CN110457695B - Online text error correction method and system - Google Patents
Online text error correction method and system Download PDFInfo
- Publication number
- CN110457695B CN110457695B CN201910696146.7A CN201910696146A CN110457695B CN 110457695 B CN110457695 B CN 110457695B CN 201910696146 A CN201910696146 A CN 201910696146A CN 110457695 B CN110457695 B CN 110457695B
- Authority
- CN
- China
- Prior art keywords
- character
- characters
- character string
- continuous
- library
- 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.)
- Active
Links
Images
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 an online character error correction method and system, which are characterized in that characters typed by a user are firstly identified as sentences, character strings are bound into language sheets according to the cohesion among the characters in the sentences, whether more than two continuous characters cannot be bound into the language sheets in the sentences can be identified, the possibility of wrongly-written characters is higher, the wrongly-written characters are often caused by the selection error of pinyin input in the process of typing the characters by the user, and the wrongly-written characters in the original characters are replaced by searching the substitute characters of the same pinyin.
Description
Technical Field
The invention relates to the field of word processing, in particular to an online word error correction method and system.
Background
In the process of inputting characters by a user, the situation of wrongly-written characters is unavoidable, but the user often has difficulty in finding out the input errors, so that the wrongly-written characters exist in the finally-finished article, the understanding of other people on the article is influenced, or the image problem of individuals and enterprises is influenced;
in the existing word processing software, although the suspected wrongly written word reminding function exists, the characters typed by the user are often only compared with the common word stock, if the characters typed by the user do not belong to the common word stock, the character strings are marked, but the method does not consider the structure of sentences and the use habit of Chinese, and can not automatically correct errors, and the effect is limited, so that an online word error correction method and an online word error correction system are needed.
Disclosure of Invention
Therefore, the invention aims to provide an online text error correction method and system, which improve the accuracy and efficiency of text processing.
Based on the above purpose, the online text error correction method provided by the invention comprises the following steps:
searching for sentence end punctuation marks in a plurality of characters typed by a user, and judging the characters between adjacent sentence end punctuation marks as sentences;
preprocessing sentences, and binding character strings into language sheets according to cohesiveness among characters;
if more than two continuous characters cannot be bundled into a language sheet, searching one by one in a database by combining cohesiveness and pinyin of each character, judging whether the same pinyin can be found out or not, so that the continuous characters can be bundled into the language sheet with high cohesiveness;
if the character can be found, replacing the original character by using the substituted character in the database, if the character can not be found, carrying out fuzzy processing on any one of the pinyin of each character, carrying out fuzzy search one by one in the database, judging whether the substituted character of the similar pinyin can be found, and binding continuous characters into a language sheet with high cohesive property;
if the character can be found, replacing the original character by using the substitute character in the database, and if the character can not be found, marking the continuous character.
Preferably, when more than two continuous characters cannot be bundled into a language sheet, the pinyin of the continuous character string is extracted, whether the person name with the same pinyin exists or not is searched in a person name library, if the person name with the same pinyin is searched, the person name is compared with the continuous character string, if the person name is the same, the continuous character is not marked, and if the comparison is different, the continuous character string is corrected to the person name.
Preferably, when the person name library is searched for whether the person name with the same pinyin exists, if the person name with the same pinyin cannot be searched for, any one bit in the pinyin of the character string is subjected to fuzzy processing, fuzzy search is performed in the person name library, if the person name with the similar pinyin is searched for, the person name is compared with the continuous character string, if the person name with the similar pinyin is the same, the continuous character is not marked, and if the comparison is different, the continuous character string is corrected to the person name.
Preferably, the method further comprises:
when a plurality of names appear in the sentence and characters representing juxtaposition are adopted among the names, the sequence of the names is reordered according to the sequence in the name ordering library.
Preferably, the method further comprises:
when the original character is replaced, the character string where the original character is located is recorded into a mispronounced character library to be used as the mispronounced character string, and if the mispronounced character string exists in the mispronounced character library, the repetition times are recorded;
when the user types in the mispronounced character string, if the repeated times of the mispronounced character string in the mispronounced character library exceeds a set threshold value, the mispronounced character string is automatically replaced.
