CN105955495A - Information input method and device - Google Patents
Information input method and device Download PDFInfo
- Publication number
- CN105955495A CN105955495A CN201610282718.3A CN201610282718A CN105955495A CN 105955495 A CN105955495 A CN 105955495A CN 201610282718 A CN201610282718 A CN 201610282718A CN 105955495 A CN105955495 A CN 105955495A
- Authority
- CN
- China
- Prior art keywords
- input
- user
- feature vector
- candidate word
- text
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
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
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Document Processing Apparatus (AREA)
Abstract
The invention discloses an information input method and device. One specific implementation manner of the method comprises the following steps of: obtaining user input information recorded by an input method application within a predetermined time period; analyzing the user input information, and extracting input characteristics for representing input habits of users; according to at least one input characteristic, determining candidate words responding to input texts of the users and to be displayed by the input method application; according to at least one input characteristic, determining the sequence of the candidate words; and displaying the candidate words according to the determined sequence. Due to the implementation manner, the information input efficiency is increased.
Description
Technical field
The application relates to field of computer technology, is specifically related to input method technique field, especially relates to
And data inputting method and device.
Background technology
During user uses application, when needing to input in the information input area of application
During information, generally completed by input method.The dress that input method inputs as a kind of user of auxiliary
Putting, target is can to allow user is more convenient, faster, input more accurately.
But, existing input method technology, typically by big data analysis, provides adaptive big portion
The unified input method at demultiplexing family, accordingly, there are the input habit not adapting to different user
Used problem, information input efficiency is relatively low.
Summary of the invention
The purpose of the application is to propose data inputting method and the device of a kind of improvement, solves
The technical problem that background section above is mentioned.
First aspect, this application provides a kind of data inputting method, and described method includes: obtain
Take input method and apply the user's input information recorded within a predetermined period of time；Described user is inputted
Information is analyzed, and extracts the input feature vector being used for characterizing the input habit of user；To described use
Family input information is analyzed, and extracts the input feature vector being used for characterizing the input habit of user；Root
According at least one input feature vector, the input text in response to described user is treated by described input
The candidate word that method application presents is determined；According at least one input feature vector described, determine
The order of candidate word；Determined by according to, order, presents candidate word.
In certain embodiments, described user's input information include input text and with described input
The upper screen result that text is corresponding, wherein, described upper screen result is that described user is from the time presented
Select the candidate word selected in word；And, described described user's input information is analyzed,
Extract the input feature vector being used for characterizing the input habit of user, including: according to described input text
At least one input feature vector is extracted with described upper screen result.
In certain embodiments, described in described method, described user's input information is analyzed,
Extract after the input feature vector of the input habit characterizing user, also include: at least one
Single target input feature vector in input feature vector, counts this mesh in described user's input information
The number of times that mark input feature vector is hit；The probability values pre-set is adjusted according to described number of times
Draw there is the general of the input habit corresponding with described target input feature vector for characterizing described user
Rate value, wherein, described probability values is used for characterizing random user to be had and inputs with described target
The probability of the input habit that feature is corresponding.
In certain embodiments, described the input in response to described user is treated by described input
The candidate word that method application presents is determined and determines the order of candidate word, including: according to
Input text in response to described user is treated to be presented by the application of described input method by described probit
The candidate word gone out is determined and determines the order of candidate word.
In certain embodiments, the described input feature vector of described statistics is in described user's input information
The number of times occurred, also includes: whether monitor described number of times more than predetermined threshold value；If it is,
Adjust the number of times after described number of times draws adjustment, wherein, before the number of times after adjustment is less than adjusting
Number of times.
Second aspect, this application provides a kind of message input device, and described device includes: institute
State device to include: acquisition module, be configured to obtain input method application and remember within a predetermined period of time
The user's input information of record；Extraction module, is configured to carry out described user's input information point
Analysis, extracts the input feature vector being used for characterizing the input habit of user；Candidate word determines module, joins
Put for according at least one input feature vector, the input text in response to described user is treated by
The candidate word that the application of described input method presents is determined；Order determines module, is configured to
According at least one input feature vector described, determine the order of candidate word；Presenting module, configuration is used
According to determined by order, present candidate word.
In certain embodiments, described user's input information include input text and with described input
The upper screen result that text is corresponding, wherein, described upper screen result is that described user is from the time presented
Select the candidate word selected in word；And, described extraction module, it is configured to further: root
At least one input feature vector is extracted according to described input text and described upper screen result.
In certain embodiments, described device also includes statistical module, is configured to: for extremely
Single target input feature vector in few a kind of input feature vector, counts at described user's input information
In the number of times that is hit of this target input feature vector；According to described number of times adjust pre-set initial
Probit draws have the input corresponding with described target input feature vector and practise for characterizing described user
Used probit, wherein, described probability values is used for characterizing random user to be had and described mesh
The probability of the input habit that mark input feature vector is corresponding.
In certain embodiments, described determine module, be configured to further: according to described generally
Rate value is treated inputting text in response to described user to be applied, by described input method, the time presented
Select word to be determined and determine the order of candidate word.
In certain embodiments, described statistical module, it is configured to further: monitor described time
Whether number is more than predetermined threshold value；If it is, adjust the number of times after described number of times draws adjustment,
Wherein, the number of times after adjustment is less than the number of times before adjusting.
