CN101866339A - Identification of multiple-content information based on image on the Internet and application of commodity guiding and purchase in indentified content information - Google Patents
Identification of multiple-content information based on image on the Internet and application of commodity guiding and purchase in indentified content information Download PDFInfo
- Publication number
- CN101866339A CN101866339A CN200910038670A CN200910038670A CN101866339A CN 101866339 A CN101866339 A CN 101866339A CN 200910038670 A CN200910038670 A CN 200910038670A CN 200910038670 A CN200910038670 A CN 200910038670A CN 101866339 A CN101866339 A CN 101866339A
- Authority
- CN
- China
- Prior art keywords
- content information
- image
- information
- identification
- commodity
- 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
Images
Abstract
The invention belongs to identification of multiple-content information based on an image on the Internet and application of commodity guiding and purchase in indentified content information, an autonomous network computer gathering information technology is triggered to fetch the content information of all the images in an website and an webpage by loading codes on the website and the webpage, through the content information analysis of the images, the image content information database processing and the user interface display at the user side, matched identification information of multiple content information in the images is output, when the content information is a commodity and information of the commodity, the merchant and the price can be provided on the user interface at the use side and a buying link is provided, the shopping guide behavior is realized, when the shopping guide succeeds, commission is returned to the website by the merchant, therefore, a new mode for shopping online and profit of the website are created.
Description
One, technical field
The invention belongs to the multiple-content information identification on the internet of image, especially the application that the commodity guiding in the content information is bought.
Two, background technology
The content information that a lot of images are comprised on the internet is very abundant at present, but does not all have and can discern these content informations, makes sign, more not the application that the commodity channeling conduct in the content information is bought.
Three, summary of the invention
The technical problem to be solved in the present invention is: to the multiple-content information of the image on the internet, can discern, make sign, and can be to the application of the purchase of the commodity channeling conduct in the content information.
The technical solution adopted for the present invention to solve the technical problems is: based on loading code on website and webpage, can trigger autonomous network computer extracting infotech the image of browsing is carried out the multiple-content information analysis, can make tangible sign to multiple-content information, when user's point identification hit or mouse through making content information zone time of sign, the explanation of energy displaying contents information, and the behavior of the commodity in the content information being done introduction and guiding purchase.What import is to the image on the network, what export is the identification of the image multiple-content information of coupling, realized image multiple-content information Feature Extraction, the management of image multiple-content information database, the comparison of image multiple-content information feature and the interface development of user side, its agent structure comprises: image multiple-content information information is obtained, the information analysis of image multiple-content information, the data base administration of image multiple-content information, client user interface, finish respectively and obtain the feature extraction of image multiple-content information from the internet, and the adding database, the content information of coupling is provided for the user, functions such as purchase.Obtaining of image multiple-content information is to have adopted autonomous network computer to grasp infotech, to color, texture, shape, the zone, the mode that the inferior visual signature of space layer combines is carried out, image multiple-content information database basic structure comprises the source material storehouse, artificial intelligence reasoning information bank, nerual network technique characteristic information extraction storehouse, the dictionary knowledge base, image multiple-content information identification semantic base, image multiple-content information recognition feature storehouse, image multiple-content information identification index database, the page and the image multiple-content information that obtains by acquiring way preserved in the source material storehouse, and in retrieving, use as cache database; Artificial intelligence reasoning information bank, nerual network technique characteristic information extraction storehouse, can carry out intellectual analysis to the source material storehouse, improve the accuracy of information processing, the dictionary knowledge base is preserved the title keyword in image multiple-content information identification field and multi-lingual interrelated relation, from multi-angle the image multiple-content information is analyzed, preserve image multiple-content information identification scheme of classes simultaneously, be convenient to the image multiple-content information is carried out classified description; The keyword and the descriptor of image multiple-content information identification semantic base memory image multiple-content information and dictionary information bank coupling; Image multiple-content information feature database is preserved the retrieval character that utilizes identification of image multiple-content information and image multiple-content information treatment technology to obtain, and it is the physical features of low layer; Attaching relation between image multiple-content information index database preservation image document and keyword, the classified information, and interface is set, be used to receive user's feedback, improve the correctness of retrieval.
The invention has the beneficial effects as follows, of the present invention based on multiple-content information identification to the internet epigraph, conveniently browsing the user discerns a plurality of content informations in the image, helping to browse the user inquires about information of interest, as content information is the words of commodity, and provide Business Information, merchandise news, data such as price, and guiding is bought, everyone then extracts corresponding commission the website from successful shopping guide, the great like this aspect of people that increased to the ecommerce use, use images to produce profit with the numerous websites of expansion, and do not need extra input, also be shopping online, online profit creates new model
Four, description of drawings
Fig. 1 is the identification framework structural representation based on the image multiple-content information of the present invention;
Fig. 2 is that the image, semantic information based on the image multiple-content information of the present invention is obtained figure;
Fig. 3 is that the image information feature based on the image multiple-content information of the present invention obtains figure;
Fig. 4 is of the present invention based on library management of image content information recognition data and organization chart;
Fig. 5 is the synoptic diagram of handling based on the how content aware field feedback of image of the present invention;
Fig. 6 is the synoptic diagram that how content aware guiding is bought based on image of the present invention.
Five, embodiment
As the identification of Fig. 1, Fig. 2, Fig. 3, Fig. 4, Fig. 5, embodiment shown in Figure 6 based on the image multiple-content information, based on loading code on website and webpage, can trigger autonomous network computer extracting infotech the image of browsing is carried out the multiple-content information analysis, can make tangible sign to the multiple-content information feature, when the user clicks sign or mouse through making content information zone time of sign, the explanation of energy displaying contents information, and the behavior of the commodity in the content information being done introduction and guiding purchase.What import is to the image on the network, what export is the image multiple-content information identification of coupling, realized image multiple-content information Feature Extraction, the management of image multiple-content information database, the comparison of image multiple-content information feature and the interface development of user side, its agent structure comprises: image multiple-content information information is obtained, the information analysis of image multiple-content information, the data base administration of image multiple-content information, client user interface, finish respectively and obtain the feature extraction of image multiple-content information from the internet, and the adding database, the content information of coupling is provided for the user, functions such as shopping guide.
What import is the image that obtains from network, what export is the identification of the image multiple-content information of coupling, realized image multiple-content information Feature Extraction, the management of image multiple-content information database, the comparison of image multiple-content information feature and the interface development of user side, its agent structure comprises: image multiple-content information information is obtained, the information analysis of image multiple-content information, the data base administration of image multiple-content information, client user interface, finish respectively and obtain the feature extraction of image multiple-content information from the internet, and the adding database, the content information of coupling is provided for the user, functions such as purchase.Obtaining of image multiple-content information is to have adopted autonomous network computer to grasp infotech, to color, texture, shape, the zone, the mode that the inferior visual signature of space layer combines is carried out, image multiple-content information database basic structure comprises the source material storehouse, artificial intelligence reasoning information bank, nerual network technique characteristic information extraction storehouse, the dictionary knowledge base, image multiple-content information identification semantic base, image multiple-content information recognition feature storehouse, image multiple-content information identification index database, the page and the image multiple-content information that obtains by acquiring way preserved in the source material storehouse, and in retrieving, use as cache database; Artificial intelligence reasoning information bank, nerual network technique characteristic information extraction storehouse, can carry out intellectual analysis to the source material storehouse, improve the accuracy of information processing, the dictionary knowledge base is preserved the title keyword in image multiple-content information identification field and multi-lingual interrelated relation, from multi-angle the image multiple-content information is analyzed, preserve image multiple-content information identification scheme of classes simultaneously, be convenient to the image multiple-content information is carried out classified description; The keyword and the descriptor of image multiple-content information identification semantic base memory image multiple-content information and dictionary information bank coupling; Image multiple-content information feature database is preserved the retrieval character that utilizes identification of image multiple-content information and image multiple-content information treatment technology to obtain, and it is the physical features of low layer; Attaching relation between image multiple-content information index database preservation image document and keyword, the classified information, and interface is set, be used to receive user's feedback, improve the correctness of retrieval.The present invention conveniently browses the user a plurality of content informations in the image is discerned, helping to browse the user inquires about information of interest, content information is the words of commodity in this way, and provide data such as Business Information, merchandise news, price, and guiding is bought, everyone then extracts corresponding commission the website from successful shopping guide, the great like this aspect of people that increased to the ecommerce use, use images to produce profit with the numerous websites of expansion, and do not need extra input, also create new model for shopping online, online profit.
Claims (6)
1. multiple-content information identification on the internet based on image, and to discerning the application of the commodity guiding purchase in the content information, it is characterized in that: after many content identification code that Load Image on website and the webpage, the user is on the internet the browse graph picture time, when as long as click identification marking or mouse move to the multiple-content information identified areas of having discerned, what can export is coupling or close content information explanation, as content information is commodity, can implement to buy inquiry and guide the behavior of buying, agent structure comprises that the image multiple-content information obtains, the image multiple-content information is analyzed, the data base administration of image multiple-content information, client user interface.
2. according to claim 1 based on the identification on the internet of image multiple-content information, and, it is characterized in that: adopted autonomous network computer to grasp infotech and carried out obtaining the image multiple-content information to the application that the commodity guiding of discerning in the content information is bought.
3. according to claim 1 based on the identification on the internet of image multiple-content information, and to discerning the application of the commodity guiding purchase in the content information, it is characterized in that: autonomous network computer is grasped infotech carry out multiple-content information image obtained, carry out the analysis that color, texture, shape, zone, the inferior visual signature of space layer combine, obtain the multiple-content information feature.
4. according to claim 1 based on the identification on the internet of image multiple-content information, and to discerning the application of the commodity guiding purchase in the content information, it is characterized in that: all semantic informations are obtained automatically by analyzer, the semantic feature of composing images, store in the index data base, simultaneously these semantemes are extracted according to dictionary again, obtain to show the keyword of this image, be saved in the storehouse.
5. according to claim 1 based on the identification on the internet of image multiple-content information, and to discerning the application of the commodity guiding purchase in the content information, it is characterized in that: image multiple-content information database basic structure bag source material storehouse, dictionary knowledge base, artificial intelligence reasoning information bank, nerual network technique, image multiple-content information feature database, image multiple-content information semantic base, image multiple-content information index database, the page and the pictorial information that obtains by acquiring way preserved in the source material storehouse, in retrieving, as cache database; The dictionary knowledge base is preserved the title keyword in picture field and multi-lingual interrelated relation, preserves the picture scheme of classes simultaneously; Intellectual analysis can be carried out to the source material storehouse in artificial intelligence reasoning information bank, nerual network technique characteristic information extraction storehouse, improves the accuracy of information processing; Keyword and the descriptor that extracts preserved in the image, semantic storehouse from the picture that returns; The retrieval character that utilizes image recognition and image processing techniques to obtain is preserved in the characteristics of image storehouse; Attaching relation between image index storehouse preservation picture information and keyword, the classified information.
6. according to claim 1 based on the identification on the internet of image multiple-content information, and to discerning the application of the commodity guiding purchase in the content information, it is characterized in that: in the time of the webpage of browsing many content identification code of load image and website, after computing machine is analyzed the multiple-content information of the image browsed on can trigger network, the result who analyzes is fed back to the user, the a plurality of content informations that on image, identified with the sign mark, when user's click sign, perhaps when identifying content information regional, can demonstrate recognition result, have briefly bright, commodity can also carry out the shopping guide to commodity in this way, the cost performance retrieval; If it is incorrect that content information is analyzed, browse user's energy online feedback information, after computing machine receives feedback, be loaded into database, this content information is revised, improve accuracy to the content information processing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200910038670A CN101866339A (en) | 2009-04-16 | 2009-04-16 | Identification of multiple-content information based on image on the Internet and application of commodity guiding and purchase in indentified content information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200910038670A CN101866339A (en) | 2009-04-16 | 2009-04-16 | Identification of multiple-content information based on image on the Internet and application of commodity guiding and purchase in indentified content information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN101866339A true CN101866339A (en) | 2010-10-20 |
Family
ID=42958070
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN200910038670A Pending CN101866339A (en) | 2009-04-16 | 2009-04-16 | Identification of multiple-content information based on image on the Internet and application of commodity guiding and purchase in indentified content information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101866339A (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102376061A (en) * | 2011-08-26 | 2012-03-14 | 浙江工业大学 | Omni-directional vision-based consumer purchase behavior analysis device |
| CN102779140A (en) * | 2011-05-13 | 2012-11-14 | 富士通株式会社 | Keyword acquiring method and device |
| CN102930577A (en) * | 2011-08-08 | 2013-02-13 | 杨博文 | Method for displaying matching of photos of clothes on online trade platform |
| CN103345645A (en) * | 2013-06-27 | 2013-10-09 | 复旦大学 | Commodity image category forecasting method based on online shopping platform |
| CN103548025A (en) * | 2011-01-04 | 2014-01-29 | 英特尔公司 | Method for support in such a way as to allow collection of objects comprised in an input image, and a recording medium able to be read by terminal devices and computers |
| CN103631890A (en) * | 2013-11-15 | 2014-03-12 | 北京奇虎科技有限公司 | Method and device for mining image principal information |
| CN104320694A (en) * | 2014-11-13 | 2015-01-28 | 北京国双科技有限公司 | Showing method and device for network television ratings distribution |
| CN104317828A (en) * | 2014-10-09 | 2015-01-28 | 深圳码隆科技有限公司 | Search method for electronic commerce product in picture |
| CN104331442A (en) * | 2014-10-24 | 2015-02-04 | 华为技术有限公司 | Video classification method and device |
| CN104599166A (en) * | 2013-10-30 | 2015-05-06 | 国际商业机器公司 | Method and system for identifying objects in photographs |
| CN104991959A (en) * | 2015-07-21 | 2015-10-21 | 北京京东尚科信息技术有限公司 | Method and system for retrieving same or similar image based on content |
| CN105989510A (en) * | 2015-02-06 | 2016-10-05 | 展讯通信（上海）有限公司 | Online goods recommending system and device based on neural network, and mobile terminal |
| CN106294527A (en) * | 2015-06-26 | 2017-01-04 | 阿里巴巴集团控股有限公司 | A kind of information recommendation method and equipment |
| CN106792157A (en) * | 2016-12-13 | 2017-05-31 | 广东中星电子有限公司 | A kind of information labeling based on video and display methods and system |
| CN107861972A (en) * | 2017-09-15 | 2018-03-30 | 广州唯品会研究院有限公司 | The method and apparatus of the full result of display of commodity after a kind of user's typing merchandise news |
| CN107862561A (en) * | 2017-09-15 | 2018-03-30 | 广州唯品会研究院有限公司 | A kind of method and apparatus that user-interest library is established based on picture attribute extraction |
| CN108830220A (en) * | 2018-06-15 | 2018-11-16 | 山东大学 | The building of vision semantic base and global localization method based on deep learning |
| CN111459595A (en) * | 2020-03-31 | 2020-07-28 | 联想(北京)有限公司 | Processing method and device and electronic equipment |
-
2009
- 2009-04-16 CN CN200910038670A patent/CN101866339A/en active Pending
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103548025B (en) * | 2011-01-04 | 2017-04-05 | 英特尔公司 | The method and termination of the object included in supporting collection input picture |
| CN103548025A (en) * | 2011-01-04 | 2014-01-29 | 英特尔公司 | Method for support in such a way as to allow collection of objects comprised in an input image, and a recording medium able to be read by terminal devices and computers |
| CN102779140B (en) * | 2011-05-13 | 2015-09-02 | 富士通株式会社 | A kind of keyword acquisition methods and device |
| CN102779140A (en) * | 2011-05-13 | 2012-11-14 | 富士通株式会社 | Keyword acquiring method and device |
| CN102930577A (en) * | 2011-08-08 | 2013-02-13 | 杨博文 | Method for displaying matching of photos of clothes on online trade platform |
| CN102376061A (en) * | 2011-08-26 | 2012-03-14 | 浙江工业大学 | Omni-directional vision-based consumer purchase behavior analysis device |
| CN102376061B (en) * | 2011-08-26 | 2015-04-22 | 浙江工业大学 | Omni-directional vision-based consumer purchase behavior analysis device |
| CN103345645B (en) * | 2013-06-27 | 2016-09-28 | 复旦大学 | Commodity image class prediction method towards net purchase platform |
| CN103345645A (en) * | 2013-06-27 | 2013-10-09 | 复旦大学 | Commodity image category forecasting method based on online shopping platform |
| CN104599166A (en) * | 2013-10-30 | 2015-05-06 | 国际商业机器公司 | Method and system for identifying objects in photographs |
| CN103631890A (en) * | 2013-11-15 | 2014-03-12 | 北京奇虎科技有限公司 | Method and device for mining image principal information |
| CN103631890B (en) * | 2013-11-15 | 2017-05-17 | 北京奇虎科技有限公司 | Method and device for mining image principal information |
| CN104317828A (en) * | 2014-10-09 | 2015-01-28 | 深圳码隆科技有限公司 | Search method for electronic commerce product in picture |
| CN104331442A (en) * | 2014-10-24 | 2015-02-04 | 华为技术有限公司 | Video classification method and device |
| CN104320694A (en) * | 2014-11-13 | 2015-01-28 | 北京国双科技有限公司 | Showing method and device for network television ratings distribution |
| CN104320694B (en) * | 2014-11-13 | 2018-02-23 | 北京国双科技有限公司 | The methods of exhibiting and device of Web TV rating distribution |
| CN105989510A (en) * | 2015-02-06 | 2016-10-05 | 展讯通信（上海）有限公司 | Online goods recommending system and device based on neural network, and mobile terminal |
| CN106294527A (en) * | 2015-06-26 | 2017-01-04 | 阿里巴巴集团控股有限公司 | A kind of information recommendation method and equipment |
| CN104991959A (en) * | 2015-07-21 | 2015-10-21 | 北京京东尚科信息技术有限公司 | Method and system for retrieving same or similar image based on content |
| CN104991959B (en) * | 2015-07-21 | 2019-11-05 | 北京京东尚科信息技术有限公司 | A kind of method and system of the same or similar image of information retrieval based on contents |
| CN106792157A (en) * | 2016-12-13 | 2017-05-31 | 广东中星电子有限公司 | A kind of information labeling based on video and display methods and system |
| CN107861972A (en) * | 2017-09-15 | 2018-03-30 | 广州唯品会研究院有限公司 | The method and apparatus of the full result of display of commodity after a kind of user's typing merchandise news |
| CN107862561A (en) * | 2017-09-15 | 2018-03-30 | 广州唯品会研究院有限公司 | A kind of method and apparatus that user-interest library is established based on picture attribute extraction |
| CN107861972B (en) * | 2017-09-15 | 2022-02-22 | 广州唯品会研究院有限公司 | Method and equipment for displaying full commodity result after user inputs commodity information |
| CN108830220A (en) * | 2018-06-15 | 2018-11-16 | 山东大学 | The building of vision semantic base and global localization method based on deep learning |
| CN108830220B (en) * | 2018-06-15 | 2021-01-05 | 山东大学 | Visual semantic library construction and global positioning method based on deep learning |
| CN111459595A (en) * | 2020-03-31 | 2020-07-28 | 联想(北京)有限公司 | Processing method and device and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101866339A (en) | Identification of multiple-content information based on image on the Internet and application of commodity guiding and purchase in indentified content information | |
| RU2720536C1 (en) | Video reception framework for visual search platform | |
| KR101511050B1 (en) | Method, apparatus, system and computer program for offering and displaying a product information | |
| CN107833082B (en) | Commodity picture recommendation method and device | |
| US8700621B1 (en) | Generating query suggestions from user generated content | |
| US20120232987A1 (en) | Image-based search interface | |
| US20130282704A1 (en) | Search system with query refinement | |
| CN106202362A (en) | Image recommendation method and image recommendation device | |
| CN105279224A (en) | Information push method and device | |
| CN103034680B (en) | For data interactive method and the device of terminal device | |
| CN110827112B (en) | Deep learning commodity recommendation method and device, computer equipment and storage medium | |
| CN107111640B (en) | Method and user interface for presenting auxiliary content with image search results | |
| US9104746B1 (en) | Identifying contrarian terms based on website content | |
| CN108763223A (en) | Method for constructing Chinese-English Mongolian Tibetan language multilingual parallel corpus | |
| WO2017088496A1 (en) | Search recommendation method, device, apparatus and computer storage medium | |
| US10296540B1 (en) | Determine image relevance using historical action data | |
| CN103198118A (en) | Method and system for backtracking product web pages | |
| Wong et al. | Learning to extract and summarize hot item features from multiple auction web sites | |
| CN109416697A (en) | The search system fed back using result | |
| US11170403B2 (en) | Content tagging | |
| CN105868299A (en) | Data search method and device | |
| US20150331886A1 (en) | Determining images of article for extraction | |
| US10255246B1 (en) | Systems and methods for providing a searchable concept network | |
| CN109255098B (en) | Matrix decomposition hash method based on reconstruction constraint | |
| CN110827063A (en) | Multi-strategy fused commodity recommendation method, device, terminal and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Open date: 20101020 |