An online text error correction system, comprising:
the database module is used for storing a common sentence pattern set and a common word set which reflect the cohesiveness of words;
the sentence discrimination module is used for discriminating sentences in the characters according to sentence end punctuation marks in a plurality of characters typed by a user;
the preprocessing module binds the character strings into language sheets according to the cohesive property among the characters in the sentence;
the retrieval module is used for carrying out one-by-one retrieval and one-by-one fuzzy retrieval on more than two continuous characters which cannot be bundled into the language sheets in the database, judging whether the same or similar pinyin substitute characters can be found, and bundling the continuous characters into the language sheets with high cohesiveness;
the correction module can replace the original character by using the replacement character in the database;
and the marking module can mark the characters and the character strings.
Preferably, the database also comprises a name database, and the retrieval module can retrieve the character strings and fuzzy retrieval according to the name database to retrieve the names of the same pinyin;
the correction module can correct the character string according to the name library.
Preferably, the system further comprises a ranking module, the database further comprises a name ranking library, and the ranking module can reorder the order of the plurality of person names according to the ranking in the name ranking library.
Preferably, the database also comprises a mispronounced character library, when the correction module replaces the original character, the character string of the original character is recorded into the mispronounced character library and used as the mispronounced character string, and if the mispronounced character string already exists in the mispronounced character library, the repetition number is recorded;
when the user types in the mispronounced character string, the search module searches the mispronounced character string, and if the repetition times of the mispronounced character string in the mispronounced character string exceeds a set threshold value, the correction module automatically replaces the mispronounced character string.
As can be seen from the above, the online character correction method and system provided by the invention can identify whether more than two continuous characters cannot be bundled into a sentence or not in the sentence by firstly identifying the characters typed by the user as sentences and bundling the character strings into the sentence according to the cohesiveness among the characters in the sentences, so that the possibility of wrongly-written characters is higher.
Drawings
FIG. 1 is a schematic flow chart of an online text error correction method according to an embodiment of the invention;
FIG. 2 is a schematic diagram of an online text error correction system according to an embodiment of the present invention.
Detailed Description
The present invention will be further described in detail below with reference to specific embodiments and with reference to the accompanying drawings, in order to make the objects, technical solutions and advantages of the present invention more apparent.
It should be noted that, in the embodiments of the present invention, all the expressions "first" and "second" are used to distinguish two entities with the same name but different entities or different parameters, and it is noted that the "first" and "second" are only used for convenience of expression, and should not be construed as limiting the embodiments of the present invention, and the following embodiments are not described one by one.
An online text error correction method comprises the following steps:
searching for punctuation marks of the sentence end class among a plurality of characters typed by a user, judging characters between adjacent sentence end class punctuation marks as sentences, wherein the sentence end class punctuation marks refer to punctuation marks representing the end of sentences such as a sentence mark, an exclamation mark, a question mark and the like.
Preprocessing sentences, binding character strings into language sheets according to the cohesiveness among characters, wherein the cohesiveness among the characters refers to the common sentence patterns and structures of symbols with Chinese use habits, such as bias phrases, dynamic complement phrases, mediate phrases and the like;
if more than two continuous characters cannot be bundled into a language sheet, the characters are searched one by one in the database in combination with cohesiveness and pinyin of each character, and whether the alternative characters of the same pinyin can be found or not is judged, so that the continuous characters can be bundled into the language sheet with high cohesiveness, more than two characters cannot be bundled into the language sheet in one sentence, and the situation of wrongly written characters is likely to exist;
if the character can be found, replacing the original character by using the substituted character in the database, if the character can not be found, carrying out fuzzy processing on any one of the pinyin of each character, carrying out fuzzy search one by one in the database, judging whether the substituted character of the similar pinyin can be found, and binding continuous characters into a language sheet with high cohesive property;
if the character can be found, replacing the original character by using the substitute character in the database, and if the character can not be found, marking the continuous character, wherein the marking mode can adopt the modes of underline, color marking and the like.
The method is characterized in that firstly, characters typed by a user are recognized as sentences, character strings are bound into language sheets according to cohesiveness among the characters in the sentences, whether more than two continuous characters cannot be bound into the language sheets in the sentences can be recognized, the possibility of wrongly-written characters is high, wrongly-written characters caused by pinyin input selection errors often occur in the process of typing the characters by the user, the wrongly-written characters in the original characters are replaced by retrieving alternative characters of the same pinyin, and wrongly-written characters caused by single pinyin typing errors often occur in the process of typing the characters by the user, so that the method carries out fuzzy processing and fuzzy retrieval on any bit in pinyin of each character, finds the alternative characters to replace wrongly-written characters, and can effectively carry out online character correction on the characters typed by the user.
In the embodiment of the invention, when more than two continuous characters cannot be bundled into a language film, the method further comprises the steps of extracting the pinyin of the continuous character string, searching whether the person names with the same pinyin exist in a person name library, comparing the person names with the continuous character string if the person names with the same pinyin are searched, marking the continuous character if the person names with the same pinyin are compared, and correcting the continuous character string into the person names if the comparison is different.
In the process of inputting characters, people names are often required to be input, and the people names obviously do not belong to common vocabularies in Chinese, so that the possibility that continuous characters cannot be bound into a language film is high, and whether the character string belongs to the people names is judged by searching whether the people names with the same pinyin exist in a people name library.
In the embodiment of the invention, when the names of the same pinyin exist in the name library, if the names of the same pinyin cannot be searched, any one bit of the pinyin of the character string is subjected to fuzzy processing, fuzzy search is performed in the name library, if the names of the similar pinyin are searched, the names are compared with the continuous character strings, if the comparison is the same, the continuous character is not marked, and if the comparison is different, the continuous character strings are corrected to the names.
When the method is used for searching the name library, the fuzzy processing and fuzzy searching methods are adopted, so that the name with incorrect pinyin typing can be corrected on line.
In the embodiment of the invention, the method further comprises the step of reordering the sequence of the plurality of personal names according to the sequence in the name sequencing library when the plurality of personal names appear in the sentence and the characters representing the parallel are adopted among the personal names.
For name typing in enterprises, when multiple names are presented in parallel, names are often required to be ordered according to the order of the leader level and the like, the method can automatically correct the wrong ordering, and the characters in parallel of the representations comprise characters such as ' pause numbers ', ' and ' AND '.
In the embodiment of the invention, the method further comprises the steps of recording the character string where the original character is in into a misplaced character library as misplaced character string when the original character is replaced, and recording the repetition times if the misplaced character string exists in the misplaced character library;
when the user types in the mispronounced character string, if the repeated times of the mispronounced character string in the mispronounced character library exceeds a set threshold value, the mispronounced character string is automatically replaced.
Because of the repeated errors frequently caused by personal input habits, the method automatically corrects and replaces the wrongly written character strings by recording the repeated times of wrongly written character strings when the wrongly written character strings exceeding a set threshold are typed again, thereby improving the processing efficiency of the invention and improving the accuracy by correlating the input habits of users.
The invention also provides an online text error correction system, which comprises a database module, wherein the database module stores a common sentence pattern set and a common word set which reflect the cohesiveness of words;
the sentence discrimination module is used for discriminating sentences in the characters according to sentence end punctuation marks in a plurality of characters typed by a user;
the preprocessing module binds the character strings into language sheets according to the cohesive property among the characters in the sentence;
the retrieval module is used for carrying out one-by-one retrieval and one-by-one fuzzy retrieval on more than two continuous characters which cannot be bundled into the language sheets in the database, judging whether the same or similar pinyin substitute characters can be found, and bundling the continuous characters into the language sheets with high cohesiveness;
the correction module can replace the original character by using the replacement character in the database;
and the marking module can mark the characters and the character strings.
In the embodiment of the invention, the database also comprises a person name library, and the retrieval module can retrieve and fuzzy retrieve the character strings according to the person name library to retrieve the person names of the same pinyin;
the correction module can correct the character string according to the name library.
In an embodiment of the present invention, the system further includes a ranking module, and the database further includes a name ranking library, where the ranking module may reorder the order of the plurality of person names according to the ranking in the name ranking library.
In the embodiment of the invention, the database also comprises a mispronounced character library, when the correction module replaces the original character, the character string where the original character is positioned is recorded into the mispronounced character library to be used as mispronounced character string, and if the mispronounced character string already exists in the mispronounced character library, the repetition number is recorded;
when the user types in the mispronounced character string, the search module searches the mispronounced character string, and if the repetition times of the mispronounced character string in the mispronounced character string exceeds a set threshold value, the correction module automatically replaces the mispronounced character string.
Those of ordinary skill in the art will appreciate that: the discussion of any of the embodiments above is merely exemplary and is not intended to suggest that the scope of the disclosure, including the claims, is limited to these examples; the technical features of the above embodiments or in the different embodiments may also be combined within the idea of the invention, the steps may be implemented in any order and there are many other variations of the different aspects of the invention as described above, which are not provided in detail for the sake of brevity.
Additionally, well-known power/ground connections to Integrated Circuit (IC) chips and other components may or may not be shown within the provided figures, in order to simplify the illustration and discussion, and so as not to obscure the invention. Furthermore, the devices may be shown in block diagram form in order to avoid obscuring the invention, and also in view of the fact that specifics with respect to implementation of such block diagram devices are highly dependent upon the platform within which the present invention is to be implemented (i.e., such specifics should be well within purview of one skilled in the art). Where specific details (e.g., circuits) are set forth in order to describe example embodiments of the invention, it should be apparent to one skilled in the art that the invention can be practiced without, or with variation of, these specific details. Accordingly, the description is to be regarded as illustrative in nature and not as restrictive.
While the invention has been described in conjunction with specific embodiments thereof, many alternatives, modifications, and variations of those embodiments will be apparent to those skilled in the art in light of the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may use the embodiments discussed.
The embodiments of the invention are intended to embrace all such alternatives, modifications and variances which fall within the broad scope of the appended claims. Therefore, any omission, modification, equivalent replacement, improvement, etc. of the present invention should be included in the scope of the present invention.
Claims (8)
1. An online text error correction method, the method comprising:
searching for sentence end punctuation marks in a plurality of characters typed by a user, and judging the characters between adjacent sentence end punctuation marks as sentences;
preprocessing sentences, and binding character strings into language sheets according to cohesiveness among characters;
if more than two continuous characters cannot be bundled into a language sheet, searching one by one in a database by combining cohesiveness and pinyin of each character, judging whether the same pinyin can be found out or not, so that the continuous characters can be bundled into the language sheet with high cohesiveness;
if the character can be found, replacing the original character by using the substituted character in the database, if the character can not be found, carrying out fuzzy processing on any one of the pinyin of each character, carrying out fuzzy search one by one in the database, judging whether the substituted character of the similar pinyin can be found, and binding continuous characters into a language sheet with high cohesive property;
if the character can be found, replacing the original character by using a substitute character in the database, and if the character can not be found, marking the continuous character;
when more than two continuous characters cannot be bundled into a language film, the pinyin of the continuous character string is extracted, whether the person names with the same pinyin exist or not is searched in a person name library, if the person names with the same pinyin are searched, the person names are compared with the continuous character string, if the person names are the same, the continuous character is not marked, and if the comparison is different, the continuous character string is corrected to the person name.
2. The online text error correction method according to claim 1, wherein when a person name of the same pinyin is searched in a person name library, if the person name of the same pinyin cannot be searched, any one of the character string pinyins is subjected to fuzzy processing, fuzzy search is performed in the person name library, if the person name of the similar pinyin is searched, the person name is compared with a continuous character string, if the comparison is the same, the continuous character is not marked, and if the comparison is different, the continuous character string is corrected to the person name.
3. The online text error correction method of claim 1 or 2, further comprising:
when a plurality of names appear in the sentence and characters representing juxtaposition are adopted among the names, the sequence of the names is reordered according to the sequence in the name ordering library.
4. The online text error correction method of claim 1, further comprising:
when the original character is replaced, the character string where the original character is located is recorded into a mispronounced character library to be used as the mispronounced character string, and if the mispronounced character string exists in the mispronounced character library, the repetition times are recorded;
when the user types in the mispronounced character string, if the repeated times of the mispronounced character string in the mispronounced character library exceeds a set threshold value, the mispronounced character string is automatically replaced.
5. An online text error correction system, comprising:
the database module is used for storing a common sentence pattern set and a common word set which reflect the cohesiveness of words;
the sentence discrimination module is used for discriminating sentences in the characters according to sentence end punctuation marks in a plurality of characters typed by a user;
the preprocessing module binds the character strings into language sheets according to the cohesive property among the characters in the sentence;
the retrieval module is used for carrying out one-by-one retrieval and one-by-one fuzzy retrieval on more than two continuous characters which cannot be bundled into the language sheets in the database, judging whether the same or similar pinyin substitute characters can be found, and bundling the continuous characters into the language sheets with high cohesiveness;
the correction module can replace the original character by using the substituted character in the database, extracts the pinyin of the continuous character string when more than two continuous characters cannot be bundled into a voice piece, searches a person name library for the person name with the same pinyin, compares the person name with the continuous character string if the person name with the same pinyin is searched, does not mark the continuous character if the person name is the same, and corrects the continuous character string into the person name if the comparison is different;
and the marking module can mark the characters and the character strings.
6. The online text error correction system of claim 5, wherein the database further comprises a name library, and the search module can search and fuzzy search the character string according to the name library to search the names of the same pinyin;
the correction module can correct the character string according to the name library.
7. The online text error correction system of claim 6, further comprising a ranking module, wherein the database further comprises a name ranking library, wherein the ranking module reorders the order of the plurality of personal names according to the ranking in the name ranking library.
8. The online text error correction system according to claim 5, wherein the database further comprises a misplaced character library, the correction module records the character string of the original character into the misplaced character library as misplaced character string when the original character is replaced, and records the repetition number if the misplaced character string exists in the misplaced character library;
when the user types in the mispronounced character string, the search module searches the mispronounced character string, and if the repetition number of the mispronounced character string in the mispronounced character string exceeds a set threshold value, the correction module automatically replaces the 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 CN110457695A (en) | 2019-11-15 |
| CN110457695B true 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) |
Families Citing this family (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 |
|---|
| 一种支持混合语言的并行查询纠错方法;颛悦等;《中文信息学报》;20160315(第02期);全文 * |
| 基于统计和特征相结合的查询纠错方法研究;段建勇等;《现代图书情报技术》;20160225(第02期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110457695A (en) | 2019-11-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107045496B (en) | Error correction method and error correction device for text after voice recognition | |
| Kukich | Techniques for automatically correcting words in text | |
| US8594999B2 (en) | Typing candidate generating method for enhancing typing efficiency | |
| US7743327B2 (en) | Table of contents extraction with improved robustness | |
| US7756871B2 (en) | Article extraction | |
| CA2642217C (en) | Method and system for verification of uncertainly recognized words in an ocr system | |
| US8190538B2 (en) | Methods and systems for matching records and normalizing names | |
| US20030046263A1 (en) | Method and system for mining a document containing dirty text | |
| CN109299233B (en) | Text data processing method, device, computer equipment and storage medium | |
| Mitton | Ordering the suggestions of a spellchecker without using context | |
| KR20070010163A (en) | Apparatus and method for handwriting recognition | |
| CN105760359B (en) | Question processing system and method thereof | |
| US11520835B2 (en) | Learning system, learning method, and program | |
| Mann et al. | Multi-field information extraction and cross-document fusion | |
| CN102033866A (en) | Method and system for checking chemical name | |
| Chaudhuri | Reversed word dictionary and phonetically similar word grouping based spell-checker to Bangla text | |
| CN110457695B (en) | Online text error correction method and system | |
| CN108628826A (en) | Candidate word appraisal procedure, device, computer equipment and storage medium | |
| US10409861B2 (en) | Method for fast retrieval of phonetically similar words and search engine system therefor | |
| CN111310457B (en) | Word mismatching recognition method and device, electronic equipment and storage medium | |
| JP2586372B2 (en) | Information retrieval apparatus and information retrieval method | |
| Mridha et al. | An approach for detection and correction of missing word in Bengali sentence | |
| JP2003331214A (en) | Character recognition error correction method, device and program | |
| Chaudhuri | Towards Indian language spell-checker design | |
| CN108595419A (en) | Candidate word appraisal procedure, candidate word sort method and device |
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 |
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. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |