CN103295145A - Mobile phone advertising method based on user consumption feature vector - Google Patents
Mobile phone advertising method based on user consumption feature vector Download PDFInfo
- Publication number
- CN103295145A CN103295145A CN2012100489803A CN201210048980A CN103295145A CN 103295145 A CN103295145 A CN 103295145A CN 2012100489803 A CN2012100489803 A CN 2012100489803A CN 201210048980 A CN201210048980 A CN 201210048980A CN 103295145 A CN103295145 A CN 103295145A
- Authority
- CN
- China
- Prior art keywords
- user
- consumption
- vector
- component
- feature vector
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 239000013598 vector Substances 0.000 title claims abstract description 116
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000013507 mapping Methods 0.000 claims abstract description 16
- 239000011159 matrix material Substances 0.000 claims abstract description 6
- 238000000605 extraction Methods 0.000 claims description 9
- 239000000284 extract Substances 0.000 claims description 6
- 238000007418 data mining Methods 0.000 abstract description 3
- 238000002372 labelling Methods 0.000 abstract 1
- 230000006870 function Effects 0.000 description 8
- 230000003796 beauty Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- 230000001413 cellular effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000011002 quantification Methods 0.000 description 2
- 206010011224 Cough Diseases 0.000 description 1
- 241001122767 Theaceae Species 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000010224 classification analysis Methods 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 230000006651 lactation Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The invention discloses a mobile phone advertising method based on a user consumption feature vector, and belongs to the field of mobile phone data mining and analyzing. The method includes the steps of establishing a user keyword to represent a vector according to browsing contents of a user mobile internet; establishing a user consumption feature vector of a corresponding user according to the browsing contents of the mobile internet; extracting a keyword from an advertisement experience text database and setting a keyword weight, and constructing a characteristic matrix for each user feature vector; computing each component value of the user consumption feature vector of each user; setting the mapping relations between a user consumption tag and each component of the consumption feature vector of the user within different threshold ranges; labeling a corresponding consumption tag for each user and then conducting advertising according to each component of the current consumption feature vector of the user and the mapping relation. The mobile phone advertising method can improve precision of advertising, reduces manual interference, and effectively lowers platform running cost.
Description
Technical field
The present invention relates to a kind of mobile phone advertisement put-on method based on the customer consumption proper vector.Belong to mobile phone advertisement, telecommunication service, data mining and analysis field.
Background technology
Mobile phone is people's medium one by one, so cellphone subscriber's analysis and interruption-free mechanism is become extremely important.Because the individual media attribute of mobile phone has determined that mobile phone advertisement can be more accurate, meet advertiser's input requirement more.
But at present, the Users'Data Analysis system of each mobile phone advertisement platform usually just by the residing geographic position of user and time (direct memory access), mobile phone attribute (comprising mobile phone model, mobile phone operating system etc.) and Demographics (based on a spot of log-on message), provides the input reference to the advertiser.Also have some operators based on user's telecommunications service brand, ARPU value, GPRS flow, roam telecommunications attribute data such as number of times, use data mining method such as cluster analysis, classification analysis that the user roughly is divided into several colonies, provide the input reference to the advertiser.
The method that these segment the user based on simple static data, not only user data can not real-time update, the accuracy of segmentation can not get guaranteeing, and the real consuming capacity of targeted customer how, consumption propensity is not know whatever, also do not accomplish real accurate input.
Summary of the invention
Problem at the prior art existence, the object of the present invention is to provide a kind of mobile phone advertisement put-on method based on the customer consumption proper vector, this method is carried out the mobile phone advertisement input based on customer consumption characteristic real-time, that enrich, and is more meaningful concerning the advertiser.Especially consider actual industrial environment, when needs are faced from the various advertiser of different industries, all the more so.But the consumer behavior feature that how to obtain the user is carried out subscriber segmentation, is to have much challenging problem in the industry.
The objective of the invention is to propose a kind of mobile phone advertisement put-on method based on the customer consumption proper vector, this method need not to obtain privacy informations (whom user itself is and is indifferent to) such as user's sex, age, real-time interest, the behavioural information of utilizing the user to reveal when browsing mobile Internet webpage and use cell-phone customer terminal are analysed in depth, and the form by vector identifies the user.
In order to realize above purpose, the present invention proposes following technical scheme:
A kind of mobile phone advertisement put-on method based on the customer consumption proper vector the steps include:
1) the mobile phone advertisement publisher server obtains user's mobile Internet browsing content, and it is carried out participle and gives the participle weight, obtains user's antistop list vector;
2) make up the customer consumption proper vector of relative users according to the mobile Internet browsing content that obtains;
3) from advertisement experience text database, extract keyword and set the keyword weight, at each customer consumption proper vector, construct an eigenmatrix then;
4) user's antistop list vector, the eigenmatrix to the user carries out similarity calculating, draws the value of each component of customer consumption proper vector of every user;
5) set mapping relations between customer consumption label and user's the different threshold ranges of consumption feature component of a vector;
6) the mobile phone advertisement publisher server according to the current consumption feature of user each component value of vector and described mapping relations for each user marks corresponding consumption label, and choose the user and carry out advertisement putting according to consuming label.
Further, the method that makes up described customer consumption proper vector is: according to the mobile Internet browsing content data of obtaining, select several popular industries to make up described customer consumption proper vector as component.
Further, the building method of described eigenmatrix is: with each component of described consumption feature vector row index as eigenmatrix, the keyword of extraction is as the row index of eigenmatrix, and the weight of keyword on respective components is matrix element; Obtain described eigenmatrix.
Further, the method for each component value of consumption feature vector that described calculating user is current is: described user's antistop list vector is multiplied each other with described eigenmatrix, draw each component value of consumption feature vector of every user.
Further, in the step 1), the mobile Internet that described mobile phone advertisement publisher server also obtains the user is browsed track data and mobile client usage behavior data.
Further, browse track data structure user according to mobile Internet and browse track consumption feature vector; According to mobile client usage behavior data construct user usage behavior consumption feature vector.
Further, described user is browsed track consumption feature vector carry out similarity calculating, obtain the value that the user browses each component of track consumption feature vector, described mobile phone advertisement publisher server is browsed mapping relations between the different threshold ranges of track consumption feature component of a vector according to customer consumption label and user then, for each user marks corresponding consumption label, and choose the user according to the consumption label and carry out advertisement putting.
Further, described user's usage behavior consumption feature vector is carried out similarity to be calculated, obtain the value of each component of user's usage behavior consumption feature vector, described mobile phone advertisement publisher server is according to the mapping relations between customer consumption label and the different threshold ranges of user's usage behavior consumption feature component of a vector then, for each user marks corresponding consumption label, and choose the user according to the consumption label and carry out advertisement putting.
Further, utilize the text feature extraction technique to extract keyword and set the keyword weight.
Further, described mobile phone advertisement publisher server is that described each component of customer consumption proper vector is set an attenuation function and half period parameters that declines, the consumption feature vector of user in a period of time done weighting by attenuation function, try to achieve the consumption feature vector value of user in this section period; Described consumption label is according to the value real-time update of customer consumption proper vector component.
Further, the method that makes up described advertisement experience text database is: at first branch trade is collected the text information about advertisement; Based on the text information of classified, the method for applicating text feature extraction extracts the keyword that the user describes advertisement then, obtains described advertisement experience text database.
Further, different consumption label correspondences the different threshold range of customer consumption vector, and a user is provided with one or more consumption labels; Described threshold range is [0,1].
Method of the present invention specifically comprises following several steps, its treatment scheme as shown in the figure:
1) the mobile phone advertisement publisher server obtains abundant user's dynamic data by the Various types of data bank interface, browses track and content-data, mobile client usage behavior data etc. as user's mobile Internet.For the mobile internet page content-data, we use participle technique and analyze and give the participle weight, draw user's antistop list vector;
2) make up the customer consumption proper vector.The customer consumption proper vector can make up flexibly according to different dimensions, browse track data for mobile Internet, can select the URL address, browsing time, browse several components structure vectors such as the frequency, for the mobile Internet browsing content, can select several popular industries to make up vector as component, select nine class key industry structuring user's industry class consumption feature vector [food and drinks such as us, real estate, automobile, clothes, beauty treatment, IT digital product, Games Software, banking and insurance business, fashion luxury goods, other industry], for mobile client usage behavior data, can select the client model, OS Type, APP types commonly used etc. make up vector as component;
When 3) passing through user's mobile Internet browsing content data analysis customer consumption feature, (the experience text database can be a database that has built from advertisement experience text database to utilize the text feature extraction technique, perhaps oneself set up as required) in select representational keyword, set the keyword weight, be customer consumption proper vector structural attitude matrix; To each specific customer consumption proper vector, has only an eigenmatrix; The eigenmatrix building method: row index is made up of each component of proper vector, and each component is a row index, and the row index is made up of keyword, and these keywords can be used for distinguishing different row indexs.With 2) in the consumption feature vector mentioned be how example illustrates the structural attitude matrix, with the row of film name as eigenmatrix, with the row title of lists of keywords as eigenmatrix, and matrix element represents to be listed as be expert at weight on the corresponding industry of corresponding antistop list, concrete weight calculation is calculated the back assignment according to history or empirical data, has so just formed an eigenmatrix about industry interest consumption feature vector; Wherein, advertisement experience text database makes up: at first, need the extensive text information of collecting about advertisement of branch trade, as obtaining from network by technology such as web crawlers; Based on the text that has divided class, the method for applicating text feature extraction as based on the information gain method, based on the method for entropy, extracts the keyword that the user describes advertisement then, thereby constitutes advertisement experience text database.
4) calculate by similarity, draw the value of each component of consumption feature vector of every user; Such as, with the user browsing behavior quantification, namely the above-mentioned the 1st) compare with each row of eigenmatrix through user's antistop list vector of composing weight in the step, calculate the similarity of two vectors, namely obtain the user in the value of each component of proper vector;
5) set mapping relations between customer consumption label and the different threshold ranges of customer consumption proper vector component;
6) based on these mapping relations, system marks corresponding consumption label for all users automatically; By setting the real-time change of attenuation function reflection customer consumption proper vector, corresponding user's consumption label also can real-time change.
7) the mobile phone advertisement publisher server is chosen the user and is carried out advertisement putting according to the consumption label.
" customer consumption proper vector " in the described invention mainly comprises and can reflect the attribute variable of user's individuality aspect consumer behavior, such as 1) in user's industry class consumption feature vector, by the consumption propensity of this vectorial user to industry-by-industry.
" user's antistop list " in the described invention mainly refers to carry out the lists of keywords that draws after participle, the weight calculation by the mobile internet page content that the user is browsed, and can user's individuality " feature word " be changed by these keywords; That is to say feature, the Cup of tea thing that just can simply describe a people with several words, the label that just looks like this people is the same.
" eigenmatrix " in the described invention, namely formed by the weight of each component on the main key vocabularies of selecting of customer consumption proper vector, and the weight calculation mode can have multiple algorithm, common have a TF-IDF assignment method, boolean's method of weighting is based on the multiple weight assignment modes such as the method for weighting of entropy concept.In addition, about the selection of main keyword, also be the key point that eigenmatrix calculates, the algorithm that relates to is also abundanter, selects effective algorithm based on different business scenarios, no longer does at this and gives unnecessary details.
" mapping relations between customer consumption label and the different threshold ranges of customer consumption proper vector component " in the described invention, with the basic data of customer consumption proper vector as analysis user, by adopting qualitative and quantitative research method that proper vector is carried out mining analysis, draw the mapping relations between customer consumption label and the different threshold ranges of customer consumption proper vector component.All between [0,1], different user label correspondence the different threshold value of component to the threshold value of each component of customer consumption proper vector.With user's industry class consumption feature vector [food and drink, real estate, automobile, clothes, beauty treatment, IT digital product, Games Software, banking and insurance business, fashion luxury goods, other industry] be example, we set two threshold values 0.4,0.7, if the threshold value of the automobile component of user A surpasses 0.4, that system is denoted as automotive hobbyist for it automatically, if the threshold value of the beauty treatment component of user B surpasses 0.7, system is denoted as the beauty treatment intelligent for it automatically.
" consumption label " in the described invention, refer to direct user ID towards the reflection advertiser demand advertiser, can be direct, vivid, different consumption label correspondences the different threshold range of customer consumption vector, and a user can have a plurality of consumption labels.
" attenuation function " in the described invention, the consumption feature vector value that refers to reflect the user are accompanied by the function that user's consumption interest changes day by day.Set a time window, be assumed to be s days, with the weighted mean value of the s days similarities value as the consumption feature component of a vector, different consumption feature component of a vector have different decay modes, and namely in consumption feature vector, each attribute variable sets different attenuation functions, attenuation function shape such as negative exponent distribute, functional form is identical, is the parameter difference, and different components are set different half life period parameters.
On the update frequency mechanism of data, the mapping relations between eigenmatrix, customer consumption label and the customer consumption proper vector are set the different update cycles respectively, and each user's consumption feature vector can be accomplished to upgrade every day.
Compared with prior art, advantage of the present invention and good effect are:
The variation of customer consumption interest and consumption propensity can be real-time the customer consumption proper vector of passing through embody, thereby make the precision marketing of accomplishing that we can be real, improve advertising income; Simultaneously, we do not go to be concerned about whom every user is actually, and we only are concerned about which user is interested in what in certain time period, and secure user data can access abundant guarantee like this; In addition, the variation of customer consumption proper vector is upgraded automatically by system substantially, has reduced manual intervention, has reduced the platform operation cost effectively.
Description of drawings
Accompanying drawing has been illustrated method flow diagram of the present invention.
Embodiment
The present invention is further described with concrete example below in conjunction with accompanying drawing.
Use a concrete example to illustrate how to use the consumption feature vector that the present invention obtains the user below, and set the mapping relations between customer consumption label and the customer consumption proper vector, be applied to mobile phone advertisement subscriber segmentation field.
Example:
Suppose to exist a kind of like this business scenario, the user uses portable terminal by the different content of pages of cellular carrier request visit, and cellular carrier turns back to user terminal with the page of user's request; The user profile that can collect has: user's solicited message, and as when landing, accessed web page sequential scheduling information, and the page info that returns to the user of operator.At this moment, there is a leading calculation of mother and baby's user advertising during the International Children's Day, to throw in marketing message about this brand to the potential user.
The computation process example:
1) accumulation each user's that can collect accession page content information, content of pages is carried out participle, how many frequencys that occurs according to word obtains user's antistop list, and gives each word different weights, namely obtains user's antistop list of the quantification of two-dimentional element group representation; Antistop list as user A be (infantile cough, 0.8), (photography, 0.3), (baby, 0.6) ... }, be designated as T
i
2) make up user's industry consumption feature vector fashion, the mother and baby, number, };
3) make up at 2) in the eigenmatrix of proper vector.Eigenmatrix is the text relevant with proper vector in the text library rule of thumb, applicating text feature extraction technology obtain feature vocabulary (lactation, lovely, green, brand ...), and obtain the weight of each word on associated vector, and shape is as shown in table 1, and the note eigenmatrix is V;
Table 1, eigenmatrix table
| Lactation | Lovely | Green | Brand | ...... | Other | |
| Fashion | v 11 | v 12 | v 13 | v 14 | v 1n | |
| The mother and baby | V 21 | v 22 | v 23 | v 24 | v 2n | |
| Digital | v 31 | v 32 | v 33 | v 34 | v 3n | |
| ...... | ||||||
| Other | v 10，1 | v 10，2 | v 10，3 | v 10，4 | v 10，n |
4) calculate the value of each component of proper vector of each user.Be about to 1) in user's antistop list and 3) in eigenmatrix multiply each other, be designated as U
i=V*T
i, obtain user's proper vector, as U
i=0.1,0.7,0.3 ... }, represent that then user A shows as 0.1 aspect fashion, the mother and baby aspect show as 0.7;
5) corresponding relation between setting customer consumption proper vector and the user tag, rule of thumb set: the value of proper vector on " mother and baby " component judges then that greater than 0.4 o'clock this user is interested in " mother and baby " product, is " mother and baby " potential user;
6) based on this corresponding relation, system marks corresponding consumption label for all users automatically; And to set half damped cycle of user aspect the mother and baby be 1 week, and it is original 1/2nd namely reducing half through a week back user in the influence aspect " mother and baby ", and the attenuation parameter that obtains the user is 0.1; User's proper vector is for a period of time done weighting by attenuation function, try to achieve the user in the proper vector of special time; Be set to t
0Constantly user's proper vector be 0.2,0.8,0.3 ... .};
7) advertiser selects consumer behavior label " mother and baby user concern person " as the directed condition of potential advertisement putting, throws in relevant advertisement to the crowd who satisfies these conditions.Such as, on the webpage that these users browse or the mobile service that uses of such user carry relevant advertisement.
Claims (12)
1. the mobile phone advertisement put-on method based on the customer consumption proper vector the steps include:
1) the mobile phone advertisement publisher server obtains user's mobile Internet browsing content, and it is carried out participle and gives the participle weight, obtains user's antistop list vector;
2) make up the customer consumption proper vector of relative users according to the mobile Internet browsing content that obtains;
3) from advertisement experience text database, extract keyword and set the keyword weight, at each customer consumption proper vector, construct an eigenmatrix then;
4) user's antistop list vector, the eigenmatrix to the user carries out similarity calculating, draws the value of each component of customer consumption proper vector of every user;
5) set mapping relations between customer consumption label and user's the different threshold ranges of consumption feature component of a vector;
6) the mobile phone advertisement publisher server according to the current consumption feature of user each component value of vector and described mapping relations for each user marks corresponding consumption label, and choose the user and carry out advertisement putting according to consuming label.
2. the method for claim 1 is characterized in that the method that makes up described customer consumption proper vector is: according to the mobile Internet browsing content data of obtaining, select several popular industries to make up described customer consumption proper vector as component.
3. method as claimed in claim 1 or 2, the building method that it is characterized in that described eigenmatrix is: with each component of described consumption feature vector row index as eigenmatrix, the keyword that extracts is as the row index of eigenmatrix, and the weight of keyword on respective components is matrix element; Obtain described eigenmatrix.
4. the method for claim 1, the method that it is characterized in that each component value of consumption feature vector that described calculating user is current is: described user's antistop list vector is multiplied each other with described eigenmatrix, draw each component value of consumption feature vector of every user.
5. the method for claim 1 is characterized in that in the step 1), and the mobile Internet that described mobile phone advertisement publisher server also obtains the user is browsed track data and mobile client usage behavior data.
6. method as claimed in claim 5 is characterized in that browsing track data structure user according to mobile Internet browses track consumption feature vector; According to mobile client usage behavior data construct user usage behavior consumption feature vector.
7. method as claimed in claim 6, it is characterized in that described user is browsed track consumption feature vector carries out similarity calculating, obtain the value that the user browses each component of track consumption feature vector, described mobile phone advertisement publisher server is browsed mapping relations between the different threshold ranges of track consumption feature component of a vector according to customer consumption label and user then, for each user marks corresponding consumption label, and choose the user according to the consumption label and carry out advertisement putting.
8. method as claimed in claim 6, it is characterized in that described user's usage behavior consumption feature vector is carried out similarity to be calculated, obtain the value of each component of user's usage behavior consumption feature vector, described mobile phone advertisement publisher server is according to the mapping relations between customer consumption label and the different threshold ranges of user's usage behavior consumption feature component of a vector then, for each user marks corresponding consumption label, and choose the user according to the consumption label and carry out advertisement putting.
9. the method for claim 1 is characterized in that utilizing text feature extraction technique extraction keyword and sets the keyword weight.
10. as claim 1 or 2 or 4 or 6 or 7 or 8 or 9 described methods, it is characterized in that described mobile phone advertisement publisher server is that described each component of customer consumption proper vector is set an attenuation function and half period parameters that declines, the consumption feature vector of user in a period of time done weighting by attenuation function, try to achieve the consumption feature vector value of user in this section period; Described consumption label is according to the value real-time update of customer consumption proper vector component.
11. the method for claim 1 is characterized in that the method that makes up described advertisement experience text database is: at first branch trade is collected the text information about advertisement; Based on the text information of classified, the method for applicating text feature extraction extracts the keyword that the user describes advertisement then, obtains described advertisement experience text database.
12. the method for claim 1 is characterized in that different consumption label correspondences the different threshold range of customer consumption vector, a user is provided with one or more consumption labels; Described threshold range is [0,1].
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210048980.3A CN103295145B (en) | 2012-02-28 | 2012-02-28 | Mobile phone advertising method based on user consumption feature vector |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210048980.3A CN103295145B (en) | 2012-02-28 | 2012-02-28 | Mobile phone advertising method based on user consumption feature vector |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103295145A true CN103295145A (en) | 2013-09-11 |
| CN103295145B CN103295145B (en) | 2017-02-15 |
Family
ID=49095959
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210048980.3A Expired - Fee Related CN103295145B (en) | 2012-02-28 | 2012-02-28 | Mobile phone advertising method based on user consumption feature vector |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103295145B (en) |
Cited By (31)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104090888A (en) * | 2013-12-10 | 2014-10-08 | 深圳市腾讯计算机系统有限公司 | Method and device for analyzing user behavior data |
| CN104750751A (en) * | 2013-12-31 | 2015-07-01 | 华为技术有限公司 | Method and device for annotating trace data |
| CN105023175A (en) * | 2015-07-24 | 2015-11-04 | 金鹃传媒科技股份有限公司 | Online advertisement classified pushing method and system based on consumer behavior data analysis and classification technology |
| WO2016131220A1 (en) * | 2015-02-16 | 2016-08-25 | Lee Ying Chiu Herbert | Characterized wireless signal mobile messaging method and system |
| CN105978729A (en) * | 2016-06-22 | 2016-09-28 | 北京拓明科技有限公司 | System and method for pushing mobile phone information based on user surfing log and position |
| CN106296257A (en) * | 2015-06-11 | 2017-01-04 | 苏宁云商集团股份有限公司 | A kind of fixation of advertisement position put-on method based on user behavior analysis and system |
| CN106407210A (en) * | 2015-07-29 | 2017-02-15 | 阿里巴巴集团控股有限公司 | Display method and device of business object |
| WO2017028093A1 (en) * | 2015-08-16 | 2017-02-23 | 常平 | Advertisement delivery method and advertisement delivery system |
| WO2017028097A1 (en) * | 2015-08-16 | 2017-02-23 | 常平 | Method for alerting information when recommending nearby user, and user recommendation system |
| CN106710012A (en) * | 2015-11-13 | 2017-05-24 | 吕宾乐 | Intelligent parking control method integrating fee collecting and advertisement pushing and intelligent parking control system thereof |
| WO2017124416A1 (en) * | 2016-01-21 | 2017-07-27 | 赵政荣 | Usage data acquisition method of coupon recommendation related technology, and recommendation system |
| WO2017124415A1 (en) * | 2016-01-21 | 2017-07-27 | 赵政荣 | Method for collecting technical data when coupon is recommended and recommendation system |
| WO2017124417A1 (en) * | 2016-01-21 | 2017-07-27 | 赵政荣 | Presentation method for recommending technical information related to coupon, and recommendation system |
| CN107194742A (en) * | 2017-06-12 | 2017-09-22 | 温州中擎信息技术有限公司 | A kind of accurate release platforms of mobile DSP |
| CN107515924A (en) * | 2017-08-24 | 2017-12-26 | 南京农纷期电子商务有限公司 | A kind of page info collection method based on react native |
| CN107578270A (en) * | 2017-08-03 | 2018-01-12 | 中国银联股份有限公司 | A kind of construction method, device and the computing device of financial label |
| CN105023175B (en) * | 2015-07-24 | 2018-08-31 | 金鹃传媒科技股份有限公司 | A kind of online advertisement classification method for pushing and its system based on consumer behaviour data analysis and classification technology |
| CN108510309A (en) * | 2018-02-27 | 2018-09-07 | 阿里巴巴集团控股有限公司 | The method and device that advertisement is recalled |
| CN108805615A (en) * | 2018-05-28 | 2018-11-13 | 广州招点信息科技有限公司 | A kind of preferential movable method for pushing and system based on consumer consumption behavior |
| CN109190898A (en) * | 2018-08-01 | 2019-01-11 | 上海信吾信息技术有限公司 | A kind of method and system dynamically distributing sale assistant director |
| CN109447717A (en) * | 2018-11-12 | 2019-03-08 | 万惠投资管理有限公司 | A kind of determination method and system of label |
| CN109670848A (en) * | 2018-09-11 | 2019-04-23 | 深圳平安财富宝投资咨询有限公司 | Customer segmentation method, user equipment, storage medium and device based on big data |
| CN109896374A (en) * | 2017-12-11 | 2019-06-18 | 日立楼宇技术（广州）有限公司 | Elevator screen methods of exhibiting and system |
| CN110335073A (en) * | 2019-06-27 | 2019-10-15 | 杭州联汇科技股份有限公司 | A kind of accurate method for pushing of Instant Ads excavated based on user behavior data |
| CN110598066A (en) * | 2019-09-10 | 2019-12-20 | 民生科技有限责任公司 | Bank full-name rapid matching method based on word vector expression and cosine similarity |
| CN111177545A (en) * | 2019-12-24 | 2020-05-19 | 百度国际科技（深圳）有限公司 | Advertisement putting method, platform, electronic device and storage medium |
| CN111459992A (en) * | 2020-06-22 | 2020-07-28 | 北京每日优鲜电子商务有限公司 | Information pushing method, electronic equipment and computer readable medium |
| CN112149029A (en) * | 2019-06-26 | 2020-12-29 | 北京百度网讯科技有限公司 | Method and device for determining user value viewing label |
| CN113590951A (en) * | 2021-07-29 | 2021-11-02 | 上海德衡数据科技有限公司 | Perception data processing method and system |
| TWI752303B (en) * | 2018-06-20 | 2022-01-11 | 開曼群島商創新先進技術有限公司 | Method and device for establishing marketing information delivery platform |
| CN117708434A (en) * | 2024-01-09 | 2024-03-15 | 青岛睿哲信息技术有限公司 | Keyword-based user recommendation browsing content generation method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101290631A (en) * | 2008-05-28 | 2008-10-22 | 北京百问百答网络技术有限公司 | Network advertisement automatic delivery method and its system |
| US20090132355A1 (en) * | 2007-11-19 | 2009-05-21 | Att Knowledge Ventures L.P. | System and method for automatically selecting advertising for video data |
| CN101477566A (en) * | 2009-01-19 | 2009-07-08 | 腾讯科技（深圳）有限公司 | Method and apparatus used for putting candidate key words advertisement |
| CN101599160A (en) * | 2009-07-14 | 2009-12-09 | 清华大学 | The method of advertisement delivery and device |
-
2012
- 2012-02-28 CN CN201210048980.3A patent/CN103295145B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090132355A1 (en) * | 2007-11-19 | 2009-05-21 | Att Knowledge Ventures L.P. | System and method for automatically selecting advertising for video data |
| CN101290631A (en) * | 2008-05-28 | 2008-10-22 | 北京百问百答网络技术有限公司 | Network advertisement automatic delivery method and its system |
| CN101477566A (en) * | 2009-01-19 | 2009-07-08 | 腾讯科技（深圳）有限公司 | Method and apparatus used for putting candidate key words advertisement |
| CN101599160A (en) * | 2009-07-14 | 2009-12-09 | 清华大学 | The method of advertisement delivery and device |
Non-Patent Citations (3)
| Title |
|---|
| 刘枚莲: "基于网络消费者偏好预测的推荐算法研究", 《图书情报工作》 * |
| 吴高: "基于数据挖掘的商品资讯投送平台研究与实现", 《中国优秀硕士学位论文全文数据库（信息科技辑）》 * |
| 吴高: "基于数据挖掘的商品资讯投送平台研究与实现", 《中国优秀硕士学位论文全文数据库（信息科技辑）》, no. 8, 15 August 2011 (2011-08-15) * |
Cited By (40)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015085967A1 (en) * | 2013-12-10 | 2015-06-18 | 腾讯科技（深圳）有限公司 | User behavior data analysis method and device |
| CN104090888A (en) * | 2013-12-10 | 2014-10-08 | 深圳市腾讯计算机系统有限公司 | Method and device for analyzing user behavior data |
| CN104750751A (en) * | 2013-12-31 | 2015-07-01 | 华为技术有限公司 | Method and device for annotating trace data |
| CN104750751B (en) * | 2013-12-31 | 2018-02-23 | 华为技术有限公司 | Track data mask method and device |
| WO2016131220A1 (en) * | 2015-02-16 | 2016-08-25 | Lee Ying Chiu Herbert | Characterized wireless signal mobile messaging method and system |
| CN106296257A (en) * | 2015-06-11 | 2017-01-04 | 苏宁云商集团股份有限公司 | A kind of fixation of advertisement position put-on method based on user behavior analysis and system |
| CN105023175B (en) * | 2015-07-24 | 2018-08-31 | 金鹃传媒科技股份有限公司 | A kind of online advertisement classification method for pushing and its system based on consumer behaviour data analysis and classification technology |
| CN105023175A (en) * | 2015-07-24 | 2015-11-04 | 金鹃传媒科技股份有限公司 | Online advertisement classified pushing method and system based on consumer behavior data analysis and classification technology |
| CN106407210B (en) * | 2015-07-29 | 2019-11-26 | 阿里巴巴集团控股有限公司 | A kind of methods of exhibiting and device of business object |
| CN106407210A (en) * | 2015-07-29 | 2017-02-15 | 阿里巴巴集团控股有限公司 | Display method and device of business object |
| WO2017028093A1 (en) * | 2015-08-16 | 2017-02-23 | 常平 | Advertisement delivery method and advertisement delivery system |
| WO2017028097A1 (en) * | 2015-08-16 | 2017-02-23 | 常平 | Method for alerting information when recommending nearby user, and user recommendation system |
| CN106710012A (en) * | 2015-11-13 | 2017-05-24 | 吕宾乐 | Intelligent parking control method integrating fee collecting and advertisement pushing and intelligent parking control system thereof |
| WO2017124417A1 (en) * | 2016-01-21 | 2017-07-27 | 赵政荣 | Presentation method for recommending technical information related to coupon, and recommendation system |
| WO2017124415A1 (en) * | 2016-01-21 | 2017-07-27 | 赵政荣 | Method for collecting technical data when coupon is recommended and recommendation system |
| WO2017124416A1 (en) * | 2016-01-21 | 2017-07-27 | 赵政荣 | Usage data acquisition method of coupon recommendation related technology, and recommendation system |
| CN105978729A (en) * | 2016-06-22 | 2016-09-28 | 北京拓明科技有限公司 | System and method for pushing mobile phone information based on user surfing log and position |
| CN105978729B (en) * | 2016-06-22 | 2019-11-26 | 北京拓明科技有限公司 | A kind of cellphone information supplying system and method based on user's internet log and position |
| CN107194742A (en) * | 2017-06-12 | 2017-09-22 | 温州中擎信息技术有限公司 | A kind of accurate release platforms of mobile DSP |
| CN107578270A (en) * | 2017-08-03 | 2018-01-12 | 中国银联股份有限公司 | A kind of construction method, device and the computing device of financial label |
| CN107515924A (en) * | 2017-08-24 | 2017-12-26 | 南京农纷期电子商务有限公司 | A kind of page info collection method based on react native |
| CN109896374B (en) * | 2017-12-11 | 2021-08-03 | 日立楼宇技术（广州）有限公司 | Elevator screen display method and system |
| CN109896374A (en) * | 2017-12-11 | 2019-06-18 | 日立楼宇技术（广州）有限公司 | Elevator screen methods of exhibiting and system |
| CN108510309A (en) * | 2018-02-27 | 2018-09-07 | 阿里巴巴集团控股有限公司 | The method and device that advertisement is recalled |
| CN108805615A (en) * | 2018-05-28 | 2018-11-13 | 广州招点信息科技有限公司 | A kind of preferential movable method for pushing and system based on consumer consumption behavior |
| CN108805615B (en) * | 2018-05-28 | 2021-09-10 | 广州招点信息科技有限公司 | Preferential activity pushing method and system based on user consumption behaviors |
| TWI752303B (en) * | 2018-06-20 | 2022-01-11 | 開曼群島商創新先進技術有限公司 | Method and device for establishing marketing information delivery platform |
| CN109190898A (en) * | 2018-08-01 | 2019-01-11 | 上海信吾信息技术有限公司 | A kind of method and system dynamically distributing sale assistant director |
| CN109670848A (en) * | 2018-09-11 | 2019-04-23 | 深圳平安财富宝投资咨询有限公司 | Customer segmentation method, user equipment, storage medium and device based on big data |
| CN109447717A (en) * | 2018-11-12 | 2019-03-08 | 万惠投资管理有限公司 | A kind of determination method and system of label |
| CN112149029B (en) * | 2019-06-26 | 2023-07-07 | 北京百度网讯科技有限公司 | Method and device for determining user value viewing labels |
| CN112149029A (en) * | 2019-06-26 | 2020-12-29 | 北京百度网讯科技有限公司 | Method and device for determining user value viewing label |
| CN110335073A (en) * | 2019-06-27 | 2019-10-15 | 杭州联汇科技股份有限公司 | A kind of accurate method for pushing of Instant Ads excavated based on user behavior data |
| CN110598066A (en) * | 2019-09-10 | 2019-12-20 | 民生科技有限责任公司 | Bank full-name rapid matching method based on word vector expression and cosine similarity |
| CN110598066B (en) * | 2019-09-10 | 2022-05-10 | 民生科技有限责任公司 | Bank full-name rapid matching method based on word vector expression and cosine similarity |
| CN111177545B (en) * | 2019-12-24 | 2023-06-09 | 百度国际科技（深圳）有限公司 | Advertisement putting method, platform, electronic equipment and storage medium |
| CN111177545A (en) * | 2019-12-24 | 2020-05-19 | 百度国际科技（深圳）有限公司 | Advertisement putting method, platform, electronic device and storage medium |
| CN111459992A (en) * | 2020-06-22 | 2020-07-28 | 北京每日优鲜电子商务有限公司 | Information pushing method, electronic equipment and computer readable medium |
| CN113590951A (en) * | 2021-07-29 | 2021-11-02 | 上海德衡数据科技有限公司 | Perception data processing method and system |
| CN117708434A (en) * | 2024-01-09 | 2024-03-15 | 青岛睿哲信息技术有限公司 | Keyword-based user recommendation browsing content generation method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103295145B (en) | 2017-02-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103295145B (en) | Mobile phone advertising method based on user consumption feature vector | |
| CN109934619A (en) | User's portrait tag modeling method, apparatus, electronic equipment and readable storage medium storing program for executing | |
| CN104394118B (en) | A kind of method for identifying ID and system | |
| CN110942337A (en) | Accurate tourism marketing method based on internet big data | |
| US8341101B1 (en) | Determining relationships between data items and individuals, and dynamically calculating a metric score based on groups of characteristics | |
| CN106940705A (en) | A kind of method and apparatus for being used to build user's portrait | |
| US20140129331A1 (en) | System and method for predicting momentum of activities of a targeted audience for automatically optimizing placement of promotional items or content in a network environment | |
| CN108805598B (en) | Similarity information determination method, server and computer-readable storage medium | |
| CN105893406A (en) | Group user profiling method and system | |
| CN103778260A (en) | Individualized microblog information recommending system and method | |
| CN105718579A (en) | Information push method based on internet-surfing log mining and user activity recognition | |
| CN109933699A (en) | A kind of construction method and device of academic portrait model | |
| CN103678647A (en) | Method and system for recommending information | |
| US11138249B1 (en) | Systems and methods for the creation, update and use of concept networks to select destinations in artificial intelligence systems | |
| US20180039675A1 (en) | Extended search method and apparatus | |
| CN101431524A (en) | Method and device for implementing oriented network advertisement delivery | |
| CN103106285A (en) | Recommendation algorithm based on information security professional social network platform | |
| CN102033883A (en) | Method, device and system for improving data transmission speed of website | |
| CN105095625B (en) | Clicking rate prediction model method for building up, device and information providing method, system | |
| CN103390194A (en) | Method, device and system for predicating user intention and recommending suggestion | |
| US20100318427A1 (en) | Enhancing database management by search, personal search, advertising, and databases analysis efficiently using core-set implementations | |
| CN103295144A (en) | Mobile internet keyword advertisement putting method | |
| US20130204823A1 (en) | Tools and methods for determining relationship values | |
| CN104751354A (en) | Advertisement cluster screening method | |
| US8478702B1 (en) | Tools and methods for determining semantic relationship indexes |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20170315 Address after: 200335 Shanghai city Yangpu District Guokang Road No. 100 room 1303H Patentee after: Shanghai lion Mdt InfoTech Ltd Address before: 100013 Dongcheng District, Beijing, North Third Ring Road, the world trade center, room A2001, room 36 Patentee before: Beijing Xingyuan Unlimited Media Technology Co., Ltd. |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20170619 Address after: 200092 Shanghai city Yangpu District Guokang Road No. 100 room 1303I Patentee after: Shanghai Ying Ying Mdt InfoTech Ltd Address before: 200335 Shanghai city Yangpu District Guokang Road No. 100 room 1303H Patentee before: Shanghai lion Mdt InfoTech Ltd |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20200608 Address after: 201802 358 Kefu Road, Jiading District, Shanghai_ Room jt5799, Zone E, 1f, building 4, No. 368 Patentee after: Shanghai Shiyu Information Technology Co., Ltd Address before: 200092 Shanghai city Yangpu District Guokang Road No. 100 room 1303I Patentee before: Shanghai Yingying Information Technology Co.,Ltd. |
|
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170215 Termination date: 20200228 |