CN112632967A - Chinese pinyin automatic generation method and device oriented to set strategy - Google Patents
Chinese pinyin automatic generation method and device oriented to set strategy Download PDFInfo
- Publication number
- CN112632967A CN112632967A CN202011611532.0A CN202011611532A CN112632967A CN 112632967 A CN112632967 A CN 112632967A CN 202011611532 A CN202011611532 A CN 202011611532A CN 112632967 A CN112632967 A CN 112632967A
- Authority
- CN
- China
- Prior art keywords
- common
- polyphone
- false
- dictionary
- module
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/232—Orthographic correction, e.g. spell checking or vowelisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/237—Lexical tools
- G06F40/242—Dictionaries
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Document Processing Apparatus (AREA)
Abstract
The invention relates to the technical field of pinyin generation, and particularly discloses a Chinese pinyin automatic generation method and device facing a set strategy, wherein the method comprises the steps of constructing a polyphone word group dictionary; constructing a dictionary of the universal kana words; inputting a set strategy article, and matching pinyin for Chinese characters in the set strategy article by contrasting a Chinese dictionary; identifying polyphone characters and phrases in the initial file by contrasting a polyphone word group dictionary, and correcting the pinyin of the polyphone characters and the phrases thereof to generate a first correction file; and identifying the common-false characters in the first correction file according to the common-false character dictionary, and correcting the pinyin of the common-false characters according to the context of the common-false characters to generate a second correction file. The invention solves the problem of the conversion error rate of polyphone and common-false word, solves the problem of low efficiency of manual examination and error correction, realizes the content updating and self-learning functions of polyphone word group dictionary and common-false word dictionary, further improves the pinyin conversion accuracy and also improves the efficiency of manual examination and error correction.
Description
Technical Field
The invention relates to the technical field of pinyin generation, in particular to a Chinese pinyin automatic generation method and device facing to a set strategy.
Background
In order to popularize classical works of national science, people open classical hurdles of national science in WeChat public numbers, search various classical books of national science, provide reading and on-line recitation functions, and mark pinyin for each Chinese character in the books. The core problem to be solved is how to accurately convert Chinese characters in the classical Chinese learning into pinyin automatically. Aiming at the problem, the prior art mainly uses a Chinese pinyin dictionary to match corresponding pinyin, and has the following obvious defects:
1) when processing polyphone characters, the trans-spelling is easy to make mistakes;
2) when dealing with common-false words (mostly different tones), the output pinyin is often wrong.
In classical books or articles in the national sciences, polyphones and common false characters are common, and the probability of misspelling is very high by adopting the existing Chinese-to-pinyin technology, manual intervention is needed, but the effect is not ideal:
1) the workload of manual error correction is too large, and the processing of a large batch of classical books in national science cannot be completed in a short time;
2) the efficiency of manual error correction is extremely low, mainly reflected in that the efficiency of error finding is low and the error needs to be checked one by one.
Based on the above background, there is a need for a new technical solution to solve the above problems.
Disclosure of Invention
Aiming at the technical problems in the prior art, the invention provides a Chinese pinyin automatic generation method and device facing to a set strategy.
The invention provides a Chinese pinyin automatic generation method facing a set strategy, which comprises the following steps:
constructing a polyphone word group dictionary which contains pronunciations of polyphones in different word groups;
constructing a common-alphabet dictionary, wherein the common-alphabet dictionary comprises common-alphabet characters, the pronunciations, sentences in which the common-alphabet characters are located, common-alphabet characters and pronunciations;
inputting a set strategy article, matching pinyin for Chinese characters in the set strategy article by contrasting a Chinese dictionary, and generating an initial file;
identifying polyphone characters and phrases in the initial file by contrasting a polyphone word group dictionary, and correcting the pinyin of the polyphone characters and the phrases thereof to generate a first correction file;
and identifying the common-false characters in the first correction file according to the common-false character dictionary, and correcting the pinyin of the common-false characters according to the context of the common-false characters to generate a second correction file.
Furthermore, the method also comprises the steps of marking polyphone words and phrases in the first correction file and marking common false words in the second correction file.
Further, the method further comprises:
and manually checking the second correction file, respectively storing the new polyphone words, the phrases and the new common false words into a polyphone phrase dictionary and a common false word dictionary, and recording the occurrence times of the new polyphone words, the phrases and the new common false words.
Further, the method further comprises:
counting the occurrence times of each polyphone and the phrase in the first correction file, and recording the polyphone and the phrase in a polyphone phrase dictionary;
and counting the occurrence times of all the common false words in the second correction file, and recording the common false words in the common false word dictionary.
Further, the method further comprises:
calculating the occurrence probability according to the occurrence times of the polyphones and the phrases, and using the probability as a reference factor for correcting the initial file;
and calculating the occurrence probability according to the occurrence times of the common false words, and using the common false words as a reference factor when the first correction file is corrected.
The invention also provides a Chinese pinyin automatic generation device facing the set strategy, which comprises a polyphone word group dictionary construction module, a common-hypothesis word dictionary construction module, a set strategy article input module, an initial file generation module, a first correction module and a second correction module, wherein:
the polyphone word group dictionary constructing module is connected with the first correcting module and is used for constructing a polyphone word group dictionary;
the common-false word dictionary construction module is connected with the second correction module and is used for constructing a common-false word dictionary;
the set strategy article recording module is connected with the initial file generating module and is used for recording the set strategy article;
the initial file generation module is connected with the set strategy article input module and the first correction module and used for matching pinyin for Chinese characters in the set strategy article by contrasting a Chinese dictionary and generating an initial file;
the first correction module is connected with the polyphone word group dictionary construction module, the initial file generation module and the second correction module and used for identifying polyphone words and word groups in the initial file by contrasting the polyphone word group dictionary and correcting the polyphone words and the pinyin of the word groups to generate a first correction file;
and the second correction module is connected with the common-false word dictionary construction module and the first correction module and is used for identifying the common-false words in the first correction file according to the common-false word dictionary and correcting the pinyin of the common-false words according to the context of the common-false words to generate a second correction file.
Further, the device also comprises a polyphone word and phrase marking module and a common false word marking module, wherein:
the polyphone and phrase marking module is connected with the first correction module and used for marking the polyphone and phrases in the first correction file;
and the common-false word marking module is connected with the second correction module and is used for marking the common-false words in the second correction file.
The present invention also provides an electronic device comprising a memory and a processor, wherein,
a memory storing computer instructions;
a processor configured to execute computer instructions to cause a computer device to perform the above-described method.
The invention also provides a storage medium having a computer program stored thereon, wherein the computer program is adapted to perform the steps of the method described above when executed by a processor.
The method, the device, the electronic equipment and the storage medium for automatically generating the Chinese pinyin facing the set strategy construct a polyphone word group dictionary and a common-case-word dictionary, correct the polyphone and the pinyin of the word group of the polyphone word after matching the pinyin for the Chinese characters in the set strategy article by referring to the Chinese dictionary, and correct the pinyin of the common-case-word according to the common-case-word dictionary, thereby solving the problem of the conversion error rate of the polyphone and the common-case-word, solving the problem of low efficiency of manual review and error correction, realizing the content updating and self-learning functions of the polyphone word group dictionary and the common-case-word dictionary, further improving the pinyin conversion accuracy and improving the efficiency of the manual review and error correction.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart of steps of a method for automatically generating Chinese Pinyin oriented to a set policy according to an embodiment of the present invention;
FIG. 2 is a flow chart of the steps of the method for automatically generating Chinese Pinyin oriented to a set policy according to the embodiment of the present invention;
FIG. 3 is a flow chart of steps of a set-policy-oriented Chinese pinyin automatic generation method according to an embodiment of the present invention (III);
FIG. 4 is a flow chart of steps of a method for automatically generating Chinese Pinyin oriented to a set policy according to an embodiment of the present Invention (IV);
FIG. 5 is a flow chart of steps of a set-policy oriented Chinese pinyin automatic generation method according to an embodiment of the present invention (V);
FIG. 6 is a structural composition diagram of an automatic Chinese pinyin generation device oriented to setting strategies according to an embodiment of the present invention;
FIG. 7 is a diagram of another structure of an apparatus for automatically generating Chinese pinyin according to an embodiment of the present invention;
fig. 8 is a structural assembly diagram of an electronic device according to an embodiment of the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings in the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, an automatic chinese pinyin generation method oriented to a setting policy according to an embodiment of the present invention includes the following steps:
step S101: and constructing a polyphone word group dictionary which contains pronunciations of polyphones in different word groups. Polyphones include multiple pronunciations, such as "more" reading "(g < nu > ng)" and "(g < yung)", reading "(g < nu > ng)" may include words such as "update", "change", "correct", "alternation", "lack of everything", "change string and piece", "self-help renew", etc., reading "(g < ng)" may include words such as "better", "more than", "more winning", "when to wait", "further" etc., and both pronunciations of polyphones and corresponding words are stored in a polyphone word dictionary.
Step S102: and constructing a common-alphabet dictionary, wherein the common-alphabet dictionary comprises common-alphabet characters, the provenance, the sentence, the common-alphabet characters and pronunciations.
What is said about the kanji "is it being studied," not to mention? "Zhong, Tong Yue (yu), leaving the department" talking words "; what is known about the false-pass word "woman" in "for the mother? "Zhong, Tong Ru (r ǔ), am out of the treatise. Storing all the pronounciation, the provenance, the sentence and the pronunciation in the dictionary.
Step S103: inputting a set strategy article, matching pinyin for Chinese characters in the set strategy article by contrasting a Chinese dictionary, and generating an initial file.
The strategy setting article in the embodiment of the method can be a classical article of the national category, so that the popularization of the national article is realized, and meanwhile, the technical personnel in the field can also select other Chinese articles to realize the matching of full-text pinyin.
The steps are that Chinese characters in a set strategy article are matched with pinyin one by one according to a Chinese dictionary, conversion is carried out only according to common pronunciation, and each Chinese character in a generated initial file is matched with corresponding pinyin.
Step S104: and identifying polyphone characters and phrases in the initial file by contrasting the polyphone word group dictionary, and correcting the pinyin of the polyphone characters and the phrases thereof to generate a first correction file.
Identifying polyphone characters and related phrases in the initial file, matching correct pronunciations of the polyphone characters, and generating a first correction file after correction is completed.
Step S105: and identifying the common-false characters in the first correction file according to the common-false character dictionary, and correcting the pinyin of the common-false characters according to the context of the common-false characters to generate a second correction file.
And then, the common-false words in the first correction file are identified by referring to the common-false word dictionary, the correct pronunciation of the common-false words is matched, and a second correction file is generated after correction is completed.
Specifically, as shown in fig. 2, the embodiment of the present invention further includes:
step S106: and marking the polyphone and the phrase in the first correction file.
After step S104 is executed, all polyphones in the first correction file are marked.
Step S107: and marking the false words in the second correction file.
After step S105 is executed, all the false words in the second correction file are marked.
Specifically, as shown in fig. 3, the embodiment of the present invention further includes:
step S108: and manually checking the second correction file, respectively storing the new polyphone words, the phrases and the new common false words into a polyphone phrase dictionary and a common false word dictionary, and recording the occurrence times of the new polyphone words, the phrases and the new common false words.
Through the correction process of the two steps, in order to ensure that the pinyin of polyphone and the Tong-Han-zi in the second correction file is correct, step S108 can be executed again, the second correction file is checked manually, and finally the Chinese and pinyin results of the full text of the set strategy article are output. Due to the previous correction step, the workload of manual examination and verification in the step is greatly reduced, so that the efficiency of Chinese pinyin generation is greatly improved, and the batch pinyin generation task of the policy-setting article can be efficiently completed.
In the process of manual examination, polyphone words and common false words which are not stored in the polyphone word group dictionary and the common false word dictionary are added, and the times of occurrence of new polyphone words and new common false words are recorded.
Specifically, as shown in fig. 4, the embodiment of the present invention further includes:
step S109: and counting the occurrence times of each polyphone and the phrase in the first correction file, and recording the result in a polyphone phrase dictionary.
And step S106 is executed to mark the polyphones and the phrases in the first correction file, and then the times of occurrence of the polyphones and the related phrases in the first correction file are counted and recorded.
Step S110: and counting the occurrence times of all the common false words in the second correction file, and recording the common false words in the common false word dictionary.
And step S107 is executed to mark the common false words in the second correction file, and then the occurrence frequency of the common false words in the second correction file is counted and recorded.
Specifically, as shown in fig. 5, the embodiment of the present invention further includes:
step S111: and calculating the occurrence probability according to the occurrence times of the polyphones and the phrases, and using the probability as a reference factor for correcting the initial file.
Step S112: and calculating the occurrence probability according to the occurrence times of the common false words, and using the common false words as a reference factor when the first correction file is corrected.
According to big data calculation and analysis experience, polyphones and common-case characters with high historical times can also appear in new articles more probably, namely, the utilization rate of one pronunciation of certain polyphones is higher, if pinyin matching cannot be carried out according to the content of the existing polyphone word group dictionary during correction, the pronunciation with high use times is preferentially matched, and the common-case character pinyin matching is carried out in the same way, so that the self-improvement and learning process of the method is realized.
The invention also provides a device 100 for automatically generating Chinese pinyin facing a set policy, as shown in fig. 6, the device comprises a polyphone phrase dictionary constructing module 101, a common fiction phrase dictionary constructing module 102, a set policy article recording module 103, an initial file generating module 104, a first correcting module 105 and a second correcting module 106, wherein:
a polyphone word group dictionary constructing module 101 connected with the first correcting module 105 for constructing a polyphone word group dictionary;
a common-false word dictionary constructing module 102 connected to the second correcting module 106 for constructing a common-false word dictionary;
a set policy article entry module 103 connected to the initial file generation module 104 for entering a set policy article;
the initial file generation module 104 is connected with the set strategy article entry module 103 and the first correction module 105 and is used for matching pinyin for Chinese characters in the set strategy article by contrasting a Chinese dictionary and generating an initial file;
a first correction module 105, connected to the polyphone word and phrase dictionary construction module 101, the initial file generation module 104 and the second correction module 106, for identifying polyphone words and phrases in the initial file by referring to the polyphone word and phrase dictionary, correcting the polyphone words and the pinyin of the phrases thereof, and generating a first correction file;
and the second correction module 106 is connected with the common-letter word dictionary construction module 102 and the first correction module 105, and is used for identifying the common-letter words in the first correction file according to the common-letter word dictionary, correcting the pinyin of the common-letter words according to the context of the common-letter words, and generating a second correction file.
Specifically, as shown in fig. 7, the apparatus further includes a polyphone and phrase marking module 107 and a common false word marking module 108, wherein:
a polyphone and phrase marking module 107 connected to the first modification module 105, for marking the polyphone and phrase in the first modification file;
and a false word marking module 108 connected to the second correction module 106, configured to mark a false word in the second correction file.
The present invention further provides an electronic device 200, as shown in fig. 8, including a memory 201 and a processor 202, where the memory 201 stores computer instructions; a processor 202 configured to execute computer instructions to cause a computer device to perform the methods of the embodiments described above.
The invention also provides a storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the above method.
The method, the device, the electronic equipment and the storage medium for automatically generating the Chinese pinyin facing the set strategy construct a polyphone word group dictionary and a common-case-word dictionary, correct the polyphone and the pinyin of the word group of the polyphone word after matching the pinyin for the Chinese characters in the set strategy article by referring to the Chinese dictionary, and correct the pinyin of the common-case-word according to the common-case-word dictionary, thereby solving the problem of the conversion error rate of the polyphone and the common-case-word, solving the problem of low efficiency of manual review and error correction, realizing the content updating and self-learning functions of the polyphone word group dictionary and the common-case-word dictionary, further improving the pinyin conversion accuracy and improving the efficiency of the manual review and error correction.
The present invention has been further described with reference to specific embodiments, but it should be understood that the detailed description should not be construed as limiting the spirit and scope of the present invention, and various modifications made to the above-described embodiments by those of ordinary skill in the art after reading this specification are within the scope of the present invention.
Claims (9)
1. A Chinese pinyin automatic generation method oriented to set strategies is characterized by comprising the following steps:
constructing a polyphone word group dictionary which contains pronunciations of polyphones in different word groups;
constructing a common-alphabet dictionary, wherein the common-alphabet dictionary comprises common-alphabet words, pronunciations, sentences in which the common-alphabet words are located, common-alphabet words and pronunciations;
inputting a set strategy article, matching pinyin for Chinese characters in the set strategy article by contrasting a Chinese dictionary, and generating an initial file;
identifying polyphone characters and phrases in the initial file by contrasting the polyphone word group dictionary, and correcting the pinyin of the polyphone characters and the phrases thereof to generate a first correction file;
and identifying the common-false characters in the first correction file by contrasting the common-false character dictionary, and correcting the pinyin of the common-false characters according to the context of the common-false characters to generate a second correction file.
2. The method for automatically generating pinyin for chinese characters oriented to setting strategies as claimed in claim 1, further comprising labeling the polyphonic characters and phrases in the first correction file and labeling the wildtype characters in the second correction file.
3. The method for automatically generating Chinese Pinyin oriented to setting strategy as claimed in claim 2, further comprising:
and manually checking the second correction file, respectively storing the new polyphone, the phrase and the new common false word into the polyphone phrase dictionary and the common false word dictionary, and recording the occurrence times of the new polyphone, the phrase and the new common false word.
4. The method for automatically generating Chinese Pinyin oriented to setting strategy as claimed in claim 3, further comprising:
counting the occurrence times of each polyphone and phrase in the first correction file, and recording the occurrences times in the polyphone and phrase dictionary;
and counting the occurrence times of each of the corresponding kana words in the second correction file and recording the counted number in the corresponding kana word dictionary.
5. The method for automatically generating Chinese Pinyin oriented to setting strategy as claimed in claim 4, further comprising:
calculating the occurrence probability of the polyphones according to the occurrence times of the polyphones and the phrases, and using the probability as a reference factor for correcting the initial file;
and calculating the occurrence probability of the common false words according to the occurrence times of the common false words, and using the common false words as a reference factor when the first correction file is corrected.
6. The device is characterized by comprising a polyphone word group dictionary construction module, a common-hypothesis word dictionary construction module, a set strategy article entry module, an initial file generation module, a first correction module and a second correction module, wherein:
the polyphone word group dictionary constructing module is connected with the first correcting module and is used for constructing a polyphone word group dictionary;
the common-false word dictionary construction module is connected with the second correction module and is used for constructing a common-false word dictionary;
the set strategy article recording module is connected with the initial file generating module and is used for recording a set strategy article;
the initial file generation module is connected with the set strategy article entry module and the first correction module and is used for matching pinyin for Chinese characters in the set strategy article by contrasting a Chinese dictionary and generating an initial file;
the first correction module is connected with the polyphone word group dictionary construction module, the initial file generation module and the second correction module and used for identifying polyphone words and word groups in the initial file by contrasting the polyphone word group dictionary and correcting pinyin of the polyphone words and the word groups to generate a first correction file;
the second correction module is connected with the common-false word dictionary construction module and the first correction module and used for identifying the common-false words in the first correction file by contrasting the common-false word dictionary and correcting the pinyin of the common-false words according to the context of the common-false words to generate a second correction file.
7. The device for automatically generating Chinese pinyin according to claim 6, further comprising a polyphone and phrase marking module and a common false word marking module, wherein:
the polyphone and phrase marking module is connected with the first correction module and used for marking the polyphone and phrases in the first correction file;
and the common false word marking module is connected with the second correction module and is used for marking the common false words in the second correction file.
8. An electronic device comprising a memory and a processor, wherein,
the memory storing computer instructions;
the processor configured to execute the computer instructions to cause the computer device to perform the method of any of claims 1-5.
9. A storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, performs the steps of the method according to any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011611532.0A CN112632967A (en) | 2020-12-30 | 2020-12-30 | Chinese pinyin automatic generation method and device oriented to set strategy |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011611532.0A CN112632967A (en) | 2020-12-30 | 2020-12-30 | Chinese pinyin automatic generation method and device oriented to set strategy |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112632967A true CN112632967A (en) | 2021-04-09 |
Family
ID=75287237
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011611532.0A Pending CN112632967A (en) | 2020-12-30 | 2020-12-30 | Chinese pinyin automatic generation method and device oriented to set strategy |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112632967A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109739369A (en) * | 2019-01-03 | 2019-05-10 | 上海中畅信息科技有限公司 | A kind of method that polyphone Chinese character turns phonetic spelling |
| CN109933215A (en) * | 2019-01-31 | 2019-06-25 | 平安科技（深圳）有限公司 | Phonetic transcriptions of Chinese characters conversion method, device, terminal and computer readable storage medium |
| CN110083711A (en) * | 2019-05-13 | 2019-08-02 | 成都启英泰伦科技有限公司 | A kind of phonetic transcriptions of Chinese characters conversion method and converting system |
| CN110874527A (en) * | 2018-08-28 | 2020-03-10 | 游险峰 | Cloud-based intelligent paraphrasing and phonetic notation system |
| CN112069805A (en) * | 2019-12-20 | 2020-12-11 | 北京来也网络科技有限公司 | Text labeling method, device, equipment and storage medium combining RPA and AI |
-
2020
- 2020-12-30 CN CN202011611532.0A patent/CN112632967A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110874527A (en) * | 2018-08-28 | 2020-03-10 | 游险峰 | Cloud-based intelligent paraphrasing and phonetic notation system |
| CN109739369A (en) * | 2019-01-03 | 2019-05-10 | 上海中畅信息科技有限公司 | A kind of method that polyphone Chinese character turns phonetic spelling |
| CN109933215A (en) * | 2019-01-31 | 2019-06-25 | 平安科技（深圳）有限公司 | Phonetic transcriptions of Chinese characters conversion method, device, terminal and computer readable storage medium |
| CN110083711A (en) * | 2019-05-13 | 2019-08-02 | 成都启英泰伦科技有限公司 | A kind of phonetic transcriptions of Chinese characters conversion method and converting system |
| CN112069805A (en) * | 2019-12-20 | 2020-12-11 | 北京来也网络科技有限公司 | Text labeling method, device, equipment and storage medium combining RPA and AI |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107291783B (en) | Semantic matching method and intelligent equipment | |
| CN111177184A (en) | Structured query language conversion method based on natural language and related equipment thereof | |
| US20120166942A1 (en) | Using parts-of-speech tagging and named entity recognition for spelling correction | |
| US11031009B2 (en) | Method for creating a knowledge base of components and their problems from short text utterances | |
| US20100076752A1 (en) | Automated Data Cleanup | |
| CN111143556B (en) | Automatic counting method and device for software function points, medium and electronic equipment | |
| WO2021174864A1 (en) | Information extraction method and apparatus based on small number of training samples | |
| CN104008123B (en) | The method and system matched for Chinese Name | |
| CN111369980B (en) | Voice detection method, device, electronic equipment and storage medium | |
| Li et al. | Improving text normalization using character-blocks based models and system combination | |
| CN113642316A (en) | Chinese text error correction method and device, electronic equipment and storage medium | |
| CN111767717A (en) | Indonesia grammar error correction method, device, equipment and storage medium | |
| CN111401012A (en) | Text error correction method, electronic device and computer readable storage medium | |
| US8041556B2 (en) | Chinese to english translation tool | |
| CN117251455A (en) | Intelligent report generation method and system based on large model | |
| Huang et al. | Chinese spelling check system based on tri-gram model | |
| CN113553853A (en) | Named entity recognition method and device, computer equipment and storage medium | |
| CN103530380B (en) | A kind of vertical search device and method | |
| CN111240971B (en) | Method and device for generating wind control rule test case, server and storage medium | |
| CN112632967A (en) | Chinese pinyin automatic generation method and device oriented to set strategy | |
| CN114490709B (en) | Text generation method and device, electronic equipment and storage medium | |
| CN111814433B (en) | Uygur language entity identification method and device and electronic equipment | |
| CN114896382A (en) | Artificial intelligent question-answering model generation method, question-answering method, device and storage medium | |
| CN114020774A (en) | Method, device and equipment for processing multiple rounds of question-answering sentences and storage medium | |
| CN113111651A (en) | Chinese word segmentation method and device and search word bank reading method |
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 |