The data inputting method of the application offer and device, by the predetermined amount of time to user
Input information be analyzed, and extract the input feature vector of input habit for characterizing user,
And according at least one input feature vector, determine candidate word and determine the order of candidate word so that wait
Select the coverage rate of word and the hit rate of head-word language to improve, and then improve the efficiency of information input.
Accompanying drawing explanation
By reading retouching in detail with reference to made non-limiting example is made of the following drawings
Stating, other features, purpose and advantage will become more apparent upon:
Fig. 1 is that the application can apply to exemplary system architecture figure therein；
Fig. 2 is the flow chart of an embodiment of the data inputting method according to the application；
Fig. 3 a is that an effect of the candidate word that the data inputting method according to the application presents is shown
It is intended to；
Fig. 3 b is another effect of the candidate word that the data inputting method according to the application presents
Schematic diagram；
Fig. 4 is the flow chart of another embodiment of the data inputting method according to the application；
Fig. 5 is the structural representation of an embodiment of the message input device according to the application；
Fig. 6 is adapted for the structure of the computer system of the server for realizing the embodiment of the present application
Schematic diagram.
Detailed description of the invention
With embodiment, the application is described in further detail below in conjunction with the accompanying drawings.It is appreciated that
, specific embodiment described herein is used only for explaining related invention, rather than to this
Bright restriction.It also should be noted that, for the ease of describe, accompanying drawing illustrate only with
About the part that invention is relevant.
It should be noted that in the case of not conflicting, the embodiment in the application and embodiment
In feature can be mutually combined.Describe this below with reference to the accompanying drawings and in conjunction with the embodiments in detail
Application.
Fig. 1 shows the reality of data inputting method or the message input device that can apply the application
Execute the exemplary system architecture 100 of example.
As it is shown in figure 1, system architecture 100 can include terminal unit 101,102,103,
Network 104 and server 105.Network 104 is in order at terminal unit 101,102,103 and
The medium of communication link is provided between server 105.Network 104 can include various connection class
Type, the most wired, wireless communication link or fiber optic cables etc..
User can use terminal unit 101,102,103 by network 104 and server 105
Alternately, to receive or to send message etc..Can be provided with on terminal unit 101,102,103
Various telecommunication customer ends are applied, and such as input method application, web browser applications, shopping class are answered
With, searching class application, JICQ, mailbox client, social platform software etc..
Terminal unit 101,102,103 can have display screen and supported web page browses
Various electronic equipments, include but not limited to smart mobile phone, panel computer, E-book reader,
(Moving Picture Experts Group Audio Layer III, dynamic image is special for MP3 player
Family compression standard audio frequency aspect 3), MP4 (Moving Picture Experts Group Audio
Layer IV, dynamic image expert's compression standard audio frequency aspect 4) player, portable meter on knee
Calculation machine and desk computer etc..
Server 105 can be to provide the server of various service, such as to terminal unit 101,
102, the data inputting method of display provides the background server supported on 103.Background server
Can be analyzed data such as the input requests received waiting and process, and by result (example
Candidate word data as to be presented) feed back to terminal unit.
It should be noted that the data inputting method that the embodiment of the present application is provided can be by servicing
Device 105 performs, and correspondingly, message input device can be arranged in server 105.This Shen
Please embodiment provide data inputting method can also be performed by terminal unit 101,102,103,
Correspondingly, message input device can be arranged at terminal unit 101,102,103；When this Shen
Before the data inputting method that please provide is performed by terminal unit 101,102,103, typically need
Terminal unit 101,102,103 is wanted to have with above-mentioned data inputting method to server 105 request
The data closed.The data inputting method provided with the embodiment of the present application in this application is by servicing
Device 105 illustrates as a example by performing.
It should be understood that the number of terminal unit, network and the server in Fig. 1 is only signal
Property.According to realizing needs, can have any number of terminal unit, network and server.
With continued reference to Fig. 2, it is shown that according to an embodiment of the data inputting method of the application
Flow process 200.Above-mentioned data inputting method, comprises the following steps:
Step 201, obtains input method and applies the user's input information recorded within a predetermined period of time.
In the present embodiment, data inputting method runs on electronic equipment thereon (such as Fig. 1
Shown server) can be utilized from user by wired connection mode or radio connection
Its terminal carrying out information input obtains input method and applies the user recorded within a predetermined period of time defeated
Enter information.It is pointed out that above-mentioned radio connection can include but not limited to 3G/4G
Connect, WiFi connects, bluetooth connects, WiMAX connects, Zigbee connects, UWB (ultra
Wideband) connection and other currently known or exploitation in the future radio connection.
In the present embodiment, input method application be pre-installed on terminal unit for receiving
The information of user's input, and present candidate word to user and select the application of purpose word for user.
Here, input method application can also record user's input information, the user's input information of record
Can be stored on the terminal unit (local) at input method place, it is also possible to be stored in input
The server end that method is supported, it is also possible to be stored in high in the clouds.Here user's input information is
The information that all operations applied in input method with user is relevant, such as, user in input method
Input frame in inputted the information of character, user is in the institute when utilizing input method to input
Input the candidate word gone out selected by the time interval between character and character, user.
In the present embodiment, can be month, a year pre-set in predetermined amount of time,
Or can also is that user utilizes its input method carrying out information input to be installed to input method place
Time point on terminal unit is this time carried out between the time between the time point of information input to user
Every.It is understood that input method applies the user's input information recorded within a predetermined period of time
It is referred to as the history input record of user.
Step 202, is analyzed user's input information, extracts the input for characterizing user
The input feature vector of custom.
In the present embodiment, based on the user's input information obtained in step 201, above-mentioned electronics
First user's input information can be analyzed by equipment (the such as server shown in Fig. 1),
Then extracting input feature vector, here, above-mentioned input feature vector is the spy for characterizing user habit
Levying, input feature vector and input habit are one to one.
In the present embodiment, the input habit of user includes but not limited to: full simplicity custom, side
Speech custom, click mistake custom or input content length custom.
In some optional implementations of the present embodiment, can be according to the use in input habit
Family time interval between character inputted when utilizing input method to input and character, carries
Take at least one input feature vector.
In some optional implementations of the present embodiment, above-mentioned user's input information includes defeated
Entering text and the upper screen result corresponding with above-mentioned input text, here, above-mentioned commodity result is
The candidate word that above-mentioned user selects from the candidate word presented.As example, in input method
Inputting " renming " in the input frame of application, the candidate word that input method is presented may have " people
Name ", " appointment " and " accepting one's fate ", if user selection " appointment ", then " appointment " is exactly
The upper screen result corresponding with " renming " this input text.
In some optional implementations of the present embodiment, can be according to input text and upper screen
Result extracts at least one input feature vector.
In some optional implementations of the present embodiment, full simplicity input habit can be to use
Family custom spelling or the custom of simplicity input, as example, user " appoints wanting input
Life " this word when, if user habit inputs in the input frame that input method is applied
" renming " this Chinese phonetic alphabet identical input text with " appointment ", then can
To say that this user has spelling custom；User want input " appointment " this word when,
If user habit input in the input frame that input method is applied " rm " this with " appointment "
The input text that the initial of the Chinese phonetic alphabet is identical, then it may be said that this user has simplicity custom.
It is understood that full simplicity custom is a general name, specific to some user, this user
It is probably and there is spelling custom, it is also possible to there is simplicity custom.
In some optional implementations of the present embodiment, dialect custom can be user habit
Use the custom of the dialect in which kind of area.As example, if the user while input method application is defeated
Entering to input in frame " renmin " this input text, the candidate word that input method is presented may have
" people " and " appointment ", user have selected " appointment " as upper screen result, then this user
It is likely to cannot distinguish between before and after's rhinophonia, it is impossible to before and after differentiation, rhinophonia is the spy of typical northwest dialect
Point, it is possible to say that this user has northwest dialect custom.It is understood that dialect custom
Being a general name, specific to some user, this user is probably has Hubei dialect custom,
It is also likely to be and there is Shanghai dialect custom, it is also possible to there is northwest dialect custom.
In some optional implementations of the present embodiment, clicking on mistake custom can be user
Habitually obscure the custom of some character position on keyboard.As example, if the user while think
The when of this input text of input " wo ", first have input " wp ", then user deletes
Have input " o " after " p ", and repeatedly occur that " p " that delete input have input " o " afterwards,
So it may be said that this user has " p " and " o " clicks on mistake custom.It is understood that
Clicking on mistake one general name of custom, specific to some user, this user is probably has " p "
" o " clicks on mistake custom, it is also possible to has " a " and " s " and clicks on mistake custom.
In some optional implementations of the present embodiment, input length custom can be user
Practising traditional long is that how many input texts is to match the custom of upper screen result.As example,
If the user while want to draw that screen result is four word Chinese idioms when " have no way out ", input
Input text is " wkn ", and that user is likely to be of and uses the input text of a length of three to draw four
The input habit of word Chinese idiom.It is understood that input length custom is a general name, have
Being probably to this user of some user to have uses the input text of a length of three to draw four words one-tenth
The input habit of language, it is also possible to have and use the input text of a length of two to draw four word Chinese idioms
Input habit.
In some optional implementations of the present embodiment, can to the input text of user and
The upper screen result corresponding with input text is analyzed, and extracts the full simplicity for characterizing user and practises
Used input feature vector, as example, can be the head of each word in upper screen result by input text
Letter is as the input feature vector of simplicity custom, and extracts.
In some optional implementations of the present embodiment, can to the input text of user and
The upper screen result corresponding with input text is analyzed, and extracts the dialect custom for characterizing user
Input feature vector, as example, can by user input text without " g " upper screen result
The Chinese phonetic alphabet has " g ", as the custom feature corresponding with northwest method custom, and carries
Take.
In some optional implementations of the present embodiment, can to the input text of user and
The upper screen result corresponding with input text is analyzed, and extracts the click mistake for characterizing user
The input feature vector of custom.As example, user first can be have input " wp ", then user
Have input " o " after deleting " p ", and repeatedly occur that " p " that delete input is the most defeated
Enter " o ", clicked on the input feature vector of mistake custom as " p " and " o ", and extract.
In some optional implementations of the present embodiment, can to the input text of user and
The upper screen result corresponding with input text is analyzed, and extracts user and characterizes the input length of user
Input feature vector.As example, user can input a length of three, upper screen result is four words
As with the input text using a length of three, Chinese idiom, show that the input habit of four word Chinese idioms is corresponding
Input feature vector, and extract.
Step 203, according at least one input feature vector, to the input text in response to user
Treat that the candidate word presented by input method application is determined.
In the present embodiment, data inputting method first run on can be on electronic equipment thereon
Receiving the input text of user, here, input text is the user needing to present candidate word
The text of input in real time；Then in response to the input text of user, according at least one input spy
Levy, it may be determined that predetermined number is treated to be applied, by input method, the candidate word presented.
It should be noted that how the input text in response to user primarily determines that out the first number
Treat that by the input method candidate word that presents of application be known in those skilled in the art, at this
Repeat no more.The application can also determine the input method to be had of the second number according to input feature vector
The candidate word that application presents, as example, primarily determines that out ten candidate word, wherein has three
Individual is Hubei vocabulary, further according to Hubei provincialism, determines and selects these three Hubei originally
Ground vocabulary is as candidate word.
Step 204, according at least one input feature vector, determines the order of candidate word.
In the present embodiment, run on electronic equipment thereon can be based on for data inputting method
The candidate word that step 203 obtains, according to the one or more input feature vectors as step 203,
Determine the order of candidate word.
As example, user inputs " renmin " in the input frame that input method is applied, in response to
Input text determines treats that the candidate word presented by input method may have " people " and " appointment ", enters
One step ground, can come " appointment " according to the input feature vector corresponding with northwest dialect custom
Before " people ".
As example, user inputs " wkn " in the input frame that input method is applied, in response to defeated
Enter text to determine and treat that the candidate word presented by input method may have " having no way out " and " without may ",
It is possible to further according to the input drawing four word Chinese idioms with the input text using a length of three
The input feature vector that custom is corresponding, will " have no way out " before coming " without possible ".
It is understood that a user is likely to be of the multiple input habit involved by the application,
Determine that the order of candidate word is similar with the situation of an input feature vector according to multiple input feature vectors,
This repeats no more.
Step 205, according to determined by order, present candidate word.
In the present embodiment, the candidate word that above-mentioned electronic equipment can determine according to step 203 and
The order of the candidate word that step 204 determines, utilizes its terminal carrying out information input to set user
Candidate word is presented on Bei.
Refer to Fig. 3 a, it illustrates the candidate word that the data inputting method according to the application presents
One effect schematic diagram of set.
In fig. 3 a, it illustrates user and input " renmin " in the input frame that input method is applied,
Determine in response to input text and treat that the candidate word presented by input method may have " people " and " appoint
Life ", it is possible to further according to the input habit corresponding with northwest dialect custom, by " appointment "
The candidate word presented before coming " people ".
Refer to Fig. 3 b, it illustrates the candidate word that the data inputting method according to the application presents
One effect schematic diagram of set.
In fig 3b, it illustrates user and input " wkn " in the input frame that input method is applied,
In response to input text determine treat the candidate word presented by input method may have " having no way out " and
" without possible ", it is possible to further draw four words according to the input text using a length of three
The input feature vector that the input habit of Chinese idiom is corresponding, " will have no way out " and come " without may " it
Before and the candidate word that presents.
Defeated by the predetermined amount of time to user of the method that above-described embodiment of the application provides
Enter information to be analyzed, and extract the input feature vector being used for characterizing the input habit of user, and root
According at least one input feature vector, determine candidate word and determine the order of candidate word so that candidate word
Coverage rate and head-word language hit rate improve, and then improve information input efficiency.
With further reference to Fig. 4, it illustrates the flow process of another embodiment of data inputting method
400.The flow process 400 of this data inputting method, comprises the following steps:
Step 401, obtains input method and applies the user's input information recorded within a predetermined period of time.
In the present embodiment, in the present embodiment, data inputting method runs on electronics thereon
Equipment (the such as server shown in Fig. 1) can be by wired connection mode or wireless connections
Mode utilizes it to carry out the terminal of information input acquisition input method from user and applies at predetermined amount of time
The user's input information of interior record.
Step 402, is analyzed user's input information, extracts the input for characterizing user
The input feature vector of custom.
In the present embodiment, based on the user's input information obtained in step 401, above-mentioned electronics
First user's input information can be analyzed by equipment (the such as server shown in Fig. 1),
Then extracting input feature vector, here, above-mentioned input feature vector is the spy for characterizing user habit
Levying, input feature vector and input habit are one to one.
In the present embodiment, can extract at least according to above-mentioned input text and above-mentioned upper screen result
A kind of input feature vector.
Step 403, for the single target input feature vector at least one input feature vector, statistics
Go out the number of times that this target input feature vector is hit in user's input information.
In the present embodiment, the input feature vector extracted based on step 402, above-mentioned electronic equipment
Can be for the single target input feature vector at least one input feature vector, within a predetermined period of time
User's input information in search the situation that this target input feature vector is consistent, add up this target input
The number of times that feature is hit.
In the present embodiment, situation about being consistent with target input feature vector occurs being properly termed as this target
Input feature vector is hit.As example, user's input information records user and deletes input
Have input " o " situation, the appearance of the most this situation after " p ", just can be regarded as hit at first time
" p " and " o " clicks on mistake input feature vector.
In some optional implementations of the present embodiment, it is also possible to whether monitor above-mentioned number of times
More than predetermined threshold value；If it is, adjust the number of times after above-mentioned number of times draws adjustment, wherein,
Number of times after adjustment is less than the number of times before adjusting.After the threshold value that above-mentioned number of times reaches predetermined, right
Number of times carries out decay and arranges, and can discover the change of the input habit of user more delicately.
Step 404, adjusts, according to number of times, the probability values pre-set and draws for characterizing use
Family has the probit of the input habit corresponding with target input feature vector.
In the present embodiment, the number of times that can obtain based on step 403, above-mentioned electronic equipment root
Adjust probability values according to above-mentioned number of times and show that user characterizes user and has and target input feature vector pair
The probit of the input habit answered.Here, above-mentioned probability values is to pre-set, and
There is the probability of the input habit corresponding with above-mentioned target characteristic for characterizing random user.
As example, above-mentioned number of times can be designated as R, above-mentioned probability values is designated as F,
Above-mentioned probit is designated as W, above-mentioned probit can be obtained by below equation:
X=a* (R-b)；
W=[1/ (1+e-x)]*F；
Here, 1 represents numeral 1 ,/representing the division sign, * represents multiplication sign ,+represent plus sige, e
Representing the nature truth of a matter, a is the zoom factor pre-set, and b is the translation coefficient pre-set,
X in second formula is calculated by first formula, and-x represents the value taken by x after bearing,
e-xRepresent-x the power of e.A, b are all the empirical values pre-set.
In some optional implementations of the present embodiment, can be obtained by following steps
State probability values: obtain the total of the some users in the predetermined amount of time of several users and input
Information；Count the total degree that a certain target input feature vector is hit in above-mentioned total input information,
Using the ratio of above-mentioned total degree and total upper screen number of times as probability values.Here, user is defeated
Enter one input text, draw and shield result on one, be an input cycle, complete one defeated
Entering periodic recording to shield for once upper, total upper screen number of times is equal with the number in input cycle.
Generally, the use interior for the previous period of user can when user inputs, be obtained
Family input information, carries out adding up for the number of times of a certain target input feature vector, passes through real-time statistics
Mode, can be along with user increasing, in adjustment the number of times that this target input feature vector hits
State probit, and then data inputting method is changed according to the custom of user, it is achieved that information
Input adaptive mates the input habit of this user.
Step 405, according to probit to treating in response to user input text to be applied by input method
The candidate word presented is determined and determines the order of candidate word.
In the present embodiment, the input text of user, here, input literary composition can first be received
Originally it is the text needing the user presenting candidate word to input in real time of single；Then in response to
The input text at family, it may be determined that predetermined number is treated to be applied, by input method, the candidate word presented,
The probit obtained according to step 404 after again, determines the order of candidate word.
As example, user inputs " wkn " in the input frame that input method is applied, in response to defeated
Enter text to determine and treat that the candidate word presented by input method may have " having no way out " and " without may ",
It will be understood by those skilled in the art that the candidate word that input method is applied all correspond to a sign and is somebody's turn to do
Candidate word is the candidate word probit that user wants the probability of the word of input；It is assumed herein that " nothing
Can be how " candidate word probit be 50%, the candidate word probit of " without may " is 70%.
Further, if this user uses the input text of a length of three to draw the input of four word Chinese idioms
The probit of custom is 60%, and random user uses the input text of a length of three to draw four words one-tenth
The probability values of the input habit of language is 10%, then because " having no way out " this candidate
Word has hit and has shown that the input habit of four word Chinese idioms is corresponding with the input text using a length of three
Input feature vector, so the candidate word probit 50% that will " have no way out " and user and this use
The input text of family use a length of three draws the probit 60% of the input habit of four word Chinese idioms
Product 30% as the probit of " having no way out " this candidate word because " without may " this
One candidate word is not hit and uses the input text of a length of three to show that the input of four word Chinese idioms is practised
Used corresponding input feature vector, thus will the candidate word probit 70% of " without may " with random
User uses the input text of a length of three to draw the probability values of input habit of four word Chinese idioms
The product 7% of 10%, as the probit of " without possible " this candidate word, compares above-mentioned two and waits
Select the size of the probit of word, determine above-mentioned two candidate according to the order that probit is descending
The order of word is: " having no way out ", front, " without possible " is rear.
Step 406, according to determined by order, present candidate word.
In the present embodiment, the candidate word that above-mentioned electronic equipment can obtain according to step 405 and
The order of candidate word, utilizes it to carry out on the terminal unit of information input user and presents candidate word.
Figure 4, it is seen that the letter compared with the embodiment that Fig. 2 is corresponding, in the present embodiment
The flow process 400 of breath input method highlights determining that user has and above-mentioned target input feature vector pair
The step of the probit of the input habit answered.Thus, the scheme that the present embodiment describes can be with user
Custom change adjust input method and apply the order of candidate word to be presented, thus realize higher efficiency
Information input.
With further reference to Fig. 5, as to the realization of method shown in above-mentioned each figure, the application provides
One embodiment of a kind of message input device, this device embodiment and the method shown in Fig. 2
Embodiment is corresponding, and this device specifically can apply in various electronic equipment.
As it is shown in figure 5, the above-mentioned message input device 500 of the present embodiment includes: acquisition module
501, extraction module 502, candidate word determine that module 503, order determine module 504 and present
Module 505.Wherein, acquisition module 501 be configured to obtain input method apply in the scheduled time
The user's input information of record in section；Extraction module 502 is configured to above-mentioned user is inputted letter
Breath is analyzed, and extracts the input feature vector being used for characterizing the input habit of user；Candidate word determines
Module 503, is configured to according at least one input feature vector, defeated in response to above-mentioned user
Enter text and treat that the candidate word presented by the application of above-mentioned input method is determined；Order determines mould
Block 504, is configured to, according at least one input feature vector above-mentioned, determine the order of candidate word；
And present module 505 be configured to according to determined by order, present candidate word.
In the present embodiment, the reception unit 501 of message input device 500 can be by wired
It is defeated that connected mode or radio connection utilize it to carry out the acquisition of the terminal of information input from user
Enter method and apply the user's input information recorded within a predetermined period of time.
In the present embodiment, based on the user's input information obtained in acquisition module 501, extract
First user's input information can be analyzed by module 502, then extracts input feature vector,
Here, above-mentioned input feature vector is the feature for characterizing user habit, and input feature vector and input are practised
Used is one to one.
In the present embodiment, candidate word determines that first module 503 can receive the input literary composition of user
This, here, input text is the text needing the user presenting candidate word to input in real time；
Then in response to the input text of user, according at least one input feature vector, it may be determined that predetermined
Number is treated to be applied, by input method, the candidate word presented.
In the present embodiment, order determines that module 504 may determine that the candidate that module 503 obtains
Word, according to the one or more input feature vectors as determining in module 503 with candidate word, determines
The order of candidate word.
In the present embodiment, present module 505 and can determine that module 503 determines according to candidate word
Candidate word and order determine the order of candidate word that module 504 determines, utilize it to enter user
Candidate word is presented on the terminal unit of row information input.
In some optional implementations of the present embodiment, above-mentioned user's input information includes defeated
Enter text and the upper screen result corresponding with above-mentioned input text, wherein, on above-mentioned upper screen result is
State the candidate word that user selects from the candidate word presented；And, said extracted module,
It is configured to further: extract at least one according to above-mentioned input text and above-mentioned upper screen result defeated
Enter feature.
In some optional implementations of the present embodiment, said apparatus also includes statistical module
(not shown), is configured to: for the single target input feature vector at least one input feature vector,
Count the number of times that this target input feature vector is hit in above-mentioned user's input information；According to upper
State number of times to adjust the probability values that pre-sets and draw have with above-mentioned for characterizing above-mentioned user
The probit of the input habit that target input feature vector is corresponding, wherein, above-mentioned probability values is used for
Characterize random user and there is the probability of the input habit corresponding with above-mentioned target input feature vector.
In some optional implementations of the present embodiment, above-mentioned determine module, join further
Put for: according to above-mentioned probit, the input text in response to above-mentioned user is treated by above-mentioned defeated
Entering method applies the candidate word presented be determined and determine the order of candidate word.
In some optional implementations of the present embodiment, above-mentioned statistical module, join further
Put for: monitor above-mentioned number of times whether more than predetermined threshold value；If it is, adjust above-mentioned number of times
Drawing the number of times after adjustment, wherein, the number of times after adjustment is less than the number of times before adjusting.
It will be understood by those skilled in the art that above-mentioned message input device 500 also includes some its
His known features, such as processor, memorizer etc., in order to unnecessarily obscure the reality of the disclosure
Executing example, structure known to these is the most not shown.
Below with reference to Fig. 6, it illustrates the server that is suitable to for realizing the embodiment of the present application
The structural representation of computer system 600.
As shown in Figure 6, computer system 600 includes CPU (CPU) 601, its
Can be according to the program being stored in read only memory (ROM) 602 or from storage part 608
It is loaded into the program in random access storage device (RAM) 603 and performs various suitable action
And process.In RAM 603, also storage has system 600 to operate required various program sums
According to.CPU 601, ROM 602 and RAM 603 are connected with each other by bus 604.Input
/ output (I/O) interface 605 is also connected to bus 604.
It is connected to I/O interface 605: include the importation 606 of keyboard, mouse etc. with lower component；
Including such as cathode ray tube (CRT), liquid crystal display (LCD) etc. and speaker etc.
Output part 607；Storage part 608 including hard disk etc.；And include such as LAN card,
The communications portion 609 of the NIC of modem etc..Communications portion 609 is via such as
The network of the Internet performs communication process.Driver 610 is connected to I/O interface also according to needs
605.Detachable media 611, such as disk, CD, magneto-optic disk, semiconductor memory etc.,
Be arranged on as required in driver 610, in order to the computer program read from it according to
Needs are mounted into storage part 608.
Especially, according to embodiment of the disclosure, the process described above with reference to flow chart is permissible
It is implemented as computer software programs.Such as, embodiment of the disclosure and include a kind of computer journey
Sequence product, it includes the computer program being tangibly embodied on machine readable media, above-mentioned meter
Calculation machine program comprises the program code for performing the method shown in flow chart.In such enforcement
In example, this computer program can be downloaded and installed from network by communications portion 609,
And/or be mounted from detachable media 611.
Flow chart in accompanying drawing and block diagram, it is illustrated that according to the various embodiment of the application system,
Architectural framework in the cards, function and the operation of method and computer program product.This point
On, each square frame in flow chart or block diagram can represent a module, program segment or code
A part, a part for above-mentioned module, program segment or code comprise one or more for
Realize the executable instruction of the logic function of regulation.It should also be noted that at some as replacement
In realization, the function marked in square frame can also be sent out to be different from the order marked in accompanying drawing
Raw.Such as, two square frames succeedingly represented can essentially perform substantially in parallel, they
Sometimes can also perform in the opposite order, this is depending on involved function.It is also noted that
It is, the square frame in each square frame in block diagram and/or flow chart and block diagram and/or flow chart
Combination, can realize by the special hardware based system of the function or operation that perform regulation,
Or can realize with the combination of specialized hardware with computer instruction.
Being described in the embodiment of the present application involved module can be real by the way of software
Existing, it is also possible to realize by the way of hardware.Described module can also be arranged on process
In device, for example, it is possible to be described as: a kind of processor includes acquisition module, extraction module, really
Cover half block and present module.Wherein, the title of these modules be not intended that under certain conditions right
The restriction of this module itself, such as, acquisition module is also described as " being used for obtaining input
The module of the user's input information that method application records within a predetermined period of time ".
As on the other hand, present invention also provides a kind of nonvolatile computer storage media,
This nonvolatile computer storage media can be in above-described embodiment included in said apparatus
Nonvolatile computer storage media；Can also be individualism, be unkitted allocate in terminal non-
Volatile computer storage medium.Above-mentioned nonvolatile computer storage media storage have one or
The multiple program of person, when said one or multiple program are performed by an equipment so that above-mentioned
Equipment: obtain input method and apply the user's input information recorded within a predetermined period of time；To above-mentioned
User's input information is analyzed, and extracts the input feature vector being used for characterizing the input habit of user；
According at least one input feature vector, the input text in response to above-mentioned user is treated by above-mentioned defeated
Entering method applies the candidate word presented to be determined；According at least one input feature vector, determine time
Select the order of word；Determined by according to, order, presents candidate word.
Above description is only the preferred embodiment of the application and saying institute's application technology principle
Bright.It will be appreciated by those skilled in the art that invention scope involved in the application, do not limit
In the technical scheme of the particular combination of above-mentioned technical characteristic, also should contain simultaneously without departing from
In the case of foregoing invention design, above-mentioned technical characteristic or its equivalent feature carry out combination in any
And other technical scheme formed.Such as features described above and (but not limited to) disclosed herein
The technical characteristic with similar functions is replaced mutually and the technical scheme that formed.
Claims (10)
1. a data inputting method, it is characterised in that described method includes:
Obtain input method and apply the user's input information recorded within a predetermined period of time；
Being analyzed described user's input information, extraction is for characterizing the input habit of user
Input feature vector；
According at least one input feature vector, the input text in response to described user is treated by institute
Stating input method applies the candidate word presented to be determined；
According at least one input feature vector described, determine the order of candidate word；
Determined by according to, order, presents candidate word.
Method the most according to claim 1, it is characterised in that described user's input information
Including input text and the upper screen result corresponding with described input text, wherein, described upper screen is tied
Fruit is the candidate word that described user selects from the candidate word presented；And,
Described described user's input information is analyzed, extracts the input for characterizing user and practise
Used input feature vector, including:
At least one input feature vector is extracted according to described input text and described upper screen result.
Method the most according to claim 1 and 2, it is characterised in that described in described method
Described user's input information is analyzed, extracts the input being used for characterizing the input habit of user
After feature, also include:
For the single target input feature vector at least one input feature vector, count in described use
The number of times that in family input information, this target input feature vector is hit；
Adjust, according to described number of times, the probability values pre-set to draw for characterizing described user
There is the probit of the input habit corresponding with described target input feature vector, wherein, described initially
Probit has the input habit corresponding with described target input feature vector for characterizing random user
Probability.
Method the most according to claim 3, it is characterised in that described in response to described
The input of user and treat that the candidate word presented by the application of described input method is determined and determines
The order of candidate word, including:
According to described probit, the input text in response to described user is treated by described input method
The candidate word that application presents is determined and determines the order of candidate word.
Method the most according to claim 4, it is characterised in that the described input of described statistics
The number of times that feature occurs in described user's input information, also includes:
Whether monitor described number of times more than predetermined threshold value；
If it is, adjust the number of times after described number of times draws adjustment, wherein, after adjustment time
Number is less than the number of times before adjusting.
6. a message input device, it is characterised in that described device includes:
Acquisition module, is configured to obtain input method and applies the user recorded within a predetermined period of time
Input information；
Extraction module, is configured to be analyzed described user's input information, extracts for table
The input feature vector of the input habit at requisition family；
Candidate word determines module, is configured to according at least one input feature vector, in response to institute
State the input text of user and treat that the candidate word presented by the application of described input method is determined；
Order determines module, is configured to, according at least one input feature vector described, determine candidate
The order of word；
Present module, be configured to according to determined by order, present candidate word.
Device the most according to claim 6, it is characterised in that described user's input information
Including input text and the upper screen result corresponding with described input text, wherein, described upper screen is tied
Fruit is the candidate word that described user selects from the candidate word presented；And,
Described extraction module, is configured to further:
At least one input feature vector is extracted according to described input text and described upper screen result.
8. according to the device described in claim 6 or 7, it is characterised in that described device also wraps
Include statistical module, be configured to:
For the single target input feature vector at least one input feature vector, count in described use
The number of times that in family input information, this target input feature vector is hit；
Adjust, according to described number of times, the probability values pre-set to draw for characterizing described user
There is the probit of the input habit corresponding with described target input feature vector, wherein, described initially
Probit has the input habit corresponding with described target input feature vector for characterizing random user
Probability.
Device the most according to claim 8, it is characterised in that described determine module, enters
One step is configured to:
According to described probit, the input text in response to described user is treated by described input method
The candidate word that application presents is determined and determines the order of candidate word.
Device the most according to claim 9, it is characterised in that described statistical module,
It is configured to further:
Whether monitor described number of times more than predetermined threshold value；
If it is, adjust the number of times after described number of times draws adjustment, wherein, after adjustment time
Number is less than the number of times before adjusting.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610282718.3A CN105955495A (en) | 2016-04-29 | 2016-04-29 | Information input method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610282718.3A CN105955495A (en) | 2016-04-29 | 2016-04-29 | Information input method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105955495A true CN105955495A (en) | 2016-09-21 |
Family
ID=56914433
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610282718.3A Pending CN105955495A (en) | 2016-04-29 | 2016-04-29 | Information input method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105955495A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106873799A (en) * | 2017-02-16 | 2017-06-20 | 北京百度网讯科技有限公司 | Input method and device |
| CN108932069A (en) * | 2018-07-11 | 2018-12-04 | 科大讯飞股份有限公司 | Input method candidate entry determines method, apparatus, equipment and readable storage medium storing program for executing |
| CN112987940A (en) * | 2021-04-27 | 2021-06-18 | 广州智品网络科技有限公司 | Input method and device based on sample probability quantization and electronic equipment |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101030157A (en) * | 2007-04-20 | 2007-09-05 | 北京搜狗科技发展有限公司 | Method and system for updating user vocabulary synchronouslly |
| CN101051323A (en) * | 2007-05-22 | 2007-10-10 | 北京搜狗科技发展有限公司 | Character input method, input method system and method for updating word stock |
| CN101055588A (en) * | 2007-05-25 | 2007-10-17 | 北京搜狗科技发展有限公司 | Method for catching limit word information, optimizing output and input method system |
| CN101256448A (en) * | 2008-03-24 | 2008-09-03 | 腾讯科技（深圳）有限公司 | Method, apparatus and client terminal for implementing input method |
| CN101388011A (en) * | 2007-09-13 | 2009-03-18 | 北京搜狗科技发展有限公司 | Method and apparatus for recording information into user thesaurus |
| 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 |
| CN102902362A (en) * | 2011-07-25 | 2013-01-30 | 腾讯科技（深圳）有限公司 | Text input method and system |
| CN102937976A (en) * | 2012-10-17 | 2013-02-20 | 北京奇虎科技有限公司 | Drop-down prompting method and apparatus based on input prefix |
-
2016
- 2016-04-29 CN CN201610282718.3A patent/CN105955495A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101030157A (en) * | 2007-04-20 | 2007-09-05 | 北京搜狗科技发展有限公司 | Method and system for updating user vocabulary synchronouslly |
| CN101051323A (en) * | 2007-05-22 | 2007-10-10 | 北京搜狗科技发展有限公司 | Character input method, input method system and method for updating word stock |
| CN101055588A (en) * | 2007-05-25 | 2007-10-17 | 北京搜狗科技发展有限公司 | Method for catching limit word information, optimizing output and input method system |
| CN101388011A (en) * | 2007-09-13 | 2009-03-18 | 北京搜狗科技发展有限公司 | Method and apparatus for recording information into user thesaurus |
| CN101256448A (en) * | 2008-03-24 | 2008-09-03 | 腾讯科技（深圳）有限公司 | Method, apparatus and client terminal for implementing input method |
| 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 |
| CN102902362A (en) * | 2011-07-25 | 2013-01-30 | 腾讯科技（深圳）有限公司 | Text input method and system |
| CN102937976A (en) * | 2012-10-17 | 2013-02-20 | 北京奇虎科技有限公司 | Drop-down prompting method and apparatus based on input prefix |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106873799A (en) * | 2017-02-16 | 2017-06-20 | 北京百度网讯科技有限公司 | Input method and device |
| CN106873799B (en) * | 2017-02-16 | 2020-10-09 | 北京百度网讯科技有限公司 | Input method and device |
| CN108932069A (en) * | 2018-07-11 | 2018-12-04 | 科大讯飞股份有限公司 | Input method candidate entry determines method, apparatus, equipment and readable storage medium storing program for executing |
| CN112987940A (en) * | 2021-04-27 | 2021-06-18 | 广州智品网络科技有限公司 | Input method and device based on sample probability quantization and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108804450B (en) | Information pushing method and device | |
| CN105893465A (en) | Automatic question answering method and device | |
| CN109460514A (en) | Method and apparatus for pushed information | |
| US10402479B2 (en) | Method, server, browser, and system for recommending text information | |
| CN107105031A (en) | Information-pushing method and device | |
| CN107832305A (en) | Method and apparatus for generating information | |
| CN109919641B (en) | Advertisement putting method and platform | |
| CN107193792A (en) | The method and apparatus of generation article based on artificial intelligence | |
| CN106874467A (en) | Method and apparatus for providing Search Results | |
| CN105117491B (en) | Page push method and apparatus | |
| CN108228906B (en) | Method and apparatus for generating information | |
| CN107305578A (en) | Human-machine intelligence's answering method and device | |
| CN109857908A (en) | Method and apparatus for matching video | |
| CN107295095A (en) | The method and apparatus for pushing and showing advertisement | |
| CN105786793A (en) | Method and device for analyzing semanteme of spoken language text information | |
| CN106708940A (en) | Method and device used for processing pictures | |
| CN107679217A (en) | Association method for extracting content and device based on data mining | |
| CN108230346A (en) | For dividing the method and apparatus of image semantic feature, electronic equipment | |
| CN107305575A (en) | The punctuate recognition methods of human-machine intelligence's question answering system and device | |
| CN114065750A (en) | Commodity information matching and publishing method and device, equipment, medium and product thereof | |
| US20180357318A1 (en) | System and method for user-oriented topic selection and browsing | |
| CN105955495A (en) | Information input method and device | |
| CN107729573A (en) | Information-pushing method and device | |
| CN107291774A (en) | Error sample recognition methods and device | |
| CN107168635A (en) | Information demonstrating method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160921 |
|
| RJ01 | Rejection of invention patent application after publication |