CN104199840B - Intelligent place name identification technology based on statistical model - Google Patents
Intelligent place name identification technology based on statistical model Download PDFInfo
- Publication number
- CN104199840B CN104199840B CN201410381574.8A CN201410381574A CN104199840B CN 104199840 B CN104199840 B CN 104199840B CN 201410381574 A CN201410381574 A CN 201410381574A CN 104199840 B CN104199840 B CN 104199840B
- Authority
- CN
- China
- Prior art keywords
- place name
- place
- name
- text
- identification
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
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)
- Machine Translation (AREA)
Abstract
The present invention relates to place name identification technology, it is desirable to provide the intelligent place name identification technology based on statistical model.The intelligent place name identification technology based on statistical model, basic segmentation sequence is obtained by way of Statistical Probabilistic Models and dictionary first and place name sign is noted, then a part of place name is first determined by independent place name identification, then for possible place name, take the superior and the subordinate's place name identification, place name statistical model context identification, the place name information such as qi that disappear perform screening to place name quality in name, last to carry out the further filter false place name of statistical analysis to the place name recognized in full.The present invention makes full use of various flexi modes of the Chinese for place name description, provides place name identification the higher accuracy of practical level, is divided for article according to geographical ownership place, and mechanism identification provides strong help.
Description
Technical field
The present invention is the intelligent place name identification technology more particularly to based on statistical model on place name identification technical field.
Background technology
The mode of current place name identification technology, mainly place name keyword match.But because Chinese Place Names flexibly describe
A variety of causes, cause to cannot recognize that in place name identification be originally place name title, or situations such as wrong identification non-place name.Over the ground
The limitation of name technology brings great difficulty for article region division.
Human brain identification place name generally has three kinds of means：Place name known to matching, unknown place name is guessed based on Inner Constitution, is based on
Context simply guesses unknown place name.In conventional research, these three means are usually integrated into system in different combinations
In meter and algorithm.The mechanism of action identified according to human brain, applied in place name identification technology, mainly has following existing at present
Technology：1st, the automatic identification of Shen Dayang Chinese Place Names, using statistical model, screened, reached using attribute matrix and frequency level
Higher recall rate is arrived, but accurate rate is relatively low；2nd, Liu Kaiying Chinese text automatic word segmentation and mark, are taken based on corpus
Method, entered according to the information of dictionary of place name statistical analysis place name word and these words in real text using program information
Row place name identification, achieves certain effect to place name identification, but also following deficiencies：The flexible describing mode of place name is examined
Survey not comprehensive；The information disturbed in place name text can not accurately distinguish (place name in such as name)；3、Tan Hong Ye
Research on Method of Automatic Recognition of Chinese Place Named Based on
Transformation, the prior art is on the basis of technology 2, it is proposed that a kind of place name identification method based on exchange, obtains
To the rule of place name context, rule to be screened, this method effectively increases the accurate rate of system, but under also having
State deficiency：The quality of identification will depend on known context rule；It is more complicated to add new context rule process.
The content of the invention
It is a primary object of the present invention to overcome deficiency of the prior art, there is provided one kind is adapted in Chinese Place Names description
A variety of flexible descriptions, and can be according to the various application scenarios of place name, the place name identification technology of self-teaching.It is above-mentioned to solve
Technical problem, solution of the invention are：
Intelligent place name identification technology based on statistical model is provided, specifically includes following step：
Step 1：By the text of required place name identification, divided using the basic segmentation methods based on Statistical Probabilistic Models
Word, word segmentation result is obtained, information of place names (such as Xinjiang), national name (such as Uygur nationality) and row are marked out in word segmentation result
Political affairs organization (such as autonomous region)；
Step 2：Word segmentation result in step 1, based on place name Basic period structure, to the text of required place name identification
Carry out place name and sort out identification：
A, independent place name identification：The text of required place name identification is included into information of place names (such as Hangzhou) and administrative unit's name
Claim in (such as city), or including information of place names (such as Hangzhou) and appear in significant phrase (such as political affairs in information of place names above or below
Mansion, public security bureau) word segmentation result, be recorded as independent place name, and the information of place names in word segmentation result is identified as the required place name
Identify the place name of text；
B, may place name identification：The text of required place name identification is included into information of place names, but not including that administrative unit
The word segmentation result of title appears in significant phrase before and after information of place names, and being recorded as may place name；
Step 3：To the possibility place name recorded in step 2, based on place name Basic period structure, classification place name identification is carried out：
, will likely ground if a, the possibility place name of record belongs in step A the subordinate unit of the independent place name identified
Name is recorded as independent place name, and the subordinate unit of independent place name is identified as to the place name of the required place name identification text；
B, to be registered as may place name text, carried out according to the keyword manually marked in place name Basic period structure
Hereafter mark, if can recognize that corresponding place name+government in place name Basic period structure in text, by the corresponding place name identification
For the place name of required place name identification text；
C, to be registered as may place name text, the word segmentation result in step 1, utilize the identification of Chinese personal name
Algorithm, judges whether context and possible place name form the name of Chinese, if the name of Chinese is formed, by the possible place name sign
Being designated as can not possibly place name；
The recognizer of the Chinese personal name is mainly using in the text for information of place names (as Hangzhou only occur) only occur
Judged, using conventional name knowledge base, by information of place names and one or two words of information of place names front or behind
Combination judge whether forming name, and (such as Zhang Hangzhou, a word belongs to the commonly used word of surname before Hangzhou, so in Zhang Hangzhou
Hangzhou be not belonging to place name)；
D, to be registered as may place name text, mark auxiliary word (such as road name, landmark building all in text
Deng), it is required place name by the place name identification of this area if at least occurring once the auxiliary word in possible place name area in text
Identify the place name of text；
Step 4：According to auxiliary word dictionary, auxiliary word all in the text of required place name identification is marked, if text
In at least there is the auxiliary word in same place name area twice, then the place name is recorded as independent place name, and the place name identification is
The place name of the required place name identification text；
Step 5：Repeat step a, judge to whether there is subordinate's place name in independent place name in possible place name, if it is,
Place name by the possible place name sign note for concern；
Step 6：All place names identified in the text of the required place name identification are exported, and mark out place name appearance
Text position.
In the present invention, the basic segmentation methods based on Statistical Probabilistic Models in the step 1, in particular to：Take
The contextual feature made by oneself, to basic dictionary and the algorithm in probabilistic model alternate analysis phrase line of demarcation.
In the present invention, the foundation of the place name Basic period structure specifically includes following step：
(1) information of place names and keyword occurred in all kinds article is compiled, and is manually marked, the pass
Keyword refers to appear in the significant phrase in place name above or below, including organization names (such as government, public security bureau), it is significant
Point (such as West Lake)；
(2) place name Basic period structure is arranged, place name Basic period structure includes national province, city, county, the place name title in area, letter
Title, nickname, relationship between superior and subordinate, administrative region code；
(3) basis of the required knowledge base for the basic segmentation methods based on Statistical Probabilistic Models that step 1 is taken is arranged,
Including arranging and training the participle model based on statistical probability segmented, participle model is labeled based on word, and takes B
Two kinds of marks of (beginning of word) and E (not being the beginning of word), finally with maximum entropy training pattern, obtain final mask；
(4) by all words in the place name Basic period structure of step (2), it is added to step (3) as supplement dictionary
In participle model；
(5) single place name Dealing the Quality Knowledge Database is established, for only there is the possibility place name of information of place names, judging whether to know
Wei not independent place name (as only occurred whether Hangzhou may determine that as Hangzhou)；
(6) conventional surname, common first names are collected, establish conventional name knowledge base；
(7) auxiliary word dictionary, street name of the auxiliary word including (important) city (main), landmark building, are established
School, hospital, and the interference between auxiliary word and the qi that disappears are arranged.
In the present invention, study module is additionally provided with the intelligent place name identification technology, for will be not true in identification process
Fixed ground list of file names, contextual information, unidentified type and have determined that information of place names is recorded, and be converted into can be for rope
The file drawn, finally include and enter storage and index in place name quality storehouse；And at regular intervals, manually to common situation
Concluded and summarized, and regularly update place name quality storehouse.
The operation principle of the present invention：Obtained first by way of Statistical Probabilistic Models and dictionary basic segmentation sequence and
Place name sign is noted, a part of place name is first then determined by independent place name identification；Then for possible place name, the superior and the subordinate are taken
Place name identification, place name statistical model context identification, the place name information such as qi that disappear perform screening to place name quality in name, last complete
Text carries out the further filter false place name of statistical analysis to the place name recognized.
Compared with prior art, the beneficial effects of the invention are as follows：
The present invention makes full use of various flexi modes of the Chinese for place name description, and practical level is provided to place name identification
Higher accuracy, divided for article according to geographical ownership place, mechanism identification provides strong help.
The consideration based on commercial Application of the invention, the advantages of inheriting statistical model and corpus, and add on this basis
Having added can be with self-teaching and the framework of supplement, so as to realize the target for constantly providing accuracy rate.
Brief description of the drawings
Fig. 1 is the fundamental diagram of the present invention.
Embodiment
It is computer technology in the one kind in field of putting on record the present invention relates to the information processing technology firstly the need of explanation
Using.In the implementation process of the present invention, the application of multiple software function modules can be related to.It is applicant's understanding that such as careful
After Reading of Application Documents, accurate understanding realization principle and goal of the invention of the invention, the situation of existing known technology is being combined
Under, those skilled in the art can use the software programming technical ability of its grasp to realize the present invention completely.Aforementioned software functional module
Including but not limited to：Place name disambiguation algorithm, study module etc., all in place name statistical model context recognizer, name
Category this category that the present patent application file refers to, applicant will not enumerate.
The present invention is described in further detail with embodiment below in conjunction with the accompanying drawings：
It is the preparation of place name Basic period structure first：
(1) information of place names and keyword occurred in all kinds article is compiled, and is manually marked, the pass
Keyword refers to appear in the significant phrase in place name above or below；
(2) place name Basic period structure is arranged, place name Basic period structure includes national province, city, county, the place name title in area, letter
Title, nickname, relationship between superior and subordinate, administrative region code；
(3) basis of the required knowledge base of the basic segmentation methods based on Statistical Probabilistic Models is arranged, including arranges and instructs
Practice and be labeled to the participle model based on statistical probability that segments, participle model based on word, and take B (beginning of word) and
Two kinds of marks of E (not being the beginning of word), finally with maximum entropy training pattern；Focus on Statistical model of segmentation feature selection and
Final mask；
(4) by all words in the place name Basic period structure of step (2), it is added to step (3) as supplement dictionary
In participle model；
(5) single place name Dealing the Quality Knowledge Database is established, for only there is the possibility place name of information of place names, judging whether to know
Not Wei independent place name, such as only occur whether Hangzhou may determine that as Hangzhou；
(6) conventional surname, common first names are collected, establish conventional name knowledge base；
(7) auxiliary word dictionary, street name of the auxiliary word including (important) city (main), landmark building, are established
School, hospital, and the interference between auxiliary word and the qi that disappears are arranged.
Secondly it is place name identification technology, as shown in figure 1, the intelligent place name identification technology based on statistical model, is specifically included
Following step：
Step 1：By the text of required place name identification, divided using the basic segmentation methods based on Statistical Probabilistic Models
Word, word segmentation result is obtained, information of place names (such as Xinjiang), national name (such as Uygur nationality) and row are marked out in word segmentation result
Political affairs organization (such as autonomous region).
Step 2：Word segmentation result in step 1, based on place name Basic period structure, to the text of required place name identification
Carry out place name and sort out identification：
A, independent place name identification：The text of required place name identification is included into information of place names (such as Hangzhou), administrative unit's name
Claim (such as city), appear in place name above or below (significant) phrase (such as government, public security bureau) word segmentation result, for place name
Title+administrative unit's combination (such as Hangzhou) or the phrase (such as Hangzhou government) of place name title+above or below (significant)
In place name be recorded as independent place name, and the information of place names in word segmentation result is identified as to the ground of the required place name identification text
Name；
B, may place name identification：The text of required place name identification is included into information of place names, but not including that administrative unit
The word segmentation result of title, being recorded as may place name.
Step 3：To the possibility place name recorded in step 2, based on place name Basic period structure, classification place name identification is carried out：
, will likely ground if a, the possibility place name of record belongs in step A the subordinate unit of the independent place name identified
Name is recorded as independent place name, and the subordinate unit of independent place name is identified as to the place name of the required place name identification text；
B, to be registered as may place name text, carried out according to the keyword manually marked in place name Basic period structure
Hereafter mark, if can recognize that corresponding place name+government in place name Basic period structure in text, by the corresponding place name identification
For the place name of required place name identification text；
C, to be registered as may place name text, the word segmentation result in step 1, utilize the identification of Chinese personal name
Algorithm, judges whether context and possible place name form the name of Chinese, if the name of Chinese is formed, by the possible place name sign
Being designated as can not possibly place name；
D, to be registered as may place name text, mark auxiliary word (such as road name, landmark building all in text
Deng), it is required place name by the place name identification of this area if at least occurring once the auxiliary word in possible place name area in text
Identify the place name of text.
Step 4：According to auxiliary word dictionary, auxiliary word all in the text of required place name identification is marked, if text
In at least there is the auxiliary word in same place name area twice, then the place name is recorded as independent place name, and the place name identification is
The place name of the required place name identification text.
Step 5：Repeat step a, judge to whether there is subordinate's place name in independent place name in possible place name, if it is,
Place name by the possible place name sign note for concern.
Step 6：Study module is additionally provided with intelligent place name identification technology, for by undetermined place name in identification process
List, contextual information, unidentified type and have determined that information of place names is recorded, and be converted into can be for the text of index
Part, finally include and enter storage and index in place name quality storehouse；And at regular intervals, manually common situation is returned
Receive and summarize, and regularly update place name quality storehouse.
Step 7：All place names identified in the text of the required place name identification are exported, and mark out place name appearance
Text position.
Finally it should be noted that listed above is only specific embodiment of the invention.It is clear that the invention is not restricted to
Above example, there can also be many variations.One of ordinary skill in the art can directly lead from present disclosure
All deformations for going out or associating, are considered as protection scope of the present invention.
Claims (2)
1. the intelligently name recognition method based on statistical model, it is characterised in that specifically include following step：
Step 1：By the text of required place name identification, segmented, obtained using the basic segmentation methods based on Statistical Probabilistic Models
To word segmentation result, information of place names, national name and administrative unit's title are marked out in word segmentation result；
Step 2：Word segmentation result in step 1, based on place name Basic period structure, the text of required place name identification is carried out
Place name sorts out identification：
A, independent place name identification：The text of required place name identification is included into information of place names and administrative unit's title, or including
Information of place names and the word segmentation result for appearing in the significant phrase in information of place names above or below, independent place name is recorded as, and will
Information of place names in word segmentation result is identified as the place name of the required place name identification text；
B, may place name identification：The text of required place name identification is included into information of place names, but not including that administrative unit's title
Word segmentation result or appear in significant phrase before and after information of place names, being recorded as may place name；
The foundation of the place name Basic period structure specifically includes following step：(1) compile what is occurred in all kinds article
Information of place names and keyword, and manually marked, the keyword refers to appear in the significant word in place name above or below
Group, including organization names, significant place；(2) arrange place name Basic period structure, place name Basic period structure include national province, city,
County, the place name title in area, abbreviation, nickname, relationship between superior and subordinate, administrative region code；(3) arrange step 1 take based on statistics
The basis of the required knowledge base of the basic segmentation methods of probabilistic model, including arrange and train to segment based on statistical probability
Participle model, participle model is labeled based on word, and takes two kinds of marks of B and E, and B represents the beginning of word, E represent be not
The beginning of word, finally with maximum entropy training pattern, obtain final mask；(4) by the institute in the place name Basic period structure of step (2)
Some words, it is added to as supplement dictionary in the participle model of step (3)；(5) establish single place name Dealing the Quality Knowledge Database, for pair
Only there is the possibility place name of information of place names, judge whether that independent place name can be identified as；(6) conventional surname, common first names are collected, are established normal
With name knowledge base；(7) auxiliary word dictionary is established, aids in street name of the word including city, landmark building, school, hospital,
And the interference between auxiliary word and the qi that disappears are arranged；
Step 3：To the possibility place name recorded in step 2, based on place name Basic period structure, classification place name identification is carried out：
, will likely ground Famous Journalist if a, the possibility place name of record belongs in step A the subordinate unit of the independent place name identified
Record as independent place name, and the subordinate unit of independent place name is identified as to the place name of the required place name identification text；
B, to be registered as may place name text, context is carried out according to the keyword that is manually marked in place name Basic period structure
Mark, if can recognize that corresponding place name+government in place name Basic period structure in text, institute is identified as by the correspondence place name
Need the place name of place name identification text；
C, to be registered as may place name text, the word segmentation result in step 1, using the recognizer of Chinese personal name,
Judge whether context and possible place name form the name of Chinese, if forming the name of Chinese, the possible place name sign is designated as
Can not possibly place name；
The recognizer of the Chinese personal name is used to judging in the text for information of place names only occur, is known using conventional name
Know storehouse, one or two word combinations of information of place names and information of place names front or behind are carried out judging whether to form surname
Name；
D, to be registered as may place name text, auxiliary word all in text is marked, if at least occurring one in text
The auxiliary word in secondary possible place name area, then by the place name of the place name identification of this area place name identification text for needed for；
Step 4：According to auxiliary word dictionary, auxiliary word all in the text of required place name identification is marked, if in text extremely
Few auxiliary word for same place name area twice occur, then be recorded as independent place name, and the place name identification is the institute by the place name
Need the place name of place name identification text；
Step 5：Repeat step a, judge to whether there is subordinate's place name in independent place name in possible place name, if it is, should
Possible place name sign note is the place name of concern；
Step 6：All place names identified in the text of the required place name identification are exported, and mark out the text of place name appearance
Position.
2. the intelligently name recognition method according to claim 1 based on statistical model, it is characterised in that the step 1
In basic segmentation methods based on Statistical Probabilistic Models, in particular to：Take the contextual feature made by oneself, to basic dictionary and
The algorithm in probabilistic model alternate analysis phrase line of demarcation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410381574.8A CN104199840B (en) | 2014-08-05 | 2014-08-05 | Intelligent place name identification technology based on statistical model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410381574.8A CN104199840B (en) | 2014-08-05 | 2014-08-05 | Intelligent place name identification technology based on statistical model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104199840A CN104199840A (en) | 2014-12-10 |
| CN104199840B true CN104199840B (en) | 2018-03-06 |
Family
ID=52085133
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410381574.8A Active CN104199840B (en) | 2014-08-05 | 2014-08-05 | Intelligent place name identification technology based on statistical model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104199840B (en) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105224522A (en) * | 2015-09-29 | 2016-01-06 | 小米科技有限责任公司 | Geographical location information recognition methods and device |
| CN106156316A (en) * | 2016-07-04 | 2016-11-23 | 长江大学 | Special name under a kind of big data environment and native place correlating method and system |
| CN106503150A (en) * | 2016-10-21 | 2017-03-15 | 天津海量信息技术股份有限公司 | Chinese Place Names administrative division belongs to recognition methods |
| CN109145095B (en) * | 2017-06-16 | 2024-03-29 | 贵州小爱机器人科技有限公司 | Place name information matching method, information matching device and computer equipment |
| CN107608959A (en) * | 2017-09-08 | 2018-01-19 | 电子科技大学 | A kind of English social media short text place name identification method |
| CN108388559B (en) * | 2018-02-26 | 2021-11-19 | 中译语通科技股份有限公司 | Named entity identification method and system under geographic space application and computer program |
| CN109299456B (en) * | 2018-08-28 | 2022-07-19 | 昆明理工大学 | Geographical name recognition method |
| CN109344233B (en) * | 2018-08-28 | 2022-07-19 | 昆明理工大学 | Chinese name recognition method |
| CN109815296B (en) * | 2018-12-29 | 2020-12-22 | 北京中科闻歌科技股份有限公司 | Figure knowledge base construction method and device for notarization document and storage medium |
| CN110110577B (en) * | 2019-01-22 | 2020-11-10 | 口碑(上海)信息技术有限公司 | Method and device for identifying dish name, storage medium and electronic device |
| CN111144121B (en) * | 2019-12-27 | 2021-12-03 | 北大方正集团有限公司 | Geographical name recognition method and device, electronic equipment and readable storage medium |
| CN117609403A (en) * | 2023-10-30 | 2024-02-27 | 合肥工业大学 | Place name identification method and system applied to service line intelligent dispatch |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101295292A (en) * | 2007-04-23 | 2008-10-29 | 北大方正集团有限公司 | Method and device for modeling and naming entity recognition based on maximum entropy model |
| CN103186524A (en) * | 2011-12-30 | 2013-07-03 | 高德软件有限公司 | Address name identification method and device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7475010B2 (en) * | 2003-09-03 | 2009-01-06 | Lingospot, Inc. | Adaptive and scalable method for resolving natural language ambiguities |
-
2014
- 2014-08-05 CN CN201410381574.8A patent/CN104199840B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101295292A (en) * | 2007-04-23 | 2008-10-29 | 北大方正集团有限公司 | Method and device for modeling and naming entity recognition based on maximum entropy model |
| CN103186524A (en) * | 2011-12-30 | 2013-07-03 | 高德软件有限公司 | Address name identification method and device |
Non-Patent Citations (1)
| Title |
|---|
| 利用地名用字分析的中文地名识别处理;李诺 等;《计算机工程与应用》;20091031;第45卷(第28期);第230-232页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104199840A (en) | 2014-12-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104199840B (en) | Intelligent place name identification technology based on statistical model | |
| CN110245981B (en) | Crowd type identification method based on mobile phone signaling data | |
| CN105022835B (en) | A kind of intelligent perception big data public safety recognition methods and system | |
| CN103970733B (en) | A kind of Chinese new word identification method based on graph structure | |
| CN106776538A (en) | The information extracting method of enterprise's noncanonical format document | |
| JP6928206B2 (en) | Data identification method based on associative clustering deep learning neural network | |
| CN103853738B (en) | A kind of recognition methods of info web correlation region | |
| CN107633250A (en) | A kind of Text region error correction method, error correction system and computer installation | |
| CN107808375B (en) | Merge the rice disease image detecting method of a variety of context deep learning models | |
| CN106845373A (en) | Towards pedestrian's attribute forecast method of monitor video | |
| CN105630884B (en) | A kind of geographical location discovery method of microblog hot event | |
| CN104809142A (en) | Trademark inquiring system and method | |
| CN104268160A (en) | Evaluation object extraction method based on domain dictionary and semantic roles | |
| CN104572958A (en) | Event extraction based sensitive information monitoring method | |
| CN104598535A (en) | Event extraction method based on maximum entropy | |
| CN102855317B (en) | A kind of multi-mode indexing means and system based on demonstration video | |
| CN106250925B (en) | A kind of zero Sample video classification method based on improved canonical correlation analysis | |
| CN103955703A (en) | Medical image disease classification method based on naive Bayes | |
| CN104252507B (en) | A kind of business data matching process and device | |
| CN104112020A (en) | Frame type retrieval method for navigation equipment | |
| CN111597331A (en) | Judgment document classification method based on Bayesian network | |
| CN107818321A (en) | A kind of watermark date recognition method for vehicle annual test | |
| CN108510307A (en) | A kind of course recommendation method and system | |
| CN110992988B (en) | Speech emotion recognition method and device based on domain confrontation | |
| CN107943514A (en) | The method for digging and system of core code element in a kind of software document |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address |
Address after: Zhejiang Zhongcai Building No. 68 Binjiang District road Hangzhou City, Zhejiang Province, the 310051 and 15 layer Patentee after: Hangzhou Annan information technology Limited by Share Ltd Address before: Hangzhou City, Zhejiang province 310051 Binjiang District and Zhejiang road in the 15 storey building Patentee before: Dbappsecurity Co.,ltd. |
|
| CP03 | Change of name, title or address |