CN112164403A - Natural language processing system based on artificial intelligence - Google Patents
Natural language processing system based on artificial intelligence Download PDFInfo
- Publication number
- CN112164403A CN112164403A CN202011030529.XA CN202011030529A CN112164403A CN 112164403 A CN112164403 A CN 112164403A CN 202011030529 A CN202011030529 A CN 202011030529A CN 112164403 A CN112164403 A CN 112164403A
- Authority
- CN
- China
- Prior art keywords
- unit
- pinyin
- target
- natural language
- voice
- 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
- 238000003058 natural language processing Methods 0.000 title claims abstract description 28
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 19
- 238000012937 correction Methods 0.000 claims abstract description 42
- 238000012545 processing Methods 0.000 claims abstract description 23
- 230000011218 segmentation Effects 0.000 claims abstract description 22
- 238000005457 optimization Methods 0.000 claims abstract description 13
- 238000012216 screening Methods 0.000 claims abstract description 10
- 230000003068 static effect Effects 0.000 claims description 25
- 238000007781 pre-processing Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 3
- 241000251468 Actinopterygii Species 0.000 description 3
- 238000000034 method Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 230000009849 deactivation Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/12—Use of codes for handling textual entities
- G06F40/126—Character encoding
- G06F40/129—Handling non-Latin characters, e.g. kana-to-kanji conversion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/12—Use of codes for handling textual entities
- G06F40/151—Transformation
-
- 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
- G06F40/253—Grammatical analysis; Style critique
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/02—Feature extraction for speech recognition; Selection of recognition unit
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
- G10L15/063—Training
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
- G10L15/18—Speech classification or search using natural language modelling
- G10L15/1822—Parsing for meaning understanding
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
- G10L15/063—Training
- G10L2015/0635—Training updating or merging of old and new templates; Mean values; Weighting
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Document Processing Apparatus (AREA)
Abstract
The invention belongs to the technical field of natural language processing, and discloses a natural language processing system based on artificial intelligence, which comprises: the voice recognition module is used for collecting and recognizing voice data and converting the voice data into a target text consisting of pinyin characters; the voice processing module is used for carrying out error correction and correction processing on the target text and outputting the processed target correction scheme as an output result; wherein the voice processing module comprises: the word segmentation unit is used for carrying out pinyin word segmentation on the target text to obtain a pinyin sequence; the text analysis unit is used for identifying the errors of the pinyin sequence and analyzing the types of the errors; the correction unit gives out at least one correction scheme according to the analysis result of the text analysis unit; and the optimization unit is used for optimizing and screening at least one correction scheme and outputting the target correction scheme after optimization and screening as an output result.
Description
Technical Field
The invention belongs to the technical field of natural language processing, and particularly relates to a natural language processing system based on artificial intelligence.
Background
Natural Language Processing (NLP) is a branching subject of the fields of artificial intelligence and linguistics. This field discusses how to handle and use natural language; natural language processing basically includes parts of recognition, understanding, generation, and the like. The natural language cognition and understanding is that the computer changes the acquired natural language into meaningful symbols and establishes corresponding relations, and then the symbols are processed according to the purpose of use. Natural language processing has recently become a popular research direction, with machine translation being the earliest research effort in natural language processing.
At present, most of natural language processing is rule-based methods, and in the method, only one isolated sentence is analyzed, and the association between contexts and the conversation context are difficult to match, so that the problems of large language processing limitation, low accuracy and low intelligence degree exist.
Disclosure of Invention
In view of the above, to solve the deficiencies in the prior art, the present invention provides a natural language processing system based on artificial intelligence.
In order to achieve the purpose, the invention provides the following technical scheme: an artificial intelligence based natural language processing system comprising:
the voice recognition module is used for collecting and recognizing voice data and converting the voice data into a target text consisting of pinyin characters;
the voice processing module is used for carrying out error correction and correction processing on the target text and outputting the processed target correction scheme as an output result;
wherein the voice processing module comprises:
the word segmentation unit is used for carrying out pinyin word segmentation on the target text to obtain a pinyin sequence;
the text analysis unit is used for identifying errors of the pinyin sequence and analyzing the types of the errors, wherein the types of the errors comprise grammar errors, semantic errors and pragmatic errors;
the correction unit gives out at least one correction scheme according to the analysis result of the text analysis unit;
and the optimization unit is used for optimizing and screening at least one correction scheme and outputting the target correction scheme after optimization and screening as an output result.
Preferably, the speech recognition module includes:
the language acquisition unit is used for acquiring voice data on line and converting the voice data into TXT format text for storage;
the preprocessing unit is used for segmenting words of the format text according to a preset word segmentation program, filtering out words or phrases which are stopped in the format text and obtaining a target characteristic set;
the characteristic extraction unit is used for extracting the characteristics of the target characteristic set to obtain a voice characteristic sequence and converting the voice characteristic sequence into a pinyin characteristic sequence;
and the identification unit is used for identifying, matching and comparing the pinyin characteristic sequence with the acoustic model to obtain a target identification result, wherein the target identification result is a target text consisting of pinyin characters.
Preferably, the word segmentation program adopted in the preprocessing unit is a Chinese character word segmentation program.
Preferably, when the preprocessing unit performs word segmentation processing, adjacent words or phrases are separated by a space.
Preferably, in the feature extraction unit, converting the speech feature sequence into a pinyin feature sequence includes:
converting the voice characteristic sequence into a pinyin characteristic sequence according to the ASCII code of the Chinese character; or
And converting the voice characteristic sequence into a pinyin characteristic sequence according to the Unicode value of the Chinese character.
Preferably, the processing system further comprises a knowledge base, and the knowledge base comprises a static base and a dynamic base, and the correction unit gives at least one correction scheme in combination with the error type and the application text stored in the static base and the dynamic base.
Preferably, the static library is used for storing standard texts and historical recognized voice texts and can be automatically updated; the dynamic library is automatically constructed based on the currently collected voice data, and standard texts or voice texts with the same context as the currently collected voice data are screened from the static library.
Preferably, in the recognition unit, the acoustic model is an acoustic model pre-trained by a standard text in a static library; and performing pre-training of the acoustic model correspondingly once every time the static library is updated.
Preferably, the optimization unit performs optimization of the target correction scheme according to the number of errors corrected by each correction scheme, and the number of errors corrected by the target correction scheme is the largest.
Preferably, the knowledge base further includes a disabled word base, and the preprocessing unit filters the disabled words or phrases according to the disabled word base.
Compared with the prior art, the invention has the following beneficial effects:
in the invention, the grammar analysis, the semantic analysis and the pragmatic analysis are combined to further correct the errors of the traditionally recognized natural language, so that the final output result can be more accurately adapted to the actual conversation environment, and the accuracy of the whole processing system for speech recognition is effectively improved.
In addition, a knowledge base comprising a static base and a dynamic base is arranged in the whole system, wherein the static base can be automatically updated based on historical recognition records, and the dynamic base automatically screens text information based on currently collected voice data, so that the adaptability and the processing efficiency of the whole system to specific problems are further improved.
Drawings
FIG. 1 is a block diagram of a natural language processing system provided by the present invention;
FIG. 2 is a flow chart of the natural language processing system of the present invention when executing processing.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of 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.
In the embodiment of the present invention, a natural language processing system based on artificial intelligence is disclosed, and specifically, referring to fig. 1, the processing system includes the following structure:
the voice recognition module 10 is used for collecting and recognizing voice data and converting the voice data into a target text consisting of pinyin characters;
specifically, the speech recognition module 10 includes the following:
the language acquisition unit 11 is used for acquiring voice data on line and converting the voice data into TXT format text for storage;
the preprocessing unit 12 is used for segmenting words of the text in the format of (TXT) according to a preset word segmentation program, filtering out deactivated words or phrases in the text in the format of (TXT) and obtaining a target feature set; the word segmentation program adopts a Chinese character word segmentation program, and when the word segmentation processing is carried out, adjacent words or phrases are separated by a blank space;
the feature extraction unit 13 is used for extracting features of the target feature set to obtain a voice feature sequence and converting the voice feature sequence into a pinyin feature sequence; dividing a target feature set into a plurality of discrete segments according to the change of a voice waveform of the target feature set along with time, and labeling the plurality of segments in sequence, wherein each segment correspondingly comprises at least one word or phrase, so that a voice feature sequence can be formed according to the labels;
and the identification unit 14 is used for identifying, matching and comparing the pinyin characteristic sequence with the acoustic model to obtain a target identification result, wherein the target identification result is a target text consisting of pinyin characters.
The voice processing module 20 is configured to perform error correction and correction processing on the target text, and output the processed target correction scheme as an output result;
specifically, the speech processing module 20 includes the following:
a word segmentation unit 21, configured to perform pinyin word segmentation on the target text to obtain a pinyin sequence;
the text analysis unit 22 is used for identifying errors of the pinyin sequence and analyzing the types of the errors, wherein the types of the errors comprise grammar errors, semantic errors and pragmatic errors;
a correction unit 23 giving at least one correction scheme based on the analysis result of the text analysis unit 22;
and the optimization unit 24 is used for performing optimization screening on at least one correction scheme and outputting the target correction scheme after optimization screening as an output result.
The knowledge base 30 includes a static base 31, a dynamic base 32, and a deactivation word base 33. The static library 31 is used for storing standard texts and historical recognized voice texts, and can be automatically updated; the dynamic library 32 is automatically constructed based on the currently collected voice data, and the standard text or voice text having the same context as the currently collected voice data is screened from the static library 31.
In addition:
the correction unit 23 provides at least one correction scheme in association with the type of error and the application text stored in the static library 31 and the dynamic library 32 when correcting the process.
In the recognition unit 14, the acoustic model is an acoustic model pre-trained by standard text in the static library 31; and each time the static library 31 is updated, pre-training of the acoustic model is performed correspondingly.
Specifically, the standard text information stored in the static library 31 may be collected from data sources such as books, news, web pages (e.g., encyclopedia, wikipedia, etc.); for example, word recognition may be performed on words in a book, particularly a standard book (such as a dictionary), and all correspondences may be stored in the static library 31 as standard texts.
In summary, the artificial intelligence based natural language processing system disclosed above specifically includes the following steps when performing the speech recognition processing:
s1, collecting voice data on line, and converting the voice data into a TXT format text for storage;
for example, the speech data collected by the language collecting unit 11 is "when fish will be dropped", and the corresponding application context is set as weather query;
s2, segmenting words of the format text according to a preset Chinese character segmentation program, and filtering out words or phrases which are stopped in the format text to obtain a target characteristic set;
specifically, the words of 'when rains will fall' are divided into words of 'when' - ', when' - 'fish will' and word group sequences; and the sequence does not contain the deactivated word or phrase, depending on the deactivated lexicon 33 in the knowledge base 30.
S3, extracting the characteristics of the target characteristic set to obtain a voice characteristic sequence, and converting the voice characteristic sequence into a pinyin characteristic sequence;
specifically, the voice characteristic sequence is converted into a pinyin characteristic sequence according to the ASCII code of the Chinese character; because the Chinese characters are represented by ASCII codes in the computer system, the sentences can be converted into pinyin sequences only by utilizing the corresponding relation between each pinyin and each ASCII code which is already in the computer system or established by a user. If the sentence contains polyphone, the determination can be made according to the collected pronunciation of the speech data. For example, "meeting" includes "hui" and "kuai", the pronunciation of the speech data is used as the standard to obtain the corresponding speech feature sequence: "shenme" - "shihou" - "hui" - "xiayu".
In addition, the phonetic characteristic sequence can be converted into phonetic characteristic sequence according to the Unicode value of Chinese characters.
S4, identifying, matching and comparing the pinyin characteristic sequence with the acoustic model to obtain a target identification result, wherein the target identification result is a target text consisting of pinyin characters;
s5, performing pinyin word segmentation on the target text to obtain a pinyin sequence;
s6, identifying errors of the pinyin sequence and analyzing the types of the errors;
in "shenme" - "shihou" - "hui" - "xiayu", there are included: the semantic error 'xiayu', such as raining/fish dropping/summer Yu/prison, has different semantics; syntax errors, lack of definition;
s7, at least one correction scheme is given by combining the error types and the application texts stored in the static library 31 and the dynamic library 32;
regarding the semantic errors described above, scheme 1 is given: "when it rains"; scheme 2 is given: "when to return to summer" day;
for syntax errors, in combination with scheme 1 above, the syntax lacks time limitation according to the application texts stored in the static library 31 and the dynamic library 32, and then the dynamic library 32 established according to the weather query context gives a correction scheme that: "when it rains on this week"; with reference to the above scheme 2, according to the application texts stored in the static library 31 and the dynamic library 32, the grammar lacks time limitation and purpose limitation, and further, the dynamic library 32 established according to the weather query context gives a modification scheme that: "when to return to summer" day;
s8, carrying out optimization screening on at least one correction scheme, and outputting by taking the target correction scheme subjected to optimization screening as an output result;
as can be seen from the two modifications given above, the number of errors corrected by "when it rains on the week" is the largest, and therefore "when it rains on the week" is output as the output result.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
1. An artificial intelligence based natural language processing system, comprising:
the voice recognition module is used for collecting and recognizing voice data and converting the voice data into a target text consisting of pinyin characters;
the voice processing module is used for carrying out error correction and correction processing on the target text and outputting the processed target correction scheme as an output result;
wherein the voice processing module comprises:
the word segmentation unit is used for carrying out pinyin word segmentation on the target text to obtain a pinyin sequence;
the text analysis unit is used for identifying errors of the pinyin sequence and analyzing the types of the errors, wherein the types of the errors comprise grammar errors, semantic errors and pragmatic errors;
the correction unit gives out at least one correction scheme according to the analysis result of the text analysis unit;
and the optimization unit is used for optimizing and screening at least one correction scheme and outputting the target correction scheme after optimization and screening as an output result.
2. An artificial intelligence based natural language processing system as claimed in claim 1, wherein said speech recognition module comprises:
the language acquisition unit is used for acquiring voice data on line and converting the voice data into TXT format text for storage;
the preprocessing unit is used for segmenting words of the format text according to a preset word segmentation program, filtering out words or phrases which are stopped in the format text and obtaining a target characteristic set;
the characteristic extraction unit is used for extracting the characteristics of the target characteristic set to obtain a voice characteristic sequence and converting the voice characteristic sequence into a pinyin characteristic sequence;
and the identification unit is used for identifying, matching and comparing the pinyin characteristic sequence with the acoustic model to obtain a target identification result, wherein the target identification result is a target text consisting of pinyin characters.
3. An artificial intelligence based natural language processing system according to claim 2, wherein: the word segmentation program adopted in the preprocessing unit is a Chinese character word segmentation program.
4. An artificial intelligence based natural language processing system according to claim 3, wherein: when the preprocessing unit carries out word segmentation processing, adjacent words or phrases are separated through a blank space.
5. The artificial intelligence based natural language processing system of claim 2, wherein in the feature extraction unit, converting the speech feature sequence into a pinyin feature sequence comprises:
converting the voice characteristic sequence into a pinyin characteristic sequence according to the ASCII code of the Chinese character; or
And converting the voice characteristic sequence into a pinyin characteristic sequence according to the Unicode value of the Chinese character.
6. An artificial intelligence based natural language processing system according to any one of claims 2 to 5 wherein: the processing system further comprises a knowledge base, the knowledge base comprises a static base and a dynamic base, and the correcting unit is used for giving out at least one correcting scheme by combining the error type and the application texts stored in the static base and the dynamic base.
7. An artificial intelligence based natural language processing system according to claim 6, wherein: the static library is used for storing standard texts and historical recognized voice texts and can be automatically updated; the dynamic library is automatically constructed based on the currently collected voice data, and standard texts or voice texts with the same context as the currently collected voice data are screened from the static library.
8. An artificial intelligence based natural language processing system according to claim 7, wherein: in the identification unit, the acoustic model is an acoustic model pre-trained by standard texts in a static library;
and performing pre-training of the acoustic model correspondingly once every time the static library is updated.
9. The artificial intelligence based natural language processing system of claim 7, wherein the preference unit performs the preference of the target correction scheme according to the number of errors corrected by each correction scheme, and the number of errors corrected by the target correction scheme is the largest.
10. An artificial intelligence based natural language processing system according to claim 6, wherein: the knowledge base also comprises a disabled word base, and the preprocessing unit filters out disabled words or phrases according to the disabled word base.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011030529.XA CN112164403A (en) | 2020-09-27 | 2020-09-27 | Natural language processing system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011030529.XA CN112164403A (en) | 2020-09-27 | 2020-09-27 | Natural language processing system based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112164403A true CN112164403A (en) | 2021-01-01 |
Family
ID=73864227
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011030529.XA Pending CN112164403A (en) | 2020-09-27 | 2020-09-27 | Natural language processing system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112164403A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102662933A (en) * | 2012-03-28 | 2012-09-12 | 成都优译信息技术有限公司 | Distributive intelligent translation method |
| CN108229137A (en) * | 2017-12-29 | 2018-06-29 | 北京长御科技有限公司 | A kind of method and device for distributing document permission |
| WO2018121757A1 (en) * | 2016-12-31 | 2018-07-05 | 深圳市优必选科技有限公司 | Method and system for speech broadcast of text |
| CN109255113A (en) * | 2018-09-04 | 2019-01-22 | 郑州信大壹密科技有限公司 | Intelligent critique system |
| CN109635298A (en) * | 2018-12-11 | 2019-04-16 | 平安科技（深圳）有限公司 | Group's state identification method, device, computer equipment and storage medium |
| CN110110041A (en) * | 2019-03-15 | 2019-08-09 | 平安科技（深圳）有限公司 | Wrong word correcting method, device, computer installation and storage medium |
| CN110717021A (en) * | 2019-09-17 | 2020-01-21 | 平安科技（深圳）有限公司 | Input text and related device for obtaining artificial intelligence interview |
| CN110909550A (en) * | 2019-11-13 | 2020-03-24 | 北京环境特性研究所 | Text processing method and device, electronic equipment and readable storage medium |
-
2020
- 2020-09-27 CN CN202011030529.XA patent/CN112164403A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102662933A (en) * | 2012-03-28 | 2012-09-12 | 成都优译信息技术有限公司 | Distributive intelligent translation method |
| WO2018121757A1 (en) * | 2016-12-31 | 2018-07-05 | 深圳市优必选科技有限公司 | Method and system for speech broadcast of text |
| CN108229137A (en) * | 2017-12-29 | 2018-06-29 | 北京长御科技有限公司 | A kind of method and device for distributing document permission |
| CN109255113A (en) * | 2018-09-04 | 2019-01-22 | 郑州信大壹密科技有限公司 | Intelligent critique system |
| CN109635298A (en) * | 2018-12-11 | 2019-04-16 | 平安科技（深圳）有限公司 | Group's state identification method, device, computer equipment and storage medium |
| CN110110041A (en) * | 2019-03-15 | 2019-08-09 | 平安科技（深圳）有限公司 | Wrong word correcting method, device, computer installation and storage medium |
| CN110717021A (en) * | 2019-09-17 | 2020-01-21 | 平安科技（深圳）有限公司 | Input text and related device for obtaining artificial intelligence interview |
| CN110909550A (en) * | 2019-11-13 | 2020-03-24 | 北京环境特性研究所 | Text processing method and device, electronic equipment and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107315737B (en) | Semantic logic processing method and system | |
| CN109255113B (en) | Intelligent proofreading system | |
| CN109635288A (en) | A kind of resume abstracting method based on deep neural network | |
| KR20110038474A (en) | Apparatus and method for detecting sentence boundaries | |
| CN109949799B (en) | Semantic parsing method and system | |
| CN110942767B (en) | Recognition labeling and optimization method and device for ASR language model | |
| CN110008473B (en) | Medical text named entity identification and labeling method based on iteration method | |
| CN113761903A (en) | Text screening method for high-volume high-noise spoken short text | |
| CN111460175A (en) | SNOMED-CT-based medical noun dictionary construction and expansion method | |
| CN114927177B (en) | Medical entity identification method and system integrating Chinese medical field characteristics | |
| KR20230009564A (en) | Learning data correction method and apparatus thereof using ensemble score | |
| CN112818680A (en) | Corpus processing method and device, electronic equipment and computer-readable storage medium | |
| CN111444704A (en) | Network security keyword extraction method based on deep neural network | |
| CN113255331A (en) | Text error correction method, device and storage medium | |
| CN109918677B (en) | English word semantic analysis method and system | |
| CN115240655A (en) | Chinese voice recognition system and method based on deep learning | |
| CN116842168B (en) | Cross-domain problem processing method and device, electronic equipment and storage medium | |
| JP2018066800A (en) | Japanese speech recognition model learning device and program | |
| CN106682642A (en) | Multi-language-oriented behavior identification method and multi-language-oriented behavior identification system | |
| CN111046663A (en) | Intelligent correction method for Chinese form | |
| Mekki et al. | COTA 2.0: An automatic corrector of Tunisian Arabic social media texts | |
| CN115577712A (en) | Text error correction method and device | |
| CN112164403A (en) | Natural language processing system based on artificial intelligence | |
| CN114996387A (en) | Index data-based natural language processing method and system | |
| CN111814433B (en) | Uygur language entity identification method and device and electronic equipment |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210101 |