CN110874527A - Cloud-based intelligent paraphrasing and phonetic notation system - Google Patents
Cloud-based intelligent paraphrasing and phonetic notation system Download PDFInfo
- Publication number
- CN110874527A CN110874527A CN201810984735.0A CN201810984735A CN110874527A CN 110874527 A CN110874527 A CN 110874527A CN 201810984735 A CN201810984735 A CN 201810984735A CN 110874527 A CN110874527 A CN 110874527A
- Authority
- CN
- China
- Prior art keywords
- unit
- request
- dictionary
- ancient
- pronunciation
- 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
Images
Landscapes
- Document Processing Apparatus (AREA)
Abstract
The invention discloses an intelligent paraphrasing and phonetic notation system based on a cloud, which comprises a client and a server, wherein the client comprises an ancient writing input unit, a text preprocessing unit, a service request unit, a request receiving unit and a local presentation unit, and the server comprises a receiving request unit, a logic processing unit, a dictionary retrieval unit, a dictionary unit and a dictionary management unit. The invention enables readers to browse and read ancient articles smoothly, greatly reduces learning cost and greatly improves reading experience.
Description
Technical Field
The invention relates to the technical field of word understanding, in particular to an intelligent paraphrasing and phonetic notation system based on a cloud.
Background
The modern Chinese character simplification is facilitated, and the reading capability of complex characters is reduced while the Chinese character popularization is facilitated. Especially, a large number of rarely used words, polyphone words, common and false words, variant words and ancient languages without sentence break and phonetic transcription exist.
The ancient works have no electronic words, the presentation forms are mainly paper works, the retrieval by readers is inconvenient, punctuation is not available, sentences are not broken, complex characters are not official published and popular characters, most readers cannot ask vast ancient texts, and a large number of uncommon characters, rare characters, false characters and variant characters exist in the ancient texts, so that the readers can see and stop the ancient texts.
Reading and understanding of ancient texts are difficult, reading interest is blocked to a great extent, and therefore the opportunity of people to know precious culture of the ancient people is indirectly reduced.
Disclosure of Invention
The invention aims to solve the defects in the prior art, and provides an intelligent paraphrasing and phonetic notation system based on a cloud end, which enables readers to browse and read ancient scripts smoothly, greatly reduces learning cost and greatly improves reading experience.
In order to achieve the purpose, the invention adopts the following technical scheme:
the cloud-based intelligent paraphrasing and phonetic notation system comprises a client and a server, wherein the client comprises an ancient writing input unit, a text preprocessing unit, a service request unit, a request receiving unit and a local presentation unit, and the server comprises a receiving request unit, a logic processing unit, a dictionary retrieval unit, a dictionary unit and a dictionary management unit.
Preferably, the text preprocessing unit is configured to convert traditional contents of ancient texts into corresponding simplified character contents, and the specific steps are as follows:
inputting an ancient text full text for analyzing and obtaining a corresponding ancient text;
removing punctuation marks, carrying out symbol removal processing and paragraph processing according to the whole ancient texts, and extracting corresponding Chinese characters for traditional and simple conversion;
extracting conversion Chinese character units, namely extracting one Chinese character from the beginning of the full text as one conversion unit each time;
sending a request for matching a retrieval unit, initiating a retrieval request to a cloud processor or a local processor according to the retrieval unit, inquiring whether the simplified character of the retrieval unit exists, and taking the character as the retrieval unit in a picture form if some rarely-used characters and special-shaped characters do not have corresponding character library codes;
the processor searches the unit request, according to searching the unit array, the server checks whether the searching unit is a special ancient vocabulary, whether it is a common complex word, whether it is a rare word, whether it is a special word, whether there is the searching unit in the dictionary, if there is the corresponding simplified word and corresponding explanation of the request;
if the converted traditional Chinese character finds a plurality of matched simplified Chinese characters, the length of the converted traditional Chinese character is increased to convert the traditional Chinese character into a phrase, and the retrieval request is continuously submitted until the retrieval unit is the only corresponding simplified Chinese character.
Preferably, the dictionary unit comprises a dictionary, an ancient dictionary and a rarely-used word picture and word dictionary, the dictionary management unit is mainly used for managing and maintaining a Buddhist special dictionary and rarely-used word picture and word, the dictionary is located at the cloud or is arranged locally and is mainly used for receiving a query request, receiving a complex and simple conversion and phonetic notation request of a client, querying and searching corresponding entries in the dictionary through a matching algorithm and sending the corresponding entries back to the request end;
the ancient Chinese has rare words without corresponding word stock codes, for the part of the request, the retrieval unit takes the font picture of the rare words as the retrieval request, the processing end needs to perform characteristic extraction on the picture to form corresponding electronic words for retrieval and matching, if the automatic extraction fails, the part of the content is manually marked, and the manually analyzed content is fed back to the request end.
Preferably, the local presentation unit includes a ZhuYin unit, and the specific flow is as follows:
inputting an ancient text full text for analyzing and obtaining a corresponding ancient text;
removing punctuation marks, namely performing symbol removal processing according to the whole ancient texts, and extracting corresponding Chinese characters for pronunciation marking conversion;
extracting a pronunciation marking unit, namely sequentially intercepting at most seven Chinese characters from the beginning of the full text at each time to serve as a pronunciation marking unit phrase;
sending a pronunciation marking unit phrase request, initiating a retrieval request to a cloud processor or a local processor according to a request phrase, and inquiring whether pinyin of the marking unit exists or not;
the server retrieves the corresponding dictionary according to the phrase unit request of the pronunciation marking unit, and after the corresponding dictionary is matched with the corresponding content, the server returns the marked pronunciation of the processing unit to the request end;
if the marking unit does not mark all the pinyin, continuing submitting the marking request by reducing the length of the word group of the retrieval unit and the word group which is not marked with the pinyin until marking the complete pinyin of the text.
Preferably, the phonetic notation unit comprises a pronunciation annotation request processing unit, the pronunciation annotation request processing unit is located at the cloud or is arranged locally and is mainly used for processing pronunciation annotations, the processing end sequentially analyzes whether the requested pronunciation annotation unit is a polyphone character, whether the requested pronunciation annotation unit is a polyphone, whether the requested pronunciation annotation unit is a phrase pronunciation or not, whether a proper noun pronounces or not, and then the best matching pronunciation annotation is returned, and if the requested pronunciation annotation unit is a polyphone annotation, other pronunciations are also returned to the request end to make secondary reference for the request end.
Compared with the prior art, the invention has the beneficial effects that: the system automatically processes big data, integrates various dictionaries, adds paraphrases word by word, intelligently distinguishes and analyzes pinyin, so that a reader can smoothly browse and read ancient scripts, the learning cost is greatly reduced, and the reading experience is greatly improved.
Drawings
FIG. 1 is a block diagram of a cloud-based intelligent paraphrasing phonetic notation system according to the present invention;
FIG. 2 is a block diagram of a client-side unit component of a cloud-based intelligent paraphrasing phonetic system according to the present invention;
FIG. 3 is a block diagram of a server of the cloud-based intelligent paraphrasing phonetic system according to the present invention;
FIG. 4 is a phonetic notation flowchart of the cloud-based intelligent paraphrase phonetic notation system of the present invention;
FIG. 5 is a flow chart of ancient paraphrase of the cloud-based intelligent paraphrase phonetic notation system of the present invention;
fig. 6 is a flowchart illustrating the ancient Chinese dictionary optimization process of the cloud-based intelligent paraphrase phonetic notation system according to the present invention.
In the figure: 110 client, 120 server, 111 Buddha entering unit, 112 text preprocessing unit, 113 service request unit, 114 request receiving unit, 115 local presenting unit, 121 receiving request unit, 122 logic processing unit, 123 dictionary retrieving unit, 124 dictionary unit, 125 dictionary management unit.
Detailed Description
Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. It should be understood that the description is illustrative only and is not intended to limit the scope of the present disclosure. Moreover, in the following description, descriptions of well-known structures and techniques are omitted so as to not unnecessarily obscure the concepts of the present disclosure.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The words "a", "an" and "the" and the like as used herein are also intended to include the meanings of "a plurality" and "the" unless the context clearly dictates otherwise. Furthermore, the terms "comprises," "comprising," and the like, as used herein, specify the presence of stated features, steps, operations, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The words "a", "an" and "the" and the like as used herein are also intended to include the meanings of "a plurality" and "the" unless the context clearly dictates otherwise. Furthermore, the terms "comprises," "comprising," and the like, as used herein, specify the presence of stated features, steps, operations, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components.
All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art unless otherwise defined. It is noted that the terms used herein should be interpreted as having a meaning that is consistent with the context of this specification and should not be interpreted in an idealized or overly formal sense.
As shown in fig. 1, a system architecture according to this embodiment may include a client 110 and a server 120. The client side mainly processes interactive contents of the user, such as inputting and displaying of ancient texts, and is responsible for interaction with readers or the user, and the server mainly is responsible for analyzing the ancient texts.
According to different application scenes, the server can be arranged in a local and cloud remote mode, if the server is arranged in the local mode, the client-side contact does not need to pass through a network, a network medium is not needed, and if the server is arranged in the cloud side, the client-side communication network communicates with the server. In some non-network environments, the server may be disposed locally and still be used normally in this embodiment.
As shown in fig. 2, the client 110 mainly comprises an ancient text entry unit 111, a text preprocessing unit 112, a service request unit 113, a request receiving unit 114, and a local presentation unit 115.
In the ancient writing unit 111, the software component unit is mainly responsible for the import work of the ancient text, and the ancient text can be imported into the system in the form of text or picture through the unit and used for analyzing and acquiring the corresponding ancient text.
In the text preprocessing unit 112, some preprocessing is performed on the imported ancient texts, such as the initial arrangement and filtering of punctuation marks, special symbols, paragraphs and pictures of the texts, and according to the whole ancient texts, symbol removal processing and paragraph processing are performed to extract corresponding Chinese characters for traditional and simplified conversion.
In the service request unit 113, a corresponding interpretation response is requested from the server according to the user's requirement for interpretation of ancient texts or phonetic notation.
In the request receiving unit 114, the server's interpretation response is received and returned to the local for further analysis and processing.
In the local presenting unit 115, the interpretation data returned by the server is compared with the original text, the phonetic notation is added at the corresponding position of the original text, and the corresponding simplified Chinese and explanation are added, and finally, a complete ancient text parsing text which is easy to read and understand is presented.
As shown in fig. 3, the server 120 is mainly composed of a reception request unit 121, a logical processing unit 122, a dictionary retrieving unit 123, a dictionary unit 124, and a dictionary managing unit 125.
The receiving request unit 121 is mainly responsible for receiving a service request sent by a client. The client may send the parsed service request in a local or network manner.
In the logic processing unit 122, the logic processing part of the retrieval unit is mainly processed, and how to logically organize the retrieval unit and the retrieval algorithm to achieve faster and more accurate retrieval of the corresponding information.
In the dictionary retrieving unit 123, how to obtain corresponding data information by retrieving a dictionary is mainly processed, and the pronunciation, simplified form and explanation of the corresponding traditional form are found by retrieving the dictionary, which is a key part of the embodiment of the present disclosure, and the flow will be described in detail later.
In the dictionary unit 124, databases of dictionaries mainly include an ancient dictionary for searching ancient retrieval information, a common chinese dictionary such as a thesaurus for general retrieval, and a rarely used word image-text dictionary without electronic coding.
In the dictionary managing unit 125, functions of managing the dictionary in the dictionary unit 124, maintaining and modifying the database, and the like are mainly included.
As shown in fig. 4, the ancient phonetic notation process includes operations S210 to S292. Wherein:
in operation S210, original ancient text data is read from the original ancient text.
In operation S220, the original ancient text data is preprocessed, including removing non-chinese character content such as punctuation marks, and preprocessing information related to paragraph and layout such as line feed.
In the operation of S230, the preprocessed ancient text is obtained from the operation of S220, and the phonetic notation processing is performed on the ancient text needing phonetic notation from the beginning of the ancient text by using the longest seven chinese characters as phonetic notation word groups, and the reason why the smallest one chinese character is not used as a phonetic notation unit for the first time is that a large number of polyphonic characters exist in the chinese characters, especially in the ancient text, and the method for processing polyphonic characters uses the front and back of the characters as reference standards, especially the words as phonetic notation units, which can greatly improve the accuracy, while in the ancient text, some longer words exist, and the accuracy of phonetic notation can be improved by using the seven characters as the longest words, but while the accuracy is improved, the efficiency of phonetic notation is reduced, the phonetic notation flow is not affected by using several chinese characters as phonetic notation unit word groups for the first time, and the smooth implementation of the embodiment of the present disclosure.
In operation S240, when the server 120 receives the phonetic notation request from the client 110, the server first starts to search whether there is any relevant matching content in the ancient dictionary, which includes a large number of ancient words, including specialized words in relevant fields such as proper expressions, personal names and place names. Since ancient understanding is mainly used in the disclosed embodiment, there is a high probability that the vocabulary will appear in the ancient dictionary. Searching the dictionary preferentially can improve the search matching efficiency.
In the operation of S250, when the vocabulary of the phonetic notation request is not hit in the ancient Chinese vocabulary in the operation of S240, the vocabulary is likely to be a common vocabulary, and the phonetic notation search can be performed through a conventional dictionary such as "chinese dictionary", and "kangxi dictionary", and "general dictionary", respectively.
In the operation S260, when the vocabulary cannot be retrieved in both the ancient dictionary and the conventional general dictionary or when the user directly provides the picture word retrieval, the operation is performed until the operation indicates that the vocabulary is a rare word which is not normally displayed in the system because it is not in the national standard character table, so that the database retrieval is performed in the form of a picture. A significant amount of this type of uncommon word text is provided in the disclosed embodiments for this retrieval operation.
In the operation of S270, if the submitted vocabulary has not retrieved the corresponding phonetic notation after the step, the number of chinese characters in the phrase is reduced, and the vocabulary is used as a new retrieval unit to perform the retrieval again, and the operation of S240 is restarted. Until the Chinese characters in the whole phonetic notation phrase unit are phonetic notation completed, the phonetic notation step is regarded as successful retrieval. And re-extracting a new phonetic notation unit to perform a new phonetic notation operation and executing S230 operation. If only one Chinese character exists and the corresponding phonetic notation is not found in the dictionary, the system can optimize the Chinese character, and the phonetic notation operation is completed through machine intelligent learning and a background personnel manual marking method.
In S280, some special playback sounds are repaired with secondary phonetic notation according to the ancient Chinese, i.e. special literary forms, such as the light pronunciation of a chinese character, which may have yi according to the context, the pronunciation of two tones, and the pronunciation of four tones, etc., and the operations are processed in a unified way. And ending the phonetic notation operation with the phonetic notation phrase as the unit.
In the operation of S290, it is checked whether there is a remaining part of the ancient text full text which has not been annotated with sound, and if so, the remaining part which has not been annotated with sound is continued to the operation of S230. Otherwise, the ancient full text is finished.
As shown in fig. 5, the ancient and ancient text paraphrasing and annotating process includes operations S310 to S329, in which:
in operation S310, original ancient text data is read from the original ancient text, and the ancient text is prepared for simplified and simplified conversion and annotation.
In operation S320, the original ancient text data is preprocessed, including removing non-chinese character content such as punctuation marks, and preprocessing information related to paragraph and layout such as line feed.
In operation S330, each time a chinese character is selected as a conversion unit for the traditional Chinese character conversion, and the server sends a request application.
In operation S340, a search is first performed to determine whether the original complex character exists in the ancient dictionary, and if so, the original complex character is converted into a simplified character.
In S350, in the ancient text, since there is a problem that one traditional character can be converted into a plurality of simplified characters according to different contexts, if the traditional character can be converted into a plurality of traditional characters, the simplified characters corresponding to the traditional character can be correctly matched only by taking phrases as units, and the length of increasing or decreasing the search for chinese characters needs to be increased or decreased, so that the previous single character search is changed into a multi-character search, as in operation 351.
In operation S360, if the traditional word does not appear in the special ancient dictionary, the traditional universal dictionary is searched for whether the simplified word exists.
In S370, when the vocabulary is not retrieved in both the ancient dictionary and the conventional general dictionary, or when the user directly provides the picture word retrieval, the operation is executed until the word is rarely used as the word, which is not displayed in the national standard character table and is therefore normally displayed in the system, so that the database retrieval is performed in the form of a picture. A significant amount of this type of uncommon word text is provided in the disclosed embodiments for this retrieval operation.
In the operation of S380, if there is only one chinese character and the corresponding traditional Chinese character is not found in the dictionary and is converted into a simplified Chinese character, the user submits a manual tagging application mark to complete the traditional Chinese character conversion operation.
In the operation of S390, when a traditional chinese of a chinese character is found, the information read by the traditional chinese in the dictionary for the reason of the annotation in the dictionary is returned to the client, which is more beneficial for the reader to understand the ancient texts
In operation S391, it is checked whether there is a remaining part of the ancient text full text which has not been annotated with sound, and this continues operation S230 with the remaining part which has not been annotated with sound. And if the original edition of the ancient Chinese is not converted into the original edition of the ancient Chinese, the original edition of the ancient Chinese is converted into the original edition of the ancient Chinese conveniently.
As shown in fig. 6, the ancient dictionary optimization procedure includes operations S410 to S480.
The system of the invention comprises the phonetic notation of a plurality of ancient languages and the interconversion of the traditional and simple of the ancient languages, and comprises a traditional Chinese corresponding to a plurality of simple language versions, and the query and retrieval of a simple language version corresponding to a plurality of traditional versions are mostly dependent on the custom-generated ancient dictionary, so the real-time optimization of the ancient dictionary database is very important.
In operation S410, a new round of optimization of the ancient dictionary is performed as required.
In operation S420, the ancient articles with the existing paraphrases that have been checked are acquired as a data training set of the dictionary.
In S430, a hidden markov model of a machine learning artificial intelligence algorithm is selected to perform word frequency statistical analysis on the data.
In S440, according to the word frequency statistical analysis, the probability statistics of the text existing in each combination of phrases can be roughly obtained.
In S450, according to the database rule sorted manually, the database rule defines the rules of whether the complex character has pronunciation corresponding to the complex character, whether the complex character has polyphone pronunciation, whether the complex character has special complex characters, whether there are many different types of characters, whether there are common and false characters, whether the complex character can be directly converted into complex characters, etc., and the result of the word frequency statistics is corrected for the second time, and the probability distribution of the corresponding word group is adjusted in the word frequency statistics. Generating new word frequency statistics
In S460, a new ancient dictionary is rebuilt in the form of a dictionary organization according to the new word frequency statistics.
In S470, the new ancient sentence dictionary is used to parse the new ancient sentence, so as to obtain the new ancient sentence with paraphrase.
In S480, according to the requirement of optimizing the ancient dictionary, a new round of optimization of the ancient dictionary can be performed on the newly obtained paraphrased ancient texts to improve the accuracy of the ancient dictionary.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and the technical solutions and the inventive concepts thereof according to the present invention should be equivalent or changed within the scope of the present invention.
Claims (5)
1. The cloud-based intelligent paraphrasing and phonetic notation system is characterized by comprising a client (110) and a server (120), wherein the client (110) comprises an ancient writing entry unit (111), a text preprocessing unit (112), a service request unit (113), a request receiving unit (114) and a local presentation unit (115), and the server (120) comprises a receiving request unit (121), a logic processing unit (122), a dictionary retrieval unit (123), a dictionary unit (124) and a dictionary management unit (125).
2. The cloud-based intelligent paraphrasing and phonetic notation system of claim 1, wherein the text preprocessing unit (112) is configured to convert traditional content of ancient languages into corresponding simplified content, and the specific steps are as follows:
inputting an ancient text full text for analyzing and obtaining a corresponding ancient text;
removing punctuation marks, carrying out symbol removal processing and paragraph processing according to the whole ancient texts, and extracting corresponding Chinese characters for traditional and simple conversion;
extracting conversion Chinese character units, namely extracting one Chinese character from the beginning of the full text as one conversion unit each time;
sending a request for matching a retrieval unit, initiating a retrieval request to a cloud processor or a local processor according to the retrieval unit, inquiring whether the simplified character of the retrieval unit exists, and taking the character as the retrieval unit in a picture form if some rarely-used characters and special-shaped characters do not have corresponding character library codes;
the processor searches the unit request, according to searching the unit array, the server checks whether the searching unit is a special vocabulary for Buddhism, whether the searching unit is a general complex word, whether the searching unit is a uncommon word, whether the searching unit is a special word, whether the searching unit exists in a dictionary, and if the searching unit exists, the corresponding simplified word and corresponding explanation of the request are returned;
if the converted traditional Chinese character finds a plurality of matched simplified Chinese characters, the length of the converted traditional Chinese character is increased to convert the traditional Chinese character into a phrase, and the retrieval request is continuously submitted until the retrieval unit is the only corresponding simplified Chinese character.
3. The cloud-based intelligent paraphrasing and phonetic notation system as claimed in claim 1, wherein the dictionary unit (124) comprises a dictionary, an ancient dictionary and a obscure word picture word dictionary, the dictionary management unit (125) is mainly used for managing and maintaining a Buddhist specific dictionary and obscure word picture words, the dictionary is located in the cloud or is arranged locally, and is mainly used for receiving a query request, receiving a complicated and simple conversion and phonetic notation request of a client, querying and searching corresponding entries in the dictionary through a matching algorithm, and sending the corresponding entries back to the request end;
the ancient Chinese has rare words without corresponding word stock codes, for the part of the request, the retrieval unit takes the font picture of the rare words as the retrieval request, the processing end needs to perform characteristic extraction on the picture to form corresponding electronic words for retrieval and matching, if the automatic extraction fails, the part of the content is manually marked, and the manually analyzed content is fed back to the request end.
4. The cloud-based intelligent paraphrasing phonetic notation system of claim 1, wherein the local presentation unit (115) comprises a phonetic notation unit, and the specific process is as follows:
inputting an ancient text full text for analyzing and obtaining a corresponding ancient text;
removing punctuation marks, namely performing symbol removal processing according to the whole ancient texts, and extracting corresponding Chinese characters for pronunciation marking conversion;
extracting a pronunciation marking unit, namely sequentially intercepting at most seven Chinese characters from the beginning of the full text at each time to serve as a pronunciation marking unit phrase;
sending a pronunciation marking unit phrase request, initiating a retrieval request to a cloud processor or a local processor according to a request phrase, and inquiring whether pinyin of the marking unit exists or not;
the server retrieves the corresponding dictionary according to the phrase unit request of the pronunciation marking unit, and after the corresponding dictionary is matched with the corresponding content, the server returns the marked pronunciation of the processing unit to the request end;
if the marking unit does not mark all the pinyin, continuing submitting the marking request by reducing the length of the word group of the retrieval unit and the word group which is not marked with the pinyin until marking the complete pinyin of the text.
5. The cloud-based intelligent paraphrasing phonetic notation system according to claim 4 is characterized in that the phonetic notation unit comprises a pronunciation annotation request processing unit, the pronunciation annotation request processing unit is located in the cloud or is arranged locally and is mainly used for processing pronunciation annotations, the processing end analyzes in sequence, whether the requested pronunciation annotation unit is a polyphonic character, whether the requested pronunciation annotation unit is a soft tone, whether the requested pronunciation annotation unit is a phrase pronunciation, whether a proper noun pronunciation exists, and then the best matching pronunciation annotation is returned, and if the requested pronunciation annotation unit is a polyphonic annotation, other pronunciations are returned to the request end to make secondary reference to the request end.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810984735.0A CN110874527A (en) | 2018-08-28 | 2018-08-28 | Cloud-based intelligent paraphrasing and phonetic notation system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810984735.0A CN110874527A (en) | 2018-08-28 | 2018-08-28 | Cloud-based intelligent paraphrasing and phonetic notation system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110874527A true CN110874527A (en) | 2020-03-10 |
Family
ID=69714278
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810984735.0A Pending CN110874527A (en) | 2018-08-28 | 2018-08-28 | Cloud-based intelligent paraphrasing and phonetic notation system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110874527A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112632967A (en) * | 2020-12-30 | 2021-04-09 | 广东德诚科教有限公司 | Chinese pinyin automatic generation method and device oriented to set strategy |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH04259060A (en) * | 1991-02-14 | 1992-09-14 | Fujitsu Ltd | Document reading support device |
| CN1099498A (en) * | 1993-03-26 | 1995-03-01 | 卡西欧计算机公司 | Translating apparatus capable of displaying original words and translated words in one-to-one corresponding relationship |
| CN1134568A (en) * | 1995-03-24 | 1996-10-30 | 松下电器产业株式会社 | Simplified Chinese character-the original complex form changingover apparatus |
| CN101470751A (en) * | 2007-12-29 | 2009-07-01 | 文小凡 | Words checking system and method based on computer network |
| CN101520786A (en) * | 2008-02-27 | 2009-09-02 | 北京搜狗科技发展有限公司 | Method for realizing input method dictionary and input method system |
| CN101533388A (en) * | 2008-03-11 | 2009-09-16 | 林烈诚 | Original text note display method |
| JP2010277178A (en) * | 2009-05-26 | 2010-12-09 | Seiko Instruments Inc | Electronic dictionary, search system, search method, and program |
| CN102346731A (en) * | 2010-08-02 | 2012-02-08 | 联想(北京)有限公司 | File processing method and file processing device |
| TW201224790A (en) * | 2010-12-02 | 2012-06-16 | Cheng-Yan Gao | Method and system for analyzing Chinese auxiliary reading and pronunciation |
| CN102929852A (en) * | 2012-10-15 | 2013-02-13 | 福建榕基软件股份有限公司 | Method and system for realizing conversion of simplified and traditional Chinese characters in rich text editor |
| CN103488305A (en) * | 2013-08-13 | 2014-01-01 | 南阳师范学院 | Chinese input method system with simplified and traditional Chinese contrasts |
| CN104169912A (en) * | 2012-03-27 | 2014-11-26 | 株式会社东芝 | Information processing terminal and method, and information management apparatus and method |
| CN104899187A (en) * | 2014-03-06 | 2015-09-09 | 武汉元宝创意科技有限公司 | Man-computer interaction word segmentation and semantic marking method and man-computer interaction word segmentation and semantic marking system |
| CN104915364A (en) * | 2014-03-14 | 2015-09-16 | 欧姆龙株式会社 | Information processing system and information processing method, information processing server and terminal apparatus |
| US20170308524A1 (en) * | 2016-04-26 | 2017-10-26 | International Business Machines Corporation | Structured dictionary population utilizing text analytics of unstructured language dictionary text |
-
2018
- 2018-08-28 CN CN201810984735.0A patent/CN110874527A/en active Pending
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH04259060A (en) * | 1991-02-14 | 1992-09-14 | Fujitsu Ltd | Document reading support device |
| CN1099498A (en) * | 1993-03-26 | 1995-03-01 | 卡西欧计算机公司 | Translating apparatus capable of displaying original words and translated words in one-to-one corresponding relationship |
| CN1134568A (en) * | 1995-03-24 | 1996-10-30 | 松下电器产业株式会社 | Simplified Chinese character-the original complex form changingover apparatus |
| CN101470751A (en) * | 2007-12-29 | 2009-07-01 | 文小凡 | Words checking system and method based on computer network |
| CN101520786A (en) * | 2008-02-27 | 2009-09-02 | 北京搜狗科技发展有限公司 | Method for realizing input method dictionary and input method system |
| CN101533388A (en) * | 2008-03-11 | 2009-09-16 | 林烈诚 | Original text note display method |
| JP2010277178A (en) * | 2009-05-26 | 2010-12-09 | Seiko Instruments Inc | Electronic dictionary, search system, search method, and program |
| CN102346731A (en) * | 2010-08-02 | 2012-02-08 | 联想(北京)有限公司 | File processing method and file processing device |
| TW201224790A (en) * | 2010-12-02 | 2012-06-16 | Cheng-Yan Gao | Method and system for analyzing Chinese auxiliary reading and pronunciation |
| CN104169912A (en) * | 2012-03-27 | 2014-11-26 | 株式会社东芝 | Information processing terminal and method, and information management apparatus and method |
| CN102929852A (en) * | 2012-10-15 | 2013-02-13 | 福建榕基软件股份有限公司 | Method and system for realizing conversion of simplified and traditional Chinese characters in rich text editor |
| CN103488305A (en) * | 2013-08-13 | 2014-01-01 | 南阳师范学院 | Chinese input method system with simplified and traditional Chinese contrasts |
| CN104899187A (en) * | 2014-03-06 | 2015-09-09 | 武汉元宝创意科技有限公司 | Man-computer interaction word segmentation and semantic marking method and man-computer interaction word segmentation and semantic marking system |
| CN104915364A (en) * | 2014-03-14 | 2015-09-16 | 欧姆龙株式会社 | Information processing system and information processing method, information processing server and terminal apparatus |
| US20170308524A1 (en) * | 2016-04-26 | 2017-10-26 | International Business Machines Corporation | Structured dictionary population utilizing text analytics of unstructured language dictionary text |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112632967A (en) * | 2020-12-30 | 2021-04-09 | 广东德诚科教有限公司 | Chinese pinyin automatic generation method and device oriented to set strategy |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111968649B (en) | Subtitle correction method, subtitle display method, device, equipment and medium | |
| US8060357B2 (en) | Linguistic user interface | |
| US6393389B1 (en) | Using ranked translation choices to obtain sequences indicating meaning of multi-token expressions | |
| JP4463256B2 (en) | System and method for providing automatically completed recommended words that link multiple languages | |
| US7092870B1 (en) | System and method for managing a textual archive using semantic units | |
| EP0971294A2 (en) | Method and apparatus for automated search and retrieval processing | |
| CN107798123B (en) | Knowledge base and establishing, modifying and intelligent question and answer methods, devices and equipment thereof | |
| US6286014B1 (en) | Method and apparatus for acquiring a file to be linked | |
| WO1997004405A9 (en) | Method and apparatus for automated search and retrieval processing | |
| US10997223B1 (en) | Subject-specific data set for named entity resolution | |
| JP2000200291A (en) | Method for automatically detecting selected character string in text | |
| US20110040553A1 (en) | Natural language processing | |
| WO2012159558A1 (en) | Natural language processing method, device and system based on semantic recognition | |
| CN111160007B (en) | Search method and device based on BERT language model, computer equipment and storage medium | |
| Wehrmeyer | A corpus for signed language<? br?> interpreting research | |
| CN111950301A (en) | English translation quality analysis method and system for Chinese translation and English translation | |
| CN101441626A (en) | Multimedia retrieval system and method | |
| CN112541109B (en) | Answer abstract extraction method and device, electronic equipment, readable medium and product | |
| CN103164398A (en) | Chinese-Uygur language electronic dictionary and automatic translating Chinese-Uygur language method thereof | |
| CN103164397A (en) | Chinese-Kazakh electronic dictionary and automatic translating Chinese- Kazakh method thereof | |
| WO2006122361A1 (en) | A personal learning system | |
| CN110874527A (en) | Cloud-based intelligent paraphrasing and phonetic notation system | |
| CN103164396A (en) | Chinese-Uygur language-Kazakh-Kirgiz language electronic dictionary and automatic translating Chinese-Uygur language-Kazakh-Kirgiz language method thereof | |
| CN103164395A (en) | Chinese-Kirgiz language electronic dictionary and automatic translating Chinese-Kirgiz language method thereof | |
| CN106776590A (en) | A kind of method and system for obtaining entry translation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |