A method for vocabulary recognition, a processing method, and a display device of an input method

Abstract

The present application discloses a vocabulary recognition method, processing method and display device for an input method, which performs initial segmentation processing on the text content of a single word input by a user to obtain a first-level text combination after segmentation, and the first-level text combination is segmented again to obtain a second-level text combination after segmentation; if the second-level text combination is the same as the vocabulary stored in the user vocabulary, the second-level text combination is eliminated, and if the second-level text combination is different, the suspected new vocabulary is stored in the user vocabulary, and the suspected new vocabulary refers to the second-level text combination. The present application, through two segmentation processes and judging whether the processed text combination is the same as the vocabulary stored in the user vocabulary, can easily identify the vocabulary input by a single word and store it in the user vocabulary. When the user inputs the same pinyin next time, the vocabulary can be placed in the candidate items, and there is no need to search from many single words.

Description

Technical Field

[0001] This application relates to an information input method, and particularly to a vocabulary recognition method, a processing method of an input method, and a display device. Background Art

[0002] When a user inputs the pinyin of a rare vocabulary using a pinyin input method, for example, inputs jijin (famine), if this vocabulary is not in the input method's lexicon, the user needs to carefully search through numerous single-character candidate items. First, find the character "饥" (hunger), and then find the character "馑" (famine) to complete the input of the entire word. Some users think that after inputting the pinyin of a rare vocabulary, it is too troublesome to first scroll past the previous candidate items and then sequentially search for the single characters after the candidates to complete the input, and it is easy to get眼花 (presumably "dizzy" or "confused" in this context). They often change to inputting the pinyin of the single characters of the rare vocabulary separately to complete the input. That is, first input ji, select the character "饥" from the candidate items, then input jin, and select the character "馑" from the candidate items to complete the input of the "饥馑" vocabulary.

[0003] However, when the user inputs the "饥馑" vocabulary by inputting the pinyin of the single characters separately, the input method cannot recognize that this is a vocabulary, so it will not record this new vocabulary in the input method's lexicon. Next time, if the user changes to inputting the complete pinyin of this vocabulary, jijin, the new vocabulary "饥馑" will not directly appear in the candidate items for the user to select. The user still needs to carefully search through numerous single-character candidate items and input the single characters separately to complete the input. Summary of the Invention

[0004] This application provides a vocabulary recognition method, a processing method of an input method, and a display device to enable the input method to recognize that this is a vocabulary when the user inputs a vocabulary by single characters.

[0005] A vocabulary recognition method of an input method includes:

[0006] Obtain the text content input by the user;

[0007] Perform an initial segmentation process on the text content to obtain a segmented first-level text combination;

[0008] Perform a second segmentation process on the first-level text combination to obtain a segmented second-level text combination;

[0009] If the second-level text combination is the same as the vocabulary saved in the user's lexicon, then eliminate the second-level text combination;

[0010] If the second-level text combination is not the same as the vocabulary saved in the user's lexicon, then store the suspected new vocabulary in the user's lexicon, where the suspected new vocabulary refers to the second-level text combination.

[0011] A vocabulary processing method of an input method includes: It should be noted that the Chinese character "眼花" in the original text seems to be an incorrect or incomplete expression. I translated it as "get眼花" based on the context, but it might need to be corrected according to the actual meaning.

[0012] Get the pinyin of the word entered by the user;

[0013] If the pinyin of a word is the same or partially the same as the pinyin of a suspected word stored in the automatic recognition word library, the suspected word will be added to the candidate items, and the number of suspected word displays will be increased by 1. The suspected word refers to a suspected new word stored in the automatic recognition word library;

[0014] If the suspected word is input as an input word, the suspected word is moved to the user-defined word library.

[0015] A display device, comprising:

[0016] The processor is configured to:

[0017] Get the text content entered by the user;

[0018] Initially segment the text content to obtain the first-level text combination after segmentation;

[0019] The first-level character combination is segmented again to obtain a segmented second-level character combination;

[0020] If the secondary character combination is the same as the words stored in the user's vocabulary, the secondary character combination will be eliminated;

[0021] If the secondary character combination is different from the words stored in the user vocabulary, the suspected new words are stored in the user vocabulary, wherein the suspected new words refer to the secondary character combination.

[0022] A display device, comprising:

[0023] The processor is configured to:

[0024] Get the pinyin of the word entered by the user;

[0025] If the pinyin of a word is the same or partially the same as the pinyin of a suspected word stored in the automatic recognition word library, the suspected word will be added to the candidate items, and the number of suspected word displays will be increased by 1. The suspected word refers to a suspected new word stored in the automatic recognition word library;

[0026] If the suspected word is input as an input word, the suspected word is moved to the user-defined word library.

[0027] Beneficial effects: The present application provides a vocabulary recognition method, processing method and display device for an input method. The text content of the user's single-word input is initially segmented to obtain a segmented first-level text combination, and the first-level text combination is segmented again to obtain a segmented second-level text combination; if the second-level text combination is the same as the vocabulary stored in the user's vocabulary, the second-level text combination is eliminated, and if the second-level text combination is different, the suspected new vocabulary is stored in the user's vocabulary, and the suspected new vocabulary refers to the second-level text combination. The present application, through two segmentation processes and judging whether the processed text combination is the same as the vocabulary stored in the user's vocabulary, can easily identify the vocabulary input by a single word and store it in the user's vocabulary. When the user enters the same pinyin next time, the vocabulary can be placed in the candidate items, and there is no need to search through many single words. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0029] Figure 1 A flowchart of a vocabulary recognition method for an input method provided in an embodiment of the present application;

[0030] Figure 2 A flowchart of a vocabulary processing method for an input method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0031] In order to enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0032] Figure 1 This is a flow chart of an input method vocabulary recognition method provided by an embodiment of the present application. Figure 1 As shown, the steps of the input method recognition method provided in the embodiment of the present application are as follows:

[0033] S100: Obtain text content input by the user.

[0034] The user inputs text content in the single - character input mode. The single - character input mode includes single - character pinyin input, single - character五笔input, etc. Since these single - character input modes can all enable the user to input text content, the embodiments of this application do not limit which specific single - character input mode is used.

[0035] When the user inputs text content in the single - character input mode, the input method can obtain the text content input by the user. For example: when the user uses the single - character input mode to input a paragraph: "This year's GDP has reached new highs repeatedly, and the apples have also had a good harvest.", the text content obtained by the processor is "This year's GDP has reached new highs repeatedly, and the apples have also had a good harvest.".

[0036] S200: Perform an initial segmentation process on the text content to obtain the segmented first - level text combination.

[0037] To facilitate finding whether there are new words, the input method performs an initial segmentation process on the obtained text content to obtain the segmented first - level text combination.

[0038] When the input method performs an initial segmentation process on the obtained text content, it can perform an initial segmentation process on the text content according to the non - Chinese characters自带by the text content. Non - Chinese characters include punctuation marks, Western letters, spaces, line breaks, tab characters, etc.

[0039] For example: for the obtained text content "This year's GDP has reached new highs repeatedly, and the apples have also had a good harvest.", perform an initial segmentation process on the text content according to the non - Chinese characters自带by the text content. The obtained first - level text combination is "This year's", "has reached new highs repeatedly", and "the apples have also had a good harvest".

[0040] S300: Perform a secondary segmentation process on the first - level text combination to obtain the segmented second - level text combination.

[0041] When the input method performs a secondary segmentation process on the first - level text combination, it can match the words in the first - level text combination with the words saved in the user dictionary, and剔除the words in the first - level text combination that are the same as the words saved in the user dictionary to obtain the segmented second - level text combination.

[0042] The user dictionary includes a default dictionary, a user - defined dictionary, and an automatically recognized dictionary.

[0043] The default dictionary is a dictionary pre - set by the input method. The default dictionary is used to save common words with two or more characters, as well as isolated single - character words. For example, pronouns: you, me, him, words formed: of, is, also, etc.

[0044] The user - defined dictionary is used to save the words that the user has input and are not in the default dictionary. The user - defined dictionary can be continuously expanded according to the user's input habits.

[0045] It should be noted that "五笔" is a traditional Chinese character input method. There may be some inaccuracies in the translation of this part as the description in the original text seems a bit unclear. It might be better to use a more accurate and common input method name if possible. Also, the "自带" in the original text is translated as "自带" here, which might not be the best translation. It could be more accurately expressed as "inherent" or "自带的" could be better translated as "inherent to" or something more context - appropriate.There are two ways to expand the user-defined word library. The first way is that the user inputs an input word, and then selects each single character of the input word from the candidates in turn. After the selection is completed, the input method will record the input word. The second way is to obtain from the user word library.

[0046] Since the expansion methods of the user-defined word library include the above two, the user-defined word library includes single-character input words and words selected from the user word library as candidates. Among them, the single-character input word is a word composed of single characters sequentially selected from the candidates of the input word. The input word can be input by the complete pinyin of a word, or input by the五笔 combination of a word, etc.

[0047] The automatic recognition word library is used to save suspected new words. Suspected new words refer to two-level text combinations that are different from the words saved in the user word library.

[0048] Since the user word library includes the above three word libraries, the input method matches the segmented two-level text combinations with the words saved in each of the three word libraries respectively.

[0049] For example, since the words saved in the default word library are "的", "也" and "了", and the words saved in the user-defined word library are "今年", "获得" and "丰收", then剔除 the words in the first-level text combination that are the same as the words saved in the user word library: "的", "也", "了", "今年", "获得" and "丰收", and the segmented two-level text combinations obtained are "屡创新高" and "苹果".

[0050] S400: Determine whether the two-level text combination is the same as the words saved in the user word library.

[0051] S500: If the two-level text combination is the same as the words saved in the user word library, then剔除 the two-level text combination.

[0052] For example, if the words saved in the user word library are "屡创新高" and "苹果", then "屡创新高" and "苹果" are剔除.

[0053] S600: If the two-level text combination is not the same as the words saved in the user word library, then store the suspected new words in the user word library.

[0054] Suspected new words refer to two-level text combinations.

[0055] For example, if the words saved in the user word library do not include "屡创新高" and "苹果", then the words saved in the user word library are not the same as the two-level text combinations "屡创新高" and "苹果". Since the two-level text combinations "屡创新高" and "苹果" are not the same as the words saved in the user word library, "屡创新高" and "苹果" are stored as suspected new words in the automatic recognition word library of the user word library.

[0056] Since the automatic recognition word library in the user word library is used to store suspected new words, the suspected new words are stored in the user word library.

[0057] This application uses two segmentation processes and determines whether the processed word combination is the same as the words stored in the user's word library. This can easily identify the words input by single words and store them in the user's word library. When the user enters the same pinyin next time, the word can be placed in the candidate list, eliminating the need to search through many single words.

[0058] According to the above steps, the vocabulary input by the user through single words can be saved in the automatic recognition vocabulary of the user vocabulary. When the user inputs the complete pinyin of the vocabulary at one time next time, the suspected new vocabulary obtained in the above steps can be placed in the candidate items for the user to select. The specific process is as follows Figure 2 shown.

[0059] Figure 2 A flowchart of a vocabulary processing method for an input method provided in an embodiment of the present application is shown as follows: Figure 2 As shown, a vocabulary processing method of an input method includes:

[0060] T100: Get the pinyin of the vocabulary input by the user.

[0061] The input method obtains the complete pinyin of the word input by the user, for example, the complete pinyin of the word input by the user is "pingguo".

[0062] T200: Determine whether the pinyin of the word is the same or partially the same as the pinyin of the suspected words stored in the automatic recognition word library.

[0063] A suspected word refers to a suspected new word stored in the automatic recognition word library.

[0064] For example, the input method determines whether the pinyin of "pingguo" is identical or partially identical to the pinyin of the suspected words stored in the automatic recognition library.

[0065] T300: If the pinyin of a word is identical or partially identical to the pinyin of a suspected word stored in the automatic recognition vocabulary, the suspected word will be added to the candidate items, and the number of times the suspected word is displayed will be increased by 1.

[0066] The position of the suspected word in the candidate list can be the first, the last, or any other position. It can be set randomly according to the specific situation.

[0067] For example, if "pingguo" has the same pinyin as the suspected word "apple" stored in the automatic recognition lexicon, the input method will add the suspected word "apple" to the candidate list. The original candidate list for "pingguo" may include "pingguo", "pingguo", "pingguo", etc. When "pingguo" has the same pinyin as the suspected word "apple" stored in the automatic recognition lexicon, the candidate list for "pingguo" will be changed to include "pingguo", "pingguo", "pingguo", "pingguo", "pingguo", and "apple", etc.

[0068] T400: If the pinyin of a word is not the same as or is not partially the same as the pinyin of a suspected word stored in the automatic recognition word library, the suspected word will not be placed in the candidate items.

[0069] For example, if the pinyin of the word "pingyu" is different or partially the same as the pinyin of the suspected word "apple" stored in the automatic recognition vocabulary, the input method will not place the suspected word "apple" in the candidate list. The original candidates for "pingyu" may include "pingyu", "pingyu", "pingyu", etc. When the pinyin of "pingyu" is different or partially the same as the suspected word "apple" stored in the automatic recognition vocabulary, the candidates for "pingyu" will still include "pingyu", "pingyu", and "pingyu".

[0070] Because some input methods detect the text content that users have entered and treat all previously entered text combinations as suspected new words, many meaningless text combinations are also considered suspected words. When users select words from the candidate list, meaningless interference text combination options appear, which reduces the user experience. Therefore, it is necessary to remove these meaningless interference text combination options. The specific process is as follows:

[0071] T500: Determine whether the suspected word is input as an input word.

[0072] The input method determines whether the user selects a suspected word as an input word.

[0073] For example, it is determined whether "apple" is input as an input word, that is, whether the user selects "apple", "pingguo", "pingguo" or "pingguo".

[0074] T600: If the suspected word is input as an input word, the suspected word is moved to the user-defined word library.

[0075] If the user selects a suspected word as an input word, the input method moves the suspected word from the automatic recognition word library to the user-defined word library.

[0076] For example, if the user selects "apple", the input method moves "apple" from the automatic recognition vocabulary to the user-defined vocabulary.

[0077] T700: If the suspected word is not input as an input word, determine whether the suspected word has not been input as an input word N times.

[0078] N can be any integer, and can be set to 3, 4, or 5. If N is set to 3, it is determined whether the suspected word is not used as an input word three times.

[0079] If the user does not select the suspected word as the input word, the input method starts to count the number of times the suspected word is added to the candidate list. The input method determines whether the user has not selected the suspected word as the input word for N cumulative times.

[0080] For example, if the user does not select "apple" as an input word, the input method determines whether the user has not selected "apple" as an input word for N cumulative times.

[0081] T800: If the suspected word is not input as an input word N times, the suspected word is removed from the automatic recognition word library.

[0082] If the user has not selected a suspected word as an input word N times, the input method will consider the suspected word to be not a real word or too rare and uncommon, and will remove the suspected word from the automatic recognition word library. The next time the user enters the full pinyin of the word, the suspected word will not appear in the candidate list.

[0083] For example, if the user has not selected "apple" as an input word for N cumulative times, the input method will remove "apple" from the automatic recognition vocabulary.

[0084] T900: If the suspected word has not been input as an input word for N times, the suspected word is continued to be stored in the automatic recognition word library.

[0085] If the user does not select the suspected word as the input word for N cumulative times, the input method will continue to save the suspected word in the automatic recognition word library.

[0086] For example, if N is set to 3, and the user does not select a suspected word as an input word only once or twice, the input method will continue to save the suspected word in the automatic recognition word library.

[0087] This application uses the above method to continuously update and adjust the automatic recognition word library based on the user's input behavior. It adds suspected words that the user actually uses to the user-defined word library, and also removes rare words or meaningless combinations that are mistakenly recognized as words from the automatic recognition word library to avoid interfering with the candidate items.

[0088] The above-mentioned method in the present application can not only be set up on existing electronic products such as televisions and set-top boxes that require text input to complete the transformation, but can also be directly used for secondary development on existing software functions, so that through software upgrades, the input method software of existing electronic products such as televisions or set-top boxes that require text input can have the functions of the above-mentioned vocabulary recognition method and vocabulary processing method.

[0089] The present application also provides two display devices, one of which includes a processor. The processor is configured to: obtain text content input by a user; segment the text content to obtain segmented text combinations; initially segment the text content to obtain segmented first-level text combinations; further segment the first-level text combinations to obtain segmented second-level text combinations; if the second-level text combination is identical to a word stored in a user vocabulary, then the second-level text combination is eliminated; if the second-level text combination is different from a word stored in the user vocabulary, then the suspected new word is stored in the user vocabulary, wherein the suspected new word refers to the second-level text combination.

[0090] Another display device includes a processor. The processor is configured to: obtain the pinyin of a word input by a user; if the pinyin of the word is identical or partially identical to the pinyin of a suspected word stored in an automatic recognition word library, add the suspected word to the candidate list and increment the number of suspected word displays by 1, wherein the suspected word is a suspected new word stored in the automatic recognition word library; and if the suspected word is input as an input word, move the suspected word to a user-defined word library.

[0091] Since the above embodiments are all described by reference in combination with other embodiments, different embodiments have the same parts, and the same and similar parts between the various embodiments in this specification can be referred to each other. No further detailed explanation is given here.

[0092] It should be noted that, in this specification, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a circuit structure, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such circuit structure, article or device. In the absence of further restrictions, the presence of an element defined by the phrase "includes a..." does not exclude the presence of other identical elements in the circuit structure, article or device comprising the element.

[0093] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and practicing the disclosure herein. This application is intended to cover any variations, uses, or adaptations of the present invention that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered merely as exemplary, and the true scope and spirit of the present invention are indicated by the claims.

[0094] The above-described embodiments of the present application do not constitute a limitation on the scope of protection of the present application.

Claims

1. A vocabulary recognition method for an input method, characterized in that: The method comprises: Get the text content entered by the user through single-word input; Initially segmenting the text content according to the non-Chinese characters in the text content to obtain a segmented first-level text combination; Matching the vocabulary of the first-level character combination with the vocabulary stored in the user vocabulary, eliminating the vocabulary in the first-level character combination that is the same as the vocabulary stored in the user vocabulary, and obtaining the segmented second-level character combination; If the secondary character combination is the same as the words stored in the user's vocabulary, the secondary character combination is eliminated; If the secondary character combination is different from the words stored in the user vocabulary, the suspected new words are stored in the automatic recognition vocabulary of the user vocabulary, wherein the suspected new words refer to the secondary character combination, and the automatic recognition vocabulary is used to store the suspected new words; Get the pinyin of the word entered by the user; Determine whether the pinyin of the word is the same or partially the same as the pinyin of the suspected words stored in the automatic recognition word library; If the pinyin of the word is the same or partially the same as the pinyin of the suspected word stored in the automatic recognition word library, the suspected word will be added to the candidate items, and the number of suspected word displays will be accumulated by 1, wherein the suspected word refers to a suspected new word stored in the automatic recognition word library; If the suspected word is input as an input word, the suspected word is moved to a user-defined word library; If the suspected word is not input as an input word, and the suspected word is input as a word that has not been input N times, the suspected word is removed from the automatic recognition word library.

2. The vocabulary recognition method according to claim 1, characterized in that The user vocabulary also includes a default vocabulary and a user-defined vocabulary; The default word library is used to store commonly used words with two or more characters, as well as isolated single-character words; The user-defined vocabulary is used to store words that have been input by the user and are not in the default vocabulary.

3. The vocabulary recognition method according to claim 2, characterized in that The words entered by the user include: a single-word input vocabulary, wherein the single-word input vocabulary is composed of words selected sequentially from the candidate items of the input vocabulary; A vocabulary is selected as a candidate from the user vocabulary.

4. A display device, characterized in that: comprising a processor configured to execute: The vocabulary recognition method according to any one of claims 1 to 3.

Images