CN106295252A - Search method for gene prod - Google Patents

Search method for gene prod Download PDF

Info

Publication number
CN106295252A
CN106295252A CN201610687440.8A CN201610687440A CN106295252A CN 106295252 A CN106295252 A CN 106295252A CN 201610687440 A CN201610687440 A CN 201610687440A CN 106295252 A CN106295252 A CN 106295252A
Authority
CN
China
Prior art keywords
gene
key word
search method
unique features
prod
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.)
Granted
Application number
CN201610687440.8A
Other languages
Chinese (zh)
Other versions
CN106295252B (en
Inventor
刘杨
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hangzhou Bree Lan Technology Co Ltd
Original Assignee
Hangzhou Bree Lan Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Hangzhou Bree Lan Technology Co Ltd filed Critical Hangzhou Bree Lan Technology Co Ltd
Priority to CN201610687440.8A priority Critical patent/CN106295252B/en
Publication of CN106295252A publication Critical patent/CN106295252A/en
Application granted granted Critical
Publication of CN106295252B publication Critical patent/CN106295252B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/22—Indexing; Data structures therefor; Storage structures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2455—Query execution
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/951—Indexing; Web crawling techniques
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
    • G16B50/00—ICT programming tools or database systems specially adapted for bioinformatics

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • Evolutionary Biology (AREA)
  • Biotechnology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioethics (AREA)
  • Software Systems (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

Present invention provide for the search method of gene prod, belong to information retrieval field, including building homologous genes data base, obtain key word to be retrieved, determine the unique features label corresponding with key word, according to unique features label, key word is expanded, obtain and expand key word, carry out network retrieval according to expanding key word.By obtaining unique features label according to key word to be retrieved, based on unique features label, key word is carried out expansion process, the expansion key word that final basis obtains carries out the whole network retrieval, contain and corresponding the re-defining of key word to be retrieved owing to expanding in key word more, thus ensure to search the resource the strongest with key word relatedness on the internet, reduce other unrelated resource interference to Search Results.

Description

Search method for gene prod
Technical field
The invention belongs to information retrieval field, particularly to the search method for gene prod.
Background technology
Along with the development of sequencing technologies, several species gene order-checking completes successively, and rapid due to Internet technology Development, carries out the search of the associated materials such as gene and gene document, gene prod based on the Internet and has become as becoming in the industry Gesture.
So far, the inner number gene of including of U.S. National Institutes gene database (NCBI) alreadys more than 1,003,000,000 Bar.But due to historical reasons and the homogenic existence of naming rule, every gene is except having gene numbering (gene ID) Outside, it is also possible to have gene full name (gene full name), gene symbol (gene symbol), another name (aliase, The title in the industry such as synonym), can not be included by unified title when including gene document, gene prod.Cause working as Before based on term single gene name keyword search inquiry specific gene relevant information and product time, search efficiency low and inquiry knot Easily there is the situation such as extraneous data or missing data in fruit.Bring huge difficulty so to the search in later stage.
Summary of the invention
In order to solve shortcoming and defect present in prior art, present invention provide for improving recall precision for The search method of gene prod.
In order to reach above-mentioned technical purpose, present invention provide for the search method of gene prod, described search method Including:
Homologous genes data base is built according to gene numbering, gene symbol, gene full name and another name；
Obtain key word to be retrieved, from homologous genes data base, determine the unique features label corresponding with key word；
According to unique features label, in conjunction with gene numbering, gene symbol, gene full name and another name, key word is opened up Exhibition, obtains and expands key word；
Network retrieval is carried out according to expanding key word, will retrieval result output.
Optionally, described search method, also include:
Build the searching database including gene document, gene prod, be provided with at described searching database described with each Gene document, the unique features label that each described gene prod is corresponding.
Optionally, described search method, also include:
Described searching database is chosen corresponding with described unique features label, include gene document and/or gene The retrieval result of product；
Described retrieval result is exported.
Optionally, described according to unique features label, in conjunction with gene numbering, gene symbol, gene full name and have another name called right Key word is expanded, and obtains and expands key word, including:
According to unique features label, determine the genes of interest numbering corresponding with unique features label, genes of interest symbol, mesh Gene full name and another name；
Based on key word, by described genes of interest numbering, described genes of interest symbol, described genes of interest full name with And another name by or logical structure expand, obtain expand key word.
Optionally, also include:
Described unique features label is character string, is provided with sequence byte and checking byte in described character string.
Optionally, it is provided with in described homologous genes data base and gene numbering, gene symbol, gene full name and another name Corresponding label.
Optionally, described expansion key word is at least including gene numbering, gene symbol, gene full name and another name Character string.
Optionally, also include:
From gene word bank, obtain species gene data, in conjunction with comparison database, species gene data are screened, To across the direct homologous genes of species；
Based on across the direct homologous genes of species, it is all standard mutually carries out in gene word bank with gene full name or gene numbering Expand coupling, obtain direct homologous genes keyword data collection, set up according to the direct homologous genes keyword data collection obtained Non-redundant database；
The expansion key word with Keywords matching is chosen in non-redundant database.
Optionally, species gene data are screened by described combination comparison database, obtain across species direct homology base Cause, including:
The sample gene data corresponding with species gene data is extracted, based on sample gene data pair from comparison database Species gene data carry out duplicate removal screening, after being screened across the direct homologous genes of species.
Optionally, in described non-redundant database, the direct homologous genes keyword data of storage has uniqueness.
The technical scheme that the present invention provides has the benefit that
By obtaining unique features label according to key word to be retrieved, based on unique features label, key word is opened up Exhibition processes, and the expansion key word that final basis obtains carries out the whole network retrieval, contains with to be retrieved owing to expanding in key word Corresponding the re-defining of key word more, thus ensure to search the resource the strongest with key word relatedness on the internet, fall Other unrelated resource interference to Search Results low.
Accompanying drawing explanation
In order to be illustrated more clearly that technical scheme, the required accompanying drawing used in embodiment being described below It is briefly described, it should be apparent that, the accompanying drawing in describing below is only some embodiments of the present invention, general for this area From the point of view of logical technical staff, on the premise of not paying creative work, it is also possible to obtain other accompanying drawing according to these accompanying drawings.
Fig. 1 is the schematic flow sheet of the search method for gene prod that the present invention provides；
Fig. 2 is the schematic flow sheet of the acquisition mode expanding key word that the present invention provides.
Detailed description of the invention
Structure and advantage for making the present invention are clearer, make the structure of the present invention further below in conjunction with accompanying drawing Describe.
Embodiment one
Present invention provide for the search method of gene prod, as it is shown in figure 1, described search method includes:
11, homologous genes data base is built according to gene numbering, gene symbol, gene full name and another name.
12, obtain key word to be retrieved, from homologous genes data base, determine the unique features mark corresponding with key word Sign.
13, according to unique features label, in conjunction with gene numbering, gene symbol, gene full name and another name, key word is entered Row is expanded, and obtains and expands key word.
14, network retrieval is carried out according to expansion key word, will retrieval result output.
In force, in order to obtain abundant as far as possible and with gene-correlation retrieval result according to key word, this Bright provide the search method for gene prod, in this search method, first build homologous genes data base, at homology base Factor data bank includes that substantial amounts of gene is numbered, gene symbol, gene full name and another name.So that in subsequent step, energy Enough particular contents according to key word, determine in homologous genes data base associate with key word gene numbering, gene symbol, Gene full name and another name.Then according to getting key word to be retrieved, the homologous genes data base built from back Middle determine the unique features label corresponding with key word.Again according to contents such as the gene numberings that unique features label is corresponding to pass Keyword carries out expansion process, the expansion key word after being processed.Finally carry out the whole network retrieval according to expansion key word, examined Hitch fruit.
In above-mentioned steps, why arrange obtain unique features label step, be in order to will include gene number, Key word is expanded by the resource in the homologous genes data base of gene symbol, gene full name and another name, enters key word Row limits accurately, thus ensures to search the resource the strongest with key word relatedness on the internet, reduces other nothings Close the resource interference to Search Results.
It should be noted that when determining unique features label in step 12, close present in homologous genes data base Keyword group may be with key word one_to_one corresponding, as such, it is possible to the crucial phrase of correspondence directly determines unique features label；If In homologous genes data base, for key word to be retrieved, there is more than one crucial phrase the most corresponding, so need Choose from multiple crucial phrases closer to crucial phrase, and then determine the unique features corresponding with the crucial phrase selected Label, consequently facilitating complete subsequent processing steps according to the unique features label determined.
The step obtaining expansion key word in step 13 specifically includes:
According to unique features label, determine the genes of interest numbering corresponding with unique features label, genes of interest symbol, mesh Gene full name and another name；
Based on key word, by described genes of interest numbering, described genes of interest symbol, described genes of interest full name with And another name by or logical structure expand, obtain expand key word.
Unique features label therein is character string, is provided with sequence byte and checking byte in described character string.So that In after determining unique features label, by checking byte, the sequence byte calculated is verified.Additionally, in order in homology Gene database is provided with the label corresponding with gene numbering, gene symbol, gene full name and another name.The expansion got is closed Keyword be at least include gene numbering, gene symbol, gene full name and another name including character string.
Concrete, described search method, also include: build the searching database including gene document, gene prod, in institute State searching database to be provided with and each described gene document, unique features label that each described gene prod is corresponding.
In force, except propose in said method expands key word, carry out the whole network based on expanding key word Retrieval is unexpected, also includes building searching database, and then retrieves in searching database according to unique features label, obtains Result after retrieval.
So-called searching database in this step, is the data base comprising gene document, gene prod, in advance may be used Can as the retrieval gene document of result and gene prod structure data base, and be in searching database with each gene pairs The content answered gives unique features label.So after determining unique features label according to key word, can be at described retrieval number According to storehouse is chosen corresponding with described unique features label, to include gene document and/or gene prod retrieval result, and then will Described retrieval result exports, and selects the retrieval content corresponding with key word, phase according to unique features label in searching database For carrying out the whole network retrieval by the Internet, it is possible to realize retrieving the most rapidly and accurately.
In the first retrieval mode, it is proposed that carry out the mode of the whole network retrieval according to expansion key word, it is set forth below another A kind of acquisition mode about expansion key word, detailed process is as shown in Figure 2.
21, from gene word bank, obtain species gene data, in conjunction with comparison database, species gene data screened, Obtain across the direct homologous genes of species.
22, based on across the direct homologous genes of species, number with gene full name or gene and be all standard mutually in gene word bank Carry out expanding coupling, obtain direct homologous genes keyword data collection, according to the direct homologous genes keyword data collection obtained Set up non-redundant database.
23, in non-redundant database, the expansion key word with Keywords matching is chosen.
In force, according to American National Biotechnology Information center (National Center of Biotechnology Information, NCBI) gene word bank arrange several species gene data, in conjunction with HomoloGene Data base, screening, across the direct homologous genes of species, is all standard at gene with gene symbol Symbol or full name full name phase In word bank, coupling expands direct homologous genes data, the direct homologous genes keyword data collection of final generation, sets up gene symbol Symbol title non-redundant database, chooses the expansion key word with Keywords matching.
Species gene data are screened by the combination comparison database in step 21, obtain across the direct homologous genes of species Concrete mode be: from comparison database, extract the sample gene data corresponding with species gene data, based on sample gene Data carry out duplicate removal screening to species gene data, after being screened across the direct homologous genes of species.
Further, in non-redundant database, the direct homologous genes keyword data of storage has uniqueness.
Present invention provide for the search method of gene prod, including building homologous genes data base, obtain to be retrieved Key word, determine the unique features label corresponding with key word, according to unique features label, key word expanded, obtain Take expansion key word, carry out network retrieval according to expanding key word.By obtaining unique features mark according to key word to be retrieved Signing, based on unique features label, key word is carried out expansion process, the expansion key word that final basis obtains carries out the whole network retrieval, Contain and to be retrieved key word corresponding re-define owing to expanding in key word more, thus ensure can search on the internet Rope, to the resource the strongest with key word relatedness, reduces other unrelated resource interference to Search Results.
Each sequence number in above-described embodiment just to describe, do not represent each parts assemble or use during elder generation Rear order.
The foregoing is only embodiments of the invention, not in order to limit the present invention, all in the spirit and principles in the present invention Within, any modification, equivalent substitution and improvement etc. made, should be included within the scope of the present invention.

Claims (10)

1. for the search method of gene prod, it is characterised in that described search method includes:
Homologous genes data base is built according to gene numbering, gene symbol, gene full name and another name；
Obtain key word to be retrieved, from homologous genes data base, determine the unique features label corresponding with key word；
According to unique features label, in conjunction with gene numbering, gene symbol, gene full name and another name, key word is expanded, Obtain and expand key word；
Network retrieval is carried out according to expanding key word, will retrieval result output.
Search method for gene prod the most according to claim 1, it is characterised in that described search method, also wraps Include:
Build the searching database including gene document, gene prod, be provided with and each described gene at described searching database Document, the unique features label that each described gene prod is corresponding.
Search method for gene prod the most according to claim 2, it is characterised in that described search method, also wraps Include:
Described searching database is chosen corresponding with described unique features label, include gene document and/or gene prod Retrieval result；
Described retrieval result is exported.
Search method for gene prod the most according to claim 1, it is characterised in that described according to unique features mark Sign, in conjunction with gene numbering, gene symbol, gene full name and another name, key word is expanded, obtain and expand key word, bag Include:
According to unique features label, determine the genes of interest numbering corresponding with unique features label, genes of interest symbol, purpose base Because of full name and another name；
Based on key word, by described genes of interest numbering, described genes of interest symbol, described genes of interest full name and not Claim by or logical structure expand, obtain expand key word.
Search method for gene prod the most according to claim 1, it is characterised in that also include:
Described unique features label is character string, is provided with sequence byte and checking byte in described character string.
Search method for gene prod the most according to claim 1, it is characterised in that in described homologous genes data Storehouse is provided with the label corresponding with gene numbering, gene symbol, gene full name and another name.
The most according to claim 1 or 5 for the search method of gene prod, it is characterised in that described expansion key word It it is the character string at least including gene numbering, gene symbol, gene full name and another name.
Search method for gene prod the most according to claim 1, it is characterised in that also include:
From gene word bank obtain species gene data, in conjunction with comparison database, species gene data are screened, obtain across The direct homologous genes of species；
Based on across the direct homologous genes of species, it is all standard mutually expands in gene word bank with gene full name or gene numbering Coupling, obtains direct homologous genes keyword data collection, and the direct homologous genes keyword data collection according to obtaining is set up non-superfluous Remaining data base；
The expansion key word with Keywords matching is chosen in non-redundant database.
Search method for gene prod the most according to claim 1, it is characterised in that described combination comparison database Species gene data are screened, obtains across the direct homologous genes of species, including:
The sample gene data corresponding with species gene data is extracted, based on sample gene data to species from comparison database Gene data carries out duplicate removal screening, after being screened across the direct homologous genes of species.
Search method for gene prod the most according to claim 8, it is characterised in that in described Non-redundant data In storehouse, the direct homologous genes keyword data of storage has uniqueness.
CN201610687440.8A 2016-08-18 2016-08-18 Search method for gene prod Active CN106295252B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610687440.8A CN106295252B (en) 2016-08-18 2016-08-18 Search method for gene prod

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610687440.8A CN106295252B (en) 2016-08-18 2016-08-18 Search method for gene prod

Publications (2)

Publication Number Publication Date
CN106295252A true CN106295252A (en) 2017-01-04
CN106295252B CN106295252B (en) 2019-05-07

Family

ID=57661318

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610687440.8A Active CN106295252B (en) 2016-08-18 2016-08-18 Search method for gene prod

Country Status (1)

Country Link
CN (1) CN106295252B (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108428137A (en) * 2017-02-14 2018-08-21 阿里巴巴集团控股有限公司 Generate the method and device of abbreviation, verification electronic banking rightness of business
CN110349632A (en) * 2019-06-28 2019-10-18 广州序科码生物技术有限责任公司 A method of from PubMed document screening-gene keyword
CN111540472A (en) * 2020-05-18 2020-08-14 霓蝶(上海)医疗科技有限公司 Intelligent risk assessment system and method for health activities
CN111739585A (en) * 2020-06-24 2020-10-02 胡嘉欣 Information extraction method based on NCBI database and related equipment thereof

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1744080A (en) * 2005-09-27 2006-03-08 南方医科大学 Specific function-related gene information searching system and method for building database of searching workds thereof
CN101201847A (en) * 2007-12-26 2008-06-18 北京东方灵盾科技有限公司 System and method for searching conventional medicament patent information
CN101266601A (en) * 2007-03-14 2008-09-17 沈诗昊 Gene chip data search engine
CN101539916A (en) * 2008-03-17 2009-09-23 亿维讯软件（北京）有限公司 Initial patent retrieving device, secondary patent retrieving device and patent retrieving system
CN101738196A (en) * 2009-12-10 2010-06-16 东软集团股份有限公司 Method and device of navigation equipment for information retrieval
CN102043812A (en) * 2009-10-13 2011-05-04 北京大学 Method and system for retrieving medical information
CN104090890A (en) * 2013-12-12 2014-10-08 深圳市腾讯计算机系统有限公司 Method, device and server for obtaining similarity of key words
CN105589936A (en) * 2015-12-11 2016-05-18 航天恒星科技有限公司 Data query method and system
CN105630813A (en) * 2014-10-30 2016-06-01 苏宁云商集团股份有限公司 Keyword recommendation method and system based on user-defined template
CN105740243A (en) * 2014-12-08 2016-07-06 深圳华大基因研究院 Method and device for constructing biological information database

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1744080A (en) * 2005-09-27 2006-03-08 南方医科大学 Specific function-related gene information searching system and method for building database of searching workds thereof
CN101266601A (en) * 2007-03-14 2008-09-17 沈诗昊 Gene chip data search engine
CN101201847A (en) * 2007-12-26 2008-06-18 北京东方灵盾科技有限公司 System and method for searching conventional medicament patent information
CN101539916A (en) * 2008-03-17 2009-09-23 亿维讯软件（北京）有限公司 Initial patent retrieving device, secondary patent retrieving device and patent retrieving system
CN102043812A (en) * 2009-10-13 2011-05-04 北京大学 Method and system for retrieving medical information
CN101738196A (en) * 2009-12-10 2010-06-16 东软集团股份有限公司 Method and device of navigation equipment for information retrieval
CN104090890A (en) * 2013-12-12 2014-10-08 深圳市腾讯计算机系统有限公司 Method, device and server for obtaining similarity of key words
CN105630813A (en) * 2014-10-30 2016-06-01 苏宁云商集团股份有限公司 Keyword recommendation method and system based on user-defined template
CN105740243A (en) * 2014-12-08 2016-07-06 深圳华大基因研究院 Method and device for constructing biological information database
CN105589936A (en) * 2015-12-11 2016-05-18 航天恒星科技有限公司 Data query method and system

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108428137A (en) * 2017-02-14 2018-08-21 阿里巴巴集团控股有限公司 Generate the method and device of abbreviation, verification electronic banking rightness of business
CN110349632A (en) * 2019-06-28 2019-10-18 广州序科码生物技术有限责任公司 A method of from PubMed document screening-gene keyword
CN111540472A (en) * 2020-05-18 2020-08-14 霓蝶(上海)医疗科技有限公司 Intelligent risk assessment system and method for health activities
CN111739585A (en) * 2020-06-24 2020-10-02 胡嘉欣 Information extraction method based on NCBI database and related equipment thereof
CN111739585B (en) * 2020-06-24 2022-10-18 胡嘉欣 Information extraction method based on NCBI database and related equipment thereof

Also Published As

Publication number Publication date
CN106295252B (en) 2019-05-07

Similar Documents

Publication Publication Date Title
CN107766371A (en) A kind of text message sorting technique and its device
CN106126543B (en) The model conversion and data migration method of a kind of relevant database to MongoDB
CN106295252A (en) Search method for gene prod
Xie et al. Fast and accurate near-duplicate image search with affinity propagation on the ImageWeb
CN101093478A (en) Method and system for identifying Chinese full name based on Chinese shortened form of entity
CN102955833A (en) Correspondence address identifying and standardizing method
CN107291895B (en) Quick hierarchical document query method
CN100354863C (en) Method and system for large scale keyboard matching
CN103294820B (en) WEB page classifying method and system based on semantic extension
CN107748745B (en) Enterprise name keyword extraction method
CN108021605A (en) A kind of keyword classification method and apparatus
CN112836067B (en) Intelligent searching method based on knowledge graph
CN108304382A (en) Mass analysis method based on manufacturing process text data digging and system
CN104573683B (en) Character string identification method and device
CN111833310A (en) Surface defect classification method based on neural network architecture search
CN103929499B (en) A kind of Internet of Things isomery index identification method and system
CN115713970A (en) Transcription factor identification method based on Transformer-Encoder and multi-scale convolutional neural network
CN111061972A (en) AC searching optimization method and device for URL path matching
CN103927325A (en) URL (uniform resource locator) classifying method and device
CN106484676A (en) Biological Text protein reference resolution method based on syntax tree and domain features
CN106096014A (en) The Text Clustering Method of mixing length text set based on DMR
CN106844338B (en) method for detecting entity column of network table based on dependency relationship between attributes
CN106570058A (en) Searching method and search engine
CN109828785B (en) Approximate code clone detection method accelerated by GPU
CN106682136A (en) Traditional-Chinese-medicine medical literature classification and storage method based on data mining

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