CN201654779U - Scientific document automatic classification system - Google Patents
Scientific document automatic classification system Download PDFInfo
- Publication number
- CN201654779U CN201654779U CN2009201516820U CN200920151682U CN201654779U CN 201654779 U CN201654779 U CN 201654779U CN 2009201516820 U CN2009201516820 U CN 2009201516820U CN 200920151682 U CN200920151682 U CN 200920151682U CN 201654779 U CN201654779 U CN 201654779U
- Authority
- CN
- China
- Prior art keywords
- text
- classification number
- unit
- data server
- feature
- 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.)
- Expired - Lifetime
Links
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The utility model provides a scientific document automatic classification system direct towards the Chinese Library Classification, comprising a basis data server, a feature selector, a trainer and a classifier, wherein the basis data server is respectively connected with the feature selector, the trainer and the classifier for storing the scientific document text; the feature selector is connected with the trainer for reading the training text from the basis data server and selecting the feature words required by the classification to obtain the feature work dictionary; the trainer is connected with the classifier for reading the training text from the basis data server and calculating the probability relationship between the feature word and the classification number obtained by the feature selector thereby obtaining a word-classification number mapping dictionary; the classifier reads the text to be classified from the basis data server and uses the feature word dictionary and the word-classification number mapping dictionary to calculate the Chinese library classification number corresponding with the text to be tested. The system accurately, preciously and intelligently classifies the scientific document to greatly increase the efficiency.
Description
Technical field
The utility model relates to a kind of computing machine and books information field, more particularly, relates to a kind of automatically classifying academic documents system towards middle figure method.
Background technology
The text classification technology is the important foundation of information retrieval and text mining, and its main task is under classification tag set given in advance, judges its classification according to content of text.Text classification all has a wide range of applications in fields such as natural language processing and understanding, information organization and management, content information filtrations.
" Chinese Library classification " is called for short " middle figure method ", english name is Chinese LibraryClassification, english abbreviation is CLC, be widely used in all types of library, the whole nation, domestic main large-scale bibliography, retrieval publication, machine-readable data storehouse, and " CNS book number " etc. all records " middle figure method " classification number.
At present, each library and digital library all carry out by " middle figure method " for the classification of Chinese academic journal.The manual examination and verification of obtaining main dependence editor of classification number not only expended lot of manpower and material resources, and efficient are lower.A large amount of personnel are being engaged in the work of repeatability throughout the year, cause the more serious wasting of resources.And the training of newly advancing personnel also takes time and effort.
The utility model content
In order to address the above problem, according to one side of the present utility model, a kind of automatically classifying academic documents system towards middle figure method is provided, comprise basic data server, feature selecting device, training aids and sorter, wherein, the basic data server respectively with connection features selector switch, training aids and sorter, be used for the form of database storage academic documents text, comprising training text with treat classifying text; The feature selecting device further connects described training aids, is used for reading described training text from described basic data server, and the required feature speech of selection sort, obtain feature speech dictionary; Training aids further connects described sorter, is used for reading described training text from described basic data server, and calculates the described feature speech and the probabilistic relation of classification number that described feature selecting device obtains, and shines upon dictionary thereby obtain word-classification number; And, sorter further connects described basic data server, be used for reading the described classifying text for the treatment of, utilize described feature speech dictionary and described word-classification number mapping dictionary to calculate the middle figure classification number of described text correspondence to be tested from described basic data server.
Wherein, preferably, described training text in the described basic data server and the described structure storage for the treatment of classifying text with unified table, comprise text piece of writing name, Chinese summary, in full, periodical name, quoted passage and classification number, wherein, the classification number of described training text is known, and the described classification number of classifying text for the treatment of is initially sky.
Preferably, described feature selecting device further comprises:
Reading unit connects computing unit, is used for reading described training text from described basic data server;
Computing unit further connects selected cell, is used for calculating the weight of all words under described each classification number of described training text;
Selected cell further connects described training aids, is used for described weight is sorted and screens, and obtains feature speech dictionary.
Wherein, preferably, described feature selecting device further comprises:
Statistic unit connects described reading unit and described computing unit respectively, is used for adding up the corresponding relation and the quantitative relation of described training text word and classification number, and statistical value is sent to described computing unit;
Judging unit, connect described computing unit and described selected cell respectively, whether the word that is used for judging described training text has all calculated and has finished, if "Yes", then the described weight that described computing unit is obtained sends to selected cell, if "No", then the word that will calculate sends to described computing unit and calculates.
In the described automatically classifying academic documents system, preferably, described training aids further comprises:
Reading unit, the connection and locating unit is used for reading described training text from described basic data server;
Search the unit, further the connection statistics unit is used for utilizing described feature speech dictionary to search the feature speech of described training text;
Statistic unit, further connect computing unit, be used for adding up the corresponding classification number of described feature speech and add up the number of documents that described feature speech appears in described training text, be the document frequency, and at a piece of writing name, the Chinese key word of described training text, in full, the Chinese abstract fields appearance quantity of adding up described feature speech correspondence classification number;
Computing unit further connects generation unit, is used for being weighted according to the appearance quantity of described feature speech in the different field position, calculates its weight under described classification number, and according to weight described classification number is sorted from high to low.
Generation unit further connects described sorter, is used for depositing described morphology, described classification number, described document frequency, described weight in described word-classification number mapping dictionary.
Preferably, described sorter further comprises:
Reading unit connects the participle unit, is used for reading the described classifying text for the treatment of from described basic data server;
The participle unit further connects computing unit, is used for according to described feature speech dictionary the described classifying text for the treatment of being carried out participle, obtains the described feature speech for the treatment of in the classifying text;
Computing unit, further link sort unit, be used to calculate the weight of described feature speech and shine upon dictionary and calculate described feature speech corresponding weights under all classification numbers, thereby calculate described total weight for the treatment of each classification number of in the classifying text all feature speech correspondences according to described word-classification number;
Taxon further connects described basic data server unit, and the total weight of described classification number that is used for described computing unit is obtained sorts, and former classification number of ordering as the described classification number for the treatment of classifying text, and is exported described classification number.
Wherein, preferably, described sorter further comprises:
Statistic unit connects described participle unit and described computing unit respectively, is used for adding up described feature speech at the described occurrence frequency for the treatment of classifying text, and the text frequency of adding up described feature speech, and sends to described computing unit.
The utility model effect:
Adopt the automatically classifying academic documents system towards middle figure method described in the utility model, have the following advantages:
1) taxonomic hierarchies is wide, level is thin: 37 big classes that this sorter can centering figure classification, subclass is trained automatically and is marked surplus in the of 50,000, and obtained higher accuracy rate, wide, the taxonomical hierarchy of coverage carefully be initiative, filled up that sorter can only be to the blank of minority category classification in the past.
2) intelligent classification of technical literature: most in the past sorters can only be short to length, the simple text of content is classified, for example webpage etc.But this sorter can carry out accurate classification to the technical literature of forms such as academic journal, rich Master's thesis, newspaper, wherein the data volume of one piece of periodical can reach tens k at most, have about the 5000-10000 word, rich Master's thesis can be crossed M, and number of words is more than 30,000 words.Moreover, the vocabulary of technical literature and classification require relatively stricter, therefore its classification are needed strict semanteme support, and embody intelligent.
3) improve the data working (machining) efficiency greatly: this sorter with automatic classification application in the workflow waterline of document processing, auxiliary and replaced manual sort in the past, promoted work efficiency greatly, the production cost of reduction.
Description of drawings
Describe embodiment below with reference to accompanying drawings in detail.
Fig. 1 is the block diagram of expression according to the general structure of the automatically classifying academic documents system towards middle figure method of the present utility model.
Fig. 2 is the block diagram of expression according to the concrete structure of an embodiment of the automatically classifying academic documents system towards middle figure method of the present utility model.
Fig. 3 is the synoptic diagram of expression according to data storage form in the basic data server of an embodiment of the automatically classifying academic documents system towards middle figure method of the present utility model.
Fig. 4 is the workflow diagram of expression according to an embodiment of the automatically classifying academic documents system towards middle figure method of the present utility model.
Embodiment
Structure and principle of work according to the automatically classifying academic documents system of an embodiment of the utility model are described below with reference to accompanying drawings.
Fig. 1 is the block diagram of expression according to the general structure of the automatically classifying academic documents system towards middle figure method of the present utility model.With reference to Fig. 1, the automatically classifying academic documents system of present embodiment comprises: basic data server, feature selecting device, training aids and sorter.Wherein, the basic data server, connection features selector switch, training aids and sorter are with the form of database storage academic documents text, comprising training text with treat classifying text.The feature selecting device connects described training aids, is used for reading described training text from described basic data server, and the required feature speech of selection sort, obtain feature speech dictionary.Training aids connects described sorter, is used for reading described training text from described basic data server, and calculates the described feature speech that described feature selecting device obtains and the probabilistic relation of classification number, thereby obtain word-classification number mapping dictionary.Sorter connects described basic data server, reads the described classifying text for the treatment of from described basic data server, utilizes described feature speech dictionary and described word-classification number mapping dictionary to calculate the middle figure classification number of described text correspondence to be tested.
Fig. 2 is the block diagram of expression according to the concrete structure of the automatically classifying academic documents system 200 towards middle figure method of the present utility model.With reference to Fig. 2, comprise basic data server 210, feature selecting device 220, training aids 230 and sorter 240 towards the automatically classifying academic documents system 200 of middle figure method.
Basic data server 210 connection features selector switchs 220, training aids 230 and sorter 240 are with the form of database storage academic documents text, as the information carrier of system's other parts, comprising training text with treat classifying text.Training text and treat that classifying text stores with the structure (referring to Fig. 3) of unified table, comprise text piece of writing name, Chinese summary, Chinese key word, in full, periodical, quoted passage and classification number, wherein, the classification number of training text is known, treats that the classification number field of classifying text is initially sky.
Feature selecting device 220 connects training aids 230, and the required feature speech of selection sort obtains feature speech dictionary automatically.Feature selecting device 220 comprises: reading unit 221, statistic unit 222, computing unit 223, judging unit 224, selected cell 225.Wherein, reading unit 221, connection statistics unit 222 reads training text from basic data server 210.Statistic unit 222 connects computing unit 223, the word in the training text that statistics reads from reading unit 210 and the corresponding relation and the quantitative relation of classification number.For example, comprise word " computing machine " in the training text, add up the relation of itself and classification number " TP3-4 ", at first add up the number of documents that comprises word " computing machine " in the training text and belong to classification number " TP3-4 "; Then, add up the number of documents that does not comprise word " computing machine " in the training text but belong to classification number " TP3-4 "; Then add up the number of documents that comprises word " computing machine " in the training text but do not belong to classification number " TP3-4 "; Add up the training text sum at last.All statistical values are sent to computing unit 223.Computing unit 223, connection judgment unit 224, the weight of the word in the calculation training text under each classification number.Judging unit 224, connect selected cell 225, judging whether word in the described training text has all calculated finishes, if "Yes", then the weight that computing unit 223 is obtained sends to selected cell 225, if "No", then the word that will calculate sends to computing unit 223 and calculates.Selected cell 225 connects training aids 230, sorts and screens obtain weight from computing unit 223, selects the suitable feature speech automatically, obtains feature speech dictionary.
Training aids 230 link sort devices 240 read training text from basic data server 210, and calculate the feature speech and the probabilistic relation of classification number that obtains from feature selecting device 220, shine upon dictionary thereby obtain word-classification number.Training aids 230 comprises: reading unit 231, search unit 232, statistic unit 233, computing unit 234, generation unit 235.Wherein, reading unit 231, connection and locating unit 232 reads training text from basic data server 210, with a piece of writing name, the Chinese key word of training text, in full, Chinese abstract fields is as input.Search unit 232, connection statistics unit 233 utilizes feature speech dictionary to search the feature speech of input field in the training text.Statistic unit 233, connect computing unit 234, the corresponding classification number of the feature speech that statistics finds, the number of documents that occurs this feature speech in the statistics training text, be the document frequency, and at a piece of writing name, the Chinese key word of training text, in full, the Chinese abstract fields appearance quantity of adding up this feature speech correspondence classification number.Computing unit 233 connects generation unit 234, is weighted according to feature speech appearance quantity of different field position in training text, calculates its weight under corresponding classification number, and according to weight classification number is sorted from high to low.Generation unit 234, link sort device 240 deposits morphology, classification number, document frequency and weight in word-classification number mapping dictionary.Be the example of word-classification number mapping dictionary below:
| Morphology | Classification number | The document frequency | Weight |
| Financial institution | F832.2；F832.3； | 57079 | 0.3912；0.3019； |
| Computing machine | TP3-4；TP399； | 408907 | 0.5292；0.1639； |
| The sub-base | E712；E273；E19； | 72 | 0.2773；0.2310；0.1848； |
| Cardiac stimulant expands the blood vessel medicine | R541.6；R473.6； | 39 | 0.4951；0.1980； |
| Modern education | G434；G40-057； | 32317 | 0.4433；0.2498； |
Sorter 240 connects basic data server 210, reads from basic data server 210 and treats classifying text, and feature speech dictionary and word-classification number mapping dictionary calculates the middle figure classification number of described text correspondence to be tested.Sorter comprises: reading unit 241, participle unit 242, statistic unit 243, computing unit 244, taxon 245.Wherein, reading unit 241 connects participle unit 242, reads from basic data server 210 and treats classifying text.Participle unit 242, connection statistics unit 243, the feature speech dictionary that utilizes feature selecting device 220 to generate is treated classifying text and is carried out participle, obtains to treat that feature speech in the classifying text at the occurrence frequency of diverse location, removes wherein dittograph item.Statistic unit 243 connects computing unit 244, the occurrence frequency of statistical nature speech in treating classifying text and the text frequency of feature speech, and statistical value sent to computing unit 244.Computing unit 244, link sort unit 245, obtain feature speech corresponding weights under all classification numbers according to the weight of the statistical value calculated characteristics speech that receives and the word that generates according to training aids 230-classification number mapping dictionary, thereby calculate total weight of corresponding each classification number for the treatment of in the classifying text of feature speech; Taxon 245 connects basic data server 210, and the total weight of classification number that computing unit 244 is obtained sorts, and the classification number of former of orderings as the classification number for the treatment of classifying text, and is exported this classification number.
In sum, automatically classifying academic documents described in the utility model system can substitute existing manual sort's work, optimizes the data work flow, and promotes work efficiency greatly.
" embodiment " spoken of in this manual, " another embodiment ", " embodiment ", etc., refer to concrete feature, structure or the characteristics described in conjunction with this embodiment and be included at least one embodiment that the application's generality describes.Occurring this statement in instructions Anywhere is not to establish a capital to refer to this same embodiment.Further, when describing a concrete feature, structure or characteristics in conjunction with arbitrary embodiment, what advocate is to realize this feature, structure or characteristics in conjunction with other embodiments, drops in those skilled in the art's the scope.
Although the utility model is described with reference to a plurality of explanatory embodiments of the present utility model, but, should be appreciated that, those skilled in the art can design a lot of other modification and embodiments, and these are revised and embodiment will drop within the disclosed principle scope and spirit of the application.More particularly, in the scope of, accompanying drawing open and claim, can carry out multiple modification and improvement to the building block and/or the layout of subject combination layout in the application.Except modification that building block and/or layout are carried out with improving, to those skilled in the art, other purposes also will be tangible.
Claims (7)
1. the automatically classifying academic documents system towards middle figure method is characterized in that, this automatically classifying academic documents system comprises basic data server, feature selecting device, training aids and sorter, wherein,
The basic data server is connected with feature selecting device, training aids and sorter respectively, is used for the form storage academic documents text with database, and described academic documents text comprises training text and treats classifying text;
The feature selecting device further is connected with training aids, is used for reading described training text from the basic data server, and the required feature speech of selection sort, obtain feature speech dictionary;
Training aids further is connected with sorter, is used for reading described training text from the basic data server, and calculates the described feature speech that described feature selecting device obtains and the probabilistic relation of classification number, thereby obtain word-classification number mapping dictionary; And
Sorter is connected with training aids with the basic data server respectively, is used for reading from the basic data server treating classifying text, utilizes described feature speech dictionary and described word-classification number mapping dictionary to calculate the middle figure classification number of described text correspondence to be tested.
2. automatically classifying academic documents according to claim 1 system is characterized in that described feature selecting device further comprises:
Reading unit is connected with computing unit, is used for reading described training text from described basic data server;
Computing unit further is connected with selected cell, is used for calculating the weight of all words under described each classification number of described training text;
Selected cell further is connected with described training aids, thereby being used for described weight sorted and screen obtains feature speech dictionary.
3. automatically classifying academic documents according to claim 2 system is characterized in that described feature selecting device further comprises:
Statistic unit is connected with described computing unit with described reading unit respectively, is used for adding up the corresponding relation and the quantitative relation of described training text word and classification number, and statistical value is sent to described computing unit;
Judging unit, be connected with described selected cell with described computing unit respectively, whether the word that is used for judging described training text has all calculated and has finished, if "Yes", then the described weight that described computing unit is obtained sends to selected cell, if "No", then the word that will calculate sends to described computing unit and calculates.
4. automatically classifying academic documents according to claim 1 system is characterized in that described training aids further comprises:
Reading unit and is searched the unit and is connected, and is used for reading described training text from described basic data server;
Search the unit, further be connected, be used for utilizing described feature speech dictionary to search the feature speech of described training text with statistic unit;
Statistic unit, further be connected with computing unit, be used for adding up the corresponding classification number of described feature speech and add up that the number of documents of described feature speech appears in described training text and in the piece of writing name of described training text, Chinese key word, in full, the Chinese abstract fields appearance quantity of adding up described feature speech correspondence classification number;
Computing unit further is connected with generation unit, is used for being weighted according to the appearance quantity of described feature speech in the different field position, calculates its weight under described classification number, and according to weight described classification number is sorted from high to low;
Generation unit further is connected with described sorter, is used for depositing number of documents, the described weight of described morphology, described classification number, the described feature speech of described training text appearance in described word-classification number mapping dictionary.
5. automatically classifying academic documents according to claim 1 system is characterized in that described sorter further comprises:
Reading unit is connected with the participle unit, is used for reading the described classifying text for the treatment of from described basic data server;
The participle unit further is connected with computing unit, is used for according to described feature speech dictionary the described classifying text for the treatment of being carried out participle, obtains the described feature speech for the treatment of in the classifying text;
Computing unit, further be connected with taxon, be used to calculate the weight of described feature speech and shine upon dictionary and calculate described feature speech corresponding weights under all classification numbers, thereby calculate described total weight for the treatment of each classification number of in the classifying text all feature speech correspondences according to described word-classification number;
Taxon further is connected with described basic data server, and the total weight of described classification number that is used for described computing unit is obtained sorts, and former classification number of ordering as the described classification number for the treatment of classifying text, and is exported described classification number.
6. automatically classifying academic documents according to claim 5 system is characterized in that described sorter further comprises:
Statistic unit is connected with described computing unit with described participle unit respectively, is used for adding up described feature speech at the described text frequency for the treatment of the occurrence frequency of classifying text and adding up described feature speech, and statistical value is sent to described computing unit.
7. automatically classifying academic documents according to claim 1 system, it is characterized in that, training text in the described basic data server and treat that classifying text is with the storage of the structure of unified table, comprise text piece of writing name, Chinese summary, in full, periodical name, quoted passage and classification number, wherein, the classification number of training text is known, treats that the classification number of classifying text is initially sky.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2009201516820U CN201654779U (en) | 2009-04-22 | 2009-04-22 | Scientific document automatic classification system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2009201516820U CN201654779U (en) | 2009-04-22 | 2009-04-22 | Scientific document automatic classification system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN201654779U true CN201654779U (en) | 2010-11-24 |
Family
ID=43120022
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2009201516820U Expired - Lifetime CN201654779U (en) | 2009-04-22 | 2009-04-22 | Scientific document automatic classification system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN201654779U (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102073704A (en) * | 2010-12-24 | 2011-05-25 | 华为终端有限公司 | Text classification processing method, system and equipment |
| CN102651092A (en) * | 2011-02-25 | 2012-08-29 | 艾迪讯科技股份有限公司 | System for managing books with color |
| CN103377216A (en) * | 2012-04-24 | 2013-10-30 | 苏州引角信息科技有限公司 | Product information base establishing method and system |
| CN104679875A (en) * | 2015-03-10 | 2015-06-03 | 杭州凡闻科技有限公司 | Method for classifying information data based on digital newspaper |
| CN106156114A (en) * | 2015-04-03 | 2016-11-23 | 北京中献电子技术开发中心 | Patent retrieval method and device |
| CN107862069A (en) * | 2017-11-21 | 2018-03-30 | 广州星耀悦教育科技有限公司 | A kind of construction method of taxonomy database and the method for book classification |
-
2009
- 2009-04-22 CN CN2009201516820U patent/CN201654779U/en not_active Expired - Lifetime
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102073704A (en) * | 2010-12-24 | 2011-05-25 | 华为终端有限公司 | Text classification processing method, system and equipment |
| CN102073704B (en) * | 2010-12-24 | 2013-09-25 | 华为终端有限公司 | Text classification processing method, system and equipment |
| CN102651092A (en) * | 2011-02-25 | 2012-08-29 | 艾迪讯科技股份有限公司 | System for managing books with color |
| CN103377216A (en) * | 2012-04-24 | 2013-10-30 | 苏州引角信息科技有限公司 | Product information base establishing method and system |
| CN104679875A (en) * | 2015-03-10 | 2015-06-03 | 杭州凡闻科技有限公司 | Method for classifying information data based on digital newspaper |
| CN104679875B (en) * | 2015-03-10 | 2017-12-15 | 杭州凡闻科技有限公司 | A kind of information data classification method based on digital newspaper |
| CN106156114A (en) * | 2015-04-03 | 2016-11-23 | 北京中献电子技术开发中心 | Patent retrieval method and device |
| CN107862069A (en) * | 2017-11-21 | 2018-03-30 | 广州星耀悦教育科技有限公司 | A kind of construction method of taxonomy database and the method for book classification |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104391942B (en) | Short essay eigen extended method based on semantic collection of illustrative plates | |
| CN201654779U (en) | Scientific document automatic classification system | |
| CN107194617B (en) | App software engineer soft skill classification system and method | |
| CN106528528A (en) | A text emotion analysis method and device | |
| CN107992633A (en) | Electronic document automatic classification method and system based on keyword feature | |
| CN106651057A (en) | Mobile terminal user age prediction method based on installation package sequence table | |
| CN109271477A (en) | A kind of method and system by internet building taxonomy library | |
| CN102194013A (en) | Domain-knowledge-based short text classification method and text classification system | |
| CN105760493A (en) | Automatic work order classification method for electricity marketing service hot spot 95598 | |
| CN109960799A (en) | A kind of Optimum Classification method towards short text | |
| CN103678576A (en) | Full-text retrieval system based on dynamic semantic analysis | |
| CN104050240A (en) | Method and device for determining categorical attribute of search query word | |
| CN101183430A (en) | Handwriting digital automatic identification method based on module neural network SN9701 rectangular array | |
| CN105893380A (en) | Improved text classification characteristic selection method | |
| CN111125116B (en) | Method and system for positioning code field in service table and corresponding code table | |
| CN107169061A (en) | A kind of text multi-tag sorting technique for merging double information sources | |
| CN109740642A (en) | Invoice category recognition methods, device, electronic equipment and readable storage medium storing program for executing | |
| CN112307153A (en) | Automatic construction method and device of industrial knowledge base and storage medium | |
| CN106777193A (en) | A kind of method for writing specific contribution automatically | |
| CN109784387A (en) | Multi-level progressive classification method and system based on neural network and Bayesian model | |
| CN103778206A (en) | Method for providing network service resources | |
| CN110276382A (en) | Listener clustering method, apparatus and medium based on spectral clustering | |
| CN110659367A (en) | Text classification number determination method and device and electronic equipment | |
| CN101178721A (en) | Method for classifying and managing useful poser information in forum | |
| CN108920508A (en) | Textual classification model training method and system based on LDA algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CX01 | Expiry of patent term |
Granted publication date: 20101124 |
|
| CX01 | Expiry of patent term |