CN1206870A - Writing style learning method and device in Chinese character input system - Google Patents
Writing style learning method and device in Chinese character input system Download PDFInfo
- Publication number
- CN1206870A CN1206870A CN 97115564 CN97115564A CN1206870A CN 1206870 A CN1206870 A CN 1206870A CN 97115564 CN97115564 CN 97115564 CN 97115564 A CN97115564 A CN 97115564A CN 1206870 A CN1206870 A CN 1206870A
- Authority
- CN
- China
- Prior art keywords
- sentence
- relation table
- speech
- phonetic
- writing style
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Document Processing Apparatus (AREA)
- Machine Translation (AREA)
Abstract
The present invention provides a writing style learning method used in Chinese characters phonetic input system and its device. It is characterized by that the relation between words embodies the user's writing style to a certain extent, and the relation between words is identical to the relation between phonetic words in that they are directly related to the correctness and speed of Chinese character input system. Said invented method includes the following steps: for inputting a Chinese article; taking out a sentence; seeking existent phonetic characters and words relation table; dividing the sentence into fields; and logging the connected retation between fields in the retation table between words. Said invention also provides the device for implementing said invented method.
Description
The present invention relates to the pinyin input system of Chinese character, relate in particular to the extending method and the device of relation table between the speech that uses in the Chinese character input system, this method and apparatus is used to learn user's writing style.
The present invention and the applicant and the name that proposes on the same day are called the application for a patent for invention of " phonetic Chinese character change method and system thereof " and name, and to be called " phonetic words relation table automatic logging method and device in the Chinese character input system " relevant.The application quotes this two patented claim, as a reference.In last application, a kind of phonetic Chinese character change method and system thereof are provided, in this method and system, utilized phonetic words relation table to search the pairing word of phonetic sign indicating number or the speech of input, improve input speed to utilize.In one application of back, be used for automatically expanding phonetic words relation table, to increase the data volume of phonetic words relation table, improve the correctness and the speed of conversion.
Equally, also will have influence on the speed of the correctness of Chinese character input system for the data volume size of relation table between the speech in the Chinese character input system.The spoken and written languages style that everyone is used, be that writing style respectively has characteristics, and what stored in the relation table between speech is exactly the relation that embodies between this writing style speech and the speech, so we can call the extending method of relation table between speech and device " Writing style learning method and device ".
Therefore, purpose of the present invention just provides a kind of Writing style learning method.Utilize this method, in Chinese character phonetic input system, can automatically increase the speech that originally do not have in the relation table between speech and the relation between the speech, expand relation table between speech.
Another object of the present invention is to provide a kind of writing style learning device, and this device can be automatically joins the relation between speech that did not originally have in the relation table between speech and the speech between speech in the relation table, automatically expands relation table between speech.
Writing style learning method of the present invention comprises the following step:
(1) input Chinese article;
(2) from article, take out a sentence;
(3) search existing phonetic words relation table, sentence is divided into field;
(4) annexation between the field is signed in between speech in the relation table.
The present invention also provides a kind of writing style learning device of realizing the inventive method, comprises:
Phonetic words relation table, the mapping relations that are used to store phonetic and institute's equivalent;
Relation table between speech is used for the annexation between stored word and the speech;
Receiving trap is used to receive Chinese article;
The subordinate sentence device links to each other with described receiving trap, is used for obtaining Chinese article from described receiving trap, and takes out a sentence;
The sentence segmenting device links to each other with described phonetic words relation table with described subordinate sentence device, and the speech that is used for having stored according to described phonetic words relation table is divided into field to the Chinese sentence of described subordinate sentence device output;
Relational learning device between speech links to each other with the sentence segmenting device, is used for the annexation between described field or the speech is signed in to relation table between institute's predicate.
As mentioned above, the user is as long as provide one piece of article with representative to the writing style learning device, and method of the present invention or device just can automatically be learnt user's writing style, automatically expand relation table between speech.
Describe embodiments of the invention in detail below in conjunction with accompanying drawing.
Fig. 1 is the process flow diagram of Writing style learning method of the present invention;
Fig. 2 is the block scheme of writing style learning device of the present invention
At first Writing style learning method of the present invention is described below with reference to Fig. 1.
See also Fig. 1, Fig. 1 shows the process flow diagram of Writing style learning method of the present invention.At first, at step S1 input Chinese article.This piece article can be one piece of ready-made text of having imported, also can pass through input media, as inputs such as keyboards.Then, at step S2, can judgement take out sentence from article.Can take out the method for sentence can be undertaken by differentiating the punctuation mark that find the expression sentence to pause.For example, seek the punctuation mark that for example expressions such as comma, fullstop, question mark, exclamation mark, branch pause.Chinese character before these punctuation marks is taken out as a sentence.In the present embodiment, with explanation and understanding, we can take out sentence (ending of not arriving article also is described) at step S2 at hypothesis, and are " company organization travels to the Zhangjiajie " at the sentence that step S3 obtains for just.Then, at step S4, the sentence of input is divided into field.That is, contrast existing phonetic words relation table, speech consistent with the speech stored in the existing phonetic words relation table in the sentence is divided into a field.In this example, suppose to have stored in the phonetic words relation table " company ", " tissue " and " tourism ".Then, this sentence is divided into these fields: " company ", " tissue ", " arriving ", " opening ", " family ", " boundary ", " tourism ".
In the field that is partitioned into, 4 continuous individual character fields are arranged.Therefore have only a Chinese character in these fields, can be called the automatic logging method that provides in " phonetic words relation table automatic logging method and device in the Chinese character input system " and device according to name above-mentioned and these individual character fields are formed neologisms and sign in in the phonetic words relation table.Because the content of forming neologisms and signing in to phonetic words relation table has been made detailed description in above-mentioned patented claim, therefore, this patented claim is incorporated herein, as a reference.Suppose, login automatically, " opening ", " family ", " boundary " have been formed neologisms " Zhangjiajie ", and signed in in the phonetic words relation table by phonetic words relation table.
Then, at step S7, the annexation between adjacent fields or the speech is signed in between speech in the relation table.Promptly, in this example, the annexation between " company " and " tissue " is signed in between speech in the relation table, " tissue " and " to " between relation sign in between speech in the relation table, " to " and " Zhangjiajie " between relation sign in in the relation table, the rest may be inferred.Then, flow process is returned step S2, and can judgement take out next sentence, if article has arrived ending, then flow process turns to step S14 to finish.Otherwise, each sentence is carried out above-mentioned steps, finish until article.
Though, in above-mentioned Writing style learning method, comprised the login step of phonetic words relation table should be appreciated that these login step are not essential for Writing style learning method.
More than describe method of the present invention in detail, describe the device that the present invention realizes said method below in conjunction with Fig. 2.Referring to Fig. 2, Fig. 2 shows the writing style learning device of realizing Writing style learning method shown in Figure 1.As shown in Figure 2, the writing style learning device by between subordinate sentence device 1, sentence segmenting device 2, phonetic words relation table entering device 3, speech between relational learning device 4, phonetic words relation table 5 and speech relation table 6 form.
Subordinate sentence device 1 is used for taking out a sentence from the Chinese article of input.Then sentence is offered sentence segmenting device 2.Segmenting device 2 utilizes phonetic words relation table 5, in the sentence with existing phonetic words relation table 5 in the consistent speech of speech of storage be divided into field (owing to done to exemplify when the describing method, so when tracing device, no longer give an example, can be referring to top example).Then, these field output spelling sound words relation table entering devices 3.Be called in " phonetic words relation table automatic logging method and device in the Chinese character input system " in above-mentioned name about the structure of phonetic words relation table entering device 3 and working condition and have a detailed description, therefore this patented claim is incorporated herein, with for referencial use.Then, between speech in the relational learning device 4, the annexation between described field or the speech is signed in between speech in the relation table 6.
Though, in above-mentioned writing style learning device, comprised phonetic words relation table entering device 3, should be appreciated that this phonetic words relation entering device 3 is not essential for the writing style learning device.Can sentence segmenting device 2 directly with speech between relational learning device 4 link to each other.
By embodiment the present invention has been done detailed description above, can utilize software or hardware to realize, also can utilize the mode soft, that hardware combines to realize but those skilled in the art should be appreciated that above-mentioned method and apparatus.
Claims (2)
1, a kind of Writing style learning method is characterized in that, comprises the following step:
The input Chinese article;
From article, take out a sentence;
Search existing phonetic words relation table, sentence is divided into field;
Annexation between the field is signed in between speech in the relation table.
2, a kind of writing style learning device of realizing the described method of claim 1 is characterized in that, comprises:
Phonetic words relation table, the mapping relations that are used to store phonetic and institute's equivalent;
Relation table between speech is used for the annexation between stored word and the speech;
Receiving trap is used to receive Chinese article;
The subordinate sentence device links to each other with described receiving trap, is used for obtaining Chinese article from described receiving trap, and takes out a sentence;
The sentence segmenting device links to each other with described phonetic words relation table with described subordinate sentence device, and the speech that is used for having stored according to described phonetic words relation table is divided into field to the Chinese sentence of described subordinate sentence device output;
Relational learning device between speech links to each other with the sentence segmenting device, is used for the annexation between described field or the speech is signed in to relation table between institute's predicate.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 97115564 CN1206870A (en) | 1997-07-25 | 1997-07-25 | Writing style learning method and device in Chinese character input system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 97115564 CN1206870A (en) | 1997-07-25 | 1997-07-25 | Writing style learning method and device in Chinese character input system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN1206870A true CN1206870A (en) | 1999-02-03 |
Family
ID=5173307
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 97115564 Pending CN1206870A (en) | 1997-07-25 | 1997-07-25 | Writing style learning method and device in Chinese character input system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN1206870A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100456214C (en) * | 2002-09-29 | 2009-01-28 | 康泰 | Chinese document quick-speed input processing technology and keyboard thereof |
-
1997
- 1997-07-25 CN CN 97115564 patent/CN1206870A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100456214C (en) * | 2002-09-29 | 2009-01-28 | 康泰 | Chinese document quick-speed input processing technology and keyboard thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8515733B2 (en) | Method, device, computer program and computer program product for processing linguistic data in accordance with a formalized natural language | |
| CN1079967C (en) | Electronic translation machine | |
| ATE401609T1 (en) | LEXICON WITH DESCRIBED DATA AND PROCEDURES FOR THEIR CONSTRUCTION AND USE | |
| CN103268313A (en) | Method and device for semantic analysis of natural language | |
| JP6526470B2 (en) | Pre-construction method of vocabulary semantic patterns for text analysis and response system | |
| CN111177350A (en) | Method, device and system for forming dialect of intelligent voice robot | |
| US20150012261A1 (en) | Method for phonetizing a data list and voice-controlled user interface | |
| Vinnarasu et al. | Speech to text conversion and summarization for effective understanding and documentation | |
| CN112580339B (en) | Model training method and device, electronic equipment and storage medium | |
| CN110851601A (en) | Cross-domain emotion classification system and method based on layered attention mechanism | |
| JP4634889B2 (en) | Voice dialogue scenario creation method, apparatus, voice dialogue scenario creation program, recording medium | |
| Kempe et al. | Parallel replacement in finite state calculus | |
| CN110196929A (en) | The generation method and device of question and answer pair | |
| US20160364483A1 (en) | Modification of search subject in predictive search sentences | |
| CN115169370B (en) | Corpus data enhancement method and device, computer equipment and medium | |
| CN1206870A (en) | Writing style learning method and device in Chinese character input system | |
| CN110457683A (en) | Model optimization method, apparatus, computer equipment and storage medium | |
| Herawati et al. | Communication Strategies Used by The Eighth Grade Students of SMP N 1 Surakarta in Developing Speaking Skill | |
| CN113393848A (en) | Method, apparatus, electronic device and readable storage medium for training speaker recognition model | |
| CN113515586A (en) | Data processing method and device | |
| JPH04169969A (en) | Communication sentence automatic division storage device | |
| US20130144609A1 (en) | Text processing system, text processing method, and text processing program | |
| JP3525999B2 (en) | Language understanding method and language understanding device | |
| Hussein et al. | How to identify elliptical poems within a digital corpus of auditory poetry | |
| Vanroose | Part-of-speech tagging from an information-theoretic point of view |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |