CN110457695A - A kind of online text error correction method and system - Google Patents
A kind of online text error correction method and system Download PDFInfo
- Publication number
- CN110457695A CN110457695A CN201910696146.7A CN201910696146A CN110457695A CN 110457695 A CN110457695 A CN 110457695A CN 201910696146 A CN201910696146 A CN 201910696146A CN 110457695 A CN110457695 A CN 110457695A
- Authority
- CN
- China
- Prior art keywords
- character
- character string
- name
- library
- sentence
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2468—Fuzzy queries
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Machine Translation (AREA)
- Document Processing Apparatus (AREA)
Abstract
The invention discloses a kind of online text error correction method and systems, it is sentence by the character recognition for first keying in user, character string is tied to language piece according to the cohesion of intercharacter in sentence, it can identify the case where can not being tied to language piece with the presence or absence of continuous more than two characters in sentence, it is higher then to there is a possibility that wrong word, due to during user's typing character, it usually will appear wrong word caused by Pinyin Input selection mistake, therefore this method passes through the substitution character of the identical phonetic of retrieval, wrong word in former character is replaced, during user's typing character, also it usually will appear wrong word caused by single phonetic key error, therefore this method to any one progress Fuzzy Processing in each character phonetic and carries out fuzzy search, substitution character is found to be replaced wrong word, can effectively to The character that family is keyed in carries out online text error correction.
Description
Technical field
The present invention relates to word processing field, a kind of online text error correction method and system are particularly related to.
Background technique
During user inputs text, the case where inevitably will appear wrong word, but user itself it is often difficult to find
Input error, this results in the article being finally completed there are wrong word, influences other people understandings to article, or influence
Personal and enterprise image problem;
In existing word processor, although there are doubtful wrong word prompting functions, often only user is keyed in
Character be compared with common character library, if the character that user keys in is not belonging to common character library, character string is marked, but
This method had not both accounted for the structure of sentence itself and the use habit of Chinese, can not carry out automatic error-correcting, effect
It is limited, it is therefore desirable to a kind of online text error correction method and system.
Summary of the invention
In view of this, improving word processing it is an object of the invention to propose a kind of online text error correction method and system
Accuracy and efficiency.
Based on a kind of above-mentioned purpose online text error correction method provided by the invention, this method includes:
The end of the sentence class punctuation mark in several characters that user keys in is found, by the word between adjacent end of the sentence class punctuation mark
Symbol is judged as sentence;
Sentence is pre-processed, character string is tied to by language piece according to the cohesion of intercharacter;
If language piece can not be tied to by continuous more than two characters occur, in conjunction with the phonetic of cohesion and each character in data
It is retrieved one by one in library, judges whether the substitution character that can find identical phonetic, continuation character is enable to be tied to cohesion
High language piece;
If can find, former character is replaced using character is substituted in database, if cannot find, to each word
Any one progress Fuzzy Processing in phonetic is accorded with, fuzzy search one by one is carried out in the database, judges whether to find similar
The substitution character of phonetic enables continuation character to be tied to the high language piece of cohesion;
If can find, former character is replaced using character is substituted in database, if cannot find, to the company
Continuous character is marked.
Preferably, when language piece can not be tied to by continuous more than two characters occur, the phonetic of the continuation character string is extracted,
And retrieval whether there is the name of identical phonetic in name library, if retrieving the name of identical phonetic, by the name and continuously
Character string is compared, and the continuation character is not marked if comparison is identical, if comparing different by the continuation character string
It is modified to name.
Preferably, when retrieval whether there is the name of identical phonetic in name library, if identical phonetic can not be retrieved
Name carries out fuzzy search, if retrieving phase then to any one progress Fuzzy Processing in character string phonetic in name library
Like the name of phonetic, which is compared with continuation character string, the continuation character is not marked if comparison is identical,
The continuation character string is modified to name if comparing difference.
Preferably, this method further include:
When retrieving in sentence and multiple names occur, and using the character for indicating arranged side by side between each name, sorted according to name
Sequence in library resequences to the sequence of multiple names.
Preferably, this method further include:
When being replaced to former character, the character string where former character is recorded in wrong word library, as Wrongly-written or mispronounced character
String, if having existed the character string in wrong word library, records number of repetition;
When user keys in the Wrongly-written or mispronounced character string, if the number of repetition of the Wrongly-written or mispronounced character string in wrong word library is more than setting
Threshold value is then automatically replaced the Wrongly-written or mispronounced character string.
A kind of online text error correction system, comprising:
Database module, the sentence patterns collection and everyday words for being stored with reaction words cohesion collect;
Sentence discrimination module, the end of the sentence class punctuation mark in several characters keyed according to user, to the sentence in character
Differentiated;
Character string is tied to language piece according to the cohesion of intercharacter in sentence by preprocessing module;
Retrieval module, in the database to continuous more than two characters that can not be tied to language piece carry out retrieval one by one and
Fuzzy search one by one judges whether the substitution character that can find same or similar phonetic, continuation character is enable to be tied to cohesion
The high language piece of property;
Correction module, substitution character is replaced former character in active bank;
Character and character string can be marked in mark module.
It preferably, further include name library in database, retrieval module can carry out retrieval and mould to character string according to name library
Paste retrieval, retrieves the name of identical phonetic;
Correction module can be modified character string according to name library.
Preferably, system further includes sorting module, further includes name sequence library in database, sorting module can be according to name
Sequence in sequence library resequences to the sequence of multiple names.
It preferably, further include wrong word library in database, it, will be where former character when correction module is replaced former character
Character string be recorded in wrong word library, as Wrongly-written or mispronounced character string, if having existed the character string in wrong word library, record weight
Again it counts;
When user keys in the Wrongly-written or mispronounced character string, retrieval module retrieves wrong word library, if the Wrongly-written or mispronounced character string exists
Number of repetition in wrong word library is more than given threshold, then correction module is automatically replaced the Wrongly-written or mispronounced character string.
From the above it can be seen that online text error correction method provided by the invention and system, by first by user's key
The character recognition entered is sentence, and character string is tied to language piece according to the cohesion of intercharacter in sentence, can identify sentence
In the case where can not being tied to language piece with the presence or absence of continuous more than two characters, then it is higher a possibility that wrong word occur, by
Wrong word caused by mistake is selected in during user's typing character, usually will appear Pinyin Input, therefore this method passes through
The substitution character for retrieving identical phonetic, is replaced the wrong word in former character, due to user's typing character during,
It usually will appear wrong word caused by single phonetic key error, therefore this method is to any one progress mould in each character phonetic
Paste handles and carries out fuzzy search, finds substitution character and is replaced to wrong word, the character that can effectively key in user
Carry out online text error correction.
Detailed description of the invention
Fig. 1 is the online text error correction method flow diagram of the embodiment of the present invention;
Fig. 2 is the online text error correction system module diagram of the embodiment of the present invention.
Specific embodiment
To make the objectives, technical solutions, and advantages of the present invention clearer, below in conjunction with specific embodiment, and reference
Attached drawing, the present invention is described in more detail.
It should be noted that all statements for using " first " and " second " are for differentiation two in the embodiment of the present invention
The non-equal entity of a same names or non-equal parameter, it is seen that " first " " second " only for the convenience of statement, does not answer
It is interpreted as the restriction to the embodiment of the present invention, subsequent embodiment no longer illustrates this one by one.
A kind of online text error correction method, comprising the following steps:
The end of the sentence class punctuation mark in several characters that user keys in is found, by the word between adjacent end of the sentence class punctuation mark
Symbol is judged as that sentence, above-mentioned end of the sentence class punctuation mark refer to that fullstop, exclamation mark, question mark etc. indicate the punctuation mark of Statement Completion.
Sentence is pre-processed, character string is tied to by language piece according to the cohesion of intercharacter, above-mentioned intercharacter it is interior
Poly- property, the sentence patterns and structure of digit symbol Chinese use habit, such as polarization phrase, dynamic benefit phrase, guest's Jie phrase;
If language piece can not be tied to by continuous more than two characters occur, in conjunction with the phonetic of cohesion and each character in data
It is retrieved one by one in library, judges whether the substitution character that can find identical phonetic, continuation character is enable to be tied to cohesion
High language piece, language piece can not be tied to by more than two characters occur in a sentence, then it is very likely that there is the feelings of wrong word
Condition;
If can find, former character is replaced using character is substituted in database, if cannot find, to each word
Any one progress Fuzzy Processing in phonetic is accorded with, fuzzy search one by one is carried out in the database, judges whether to find similar
The substitution character of phonetic enables continuation character to be tied to the high language piece of cohesion;
If can find, former character is replaced using character is substituted in database, if cannot find, to the company
Continuous character is marked, and the modes such as underscore, mark color can be used in mark mode.
This method is sentence by the character recognition for first keying in user, according to the cohesion of intercharacter in sentence by character
String is tied to language piece, can identify the case where can not being tied to language piece with the presence or absence of continuous more than two characters in sentence,
It is higher a possibility that wrong word then occur, wrong due to during user's typing character, usually will appear Pinyin Input selection
Wrong word caused by accidentally, therefore this method is replaced the wrong word in former character by the substitution character of the identical phonetic of retrieval,
During due to user's typing character, it also usually will appear wrong word caused by single phonetic key error, therefore this method pair
Any one progress Fuzzy Processing in each character phonetic simultaneously carries out fuzzy search, finds substitution character and replaces to wrong word
It changes, online text error correction effectively can be carried out to the character that user keys in.
In an embodiment of the present invention, this method further comprises continuous more than two characters occur not being tied to
When language piece, the phonetic of the continuation character string is extracted, and retrieval whether there is the name of identical phonetic in name library, if retrieving
The name is compared the name of identical phonetic with continuation character string, does not mark to the continuation character if comparison is identical
The continuation character string is modified to name if comparing difference by note.
During inputting character, it is often necessary to name is inputted, and name is obviously not belonging to the common words in Chinese,
Therefore it is higher a possibility that continuation character can not bind language piece occur, therefore whether there is in this method by being retrieved in name library
The name of identical phonetic, judges whether the character string belongs to name.
In an embodiment of the present invention, this method further comprises that retrieval is with the presence or absence of identical phonetic in name library
When name, if the name of identical phonetic can not be retrieved, to any one progress Fuzzy Processing in character string phonetic, in people
Name carries out fuzzy search in library, if retrieving the name of similar pinyin, which is compared with continuation character string, if comparing
It is identical, which is not marked, the continuation character string is modified to name if comparing difference.
When retrieving name library, the same method for using Fuzzy Processing and fuzzy search can key in phonetic this method
The name of mistake carries out on-line amending.
In an embodiment of the present invention, this method further comprises retrieving in sentence multiple names occur, and each name
Between using character arranged side by side is indicated when, resequenced according to the name sequence in library of sorting to the sequence of multiple names.
For the name in enterprise is keyed in, when multiple names occur indicates side by side, it is often necessary to according to leader's grade
Not Deng sequence name is ranked up, then the sequence that this method can correct mistake automatically, above-mentioned expression character arranged side by side includes
The characters such as " pause mark ", "and" "AND".
In an embodiment of the present invention, this method further comprises, will be where former character when being replaced to former character
Character string is recorded in wrong word library, records repetition if having existed the character string in wrong word library as Wrongly-written or mispronounced character string
Number;
When user keys in the Wrongly-written or mispronounced character string, if the number of repetition of the Wrongly-written or mispronounced character string in wrong word library is more than setting
Threshold value is then automatically replaced the Wrongly-written or mispronounced character string.
Due to personal input habit, the mistake usually duplicated, the repetition that this method passes through record Wrongly-written or mispronounced character string
Number is modified replacement when keying in the Wrongly-written or mispronounced character string more than given threshold again automatically, improves processing effect of the invention
Rate, and by the input habit of association user, improve accuracy rate.
The present invention also provides a kind of online text error correction systems, including database module, are stored with reaction words cohesion
Sentence patterns collection and everyday words collect;
Sentence discrimination module, the end of the sentence class punctuation mark in several characters keyed according to user, to the sentence in character
Differentiated;
Character string is tied to language piece according to the cohesion of intercharacter in sentence by preprocessing module;
Retrieval module, in the database to continuous more than two characters that can not be tied to language piece carry out retrieval one by one and
Fuzzy search one by one judges whether the substitution character that can find same or similar phonetic, continuation character is enable to be tied to cohesion
The high language piece of property;
Correction module, substitution character is replaced former character in active bank;
Character and character string can be marked in mark module.
It in an embodiment of the present invention, further include name library in database, retrieval module can be according to name library to character string
Retrieval and fuzzy search are carried out, the name of identical phonetic is retrieved;
Correction module can be modified character string according to name library.
In an embodiment of the present invention, system further includes sorting module, further includes name sequence library in database, sort mould
Block can resequence to the sequence of multiple names according to the sequence in name sequence library.
It in an embodiment of the present invention, further include wrong word library in database, when correction module is replaced former character,
Character string where former character is recorded in wrong word library, as Wrongly-written or mispronounced character string, if having existed the word in wrong word library
Symbol string, then record number of repetition;
When user keys in the Wrongly-written or mispronounced character string, retrieval module retrieves wrong word library, if the Wrongly-written or mispronounced character string exists
Number of repetition in wrong word library is more than given threshold, then correction module is automatically replaced the Wrongly-written or mispronounced character string.
It should be understood by those ordinary skilled in the art that: the discussion of any of the above embodiment is exemplary only, not
It is intended to imply that the scope of the present disclosure (including claim) is limited to these examples;Under thinking of the invention, above embodiments
Or can also be combined between the technical characteristic in different embodiments, step can be realized with random order, and be existed such as
Many other variations of the upper different aspect of the invention, for simplicity, they are not provided in details.
In addition, to simplify explanation and discussing, and in order not to obscure the invention, it can in provided attached drawing
It is connect with showing or can not show with the well known power ground of integrated circuit (IC) chip and other components.Furthermore, it is possible to
Device is shown in block diagram form, to avoid obscuring the invention, and this has also contemplated following facts, i.e., about this
The details of the embodiment of a little block diagram arrangements be height depend on will implementing platform of the invention (that is, these details should
It is completely within the scope of the understanding of those skilled in the art).Elaborating that detail (for example, circuit) is of the invention to describe
In the case where exemplary embodiment, it will be apparent to those skilled in the art that can be in these no details
In the case where or implement the present invention in the case that these details change.Therefore, these descriptions should be considered as explanation
Property rather than it is restrictive.
Although having been incorporated with specific embodiments of the present invention, invention has been described, according to retouching for front
It states, many replacements of these embodiments, modifications and variations will be apparent for those of ordinary skills.Example
Such as, discussed embodiment can be used in other memory architectures (for example, dynamic ram (DRAM)).
The embodiment of the present invention be intended to cover fall into all such replacements within the broad range of appended claims,
Modifications and variations.Therefore, all within the spirits and principles of the present invention, any omission, modification, equivalent replacement, the improvement made
Deng should all be included in the protection scope of the present invention.
Claims (9)
1. a kind of online text error correction method, which is characterized in that the described method includes:
The end of the sentence class punctuation mark in several characters that user keys in is found, the character between adjacent end of the sentence class punctuation mark is sentenced
Break as sentence;
Sentence is pre-processed, character string is tied to by language piece according to the cohesion of intercharacter;
If language piece can not be tied to by continuous more than two characters occur, in the database in conjunction with the phonetic of cohesion and each character
It is retrieved one by one, judges whether the substitution character that can find identical phonetic, so that continuation character is tied to cohesion high
Language piece;
If can find, former character is replaced using character is substituted in database, if cannot find, each character is spelled
Any one progress Fuzzy Processing in sound, carries out fuzzy search one by one in the database, judges whether that similar pinyin can be found
Substitution character, so that continuation character is tied to the high language piece of cohesion;
If can find, former character is replaced using character is substituted in database, if cannot find, to the consecutive word
Symbol is marked.
2. online text error correction method according to claim 1, which is characterized in that occur continuous more than two characters without
When method is tied to language piece, the phonetic of the continuation character string is extracted, and retrieval whether there is the name of identical phonetic in name library,
If retrieving the name of identical phonetic, which is compared with continuation character string, not to the consecutive word if comparison is identical
Symbol is marked, and the continuation character string is modified to name if comparing difference.
3. online text error correction method according to claim 2, which is characterized in that retrieval whether there is phase in name library
With phonetic name when, if the name of identical phonetic can not be retrieved, any one position in character string phonetic is obscured
Processing, fuzzy search is carried out in name library, if retrieving the name of similar pinyin, the name and continuation character string are compared
It is right, the continuation character is not marked if comparison is identical, the continuation character string is modified to name if comparing difference.
4. online text error correction method according to claim 2 or 3, which is characterized in that the method also includes:
When retrieving in sentence and multiple names occur, and using the character for indicating arranged side by side between each name, according in name sequence library
Sequence resequence to the sequence of multiple names.
5. online text error correction method according to claim 1, which is characterized in that the method also includes:
When being replaced to former character, the character string where former character is recorded in wrong word library, as Wrongly-written or mispronounced character string, if
The character string is had existed in wrong word library, then records number of repetition;
When user keys in the Wrongly-written or mispronounced character string, if the number of repetition of the Wrongly-written or mispronounced character string in wrong word library is more than setting threshold
Value, then be automatically replaced the Wrongly-written or mispronounced character string.
6. a kind of online text error correction system characterized by comprising
Database module, the sentence patterns collection and everyday words for being stored with reaction words cohesion collect;
Sentence discrimination module, the end of the sentence class punctuation mark in several characters keyed according to user, carries out the sentence in character
Differentiate;
Character string is tied to language piece according to the cohesion of intercharacter in sentence by preprocessing module;
Retrieval module carries out retrieval one by one and one by one to continuous more than two characters that can not be tied to language piece in the database
Fuzzy search judges whether the substitution character that can find same or similar phonetic, continuation character is enable to be tied to cohesion height
Language piece;
Correction module, substitution character is replaced former character in active bank;
Character and character string can be marked in mark module.
7. online text error correction system according to claim 6, which is characterized in that further include name in the database
Library, the retrieval module can carry out retrieval and fuzzy search to character string according to name library, retrieve the name of identical phonetic;
The correction module can be modified character string according to name library.
8. online text error correction system according to claim 7, which is characterized in that the system also includes sorting module,
It further include name sequence library in the database, the sorting module can be according to the sequence in name sequence library to multiple names
Sequence is resequenced.
9. online text error correction system according to claim 6, which is characterized in that further include wrong word in the database
Library when the correction module is replaced former character, the character string where former character is recorded in wrong word library, as mistake
Other character string records number of repetition if having existed the character string in wrong word library;
When user keys in the Wrongly-written or mispronounced character string, the retrieval module retrieves wrong word library, if the Wrongly-written or mispronounced character string exists
Number of repetition in wrong word library is more than given threshold, then correction module is automatically replaced the Wrongly-written or mispronounced character string.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910696146.7A CN110457695B (en) | 2019-07-30 | 2019-07-30 | Online text error correction method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910696146.7A CN110457695B (en) | 2019-07-30 | 2019-07-30 | Online text error correction method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110457695A true CN110457695A (en) | 2019-11-15 |
CN110457695B CN110457695B (en) | 2023-05-12 |
Family
ID=68484050
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910696146.7A Active CN110457695B (en) | 2019-07-30 | 2019-07-30 | Online text error correction method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110457695B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111310013A (en) * | 2020-02-17 | 2020-06-19 | 上海蓝鹇信息科技有限公司 | Automatic error correction method based on artificial intelligence |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101287228A (en) * | 2008-05-26 | 2008-10-15 | 北京捷讯畅达科技发展有限公司 | Phoneticizing error correcting technique and device applying to query by short message service of mobile phone |
JP2010102676A (en) * | 2008-10-23 | 2010-05-06 | Hiroshima Dia System Co Ltd | Fuzzy search method of search character string including a plurality of words |
CN107741928A (en) * | 2017-10-13 | 2018-02-27 | 四川长虹电器股份有限公司 | A kind of method to text error correction after speech recognition based on field identification |
CN108121455A (en) * | 2016-11-29 | 2018-06-05 | 渡鸦科技(北京)有限责任公司 | Identify method and device for correcting |
WO2018120889A1 (en) * | 2016-12-28 | 2018-07-05 | 平安科技(深圳)有限公司 | Input sentence error correction method and device, electronic device, and medium |
CN108717412A (en) * | 2018-06-12 | 2018-10-30 | 北京览群智数据科技有限责任公司 | Chinese check and correction error correction method based on Chinese word segmentation and system |
-
2019
- 2019-07-30 CN CN201910696146.7A patent/CN110457695B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101287228A (en) * | 2008-05-26 | 2008-10-15 | 北京捷讯畅达科技发展有限公司 | Phoneticizing error correcting technique and device applying to query by short message service of mobile phone |
JP2010102676A (en) * | 2008-10-23 | 2010-05-06 | Hiroshima Dia System Co Ltd | Fuzzy search method of search character string including a plurality of words |
CN108121455A (en) * | 2016-11-29 | 2018-06-05 | 渡鸦科技(北京)有限责任公司 | Identify method and device for correcting |
WO2018120889A1 (en) * | 2016-12-28 | 2018-07-05 | 平安科技(深圳)有限公司 | Input sentence error correction method and device, electronic device, and medium |
CN107741928A (en) * | 2017-10-13 | 2018-02-27 | 四川长虹电器股份有限公司 | A kind of method to text error correction after speech recognition based on field identification |
CN108717412A (en) * | 2018-06-12 | 2018-10-30 | 北京览群智数据科技有限责任公司 | Chinese check and correction error correction method based on Chinese word segmentation and system |
Non-Patent Citations (2)
Title |
---|
段建勇等: "基于统计和特征相结合的查询纠错方法研究", 《现代图书情报技术》 * |
颛悦等: "一种支持混合语言的并行查询纠错方法", 《中文信息学报》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111310013A (en) * | 2020-02-17 | 2020-06-19 | 上海蓝鹇信息科技有限公司 | Automatic error correction method based on artificial intelligence |
Also Published As
Publication number | Publication date |
---|---|
CN110457695B (en) | 2023-05-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108376151B (en) | Question classification method and device, computer equipment and storage medium | |
AU2005201758B2 (en) | Method of learning associations between documents and data sets | |
US7672833B2 (en) | Method and apparatus for automatic entity disambiguation | |
US7003725B2 (en) | Method and system for normalizing dirty text in a document | |
Kestemont et al. | Cross-genre authorship verification using unmasking | |
US9043339B2 (en) | Extracting terms from document data including text segment | |
CN112287684B (en) | Short text auditing method and device for fusion variant word recognition | |
CN103365573B (en) | A kind of method and apparatus that many key input characters are identified | |
JP2005122533A (en) | Question-answering system and question-answering processing method | |
JPH058464B2 (en) | ||
CN106844413A (en) | The method and device of entity relation extraction | |
CN104916177B (en) | The data output method of electronic equipment and electronic equipment | |
JP5591871B2 (en) | Answer type estimation apparatus, method, and program | |
Salah et al. | A comparative review of machine learning for Arabic named entity recognition | |
CN114118053A (en) | Contract information extraction method and device | |
CN110457695A (en) | A kind of online text error correction method and system | |
US11669574B2 (en) | Method, apparatus, and computer-readable medium for determining a data domain associated with data | |
Yang et al. | EcForest: extractive document summarization through enhanced sentence embedding and cascade forest | |
JP4511892B2 (en) | Synonym search device, method thereof, program thereof, and information search device | |
AU2022204425A1 (en) | Extracting key value pairs using positional coordinates | |
Li et al. | Prediction of yelp review star rating using sentiment analysis | |
CN107577760A (en) | A kind of file classification method and device based on constrained qualification | |
CA3156204A1 (en) | Domain based text extraction | |
Fatima et al. | HITS-SBD at the FinSBD task: machine learning vs. rule-based sentence boundary detection | |
Plu et al. | Revealing entities from textual documents using a hybrid approach |
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 | ||
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20230425 Address after: 4th Floor, China Telecom Group Wuhu Cloud Computing Center, No. 2 Guotai Road, Jiujiang District, Wuhu City, Anhui Province, 241000 Applicant after: Anhui Huolan Data Co.,Ltd. Address before: No. 206, D3 District, Fuxing City, No. 32 Binhai Avenue, Longhua District, Haikou City, Hainan Province, 570100 Applicant before: HAINAN HUOLAN DATA Co.,Ltd. |
|
GR01 | Patent grant | ||
GR01 | Patent grant |