CN107918496B

CN107918496B - Input error correction method and device for input error correction

Info

Publication number: CN107918496B
Application number: CN201610884238.4A
Authority: CN
Inventors: 费腾
Original assignee: Beijing Sogou Technology Development Co Ltd
Current assignee: Beijing Sogou Technology Development Co Ltd
Priority date: 2016-10-10
Filing date: 2016-10-10
Publication date: 2021-10-22
Anticipated expiration: 2036-10-10
Also published as: CN107918496A

Abstract

The embodiment of the invention provides an input error correction method and device and a device for input error correction, wherein the method specifically comprises the following steps: acquiring an input string in an input process; carrying out error correction processing on the input string to obtain an error correction candidate corresponding to the input string; searching in a user multivariate lexicon according to the error correction candidates and the context corresponding to the input string to obtain corresponding search results; the user multivariate word bank is used for recording multivariate word groups input by a user; sorting the error correction candidates corresponding to the input string according to the search result; and displaying the sorted error correction candidates to a user. The embodiment of the invention can provide error correction candidates which accord with the personalized input habit, thereby improving the quality of the error correction candidates and improving the accuracy of error correction.

Description

Input error correction method and device for input error correction

Technical Field

The invention relates to the technical field of computer information input, in particular to an input error correction method and device and a device for input error correction.

Background

At present, devices involved in interaction generally require a user to recognize their own operation intention in interaction with the devices through an input method system. For example, a user can type an input string through a keyboard, and then the input string is converted into a candidate item of a corresponding language and displayed by the input method system according to a preset standard mapping rule, so that the candidate item selected by the user is displayed on a screen.

In practical applications, the user may press a wrong key (on the PC) or click a wrong screen position (on the smart terminal), which may cause a wrong input string to be typed. The input error correction is an input method system solution aiming at the errors, and can actively identify the input errors of the user and correct the input strings with the errors into correct input strings, so that the user can input correct characters on the premise of not modifying the input strings.

The existing input error correction scheme may specifically include: an edit distance based error correction scheme and a statistical based error correction scheme; wherein the edit distance based error correction scheme may perform the following error correction attempts for each position of the input string: inserting a character, deleting a character, replacing a character, etc., to generate an error correction candidate corresponding to the input string; a statistical-based error correction scheme may generate an error correction model through big data mining that may be used to learn the probability of error correction candidates being mistaken for an input string.

The inventor finds that the error correction scheme based on the edit distance and the error correction scheme based on statistics provide the same error correction candidates for different users, and the error correction scheme has no capability of realizing personalized error correction, so that the accuracy of error correction is easily influenced.

Disclosure of Invention

In view of the above problems, embodiments of the present invention provide an input error correction method, an input error correction apparatus, and an apparatus for input error correction that overcome or at least partially solve the above problems, and may provide error correction candidates that conform to personalized input habits, thereby improving the quality of the error correction candidates and improving the accuracy of error correction.

In order to solve the above problems, the present invention discloses an input error correction method, comprising:

acquiring an input string in an input process;

carrying out error correction processing on the input string to obtain an error correction candidate corresponding to the input string;

searching in a user multivariate lexicon according to the error correction candidates and the context corresponding to the input string to obtain corresponding search results; the user multivariate word bank is used for recording multivariate word groups input by a user;

sorting the error correction candidates corresponding to the input string according to the search result;

and displaying the sorted error correction candidates to a user.

Optionally, the search result searched in the user multivariate thesaurus includes: the step of sorting the error correction candidates corresponding to the input string according to the search result if the error correction candidate is hit or not hit includes:

determining a second score of the error correction candidate according to the search result; wherein the second score of the hit error correction candidate is greater than zero and the second score of the miss error correction candidate is zero;

adding the second score of the error correction candidate and the first score of the error correction candidate to obtain a third score; wherein the first score is obtained according to the attribute characteristics of the error correction candidate;

and sorting the error correction candidates corresponding to the input string according to the third score.

determining a fourth score of the error correction candidate according to the search result; wherein the fourth score of the hit error correction candidate is greater than 1 and the fourth score of the missed error correction candidate is less than 1;

multiplying the fourth score of the error correction candidate with the first score of the error correction candidate to obtain a fifth score; wherein the first score is obtained according to the attribute characteristics of the error correction candidate;

and sorting the error correction candidates corresponding to the input string according to the fifth score.

Optionally, the method further comprises:

respectively taking preset values as second scores and/or fourth scores corresponding to the error correction candidates; or

And determining a second score and/or a fourth score corresponding to the error correction candidate according to the attribute characteristics of the multi-element word groups recorded in the user multi-element word stock.

Optionally, the attribute feature of the user multinary phrase includes at least one of the following features: and determining a second score and/or a fourth score corresponding to the error correction candidate according to the attribute characteristics of the multi-element phrases recorded in the user multi-element word stock by using the input times, the historical input time and the historical input environment information, wherein the step comprises the following steps of:

and determining a second score and/or a fourth score corresponding to the error correction candidate according to at least one of the input times, the difference between the historical input time and the current time, and the matching degree between the historical input environment information and the current input environment information.

Optionally, the attribute feature of the error correction candidate includes at least one of the following features: editing distance between the error correction string corresponding to the error correction candidate and the input string, type of the word bank corresponding to the error correction candidate, and word frequency of the error correction candidate.

Optionally, when the search result searched in the user multivariate thesaurus includes: the method further comprises, for a plurality of hit error correction candidates:

according to the attribute characteristics of the multi-element word groups recorded in the user multi-element word stock, sequencing a plurality of hit error correction candidates;

and displaying the corresponding error correction candidates according to the sorting results of the plurality of hit error correction candidates.

Optionally, before the step of performing error correction processing on the input string, the method further includes:

searching in a user multivariate word library according to the common candidate and the context corresponding to the input string;

and when the common candidate and the context corresponding to the input string hit the user multivariate lexicon, not executing the step of carrying out error correction processing on the input string.

Optionally, the user multivariate thesaurus is established by the following steps:

recording the on-screen content of the user;

selecting a user multi-element phrase from one-time screen-on content or continuous screen-on contents for multiple times;

and storing the user multi-element word group and the corresponding attribute characteristics thereof into a user multi-element word library.

Optionally, the step of selecting the user-related phrase from the one-time on-screen content or the continuous multiple-time on-screen content includes:

selecting adjacent phrases from the one-time screen-on content or the continuous multi-time screen-on content as user multi-element phrases; or

Selecting phrases meeting preset collocation conditions from the content on one screen or the content on multiple screens continuously as user multi-phrase.

In another aspect, the present invention discloses an input error correction apparatus, comprising:

the input string acquisition module is used for acquiring an input string in an input process;

the input string error correction module is used for carrying out error correction processing on the input string to obtain an error correction candidate corresponding to the input string;

the multivariate lexicon searching module is used for searching in the multivariate lexicon of the user according to the error correction candidates and the context corresponding to the input string to obtain a corresponding searching result; the user multivariate word stock records multivariate word groups input by a user;

the error correction candidate sorting module is used for sorting the error correction candidates corresponding to the input string according to the search result; and

and the error correction candidate display module is used for displaying the sorted error correction candidates to a user.

Optionally, the search result searched in the user multivariate thesaurus includes: a hit error correction candidate or a miss error correction candidate, the error correction candidate sorting module comprising:

a second score determining sub-module, configured to determine a second score of the error correction candidate according to the search result; wherein the second score of the hit error correction candidate is greater than zero and the second score of the miss error correction candidate is zero;

the addition processing sub-module is used for adding the second score of the error correction candidate and the first score of the error correction candidate to obtain a third score; wherein the first score is obtained according to the attribute characteristics of the error correction candidate;

and the first sequencing submodule is used for sequencing the error correction candidates corresponding to the input string according to the third score.

a fourth score determining sub-module, configured to determine a fourth score of the error correction candidate according to the search result; wherein the fourth score of the hit error correction candidate is greater than 1 and the fourth score of the missed error correction candidate is less than 1;

the multiplication processing submodule is used for multiplying the fourth score of the error correction candidate with the first score of the error correction candidate to obtain a fifth score; wherein the first score is obtained according to the attribute characteristics of the error correction candidate;

and the first sequencing submodule is used for sequencing the error correction candidates corresponding to the input string according to the fifth score.

Optionally, the apparatus further comprises:

a score presetting module, configured to use preset values as second scores and/or fourth scores corresponding to the error correction candidates respectively; or

And the score determining module is used for determining a second score and/or a fourth score corresponding to the error correction candidate according to the attribute characteristics of the multi-element word groups recorded in the user multi-element word stock.

Optionally, the attribute feature of the multi-element phrase includes at least one of the following features: the score determining module includes:

and the matching calculation sub-module is used for determining a second score and/or a fourth score corresponding to the error correction candidate according to at least one of the input times, the difference value between the historical input time and the current time and the matching degree between the historical input environment information and the current input environment information.

Optionally, when the search result searched in the user multivariate thesaurus includes: in the case of multiple hit error correction candidates, the apparatus further comprises:

the hit candidate sorting module is used for sorting a plurality of hit error correction candidates according to the attribute characteristics of the multi-element word groups recorded in the user multi-element word stock;

and the display module is used for displaying the corresponding error correction candidates according to the sorting results of the plurality of hit error correction candidates.

Optionally, the apparatus further comprises:

the searching module is used for searching in the user multivariate lexicon according to the common candidate and the context corresponding to the input string;

and the execution processing module is used for not executing the operation of carrying out error correction processing on the input string when the common candidate and the context corresponding to the input string hit the user multivariate thesaurus. Optionally, when the common candidate and the context corresponding to the input string miss the user multiword stock, triggering an input string error correction module to perform an operation of performing error correction processing on the input string.

Optionally, the apparatus further comprises: the establishing module is used for establishing the user multivariate thesaurus;

the establishing module comprises:

the recording submodule is used for recording the on-screen content of the user;

the selection submodule is used for selecting a multi-element phrase from one-time screen-on content or continuous multi-time screen-on content; and

and the storage submodule is used for storing the multi-element phrases and the corresponding attribute characteristics thereof into a user multi-element word bank.

Optionally, the selection submodule includes:

the first selection unit is used for selecting adjacent phrases from one-time screen-on content or continuous multi-time screen-on content to serve as multi-element phrases; or

And the second selection unit is used for selecting the phrases which accord with the preset collocation condition from the content which is displayed on the screen for one time or the content which is displayed on the screen for a plurality of times continuously as the multi-element phrases.

Optionally, the continuous multiple-time on-screen content is obtained through a continuous on-screen operation, and then the apparatus further includes: an end determining module for determining the end of the continuous screen-on operation;

the end determination module includes:

the first end determining submodule is used for determining that the continuous screen-up operation is ended when the clicking operation aiming at a preset end key is received; wherein, the preset end key comprises: punctuation mark keys and/or backspace keys and/or space keys and/or function keys; or

And the second ending determination submodule is used for determining that the current screen-on operation is the ending of the continuous screen-on operation when the time interval between the current screen-on operation and the next screen-on operation is greater than the interval threshold.

In yet another aspect, an apparatus for input error correction is disclosed that includes a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured for execution by the one or more processors to include instructions for:

acquiring an input string in an input process;

searching in a user multivariate lexicon according to the error correction candidates and the context corresponding to the input string to obtain corresponding search results; the user multivariate word stock records multivariate word groups input by a user;

and displaying the sorted error correction candidates to a user.

The embodiment of the invention has the following advantages:

in the input error correction process, the error correction candidates are sequenced according to the error correction candidates corresponding to the input strings and the search results of the context in the user multivariate lexicon; because the user multi-element word stock is used for recording multi-element word groups input by the user, and the multi-element word groups can reflect the personalized input habits of the user, the sorting of the embodiment of the invention can arrange the hit error correction candidates in front of the missed error correction candidates, or increase the scores of the hit error correction candidates on the basis of normal scores, in other words, the embodiment of the invention advances the positions of the error correction candidates hitting the user multi-element word stock, and can provide the error correction candidates conforming to the personalized input habits, thereby improving the quality of the error correction candidates and improving the accuracy of error correction. Furthermore, the position of the error correction candidate hitting the user multivariate lexicon is advanced, so that the user can quickly select the required error correction candidate on a screen under the condition of no page turning or less page turning, and the input efficiency can be improved.

Drawings

FIG. 1 is a flowchart illustrating steps of a first embodiment of an input error correction method according to the present invention;

FIG. 2 is a flowchart illustrating steps of a second embodiment of an input error correction method according to the present invention;

FIG. 3 is a flowchart illustrating the steps of a third embodiment of an input error correction method according to the present invention;

FIG. 4 is a flowchart illustrating the fourth step of an input error correction method according to a fourth embodiment of the present invention;

FIG. 5 is a block diagram of an embodiment of an input error correction apparatus according to the present invention;

FIG. 6 is a block diagram of an apparatus 900 for input error correction in accordance with the present invention; and

fig. 7 is a schematic diagram of a server in some embodiments of the invention.

Detailed Description

In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.

Method embodiment one

Referring to fig. 1, a flowchart illustrating steps of a first embodiment of an input error correction method according to the present invention is shown, which may specifically include the following steps:

step 101, acquiring an input string in an input process;

102, carrying out error correction processing on the input string to obtain an error correction candidate corresponding to the input string;

103, searching in a user multivariate lexicon according to the error correction candidates and the context corresponding to the input string to obtain a corresponding search result; the user multivariate word bank is used for recording multivariate word groups input by a user;

step 104, sorting the error correction candidates corresponding to the input string according to the search result;

and 105, displaying the sorted error correction candidates to a user.

The embodiment of the invention can be applied to input method systems of various input modes, for example, the input modes can specifically include input modes such as keyboard symbols, handwritten information and the like, that is, a user can input on-screen contents through coded character strings, handwritten attribute characteristics and the like. In the following, only the input method of the code string (hereinafter, simply referred to as an input string) will be described as an example, and other input methods may be referred to each other.

In the field of input method systems, no matter the input method systems are in Chinese, Japanese, Korean or other languages, coded character strings input by users are converted into candidate items of corresponding languages, and then the users select contents output to application programs, wherein the contents output to the application programs, namely, on-screen contents, are output through on-screen operation. In an alternative embodiment of the present invention, an input process may begin with the receipt of an input string and end with the screen of the candidate item corresponding to the input string. Taking the input process of the input string "nihao" and the on-screen content "hello" as an example, the input process starts when the character "n" is received, and the input process ends after the on-screen operation of the candidate item "hello" corresponding to the input string "nihao" is received. In the embodiment of the present invention, the input process in step 101 may generally refer to a series of processes in which a user uses an input method system to input and edit input content, for example, the input process may specifically include: one input process, multiple input processes, even a process of changing the content on the screen between adjacent input processes, and the like, it can be understood that the specific input process is not limited by the embodiment of the present invention.

The input error correction method provided by the embodiment of the invention can be applied to application environments corresponding to the client and the server of the input method system, wherein the client and the server of the input method system can be positioned in a wired or wireless network, and the client and the server perform data interaction through the wired or wireless network.

Specifically, a client of the input method system may run on the intelligent terminal, and the client may capture a series of operations of a user in an input process, such as an operation of typing an input string, an operation of displaying a screen for a candidate item, and the like. The intelligent terminal may specifically include, but is not limited to: smart phones, tablet computers, electronic book readers, MP3 (Moving Picture Experts Group Audio Layer III) players, MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop portable computers, car-mounted computers, desktop computers, set-top boxes, smart televisions, wearable devices, and the like.

In practical applications, a user may input an incorrect input string due to pressing an incorrect key (on a PC), clicking an incorrect screen position (on a smart terminal), or an incorrect operation intention. Although the existing error correction scheme based on the edit distance and the error correction scheme based on the statistics can obtain error correction candidates, the existing error correction scheme and the existing error correction scheme based on the statistics often provide the same error correction candidates for different users, and the existing error correction scheme based on the edit distance cannot realize personalized error correction.

In the input error correction process, the error correction candidates are sequenced according to the error correction candidates corresponding to the input strings and the search results of the context in the user multivariate lexicon; because the user multivariate word library records the multivariate word group input by the user, and the multivariate word group can reflect the personalized input habit of the user, the sorting of the embodiment of the invention can arrange the hit error correction candidates in front of the missed error correction candidates, or increase the scores of the hit error correction candidates on the basis of the normal scores, in other words, the embodiment of the invention advances the positions of the error correction candidates hitting the multivariate word library of the user, and can provide the error correction candidates conforming to the personalized input habit, thereby improving the quality of the error correction candidates and simultaneously improving the accuracy of error correction. Furthermore, the position of the error correction candidate hitting the user multivariate lexicon is advanced, so that the user can quickly select the required error correction candidate on a screen under the condition of no page turning or less page turning, and the input efficiency can be improved.

In an application example 1 of the present invention, a user multiword library records a multiword phrase "extraordinary force", after the user again screens "extraordinary", if the input string "gili" is wrongly inputted, the input method system may correct the "gili", assuming that the correction of the "gili" is performed using an error correction scheme based on the edit distance and/or an error correction scheme based on statistics, resulting in correction candidates "encouragement" and "give force", the "encouragement" is ranked ahead of the "give force" according to the normal score, by applying the embodiment of the invention, the 'extraordinary' and the 'given force' of the error correction candidate hit the user multivariate word bank, the hit error correction candidate may be "given" ahead of the missed error correction candidate "encouragement", or, and increasing the score of the hit error correction candidate 'give power' on the basis of the normal score so as to enable the error correction candidate to be more consistent with the personalized habit of the user.

In practical applications, step 102 may utilize any error correction scheme to perform error correction processing on the input string to obtain an error correction string corresponding to the input string, and search for a corresponding error correction candidate in the lexicon according to the error correction string. The word bank of the embodiment of the present invention may specifically include: the system word stock, the user word stock, the cell word stock, the cloud word stock, the hot word stock and the like, and the embodiment of the invention does not limit the specific word stock. Optionally, the error correction scheme may specifically include: edit distance based error correction schemes and statistical based error correction schemes.

The error correction process of the error correction scheme based on the edit distance may specifically include: four error correction attempts are made for each position of the input string as follows: inserting a character, deleting a character, replacing a character and replacing two character positions before and after the character to generate an error correction string sequence corresponding to the input string.

The statistical-based error correction scheme may generate an error correction model through big data mining, where the error correction model may be used to learn a probability that an error correction string is mistakenly input as an input string (hereinafter, referred to as an error correction model probability), input strings may be input to the error correction model, and the error correction model may output a probability that each error correction string is mistakenly input as an input string. For example, if the input string is "gili" and the error correction string is "geili", the error correction model probability may be used to represent the probability that "gili" is mistakenly input as "gili", and in practical applications, the input behavior of the user may be statistically analyzed to obtain the error correction model probability.

Alternatively, the best error correction string may be selected from the sequence of error correction strings. In the selection process, the score of the probability of the error correction model and/or the word frequency score of the candidate corresponding to each error correction string may be based. The word frequency score corresponding to the candidate for the error correction string is typically the word frequency score corresponding to the preferred word frequency score for the error correction string. In the process of selecting the optimal error correction string from the error correction string sequence according to the score of the error correction model probability and the word frequency score of the candidate corresponding to each error correction string, the score of the error correction model probability and the word frequency score of the candidate corresponding to each error correction string can be subjected to weighted operation, all error correction strings are sorted according to the weighted operation result, and the optimal error correction string is selected according to the sorting result.

In the embodiment of the invention, the multi-element word group can be obtained from the content input by the user, and the obtained user multi-element word stock and the corresponding attribute characteristics thereof are stored in the user multi-element word stock.

In an optional embodiment of the present invention, the user multivariate thesaurus may be established by the following steps:

recording the on-screen content of the user; during the user's continuous input, the on-screen contents can be recorded once they are output through the on-screen action. For example: i like you (the "|" represents the screen-on action of the user), and the screen-on contents of three times are recorded in sequence; as another example, friday morning | sky | is very blue, and five screenings are recorded in sequence.

Selecting a multi-element phrase from one-time screen-on content or continuous screen-on contents for multiple times;

and storing the multi-element word group and the corresponding attribute characteristics thereof into a user multi-element word bank.

Optionally, the process of selecting the multi-element phrase may include: selecting adjacent phrases from the one-time screen-on content or the continuous multi-time screen-on content as multi-element phrases; or selecting a plurality of phrases which accord with preset collocation conditions from the content which is displayed on the screen for one time or the content which is displayed on the screen for a plurality of times continuously as the multi-element phrases. In practical application, some users are used to input a phrase at a time, and some users are used to input a long sentence comprising a plurality of phrases at a time, even for the same user, in most cases, the long sentence comprising the plurality of phrases is input at a time while thinking, and in few cases, the long sentence comprising the plurality of phrases is input at a time. The number of elements of the multi-element phrase may be greater than or equal to 2, that is, 2-element phrases, 3-element phrases, 4-element phrases, 5-element phrases, and the like are all within the protection scope of the multi-element phrase of the embodiment of the present invention.

In the embodiments of the present invention, a plurality of phrases included in a multi-element phrase may be adjacent to each other. Thus, a series of multi-element phrases can be extracted from the on-screen content of the user. For example, the 3 phrases that the user's 3-element phrase "i | like | you" includes are adjacent in the on-screen content.

Or, the selected multiple phrases may not be adjacent, and only need to meet preset collocation conditions, for example, the on-screen content is "i make flood force", but the phrase included in the selected user 2-element phrase "make flood force" may not be adjacent in the on-screen content; as another example, the on-screen content is "my inner is almost collapsed", but the multi-element phrases "i's | inner | collapsed", "i's | inner | is | collapsed | and" inner | collapsed "selected from them may include phrases that are not adjacent in the on-screen content. The preset matching condition may indicate that the multi-element phrase conforms to a matching rule or a custom usage of a corresponding language, and the language corresponding to the multi-element phrase may be one or more languages, for example, "make | flood and wilderness force" conform to a matching rule of Chinese, and for example, "press | ctrl | key" conforms to a matching rule of Chinese and English, "We | are | logging | tired," and | there is no | what | mean | used "conforms to a custom usage of Chinese.

It can be seen that the multi-element phrase in the embodiment of the present invention does not necessarily conform to the collocation rules of languages, and conforms to the current usage habits of users or most users, or the multi-element phrase can be considered reasonable as long as the user inputs the multi-element phrase.

In an optional embodiment of the present invention, the continuous multiple-time on-screen content may be a content obtained through a continuous on-screen operation, that is, the continuous multiple-time on-screen content may be taken as a whole, and a plurality of phrases are mined from the whole, and then it may be determined that the continuous on-screen operation is ended through the following steps:

when receiving a click operation aiming at a preset ending key, determining that the continuous screen-loading operation is ended; the preset end key may specifically include: punctuation mark keys and/or backspace keys and/or space keys and/or function keys; or

And when the time interval between the current screen-on operation and the next screen-on operation is larger than the interval threshold value, determining that the current screen-on operation is the end of the continuous screen-on operation.

In practical applications, when a complete sentence or long word is input, a user usually presses a preset end key such as a punctuation mark, or inputs a next sentence or long word after stopping inputting the next sentence or long word. Therefore, in the embodiment of the present invention, the operation of inputting various preset ending keys such as a comma, a period, a question mark, a backspace key, a enter key, and the like by the user is received, or no on-screen word is received within the time corresponding to the interval threshold as a mark for ending the on-screen operation, so that the obtained continuous multi-time on-screen content is obtained by naturally dividing the on-screen content according to the input behavior of the user. Of course, the preset end key is not limited to the above listed keys, and for example, a sending function key (e.g., enter key or CTRL + enter key) in an instant messaging program (e.g., QQ, WeChat, etc.) may be used as the preset end key. It should be understood that the specific form of the preset end key in the embodiments of the present invention is not limited, for example, any one of the above listed various keys may be used as the preset end key, or a combination of any several of the above keys may also be used as the preset end key.

The interval threshold may be a preset time value, such as 2 seconds. Alternatively, the interval threshold may be determined by: recording the screen-on time corresponding to the screen-on contents, calculating to obtain an average screen-on interval according to the interval between the screen-on times corresponding to every two screen-on contents, and taking the average screen-on interval as an interval threshold. Optionally, a value obtained by multiplying the average on-screen interval by a weighting coefficient may be used as an interval threshold, where the weighting coefficient value may be greater than 1, greater than 0 and less than 1, or may be adjusted based on the input behavior of the user. In summary, the embodiment of the present invention does not limit the specific determination manner of the interval threshold.

Optionally, the user multivariate thesaurus may record a mapping relationship between multivariate phrases and attribute features, and the attribute features may specifically include at least one of the following information: the number of inputs, the historical input time, and the historical input environment information. The number of inputs may be used to indicate the number of times the multi-element phrase was input, and the input time may be used to indicate the time the multi-element phrase was input, such as 201609190724. The historical input environment information may be used for input environment information where the intelligent terminal is located when the multi-element phrase is input, and the input environment information may include: external environment information such as time information, location information, etc., and the input environment information may also include: internal environment information, such as application environment information hosted by an input method system, for example, a user inputs a multi-element phrase "i" makes i flood in the environment of an instant messenger program, or a multi-element phrase "in i one of i an embodiment of i an invention" in the environment of an office document program, and so on. It is understood that those skilled in the art can adopt the required input environment information according to the actual application requirements, and the embodiment of the present invention does not limit the specific input environment information.

In practical application, a word group field may be set in the user multi-element word stock for a multi-element word group, and if "give too much force" is a word group, step 103 may combine the error correction candidates and the context corresponding to the input string to obtain a corresponding combined word, and match the combined word with the word group field recorded in the user multi-element word stock, if the matching is successful, the search result is a hit, otherwise, the search result is a miss.

Or, corresponding basic phrase fields may be set in the user multi-element word stock for each basic phrase of the multi-element word stock, for example, "give power" corresponds to "give power" and "give power" two basic phrase fields, "friday morning sky is very blue," corresponds to "friday", "morning", "sky", "very" and "blue" and the like, then step 103 may match the error correction candidates and context corresponding to the input string with each basic phrase field, if matching is successful, the search result is hit, otherwise, if matching is unsuccessful, the search result is miss. Where the base phrase may represent the smallest unit of a word, typically the word is not resolvable into other words, e.g., "together" may serve as a base phrase that is not resolvable into other words, and "give force" may be further resolved into the words "give force" and "give force", and thus "give force" is not a base phrase. It is understood that one skilled in the art can decompose the multiple phrases into corresponding multiple basic phrases according to the actual application requirement, and the embodiment of the present invention is not limited to the specific decomposition process.

It should be noted that the context of the embodiment of the present invention may specifically include: the foregoing and/or the following, wherein, in most scenarios, the foregoing corresponding to the input string may be captured, for example, the above application example 1 is a scenario of searching the user multivariate thesaurus according to the error correction candidate corresponding to the input string and the foregoing.

In a scenario where a user edits an input content, a context corresponding to an input string may be captured. In an application example 2 of the present invention, a user first inputs "blue in morning of friday", then moves a cursor to "morning", and inputs "tiany", and then a lower context "very blue" corresponding to "tiany" can be captured, assuming that a multivariate phrase "sky | very blue" and "sky | very blue of" morning | are recorded in a multivariate thesaurus of the user, and assuming that error correction candidates corresponding to "tiany" include: "sky" and "very blue", and "morning", "sky" and "very blue" all hit the user multiword stock, and other error correction candidates and their corresponding contexts miss the user multiword stock, so the "sky" can be arranged at a position closer to the front, which is convenient for the user to select.

In an optional embodiment of the present invention, the search result may specifically include: the hit error correction candidates or the miss error correction candidates, step 104 may rank the hit error correction candidates before the miss error correction candidates, or increase the scores of the hit error correction candidates based on the normal scores, thereby advancing the positions of the error correction candidates hitting the user multinary thesaurus.

In an optional embodiment of the present invention, when the search result searched in the user multivariate thesaurus comprises: when there are multiple hit error correction candidates, the method may further include: according to the attribute characteristics of the multi-element word groups recorded in the user multi-element word stock, sequencing a plurality of hit error correction candidates; and displaying the corresponding error correction candidates according to the sorting results of the plurality of hit error correction candidates. In practical application, the number of error correction candidates that generally need to be presented is limited, and assuming that the number of error correction candidates that need to be presented is N (generally N is a numerical value such as 1, 2), and the number of hit error correction candidates is M, and M is greater than N, the M hit error correction candidates may be sorted according to the attribute characteristics of the multi-element word group recorded in the user multi-element word library, so as to present the optimal N hit error correction candidates. Of course, the attribute feature of the multi-element phrase may also be used in combination with other ranking factors (e.g., the attribute feature of the error correction candidate itself), and the specific process of ranking the multiple hit error correction candidates is not limited in the embodiment of the present invention.

In practical applications, step 105 may present the sorted error correction candidates to the user through a candidate window of the input method system. Optionally, all or part of the error correction candidates may be selected to be presented according to the sorting result, and the embodiment of the present invention does not limit the specific presentation manner.

In an optional embodiment of the present invention, the common candidate corresponding to the error correction candidate and the input string may also be presented to the user. The common candidate corresponding to the input string may be obtained by querying in a lexicon, and the specific process of obtaining the common candidate is not limited in the embodiment of the present invention.

Alternatively, scores of the error correction candidates and the normal candidates may be determined separately, and then the error correction candidates and the normal candidates may be sorted according to the scores of the error correction candidates and the normal candidates, and the candidates may be provided to the user according to the sorting result. Optionally, the score of the common candidate may be a score corresponding to the preference of the input string, where the score of the preference may be a score calculated according to at least one feature of the preference, the word frequency, the classification information, the level, and the weight information, and may be used to measure the quality of the preference. In the sorting process, the score of the error correction candidate may be first subtracted by a penalty value, and then the subtraction result may be compared with the normal score. In practical application, the penalty value can be determined through an experiment simulating the input process of a user, so that the accuracy rate of input error correction is ensured as much as possible. It is understood that the specific sorting procedure of the error correction candidates and the common candidates is not limited by the embodiments of the present invention.

In summary, in the input error correction process, the embodiment of the invention sorts the error correction candidates according to the error correction candidates corresponding to the input string and the search result of the context in the user multivariate lexicon; because the user multivariate word library records the multivariate word group input by the user, and the multivariate word group can reflect the personalized input habit of the user, the sorting of the embodiment of the invention can arrange the hit error correction candidates in front of the missed error correction candidates, or increase the scores of the hit error correction candidates on the basis of the normal scores, in other words, the embodiment of the invention advances the positions of the error correction candidates hitting the multivariate word library of the user, and can provide the error correction candidates conforming to the personalized input habit, thereby improving the quality of the error correction candidates and simultaneously improving the accuracy of error correction. Furthermore, the position of the error correction candidate hitting the user multivariate lexicon is advanced, so that the user can quickly select the required error correction candidate on a screen under the condition of no page turning or less page turning, and the input efficiency can be improved.

In this embodiment of the present invention, the process of sorting the error correction candidates corresponding to the input string according to the search result may specifically include: and ranking the hit error correction candidates before the missed error correction candidates, or increasing the scores of the hit error correction candidates on the basis of the normal scores, thereby advancing the positions of the error correction candidates hitting the user multinary lexicon. The process of increasing the score of the error correction candidate of the hit on the basis of the normal score is explained here by the method embodiment two and the method embodiment three.

Method embodiment two

Referring to fig. 2, a flowchart illustrating steps of a second embodiment of an input error correction method according to the present invention is shown, which may specifically include the following steps:

step 201, acquiring an input string in an input process;

step 202, performing error correction processing on the input string to obtain an error correction candidate corresponding to the input string;

step 203, searching in a user multivariate lexicon according to the error correction candidates and the context corresponding to the input string to obtain corresponding search results; the user multivariate word bank is used for recording multivariate word groups input by a user; the search result searched in the user multivariate word library may include: a hit error correction candidate, or a miss error correction candidate;

step 204, determining a second score of the error correction candidate according to the search result; wherein the second score of the hit error correction candidate is greater than zero and the second score of the miss error correction candidate is zero;

step 205, adding the second score of the error correction candidate and the first score of the error correction candidate to obtain a third score; wherein the first score is obtained according to the attribute characteristics of the error correction candidate;

step 206, sorting the error correction candidates corresponding to the input string according to the third score;

step 207, presenting the sorted error correction candidates to the user.

Compared with the first embodiment of the method shown in fig. 1, in this embodiment, a process of sorting the error correction candidates corresponding to the input string according to the search result is described through steps 204 to 206, where step 204 is a process of determining a second score corresponding to an error correction candidate, and step 205 is a process of adding the second score and a first score, where the first score may be used to represent a normal score obtained according to the attribute feature of the error correction candidate, and the adding process may increase the score of a hit error correction candidate on the basis of the normal score, so as to advance the position of the error correction candidate hitting the user multinary thesaurus.

In the embodiment of the present invention, the second score of the error correction candidate and the first score of the error correction candidate may be added to obtain a third score; since the second score of the hit error correction candidate is greater than zero and the second score of the missed error correction candidate is zero, that is, the second score of the hit error correction candidate is greater than the second score of the missed error correction candidate, the score of the hit error correction candidate may be increased on the basis of the first score, thereby advancing the position of the error correction candidate hitting the user multinary thesaurus.

Optionally, when the second score is not zero, the method may further include:

taking a first preset value as a second score corresponding to the error correction candidate; or

And determining a second score corresponding to the error correction candidate according to the attribute characteristics of the multi-element word groups recorded in the user multi-element word stock.

It is understood that, a person skilled in the art may determine the first preset value according to the actual application requirement, for example, the second score of the hit error correction candidate may be set to a first preset value greater than 0, such as 0.5,1, and the like, and the embodiment of the present invention does not limit the specific first preset value.

Optionally, the attribute feature of the above-mentioned multinary phrase may specifically include at least one of the following features: the step of determining a second score corresponding to the error correction candidate according to the attribute characteristics of the multi-element word group recorded in the user multi-element word stock may specifically include: and determining a second score corresponding to the error correction candidate according to at least one of the input times, the difference between the historical input time and the current time, and the matching degree between the historical input environment information and the current input environment information. Alternatively, the second score may be proportional to the number of inputs, the second score may be inversely proportional to an absolute value of a difference between the historical input time and the current time, and the second score may be proportional to a degree of matching between the historical input environment information and the current input environment information. When the input environment information is the application program environment information hosted by the input method system, the matching degree can be determined according to the name of the application program or the category of the application program, for example, if the historical input environment information is a first instant messaging application program, and the current input environment information is a second instant messaging application program, a higher matching degree can be obtained because the category of the historical input environment information is the same as that of the second instant messaging application program; for another example, the historical input environment information is a first e-commerce application program, the current input environment information is a second e-commerce application program, and a higher matching degree can be obtained because the two are the same in category. It is to be understood that the embodiment of the present invention does not limit the specific determination manner of the matching degree between the historical input environment information and the current input environment information.

In yet another alternative embodiment of the present invention, the first score of the error correction candidate may be determined according to the attribute feature of the error correction candidate, and the embodiment of the present invention does not limit the specific determination manner of the first score. The attribute feature of the error correction candidate may specifically include at least one of the following features: editing distance between the error correction string corresponding to the error correction candidate and the input string, type of the word bank corresponding to the error correction candidate, and word frequency of the error correction candidate. It is understood that those skilled in the art may also adopt other attribute features, such as the on-screen time of the error correction candidate, etc., according to the actual application requirements.

In general, the first score may be inversely proportional to the edit distance, and the smaller the edit distance, the higher the first score, for example, the edit distances between the input string "gili" and the error correction string "guli" and between the input string "gili" and the error correction string "geili" are all 1, and the same first score may be obtained according to the edit distance.

The type of the lexicon corresponding to the error correction candidate may specifically include: a user type and a system type, and in general, the first score corresponding to the user type may be higher than the first score corresponding to the system type.

In general, the first score may be proportional to the word frequency and the on-screen time, i.e., the higher the word frequency the higher the first score, the greater the on-screen time (closer to the current time), the higher the first score, etc.

In still another alternative embodiment of the present invention, the adding process of the second score of the error correction candidate and the first score of the error correction candidate in step 205 may be performed in various ways, and for example, the adding process may be a normal adding process, or may be a weighted average process. Since the second score corresponding to the hit error correction candidate is greater than the second score corresponding to the missed error correction candidate, the above combination may increase the third score corresponding to the hit error correction candidate, thereby advancing the position of the hit error correction candidate.

Method embodiment three

Referring to fig. 3, a flowchart illustrating a third step of an input error correction method according to an embodiment of the present invention is shown, which may specifically include the following steps:

301, acquiring an input string in an input process;

step 302, performing error correction processing on the input string to obtain an error correction candidate corresponding to the input string;

step 303, searching in a user multivariate lexicon according to the error correction candidates and the context corresponding to the input string to obtain a corresponding search result; the user multivariate word bank is used for recording multivariate word groups input by a user; the search result searched in the user multivariate word library may include: a hit error correction candidate, or a miss error correction candidate;

step 304, determining a fourth score of the error correction candidate according to the search result; wherein the fourth score of the hit error correction candidate is greater than 1 and the fourth score of the missed error correction candidate is less than 1;

step 305, multiplying the fourth score of the error correction candidate with the first score of the error correction candidate to obtain a fifth score; wherein the first score is obtained according to the attribute characteristics of the error correction candidate;

step 306, sorting the error correction candidates corresponding to the input string according to the fifth score;

step 307, the sorted error correction candidates are presented to the user.

With respect to the first embodiment of the method shown in fig. 1, the process of sorting the error correction candidates corresponding to the input string according to the search result is described through steps 304-306, where step 304 is a process of determining a fourth score corresponding to the error correction candidate, and step 305 is a process of multiplying the fourth score by a first score, where the first score may be used to represent a normal score obtained according to the attribute feature of the error correction candidate, and the multiplying process may increase the score of the hit error correction candidate on the basis of the normal score, so as to advance the position of the error correction candidate hitting the user multinary thesaurus.

In this embodiment of the present invention, the fourth score of the error correction candidate may be multiplied by the first score of the error correction candidate to obtain a fifth score; since the fourth score of the hit error correction candidate is greater than 1 and the fourth score of the missed error correction candidate is less than 1, the score of the hit error correction candidate may be increased on the basis of the first score, thereby advancing the position of the error correction candidate hitting the user multinary thesaurus.

Optionally, the method may further include:

taking a second preset value as a fourth score corresponding to the error correction candidate; or

And determining a fourth score corresponding to the error correction candidate according to the attribute characteristics of the multi-element word groups recorded in the user multi-element word stock.

It is to be understood that, a person skilled in the art may determine the second preset value according to practical application requirements, for example, the fourth score of a hit error correction candidate may be set to a second preset value larger than 1, and a number of values 1.5, 2, and the like, and for example, the fourth score of a missed error correction candidate may be set to a second preset value smaller than 1, such as 0.5, 0.8, and the like, and the specific second preset value is not limited by the embodiment of the present invention.

Method example four

Referring to fig. 4, a flowchart illustrating a fourth step of an input error correction method according to an embodiment of the present invention is shown, which may specifically include the following steps:

step 401, acquiring an input string in an input process;

step 402, searching in a user multivariate word bank according to the common candidate and the context corresponding to the input string;

step 403, when the common candidate and context corresponding to the input string hit the user multivariate lexicon, not executing the operation of performing error correction processing on the input string;

step 404, when the common candidate and context corresponding to the input string miss the user multivariate lexicon, performing error correction processing on the input string to obtain an error correction candidate corresponding to the input string;

step 405, searching in a user multivariate lexicon according to the error correction candidates and the context corresponding to the input string to obtain a corresponding search result; the user multivariate word stock records multivariate word groups input by a user;

step 406, sorting the error correction candidates corresponding to the input string according to the search result;

step 407, presenting the sorted error correction candidates to the user.

In existing schemes, error correction processing is typically performed on each input string in an attempt to improve candidate quality by error correction candidates. However, the error correction process takes a certain time cost, and also takes a series of terminal resource costs such as memory of the smart terminal.

Compared with the first method embodiment shown in fig. 1, the second method embodiment shown in fig. 2, or the third method embodiment shown in fig. 3, in this embodiment, the execution condition of the error correction processing on the input string may be determined according to the user multivariate lexicon, and if the common candidate and the context corresponding to the input string hit the user multivariate lexicon, it is indicated that the common candidate can already meet the personalized input habit of the user, that is, the quality of the common candidate is already high, so the step of performing the error correction processing on the input string may not be performed, and thus the time spent on the error correction processing and the terminal resource cost may be saved to a certain extent, and further the performance such as the standby time of the intelligent terminal may be improved.

When the common candidate and the context corresponding to the input string miss the user multi-element word bank, the common candidate does not accord with the personalized input habit of the user, so the embodiment of the invention can try to improve the candidate quality by correcting the candidate.

It should be noted that, for simplicity of description, the method embodiments are described as a series of motion combinations, but those skilled in the art should understand that the present invention is not limited by the described motion sequences, because some steps may be performed in other sequences or simultaneously according to the present invention. Further, those skilled in the art will appreciate that the embodiments described in the specification are presently preferred and that no moving act is required as an embodiment of the invention.

Device embodiment

Referring to fig. 5, a block diagram of an embodiment of an input device according to the present invention is shown, which may specifically include: an input string obtaining module 501, an input string error correction module 502, a multivariate thesaurus searching module 503, an error correction candidate sorting module 504 and an error correction candidate presenting module 505.

The input string obtaining module 501 is configured to obtain an input string in an input process;

an input string error correction module 502, configured to perform error correction processing on the input string to obtain an error correction candidate corresponding to the input string;

the multivariate lexicon search module 503 is configured to search in the multivariate lexicon of the user according to the error correction candidates and the context corresponding to the input string to obtain a corresponding search result; the user multi-element word stock can record multi-element word groups input by a user;

an error correction candidate sorting module 504, configured to sort, according to the search result, the error correction candidates corresponding to the input string; and

and an error correction candidate presenting module 505, configured to present the sorted error correction candidates to a user.

Optionally, the search result searched in the user multivariate thesaurus may include: a hit error correction candidate, or a miss error correction candidate, the error correction candidate sorting module 504 may include:

Optionally, the apparatus may further include:

Optionally, the attribute feature of the above-mentioned multinary phrase may include at least one of the following features: the input times, the historical input time, and the historical input environment information, the score determining module may include:

Optionally, the attribute feature of the error correction candidate may include at least one of the following features: editing distance between the error correction string corresponding to the error correction candidate and the input string, type of the word bank corresponding to the error correction candidate, and word frequency of the error correction candidate.

Optionally, when the search result searched in the user multivariate thesaurus includes: when there are multiple hit error correction candidates, the apparatus may further include:

Optionally, the apparatus may further include:

and the execution processing module is used for not executing the operation of carrying out error correction processing on the input string when the common candidate and the context corresponding to the input string hit the user multivariate thesaurus. Optionally, when the common candidate and the context corresponding to the input string miss the user multiword stock, the input string error correction module 502 may be triggered to perform an operation of performing error correction processing on the input string.

Optionally, the apparatus may further include: the establishing module is used for establishing the user multivariate thesaurus;

the establishing module may include:

Optionally, the selecting sub-module may include:

Optionally, the continuous multiple-time on-screen content may be content obtained through a continuous on-screen operation, and the apparatus may further include: an end determining module for determining the end of the continuous screen-on operation;

the end determination module may include:

For the device embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, refer to the partial description of the method embodiment.

The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.

With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.

Fig. 6 is a block diagram illustrating an apparatus 900 for input error correction according to an example embodiment. For example, the apparatus 900 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, an exercise device, a personal digital assistant, and the like.

Referring to fig. 6, apparatus 900 may include one or more of the following components: processing component 902, memory 904, power component 906, multimedia component 908, audio component 910, input/output (I/O) interface 912, sensor component 914, and communication component 916.

The processing component 902 generally controls overall operation of the device 900, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. Processing element 902 may include one or more processors 920 to execute instructions to perform all or a portion of the steps of the methods described above. Further, processing component 902 can include one or more modules that facilitate interaction between processing component 902 and other components. For example, the processing component 902 can include a multimedia module to facilitate interaction between the multimedia component 908 and the processing component 902.

The memory 904 is configured to store various types of data to support operation at the device 900. Examples of such data include instructions for any application or method operating on device 900, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 904 may be implemented by any type or combination of volatile or non-volatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.

The power supply component 906 provides power to the various components of the device 900. The power components 906 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device 900.

The multimedia component 908 comprises a screen providing an output interface between the device 900 and a user. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide motion action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 908 includes a front facing camera and/or a rear facing camera. The front-facing camera and/or the rear-facing camera may receive external multimedia data when the device 900 is in an operating mode, such as a shooting mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

The audio component 910 is configured to output and/or input audio signals. For example, audio component 910 includes a Microphone (MIC) configured to receive external audio signals when apparatus 900 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may further be stored in the memory 904 or transmitted via the communication component 916. In some embodiments, audio component 910 also includes a speaker for outputting audio signals.

I/O interface 912 provides an interface between processing component 902 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: a home button, a volume button, a start button, and a lock button.

The sensor component 914 includes one or more sensors for providing status assessment of various aspects of the apparatus 900. For example, the sensor assembly 914 may detect an open/closed state of the device 900, the relative positioning of the components, such as a display and keypad of the apparatus 900, the sensor assembly 914 may also detect a change in the position of the apparatus 900 or a component of the apparatus 900, the presence or absence of user contact with the apparatus 900, orientation or acceleration/deceleration of the apparatus 900, and a change in the temperature of the apparatus 900. The sensor assembly 914 may include a proximity sensor configured to detect the presence of a nearby object in the absence of any physical contact. The sensor assembly 914 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 914 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 916 is configured to facilitate communications between the apparatus 900 and other devices in a wired or wireless manner. The apparatus 900 may access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 916 receives a broadcast signal or broadcast associated information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communications component 916 further includes a Near Field Communication (NFC) module to facilitate short-range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, the apparatus 900 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic components for performing the above-described methods.

In an exemplary embodiment, a non-transitory computer readable storage medium comprising instructions, such as the memory 904 comprising instructions, executable by the processor 920 of the apparatus 900 to perform the above-described method is also provided. For example, the non-transitory computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

A non-transitory computer readable storage medium, instructions in which, when executed by a processor of a smart terminal, enable the smart terminal to perform a method of input error correction, the method comprising: acquiring an input string in an input process; carrying out error correction processing on the input string to obtain an error correction candidate corresponding to the input string; searching in a user multivariate lexicon according to the error correction candidates and the context corresponding to the input string to obtain corresponding search results; the user multivariate word stock records multivariate word groups input by a user; sorting the error correction candidates corresponding to the input string according to the search result; and displaying the sorted error correction candidates to a user.

Fig. 7 is a schematic diagram of a server in some embodiments of the invention. The server 1900 may vary widely by configuration or performance and may include one or more Central Processing Units (CPUs) 1922 (e.g., one or more processors) and memory 1932, one or more storage media 1930 (e.g., one or more mass storage devices) storing applications 1942 or data 1944. Memory 1932 and storage medium 1930 can be, among other things, transient or persistent storage. The program stored in the storage medium 1930 may include one or more modules (not shown), each of which may include a series of instructions operating on a server. Still further, a central processor 1922 may be provided in communication with the storage medium 1930 to execute a series of instruction operations in the storage medium 1930 on the server 1900.

The server 1900 may also include one or more power supplies 1926, one or more wired or wireless network interfaces 1950, one or more input-output interfaces 1958, one or more keyboards 1956, and/or one or more operating systems 1941, such as Windows Server, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.

Other embodiments of the invention will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the invention and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the invention being indicated by the following claims.

It will be understood that the invention is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the invention is only limited by the appended claims

The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.

The input error correction method, the input error correction device and the device for input error correction provided by the present invention are introduced in detail, and specific examples are applied in this text to explain the principle and the implementation of the present invention, and the description of the above embodiments is only used to help understanding the method of the present invention and the core idea thereof; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.

Claims

1. An input error correction method, comprising:

acquiring an input string in an input process;

displaying the sorted error correction candidates to a user;

before the step of performing error correction processing on the input string, the method further includes:

2. The method of claim 1, wherein the search result searched in the user multivariate thesaurus comprises: the step of sorting the error correction candidates corresponding to the input string according to the search result if the error correction candidate is hit or not hit includes:

3. The method of claim 1, wherein the search result searched in the user multivariate thesaurus comprises: the step of sorting the error correction candidates corresponding to the input string according to the search result if the error correction candidate is hit or not hit includes:

4. A method according to claim 2 or 3, characterized in that the method further comprises:

5. The method according to claim 4, wherein the attribute features of the multi-element phrase comprise at least one of the following features: and determining a second score and/or a fourth score corresponding to the error correction candidate according to the attribute characteristics of the multi-element phrases recorded in the user multi-element word stock by using the input times, the historical input time and the historical input environment information, wherein the step comprises the following steps of:

6. The method according to claim 2, wherein the attribute features of the error correction candidates comprise at least one of the following features: editing distance between the error correction string corresponding to the error correction candidate and the input string, type of the word bank corresponding to the error correction candidate, and word frequency of the error correction candidate.

7. The method according to any one of claims 1 to 3, wherein when the search result searched in the user thesaurus comprises: the method further comprises, for a plurality of hit error correction candidates:

8. A method according to any one of claims 1 to 3, wherein the user multiword library is created by:

recording the on-screen content of the user;

9. The method of claim 8, wherein the step of selecting the user-related phrase from one-time on-screen content or consecutive multiple-time on-screen content comprises:

10. An input error correction apparatus, comprising:

the multivariate lexicon searching module is used for searching in the multivariate lexicon of the user according to the error correction candidates and the context corresponding to the input string to obtain a corresponding searching result; the user multivariate word bank is used for recording multivariate word groups input by a user;

the error correction candidate display module is used for displaying the sorted error correction candidates to a user;

the device further comprises:

and the execution processing module is used for not executing the operation of carrying out error correction processing on the input string when the common candidate and the context corresponding to the input string hit the user multivariate thesaurus.

11. The apparatus of claim 10, wherein the search result searched in the user multivariate thesaurus comprises: a hit error correction candidate or a miss error correction candidate, the error correction candidate sorting module comprising:

12. The apparatus of claim 10, wherein the search result searched in the user multivariate thesaurus comprises: a hit error correction candidate or a miss error correction candidate, the error correction candidate sorting module comprising:

13. The apparatus of claim 11 or 12, further comprising:

14. The apparatus of claim 13, wherein the attribute feature of the multi-element phrase comprises at least one of the following features: the score determining module includes:

15. The apparatus according to claim 11, wherein the attribute feature of the error correction candidate comprises at least one of the following features: editing distance between the error correction string corresponding to the error correction candidate and the input string, type of the word bank corresponding to the error correction candidate, and word frequency of the error correction candidate.

16. The apparatus according to any one of claims 10 to 12, wherein when the search result searched in the user thesaurus comprises: in the case of multiple hit error correction candidates, the apparatus further comprises:

17. The apparatus of any of claims 10 to 12, further comprising: the establishing module is used for establishing the user multivariate thesaurus;

the establishing module comprises:

18. The apparatus of claim 17, wherein the selection submodule comprises:

19. An apparatus for input error correction comprising a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by one or more processors the one or more programs including instructions for:

acquiring an input string in an input process;

displaying the sorted error correction candidates to a user;

before the input string is subjected to error correction processing, searching in a user multivariate lexicon according to common candidates and contexts corresponding to the input string;

and when the common candidate and the context corresponding to the input string hit the user multivariate lexicon, not executing the error correction processing on the input string.

20. The apparatus of claim 19, wherein the search result searched in the user multiword library comprises: if the error correction candidate is hit or not hit, the sorting the error correction candidates corresponding to the input string according to the search result includes:

21. The apparatus of claim 19, wherein the search result searched in the user multiword library comprises: if the error correction candidate is hit or not hit, the sorting the error correction candidates corresponding to the input string according to the search result includes:

22. The apparatus of claim 19 or 20, wherein the apparatus is also configured to execute the one or more programs by one or more processors includes instructions for:

23. The apparatus of claim 22, wherein the attribute feature of the multi-element phrase comprises at least one of the following features: and determining a second score and/or a fourth score corresponding to the error correction candidate according to the attribute characteristics of the multi-element word group recorded in the user multi-element word stock by using the input times, the historical input time and the historical input environment information, wherein the determining comprises the following steps:

24. The apparatus according to claim 20, wherein the attribute feature of the error correction candidate comprises at least one of the following features: editing distance between the error correction string corresponding to the error correction candidate and the input string, type of the word bank corresponding to the error correction candidate, and word frequency of the error correction candidate.

25. The apparatus according to any one of claims 19 to 21, wherein when the search result searched in the user thesaurus comprises: when multiple hit error correction candidates, the device is also configured to execute, by one or more processors, the one or more programs including instructions for:

26. The apparatus of any of claims 19-21, wherein the apparatus is also configured to execute the one or more programs by one or more processors includes instructions for:

recording the on-screen content of the user;

27. The apparatus of claim 26, wherein selecting the user-related phrase from one-time on-screen content or consecutive multiple-time on-screen content comprises:

28. One or more machine readable media having instructions stored thereon that, when executed by one or more processors, cause an apparatus to perform the method of any of claims 1-9.