CN110321471A - A kind of internet techno-financial intelligent Matching method based on the convergence of policy resource - Google Patents
A kind of internet techno-financial intelligent Matching method based on the convergence of policy resource Download PDFInfo
- Publication number
- CN110321471A CN110321471A CN201910318616.6A CN201910318616A CN110321471A CN 110321471 A CN110321471 A CN 110321471A CN 201910318616 A CN201910318616 A CN 201910318616A CN 110321471 A CN110321471 A CN 110321471A
- Authority
- CN
- China
- Prior art keywords
- text
- target
- classification
- quality inspection
- convergence
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000007689 inspection Methods 0.000 claims abstract description 34
- 238000001914 filtration Methods 0.000 claims abstract description 5
- 238000012545 processing Methods 0.000 claims abstract description 4
- 239000013598 vector Substances 0.000 claims description 17
- 238000012549 training Methods 0.000 claims description 8
- 239000003550 marker Substances 0.000 claims description 7
- 238000013499 data model Methods 0.000 claims description 6
- 230000008520 organization Effects 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 230000003252 repetitive effect Effects 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 4
- 230000006872 improvement Effects 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 230000035945 sensitivity Effects 0.000 claims 1
- 230000008676 import Effects 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 239000002344 surface layer Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000010410 layer Substances 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000699 topical effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of internet techno-financial intelligent Matching methods based on the convergence of policy resource, comprising the following steps: S1, establishes keywords database, imports the target keyword of setting；S2, web crawlers is set up, the crawl of webpage target is carried out according to the target keyword in keywords database, obtains target webpage text；S3, text preanalysis and filtering are carried out to the target webpage text of web crawlers crawl, filters out effective text；S4, classification processing is carried out to the effective text filtered out, is then passed to quality inspection unit and carries out classification quality inspection；S5, the effective text that quality inspection passes through that will classify are sent to corresponding client according to its classification, and the unacceptable effective text of the quality inspection that will classify carries out manual sort, corresponding client after retransmiting to manual sort.It is in application, may be implemented the accurate efficient collection of internet policy resource, and to the classification of the policy resource accurate intelligent of collection, be then sent to matching client according to classification results are corresponding.
Description
Technical field
The present invention relates to Data Analysis Services technical fields, and in particular to a kind of internet based on the convergence of policy resource
Techno-financial intelligent Matching method.
Background technique
Internet application is throughout the every aspect lived, such as instant messaging, social networks, news website, Intelligent life man
Electricity etc., we have been accustomed to the convenient and fast information of dependence internet offer and have gone to understand the world, form interpersonal social networks, network interaction
The information generated in the process is textual form mostly.Text information becomes the important bearer of internet social media information.
The prior art provides policy resource specifically for internet financial industry not yet and collects matched effective technology
Means.
Summary of the invention
The present invention is in view of the deficienciess of the prior art, provide a kind of internet science and technology gold based on the convergence of policy resource
Melt intelligent Matching method, in application, the accurate efficient collection of internet policy resource may be implemented, and to the policy of collection
Property the classification of resource accurate intelligent, be then sent to matching client according to classification results are corresponding.
The invention is realized by the following technical scheme:
A kind of internet techno-financial intelligent Matching method based on the convergence of policy resource, comprising the following steps:
S1, keywords database is established, the target keyword of setting is imported in keywords database；
S2, web crawlers is set up, it is associated with keywords database, and be put into network and closed according to the target in keywords database
Keyword carries out the crawl of webpage target, obtains target webpage text；
S3, text preanalysis and filtering are carried out to the target webpage text of web crawlers crawl, filters out effective text；
S4, classification processing is carried out to the effective text filtered out, is then passed to quality inspection unit and carries out classification quality inspection；
S5, the effective text that quality inspection passes through that will classify are sent to corresponding client according to its classification, and the quality inspection that will classify is obstructed
The effective text crossed carries out manual sort, corresponding client after retransmiting to manual sort.
Preferably, in step sl, keywords database includes subject term library and target dictionary, and subject term library is for storing history keyword
Word data, for importing target keyword, the web crawlers in step S2 is associated target dictionary with target dictionary.
Preferably, in step sl, the target keyword in target dictionary is provided by client or/and is selected from subject term library
It takes comprising but it is not limited only to government organization organization names, field person names, the field chamber of commerce, association title, internet science and technology
Financial industry noun.
