Movatterモバイル変換


[0]ホーム

URL:


CN104133906A - Technical method for filtering and intelligent sorting of information - Google Patents

Technical method for filtering and intelligent sorting of information
Download PDF

Info

Publication number
CN104133906A
CN104133906ACN201410382244.0ACN201410382244ACN104133906ACN 104133906 ACN104133906 ACN 104133906ACN 201410382244 ACN201410382244 ACN 201410382244ACN 104133906 ACN104133906 ACN 104133906A
Authority
CN
China
Prior art keywords
user
information
content
score
list
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201410382244.0A
Other languages
Chinese (zh)
Other versions
CN104133906B (en
Inventor
不公告发明人
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ying Weinuo Science And Technology Ltd Of Shenzhen
Original Assignee
Ying Weinuo Science And Technology Ltd Of Shenzhen
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Ying Weinuo Science And Technology Ltd Of ShenzhenfiledCriticalYing Weinuo Science And Technology Ltd Of Shenzhen
Priority to CN201410382244.0ApriorityCriticalpatent/CN104133906B/en
Publication of CN104133906ApublicationCriticalpatent/CN104133906A/en
Application grantedgrantedCritical
Publication of CN104133906BpublicationCriticalpatent/CN104133906B/en
Expired - Fee Relatedlegal-statusCriticalCurrent
Anticipated expirationlegal-statusCritical

Links

Classifications

Landscapes

Abstract

Translated fromChinese

本发明公开了一种提供综合的海量资讯过滤并智能排序的解决方法,记录下用户已经读过的资讯列表,根据用户的机型、所在地区、设置各类资讯的默认权重,根据用户的点击,计算出用户偏好权重,再代入资讯的发布时间,所在地区,总点击量,计算资讯的得分,再根据得分进行排序,如用户点击了非用户喜欢的内容,那么加大这个内容的权重,如资讯的总点击量过高,需要归一化,避免点击较小的资讯没有机会被展示,如资讯的发布时间已经超过一段时间,需要降低资讯的得分,减少展示机会。The invention discloses a solution to provide comprehensive massive information filtering and intelligent sorting, record the information list that the user has read, set the default weight of various information according to the user's model and location, and set the default weight of various information according to the user's click , calculate the user preference weight, and then substitute the release time of the information, the region, the total number of clicks, calculate the score of the information, and then sort according to the score. If the user clicks on the content that the user does not like, then increase the weight of this content. If the total number of clicks on the information is too high, it needs to be normalized to avoid that clicks on smaller information will not have a chance to be displayed. If the information has been published for more than a period of time, it is necessary to reduce the score of the information and reduce the chance of display.

Description

A kind of information is filtered the also technical method of intelligent sequencing
 
technical field:
The information that the present invention relates to smart mobile phone information software is shown ordering techniques field, relates to especially a kind of technical method of content ordering of internet applications.
 
background technology:
Along with the development of Internet technology, all live in a large amount of information every day at us, news, advertisement, science and technology, sale etc.Not that user wants to see mostly, cannot accept so much quantity of information yet, more cannot effectively find self interested content.We need to filter information, sequence, and what finally show user is the content of high-quality, otherwise user will be difficult in the information of magnanimity, finds content own interested, focus.Application market has the information software that is much applicable to smart mobile phone at present, but can be according to user preferences, and social hotspots, issuing time are done integrated ordered application also precedent.Information is filtered and the technical method of intelligent sequencing, has solved and cannot carry out the problem of the filtration of magnanimity information and recommendation in the market, and successful, has attracted user's reading interest greatly, better experiences to user.
 
summary of the invention:
Fundamental purpose of the present invention is to provide a kind of comprehensive magnanimity information and filters the also solution of intelligent sequencing, to meet user's reading requirement, improves user's reading experience.
 
For addressing the above problem, the invention provides following technical scheme:
1, first record the information list that user had read, the information of having read for user, no longer shows user.
2, the initialization of user preferences, does not provide starting stage of hobby user, according to user's type, location, the default-weight of all kinds of information is set.
3, according to user's click, calculate user preference weight, then the issuing time of substitution information, location, total click volume, calculates the score of information, then sorts according to score.If user has clicked the content that non-user likes, strengthen so the weight of this content, illustrate that user's hobby changes.If total click volume of information is too high, need normalization, avoid clicking the little information of religion and have no chance to be demonstrated.If the issuing time of information has surpassed a period of time, need to reduce the score of information, reduce display machine meeting.
accompanying drawing explanation:
Fig. 1: the curve map that affected by information clicks
Fig. 2: different type of machines user's click custom
Embodiment:
one, the recording user information list of having read sequence, be designated as U (id1, id2, id3 ..., idn), with the information list of having sorted of the overall situation of system, be designated as T (id1, id2, id3,, idn), the list that wherein user had read needs permanent reservation, unless the id of overall information T has deletion, could delete the list of having read.First according to formula Tu obtain the list N that user do not read (id1, id2, id3 ..., idn).
two, user preferences initialization, according to user's type, location, with the total weight calculation of each classification information in each type, area, the user of different type of machines obtains the approximate value of user preferences, the user of A brand mobile phone just pays close attention to the more of amusement and life, and the user of B brand mobile phone pays close attention to the more of science and technology.As Fig. 2
According to user's click, change, in order to reflect the variation of user preferences, when user has clicked the classification that there is no before the deadline click, need to strengthen the weight of this classification.
User hobby=user click/user that classifies that classifies always clicks.
User hobby=(user classify click+classification on average the click)/user that classifies always clicks.
Total click volume of information is excessive, but can affect the chance that the nearer information of the little issuing time of click volume is demonstrated, so need to do normalized, the clicks X=log10 of information (x), as Fig. 1.
Three, along with the increase of time, the information that originally score is higher should reduce chance for exposure slowly, corresponding, the information that score is higher, and issuing time is not up-to-date, can have the chance of exposure yet.
Information dissemination time T;
Current time NOW;
Information announced second in the time interval of t=NOW-T;
Information time score:
86400 is number of seconds of one day, along with the variation of time, new information branch slowly surpass the high old information of score.The clicks scope that total number of clicks normalization is conducive to dwindle to information.
Four, the regional attribute of information has important weight for local user, the news in A area should preferentially push away the user to A area, singularity due to regional information, we have attached regional attribute to information, if user location equals the regional attribute of information, the weight of this information strengthens so, otherwise reduction weight, can allow like this user also have the chance that can see strange land information, if user has clicked strange land information, strange land information joins user's hobby setting so, and strange land attribute is considered its singularity, and the term of validity needs to reduce.

Claims (7)

CN201410382244.0A2014-08-062014-08-06A kind of information filters the technical method of simultaneously intelligent sequencingExpired - Fee RelatedCN104133906B (en)

Priority Applications (1)

Application NumberPriority DateFiling DateTitle
CN201410382244.0ACN104133906B (en)2014-08-062014-08-06A kind of information filters the technical method of simultaneously intelligent sequencing

Applications Claiming Priority (1)

Application NumberPriority DateFiling DateTitle
CN201410382244.0ACN104133906B (en)2014-08-062014-08-06A kind of information filters the technical method of simultaneously intelligent sequencing

Publications (2)

Publication NumberPublication Date
CN104133906Atrue CN104133906A (en)2014-11-05
CN104133906B CN104133906B (en)2018-07-31

Family

ID=51806584

Family Applications (1)

Application NumberTitlePriority DateFiling Date
CN201410382244.0AExpired - Fee RelatedCN104133906B (en)2014-08-062014-08-06A kind of information filters the technical method of simultaneously intelligent sequencing

Country Status (1)

CountryLink
CN (1)CN104133906B (en)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN104809154A (en)*2015-03-192015-07-29百度在线网络技术(北京)有限公司Method and device for recommending information
CN105574061A (en)*2015-05-242016-05-11刘晓建Method for filtering user generated content by network information acquisition tool
CN106547922A (en)*2016-12-072017-03-29广州优视网络科技有限公司A kind of sort method of application program, device and server
CN107193891A (en)*2017-05-022017-09-22百度在线网络技术(北京)有限公司Content recommendation method and device
CN108628949A (en)*2018-03-302018-10-09北京金堤科技有限公司A kind of processing method and processing device that information is shown
CN108961097A (en)*2018-07-122018-12-07北京猫眼文化传媒有限公司A kind of information processing method and device
CN110399572A (en)*2018-04-232019-11-01腾讯科技(深圳)有限公司A kind of information application control method, apparatus and information display systems
CN112131465A (en)*2020-09-142020-12-25绿瘦健康产业集团有限公司Activity information matching method, device, medium and terminal equipment

Citations (5)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
US20090125464A1 (en)*2005-01-212009-05-14Koninklijke Philips Electronics, N.V.Method and Apparatus for Acquiring a Common Interest-Degree of a User Group
CN102611785A (en)*2011-01-202012-07-25北京邮电大学Personalized active news recommending service system and method for mobile phone user
CN102779136A (en)*2011-05-132012-11-14北京搜狗科技发展有限公司Method and device for information search
CN103218355A (en)*2012-01-182013-07-24腾讯科技(深圳)有限公司Method and device for generating tags for user
CN103631823A (en)*2012-08-282014-03-12腾讯科技(深圳)有限公司Method and device for recommending media content

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
US20090125464A1 (en)*2005-01-212009-05-14Koninklijke Philips Electronics, N.V.Method and Apparatus for Acquiring a Common Interest-Degree of a User Group
CN102611785A (en)*2011-01-202012-07-25北京邮电大学Personalized active news recommending service system and method for mobile phone user
CN102779136A (en)*2011-05-132012-11-14北京搜狗科技发展有限公司Method and device for information search
CN103218355A (en)*2012-01-182013-07-24腾讯科技(深圳)有限公司Method and device for generating tags for user
CN103631823A (en)*2012-08-282014-03-12腾讯科技(深圳)有限公司Method and device for recommending media content

Cited By (11)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN104809154A (en)*2015-03-192015-07-29百度在线网络技术(北京)有限公司Method and device for recommending information
CN104809154B (en)*2015-03-192019-03-08百度在线网络技术(北京)有限公司The method and device recommended for information
CN105574061A (en)*2015-05-242016-05-11刘晓建Method for filtering user generated content by network information acquisition tool
CN106547922A (en)*2016-12-072017-03-29广州优视网络科技有限公司A kind of sort method of application program, device and server
CN106547922B (en)*2016-12-072020-08-25阿里巴巴(中国)有限公司Application program sorting method and device and server
CN107193891A (en)*2017-05-022017-09-22百度在线网络技术(北京)有限公司Content recommendation method and device
CN108628949A (en)*2018-03-302018-10-09北京金堤科技有限公司A kind of processing method and processing device that information is shown
CN110399572A (en)*2018-04-232019-11-01腾讯科技(深圳)有限公司A kind of information application control method, apparatus and information display systems
CN108961097A (en)*2018-07-122018-12-07北京猫眼文化传媒有限公司A kind of information processing method and device
CN108961097B (en)*2018-07-122021-01-15北京猫眼文化传媒有限公司Information processing method and device
CN112131465A (en)*2020-09-142020-12-25绿瘦健康产业集团有限公司Activity information matching method, device, medium and terminal equipment

Also Published As

Publication numberPublication date
CN104133906B (en)2018-07-31

Similar Documents

PublicationPublication DateTitle
CN104133906A (en)Technical method for filtering and intelligent sorting of information
US12118623B2 (en)Method for selectively advertising items in an image
US10290062B2 (en)System and method for utilizing annotated images to facilitate interactions between commercial and social users
US20150172396A1 (en)Systems and methods for enriching geographically delineated content
US20170316517A1 (en)System and method for managing interaction between commercial and social users
CN104008184A (en)Method and device for pushing information
US20130179806A1 (en)Customizing a tag cloud
CN109471657A (en)Gray scale dissemination method, device, computer equipment and computer storage medium
CN105095219A (en)Weibo recommendation method and terminal
WO2012068677A1 (en)Systems and methods for managing a profile of a user accessing electronic content
TW201108004A (en)Server apparatus, electronic apparatus, electronic book providing system, electronic book providing method, electronic book displaying method, and program
CN107864192A (en)Information-pushing method, device, server and readable storage medium storing program for executing
CN104574146A (en)Service recommending method and system
US20160299639A1 (en)User interface for providing geographically delineated content
CN106412635B (en)A kind of intelligence advertisement placement method and system
US20150254711A1 (en)Grouping Channels Based on User Activity
WilkenSocial media app economies
US11023924B1 (en)Event triggers in audio advertising
CN113627983A (en)Network advertisement promotion method and system based on video creativity
CN106933904B (en) Data filtering method and device
JP6060833B2 (en) Information processing apparatus, information processing method, and information processing program
CN106713952B (en)Video processing method and device
CN111737566A (en) Work sorting method, device and storage medium
Larsen et al.Handmade: how indie girl culture is changing the market
CN113051449A (en)Method and device for displaying wine and intelligent wine cabinet

Legal Events

DateCodeTitleDescription
C06Publication
PB01Publication
C10Entry into substantive examination
SE01Entry into force of request for substantive examination
GR01Patent grant
GR01Patent grant
CF01Termination of patent right due to non-payment of annual fee
CF01Termination of patent right due to non-payment of annual fee

Granted publication date:20180731


[8]ページ先頭

©2009-2025 Movatter.jp