Input methods, devices and media

By sorting and judging multiple word grouping results of the input string, the system distinguishes between word replacement and non-word replacement scenarios, thereby improving input efficiency and accuracy in existing technologies and solving the problem that the highest-scoring word grouping result does not meet user needs.

CN115016652BActive Publication Date: 2024-11-01BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202110236480.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-03-03
Publication Date
2024-11-01
Estimated Expiration
2041-03-03

AI Technical Summary

Technical Problem

In existing technologies, when the highest-scoring word combination does not meet the user's input requirements, the user needs to select candidate options by displaying them in segments, resulting in low input efficiency.

Method used

Obtain and sort multiple word grouping results corresponding to the input string. Based on the judgment result of the first word grouping result, determine the candidate option from at least one second word grouping result. Determine whether the result contains the first word in the preset word pair to distinguish between word grouping scenarios with and without word replacement, and select the appropriate candidate option.

Benefits of technology

By presenting more word combination results, the likelihood of candidate words meeting user input needs is increased, input efficiency is improved, and the accuracy of word combination results is enhanced.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115016652B_ABST
    Figure CN115016652B_ABST
Patent Text Reader

Abstract

The embodiment of the present invention provides an input method, device and medium, wherein the method specifically includes: obtaining multiple word group results corresponding to an input string and sorting them; the corresponding sorting results include: a first word group result ranked first, and at least one second word group result ranked not first; according to a judgment result corresponding to the first word group result, determining a candidate item from the at least one second word group result; the judgment result corresponds to: whether the first word group result includes the first word in a preset word pair. The embodiment of the present invention can increase the possibility that the candidate item meets the user's input needs, thereby improving the user's input efficiency.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of computer information input, and in particular to an input method, device and medium. Background Art

[0002] For users of languages ​​such as Chinese, Japanese, and Korean, they generally need to interact with the computer through an input method program. For example, the user can enter an input string, and the input method program will query the vocabulary and convert the input string into candidate items in the corresponding language according to preset standard mapping rules and display them, and then display the candidate item selected by the user on the screen.

[0003] When there is no entry in the word library that is directly hit by the input string, the input method program can trigger the word combination function. In order to avoid the interference of poor quality word combination results on users, multiple word combination results are usually obtained based on multi-dimensional relationships, and the word combination result with the highest score is displayed as a candidate.

[0004] During the implementation of the embodiments of the present invention, the inventors found that if the word combination result with the highest score does not meet the user's input requirements, the user often needs to select candidate items corresponding to multiple partial input strings in sequence through a segmented screen method to form an input result corresponding to the complete input string, resulting in low input efficiency. Summary of the invention

[0005] In view of the above problems, the embodiments of the present invention propose an input method, an input device and a device for input that overcome the above problems or at least partially solve the above problems. The embodiments of the present invention can increase the possibility that the candidate items meet the user's input needs, thereby improving the user's input efficiency.

[0006] In order to solve the above problem, an embodiment of the present invention discloses an input method, including:

[0007] Acquire multiple word group results corresponding to the input string and sort them; the corresponding sorted results include: a first word group result ranked first, and at least one second word group result ranked not first;

[0008] According to the judgment result corresponding to the first word group result, a candidate item is determined from the at least one second word group result; the judgment result corresponds to: whether the first word group result includes the first word in the preset word pair.

[0009] On the other hand, an embodiment of the present invention discloses an input device, comprising:

[0010] An acquisition and sorting module is used to acquire and sort multiple word grouping results corresponding to the input string; the corresponding sorting results include: a first word grouping result ranked first, and at least one second word grouping result ranked not first; and

[0011] A candidate item determination module is used to determine a candidate item from the at least one second word group result based on a judgment result corresponding to the first word group result; the judgment result corresponds to: whether the first word group result includes the first word in the preset word pair.

[0012] In another aspect, an embodiment of the present invention discloses a device for input, comprising a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors, and the one or more programs include instructions for performing the following operations:

[0013] Acquire multiple word group results corresponding to the input string and sort them; the corresponding sorted results include: a first word group result ranked first, and at least one second word group result ranked not first;

[0014] According to the judgment result corresponding to the first word group result, a candidate item is determined from the at least one second word group result; the judgment result corresponds to: whether the first word group result includes the first word in the preset word pair.

[0015] On the other hand, an embodiment of the present invention discloses one or more machine-readable media having instructions stored thereon, which, when executed by one or more processors, cause the device to perform one or more of the methods described above.

[0016] The embodiments of the present invention include the following advantages:

[0017] On the basis of the conventional technology that uses the first word group result with the highest score as a candidate, the embodiment of the present invention determines a candidate from at least one second word group result according to the judgment result corresponding to the first word group result. Since the embodiment of the present invention can present more word group results to the user in the form of candidate items, it can increase the possibility that the candidate items meet the user's input requirements, thereby improving the user's input efficiency.

[0018] Furthermore, the embodiments of the present invention can distinguish between word-replacement word-grouping scenarios and non-word-replacement word-grouping scenarios based on the judgment results. In this way, candidate items can be determined from the second word-grouping results in a targeted manner based on the distinguished word-grouping scenarios, thereby improving the accuracy of the word-grouping results that serve as candidate items. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 is a flow chart of steps of an input method embodiment 1 of the present invention;

[0020] Figure 2 is a flow chart of steps of Embodiment 2 of an input method of the present invention;

[0021] Figure 3 is a flow chart of steps of Embodiment 3 of an input method of the present invention;

[0022] Figure 4 is a structural block diagram of an input device embodiment of the present invention;

[0023] Figure 5 is a block diagram of a device 900 for inputting according to the present invention; and

[0024] Figure 6 It is a schematic diagram of the structure of the server in some embodiments of the present invention. DETAILED DESCRIPTION

[0025] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0026] In order to avoid the interference of poor quality word combination results on users, currently only one word combination result is usually provided among the candidate items. Specifically, only the word combination result with the highest score is displayed as a candidate item. However, if the word combination result with the highest score does not meet the user's input requirements, the user often needs to select candidate items corresponding to multiple partial input strings in sequence to form an input result corresponding to the complete input string by means of segmented screen display, resulting in low input efficiency.

[0027] For example, input string A is "jiaotayiqiguolaiba". Assume that multiple word grouping results are obtained for input string A, among which word grouping result A "Ask him to come together" has the highest score, so word grouping result A is displayed as a candidate. If word grouping result A does not meet the user's input requirements, the user needs to select the candidate by segmenting the screen. For example, the user selects the candidate corresponding to "jiaota", "yiqi", "guolai", and "ba" in turn. The above segmented screen display method results in low input efficiency.

[0028] In response to the technical problem of low input efficiency in related technologies, an embodiment of the present invention provides an input solution, which may specifically include: obtaining multiple word group results corresponding to the input string and sorting them; the corresponding sorting results specifically include: a first word group result ranked first, and at least one second word group result ranked not first; based on the judgment result corresponding to the above-mentioned first word group result, determining a candidate item from the above-mentioned at least one second word group result; the above-mentioned judgment result corresponds to: whether the above-mentioned first word group result contains the first word in the preset word pair.

[0029] On the basis of the conventional technology that uses the first word group result with the highest score as a candidate, the embodiment of the present invention determines a candidate from at least one second word group result according to the judgment result corresponding to the first word group result. Since the embodiment of the present invention can present more word group results to the user in the form of candidate items, it can increase the possibility that the candidate items meet the user's input requirements, thereby improving the user's input efficiency.

[0030] Furthermore, in an embodiment of the present invention, the judgment result corresponding to the first word group result corresponds to: whether the above-mentioned first word group result includes the first word in the preset word pair. The preset word pair can characterize the pairing relationship between words, and the two words included in the preset word pair are usually highly interchangeable. In the case where the first word group result includes the first word in the preset word pair, it can correspond to a word grouping scenario of word replacement. In this case, a candidate item that can replace the first word can be found from the second word group result, thereby enabling the expansion of similar expressions of the first word group result. In the case where the first word group result does not include the first word in the preset word pair, it can correspond to a word grouping scenario of non-word replacement. In this case, a candidate item can be determined from the second word group result based on the quality requirements for word group results in this field.

[0031] Therefore, the embodiment of the present invention can distinguish between the word grouping scenarios of word replacement and the word grouping scenarios of non-word replacement based on the judgment results. In this way, candidate items can be determined from the second word grouping results in a targeted manner based on the distinguished word grouping scenarios, thereby improving the accuracy of the word grouping results as candidate items.

[0032] The data processing method provided by the embodiment of the present invention can be applied to an application environment corresponding to a client and a server. The client and the server are located in a wired or wireless network, and the client and the server interact with each other through the wired or wireless network.

[0033] Optionally, the client can be run on a terminal, which specifically includes but is not limited to: a smart phone, a tablet computer, an e-book reader, an MP3 (Moving Picture Experts Group Audio Layer III) player, an MP4 (Moving Picture Experts Group Audio Layer IV) player, a laptop computer, a car computer, a desktop computer, a set-top box, a smart TV, a wearable device, etc. The operating system installed in the above terminal may include: IOS, Android, Windows, Linux, etc. It can be understood that the embodiment of the present invention does not limit the specific operating system installed in the terminal.

[0034] The above client may correspond to an input method program, wherein the input method program has a hosting feature and can be hosted in a host program environment such as a social program to provide services to the host program.

[0035] The server of the embodiment of the present invention may be a cloud server. A cloud server is a simple, efficient, safe, reliable, and elastically scalable computing service. The resource information of the cloud server is dynamic, so that its processing capacity can be elastically scalable.

[0036] Input method refers to the encoding method used to input various texts into computers or other devices (such as mobile phones and tablets). The input interface is a UI (User Interface), which is the medium for interaction and information exchange between the system and the user.

[0037] The embodiment of the present invention can be applied to input method programs of input methods such as keyboard symbol input, handwriting input, and voice input. For the convenience of description, the embodiment of the present invention refers to the encoded string input by the user in the above input methods as an input string. In the field of input methods, for input method programs such as Chinese, Japanese, Korean, or other languages, the input string input by the user can usually be converted into a candidate of the corresponding language. The following mainly uses Chinese as an example to illustrate the input process of the embodiment of the present invention, and other languages ​​can be referenced. It can be understood that the above-mentioned Chinese input method may include but is not limited to full spelling, simplified spelling, strokes, Wubi, etc., and the embodiment of the present invention does not limit the specific input method program corresponding to a certain language.

[0038] According to some embodiments, the input string may include, but is not limited to, a key symbol or a combination of multiple key symbols input by the user through keys. The key symbol may specifically include pinyin, strokes, kana, and the like.

[0039] The embodiment of the present invention can call up the input method program in any application scenario in response to the calling operation. Optionally, the calling operation can be a trigger operation on the input window, etc. The input window can include: an input box, etc. For example, if a click operation on the input box is received, the input method program is called up.

[0040] Optionally, after the input method program is called up, an input interface may be displayed for the user to input the input content through the input interface. The input interface may include an input keyboard, which generally includes a plurality of keys. The keys may include character keys and function keys. Function keys may include setting keys, search keys, enter keys, etc. Character keys may further include letter keys, number keys, symbol keys, function keys, etc.

[0041] Method Example 1

[0042] Reference Figure 1 , shows a flow chart of the steps of an input method embodiment 1 of the present invention, which may specifically include the following steps:

[0043] Step 101, obtaining multiple word group results corresponding to the input string and sorting them; the corresponding sorted results specifically include: a first word group result ranked first, and at least one second word group result ranked not first;

[0044] Step 102: Determine a candidate item from the at least one second word group result based on a judgment result corresponding to the first word group result; the judgment result specifically corresponds to: whether the first word group result includes the first word in the preset word pair.

[0045] In step 101, a search may be performed in the word library according to the input string, and if a hit is found, the entry obtained by the search may be used as the target entry. Optionally, the word library of the embodiment of the present invention may specifically include: a system word library, a user word library, a cell word library, a cloud word library, etc., and the embodiment of the present invention does not limit the specific word library.

[0046] In the case where there is no target entry directly hit by the input string in the vocabulary, word combination can be triggered, and the word combination technology is used to determine the word combination result corresponding to the above input string. The above word combination technology usually obtains the word combination path based on multi-relationships, and then obtains the word combination result according to the word combination path. Of course, word combination can also be triggered when there is a target entry directly hit by the input string in the vocabulary. The embodiment of the present invention does not limit the specific triggering conditions for word combination.

[0047] Here is an example of a word formation process, which may specifically include the following steps:

[0048] Step S1, segmenting the input string, and obtaining segmentation results including: a plurality of segmentation character strings.

[0049] In a specific implementation, the input string can be segmented according to the encoding units corresponding to the characters. Taking the pinyin input method as an example, the encoding units corresponding to the characters may include: syllables.

[0050] For example, by segmenting according to the full pinyin syllables, the input string A "jiaotayiqiguolaiba" can be segmented into "jiao", "ta", "yi", "qi", "guo", "lai", "ba". For another example, by segmenting according to the simplified pinyin syllables, "jtyqglb" can be segmented into "j", "t", "y", "q", "g", "l", "b".

[0051] Step S2: searching the word library for words corresponding to the multiple segmented character strings in the segmentation result, and grouping the words to obtain at least one grouping result corresponding to the segmentation result.

[0052] For example, the segmentation results corresponding to the input string A "jiaotayiqiguolaiba" include the following segmentation character strings: "jiao", "ta", "yi", "qi", "guo", "lai", "ba", and the words corresponding to multiple segmentation character strings can be searched in the vocabulary, such as the words "jiao", "jiao", "call", etc. corresponding to "jiao", the words "she", "he", "it", etc. corresponding to "ta", the words "together", "instrument", "first period", etc. corresponding to "yi" and "qi", the words "come here", etc. corresponding to "guo" and "lai", etc., and the words "bar", "dad", etc. corresponding to "ba".

[0053] The embodiment of the present invention can combine the words corresponding to the multiple segmented character strings respectively according to the order of segmented character strings to obtain at least one word combination result. For example, according to the order of segmented character strings, "call", "she", "together", "come here" and "bar" are combined to obtain the word combination result "call her to come together" and the like. For another example, according to the order of segmented character strings, "teach", "she", "one period", "come here" and "dad" are combined to obtain the word combination result "teach her one period come here dad" and the like. Similarly, the word combination results such as "call him to come together" and "call him to come together dad" can also be obtained.

[0054] Step S3: determine the score corresponding to the word combination result.

[0055] The score is used to characterize the quality of the word combination result. The quality can characterize the probability of occurrence of the word combination result in the corresponding language. The score can be used to screen the word combination results, which can not only improve the quality of the target word combination result as a candidate, but also increase the possibility that the target word combination result meets the user's input requirements.

[0056] Factors determining the score may include: the frequency of words in the word group result, and any one or a combination of the probabilities of adjacent appearance of words in the word group result.

[0057] The frequency of a word in the word group result can represent the frequency of the user's input of the word in the word group result, which can reflect the frequency of use of the word. In practical applications, the frequency of the word in the word library can be determined based on the number of times the user puts the word corresponding to the candidate item on the screen, which will not be elaborated here.

[0058] The probability of adjacent words in the word grouping result can characterize the connection or collocation of adjacent words in the word grouping result. In a specific implementation, the probability of adjacent words in the word grouping result can be determined based on multi-element relationship data. Multi-element relationship data can include binary and multi-element relationship data. A binary relationship, also known as a 2-gram, is used to represent the probability of two sentence words appearing one after another. A relationship with more than two elements is used to represent the probability of more than two words appearing one after another.

[0059] In an embodiment of the present invention, the score corresponding to the word grouping result may be determined based on the word frequency of the words in the word grouping result and the probability of adjacent appearance of the words in the word grouping result.

[0060] The above-mentioned determination of the score corresponding to the word combination result may specifically include:

[0061] The word frequencies of all words in the word grouping result are first fused to obtain a first fusion result. The corresponding first fusion method may include: a product method, a summation method, a weighted average method, etc.

[0062] The probabilities of adjacent word pairs in the word grouping result appearing adjacently are subjected to a second fusion to obtain a second fusion result. The corresponding second fusion method may include: a product method, a summation method, a weighted average method, etc.

[0063] The third fusion result obtained by performing a third fusion on the first fusion result and the second fusion result can be used as a score. The corresponding third fusion method can include: a product method, a summation method, a weighted average method, etc.

[0064] It is understood that the first fusion, the second fusion and the third fusion are merely examples of determining the score corresponding to the word grouping result, and are not to be construed as limitations on determining the score corresponding to the word grouping result. It is understood that those skilled in the art may adopt other methods of determining the score corresponding to the word grouping result according to actual application requirements.

[0065] For example, in one determination method, the score corresponding to a single adjacent word pair can be determined, and the scores corresponding to all adjacent word pairs can be fused to obtain a score. Determining the score corresponding to a single adjacent word pair can include: performing a fourth fusion on the word frequencies of the words included in the single adjacent word pair, and determining the score based on the fourth fusion result and the probability of adjacent appearance of the single adjacent word pair. For example, the word grouping result includes: word A, word B, word C, word D... in sequence, then the adjacent word pairs can include: word A and word B, word B and word C, word C and word D, etc. In this way, the score of word A and word B can include: the product of the word frequency fusion result of word A and word B and the probability of adjacent appearance of word A and word B.

[0066] The embodiment of the present invention can sort multiple word grouping results according to the scores of the word grouping results. Specifically, the multiple word grouping results can be sorted in order from high to low scores. The corresponding sorting results may include: a first word grouping result ranked first, and at least one second word grouping result ranked not first. In the sorting results, the first word grouping result has the highest score, and the score of the second word grouping result may be less than the score of the first word grouping result.

[0067] In conventional technology, usually only the first group of word results are used as candidate items. In other words, in order to avoid interference of the second group of word results to the user, the second group of word results are not considered as candidate items.

[0068] The embodiment of the present invention considers the possibility of using the second word group result as a candidate item. Specifically, in step 102, a candidate item is determined from at least one second word group result according to the judgment result corresponding to the first word group result. Since the embodiment of the present invention can present more word group results to the user in the form of candidate items, it can increase the possibility that the candidate items meet the user's input needs, thereby improving the user's input efficiency.

[0069] Furthermore, the embodiment of the present invention can distinguish between a word-replacement word-combination scenario and a non-word-replacement word-combination scenario based on the judgment result.

[0070] The preset word pair can represent the pairing relationship between words, and the two words included in the preset word pair are usually highly interchangeable.

[0071] The two words included in the preset word pair may satisfy any one or a combination of the following preset conditions: homonymy, synonymy, near-synonymy, same application scenario, and word frequency greater than a frequency threshold.

[0072] The embodiments of the present invention can construct preset word pairs based on preset conditions. For example, based on the preset conditions of homophony and word frequency greater than a frequency threshold, a preset word pair can be constructed: "he" and "she". For another example, based on the preset conditions of homophony and the same application scenario, a preset word pair can be constructed: "buy" and "sell", as well as "that" and "which", etc. It can be understood that those skilled in the art can construct preset word pairs based on actual application requirements using the required preset conditions, and the embodiments of the present invention do not limit the specific process of constructing preset word pairs.

[0073] In a specific implementation, the preset word pair may include: a first word and a second word, and then it can be determined whether the first word group result includes the first word in the preset word pair. If so, the judgment result is yes, otherwise, the judgment result is no.

[0074] After determining the candidate item from the second word group result, assuming that the second word group result A is determined as the candidate item, the second word group result A can be presented as the candidate item corresponding to the above input string, which can increase the possibility that the candidate item meets the user's input requirements.

[0075] In a specific implementation, the second word group result A can be presented at a preset candidate position for user selection. The preset candidate position can be a non-preferred position on the first screen, such as the second candidate position, or the third candidate position. Wherein, if there is a target entry, the preferred position (first candidate position) on the first screen can be used to present the target entry; or, if there is no target entry, the preferred position on the first screen can be used to present the first word group result.

[0076] In summary, the input method of the embodiment of the present invention, based on the traditional technology of taking the first word group result with the highest score as the candidate, the embodiment of the present invention determines the candidate from at least one second word group result according to the judgment result corresponding to the first word group result. Since the embodiment of the present invention can present more word group results to the user in the form of candidate items, it can increase the possibility that the candidate items meet the user's input needs, thereby improving the user's input efficiency.

[0077] Furthermore, the embodiments of the present invention can distinguish between word-replacement word-grouping scenarios and non-word-replacement word-grouping scenarios based on the judgment results. In this way, candidate items can be determined from the second word-grouping results in a targeted manner based on the distinguished word-grouping scenarios, thereby improving the accuracy of the word-grouping results that serve as candidate items.

[0078] Method Example 2

[0079] Reference Figure 2 , shows a flow chart of the steps of Embodiment 2 of an input method of the present invention, which may specifically include the following steps:

[0080] Step 201, obtaining multiple word group results corresponding to the input string and sorting them; the corresponding sorted results specifically include: a first word group result ranked first, and at least one second word group result ranked not first;

[0081] Step 202: If the first word group result includes the first word in the preset word pair, determine whether to use the second word group result as a candidate item based on word difference information between the first word group result and the second word group result.

[0082] In this embodiment, when the first word grouping result includes the first word in a preset word pair, it can be considered to be applied to a word grouping scenario of word replacement.

[0083] In the word combination scenario of word replacement, candidates for replacing the first word can be found from the second word combination result based on the word difference information between the first word combination result and the second word combination result, thereby enabling the expansion of similar expressions of the first word combination result.

[0084] For example, the word combination results corresponding to the input string A "jiaotayiqiguolaiba" include: the first word combination result "叫他一起过来吧" (Ask him to come over together), and the second word combination results "叫他一起过来爸" (Ask him to come over together, dad), "叫她一起过来吧" (Ask her to come over together), "教她一期过来爸" (Teach her to come over together, dad), etc.

[0085] In specific implementation, the words included in the first word combination result and the second word combination result can be compared to obtain the word difference information. It should be noted that in the case where the first word combination result and the second word combination result have the same segmentation result, the number of words they include can be the same; in the case where the first word combination result and the second word combination result have different segmentation results, the number of words they include can be the same or different.

[0086] The word difference information can include: the word positions, and the words corresponding to the word positions respectively. For example, the word difference information between the first word combination result "叫他一起过来吧" (Ask him to come over together) and the second word combination result "叫他一起过来爸" (Ask him to come over together, dad) includes: "吧" (ba) and "爸" (dad) corresponding to the last positions respectively. Another example, the word difference information between the first word combination result "叫他一起过来吧" (Ask him to come over together) and the second word combination result "叫她一起过来吧" (Ask her to come over together) includes: "他" (him) and "她" (her) corresponding to the second position from the left respectively.

[0087] In an embodiment of the present invention, if the word difference information includes: the replacement difference between the first word and the second word, then the second word combination result is used as a candidate; the first word and the second word match a preset word pair, and the position of the first word in the first word combination result matches the position of the second word in the second word combination result.

[0088] The replacement difference between the first word and the second word can represent that the first word and the second word correspond to the same position in their respective word combination results, and the first word and the second word match a preset word pair. In this case, using the second word combination result as a candidate can expand the similar expression of the first word combination result based on the second word combination result.

[0089] For the first word combination result "叫他一起过来吧" (Ask him to come over together) and the second word combination result "叫她一起过来吧" (Ask her to come over together), there is a replacement difference between "他" (him) and "她" (her) at the second position from the left. Since "他" (him) and "她" (her) can match a preset word pair, therefore, the second word combination result "叫她一起过来吧" (Ask her to come over together) can be used as a candidate.

[0090] In another embodiment of the present invention, in addition to considering word difference information, score difference information may also be considered to avoid using the second group of word results with too low scores as candidate items, thereby improving the quality of the candidate items.

[0091] Accordingly, the above step 202 may specifically include: if the word difference information includes: the replacement difference between the first word and the second word, and the score difference information between the first word group result and the second word group result is less than a first threshold, then the second word group result is used as a candidate.

[0092] The first threshold value may be determined by those skilled in the art according to actual application requirements. For example, the first threshold value may be determined based on information about a preset word pair corresponding to the first word and the second word.

[0093] The information of the preset word pair may include: word frequency. The word frequency of the preset word pair may include: the average of the word frequency of the first word and the word frequency of the second word, or the smaller of the word frequency of the first word and the word frequency of the second word. Generally, the higher the word frequency of the preset word pair, the lower the first threshold. It can be understood that the embodiment of the present invention does not limit the specific first threshold and its determination method.

[0094] In summary, the input method of the embodiment of the present invention, in the word grouping scenario of word replacement, can find a candidate item that can replace the first word from the second word grouping result based on the word difference information between the first word grouping result and the second word grouping result, thereby achieving the expansion of similar expressions of the first word grouping result.

[0095] Method Example 3

[0096] Reference Figure 3 , shows a flow chart of the steps of Embodiment 3 of an input method of the present invention, which may specifically include the following steps:

[0097] Step 301, obtaining multiple word grouping results corresponding to the input string and sorting them; the corresponding sorting results specifically include: a first word grouping result ranked first, and at least one second word grouping result ranked not first;

[0098] Step 302: If the first word group result does not include the first word in the preset word pair, determine whether to use the second word group result as a candidate item based on the connection information of the words included in the second word group result.

[0099] In the case where the first word grouping result does not include the first word in the preset word pair, this embodiment can be considered to be applied to the word grouping scenario of non-word replacement. In this case, the candidate items can be determined from the second word grouping result based on the quality requirements for the word grouping results in this field. The word grouping result includes the connection information of the words, which is a quality indicator of the word grouping result, which can reflect the collocation relationship of the words included in the word grouping result. The embodiment of the present invention determines whether to use the second word grouping result as a candidate item based on the connection information of the words included in the second word grouping result, and can use the second word grouping result with a stronger collocation relationship as a candidate item, thereby improving the quality of the word grouping result as a candidate item.

[0100] The embodiment of the present invention may provide the following technical solution for determining whether to use the second word group result as a candidate item according to the connection information of the words included in the second word group result:

[0101] Technical solution 1,

[0102] In technical solution 1, the connection difference information between the first connection information of the words included in the first word group result and the second connection information of the words included in the second word group result can be determined; based on the connection difference information, it is determined whether to use the second word group result as a candidate.

[0103] In a specific implementation, the method for determining the connection information may include: performing a second fusion on the probabilities of adjacent word pairs in the word grouping result, and determining that the word grouping result includes the connection information of the words based on the second fusion result. According to the above method for determining the connection information, the first connection information and the second connection information may be determined.

[0104] The embodiment of the present invention can determine, according to actual application requirements, the connection difference conditions that the connection difference information needs to satisfy when the second word group result is used as a candidate item.

[0105] For example, the connection difference condition may include: the second connection value corresponding to the second connection information is not less than the first connection value corresponding to the first connection information. In this case, the collocation relationship of the words included in the second group of words is not weaker than the collocation relationship of the words included in the first group of words. Therefore, the second group of words can be used as a candidate.

[0106] Technical Solution 2

[0107] In technical solution 2, whether to use the second word group result as a candidate can be determined based on the connection information between the left word and the right word in the second word group result. The connection information between the left word and the right word can include: connection information between non-adjacent word pairs, and connection information between adjacent word pairs. Since the connection information between the left word and the right word can constrain the connection information of more words in the second word group result, technical solution 2 can enhance the collocation relationship of the words included in the second word group result as a candidate.

[0108] In a specific implementation, the right-side words may include: the last word, and the left-side words may include: the words before the last word in the second group of word results.

[0109] The embodiment of the present invention can determine, based on actual application requirements, the left-right connection conditions that the connection information between the left-hand word and the right-hand word needs to satisfy when the second word group result is used as a candidate item.

[0110] For example, the left and right connection conditions may include: the last word in the second group of word results has a connection relationship with other words. In this case, taking the second group of word results as candidates can enhance the collocation relationship of the words included in the second group of word results as candidates.

[0111] The connection relationship between the last word and other words may include: the connection probability between the last word and other words exceeds the probability threshold. In practical applications, the connection probability between any two words can be determined based on the language model. The language model may include: a multi-relation language model, and / or a long-distance language model, etc. Among them, the multi-relation language model can describe the connection probability between adjacent word pairs. The long-distance language model can describe the connection probability between any two words. In other words, no matter whether the two words are adjacent, the long-distance language model can give the connection probability between the two words.

[0112] The above technical solutions 1 and 2 have introduced in detail the process of determining whether to use the second group of word results as candidate items based on the connection information of the words included in the second group of word results. It can be understood that those skilled in the art can adopt any one or a combination of technical solutions 1 and 2 according to actual application requirements.

[0113] For example, the score difference information between the first group of word results and the second group of word results can be used. If the score difference information is less than the second threshold, technical solution 1 can be adopted. Alternatively, if the score difference information is between the second threshold and the third threshold, technical solution 2 can be adopted, wherein the second threshold can be less than the third threshold.

[0114] For example, the word group results corresponding to the input string B "xianzaishiyizhounian" include: the first word group result "now is the first anniversary", and the second word group results "now is the eleventh anniversary", "now is the first anniversary", etc. Assuming that the score difference information between the second word group result "now is the eleventh anniversary" and the first word group result "now is the first anniversary" is between the second threshold and the third threshold, technical solution 2 can be adopted. Since "now" and "anniversary" have a connection relationship, and "eleven" and "anniversary" have a connection relationship, the second word group result "now is the eleventh anniversary" can be used as a candidate.

[0115] In summary, the input method of the embodiment of the present invention can be considered to be applied to the word grouping scenario of non-word replacement when the above-mentioned first word grouping result does not include the first word in the preset word pair. In this case, the candidate items are determined from the second word grouping result based on the word grouping result including the connection information of the words. Since the word grouping result includes the connection information of the words, which is a quality indicator of the word grouping result, it can reflect the collocation relationship of the words included in the word grouping result. The embodiment of the present invention determines whether to use the above-mentioned second word grouping result as a candidate item based on the above-mentioned second word grouping result including the connection information of the words, and can use the second word grouping result with a stronger collocation relationship as a candidate item, thereby improving the quality of the word grouping result as a candidate item.

[0116] It should be noted that, for the method embodiments, for the sake of simplicity of description, they are all described as a series of motion action combinations, but those skilled in the art should know that the embodiments of the present invention are not limited by the order of the described motion actions, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the motion actions involved are not necessarily required by the embodiments of the present invention.

[0117] Device Embodiment

[0118] Reference Figure 4 , shows a structural block diagram of an input device embodiment of the present invention, which may specifically include: an acquisition and sorting module 401 and a candidate item determination module 402.

[0119] The acquisition and sorting module 401 is used to acquire and sort multiple word grouping results corresponding to the input string; the corresponding sorting results include: a first word grouping result ranked first, and at least one second word grouping result not ranked first.

[0120] The candidate item determination module 402 is used to determine a candidate item from the at least one second word group result according to a judgment result corresponding to the first word group result; the judgment result corresponds to: whether the first word group result includes the first word in the preset word pair.

[0121] Optionally, the candidate item determination module 402 may include:

[0122] The first candidate item determination module is used to determine whether to use the second word group result as a candidate item according to the word difference information between the first word group result and the second word group result when the judgment result is yes; or

[0123] The second candidate item determination module is used to determine whether to use the second word group result as a candidate item based on the connection information of the words that the second word group result may include when the judgment result is no.

[0124] Optionally, the first candidate item determination module may include:

[0125] A replacement difference processing module is used to use the second word group result as a candidate item when the above-mentioned word difference information may include: the replacement difference between the first word and the second word; the above-mentioned first word and the above-mentioned second word hit a preset word pair, and the position of the above-mentioned first word in the above-mentioned first word group result matches the position of the above-mentioned second word in the above-mentioned second word group result.

[0126] Optionally, the above-mentioned replacement difference processing module is specifically used to use the above-mentioned second group of word results as candidates when the above-mentioned word difference information may include: the replacement difference between the first word and the second word, and the score difference information between the above-mentioned first group of word results and the above-mentioned second group of word results is less than a first threshold.

[0127] Optionally, the second candidate item determination module may include:

[0128] A connection difference information determination module, used to determine connection difference information between the connection information of the words that the first word group result can include and the connection information of the words that the second word group result can include;

[0129] The first connection processing module is used to determine whether to use the second word group result as a candidate item according to the connection difference information.

[0130] Optionally, the second candidate item determination module may include:

[0131] The second connection processing module is used to determine whether to use the second word group result as a candidate item based on the connection information between the left word and the right word in the second word group result.

[0132] Optionally, the connection processing module is specifically used to use the second word group result as a candidate item when the last word in the second word group result has a connection relationship with other words. The other words may include: words in the second word group result that are located before the last word.

[0133] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0134] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0135] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0136] Figure 5 1 is a block diagram of a device 900 for input according to an exemplary embodiment. For example, the device 900 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0137] Reference Figure 5 , the device 900 may include one or more of the following components: a processing component 902 , a memory 904 , a power component 906 , a multimedia component 908 , an audio component 910 , an input / output (I / O) interface 912 , a sensor component 914 , and a communication component 916 .

[0138] The processing component 902 generally controls the overall operation of the device 900, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 902 may include one or more processors 920 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 902 may include one or more modules to facilitate the interaction between the processing component 902 and other components. For example, the processing component 902 may include a multimedia module to facilitate the interaction between the multimedia component 908 and the processing component 902.

[0139] The memory 904 is configured to store various types of data to support operations on the device 900. Examples of such data include instructions for any application or method operating on the device 900, contact data, phone book data, messages, pictures, videos, etc. The memory 904 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, 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 disk or optical disk.

[0140] The power supply component 906 provides power to the various components of the device 900. The power supply component 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.

[0141] The multimedia component 908 includes a screen that provides an output interface between the device 900 and the 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 input signals from the 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 boundaries of the 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 camera and / or a rear camera. When the device 900 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0142] The audio component 910 is configured to output and / or input audio signals. For example, the audio component 910 includes a microphone (MIC), and when the device 900 is in an operating mode, such as a call mode, a recording mode, and a speech recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 904 or sent via the communication component 916. In some embodiments, the audio component 910 also includes a speaker for outputting audio signals.

[0143] I / O interface 912 provides an interface between processing component 902 and peripheral interface modules, such as 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.

[0144] The sensor assembly 914 includes one or more sensors for providing various aspects of status assessment for the device 900. For example, the sensor assembly 914 can detect the open / closed state of the device 900, the relative positioning of components, such as the display and keypad of the device 900, and the sensor assembly 914 can also detect the position change of the device 900 or a component of the device 900, the presence or absence of user contact with the device 900, the orientation or acceleration / deceleration of the device 900, and the temperature change of the device 900. The sensor assembly 914 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 914 may also include an optical 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 accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0145] The communication component 916 is configured to facilitate wired or wireless communication between the device 900 and other devices. The device 900 can 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-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 916 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0146] 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, microcontrollers, microprocessors, or other electronic components to perform the above method.

[0147] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 904 including instructions, and the instructions can be executed by the processor 920 of the device 900 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0148] A non-temporary computer-readable storage medium, when the instructions in the storage medium are executed by the processor of a terminal, enables the terminal to execute an input method, the method comprising: obtaining multiple word group results corresponding to an input string and sorting them; the corresponding sorting results include: a first word group result ranked first, and at least one second word group result ranked not first; based on a judgment result corresponding to the first word group result, determining a candidate item from the at least one second word group result; the judgment result corresponds to: whether the first word group result contains the first word in a preset word pair.

[0149] Figure 6 1 is a schematic diagram of the structure of the server in some embodiments of the present invention. The server 1900 may have relatively large differences due to different configurations or performances, and may include one or more central processing units (CPU) 1922 (for example, one or more processors) and memory 1932, and one or more storage media 1930 (for example, one or more mass storage devices) storing application programs 1942 or data 1944. Among them, the memory 1932 and the storage medium 1930 can be short-term storage or permanent storage. The program stored in the storage medium 1930 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations on the server. Furthermore, the central processing unit 1922 can be configured to communicate with the storage medium 1930 and execute a series of instruction operations in the storage medium 1930 on the server 1900.

[0150] 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 and output interfaces 1958, one or more keyboards 1956, and / or one or more operating systems 1941, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.

[0151] The embodiment of the present invention discloses A1, an input method, comprising:

[0152] Acquire multiple word group results corresponding to the input string and sort them; the corresponding sorted results include: a first word group result ranked first, and at least one second word group result ranked not first;

[0153] According to the judgment result corresponding to the first word group result, a candidate item is determined from the at least one second word group result; the judgment result corresponds to: whether the first word group result includes the first word in the preset word pair.

[0154] A2. The method according to A1, wherein determining a candidate item from the at least one second word group result comprises:

[0155] If the judgment result is yes, then judging whether to use the second word group result as a candidate item according to the word difference information between the first word group result and the second word group result; or

[0156] If the judgment result is no, then judging whether to use the second word group result as a candidate item is based on the connection information of the words included in the second word group result.

[0157] A3. According to the method described in A2, judging whether to use the second word group result as a candidate item based on the word difference information between the first word group result and the second word group result includes:

[0158] If the word difference information includes: the replacement difference between the first word and the second word, the second word group result is used as a candidate; the first word and the second word hit a preset word pair, and the position of the first word in the first word group result matches the position of the second word in the second word group result.

[0159] A4. The method according to A3, wherein if the word difference information includes: a replacement difference between the first word and the second word, then taking the second word group result as a candidate, comprises:

[0160] If the word difference information includes: a replacement difference between a first word and a second word, and the score difference information between the first word group result and the second word group result is less than a first threshold, the second word group result is used as a candidate.

[0161] A5. The method according to A2, wherein judging whether to use the second word group result as a candidate item based on the connection information of the words included in the second word group result comprises:

[0162] Determine connection difference information between connection information of words included in the first word group result and connection information of words included in the second word group result;

[0163] According to the connection difference information, it is determined whether to use the second word group result as a candidate item.

[0164] A6. The method according to A2, wherein judging whether to use the second word group result as a candidate item based on the connection information of the words included in the second word group result comprises:

[0165] Based on the connection information between the left-hand word and the right-hand word in the second word group result, it is determined whether to use the second word group result as a candidate item.

[0166] A7. The method according to A6, wherein judging whether to use the second word group result as a candidate item based on the connection information between the left word and the right word in the second word group result comprises:

[0167] If the last word in the second word group result has a connection relationship with other words, the second word group result is used as a candidate, and the other words include: the words in the second word group result that are located before the last word.

[0168] The embodiment of the present invention discloses B8, an input device, comprising:

[0169] An acquisition and sorting module is used to acquire and sort multiple word grouping results corresponding to the input string; the corresponding sorting results include: a first word grouping result ranked first, and at least one second word grouping result ranked not first; and

[0170] A candidate item determination module is used to determine a candidate item from the at least one second word group result based on a judgment result corresponding to the first word group result; the judgment result corresponds to: whether the first word group result includes the first word in the preset word pair.

[0171] B9. According to the device described in B8, the candidate item determination module includes:

[0172] A first candidate item determination module is configured to determine whether to use the second word group result as a candidate item according to word difference information between the first word group result and the second word group result when the judgment result is yes; or

[0173] The second candidate item determination module is used to determine whether to use the second word group result as a candidate item according to the connection information of the words included in the second word group result when the judgment result is no.

[0174] B10. According to the apparatus described in B9, the first candidate item determination module comprises:

[0175] A replacement difference processing module is used to use the second group of word results as a candidate item when the word difference information includes: the replacement difference between the first word and the second word; the first word and the second word hit a preset word pair, and the position of the first word in the first group of word results matches the position of the second word in the second group of word results.

[0176] B11. According to the device described in B10, the replacement difference processing module is specifically used to use the second group of word results as a candidate item when the word difference information includes: the replacement difference between the first word and the second word, and the score difference information between the first group of word results and the second group of word results is less than a first threshold.

[0177] B12. According to the apparatus described in B9, the second candidate item determination module comprises:

[0178] A connection difference information determination module, used to determine connection difference information between connection information of words included in the first word group result and connection information of words included in the second word group result;

[0179] The first connection processing module is used to determine whether to use the second word group result as a candidate item according to the connection difference information.

[0180] B13. According to the apparatus described in B9, the second candidate item determination module comprises:

[0181] The second connection processing module is used to determine whether to use the second word group result as a candidate item according to the connection information between the left word and the right word in the second word group result.

[0182] B14. According to the device described in B13, the connection processing module is specifically used to use the second word group result as a candidate item when the last word in the second word group result has a connection relationship with other words, and the other words include: words in the second word group result that are located before the last word.

[0183] The embodiment of the present invention discloses C15, a device for input, comprising a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors, wherein the one or more programs include instructions for performing the following operations:

[0184] Acquire multiple word group results corresponding to the input string and sort them; the corresponding sorted results include: a first word group result ranked first, and at least one second word group result ranked not first;

[0185] According to the judgment result corresponding to the first word group result, a candidate item is determined from the at least one second word group result; the judgment result corresponds to: whether the first word group result includes the first word in the preset word pair.

[0186] C16. According to the apparatus of C15, determining a candidate item from the at least one second word group result comprises:

[0187] If the judgment result is yes, then judging whether to use the second word group result as a candidate item according to the word difference information between the first word group result and the second word group result; or

[0188] If the judgment result is no, then judging whether to use the second word group result as a candidate item is based on the connection information of the words included in the second word group result.

[0189] C17. According to the device described in C16, the determining whether to use the second word group result as a candidate item based on the word difference information between the first word group result and the second word group result comprises:

[0190] If the word difference information includes: the replacement difference between the first word and the second word, the second word group result is used as a candidate; the first word and the second word hit a preset word pair, and the position of the first word in the first word group result matches the position of the second word in the second word group result.

[0191] C18. The device according to C17, wherein if the word difference information includes: a replacement difference between the first word and the second word, the second word group result is used as a candidate, comprising:

[0192] If the word difference information includes: a replacement difference between a first word and a second word, and the score difference information between the first word group result and the second word group result is less than a first threshold, the second word group result is used as a candidate.

[0193] C19. According to the apparatus described in C16, the step of determining whether to use the second word group result as a candidate item based on the connection information of words included in the second word group result comprises:

[0194] Determine connection difference information between connection information of words included in the first word group result and connection information of words included in the second word group result;

[0195] According to the connection difference information, it is determined whether to use the second word group result as a candidate item.

[0196] C20. According to the apparatus described in C16, judging whether to use the second word group result as a candidate item based on the connection information of words included in the second word group result comprises:

[0197] Based on the connection information between the left-hand word and the right-hand word in the second word group result, it is determined whether to use the second word group result as a candidate item.

[0198] C21. According to the apparatus described in C20, the step of determining whether to use the second word group result as a candidate item based on the connection information between the left word and the right word in the second word group result comprises:

[0199] If the last word in the second word group result has a connection relationship with other words, the second word group result is used as a candidate, and the other words include: the words in the second word group result that are located before the last word.

[0200] The embodiment of the present invention discloses D22, one or more machine-readable media having instructions stored thereon, which, when executed by one or more processors, enable the device to execute one or more of the methods described in A1 to A7.

[0201] Those skilled in the art will readily appreciate other embodiments of the invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art that are not disclosed in this disclosure. The description and examples are to be considered exemplary only, and the true scope and spirit of the present invention are indicated by the following claims.

[0202] It should be understood that the present invention is not limited to the exact construction that has been 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 present invention is limited only by the appended claims.

[0203] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

[0204] The above is a detailed introduction to an input method, an input device, a device for input, and a machine-readable medium provided by the present invention. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for a person skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. An input method, characterized in that: include: Get multiple word group results corresponding to the input string and sort them; The corresponding sorting results include: a first group of word results ranked first, and at least one second group of word results ranked not first; Determine a candidate item from the at least one second word group result according to a judgment result corresponding to the first word group result; the judgment result corresponds to: whether the first word group result includes the first word in the preset word pair; Wherein, determining a candidate item from the at least one second word group result according to the judgment result corresponding to the first word group result includes: If the judgment result is yes, then judging whether to use the second word group result as a candidate item according to the word difference information between the first word group result and the second word group result; or, If the judgment result is no, then judging whether to use the second word group result as a candidate item according to the connection information of the words included in the second word group result.

2. The method according to claim 1, characterized in that The step of judging whether to use the second word group result as a candidate item according to the word difference information between the first word group result and the second word group result includes: If the word difference information includes: the replacement difference between the first word and the second word, the second word group result is used as a candidate; the first word and the second word hit a preset word pair, and the position of the first word in the first word group result matches the position of the second word in the second word group result.

3. The method according to claim 2, characterized in that If the word difference information includes: the replacement difference between the first word and the second word, then taking the second word group result as a candidate, including: If the word difference information includes: a replacement difference between a first word and a second word, and the score difference information between the first word group result and the second word group result is less than a first threshold, the second word group result is used as a candidate.

4. The method according to claim 1, characterized in that The step of judging whether to use the second word group result as a candidate item according to the connection information of the words included in the second word group result includes: Determine connection difference information between connection information of words included in the first word group result and connection information of words included in the second word group result; According to the connection difference information, it is determined whether to use the second word group result as a candidate item.

5. The method according to claim 1, characterized in that The step of judging whether to use the second word group result as a candidate item according to the connection information of the words included in the second word group result includes: Based on the connection information between the left-hand word and the right-hand word in the second word group result, it is determined whether to use the second word group result as a candidate item.

6. The method according to claim 5, characterized in that The step of judging whether to use the second word group result as a candidate item according to the connection information between the left word and the right word in the second word group result includes: If the last word in the second word group result has a connection relationship with other words, the second word group result is used as a candidate, and the other words include: the words in the second word group result that are located before the last word.

7. An input device, characterized in that: include: An acquisition and sorting module is used to acquire and sort multiple word grouping results corresponding to the input string; The corresponding sorting results include: a first group of word results ranked first, and at least one second group of word results ranked not first; and A candidate item determination module, configured to determine a candidate item from the at least one second word group result according to a judgment result corresponding to the first word group result; the judgment result corresponds to: whether the first word group result includes the first word in the preset word pair; Wherein, the candidate item determination module includes: A first candidate item determination module is configured to determine whether to use the second word group result as a candidate item according to word difference information between the first word group result and the second word group result when the judgment result is yes; or The second candidate item determination module is used to determine whether to use the second word group result as a candidate item according to the connection information of the words included in the second word group result when the judgment result is no.

8. A device for input, characterized in that The system comprises a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors, wherein the one or more programs include instructions for performing the following operations: Acquire multiple word group results corresponding to the input string and sort them; the corresponding sorted results include: a first word group result ranked first, and at least one second word group result ranked not first; Determine a candidate item from the at least one second word group result according to a judgment result corresponding to the first word group result; the judgment result corresponds to: whether the first word group result includes the first word in the preset word pair; Wherein, determining a candidate item from the at least one second word group result according to the judgment result corresponding to the first word group result includes: If the judgment result is yes, then judging whether to use the second word group result as a candidate item according to the word difference information between the first word group result and the second word group result; or, If the judgment result is no, then judging whether to use the second word group result as a candidate item according to the connection information of the words included in the second word group result.

9. A machine-readable medium, characterized in that Instructions are stored thereon which, when executed by one or more processors, cause the apparatus to perform the method as claimed in one or more of claims 1 to 6.