Preferably, in step s 2, target webpage text grab the step of include:
S21, the crawl seed that target keyword is set as to web crawlers；
S22, using based on target webpage feature, based on target data model and based on field concept parallel form according to
It grabs seed and grabs internet target web page text；
S23, the target webpage text of crawl is fed back, and centrally stored.
Preferably, in step s 2, the web crawlers includes universal network crawler, focused web crawler, increment type net
Network crawler and Deep Web Crawler.
Preferably, in step s3, the step of screening effective text include:
S31, all target webpage texts are carried out with repetitive rate retrieval, internally holds multiple mesh that repetitive rate reaches given threshold
Mark web page text extracts；
S32, the multiple target webpage texts extracted are subjected to number of words comparison, leave one of number of words at most, remaining is lost
It abandons；
S33, sensitive dictionary is established, is carried out using sensitive dictionary to not extracting and extracting the target webpage text for comparing and leaving
Sensitive words and phrases retrieval；
S34, the target webpage text removing containing sensitive words and phrases will be retrieved, remaining target webpage text is effectively literary
This.
Preferably, in step s 4, the classification process of effective text includes:
S41, participle extraction is carried out to the target keyword of effective text, then to the word frequency of target keyword, word order and
Semanteme carries out setting scoring statistics；
S42, it is ranked up according to the comprehensive score of word frequency, word order and semanteme, chooses the highest target of top n comprehensive score
Keyword is as term vector, and wherein N is the integer greater than 0；
S43, term vector is imported to the text classification training pattern pre-established, is classified automatically, obtains effective text
Automatic classification results；
S44, classification marker is carried out to effective text according to classification results, then passes to quality inspection unit.
Preferably, artificial Quality Inspector is set to carry out classification quality inspection to effective text in quality inspection unit, then quality inspection is passed through
Effective text be sent to corresponding client by its classification marker, effective text unacceptable to quality inspection carries out manual sort and simultaneously marks
Note, effective text after manual sort is marked is sent to corresponding client by manual sort's label, and it is obstructed to feed back corresponding quality inspection
Information is crossed, the improvement reference for classification based training model.
The present invention has the advantage that and the utility model has the advantages that
1, a kind of internet techno-financial intelligent Matching method based on the convergence of policy resource of the present invention, may be implemented mutually
The accurate efficient collection for policy resource of networking.
2, a kind of internet techno-financial intelligent Matching method based on the convergence of policy resource of the present invention, can be to collection
Policy resource carry out preanalysis and filtering, screen out duplicate contents and the resource containing sensitive words and phrases.
3, a kind of internet techno-financial intelligent Matching method based on the convergence of policy resource of the present invention, can be to collection
The classification of policy resource accurate intelligent, be then sent to matching client according to classification results are corresponding.
Detailed description of the invention
Attached drawing described herein is used to provide to further understand the embodiment of the present invention, constitutes one of the application
Point, do not constitute the restriction to the embodiment of the present invention.In the accompanying drawings:
Fig. 1 is step schematic block diagram of the invention；
Fig. 2 is the classification process schematic diagram of effective text.
Specific embodiment
To make the objectives, technical solutions, and advantages of the present invention clearer, below with reference to embodiment and attached drawing, to this
Invention is described in further detail, and exemplary embodiment of the invention and its explanation for explaining only the invention, are not made
For limitation of the invention.
Embodiment
As shown in Figure 1, a kind of internet techno-financial intelligent Matching method based on the convergence of policy resource, including it is following
Step:
S1, keywords database is established, the target keyword of setting is imported in keywords database；
S2, web crawlers is set up, it is associated with keywords database, and be put into network and closed according to the target in keywords database
Keyword carries out the crawl of webpage target, obtains target webpage text；
S3, text preanalysis and filtering are carried out to the target webpage text of web crawlers crawl, filters out effective text；
S4, classification processing is carried out to the effective text filtered out, is then passed to quality inspection unit and carries out classification quality inspection；
S5, the effective text that quality inspection passes through that will classify are sent to corresponding client according to its classification, and the quality inspection that will classify is obstructed
The effective text crossed carries out manual sort, corresponding client after retransmiting to manual sort.
In step sl, keywords database includes subject term library and target dictionary, and subject term library is used to store history keyword word data,
For importing target keyword, the web crawlers in step S2 is associated target dictionary with target dictionary.
In step sl, the target keyword in target dictionary is provided by client or/and is chosen from subject term library comprising
But it is not limited only to government organization organization names, field person names, the field chamber of commerce, association title, internet techno-financial industry name
Word.
In step s 2, target webpage text grab the step of include:
S21, the crawl seed that target keyword is set as to web crawlers；
S22, using based on target webpage feature, based on target data model and based on field concept parallel form according to
It grabs seed and grabs internet target web page text；
S23, the target webpage text of crawl is fed back, and centrally stored.
The description and definition for grabbing target are the bases for determining web page analysis algorithm and URL search strategy and how working out.And
Web page analysis algorithm and candidate's URL sort algorithm are to determine service form and crawler webpage capture behavior provided by search engine
Key point.The algorithm of the two parts is closely related again.Web crawlers, which can be divided into the description of crawl target, to be based on
Target webpage feature is based on target data model and based on 3 kinds of field concept.
The object that crawler based on target webpage feature grabs, stores and indexes is generally website or webpage.According to kind
Subsample acquisition modes can be divided into:
1, previously given initial crawl seed specimen；
2, previously given Web page classifying catalogue and seed specimen corresponding with classified catalogue；
3, the crawl target sample determined by user behavior；
Wherein, web page characteristics can be the content characteristic of webpage, be also possible to link structure feature of webpage etc..
Crawler based on target data model is directed to the data on webpage, and the data grabbed will generally meet centainly
Mode, or can convert or be mapped as target data model.
Another describing mode is the ontology or dictionary for establishing target domain, for existing from semantic angle analysis different characteristic
Significance level in a certain theme.
In step s 2, the web crawlers include universal network crawler, focused web crawler, increment type web crawlers and
Deep Web Crawler.Web crawlers is according to system structure and realizes technology, can substantially be divided into following several types: universal network
Crawler (General Purpose Web Crawler), focused web crawler (Focused Web Crawler), increment type net
Network crawler (Incremental Web Crawler), Deep Web Crawler (Deep Web Crawler).Universal network crawler
Also known as the whole network crawler (Scalable Web Crawler), object of creeping extend to entire Web from some seed URL, predominantly
Portal search engine and large-scale Web service provider acquire data；Focused web crawler (Focused Crawler), again
Claim theme network crawler (Topical Crawler), refers to selectively creep those and the theme related pages that pre-define
The web crawlers in face.It is compared with universal network crawler, focused crawler only needs to creep the page relevant to theme, greatly saves
Hardware and Internet resources, the page of preservation can also meet some specific crowds also due to quantity is few and updating decision well
Demand to specific area information；Increment type web crawlers (Incremental Web Crawler) refers to having downloaded webpage
Take incrementally updating and the crawler that is newly generated or having occurred and that variation webpage that only creeps, it can be protected to a certain extent
Demonstrate,proving the creeped page is the page as new as possible；Web page can be divided into surface layer webpage (Surface Web) by existing way
With deep layer net page (Deep Web, also referred to as Invisible Web Pages or Hidden Web).Surface layer webpage refers to conventional search
The page that engine can index, the Web page constituted based on the static Web page that can be reached with hyperlink.Deep Web is those
It is that most contents cannot be obtained by static linkage, be hidden in searchable form after, only user submits some keywords
Obtainable Web page, Deep Web crawler architecture include six basic function modules (controller of creeping, resolver, tables
Single analyzer, form processor, response analyzer, LVS controller) and two crawler internal data structures (url lists, LVS
Table).Wherein LVS (Label Value Set) indicates label/numerical value set, for indicating the data source of filling form, Deep
Web crawler handles the page submission form processor comprising list, and form processor first extracts list from the page, from preparatory
Data are selected to fill simultaneously submission form automatically in ready data set, controller downloads corresponding results page by creeping.
In step s3, the step of screening effective text include:
S31, all target webpage texts are carried out with repetitive rate retrieval, internally holds multiple mesh that repetitive rate reaches given threshold
Mark web page text extracts；
S32, the multiple target webpage texts extracted are subjected to number of words comparison, leave one of number of words at most, remaining is lost
It abandons；
S33, sensitive dictionary is established, is carried out using sensitive dictionary to not extracting and extracting the target webpage text for comparing and leaving
Sensitive words and phrases retrieval；
S34, the target webpage text removing containing sensitive words and phrases will be retrieved, remaining target webpage text is effectively literary
This.
As shown in Fig. 2, in step s 4, the classification process of effective text includes:
S41, participle extraction is carried out to the target keyword of effective text, then to the word frequency of target keyword, word order and
Semanteme carries out setting scoring statistics；
S42, it is ranked up according to the comprehensive score of word frequency, word order and semanteme, chooses the highest target of top n comprehensive score
Keyword is as term vector, and wherein N is the integer greater than 0；
S43, term vector is imported to the text classification training pattern pre-established, is classified automatically, obtains effective text
Automatic classification results；
S44, classification marker is carried out to effective text according to classification results, then passes to quality inspection unit.
In the classification process of effective text, using SVM to text classification, new samples are added using following equation:
Wherein (Xi, X) indicate two vectors inner product；During carrying out classification prediction to text, predict new point X's
When classification, it is only necessary to calculate the inner product for predicting new point X and training data point；The training data point used is supporting vector
The point of point, only supporting vector can be used for the prediction of new samples.
If the data point of the model of input is supporting vector, have:
yi(WTXi+ b)=1
And aiIt is a non-zero number, therefore the point of supporting vector is included into model, the meter for the classification prediction newly put
It calculates；If the data point of the model of input is not supporting vector, have:
yi(WTXi+b)>1
And due to aiIt is non-negative, then a is maximized to meetiIt is 0, therefore when predicting new point X, in a model, due to aiIt is 0,
Therefore the point of non-supporting vector is not included in calculating.
The scoring of word frequency is first to carry out evidence participle to notice, and count time that participle occurs in evidence notice in notice
Number, to calculate word frequency score.
The scoring of word order is the 2-gram expression formula of building notice word, and statistics 2-gram expression formula and evidence are matched secondary
Number, to calculate word order score.
Semantic scoring is that first vectorization indicates problem and evidence, then carries out evidence vector respectively, principal vector set, asks
Principal vector to be inscribed, the Evidence Problems degree of correlation is calculated, evidence vector set, which is closed, calculates evidence weight by Page Rank algorithm, in conjunction with
Evidence weight and the Evidence Problems degree of correlation, are calculated semantic score.
Artificial Quality Inspector is set in quality inspection unit to carry out classification quality inspection to effective text, the effective text then passed through to quality inspection
This is sent to corresponding client by its classification marker, and effective text unacceptable to quality inspection carries out manual sort and marks, will be artificial
Effective text after classification marker is sent to corresponding client by manual sort's label, and feeds back corresponding quality inspection and do not pass through information, uses
In the improvement reference of classification based training model.
Above-described specific embodiment has carried out further the purpose of the present invention, technical scheme and beneficial effects
It is described in detail, it should be understood that being not intended to limit the present invention the foregoing is merely a specific embodiment of the invention
Protection scope, all within the spirits and principles of the present invention, any modification, equivalent substitution, improvement and etc. done should all include
Within protection scope of the present invention.
Claims (8)
1. a kind of internet techno-financial intelligent Matching method based on the convergence of policy resource, which is characterized in that including following
Step:
S1, keywords database is established, the target keyword of setting is imported in keywords database；
S2, web crawlers is set up, it is associated with keywords database, and be put into network according to the target keyword in keywords database
The crawl of webpage target is carried out, target webpage text is obtained；
S3, text preanalysis and filtering are carried out to the target webpage text of web crawlers crawl, filters out effective text；
S4, classification processing is carried out to the effective text filtered out, is then passed to quality inspection unit and carries out classification quality inspection；
S5, the effective text that quality inspection passes through that will classify are sent to corresponding client according to its classification, and the quality inspection that will classify is unacceptable
Effective text carries out manual sort, corresponding client after retransmiting to manual sort.
2. a kind of internet techno-financial intelligent Matching method based on the convergence of policy resource according to claim 1,
It is characterized in that, in step sl, keywords database includes subject term library and target dictionary, and subject term library is for storing history keyword word number
According to for importing target keyword, the web crawlers in step S2 is associated target dictionary with target dictionary.
3. a kind of internet techno-financial intelligent Matching method based on the convergence of policy resource according to claim 2,
It is characterized in that, in step sl, the target keyword in target dictionary is provided by client or/and is chosen from subject term library,
Include but are not limited to government organization organization names, field person names, the field chamber of commerce, association title, internet techno-financial row
Industry noun.
4. a kind of internet techno-financial intelligent Matching method based on the convergence of policy resource according to claim 1,
It is characterized in that, in step s 2, the step of target webpage text grabs, includes:
S21, the crawl seed that target keyword is set as to web crawlers；
S22, using based on target webpage feature, based on target data model and based on field concept parallel form according to crawl
Seed grabs internet target web page text；
S23, the target webpage text of crawl is fed back, and centrally stored.
5. a kind of internet techno-financial intelligent Matching method based on the convergence of policy resource according to claim 1,
It is characterized in that, in step s 2, the web crawlers includes that universal network crawler, focused web crawler, increment type network are climbed
Worm and Deep Web Crawler.
6. a kind of internet techno-financial intelligent Matching method based on the convergence of policy resource according to claim 1,
It is characterized in that, in step s3, the step of screening effective text, includes:
S31, all target webpage texts are carried out with repetitive rate retrieval, internally holds multiple target networks that repetitive rate reaches given threshold
Page text extracts；
S32, the multiple target webpage texts extracted are subjected to number of words comparison, leave one of number of words at most, remaining discarding；
S33, sensitive dictionary is established, carries out sensitivity to not extracting and extracting the target webpage text for comparing and leaving using sensitive dictionary
Words and phrases retrieval；
S34, the target webpage text removing containing sensitive words and phrases will be retrieved, remaining target webpage text is effective text.
7. a kind of internet techno-financial intelligent Matching method based on the convergence of policy resource according to claim 1,
It is characterized in that, in step s 4, the classification process of effective text includes:
S41, participle extraction is carried out to the target keyword of effective text, then to the word frequency of target keyword, word order and semanteme
Carry out setting scoring statistics；
S42, it is ranked up according to the comprehensive score of word frequency, word order and semanteme, chooses the highest target critical of top n comprehensive score
Word is as term vector, and wherein N is the integer greater than 0；
S43, term vector is imported to the text classification training pattern pre-established, is classified automatically, obtain oneself of effective text
Dynamic classification results；
S44, classification marker is carried out to effective text according to classification results, then passes to quality inspection unit.
8. a kind of internet techno-financial intelligent Matching method based on the convergence of policy resource according to claim 7,
It is characterized in that, setting artificial Quality Inspector in quality inspection unit to carry out classification quality inspection to effective text, then have to what quality inspection passed through
It imitates text and is sent to corresponding client by its classification marker, effective text unacceptable to quality inspection carries out manual sort and marks, will
Effective text after manual sort's label is sent to corresponding client by manual sort's label, and feeds back corresponding quality inspection and do not pass through letter
Breath, the improvement reference for classification based training model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910318616.6A CN110321471A (en) | 2019-04-19 | 2019-04-19 | A kind of internet techno-financial intelligent Matching method based on the convergence of policy resource |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910318616.6A CN110321471A (en) | 2019-04-19 | 2019-04-19 | A kind of internet techno-financial intelligent Matching method based on the convergence of policy resource |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110321471A true CN110321471A (en) | 2019-10-11 |
Family
ID=68113073
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910318616.6A Pending CN110321471A (en) | 2019-04-19 | 2019-04-19 | A kind of internet techno-financial intelligent Matching method based on the convergence of policy resource |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110321471A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111126879A (en) * | 2019-12-31 | 2020-05-08 | 厦门美契信息技术有限公司 | Green financial item selection evaluation method |
| CN111460253A (en) * | 2020-03-24 | 2020-07-28 | 国家电网有限公司 | Internet data capture method suitable for big data analysis |
| CN113065050A (en) * | 2021-03-26 | 2021-07-02 | 深圳供电局有限公司 | Electricity price policy document collection method and system |
| CN113312343A (en) * | 2021-06-11 | 2021-08-27 | 北京思特奇信息技术股份有限公司 | Business opportunity management method and system based on web crawler tool |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020194161A1 (en) * | 2001-04-12 | 2002-12-19 | Mcnamee J. Paul | Directed web crawler with machine learning |
| CN101452470A (en) * | 2007-10-18 | 2009-06-10 | 石忠民 | Method and apparatus for a web search engine generating summary-style search results |
| CN103235827A (en) * | 2013-05-13 | 2013-08-07 | 济南政和科技有限公司 | Method for automatically classifying and screening scientific and technological information |
| CN104035997A (en) * | 2014-06-13 | 2014-09-10 | 淮阴工学院 | Scientific and technical information acquisition and pushing method based on text classification and image deep mining |
| CN104915356A (en) * | 2014-03-13 | 2015-09-16 | ***通信集团上海有限公司 | Text classification correcting method and device |
| CN108932318A (en) * | 2018-06-26 | 2018-12-04 | 四川政资汇智能科技有限公司 | A kind of intellectual analysis and accurate method for pushing based on Policy resources big data |
-
2019
- 2019-04-19 CN CN201910318616.6A patent/CN110321471A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020194161A1 (en) * | 2001-04-12 | 2002-12-19 | Mcnamee J. Paul | Directed web crawler with machine learning |
| CN101452470A (en) * | 2007-10-18 | 2009-06-10 | 石忠民 | Method and apparatus for a web search engine generating summary-style search results |
| CN103235827A (en) * | 2013-05-13 | 2013-08-07 | 济南政和科技有限公司 | Method for automatically classifying and screening scientific and technological information |
| CN104915356A (en) * | 2014-03-13 | 2015-09-16 | ***通信集团上海有限公司 | Text classification correcting method and device |
| CN104035997A (en) * | 2014-06-13 | 2014-09-10 | 淮阴工学院 | Scientific and technical information acquisition and pushing method based on text classification and image deep mining |
| CN108932318A (en) * | 2018-06-26 | 2018-12-04 | 四川政资汇智能科技有限公司 | A kind of intellectual analysis and accurate method for pushing based on Policy resources big data |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111126879A (en) * | 2019-12-31 | 2020-05-08 | 厦门美契信息技术有限公司 | Green financial item selection evaluation method |
| CN111126879B (en) * | 2019-12-31 | 2024-05-31 | 厦门美契信息技术有限公司 | Green melt item selection evaluation method |
| CN111460253A (en) * | 2020-03-24 | 2020-07-28 | 国家电网有限公司 | Internet data capture method suitable for big data analysis |
| CN113065050A (en) * | 2021-03-26 | 2021-07-02 | 深圳供电局有限公司 | Electricity price policy document collection method and system |
| CN113312343A (en) * | 2021-06-11 | 2021-08-27 | 北京思特奇信息技术股份有限公司 | Business opportunity management method and system based on web crawler tool |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110321471A (en) | A kind of internet techno-financial intelligent Matching method based on the convergence of policy resource | |
| EP2041669B1 (en) | Text categorization using external knowledge | |
| CN102208992B (en) | The malicious information filtering system of Internet and method thereof | |
| TWI437452B (en) | Web spam page classification using query-dependent data | |
| CN101470731B (en) | Personalized web page filtering method | |
| KR101315554B1 (en) | Keyword assignment to a web page | |
| CN110543595B (en) | In-station searching system and method | |
| CN107025310A (en) | A kind of automatic news in real time recommends method | |
| CN101609450A (en) | Web page classification method based on training set | |
| CN106033445B (en) | The method and apparatus for obtaining article degree of association data | |
| CN108256104A (en) | Internet site compressive classification method based on multidimensional characteristic | |
| KR20090126241A (en) | Identifying and changing personal information | |
| CN108647225A (en) | A kind of electric business grey black production public sentiment automatic mining method and system | |
| CN103886020B (en) | A kind of real estate information method for fast searching | |
| CN103177036A (en) | Method and system for label automatic extraction | |
| CN110555154B (en) | Theme-oriented information retrieval method | |
| CN104915443A (en) | Extraction method of Chinese Microblog evaluation object | |
| CN108681548A (en) | A kind of lawyer's information processing method and system | |
| CN110287314A (en) | Long text credibility evaluation method and system based on Unsupervised clustering | |
| Chen et al. | The best answers? think twice: online detection of commercial campaigns in the CQA forums | |
| CN105468780B (en) | The normalization method and device of ProductName entity in a kind of microblogging text | |
| CN105095400B (en) | The lookup method of personal homepage | |
| CN108614860A (en) | A kind of lawyer's information processing method and system | |
| KR101556714B1 (en) | Method, system and computer readable recording medium for providing search results | |
| Sumathi et al. | Fake review detection of e-commerce electronic products using machine learning techniques |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB03 | Change of inventor or designer information |
Inventor after: Tu Xiaodong Inventor after: Li Kai Inventor after: Huang Li Inventor after: Wang Jun Inventor after: Li Yiguang Inventor before: Tu Xiaodong Inventor before: Li Kai Inventor before: Huang Li Inventor before: Chen Wei Inventor before: Wang Jun Inventor before: Li Yiguang |
|
| CB03 | Change of inventor or designer information | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191011 |