CN108062688A - A kind of network information release method and device - Google Patents
A kind of network information release method and device Download PDFInfo
- Publication number
- CN108062688A CN108062688A CN201711392940.XA CN201711392940A CN108062688A CN 108062688 A CN108062688 A CN 108062688A CN 201711392940 A CN201711392940 A CN 201711392940A CN 108062688 A CN108062688 A CN 108062688A
- Authority
- CN
- China
- Prior art keywords
- user
- network information
- information
- network
- keyword
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0269—Targeted advertisements based on user profile or attribute
- G06Q30/0271—Personalized advertisement
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
- G06Q30/0256—User search
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0277—Online advertisement
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The present invention provides a kind of network information release method and devices, are related to technical field of network information.The described method includes:For the network behavior of user, each keyword and user information for corresponding to user are extracted;According to the corresponding each network information of each keyword query;For each network information, according to the network information that the filtering user information user dislikes, obtain and the matched network information of user information;At least one network information is selected to be delivered to the user in the network information after filtration.It is of the invention more targeted to carry out network information dispensing, the unnecessary occupancy to the system resource of user terminal can be reduced, treating capacity when server launches the network information can be substantially reduced, improves the performance of server, improves treatment effeciency of the server to the network information.
Description
Technical field
The present invention relates to technical field of network information, more particularly to a kind of network information release method and device.
Background technology
With the development of Internet industry, Internet advertising has become the profit mode of most of website, and advertisement is launched
Amount is also more and more.With the development of internet, user in search and webpage and when browsing, ad system according to search key into
Row Keywords matching searches advertisement associated with search key and is delivered to user.
But mode is launched in the advertisement for above-mentioned Keywords matching pattern, it is wide pointed by significant portion of keyword
Announcement is not the interested advertisement of user, it may be possible to which user dislikes and known advertisement;The above method can not make advertisement launch with
The web advertisement of user accesses behavior and is adapted, and antagonistic psychology is still easily caused to user, and unnecessary advertisement is launched
Substantial amounts of ad traffic is also wasted, is the current technical issues that need to address.
The content of the invention
The present invention is to provide a kind of network information release method and device, with the accuracy launched by the network information, carries
The high network information launches effect, avoids waste network information flow volume.
To solve the above-mentioned problems, the invention discloses a kind of network informations to put method, including:For the network row of user
To extract each keyword and user information for corresponding to user;According to the corresponding each network information of each keyword query;For
Each network information according to the network information that the filtering user information user dislikes, obtains and the matched net of user information
Network information;At least one network information is selected to be delivered to the user in the network information after filtration.
Preferably, the user information of the corresponding user of the extraction includes:The user extracted in dictionary is filtered from vocational match
The keyword of the dislike network information of each occupation and corresponding each occupation;The vocational match filtering dictionary passes through in advance for complete
Network data and user are analyzed and are built to the click historical data of the network information;The vocational match filtering dictionary includes using
The keyword of the dislike network information of each occupation in family and corresponding each occupation.
Preferably, it is described for each network information, according to the network information that the filtering user information user dislikes,
Acquisition includes with the most matched network information of user information:Each network is filtered according to the keyword of the dislike network information
The corresponding network information in information.
Preferably, it is described in advance for whole network data and user to the click historical data of the network information, it is analyzed simultaneously
Structure vocational match filtering dictionary includes:The confidence level of each occupational group of each user is analyzed from the whole network data;For
Confidence level is more than each user of first threshold under each occupational group, and the network information for obtaining each user clicks on historical data
And analyze the keyword of the corresponding dislike network information of the occupational group;It is crucial for each occupational group and the corresponding network information
Word structure vocational match filtering dictionary.
Preferably, the confidence level of each occupational group that each user is analyzed from the whole network data includes:By occupation
Classification classifies whole network data;For each webpage information of any occupational group, obtain and access occupational group's webpage
Each user and the occupational information with user;For each user, the weight classified according to the occupational group, each occupational information
Weight calculation described in user the occupational group confidence level.
Preferably, further include:For each user, extraction the user is in each occupational information of forum website;Further,
The confidence level of each occupational group that each user is analyzed from the whole network data includes:For each user, according to described
The duty of the weight, the weight of each occupational information, user described in the weight calculation of forum website occupational information of occupational group's classification
The confidence level of industry classification.
Preferably, each user that first threshold is more than for confidence level under each occupational group, obtains each use
The network information at family, which clicks on historical data and analyzes the corresponding keyword for disliking the network information of the occupational group, to be included:Statistics institute
It states under occupational group, confidence level is more than the clicking rate to various network information classifications of each user of first threshold;It is small to will click on rate
In each network information classification of second threshold, the network information classification crucial phrase cooperation of the network information classification is extracted as dislike
The keyword of the network information.
Preferably, further include:Persistently obtain the access history data of the user, the personalized preference class of counting user
Not;According to the categories of preferences, adjustment is for the vocational match filtering dictionary of the user.
Preferably, described according to the categories of preferences, adjustment includes for the vocational match filtering dictionary of the user:For
User preference type increases putting for the corresponding occupational group of type of preferences described in the vocational match filtering dictionary of corresponding the user
Reliability;When the weight reaches weight threshold, historical data, statistics are clicked on for the network information of the user of the occupational group
Clicking rate is less than the network information classification of click threshold, and the network information classification keyword of the extraction category network information is as anti-
Feel the keyword of the network information.
Preferably, the corresponding network information in each network information is filtered according to the keyword of the dislike network information
Including:Extract the network information classification keyword of each network information, and by the network information classification keyword and the dislike
The keyword of the network information is matched;Each network information is filtered according to matching result.
Preferably, at least one network information is selected to be delivered to user's bag in the network information after filtration
It includes:For the network information after the corresponding filtering of same a batch keyword, multiple nets to belong to a different category are selected in different periods
Network information is delivered to the user.
The invention also discloses a kind of network information delivery device, including:Information extraction modules, for being directed to the net of user
Each keyword and user information of corresponding user are extracted in network behavior;Network information acquisition module, for according to each keyword
Inquire about corresponding each network information;Internet Filtering module, for being directed to each network information, according to the user information
The network information of user's dislike is filtered, is obtained and the matched network information of user information;Putting module, for net after filtration
At least one network information is selected to be delivered to the user in network information.
Compared with prior art, the present invention includes advantages below:The present invention believes first with whole network data and user network
Breath clicks on history structure vocational match filtering dictionary, and vocational match filtering dictionary make use of the network data of objective reality, can visitor
The keyword of the dislike network information of the occupation of the analysis user of sight and the network information type of user's dislike.Then it is of the invention
Dictionary is filtered using vocational match, filtering can effectively avoid user and generate the converse heart for the dislike information of the keyword of user
Reason, and bring good experience to customer access network;In this process, due to will believe with the keyword map network of user
Breath is filtered, and is then extracted some or certain a few network informations from the network information after filtering again and is delivered to user terminal,
This kind of more targeted network information launch process, can reduce the unnecessary occupancy to the system resource of user terminal, can be significantly
Treating capacity when server launches the network information is reduced, improves the performance of server, improves server to the network information
Treatment effeciency.Meanwhile such as the dispensing for ad data, targetedly ad data dispensing also avoids information push
The unnecessary ad data of server is launched, and saves its calculation amount and ad traffic, and in Information Push Server performance
Its treatment effeciency can be greatly improved in the case of constant.
Description of the drawings
Fig. 1 is a kind of network information release method flow diagram of the embodiment of the present invention one;
Specific embodiment
In order to make the foregoing objectives, features and advantages of the present invention clearer and more comprehensible, it is below in conjunction with the accompanying drawings and specific real
Applying mode, the present invention is described in further detail.
With reference to Fig. 1, a kind of network information release method flow diagram of the embodiment of the present invention one is shown, it specifically can be with
Including:Step 50, for the network behavior of user, each keyword and user information for corresponding to user are extracted;When user is in network
In scan for, when network behaviors, extracting key word information (such as search key input by user) and the user of user
Information (such as the customized information of user, obtained such as through statistical analysis the dislike network information of user keyword (such as
Dislike advertisement keyword) etc. or user configuration the keyword of the dislike network information etc.).It is filtered from vocational match in dictionary
Each occupation of user of extraction and the keyword of the dislike network information of corresponding each occupation;The vocational match filtering dictionary passes through
The click historical data of the network information is analyzed and built for whole network data and user in advance;The vocational match filtering
Dictionary includes the keyword of the dislike network information of each occupation of user and corresponding each occupation.
In this application, the network information includes ad content.
Step 60, according to the corresponding each network information of each keyword query;For each key of user network behavior
Word, the data of each network information of inquiry Corresponding matching from network information system (such as ad system).
Step 70, for each network information, according to the network information that the filtering user information user dislikes, obtain
With the most matched network information of user information;(such as each advertisement of each network information is obtained in each keyword search for user
Content) after, the present invention can utilize the network information of its dislike of filtering user information, launch and believe with the most matched network of user information
It ceases to user.
Step 80, in the network information after filtration at least one network information is selected to be delivered to the user.
Claims (3)
1. a kind of network information release method, which is characterized in that including:For the network behavior of user, extract corresponding user's
Each keyword and user information;According to the corresponding each network information of each keyword query;For each network information, root
According to the network information that the filtering user information user dislikes, obtain and the matched network information of user information;After filtration
At least one network information is selected to be delivered to the user in the network information.
2. according to the method described in claim 1, it is characterized in that, the user information of the corresponding user of the extraction includes:From duty
Each occupation of user extracted in industry matching filtering dictionary and the keyword of the dislike network information of corresponding each occupation;The occupation
Matching filtering dictionary is by being analyzed and being built to the click historical data of the network information for whole network data and user in advance;
The vocational match filtering dictionary includes the keyword of the dislike network information of each occupation of user and corresponding each occupation.
3. according to the method described in claim 2, it is characterized in that, described be directed to each network information, according to the user
The network information of information filtering user dislike, acquisition include with the most matched network information of user information:According to the dislike net
The keyword of network information filters the corresponding network information in each network information.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711392940.XA CN108062688A (en) | 2017-12-14 | 2017-12-14 | A kind of network information release method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711392940.XA CN108062688A (en) | 2017-12-14 | 2017-12-14 | A kind of network information release method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108062688A true CN108062688A (en) | 2018-05-22 |
Family
ID=62139597
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711392940.XA Pending CN108062688A (en) | 2017-12-14 | 2017-12-14 | A kind of network information release method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108062688A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111192076A (en) * | 2019-12-12 | 2020-05-22 | 西安冉科信息技术有限公司 | Promotion information delivery method based on mobile terminal |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103198098A (en) * | 2013-03-12 | 2013-07-10 | 亿赞普(北京)科技有限公司 | Network information transfer method and device |
-
2017
- 2017-12-14 CN CN201711392940.XA patent/CN108062688A/en active Pending
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103198098A (en) * | 2013-03-12 | 2013-07-10 | 亿赞普(北京)科技有限公司 | Network information transfer method and device |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111192076A (en) * | 2019-12-12 | 2020-05-22 | 西安冉科信息技术有限公司 | Promotion information delivery method based on mobile terminal |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111190939B (en) | User portrait construction method and device | |
CN106022834B (en) | Advertisement anti-cheating method and device | |
CN103493089B (en) | Method and apparatus for tracking the feeding in social networks | |
CN103218431B (en) | A kind ofly can identify the system that info web gathers automatically | |
CN107862022B (en) | Culture resource recommendation system | |
CN109325179B (en) | Content promotion method and device | |
CN108984675B (en) | Data query method and apparatus based on evaluation | |
CN110942337A (en) | Accurate tourism marketing method based on internet big data | |
CN106997549A (en) | The method for pushing and system of a kind of advertising message | |
CN106682686A (en) | User gender prediction method based on mobile phone Internet-surfing behavior | |
CN104281622A (en) | Information recommending method and information recommending device in social media | |
CN103177129B (en) | Internet real-time information recommendation prognoses system | |
CN103455522A (en) | Recommendation method and system of application extension tools | |
CN110472154A (en) | A kind of resource supplying method, apparatus, electronic equipment and readable storage medium storing program for executing | |
CN105117482B (en) | A kind of method and apparatus for realizing guidance to website | |
CN113239275B (en) | Information pushing method, device, electronic equipment and storage medium | |
CN112561565A (en) | User demand identification method based on behavior log | |
JP2017138880A (en) | Learning device, learning method and learning program | |
KR20110023750A (en) | Object customization and management system | |
WO2019062013A1 (en) | Electronic apparatus, user grouping method and system, and computer-readable storage medium | |
KR102119238B1 (en) | Personalized persona management server and mangment method thereof | |
CN108595580B (en) | News recommendation method, device, server and storage medium | |
CN111373395A (en) | Artificial intelligence system and method based on hierarchical clustering | |
CN116823410B (en) | Data processing method, object processing method, recommending method and computing device | |
CN108062688A (en) | A kind of network information release method and device |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180522 |
|
WD01 | Invention patent application deemed withdrawn after publication |