
According to position error correction, dynamics error correction and at least one of key mapping error correction error correction algorithm is closed on, determines the input Error character in string；
Correction process is carried out to the error character, obtains error correction string corresponding to the input string.
Alternatively, methods described also includes：
According to the preset dictionary of prefix lookups of the error correction string, first to match with the prefix of the error correction string is obtained With entry；
First match entry is showed as candidate item.
Alternatively, methods described also includes：
When the input string meets preset group entry part, intelligent word is carried out to the input string, obtains the input Second group of word result corresponding to string；
The preset dictionary of prefix lookups according to the input string, obtains second to match with the prefix of the input string With entry；
According to context, current input environment, system word frequency corresponding to the input string and organize in word language model extremely Few one kind, is ranked up to first group of word result, second group of word result, the first match entry and the second match entry；
Using first group of word result after sequence, second group of word result, the first match entry and the second match entry as time Option is showed.
On the other hand, the invention discloses a kind of input unit, including：
Correction module, for carrying out error correction to input string, obtain error correction string corresponding to the input string；
First group of word module, for when the error correction string meets preset group entry part, intelligence to be carried out to the error correction string Group word, obtains first group of word result corresponding to the error correction string；
Display module, for first group of word result to be showed as candidate item.
Alternatively, first group of word module, including：
Submodule is divided, for carrying out cutting according to syllable to the error correction string；
Determination sub-module, when the number of syllables for being obtained in cutting exceeds preset group word threshold value, determine the error correction string Meet preset group entry part.
Alternatively, first group of word module, including：
Submodule is inquired about, for according to the error correction string inquiry system dictionary；
Determination sub-module, for the system word to match with the error correction string in the system dictionary be present, and it is described When the word frequency of system word is less than default word frequency threshold value, determine that the error correction string meets preset group entry part.
Alternatively, first group of word module, including：
Submodule is inquired about, for according to the error correction string inquiry system dictionary；
Determination sub-module, for the system word to match with the error correction string in the system dictionary be present, and it is described When error correction string has a plurality of group of word path, determine that the error correction string meets preset group entry part.
Alternatively, first group of word module, including：
Cutting submodule, for carrying out cutting according to syllable to the error correction string, obtain a plurality of corresponding to the error correction string Group word path；
Group lexon module, for by inquiry system dictionary and user thesaurus, a group word to be carried out to every group word path；
Molecular modules are calculated to obtain, for according to preset binary storehouse, determining path score corresponding to the Zu Ci roads warp；
Acquisition submodule, meet first group of word result corresponding to the group word path of predetermined threshold value for acquisition approach score.
Alternatively, the correction module, including：
Mistake determination sub-module, for according to position error correction, dynamics error correction and closing at least one of key mapping error correction and entangling Method is miscounted, determines the error character in the input string；
Error correction submodule, for carrying out correction process to the error character, obtain error correction string corresponding to the input string.
Alternatively, described device also includes：
First matching module, for the preset dictionary of prefix lookups according to the error correction string, obtain and the error correction string The first match entry that prefix matches；
Display module, it is additionally operable to be showed first match entry as candidate item.
Alternatively, described device also includes：
Second group of word module, for when the input string meets preset group entry part, intelligence to be carried out to the input string Group word, obtains second group of word result corresponding to the input string；
Second matching module, for the preset dictionary of prefix lookups according to the input string, obtain and the input string The second match entry that prefix matches；
Order module, for according to context, current input environment, system word frequency and group word corresponding to the input string At least one of model is sayed, to first group of word result, second group of word result, the first match entry and the second match entry It is ranked up；
Display module, it is additionally operable to first group of word result after sequence, second group of word result, the first match entry and second Match entry is showed as candidate item.
Another further aspect, the invention discloses a kind of device for being used to input, include memory, and one or one More than program, one of them or more than one program storage in memory, and be configured to by one or one with Upper computing device is one or more than one program bag contains the instruction for being used for being operated below：
Error correction is carried out to input string, obtains error correction string corresponding to the input string；
When the error correction string meets preset group entry part, intelligent word is carried out to the error correction string, obtains the error correction First group of word result corresponding to string；
First group of word result is showed as candidate item.
The embodiment of the present invention includes advantages below：
The embodiment of the present invention first carries out error correction to input string, obtained described defeated before intelligent word is carried out to input string Enter error correction string corresponding to string；When the error correction string meets preset group entry part, intelligent word is carried out to the error correction string, obtained First group of word result corresponding to the error correction string；And first group of word result is showed as candidate item.Due to this Inventive embodiments are to carry out intelligent word, correct group of word knot after directly exporting error correction to user to the input string after error correction Fruit, so as to improve a group accuracy for word result, and then can solve in the prior art, user is seeing the group word knot of mistake Just recognize oneself to have input the pinyin string of mistake during fruit, it is necessary to the input string of deletion error and re-start input, cause The problem of input efficiency is relatively low, to improve input efficiency.
Brief description of the drawings
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below by institute in the description to the embodiment of the present invention The accompanying drawing needed to use is briefly described, it should be apparent that, drawings in the following description are only some implementations of the present invention Example, for those of ordinary skill in the art, without having to pay creative labor, can also be according to these accompanying drawings Obtain other accompanying drawings.
Fig. 1 is a kind of step flow chart of input method embodiment one of the present invention；
Fig. 2 is a kind of step flow chart of input method embodiment two of the present invention；
Fig. 3 is a kind of step flow chart of input method embodiment three of the present invention；
Fig. 4 is a kind of structured flowchart of input unit embodiment of the present invention；
Fig. 5 is a kind of block diagram of device 800 for being used to input of the present invention；And
Fig. 6 is a kind of structural representation of server of the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete Site preparation describes, it is clear that described embodiment is part of the embodiment of the present invention, rather than whole embodiments.Based on this hair Embodiment in bright, the every other implementation that those of ordinary skill in the art are obtained under the premise of creative work is not made Example, belongs to the scope of protection of the invention.
Embodiment of the method one
Reference picture 1, a kind of step flow chart of input method embodiment one of the present invention is shown, can specifically be included：
Step 101, error correction is carried out to input string, obtain error correction string corresponding to the input string；
The embodiment of the present invention first carries out correction process before intelligent word is carried out to the input string of user to input string, Then intelligent word is carried out to error correction string again, thus, it is possible to a group accuracy for word result be improved, after directly exporting error correction to user Correct group of word result, just recognize oneself to have input wrong phonetic when seeing the group word result of mistake so as to solve user String is, it is necessary to the input string of backspace deletion error and re-start input, the problem of causing input efficiency relatively low.
The embodiment of the present invention is applied to the input of Chinese, the various language such as English, Japanese, for convenience, below with It is described exemplified by Chinese.When inputting Chinese, it usually needs key in letter, the character such as numeral, symbol, input method procedure is by institute The user inputs character of acquisition is converted to Chinese.The embodiment of the present invention is entered for the mistake that user is likely to occur in input process Row error correction, involved error correction scene can include but is not limited to such as Types Below：User when being inputted using keyboard, due to Input speed is higher or during touch system, overdue on the neighbouring button of target button；Or using the intelligent terminals such as mobile phone Touch dummy keyboard when being inputted, because the button size of dummy keyboard is relatively small, occur overdue in neighbouring button Situation；Or cause the finger of intelligent terminal or operation mobile terminal because walking, vehicle such as jolt or collides at the reason Or jitter phenomenon occurs in stylus, situation is hit so as to cause to occur the overdue of neighbouring button.Therefore, the embodiment of the present invention is applicable In the different input unit such as physical keyboard, dummy keyboard.
It is described that error correction is carried out to input string in a kind of alternative embodiment of the present invention, obtain corresponding to the input string The step of error correction string, it can specifically include：
Step S11, according to position error correction, dynamics error correction and at least one of key mapping error correction error correction algorithm is closed on, it is determined that Error character in the input string；
Step S12, correction process is carried out to the error character, obtains error correction string corresponding to the input string.
In actual applications, the error correction algorithm of the input string can have a variety of, can specifically include position error correction, dynamics Error correction and close at least one of key mapping error correction.
Wherein, position error correction algorithm refer to by determine user's click keys position deviate key center direction and away from From the character progress error correction to input.For example, user clicks on button " c " upper left position, then user is possible to beat originally Input character " d " is calculated, and is clicked on by mistake on button " c ".
Dynamics error correction algorithm refers to the dynamics by determining user's click keys, and error correction is carried out to the character of input.It is for example, logical The click behavior of counting user is crossed, dynamics scope during the normal click keys of user is obtained, if certain click of user does not exist In the range of the dynamics, it is believed that be the mistake clicking operation of user.It is not small for example user is in the case where mobile phone screen unlocks The heart touches certain button, and click force now is less than dynamics scope during the normal click keys of user, then can delete user The overdue error character for hitting key-press input.
Key mapping error correction algorithm is closed on to refer to by the way that user inputs character is replaced with into each button character that the character closes on, to right The character of input carries out error correction.For example, the input string that user wants input originally is " woai ", can be due to button in keyboard " o " and button " i " is close on key mapping, and " o " input is by mistake " i " by user, then the input string actually entered is " wiai ", the present invention Embodiment can be by carrying out closing on key mapping error correction to input string " wiai ", and it is " i " to determine the error character in the input string, and And correction process is carried out to the error character, correct characters " o " are replaced with, obtain error correction string " woai ".
Wherein, correction process is carried out to error character, can specifically includes the operations such as replacement, deletion, increase.For example, by In keyboard is narrow and small etc., reason, user are clicked on error character by mistake, then correct characters can be used to replace error character and be entangled Fault is managed；For another example, due to the reason such as user's click speed is too fast, clicked on or leak source hits the feelings of some character it is possible that more Condition, then the character clicked on more can be deleted, or the character that increase leak source is hit carries out correction process.
Certainly, in actual applications, correction process can be carried out to input string using arbitrary error correction algorithm, to obtain State error correction string corresponding to input string.For example, in addition to the above-mentioned error correction algorithm enumerated, entangling based on editing distance can also be used Miscount method and the error correction algorithm based on statistics etc..
Wherein, the error correction algorithm based on editing distance can specifically include：Following four are carried out to each position of input string Kind error correction is attempted：One character of insertion, a character is deleted, replace a character and replaces former and later two character positions, with production Error correction string sequence corresponding to the raw input string.
Error correction algorithm based on statistics can excavate generation error correcting model by big data, and the error correcting model can be used for learning Error correction string then can input input by the wrong defeated probability (hereinafter referred to as error correcting model probability) for input string to the error correcting model String, and each error correction string is exported by the wrong defeated probability for input string by the error correcting model.For example, input string is " wiai ", error correction string For " woai ", then above-mentioned error correcting model probability can be used for representing " woai " by the wrong defeated probability into " wiai ", in actual applications, Statistical analysis can be carried out to the input behavior of user, to obtain above-mentioned error correcting model probability.It is appreciated that the embodiment of the present invention It is not any limitation as specific error correction algorithm.
Step 102, when the error correction string meets preset group entry part, to the error correction string carry out intelligent word, obtain First group of word result corresponding to the error correction string；
After error correction is carried out to input string and obtains error correction string, it can determine whether the error correction string meets preset group Entry part, if satisfied, then intelligent word can be carried out to the error correction string, obtain first group of word knot corresponding to the error correction string Fruit, thus, it is possible to correctly group word result after directly obtaining error correction, so as to improve the accuracy of intelligent word.
The embodiment of the present invention can specifically provide the scheme whether error correction string meets preset group entry part that is identified below.
Scheme one
The syllable number that scheme one is included by error correction string judges whether the error correction string meets preset group entry part, specifically may be used To comprise the following steps：
Step S21, cutting is carried out according to syllable to the error correction string；
Step S22, when the number of syllables that cutting obtains exceeds preset group word threshold value, it is default to determine that the error correction string meets Group entry part.
In a particular application, if a syllable is only included in error correction string, a group word need not be carried out to the error correction string； If two syllables are included in error correction string, as included syllable " wo " and " men " in " women ", it is easy to hit system dictionary. Therefore, can not have to carry out a group word when the number of syllables for obtaining error correction string cutting is less than or equal to m (such as m=2).Therefore, may be used To set preset group word threshold value as 2, when the number of syllables that cutting obtains exceeds 2, it is believed that error correction string meets preset group word Condition.
In embodiments of the present invention, the preset group word threshold value can also be suitably adjusted according to current input environment.Example Such as, can be under different input environments, the average number of syllables that includes in the input string of counting user input, and set pre- If group word threshold value is：Average number of syllables/2.Such as under the input environment of game application, statistics obtains the defeated of certain user input It is a to enter the average number of syllables included in string, then the preset group word threshold value that can be arranged under the input environment of game application is： a/2.And under the input environment of document application, the average number of syllables that statistics obtains including in the input string of user input is B, then the preset group word threshold value that can be arranged under the input environment of document application are：b/2.Thus, in different input environments Under, it is more than in the number of syllables obtained to error correction string cutting " during average number of syllables/2 ", it may be determined that the error correction string meets Preset group entry part.
It is appreciated that the embodiment of the present invention can adjust the preset group word threshold value according to actual conditions, the present invention is implemented Example is for setting the concrete mode of the preset group word threshold value not to be any limitation as.For example, it is also possible to the preset group word threshold is set It is worth and is：Average number of syllables/4.When the number of syllables obtained to error correction string cutting meets following condition：[1/4,1] × be averaged sound When saving number, it may be determined that the error correction string meets preset group entry part, can now trigger and carry out intelligent word to error correction string, First group of word result is obtained, and first group of word result is showed as candidate item.Now, input method procedure can be with The probability that user in this case selects first group of word result to carry out screen is counted, if probability is less than certain threshold value, The preset group word threshold value can suitably be increased, otherwise can suitably reduce the preset group word threshold value.
In a particular application, user can be obtained by counters count selects first group of word result to carry out the general of upper screen Rate.For example, two counters can be set, one of them is used to be recorded in the first group of word result deposited in candidate item after error correction When, user selects the number of " first group of word result ", and such as c1, another is used to be recorded in first deposited in candidate item after error correction During group word result, user is without the number of selection " first group of word result ", such as c2, then above-mentioned probability is c1/ (c1+c2).
Or to count to obtain user first group of word result can also be selected to enter by shielding the log recording of operation on user The probability shielded on row.For example, when first group of word result after error correction is deposited in candidate item, if user selects " first group of word As a result ", then a jc_zu upper screen operation log recording is recorded, if user does not select " first group of word result ", is recorded One jc_zu_null upper screen operation log recording.
So, the log recording of operation can be shielded on the user in nearest period T by counting, user's choosing can be obtained Select the probability that first group of word result carries out screen.
Scheme two
Scheme two judges whether the error correction string meets preset group word by the word frequency of the system word to match with error correction string Condition, specifically it may include steps of：
Step S31, according to the error correction string inquiry system dictionary；
Step S32, the system word that matches with the error correction string in the system dictionary be present, and the system word When word frequency is less than default word frequency threshold value, determine that the error correction string meets preset group entry part.
In embodiments of the present invention, the system word in the error correction string completely hits system dictionary, and the word frequency of system word , can be without a group word when higher；Namely the system word to match with the error correction string in the system dictionary be present, and institute When stating the word frequency of the system word to match less than default word frequency threshold value, illustrate that the system word frequency is poor, it is now it is considered that described Error correction string meets preset group entry part, can carry out intelligent word to the error correction string.
Scheme three
Scheme three judges whether the error correction string meets preset group entry part, specifically by the group word path with error correction string It may include steps of：
Step S41, according to the error correction string inquiry system dictionary；
Step S42, the system word to match with the error correction string in the system dictionary be present, and the error correction string is deposited At a plurality of group of word path, determine that the error correction string meets preset group entry part.
In embodiments of the present invention, system word is completely hit in the error correction string, but the error correction string has a plurality of group During word path, it may be determined that the error correction string meets preset group entry part.For example, the error correction string is " xianzai ", the error correction String can include group word path, and " xian ' zai " and group word path " xi ' an ' zai ", then it is pre- can to determine that the error correction string meets If organize entry part.In a particular application, intelligent word can be carried out to a plurality of group of word path, then again to each bar group word path pair The phrase result answered is ranked up.
Scheme four
In a particular application, if the entry corresponding with the pinyin string of user's input is not present in system dictionary, i.e., The intelligent word function of input method can be triggered.Therefore, whether scheme four completely hits system dictionary to judge by error correction string State whether error correction string meets preset group entry part, specifically may include steps of：
Step S51, according to the error correction string inquiry system dictionary；
When the system word to match with the error correction string being not present step S52, in the system dictionary, it is determined that described entangle Mistake string meets preset group entry part.
For example, the input string of user's input is " chianlema ", corresponding entangle is obtained by carrying out error correction to the input string Mistake string is " chifanlema ", entry " having a meal " corresponding with pinyin string " chifan " in system dictionary be present, and with spelling Entry corresponding to sound string " lema " " ", but " had a meal in the absence of complete entry corresponding with error correction string " chifanlema " ", hence, it can be determined that the error correction string meets preset group entry part, trigger the intelligent word function of input method procedure.
It is appreciated that in actual applications, when judging whether the error correction string meets preset group entry part, it can use Any one in above-mentioned four kinds of schemes or several combinations, the embodiment of the present invention is for judging whether the error correction string meets The concrete mode of preset group entry part is not any limitation as.
When it is determined that the error correction string meets preset group entry part, intelligent word can be carried out to the error correction string, obtained First group of word result corresponding to the error correction string.Alternatively, it is described that intelligent word is carried out to the error correction string, obtain the error correction Corresponding to string the step of first group of word result, it can specifically include：
Step S61, cutting is carried out according to syllable to the error correction string, obtains a plurality of Zu Ci roads corresponding to the error correction string Footpath；
Step S62, by inquiry system dictionary and user thesaurus, a group word is carried out to every group word path；
Step S63, according to preset binary storehouse, path score corresponding to the Zu Ci roads warp is determined；
Step S64, acquisition approach score meets first group of word result corresponding to the group word path of predetermined threshold value.
In one kind application example of the present invention, it is assumed that obtained error correction string is： “nanjingshichangjiangdaqiao”.Cutting is carried out according to syllable to the error correction string first, obtains following cutting result： " Nan/jing/shi/chang/jiang/da/qiao ", and a plurality of group of word path corresponding to the error correction string is obtained, having In body application, if error correction string can be using cutting as N number of syllable, the error correction string just has the different group word path of 2^N kinds, such as can To obtain such as the following group word path：
Group word path 1：nan’/jing’shi’/chang’jiang’/da’qiao/
Group word path 2：nan’jing’/shi’chang’/jiang’da’qiao/
Group word path 3：nan’jing’shi’/chang’jiang’/da’qiao/
Then, by inquiry system dictionary and user thesaurus, a group word is carried out to every group word path, and calculate to reduce Complexity, beam search algorithms can be used, i.e., each group word path only retains unitary probability topK (such as k=3) individual word Bar.Such as include " south ", " man ", " hardly possible " for above-mentioned group of word path 1, the entry of the corresponding topk unitary probability of syllable " nan "； The entry of the corresponding topk unitary probability of syllable " Jingshi " includes " being unexpectedly ", " warning ", " being only "；
Next, according to preset binary storehouse, path score corresponding to the Zu Ci roads warp is determined；Path score can pass through two First probability product is calculated.For example, for above-mentioned group of word path 1, syllable " nan " can be obtained by inquiring about preset binary storehouse With the bivariate probability score of syllable " jingshi ", and obtain wherein highest bivariate probability score, for example, syllable " nan " with The bivariate probability in topK group word path is scored at corresponding to syllable " jingshi "：The bivariate probability of " man's warning " is scored at p1, The bivariate probability of " man is unexpectedly " is scored at p2, and the bivariate probability of " hardly possible is unexpectedly " is scored at p3；So next syllable Top_k of " changjiang " and above " warning ", which organizes word path, includes " the Changjiang river ", " sing by ", " Chang River ", and corresponds to respectively Bivariate probability be scored at t1, t2, t3；" changjiang " and the top_k group word path of " being unexpectedly " above include " the Changjiang river ", " Chang Jiang ", " sing by ", and corresponding bivariate probability is scored at t4, t5, t6 respectively；Then syllable " nan " and syllable " jingshi " Highest bivariate probability is scored at：max(p1*t1,p1*t2,p1*t3,P2*t4,p2*t5,p2*t6,P3*t4,p3*t5,p3* t6)；If the score is less than predetermined threshold value G, the group word process to this group of word path can be stopped.As procedure described above, successively A group word is carried out to each group word paths such as a group word path 2, group word paths 3.Following first group of word result may finally be obtained：" hardly possible is alert Show the Yangtze Bridge ", " Nanjing market Jiang great Qiao ", " the Nanjing Yangtze Bridge " etc..
Step 103, first group of word result showed as candidate item.
Intelligent word is being carried out to the error correction string, can be with after obtaining first group of word result corresponding to the error correction string First group of word result is showed as candidate item, so that user is selected.
To sum up, the embodiment of the present invention first carries out error correction to input string, obtains institute before intelligent word is carried out to input string State error correction string corresponding to input string；When the error correction string meets preset group entry part, intelligent word is carried out to the error correction string, Obtain first group of word result corresponding to the error correction string；And first group of word result is showed as candidate item.By It is that intelligent word, correct group of word after directly exporting error correction to user are carried out to the input string after error correction in the embodiment of the present invention As a result, so as to improve a group accuracy for word result, and then can solve in the prior art, user is seeing the group word of mistake Just recognize oneself to have input the pinyin string of mistake when as a result, it is necessary to the input string of deletion error and re-start input, lead The problem of causing input efficiency relatively low, to improve input efficiency.
Embodiment of the method two
The present embodiment can also obtain on the basis of above-described embodiment one and show what is matched with the prefix of error correction string Match entry.Reference picture 2, a kind of step flow chart of input method embodiment two of the present invention is shown, can specifically be included：
Step 201, error correction is carried out to input string, obtain error correction string corresponding to the input string；
Step 202, when the error correction string meets preset group entry part, to the error correction string carry out intelligent word, obtain First group of word result corresponding to the error correction string；
Step 203, first group of word result showed as candidate item；
Step 204, the preset dictionary of prefix lookups according to the error correction string, obtain matching with the prefix of the error correction string Match entry；
Step 205, the match entry showed as candidate item.
In embodiments of the present invention, except first group of word that intelligent word is carried out to error correction string and is obtained can be shown to user As a result, the match entry to match with the prefix of the input string can also be shown to user, so that in first group of word result not When can meet user's request, more selections can be provided the user.
Wherein, the preset dictionary can specifically include local dictionary and/or cloud dictionary.The local dictionary specifically can be with Including：Local cache dictionary and/or user thesaurus and/or system dictionary and/or cell dictionary etc..It is appreciated that the local Dictionary can include any of conventional art dictionary or its combination, or by those skilled in the art according to preset rule Any dictionary then obtained, and the storage location of the local dictionary may reside in server end or client, this hair Bright embodiment is not any limitation as the type and storage mode of the local dictionary.
The cloud dictionary can be stored in Cloud Server, and the cloud dictionary can be with the input number of real-time collecting different user According to expand the entry in local dictionary, meeting the input demand of more users.
In embodiments of the present invention, the error correction string can include simplicity sequence or spelling sequence.The one of the present invention Kind is applied in example, it is assumed that error correction string is " zhonghuarenmin ", then the error correction string is spelling sequence, and the error correction string meets Preset group entry part, then intelligent word is carried out to the error correction string, following first group of word result corresponding to the error correction string can be obtained： " the Chinese people ".Further, it is also possible to by inquiring about local dictionary, matching corresponding with the prefix of the error correction string " zhong " is obtained Entry, such as " in ", " kind ", " weight ", " clock ", then can be by above-mentioned first group of word result " the Chinese people " and above-mentioned match entry " in ", " kind ", " weight ", " clock " etc. showed as candidate item.
For another example, it is assumed that error correction string is " zhog ", the error correction string can be used as phonetic " zhongguo ", " zhonggong ", The simplicity sequence of " zhonggao " etc., and the error correction string includes two simplicity syllables, therefore meet preset group entry part, then to this Error correction string carries out intelligent word, can obtain following first group of word result corresponding to the error correction string：" China ", " final draft ", " in Altogether " etc..Further, it is also possible to by inquiring about local dictionary, match entry corresponding with the prefix of the error correction string " zho " is obtained, such as " in ", " last ", " afterwards ", " kind " etc., then can be by above-mentioned first group of word result " China ", " final draft ", " in altogether " and above-mentioned Match entry " in ", " last ", " afterwards ", " kind " etc. showed as candidate item.
To sum up, the embodiment of the present invention is in the first group of word result obtained to user's displaying to error correction string progress intelligent word On the basis of, the match entry to match with the prefix of the input string can also be shown to user, provides the user more choosings Select, the flexibility of input method can be improved, and meet the needs of different user.
Embodiment of the method three
The present embodiment can also obtain second group of word knot corresponding to the input string on the basis of above-described embodiment one Fruit, and first group of word result, second group of word result and match entry are ranked up.Reference picture 3, show the one of the present invention The step flow chart of kind input method embodiment three, can specifically include：
Step 301, error correction is carried out to input string, obtain error correction string corresponding to the input string；
Step 302, when the error correction string meets preset group entry part, to the error correction string carry out intelligent word, obtain First group of word result corresponding to the error correction string；
Step 303, when the input string meets preset group entry part, to the input string carry out intelligent word, obtain Second group of word result corresponding to the input string；
Step 304, the preset dictionary of prefix lookups according to the error correction string, obtain matching with the prefix of the error correction string The first match entry；
Step 305, the preset dictionary of prefix lookups according to the input string, obtain matching with the prefix of the input string The second match entry；
Step 306, according to context corresponding to the input string, current input environment, system word frequency and group word speech mould At least one of type, first group of word result, second group of word result, the first match entry and the second match entry are carried out Sequence；
Step 307, first group of word result by after sequence, second group of word result, the first match entry and the second matching word Bar is showed as candidate item.
In a particular application, during error correction is carried out to input string, it is possible to occur correct input string by mistake Error correction is the scene of the input string of mistake, is sent out in order to avoid providing the user the situation of the group word result of mistake in such a scenario Raw, the embodiment of the present invention, can also be defeated to user on the basis of intelligent word is carried out to error correction string and obtains first group of word result The input string entered also carries out intelligent word and obtains second group of word result, and can show second group of word result to user, So so that user can select from second group of word result corresponding to first group of word result corresponding to error correction string and input string Required group word result, so as to improve a group correctness for word result.
In addition, the embodiment of the present invention can also according to the error correction string and the preset dictionary of prefix lookups of the input string, The first match entry and the second match entry to match with the prefix of the error correction string and the input string is respectively obtained, finally First group of word result, second group of word result, the first match entry and the second match entry are ranked up and are presented to use Family.So as to provide the user as more as possible and accurate candidate item, offered convenience for the input of user, and improve defeated The accuracy entered.
In embodiments of the present invention, can be according to context, current input environment, system word frequency corresponding to the input string At least one of with group word language model, to first group of word result, second group of word result, the first match entry and second Match entry be calculated respectively one sequence score, and according to the sequence score to first group of word result, second group Word result, the first match entry and the second match entry are ranked up and showed.
For example, the sequence score can be：Group word path score+and hereinbefore or hereinafter between bivariate probability+error correction Candidate's punishment (can be the different punishment assigned according to different type of error correction)+environment attribute score, by coming for highest scoring The foremost of candidate list.
Wherein, the environment attribute score can be stored in system dictionary, and each entry is corresponding with system dictionary Probability is used under varying environment, can be more in word path by that will organize for first group of word result or second group of word result The environment score accumulation calculating of individual entry obtains.It is appreciated that the mode of above-mentioned calculating sequence score is only as of the invention one Kind applies example, and the embodiment of the present invention is not any limitation as calculating the concrete mode for the score that sorts.
For example, the use probability of each entry under various circumstances can be preserved in system dictionary, such as entry " so simultaneously Ovum " under the environment such as instant messaging, office system is respectively p1, p2 etc. using probability, at the same time it can also preserve process with not With the mapping relations between environment, when being inputted in different processes using input method, input method identifies currently first Environment corresponding to the process of place, then can be got during word is looked into each entry correspond to current environment use it is general Rate, whole first group of word is obtained finally by the use probability accumulation calculating that multiple entries in group word path are corresponded to current environment As a result or second group of word result environment attribute score.
To sum up, the embodiment of the present invention can be according to context, current input environment, system word frequency and group corresponding to input string At least one of word language model, to obtained first group of word result, second group of word result, the first match entry and second It is ranked up and shows with entry, to provide the user as more as possible and accurate candidate item, avoids providing the user mistake The situation of group word result occurs, and is offered convenience for the input of user, and improves the accuracy of input.
Using example
In one kind application example of the present invention, it is assumed that user's word to be inputted " having had a meal ", which corresponds to input string, to be " chifanlema ", but user has but been incorrectly entered input string " chianlema ", then input process of the present invention specifically can be with It is as follows：
(1) input string for obtaining user's input is " chianlema "；
(2) according to input string inquiry system dictionary, because the input string fails completely to hit system word, then according to input string Prefix lookups system dictionary etc., and the entry hit by sequence, frequency modulation returning part obtains candidate list 1, wherein can With including the candidate item such as " eating peace ", " red bank "；
(3) error correction is carried out to input string " chianlema ", it is " chifanlema " to obtain error correction string.Due to the error correction string Fail completely to hit system word, then according to prefix lookups system dictionary of error correction string etc., and pass through sequence, frequency modulation returning part The entry of hit, candidate list 2 is obtained, wherein the candidate items such as " having a meal ", " red meal " can be included；
(4) because error correction string " chifanlema " includes four syllables, meet preset group entry part, then the error correction string is entered Row intelligent word, first group of word result corresponding to the error correction string is obtained, first group of word result is ranked up, frequency modulation, waited List 3 is selected, wherein the candidate items such as " having had a meal ", " having eaten instead ", " red meal " can be included；
(5) because input string " chianlema " also meets preset group entry part, then intelligent word is carried out to input string, obtained To candidate list 4, wherein the candidate items such as " eat and pacified ", " red bank " can be included；
(6) according in context, current input environment, system word frequency and group word language model corresponding to the input string At least one candidate item in candidate list 1- candidate lists 4 is ranked up merging, the candidate list bag after being sorted Include：The candidate item such as " having had a meal ", " having eaten instead ", " red meal ", " having a meal ", " eating peace ", user may be selected " to have a meal " carry out screen.
Device embodiment
Reference picture 4, a kind of structured flowchart of input unit embodiment of the present invention is shown, can specifically be included：
Correction module 401, for carrying out error correction to input string, obtain error correction string corresponding to the input string；
First group of word module 402, for when the error correction string meets preset group entry part, intelligence to be carried out to the error correction string Word can be organized, obtains first group of word result corresponding to the error correction string；
Display module 403, for first group of word result to be showed as candidate item.
In a kind of alternative embodiment of the present invention, first group of word module 402, it can specifically include：
Submodule is divided, for carrying out cutting according to syllable to the error correction string；
Determination sub-module, when the number of syllables for being obtained in cutting exceeds preset group word threshold value, determine the error correction string Meet preset group entry part.
In another alternative embodiment of the present invention, first group of word module 402, it can specifically include：
Submodule is inquired about, for according to the error correction string inquiry system dictionary；
Determination sub-module, for the system word to match with the error correction string in the system dictionary be present, and it is described When the word frequency of system word is less than default word frequency threshold value, determine that the error correction string meets preset group entry part.
In another alternative embodiment of the present invention, first group of word module 402, it can specifically include：
Submodule is inquired about, for according to the error correction string inquiry system dictionary；
Determination sub-module, for the system word to match with the error correction string in the system dictionary be present, and it is described When error correction string has a plurality of group of word path, determine that the error correction string meets preset group entry part.
In another alternative embodiment of the present invention, first group of word module 402, it can specifically include：
Cutting submodule, for carrying out cutting according to syllable to the error correction string, obtain a plurality of corresponding to the error correction string Group word path；
Group lexon module, for by inquiry system dictionary and user thesaurus, a group word to be carried out to every group word path；
Molecular modules are calculated to obtain, for according to preset binary storehouse, determining path score corresponding to the Zu Ci roads warp；
Acquisition submodule, meet first group of word result corresponding to the group word path of predetermined threshold value for acquisition approach score.
In another alternative embodiment of the present invention, the correction module 401, it can specifically include：
Mistake determination sub-module, for according to position error correction, dynamics error correction and closing at least one of key mapping error correction and entangling Method is miscounted, determines the error character in the input string；
Error correction submodule, for carrying out correction process to the error character, obtain error correction string corresponding to the input string.
In another alternative embodiment of the present invention, described device can also include：
First matching module, for the preset dictionary of prefix lookups according to the error correction string, obtain and the error correction string The first match entry that prefix matches；
Display module, it is additionally operable to be showed first match entry as candidate item.
In another alternative embodiment of the present invention, described device can also include：
Second group of word module, for when the input string meets preset group entry part, intelligence to be carried out to the input string Group word, obtains second group of word result corresponding to the input string；
Second matching module, for the preset dictionary of prefix lookups according to the input string, obtain and the input string The second match entry that prefix matches；
Order module, for according to context, current input environment, system word frequency and group word corresponding to the input string At least one of model is sayed, to first group of word result, second group of word result, the first match entry and the second match entry It is ranked up；
Display module, it is additionally operable to first group of word result after sequence, second group of word result, the first match entry and second Match entry is showed as candidate item.
For device embodiment, because it is substantially similar to embodiment of the method, so description is fairly simple, it is related Part illustrates referring to the part of embodiment of the method.
Each embodiment in this specification is described by the way of progressive, what each embodiment stressed be with The difference of other embodiment, between each embodiment identical similar part mutually referring to.
On the device in above-described embodiment, wherein modules perform the concrete mode of operation in relevant this method Embodiment in be described in detail, explanation will be not set forth in detail herein.
Fig. 5 is a kind of block diagram of device 800 for being used to input according to an exemplary embodiment.For example, device 800 Can be mobile phone, computer, digital broadcast terminal, messaging devices, game console, tablet device, Medical Devices, Body-building equipment, personal digital assistant etc..
Reference picture 5, device 800 can include following one or more assemblies：Processing component 802, memory 804, power supply Component 806, multimedia groupware 808, audio-frequency assembly 810, the interface 812 of input/output (I/O), sensor cluster 814, and Communication component 816.
The integrated operation of the usual control device 800 of processing component 802, such as communicated with display, call, data, phase The operation that machine operates and record operation is associated.Treatment element 802 can refer to including one or more processors 820 to perform Order, to complete all or part of step of above-mentioned method.In addition, processing component 802 can include one or more modules, just Interaction between processing component 802 and other assemblies.For example, processing component 802 can include multi-media module, it is more to facilitate Interaction between media component 808 and processing component 802.
Memory 804 is configured as storing various types of data to support the operation in equipment 800.These data are shown Example includes the instruction of any application program or method for being operated on device 800, contact data, telephone book data, disappears Breath, picture, video etc..Memory 804 can be by any kind of volatibility or non-volatile memory device or their group Close and realize, as static RAM (SRAM), Electrically Erasable Read Only Memory (EEPROM) are erasable to compile Journey read-only storage (EPROM), programmable read only memory (PROM), read-only storage (ROM), magnetic memory, flash Device, disk or CD.
Power supply module 806 provides electric power for the various assemblies of device 800.Power supply module 806 can include power management system System, one or more power supplys, and other components associated with generating, managing and distributing electric power for device 800.
Multimedia groupware 808 is included in the screen of one output interface of offer between described device 800 and user.One In a little embodiments, screen can include liquid crystal display (LCD) and touch panel (TP).If screen includes touch panel, screen Curtain may be implemented as touch-screen, to receive the input signal from user.Touch panel includes one or more touch sensings Device is with the gesture on sensing touch, slip and touch panel.The touch sensor can not only sensing touch or sliding action Border, but also detect and touched or the related duration and pressure of slide with described.In certain embodiments, more matchmakers Body component 808 includes a front camera and/or rear camera.When equipment 800 is in operator scheme, such as screening-mode or During video mode, front camera and/or rear camera can receive outside multi-medium data.Each front camera and Rear camera can be a fixed optical lens system or have focusing and optical zoom capabilities.
Audio-frequency assembly 810 is configured as output and/or input audio signal.For example, audio-frequency assembly 810 includes a Mike Wind (MIC), when device 800 is in operator scheme, during such as call model, logging mode and speech recognition mode, microphone by with It is set to reception external audio signal.The audio signal received can be further stored in memory 804 or via communication set Part 816 is sent.In certain embodiments, audio-frequency assembly 810 also includes a loudspeaker, for exports audio signal.
I/O interfaces 812 provide interface between processing component 802 and peripheral interface module, and above-mentioned peripheral interface module can To be keyboard, click wheel, button etc..These buttons may include but be not limited to：Home button, volume button, start button and lock Determine button.
Sensor cluster 814 includes one or more sensors, and the state for providing various aspects for device 800 is commented Estimate.For example, sensor cluster 814 can detect opening/closed mode of equipment 800, and the relative positioning of component, for example, it is described Component is the display and keypad of device 800, and sensor cluster 814 can be with 800 1 components of detection means 800 or device Position change, the existence or non-existence that user contacts with device 800, the orientation of device 800 or acceleration/deceleration and device 800 Temperature change.Sensor cluster 814 can include proximity transducer, be configured to detect in no any physical contact The presence of neighbouring object.Sensor cluster 814 can also include optical sensor, such as CMOS or ccd image sensor, for into As being used in application.In certain embodiments, the sensor cluster 814 can also include acceleration transducer, gyro sensors Device, Magnetic Sensor, pressure sensor or temperature sensor.
Communication component 816 is configured to facilitate the communication of wired or wireless way between device 800 and other equipment.Device 800 can access the wireless network based on communication standard, such as WiFi, 2G or 3G, or combinations thereof.In an exemplary implementation In example, communication component 816 receives broadcast singal or broadcast related information from external broadcasting management system via broadcast channel. In one exemplary embodiment, the communication component 816 also includes near-field communication (NFC) module, to promote junction service.Example Such as, in NFC module radio frequency identification (RFID) technology can be based on, Infrared Data Association (IrDA) technology, ultra wide band (UWB) technology, Bluetooth (BT) technology and other technologies are realized.
In the exemplary embodiment, device 800 can be believed by one or more application specific integrated circuits (ASIC), numeral Number processor (DSP), digital signal processing appts (DSPD), PLD (PLD), field programmable gate array (FPGA), controller, microcontroller, microprocessor or other electronic components are realized, for performing the above method.
In the exemplary embodiment, a kind of non-transitorycomputer readable storage medium including instructing, example are additionally provided Such as include the memory 804 of instruction, above-mentioned instruction can be performed to complete the above method by the processor 820 of device 800.For example, The non-transitorycomputer readable storage medium can be ROM, random access memory (RAM), CD-ROM, tape, floppy disk With optical data storage devices etc..
A kind of non-transitorycomputer readable storage medium, when the instruction in the storage medium is by the processing of mobile terminal When device performs so that mobile terminal is able to carry out a kind of input method, and methods described includes：Error correction is carried out to input string, obtained Error correction string corresponding to the input string；When the error correction string meets preset group entry part, smart group is carried out to the error correction string Word, obtain first group of word result corresponding to the error correction string；First group of word result is showed as candidate item.
Fig. 6 is the structural representation of server in the embodiment of the present invention.The server 1900 can be different because of configuration or performance And produce bigger difference, can include one or more central processing units (central processing units, CPU) 1922 (for example, one or more processors) and memory 1932, one or more storage application programs 1942 or the storage medium 1930 (such as one or more mass memory units) of data 1944.Wherein, memory 1932 Can be of short duration storage or persistently storage with storage medium 1930.Be stored in storage medium 1930 program can include one or More than one module (diagram does not mark), each module can include operating the series of instructions in server.Further Ground, central processing unit 1922 be could be arranged to communicate with storage medium 1930, and storage medium 1930 is performed on server 1900 In series of instructions operation.
Server 1900 can also include one or more power supplys 1926, one or more wired or wireless nets Network interface 1950, one or more input/output interfaces 1958, one or more keyboards 1956, and/or, one or More than one operating system 1941, such as WindowsServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM Etc..
Those skilled in the art will readily occur to the present invention its after considering specification and putting into practice invention disclosed herein Its embodiment.It is contemplated that cover the present invention any modification, purposes or adaptations, these modifications, purposes or Person's adaptations follow the general principle of the present invention and including the undocumented common knowledges in the art of the disclosure Or conventional techniques.Description and embodiments are considered only as exemplary, and true scope and spirit of the invention are by following Claim is pointed out.
It should be appreciated that the invention is not limited in the precision architecture for being described above and being shown in the drawings, and And various modifications and changes can be being carried out without departing from the scope.The scope of the present invention is only limited by appended claim
The foregoing is only presently preferred embodiments of the present invention, be not intended to limit the invention, it is all the present invention spirit and Within principle, any modification, equivalent substitution and improvements made etc., it should be included in the scope of the protection.
Above to a kind of input method provided by the present invention, a kind of input unit and a kind of device for being used to input, enter Go and be discussed in detail, specific case used herein is set forth to the principle and embodiment of the present invention, and the above is implemented The explanation of example is only intended to help the method and its core concept for understanding the present invention；Meanwhile for the general technology people of this area Member, according to the thought of the present invention, there will be changes in specific embodiments and applications, in summary, this explanation Book content should not be construed as limiting the invention.

Claims (10)

1. a kind of input method, it is characterised in that methods described includes：
Error correction is carried out to input string, obtains error correction string corresponding to the input string；
When the error correction string meets preset group entry part, intelligent word is carried out to the error correction string, obtains the error correction string pair The first group of word result answered；
First group of word result is showed as candidate item.
2. according to the method for claim 1, it is characterised in that determine that the error correction string meets the step of preset group entry part Suddenly, including：
Cutting is carried out according to syllable to the error correction string；
When the number of syllables that cutting obtains exceeds preset group word threshold value, determine that the error correction string meets preset group entry part.
3. according to the method for claim 1, it is characterised in that determine that the error correction string meets the step of preset group entry part Suddenly, including：
According to the error correction string inquiry system dictionary；
The system word to match with the error correction string in the system dictionary be present, and the word frequency of the system word is less than default During word frequency threshold value, determine that the error correction string meets preset group entry part.
4. according to the method for claim 1, it is characterised in that determine that the error correction string meets the step of preset group entry part Suddenly, including：
According to the error correction string inquiry system dictionary；
The system word to match with the error correction string in the system dictionary be present, and the error correction string has a plurality of Zu Ci roads During footpath, determine that the error correction string meets preset group entry part.
5. according to the method for claim 1, it is characterised in that it is described that intelligent word is carried out to the error correction string, obtain institute The step of stating first group of word result corresponding to error correction string, including：
Cutting is carried out according to syllable to the error correction string, obtains a plurality of group of word path corresponding to the error correction string；
By inquiry system dictionary and user thesaurus, a group word is carried out to every group word path；
According to preset binary storehouse, path score corresponding to the Zu Ci roads warp is determined；
Acquisition approach score meets first group of word result corresponding to the group word path of predetermined threshold value.
6. according to the method for claim 1, it is characterised in that it is described that error correction is carried out to input string, obtain the input string The step of corresponding error correction string, including：
According to position error correction, dynamics error correction and at least one of key mapping error correction error correction algorithm is closed on, is determined in the input string Error character；
Correction process is carried out to the error character, obtains error correction string corresponding to the input string.
7. according to the method for claim 1, it is characterised in that methods described also includes：
According to the preset dictionary of prefix lookups of the error correction string, obtain and the prefix of the error correction string matches first matches word Bar；
First match entry is showed as candidate item.
8. according to the method for claim 7, it is characterised in that methods described also includes：
When the input string meets preset group entry part, intelligent word is carried out to the input string, obtains the input string pair The second group of word result answered；
The preset dictionary of prefix lookups according to the input string, is obtained and the prefix of the input string matches second matches word Bar；
According at least one in context, current input environment, system word frequency and group word language model corresponding to the input string Kind, first group of word result, second group of word result, the first match entry and the second match entry are ranked up；
Using first group of word result after sequence, second group of word result, the first match entry and the second match entry as candidate item Showed.
A kind of 9. input unit, it is characterised in that including：
Correction module, for carrying out error correction to input string, obtain error correction string corresponding to the input string；
First group of word module, for when the error correction string meets preset group entry part, intelligent word to be carried out to the error correction string, Obtain first group of word result corresponding to the error correction string；
Display module, for first group of word result to be showed as candidate item.
A kind of 10. device for being used to input, it is characterised in that include memory, and one or more than one program, One of them or more than one program storage is configured to by one or more than one computing device in memory One or more than one program bag contains the instruction for being used for being operated below：
Error correction is carried out to input string, obtains error correction string corresponding to the input string；
When the error correction string meets preset group entry part, intelligent word is carried out to the error correction string, obtains the error correction string pair The first group of word result answered；
First group of word result is showed as candidate item.
CN201610849668.2A 2016-09-23 2016-09-23 Input method, input device and input device Active CN107870677B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610849668.2A CN107870677B (en) 2016-09-23 2016-09-23 Input method, input device and input device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610849668.2A CN107870677B (en) 2016-09-23 2016-09-23 Input method, input device and input device

Publications (2)

Publication Number Publication Date
CN107870677A true CN107870677A (en) 2018-04-03
CN107870677B CN107870677B (en) 2022-02-25

Family

ID=61751436

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610849668.2A Active CN107870677B (en) 2016-09-23 2016-09-23 Input method, input device and input device

Country Status (1)

Country Link
CN (1) CN107870677B (en)

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109597500A (en) * 2018-12-06 2019-04-09 北京金山安全软件有限公司 Input error correction method and device for Chinese pinyin and electronic equipment
CN110262672A (en) * 2019-06-18 2019-09-20 北京字节跳动网络技术有限公司 It is recommended that candidate list generation method and device
CN110297549A (en) * 2019-05-15 2019-10-01 北京百度网讯科技有限公司 Input processing method, device, equipment and storage medium
CN110333787A (en) * 2019-04-28 2019-10-15 华为技术有限公司 The method and apparatus for inputting character
CN110389666A (en) * 2018-04-16 2019-10-29 北京搜狗科技发展有限公司 A kind of input error correction method and device
CN110389668A (en) * 2018-04-20 2019-10-29 北京搜狗科技发展有限公司 A kind of input method, device and the device for input
CN110780749A (en) * 2018-07-11 2020-02-11 北京搜狗科技发展有限公司 Character string error correction method and device
CN112015279A (en) * 2019-05-28 2020-12-01 北京搜狗科技发展有限公司 Key mis-touch error correction method and device
CN112989148A (en) * 2019-12-13 2021-06-18 华为技术有限公司 Error correction word ordering method and device, terminal equipment and storage medium

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5634134A (en) * 1991-06-19 1997-05-27 Hitachi, Ltd. Method and apparatus for determining character and character mode for multi-lingual keyboard based on input characters
CN101710262A (en) * 2009-12-11 2010-05-19 北京搜狗科技发展有限公司 Error correction method and error correction device of characters
CN102135814A (en) * 2011-03-30 2011-07-27 北京搜狗科技发展有限公司 Word input method and system
CN102866782A (en) * 2011-07-06 2013-01-09 哈尔滨工业大学 Input method and input method system for improving sentence generating efficiency
CN104915264A (en) * 2015-05-29 2015-09-16 北京搜狗科技发展有限公司 Input error-correction method and device

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5634134A (en) * 1991-06-19 1997-05-27 Hitachi, Ltd. Method and apparatus for determining character and character mode for multi-lingual keyboard based on input characters
CN101710262A (en) * 2009-12-11 2010-05-19 北京搜狗科技发展有限公司 Error correction method and error correction device of characters
CN102135814A (en) * 2011-03-30 2011-07-27 北京搜狗科技发展有限公司 Word input method and system
CN102866782A (en) * 2011-07-06 2013-01-09 哈尔滨工业大学 Input method and input method system for improving sentence generating efficiency
CN104915264A (en) * 2015-05-29 2015-09-16 北京搜狗科技发展有限公司 Input error-correction method and device

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110389666A (en) * 2018-04-16 2019-10-29 北京搜狗科技发展有限公司 A kind of input error correction method and device
CN110389668A (en) * 2018-04-20 2019-10-29 北京搜狗科技发展有限公司 A kind of input method, device and the device for input
CN110780749A (en) * 2018-07-11 2020-02-11 北京搜狗科技发展有限公司 Character string error correction method and device
CN110780749B (en) * 2018-07-11 2024-03-08 北京搜狗科技发展有限公司 Character string error correction method and device
CN109597500A (en) * 2018-12-06 2019-04-09 北京金山安全软件有限公司 Input error correction method and device for Chinese pinyin and electronic equipment
CN110333787A (en) * 2019-04-28 2019-10-15 华为技术有限公司 The method and apparatus for inputting character
CN110297549A (en) * 2019-05-15 2019-10-01 北京百度网讯科技有限公司 Input processing method, device, equipment and storage medium
CN112015279A (en) * 2019-05-28 2020-12-01 北京搜狗科技发展有限公司 Key mis-touch error correction method and device
CN112015279B (en) * 2019-05-28 2024-02-13 北京搜狗科技发展有限公司 Key false touch error correction method and device
CN110262672A (en) * 2019-06-18 2019-09-20 北京字节跳动网络技术有限公司 It is recommended that candidate list generation method and device
CN110262672B (en) * 2019-06-18 2023-08-08 抖音视界有限公司 Suggested candidate list generation method and device
CN112989148A (en) * 2019-12-13 2021-06-18 华为技术有限公司 Error correction word ordering method and device, terminal equipment and storage medium

Also Published As

Publication number Publication date
CN107870677B (en) 2022-02-25

Similar Documents

Publication Publication Date Title
CN107870677A (en) A kind of input method, device and the device for input
CN107102746B (en) Candidate word generation method and device and candidate word generation device
CN107436691B (en) Method, client, server and device for correcting errors of input method
CN107229348A (en) A kind of input error correction method, device and the device for inputting error correction
CN107544684B (en) Candidate word display method and device
CN107608532A (en) A kind of association-feeding method, device and electronic equipment
CN107092424B (en) Display method and device of error correction items and device for displaying error correction items
CN108958503A (en) input method and device
CN107305438A (en) The sort method and device of candidate item, the device sorted for candidate item
CN107340880A (en) A kind of association-feeding method, device and the electronic equipment for realizing association's input
CN108121736A (en) A kind of descriptor determines the method for building up, device and electronic equipment of model
CN107918496A (en) It is a kind of to input error correction method and device, a kind of device for being used to input error correction
CN107193393A (en) Input method switching method and device
CN109961791A (en) A kind of voice information processing method, device and electronic equipment
CN108241690A (en) A kind of data processing method and device, a kind of device for data processing
CN108073292A (en) A kind of intelligent word method and apparatus, a kind of device for intelligent word
CN106886294B (en) Input method error correction method and device
CN109002184A (en) A kind of association method and device of input method candidate word
CN107797676B (en) Single character input method and device
CN108803890A (en) A kind of input method, input unit and the device for input
CN111611369B (en) Interaction method and related device based on artificial intelligence
CN110286775A (en) A kind of dictionary management method and device
CN112015279B (en) Key false touch error correction method and device
CN108073293A (en) A kind of definite method and apparatus of target phrase
CN108628461A (en) A kind of input method and device, a kind of method and apparatus of update dictionary

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant