Input method, input device and electronic device for korean language

Abstract

The application discloses a Korean input method, an input device and an electronic device, and relates to the technical field of input methods. The Korean input method comprises the following steps: obtaining a Korean character input by a user; performing single-character processing on the Korean character based on the input sequence of the Korean character, determining combinations capable of forming a single character and characters incapable of forming a single character; directly decoding the combinations capable of forming a single character into single characters, and performing a completion operation based on the single characters and / or the characters incapable of forming a single character to obtain new candidate words and / or candidate characters. The application firstly establishes a Korean basic term model, performs character forming processing on Korean characters through a Korean maximum combination algorithm, expands single characters into word groups through the Korean basic term model, expands Korean characters into Korean single characters, and trains the Korean basic term model according to the last selection of a user, thereby providing more suitable expansion results for the user and improving input efficiency during input.

Description

Technical Field

[0001] This invention relates to the field of information input technology, and in particular to a Korean language input method, input device, and electronic device. Background Technology

[0002] As the development of multilingual input methods accelerates, major input method manufacturers are racing to develop multilingual input methods to win over multilingual users. However, Korean input methods still primarily rely on conventional character-based rule tree construction to trigger single-character decoding. This approach cannot accurately and quickly decode diverse results for users to choose from, resulting in low typing efficiency. Summary of the Invention

[0003] The main technical problem solved by this invention is to provide a Korean input method, input device, and electronic device that can provide a variety of results for users to choose from, thereby improving input efficiency.

[0004] To solve the above-mentioned technical problems, the first technical solution adopted by the present invention is: to provide a Korean input method, the method comprising: acquiring Korean characters input by a user; converting the Korean characters into single characters based on the input order of the Korean characters, determining combinations that can form single characters and characters that cannot form single characters; directly decoding the combinations that can form single characters into single characters; and performing a completion operation based on the single characters and / or the characters that cannot form single characters to obtain new candidate words and / or candidate characters.

[0005] The step of converting Korean characters into single characters based on the input order of the Korean characters, and determining the combinations that can form single characters and the characters that cannot form single characters, includes: The input order of the obtained Korean characters is used to segment the Korean characters into Korean character groups; Based on the segmented Korean character groups, the Korean character group ranked first is combined into characters according to the Korean maximum combination algorithm; If the Korean character group contains characters that cannot form a single character, and there are still Korean characters that have not been combined into characters, all Korean characters that have not been combined into characters are further segmented and combined into characters again according to the maximum single character rule; Identify all combinations that can form words and the single characters that cannot.

[0006] The step of combining the top-ranked Korean character group into characters using the Korean maximum combination algorithm, based on the segmented Korean character groups, includes: The Korean character groups are combined into characters using at least one of the following rules: “FYYSS”, “FYYS”, “FYY / FYS”, and “FY”; where “F” represents a consonant, “Y” represents a vowel, and “S” represents a final consonant.

[0007] The step of combining the Korean character groups into characters using at least one of the rules “FYYSS”, “FYYS”, “FYY / FYS”, and “FY” includes: Determine if the given Korean character set can be formed into a character using "FYYSS". If it can, check if the next character is "Y". If it is "Y", remove the last character from the Korean character set and generate a new Korean character set. If it is not "Y", then it can be formed into a character using "FYYSS". Determine whether the new Korean character group can form a character using "FYYS". If it can form a character, determine whether the next character is "Y". If it is "Y", remove the last character of the new Korean character group and update the Korean character group. If it is not "Y", it can form a character using "FYYS". Determine if the updated Korean character set can form a character using "FYY / FYS". If it can, check if the next character is "Y". If it is "Y", remove the last character from the updated Korean character set and update the Korean character set again. If it cannot form a character, check if it can form a character using "FY". If it cannot form a character using "FY", save the first character in the Korean character set.

[0008] The steps of directly decoding the combinations that can form single characters into single characters, and performing a completion operation based on the single characters and / or the characters that cannot form single characters to obtain new candidate words and / or candidate characters, include: Obtain the combinations that make up individual characters, and calculate the index of the combinations of individual characters according to the single-character combination algorithm to obtain the index number; Find the corresponding single character based on the index number; A completion operation is performed based on the single character and / or the characters that cannot form a single character to obtain new candidate words and / or candidate characters.

[0009] The step of obtaining the combination of constituent characters, and calculating the index of the combination of constituent characters according to the single-character synthesis algorithm to obtain the index number includes: The index number is obtained by multiplying the total number of consonants, vowels, and final consonants in a character by the corresponding index positions of the consonants and vowels, and adding the index position of the final consonant to the default number of characters.

[0010] The step of performing a completion operation based on the single character and / or the characters that cannot form a single character to obtain new candidate words and / or candidate characters includes: By expanding and processing determined single characters and / or non-single characters in Korean through the basic Korean vocabulary model, various Korean phrases and / or single characters are obtained; After selecting the target Korean phrase and / or single character, the Korean basic vocabulary model records the processing results; The Korean basic vocabulary model is trained based on the processing results to obtain the trained Korean basic vocabulary model.

[0011] Prior to the step of obtaining the Korean characters input by the user, the following steps are included: Collect corpora, construct a basic Korean vocabulary model and verify it. If the corpora are found to be erroneous, they are removed from the basic Korean vocabulary model.

[0012] To solve the above-mentioned technical problems, the second technical solution adopted by the present invention is to provide an electronic device, including a processor and a memory, wherein the processor is configured with a Korean input method as described in any one of the first technical solutions.

[0013] To solve the above-mentioned technical problems, the third technical solution adopted by the present invention is: to provide an input device, comprising: a receiving module for acquiring Korean characters input by a user; a segmentation module for segmenting the Korean characters into multiple Korean character groups; a decoding module for decoding the Korean character groups that can form single characters to obtain Korean single characters; and a completion module for expanding the obtained Korean single characters to obtain more types of Korean word groups.

[0014] The above solution first establishes a basic Korean vocabulary model, obtains Korean characters, processes them into characters using the Korean maximum synthesis algorithm, expands single characters into phrases and Korean characters into single Korean characters using the basic Korean vocabulary model, and trains the basic Korean vocabulary model based on the user's final selection, thereby providing more suitable expansion results for the user and improving the user's input efficiency. Attached Figure Description

[0015] Figure 1 This is a flowchart of the first embodiment of the Korean input method of this application; Figure 2 This is a flowchart of the second embodiment of the Korean input method of this application; Figure 3 This is a partial expanded result diagram of the Korean basic vocabulary model in the second embodiment of the Korean input method of this application; Figure 4 This is a diagram of the final candidate results in the Korean basic vocabulary model in the second embodiment of the Korean input method of this application; Figure 5 This is a schematic diagram of the structure of an embodiment of the electronic device of this application; Figure 6 This is a schematic diagram of the structure of an embodiment of the input device of this application. Detailed Implementation

[0016] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0017] If the technical solution of this application involves personal information, the product using this technical solution has clearly informed the user of the personal information processing rules and obtained the user's voluntary consent before processing the personal information. If the technical solution of this application involves sensitive personal information, the product using this technical solution has obtained the user's separate consent before processing the sensitive personal information, and also meets the requirement of "express consent". For example, at personal information collection devices such as cameras, clear and prominent signs are set up to inform users that they have entered the scope of personal information collection and that personal information will be collected. If an individual voluntarily enters the collection scope, it is deemed that they have agreed to the collection of their personal information; or on the personal information processing device, with clear signs / information informing users of the personal information processing rules, authorization is obtained from the individual through pop-up information or by asking the individual to upload their personal information; wherein, the personal information processing rules may include information such as the personal information processor, the purpose of personal information processing, the processing method, and the types of personal information processed.

[0018] Please see Figure 1 , Figure 1 This is a flowchart of the first embodiment of the Korean input method of the present invention. It should be noted that if substantially the same result is obtained, the method of the present invention is not necessarily identical. Figure 1 The illustrated process sequence is limited. For example... Figure 1 As shown, the method includes the following steps: S101: Obtain the Korean characters input by the user.

[0019] In this embodiment, the customer inputs Korean characters on a keyboard, such as a mobile phone, tablet, or laptop. Then, the user inputs one or more Korean characters.

[0020] S102: Based on the input order of the Korean characters, the Korean characters are converted into single characters to determine the combinations that can form single characters and the characters that cannot form single characters.

[0021] In this embodiment, the acquired Korean characters are sorted in the order they were acquired, and then the sorted Korean characters are processed to form characters, turning a string of characters into one or more single characters, thereby obtaining single characters and characters that could not form characters.

[0022] S103: Directly decode the combinations that can form single characters into single characters, and perform a completion operation based on the single characters and / or the characters that cannot form single characters to obtain new candidate words and / or candidate characters.

[0023] In this embodiment, character combinations that can form words are transcoded to output the resulting single characters, and the formed single characters can be completed. For example, if a user needs to input a phrase, after inputting the first character, the phrase can be completed to obtain the desired phrase, thus reducing the number of characters input. When a user is about to input a single character, and has input the first character of that character, since characters that are not yet formed can be completed to form a single character, the user has a chance to obtain the desired single character when inputting the first character.

[0024] By completing Korean words and characters, more candidate results can be provided to users, expanding their choices during the input process and saving input time. Furthermore, the system can analyze users' input habits to ensure that the expanded phrases and words match the words the user wants to input, thereby further saving input time and improving typing efficiency.

[0025] Please see Figure 2 , Figure 2 This is a flowchart of the second embodiment of the Korean input method of the present invention. It should be noted that if substantially the same result is achieved, the method of the present invention is not necessarily identical. Figure 2 The illustrated process sequence is limited. For example... Figure 2 As shown, the method includes the following steps: S201: Collect corpus data, construct a basic Korean vocabulary model and verify it. If the verification shows that the corpus data is incorrect, remove it from the basic Korean vocabulary model.

[0026] In this embodiment, the first step is to establish a basic Korean vocabulary model and symbol table. The model contains various types of corpora collected from authoritative news articles and journals, as well as official forums and other web pages. Before being added to the model, each corpus must be checked against an authoritative Korean dictionary to ensure its accuracy. If any corpus cannot be found in an authoritative Korean dictionary, it is recorded and periodically reviewed by Korean experts. Corpusulas with errors are removed from the model; only correct corpusulas are included.

[0027] S202: Obtain the Korean characters input by the user.

[0028] In this embodiment, step S202 is the same as step S101 in the previous embodiment, and will not be described again here.

[0029] S203: Obtain the input order of the Korean characters, and segment the Korean characters to obtain Korean character groups.

[0030] In this embodiment, the obtained Korean characters are sorted according to their order. After the sorting is completed, the Korean characters are segmented into multiple Korean character groups. Starting from the first character in the sorting, five Korean characters are formed into a Korean character group. If there are fewer than five Korean characters, they are still formed into one Korean character group. Segmenting the Korean characters into Korean character groups facilitates subsequent character grouping and analysis.

[0031] S204: Based on the segmented Korean character groups, the Korean character group ranked first is combined into characters according to the Korean maximum combination algorithm.

[0032] In this embodiment, the segmented Korean character groups will be combined into characters according to the maximum combination algorithm, which includes the four major Korean character formation rules.

[0033] Specifically, based on the characteristics of the composition and distribution of Korean characters, Korean is divided into three parts: consonants, vowels, and final consonants, with consonants being an essential part for forming characters. In this embodiment, consonants are marked with "F", vowels with "Y", and final consonants with "S". The four main character-forming rules are "FYYSS", "FYYS", "FYY / FYS", and "FY". Based on these four rules, Korean character groups are then combined to form characters.

[0034] The maximum synthesis algorithm, after acquiring the Korean character set, begins a loop-based judgment. If a matching character is found, the algorithm moves to the next character attribute. If no matching character is found, the last character of the Korean character set is removed, and the algorithm checks if it can form a complete character. Specifically, based on the four character formation rules, the algorithm checks if the first five Korean characters can form a character. If so, it checks if the sixth character is a vowel. If not, the character is formed; if it is, it's the same as if it cannot form a character, requiring the removal of the fifth character and continuing the judgment with the first four characters. The algorithm then checks if the first four characters can form a character. If so, it checks if the fifth character is a vowel. If not, the character is formed; if it is, it's the same as if it cannot form a character, requiring the removal of the fourth character and continuing the judgment with the first three characters. The process involves determining whether the first three Korean characters can be converted into a word. If not, the third character is removed, and the first two remaining characters are used for further analysis. If the conversion is possible, it's necessary to check if both the third and fourth characters are non-vowels. If neither is a vowel, the word can be formed. If not, the fourth character is further checked for consonants. If it is, the word can be formed; otherwise, the third character is removed, and the first two remaining characters are used for analysis. The process continues, again checking if the first two characters can form a word. If not, the second character is removed, and the first character is saved. When the number of characters in the Korean character set is less than five, the current number of characters is matched with the number of characters in the above analysis steps, and the process can proceed as described above.

[0035] For example, to obtain the input Korean character " (These are all phonetic characters in Korean, not actual characters and have no Chinese meaning), among which " , " is a consonant, “ is a vowel,” The final consonant is represented by the Korean character "FYSFYS". Taking the first five characters to form a Korean character group, it can be seen that the first five characters do not conform to the rule "FYYSS", and therefore cannot form a character. So the fifth character is removed and the Korean character group becomes "FYSF". It can be seen that this does not conform to the rule "FYYS" of the same number of characters, and therefore cannot form a character. So the fourth character is removed. The first three characters conform to the rule "FYS", and therefore the fourth character is determined to be a non-vowel, which can form a character.

[0036] S205: If the Korean character group contains characters that cannot form a single character, and there are still Korean characters that have not been combined into characters, then all the Korean characters that have not been combined into characters are further segmented and combined into characters again using the maximum combination algorithm.

[0037] In this embodiment, if a Korean character group has already formed a character, but there are still some characters in the Korean character group that have not formed a character, then it is necessary to re-segment the Korean characters that have not formed a character and those that have not yet been judged to form a character in the previous Korean character group, and then form a new Korean character group. After forming a new Korean character group, the Korean maximum synthesis algorithm is used again to judge whether the character has formed, until all Korean characters have been judged to form a character.

[0038] Specifically, the above input Korean characters " The first three characters have been formed into a single character, which originally belonged to the Korean character set. "Characters that do not form a single character need to be combined with the sixth character that is not in the Korean character group to form a new Korean character group, and then the character formation process is repeated until all characters have been included in the Korean character group and judged."

[0039] S206: Determine all combinations that can form a word and the single characters that cannot form a word.

[0040] In this embodiment, the above-mentioned input Korean character " Finally, it can be combined into two single characters. After determining all Korean characters to form words, all combinations that can form words and those that cannot are identified.

[0041] S207: Obtain the combination of individual characters, and calculate the index of the combination of individual characters according to the single-character synthesis algorithm to obtain the index number.

[0042] In this embodiment, there are 40 basic characters that make up a single Korean word: 19 consonants, 21 vowels, and 27 final consonants. Due to the special case of final consonants, when a word is composed only of consonants and vowels, and the vowel is the first character, the total number of final consonant indices needs to be increased by 1. Based on a calculation of 28 bits, one bit needs to be reserved in the final consonant position for calculation. Therefore, the consonant and final consonant parts are reused.

[0043] Among them, the consonants are " , , , , , , , , , , , , , , , , , , "A total of 19" The vowels are respectively " , , , , , , , , , , , , , , , , , , , , "A total of 21" The final sounds are respectively " , , , , , , , , , , , , , , , , , , , , , , , , , , There are 27 in total. (These are all Korean phonetic characters and have no specific Chinese meaning.) There are a total of 11,172 Korean characters. Of these, 399 are characters without a final consonant (formed using rule 4), and 10,773 are characters with a final consonant (formed using rules 1, 2, and 3). The index number is obtained by multiplying the total number of consonant, vowel, and final consonant characters in the formed character by the corresponding index positions of the consonants and vowels, and then adding the index position of the final consonant to the default character count.

[0044] Specifically, the formula for the single-character synthesis algorithm is as follows: Uid(i)=F(i)*Y(len)*S(len)+Y(i)*S(len)+S(i)+def(count) Here, "(i)" refers to the index of the character in the corresponding consonant, vowel, and final consonant array. Uid(i) determines the index of the Unicode code point for each character in the symbol table. "(len)" refers to the total number of characters in this class, and def(count) is the default number of characters. It can be seen that Korean characters are composed of Korean characters, and different Korean characters correspond to different indices. The index number of the constituent characters can be calculated using the character composition formula.

[0045] For example, first obtain the input Korean character " Entering three Korean characters that conform to the character formation rule "FYS" will form a character, and the decoded result is "". (meaning in Chinese: of) The index number of " is 10684. The character " "The character with index 18 in the consonant array..." "The character with index 0 in the vowel array" "It has an index of 4 in the receiver array. According to the single-word synthesis algorithm described above, Uid(" =18*21*28+ 0 * 28+ 4 + 96= 10684.

[0046] Korean characters " The decoding result is " (Chinese meaning: times) The index number of " is 4328. The character " "The character with index 7 in the consonant array..." "The character with index 21 in the vowel array..." "It has an index of 28 in the receiver array. According to the single-word synthesis algorithm described above, Uid(" =7*21*28+ 4 * 28+ 4 + 96= 4328.

[0047] S208: Find the corresponding single word based on the index number.

[0048] In this embodiment, the index number of the single character calculated using the single-character synthesis algorithm formula is used to find the specific location of the single character in the symbol table, thereby determining the single character. For example, using index number 10684, the decoding result can be the single character "". The decoding result, obtained from index number 4328, is the single character "". ".

[0049] S209: By expanding the defined single characters and / or non-single characters of Korean through the basic Korean vocabulary model, a variety of Korean phrases and / or single characters are obtained.

[0050] In this embodiment, since the Korean basic vocabulary model stores a large amount of corpus, the Korean basic glossary can serve as a foundation for expanding certain characters. By recognizing the confirmed characters, the vocabulary related to the confirmed characters in the Korean basic vocabulary model is provided to the user for analysis, and expansion is performed based on the currently input characters. Korean characters that are not yet characters can be expanded through the Korean basic vocabulary model to form characters, providing multiple characters for the user to choose from. By establishing the Korean vocabulary model, the efficiency of the input process is improved.

[0051] For example, after decoding, we get " (Chinese meaning: once) Please refer to this. Figure 3 , Figure 3 This is a partial expanded result diagram of the basic Korean vocabulary model in the second embodiment of the Korean input method of this application. It can be seen that when the user inputs the single character "..." Then, by completing and expanding the basic Korean language rack model, more Korean words can be selected, greatly expanding the customer's choices and improving the user's input efficiency.

[0052] S210: After selecting the target Korean phrase and / or single character, the Korean basic vocabulary model records the processing results.

[0053] In this embodiment, expanded Korean phrases and / or single Korean characters are provided for the user to select. The user selects the desired Korean phrases and / or single Korean characters. At this time, the basic Korean rack model will record the user's selection results and calculate the score of the corresponding phrase according to the frequency, which is beneficial for processing the same single character or characters that have not yet become single characters in the future.

[0054] S211: Based on the processing results, the Korean basic vocabulary model is trained to obtain the trained Korean basic vocabulary model.

[0055] In this embodiment, by continuously recording the processing results, the Korean basic vocabulary model performs frequency analysis on the processing results, thereby gaining a better understanding of the user's input habits. When selecting expansion schemes for single characters or words, it can push more accurate expansion schemes, thereby improving the input efficiency of the typing process.

[0056] Please see Figure 4 , Figure 4 This is the final candidate result image in the Korean basic vocabulary model in the second embodiment of the Korean input method of this application. For example, the above-mentioned image shows the result when the user inputs the single character "". Afterwards, the basic Korean vocabulary model is continuously trained and scored, constantly optimized. When displayed, users sort the vocabulary according to the scores, placing frequently selected and more likely words at the top, thus reducing search time and improving input efficiency.

[0057] Please see Figure 5 , Figure 5 This is a schematic diagram of the structure of an embodiment of the electronic device of this application. In this embodiment, the electronic device 30 includes a processor 31 and a memory 32.

[0058] In this embodiment, the processor 31 can be a central processing unit (CPU). The memory 32 can be random access memory (RAM); it can also be stable memory, such as non-volatile memory.

[0059] The electronic device 30 calls the language input program in the memory 32 through the processor 31 and executes any method or step of the first or second embodiment of the Korean input method of this application.

[0060] Furthermore, the functional units in the various embodiments of this invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0061] Please see Figure 6 , Figure 6 This is a schematic diagram of the structure of an embodiment of the input device of this application. In this embodiment, the input device 40 includes: a receiving module 41, a segmentation module 42, a decoding module 43, and a completion module 44.

[0062] In this module, the receiving module 44 receives the Korean characters input by the user and sends them to the segmentation module 42. The segmentation module 42 sorts the input Korean characters and segments them into Korean character groups to facilitate subsequent character formation. After forming characters, the segments are sent to the decoding module 43. The decoding module 43 receives the combination of the formed characters and decodes them to obtain the corresponding single characters. The single characters are then sent to the completion module 44. The completion module 44 expands the single characters to obtain more types of Korean phrases for the user to choose from. The completion module 44 can also analyze the user's input habits and provide more accurate expansion schemes based on the user's input habits.

[0063] The above description is merely an embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structural or procedural transformations made based on the content of the present invention specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of the present invention.

Claims

1. A Korean input method, characterized in that, The input method includes: Obtain the Korean characters input by the user; Based on the input order of the Korean characters, the Korean characters are converted into single characters to determine the combinations that can form single characters and the characters that cannot form single characters. The combinations that can form a single character are directly decoded into a single character, and a completion operation is performed based on the single character and / or the characters that cannot form a single character to obtain new candidate words and / or candidate characters; The step of converting Korean characters into single characters based on the input order of the Korean characters, and determining the combinations that can form single characters and the characters that cannot form single characters, includes: The input order of the obtained Korean characters is used to segment the Korean characters into Korean character groups; Based on the segmented Korean character groups, the Korean character group ranked first is combined into characters according to the Korean maximum combination algorithm; If the Korean character group contains characters that cannot form a single character, and there are still Korean characters that have not been combined into characters, all Korean characters that have not been combined into characters are further segmented and combined into characters again according to the maximum single character rule; Identify all combinations that can form words and the single characters that cannot; The step of combining the top-ranked Korean character group into characters using the Korean maximum combination algorithm, based on the segmented Korean character groups, includes: The Korean character groups are combined into characters using at least one of the following rules: "FYYSS", "FYYS", "FYY / FYS", and "FY"; where "F" represents a consonant, "Y" represents a vowel, and "S" represents a final consonant. The step of combining the Korean character groups into characters using at least one of the rules "FYYSS", "FYYS", "FYY / FYS", and "FY" includes: Determine whether the Korean character group can be formed into a character using "FYYSS". If it can be formed into a character, determine whether the next character is "Y". If it is "Y", remove the last character of the Korean character group and generate a new Korean character group. If it is not "Y", it can be formed into a character using "FYYSS". Determine whether the new Korean character group can form a character using "FYYS". If it can form a character, determine whether the next character is "Y". If it is "Y", remove the last character of the new Korean character group and update the Korean character group. If it is not "Y", it can form a character using "FYYS". Determine if the updated Korean character set can form a character using "FYY / FYS". If it can, check if the next character is "Y". If it is "Y", remove the last character from the updated Korean character set and update the Korean character set again. If it cannot form a character, check if it can form a character using "FY". If it cannot form a character using "FY", save the first character in the Korean character set directly.

2. The input method according to claim 1, characterized in that, The steps of directly decoding the combinations that can form single characters into single characters, and performing a completion operation based on the single characters and / or the characters that cannot form single characters to obtain new candidate words and / or candidate characters include: Obtain the combinations that make up individual characters, and calculate the index of the combinations of individual characters according to the single-character combination algorithm to obtain the index number; Find the corresponding single character based on the index number; A completion operation is performed based on the single character and / or the characters that cannot form a single character to obtain new candidate words and / or candidate characters.

3. The input method according to claim 2, characterized in that, The steps of obtaining the combination of constituent characters, and calculating the index of the combination of constituent characters according to the single-character synthesis algorithm to obtain the index number include: The index number is obtained by multiplying the total number of consonants, vowels, and final consonants in a character by the corresponding index positions of the consonants and vowels, and adding the index position of the final consonant to the default number of characters.

4. The input method according to claim 2, characterized in that, The step of performing a completion operation based on the single character and / or the characters that cannot form a single character to obtain new candidate words and / or candidate characters includes: By expanding and processing determined single characters and / or non-single characters in Korean through the basic Korean vocabulary model, various Korean phrases and / or single characters are obtained; After selecting the target Korean phrase and / or single character, the Korean basic vocabulary model records the processing results; The Korean basic vocabulary model is trained based on the processing results to obtain the trained Korean basic vocabulary model.

5. The input method according to claim 1, characterized in that, Before the step of obtaining the Korean characters input by the user, the following steps are included: Collect corpora, construct a basic Korean vocabulary model and verify it. If the corpora are found to be erroneous, they are removed from the basic Korean vocabulary model.

6. An electronic device, characterized in that, include: A processor and a memory, wherein the processor is configured with a Korean input method according to any one of claims 1-5.

7. An input device, characterized in that, The input device includes: Receiving module: Used to acquire Korean characters input by the user; Segmentation module: used to segment several Korean characters into multiple Korean character groups; Decoding module: This module decodes Korean character groups that can form single characters to obtain Korean characters; it also obtains the input order of the Korean characters, segments the Korean characters to obtain Korean character groups; based on the segmented Korean character groups, it combines the first-ranked Korean character group into characters using the maximum Korean character combination algorithm; if a Korean character group contains characters that cannot form single characters, and there are still Korean characters that have not been combined into characters, it segments all the uncombined Korean characters again and combines them into characters again using the maximum single character rule; it determines all combinations that can form single characters and the single characters that cannot; it also combines the Korean character groups into characters using at least one of the rules "FYYSS", "FYYS", "FYY / FYS", and "FY"; where "F" represents a consonant, "Y" represents a vowel, and "S" represents a final consonant; it also determines whether the Korean character group can be combined into characters. If a character can be formed using "FYYSS", then check if the next character is "Y". If it is "Y", remove the last character of the Korean character group and generate a new Korean character group. If it is not "Y", then a character can be formed using "FYYSS". Next, check if the new Korean character group can be formed using "FYYS". If it can, check if the next character is "Y". If it is "Y", remove the last character of the new Korean character group and update the Korean character group. If it is not "Y", then a character can be formed using "FYYS". Finally, check if the updated Korean character group can be formed using "FYY / FYS". If it can, check if the next character is "Y". If it is "Y", remove the last character of the updated Korean character group and update the Korean character group again. If it cannot be formed, check if it can be formed using "FY". If it cannot be formed using "FY", then directly save the first character in the Korean character group. The completion module is used to expand the obtained Korean words to obtain more types of Korean phrases.

Images