CN101515269A - Method for achieving view search engine ranking - Google Patents
Method for achieving view search engine ranking Download PDFInfo
- Publication number
- CN101515269A CN101515269A CNA2008100578798A CN200810057879A CN101515269A CN 101515269 A CN101515269 A CN 101515269A CN A2008100578798 A CNA2008100578798 A CN A2008100578798A CN 200810057879 A CN200810057879 A CN 200810057879A CN 101515269 A CN101515269 A CN 101515269A
- Authority
- CN
- China
- Prior art keywords
- user comment
- information
- comment information
- user
- search engine
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000007418 data mining Methods 0.000 claims abstract description 7
- 238000012552 review Methods 0.000 claims description 39
- 230000000007 visual effect Effects 0.000 claims description 13
- 238000005516 engineering process Methods 0.000 claims description 11
- 241000272183 Geococcyx californianus Species 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 5
- 230000036962 time dependent Effects 0.000 claims description 5
- 230000000052 comparative effect Effects 0.000 claims description 4
- 238000005065 mining Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 abstract 1
- 238000012800 visualization Methods 0.000 abstract 1
- 238000011161 development Methods 0.000 description 7
- 230000018109 developmental process Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 210000003813 thumb Anatomy 0.000 description 2
- 238000013075 data extraction Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000035800 maturation Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000007306 turnover Effects 0.000 description 1
Images
Abstract
The invention discloses a method for achieving view search engine ranking, which comprises: using a network crawler to capture user comment web pages, preprocessing the captured web pages, and extracting user comment information from the preprocessed web pages; using a data mining technique to extract the attributes of a product from the user comment information, and determining the polarity of the attribute comment information to construct a comment information library; converting formats of all user comment information files in the comment information library to construct a hierarchical structure of the user comment information files; establishing an inverse ranking index for the converted user comment information; ranking the user comment information for establishing the inverse ranking index; and performing statistic analysis and visualization for the user comment information. The method effectively merges the quality factors of the user comment information, fully considers the time dimension information, and can supply view information services for potential users more accurately, relatively and timely.
Description
Technical field
The present invention relates to information retrieval and search engine technique field, is a kind of method that realizes view search engine ranking.
Background technology
21st century is the informationalized epoch, the tertiary industry constantly rises at the proportion of various countries, particularly service sector, information service industry becomes the leading industry of 21 century, this has caused the generation and the development of ecommerce, under the influence that the global IT application general trend of events is driven, the ecommerce of various countries constantly improves and is perfect, and ecommerce becomes the focus of each country and the contention of each major company.And in China, the universal and development of computer and network technology, ecommerce emerges rapidly, and numerous infotech enterprises, venture capital firm, production circulation enterprise carry out ecommerce one after another.
2007, world's ecommerce continued fast-developing, became the roll booster of economic globalization.The widespread use of ecommerce reduced the cost of enterprise operation, management and commercial activity, promoted fund, technology, product, service and personnel flowing in the world, promoted development of economic globalization.At present, the application of ecommerce has become the key factor of decision enterprise international competitiveness, successful explanation ecommerce with the companies such as Alibaba of U.S.'s Amazon, EBAY and China is leading world's service sector development, and affects following business development pattern.
From a holistic point of view, world's turnovers of e-commerce reached 12.8 trillion dollars in 2007, accounted for 18% of global commodity transaction.With the developed country headed by the U.S., remain ecommerce main force, developing country's ecommerce such as China are a dark horse, and become the important force of international E-commerce market day by day.2007, B2B E-commerce was still occupied an leading position, and e-commerce developments such as B2C, G2C, G2B, C2C are swift and violent, present diverse development situation.With the leading industry ecommerce of large-scale leading enterprise is B2B main flow strength, and third party's e-commerce platforms such as ASP become one of successful pattern of medium-sized and small enterprises E-business applications.
When doing shopping on the net, the very big problem that the user faces is exactly how to find own desired articles evaluation information on numerous e-commerce websites, viewpoint search engine based on user comment information is the key that addresses this problem, when the user imports a product or product attribute, the viewpoint search engine is just searched in index file according to key words, and returns maximally related product viewpoint information.
Viewpoint search engine at user comment information also is in conceptual phase at present.And have following problem, first does not fully take into account the quality height of review information.Second does not consider the importance of time dimension information in the Search Results ordering.The 3rd does not carry out statistical study and visual to Search Results.
Summary of the invention
(1) technical matters that will solve
In view of this, for the viewpoint information service efficiently of providing convenience for the potential user, and the problem that solves existing viewpoint search ordering method existence, fundamental purpose of the present invention provides a kind of method that realizes view search engine ranking, to overcome the problem that existing view search engine ranking method exists, as only considering the correlativity of viewpoint information, Search Results is not carried out defectives such as visual, for the potential user provides more effective viewpoint information service.
(2) technical scheme
In order to achieve the above object, the invention provides a kind of method that realizes view search engine ranking, this method comprises:
Step S1: use web crawlers that the user comment webpage is grasped, the webpage that grasps is carried out pre-service, from pretreated webpage, extract user comment information;
Step S2: use data mining technology from this user comment information, to extract the attribute of product, and the polarity of definite attribute review information, make up the review information storehouse;
Step S3: change the form of all user comment information documents in this review information storehouse, make up the hierarchical structure of user comment information document;
Step S4: set up ranking index to changing later user comment information;
Step S5: the user comment information of setting up ranking index is sorted;
Step S6: user comment information is carried out statistical study and visual.
Preferably, described in the step S1 user comment webpage is grasped, at first the URL network address of electron gain business web site utilizes grabber to adopt the strategy of breadth-first extracting that these e-commerce websites are grasped then.
Preferably, extracting user comment information described in the step S1 adopts the RoadRunner algorithm that the user comment information webpage that grasps is extracted.
Preferably, data mining technology described in the step S2 is an association rule mining technology, and the polarity of described definite attribute review information is to determine that the user is positive to the comment of this attribute or reverse side.
Preferably, the hierarchical structure of the document of user comment information described in the step S3 is used for representing the metadata information of user comment information and the particular content of user comment information, the comment sentence that contains product attribute and viewpoint polarity in the particular content of user comment information is represented with user comment information is a unit, and the comment sentence comprises the particular content of product attribute, viewpoint polarity and sentence that this sentence contains.
Preferably, that sets up described in the step S4 falls ranking index, is used for storing the metadata of user comment information, simultaneously index the particular content of comment sentence, this index is the index that is based upon on the sentence level, rather than the index on user comment document level.
Preferably, described in the step S5 user comment information of setting up ranking index being sorted, is that keyword carries out with the correlativity of review information, the quality factor of review information, the time dimension information of review information.
Preferably, described in the step S6 user comment information is carried out statistical study and visual, be by the user comment information that searches out is carried out statistical study, with the time dependent tendency information of user comment information, and estimate comparative information for the pros and cons of certain product attribute and carry out visual.
(3) beneficial effect
From technique scheme as can be seen, the method of this realization view search engine ranking provided by the invention, merged the quality factor of user comment information effectively, and taken into full account time dimension information, can provide more accurate, more relevant, viewpoint information service more timely for the potential user.Therefore, the present invention has solved the problem that existing viewpoint search ordering method exists to a certain extent.The present invention simultaneously carries out statistical study to Search Results, with the time dependent tendency information of user comment information, and estimates comparative information for the pros and cons of certain product attribute and carries out visually, gives the clear and intuitive user comment information of potential user.
Description of drawings
Fig. 1 is the method flow diagram of realization view search engine ranking provided by the invention;
Fig. 2 is through the pretreated result schematic diagram of step S1 according to the embodiment of the invention;
Fig. 3 is the result schematic diagram of determining according to the polarity of embodiment of the invention step S2 attribute extraction and attribute review information;
Fig. 4 is a hierarchical chart of representing the user comment information document according to the embodiment of the invention;
Fig. 5 is the result schematic diagram after changing through step S3 according to the embodiment of the invention;
Fig. 6 is according to embodiment of the invention review information time history plot;
Fig. 7 is the histogram according to embodiment of the invention pros and cons viewpoint contrast usefulness;
Fig. 8 is to be the figure as a result that system returns according to embodiment of the invention user search product attribute " Sony W55 Size ".
Embodiment
For making the purpose, technical solutions and advantages of the present invention clearer, below in conjunction with specific embodiment, and with reference to accompanying drawing, the present invention is described in more detail.Be to be noted that described embodiment only is intended to be convenient to the understanding of the present invention, and it is not played any qualification effect.
In order to realize method of the present invention, consider that algorithm relates to multithreading and grasps and set up ranking index, if realize that at unit guarantee that preferably processor host frequency is not less than 2GHz, internal memory is not less than 1G, can adopt any programming language commonly used to write.
The view search engine ranking method that the present invention proposes, overall procedure specifically comprises as shown in Figure 1: user comment information grasps (step S1) part and makes up review information storehouse (S2) prepares data for whole search engine; Step S3 converts all user comment information documents in the review information storehouse to as shown in Figure 4 hierarchical structure; Step S4 sets up ranking index to changing later user comment information; Step S5 is that the Search Results to the user sorts; Step S6 carries out statistical study and visual to the user search result.
Based on the method flow diagram of realization view search engine ranking shown in Figure 1, below describe the method flow diagram of this realization view search engine ranking provided by the invention in detail.
Step S1: use web crawlers that the user comment webpage is grasped, the webpage that grasps is carried out pre-service, from pretreated webpage, extract user comment information.
In this step, the user comment webpage is grasped, at first the URL network address of electron gain business web site website utilizes grabber to adopt the strategy of breadth-first extracting that these e-commerce websites are grasped then.E-commerce website is carried out the catalogue formula grasp, because The present invention be directed to user comment information, so the target web that will grasp is mainly from e-commerce website, such as Amazon etc.At first artificially obtain the URL network address of these websites, the grabber of writing with oneself grasps these e-commerce websites.Because these websites overwhelming majority is the information of ecommerce theme, and level is less, so the strategy that adopts breadth-first to grasp.See step S 1 among Fig. 1.Because webpage grasps the method for many maturations has been arranged, so do not belong to the content that the present invention emphasizes.
Use is carried out relevant information based on the RoadRunner algorithm to the user comment information webpage that grasps and is extracted, main extraction user is published in review information on the website, RoadRunner algorithm list of references: " RoadRunner:Towards Automatic Data Extraction from Large WebSites ".Pretreated result as shown in Figure 2.
Step S2: use data mining technology from this user comment information, to extract the attribute of product, and the polarity of definite attribute review information, make up the review information storehouse.
In this step, the described user comment information that extracts adopts the RoadRunner algorithm that the user comment information webpage that grasps is extracted, promptly adopt association rulemining technology in the data mining to extract product attribute and to the review information of attribute, concrete grammar list of references: " Mining Opinion Features in CustomerReviews " from the pretreated result of step S1.Determine the viewpoint polarity of the review information of attribute then, determine that promptly the user is positive to the comment of this attribute or reverse side, determines the method list of references of viewpoint polarity: " Thumbs Up or Thumbs Down? Semantic Orientation Applied toUnsupervised Classification of Reviews ".Extract the result as shown in Figure 3.
Step S3: change the form of all user comment information documents in this review information storehouse, make up the hierarchical structure of user comment information document.
In this step, the hierarchical structure of described user comment information document is used for representing the metadata information of user comment information and the particular content of user comment information, the comment sentence that contains product attribute and viewpoint polarity in the particular content of user comment information is represented with user comment information is a unit, and the comment sentence comprises the particular content of product attribute, viewpoint polarity and sentence that this sentence contains.
The result that step S2 is handled converts hierarchical structure as shown in Figure 4 to, and transformation result as shown in Figure 5.This hierarchical structure can clear expression user comment document metadata and the particular content of user comment document.
Step S4: set up ranking index to changing later user comment information.
In this step, described foundation fall ranking index, be used for storing the metadata of user comment information, simultaneously index the particular content of comment sentence, this index is the index that is based upon on the sentence level, rather than the index on user comment document level.In order to find the information of user's request fast, we set up ranking index for the result that step S3 handles, the so-called ranking index of falling is exactly among the quoting of search engine reality, sometimes need search record according to some value of key word, so we set up index according to key word, we just are referred to as inverted index this index, and have inverted index file we be called the inverted index file and also can make it realize retrieving fast and at a high speed efficient for inverted file.The characteristics of ranking index of noting falling among the present invention are stored metadata, and metadata in an embodiment is: " Avery good choice for lots of people-easy to carry, easy to use "; " 257/261 "; " on March 24th, 2007 ".And we are to be that unit carries out index with the sentence to the particular content of user comment information, rather than are that unit carries out index with a user comment information document.The benefit of doing like this is, tend in the user comment information document a plurality of attributes of product are commented on, and each sentence generally only contains the review information to an attribute, is that unit carries out index with the sentence, helps the attribute to user inquiring of accurate localization more.
Step S5: the user comment information of setting up ranking index is sorted.
In this step, described the user comment information of ranking index sorts to setting up, is that keyword carries out with the correlativity of review information, the quality factor of review information, the time dimension information of review information.Sort method is not merely considered correlativity among the present invention, and has considered user comment information quality factor, time dimension information.Specific algorithm is as described below:
The quality factor computing formula:
OQ wherein
iIt is the quality factor of i user comment document; a
iBe to have read among the reader of this comment to think that this comments on helpful number; b
iIt is the Readership of having read this comment.
Time dimension information calculations formula:
TDF wherein
iBe the time dimension information of i user comment document; t
iIt is the time that this user comment information is delivered; T is the time of user inquiring; β is a constant.
The correlation calculations formula:
This formula.
Final score computing formula: FR
i=α LR+ (1-α) (TDF
i+ OQ
i), FR
iIt is the final score of i user comment document.It will determine the ordering that the document is final; α is 0 to 1 constant.
Provide the example of a concrete calculating ordering below, in order to be example with 3 user comment information documents simply here, as shown in table 1.α in this example=0.65, β=10.
Review1 | | Review3 | |
Help | |||
257/261 | 16/17 | 15/18 | |
Date | 3/24/07 | 4/10/07 | 5/15/07 |
Table 1
The quality factor of three review information is respectively:
The time dimension information of three review information is respectively:
The correlativity of three review information is respectively:
LR
i=0.87
LR
2=0.91
LR
3=0.96
Three review information final scores are:
FR
1=0.65*0.87+0.35*(1.85+1.49)=1.73
FR
2=0.65*0.91+0.35*(0.99+1.51)=1.47
FR
3=0.65*0.96+0.35*(0.88+1.58)=1.49
According to last score FR
1>FR
3>FR
2, can determine three review information ranks.
Step S6: user comment information is carried out statistical study and visual.
In this step, described user comment information is carried out statistical study and visual, be by the user comment information that searches out is carried out statistical study,, and estimate comparative information for the pros and cons of certain product attribute and carry out visual the time dependent tendency information of user comment information.
For information more intuitively is provided to the user, need carry out visual to Search Results, review information change curve specific implementation method in time is as follows, with the month is base unit, add up in each month sum at certain product review, be horizontal ordinate then with the month, the comment number in each month is that ordinate obtains the time dependent trend curve of user comment information, sees Fig. 6.Pros and cons viewpoint information contrast histogram implementation method is that positive viewpoint sum of statistics and reverse side viewpoint sum are represented the contrast of pros and cons viewpoint then with histogram in Search Results, see Fig. 7.Fig. 8 is that user search product attribute " Sony W55 Size " is the figure as a result that system returns.Wherein the upper left side is the review information change trend curve in time of " Sony W55 Size ", and the upper right side is " Sony W55 Size " pros and cons viewpoint information contrast histogram, and the below is at " Sony W55 Size " the concrete review information of this attribute.
Above-described specific embodiment; purpose of the present invention, technical scheme and beneficial effect are further described; institute is understood that; the above only is specific embodiments of the invention; be not limited to the present invention; within the spirit and principles in the present invention all, any modification of being made, be equal to replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (8)
1, a kind of method that realizes view search engine ranking is characterized in that, this method comprises:
Step S1: use web crawlers that the user comment webpage is grasped, the webpage that grasps is carried out pre-service, from pretreated webpage, extract user comment information;
Step S2: use data mining technology from this user comment information, to extract the attribute of product, and the polarity of definite attribute review information, make up the review information storehouse;
Step S3: change the form of all user comment information documents in this review information storehouse, make up the hierarchical structure of user comment information document;
Step S4: set up ranking index to changing later user comment information;
Step S5: the user comment information of setting up ranking index is sorted;
Step S6: user comment information is carried out statistical study and visual.
2, the method for realization view search engine ranking according to claim 1, it is characterized in that, described in the step S1 user comment webpage is grasped, at first the URL network address of electron gain business web site utilizes grabber to adopt the strategy of breadth-first extracting that these e-commerce websites are grasped then.
3, the method for realization view search engine ranking according to claim 1 is characterized in that, extracts user comment information described in the step S1 and adopts the RoadRunner algorithm that the user comment information webpage that grasps is extracted.
4, the method for realization view search engine ranking according to claim 1, it is characterized in that, data mining technology described in the step S2 is an association rule mining technology, and the polarity of described definite attribute review information is to determine that the user is positive to the comment of this attribute or reverse side.
5, the method for realization view search engine ranking according to claim 1, it is characterized in that, the hierarchical structure of the document of user comment information described in the step S3 is used for representing the metadata information of user comment information and the particular content of user comment information, the comment sentence that contains product attribute and viewpoint polarity in the particular content of user comment information is represented with user comment information is a unit, and the comment sentence comprises the particular content of product attribute, viewpoint polarity and sentence that this sentence contains.
6, the method for realization view search engine ranking according to claim 1, it is characterized in that, the ranking index of setting up described in the step S4, be used for storing the metadata of user comment information, simultaneously index the particular content of comment sentence, this index is the index that is based upon on the sentence level, rather than the index on user comment document level.
7, the method for realization view search engine ranking according to claim 1, it is characterized in that, described in the step S5 user comment information of setting up ranking index being sorted, is that keyword carries out with the correlativity of review information, the quality factor of review information, the time dimension information of review information.
8, the method for realization view search engine ranking according to claim 1, it is characterized in that, described in the step S6 user comment information is carried out statistical study and visual, be by the user comment information that searches out is carried out statistical study, with the time dependent tendency information of user comment information, and estimate comparative information for the pros and cons of certain product attribute and carry out visual.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2008100578798A CN101515269B (en) | 2008-02-20 | 2008-02-20 | Method for achieving view search engine ranking |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2008100578798A CN101515269B (en) | 2008-02-20 | 2008-02-20 | Method for achieving view search engine ranking |
Publications (2)
Publication Number | Publication Date |
---|---|
CN101515269A true CN101515269A (en) | 2009-08-26 |
CN101515269B CN101515269B (en) | 2011-08-31 |
Family
ID=41039726
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2008100578798A Expired - Fee Related CN101515269B (en) | 2008-02-20 | 2008-02-20 | Method for achieving view search engine ranking |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN101515269B (en) |
Cited By (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102214201A (en) * | 2010-04-08 | 2011-10-12 | 微软公司 | Deriving statement from product or service reviews |
CN102609481A (en) * | 2012-01-20 | 2012-07-25 | 苏州简拔林网络科技有限公司 | Method for updating and gathering comment information in real time |
CN102609424A (en) * | 2011-01-21 | 2012-07-25 | 日电(中国)有限公司 | Method and equipment for extracting assessment information |
CN102637165A (en) * | 2012-02-17 | 2012-08-15 | 清华大学 | Method for extracting attribute-viewpoint pairs of Chinese viewpoint and evaluation information |
CN102722545A (en) * | 2012-05-25 | 2012-10-10 | 百度在线网络技术(北京)有限公司 | Method and device for sequencing published information and equipment |
CN103164438A (en) * | 2011-12-13 | 2013-06-19 | 北大方正集团有限公司 | Acquisition method and system for web reviews |
CN103593426A (en) * | 2013-11-07 | 2014-02-19 | 北京奇虎科技有限公司 | Commodity searching and providing method and device |
CN103823893A (en) * | 2014-03-11 | 2014-05-28 | 北京大学 | User comment-based product search method and system |
CN103870973A (en) * | 2012-12-13 | 2014-06-18 | 阿里巴巴集团控股有限公司 | Information push and search method and apparatus based on electronic information keyword extraction |
CN103914373A (en) * | 2012-12-31 | 2014-07-09 | 百度在线网络技术(北京)有限公司 | Method and device for determining priority corresponding to module characteristic information |
CN103927381A (en) * | 2014-04-29 | 2014-07-16 | 北京百度网讯科技有限公司 | Right-and-wrong problem processing method and device |
CN104156390A (en) * | 2014-07-07 | 2014-11-19 | 乐视网信息技术(北京)股份有限公司 | Comment recommendation method and system |
WO2015062313A1 (en) * | 2013-10-28 | 2015-05-07 | 百度在线网络技术(北京)有限公司 | Method and device for processing and providing evaluation information |
CN104951558A (en) * | 2015-06-30 | 2015-09-30 | 北京奇艺世纪科技有限公司 | Video to-be-improved item determining method and device |
CN105975487A (en) * | 2016-04-26 | 2016-09-28 | 昆明理工大学 | Method for judging correlativity of user comments of APP software |
CN106485634A (en) * | 2016-09-27 | 2017-03-08 | 北京百度网讯科技有限公司 | Opinion poll method and device based on artificial intelligence |
CN107807933A (en) * | 2016-09-09 | 2018-03-16 | 阿里巴巴集团控股有限公司 | A kind of answering method and device for puing question to |
CN112214573A (en) * | 2020-10-30 | 2021-01-12 | 数贸科技(北京)有限公司 | Information search system, method, computing device, and computer storage medium |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1395206A (en) * | 2002-08-23 | 2003-02-05 | 北京大学 | Method for collecting, analyzing and providing network information and its system |
-
2008
- 2008-02-20 CN CN2008100578798A patent/CN101515269B/en not_active Expired - Fee Related
Cited By (28)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102214201A (en) * | 2010-04-08 | 2011-10-12 | 微软公司 | Deriving statement from product or service reviews |
CN102609424A (en) * | 2011-01-21 | 2012-07-25 | 日电(中国)有限公司 | Method and equipment for extracting assessment information |
CN102609424B (en) * | 2011-01-21 | 2014-10-08 | 日电(中国)有限公司 | Method and equipment for extracting assessment information |
CN103164438B (en) * | 2011-12-13 | 2016-07-06 | 北大方正集团有限公司 | The acquisition method of a kind of network comment and system |
CN103164438A (en) * | 2011-12-13 | 2013-06-19 | 北大方正集团有限公司 | Acquisition method and system for web reviews |
WO2013087005A1 (en) * | 2011-12-13 | 2013-06-20 | 北大方正集团有限公司 | Network comment collection method and system |
US20140289395A1 (en) * | 2011-12-13 | 2014-09-25 | Peking University Founder Group Co., Ltd. | Network comment collection method and system |
CN102609481A (en) * | 2012-01-20 | 2012-07-25 | 苏州简拔林网络科技有限公司 | Method for updating and gathering comment information in real time |
CN102637165A (en) * | 2012-02-17 | 2012-08-15 | 清华大学 | Method for extracting attribute-viewpoint pairs of Chinese viewpoint and evaluation information |
CN102637165B (en) * | 2012-02-17 | 2014-08-20 | 清华大学 | Method for extracting attribute-viewpoint pairs of Chinese viewpoint and evaluation information |
CN102722545A (en) * | 2012-05-25 | 2012-10-10 | 百度在线网络技术(北京)有限公司 | Method and device for sequencing published information and equipment |
CN102722545B (en) * | 2012-05-25 | 2015-11-25 | 百度在线网络技术(北京)有限公司 | A kind of method, device and equipment for sorting to releasing news |
CN103870973A (en) * | 2012-12-13 | 2014-06-18 | 阿里巴巴集团控股有限公司 | Information push and search method and apparatus based on electronic information keyword extraction |
CN103870973B (en) * | 2012-12-13 | 2017-12-19 | 阿里巴巴集团控股有限公司 | Information push, searching method and the device of keyword extraction based on electronic information |
CN103914373A (en) * | 2012-12-31 | 2014-07-09 | 百度在线网络技术(北京)有限公司 | Method and device for determining priority corresponding to module characteristic information |
WO2015062313A1 (en) * | 2013-10-28 | 2015-05-07 | 百度在线网络技术(北京)有限公司 | Method and device for processing and providing evaluation information |
CN103593426A (en) * | 2013-11-07 | 2014-02-19 | 北京奇虎科技有限公司 | Commodity searching and providing method and device |
CN103593426B (en) * | 2013-11-07 | 2018-04-06 | 北京奇虎科技有限公司 | A kind of commercial articles searching and offer method and device |
CN103823893A (en) * | 2014-03-11 | 2014-05-28 | 北京大学 | User comment-based product search method and system |
CN103927381A (en) * | 2014-04-29 | 2014-07-16 | 北京百度网讯科技有限公司 | Right-and-wrong problem processing method and device |
CN103927381B (en) * | 2014-04-29 | 2018-03-06 | 北京百度网讯科技有限公司 | A kind of processing method and processing device of the matter of right and wrong |
CN104156390A (en) * | 2014-07-07 | 2014-11-19 | 乐视网信息技术(北京)股份有限公司 | Comment recommendation method and system |
CN104951558A (en) * | 2015-06-30 | 2015-09-30 | 北京奇艺世纪科技有限公司 | Video to-be-improved item determining method and device |
CN105975487A (en) * | 2016-04-26 | 2016-09-28 | 昆明理工大学 | Method for judging correlativity of user comments of APP software |
CN105975487B (en) * | 2016-04-26 | 2019-07-16 | 昆明理工大学 | A kind of APP software users comment pertinence judgment method |
CN107807933A (en) * | 2016-09-09 | 2018-03-16 | 阿里巴巴集团控股有限公司 | A kind of answering method and device for puing question to |
CN106485634A (en) * | 2016-09-27 | 2017-03-08 | 北京百度网讯科技有限公司 | Opinion poll method and device based on artificial intelligence |
CN112214573A (en) * | 2020-10-30 | 2021-01-12 | 数贸科技(北京)有限公司 | Information search system, method, computing device, and computer storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN101515269B (en) | 2011-08-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101515269B (en) | Method for achieving view search engine ranking | |
CN102722498B (en) | Search engine and implementation method thereof | |
CN103226578B (en) | Towards the website identification of medical domain and the method for webpage disaggregated classification | |
CN102982153B (en) | A kind of information retrieval method and device thereof | |
US9798820B1 (en) | Classification of keywords | |
CN106126648B (en) | It is a kind of based on the distributed merchandise news crawler method redo log | |
CN102722501B (en) | Search engine and realization method thereof | |
CN100444591C (en) | Method for acquiring front-page keyword and its application system | |
CN102207936B (en) | Method and system for indicating content change of electronic document | |
CN102737021B (en) | Search engine and realization method thereof | |
CN102722499B (en) | Search engine and implementation method thereof | |
CN101620608A (en) | Information collection method and system | |
CN103365839A (en) | Recommendation search method and device for search engines | |
US20150287047A1 (en) | Extracting Information from Chain-Store Websites | |
CN103389998A (en) | Novel Internet commercial intelligence information semantic analysis technology based on cloud service | |
CN101706812B (en) | Method and device for searching documents | |
CN101963965A (en) | Document indexing method, data query method and server based on search engine | |
CN101105801A (en) | Automatic positioning method of network key resource page | |
CN102214183A (en) | Search engine query method for combining feedback contents of pages with fixed ranking | |
US20150302090A1 (en) | Method and System for the Structural Analysis of Websites | |
CN103491116A (en) | Method and device for processing text-related structural data | |
CN103970800A (en) | Method and system for extracting and processing webpage related keywords | |
CN116775972A (en) | Remote resource arrangement service method and system based on information technology | |
Chen et al. | Finding keywords in blogs: Efficient keyword extraction in blog mining via user behaviors | |
CN103177126B (en) | For pornographic user query identification method and the equipment of search engine |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20110831 |