CN113129078A - Social software advertisement information delivery method based on feature recognition and data visualization analysis - Google Patents
Social software advertisement information delivery method based on feature recognition and data visualization analysis Download PDFInfo
- Publication number
- CN113129078A CN113129078A CN202110506067.2A CN202110506067A CN113129078A CN 113129078 A CN113129078 A CN 113129078A CN 202110506067 A CN202110506067 A CN 202110506067A CN 113129078 A CN113129078 A CN 113129078A
- Authority
- CN
- China
- Prior art keywords
- advertisement
- age group
- user
- advertisements
- preference
- 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.)
- Withdrawn
Links
Images
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
- G06Q30/0257—User requested
- G06Q30/0258—Registration
-
- 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)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a social software advertisement information delivery method based on feature recognition and data visual analysis, which determines the comprehensive preference advertisement category corresponding to each age group of users by carrying out age group user division on each user registered on social software and analyzing the preference advertisement category corresponding to each user in each age group on the social software, thereby carrying out intelligent delivery of advertisements corresponding to the comprehensive preference advertisement category on the social software to all users in the corresponding age group according to the comprehensive preference advertisement category corresponding to each age group of users, realizing accurate and high matching delivery of user preference advertisements on the social software, having the characteristics of high delivery intelligence level and strong practicability, improving the matching degree with the user preference advertisement category, making up the deficiency of coarse delivery of advertisements of the social software, enhancing the advertisement experience of users watching advertisements on the social software, and the advertisement putting effect is also improved.
Description
Technical Field
The invention belongs to the technical field of advertisement putting, relates to a social software advertisement putting technology, and particularly relates to a social software advertisement information putting method based on feature recognition and data visualization analysis.
Background
In recent years, with the rapid development of mobile internet, social software, such as microblog WeChat and Facebook, is more and more popular, and on one hand, the social software provides a convenient communication platform for people, and on the other hand, the social software becomes a mobile advertisement delivery platform which is highly popular with advertisers and brand owners by virtue of the huge user groups and the remarkable interaction attributes.
However, most of the advertisement putting modes of the current social software are rough putting, that is, the advertisement characteristic of the preference of the user group is not considered, so that the matching degree of the advertisement characteristic of the preference of the user is not high, and therefore, on one hand, in the process of using the social software, the rough putting advertisement appears in real time to bring advertisement disturbance to the user, and the user experience is not good; on the other hand, money of advertisers is wasted, meanwhile, an expected delivery effect cannot be achieved, and the accurate high-matching delivery requirement of the user preference advertisement on the social software is difficult to achieve.
Disclosure of Invention
In order to overcome the defects in the background art, the invention provides a social software advertisement information delivery method based on feature recognition and data visualization analysis, which determines the comprehensive preference advertisement category corresponding to each age-stage user by performing age-stage division on each user registered on the social software and analyzing the preference advertisement category corresponding to each user in each age-stage on the social software, so that intelligent delivery of advertisements corresponding to the comprehensive preference advertisement category is performed on the social software for all users in the corresponding age-stage according to the comprehensive preference advertisement category corresponding to each age-stage user, and the accurate high-matching delivery requirement of the user preference advertisements on the social software is realized.
The purpose of the invention can be realized by the following technical scheme:
the social software advertisement information delivery method based on feature recognition and data visualization analysis comprises the following steps;
s1, acquiring the age of a user registered by social software: acquiring all users correspondingly registered on the social software, and acquiring the age corresponding to each user according to the registered account corresponding to each user;
s2, user classification: dividing the ages corresponding to the users according to a set age division mode to obtain divided age groups, numbering the divided age groups according to the sequence of the ages from small to large, and respectively marking the divided age groups as A, B, a.
S3, obtaining advertisement types and viewing parameters: screening advertisements pushed on the social software of each user in each age group in a preset time period according to the corresponding registered account number of each user in each age group on the social software, numbering the screened advertisements according to the sequence of pushing time points, and respectively marking the advertisements as 1,2,. once, j,. once, m so as to obtain the advertisement types and the viewing parameters corresponding to the advertisements;
s4, viewing interest index statistics: counting viewing interest indexes corresponding to the advertisements on the social software of the users in all age groups according to the viewing parameters corresponding to the advertisements;
s5, analyzing the preferred advertisement type and the preferred advertisement display form: summarizing and classifying advertisements corresponding to the same advertisement category on social software of each user in each age group according to the advertisement category corresponding to each advertisement, so as to obtain each advertisement corresponding to each same advertisement category of each user in each age group, and further analyzing the preference advertisement category corresponding to each user in each age group and the preference advertisement display form corresponding to the preference advertisement category according to the above;
s6, determining the comprehensive preference advertisement types of the age group users: analyzing the preferred advertisement categories corresponding to the users in all age groups, and determining the comprehensive preferred advertisement categories corresponding to the users in all age groups;
s7, intelligent advertisement putting for age group users: and carrying out intelligent advertisement putting on the social software for all users in the corresponding age bracket according to the comprehensive preferred advertisement category corresponding to the user in each age bracket and the preferred advertisement display form corresponding to the preferred advertisement category corresponding to each user in each age bracket.
Further, in S3, each advertisement pushed on the social software of each user corresponding to each age group within a preset time period is screened according to the registered account corresponding to each user corresponding to each age group on the social software, and the specific screening method performs the following steps:
h1, acquiring all advertisements pushed on the social software of each user according to the registered accounts of the users corresponding to each age bracket on the social software, and acquiring the pushing time points corresponding to the advertisements;
h2, acquiring a screening starting time point and a screening ending time point corresponding to a preset time period;
h3, comparing the pushing time point corresponding to each advertisement pushed on the social software of each user with the screening starting time point and the screening ending time point corresponding to the preset time period, if the pushing time point corresponding to a certain advertisement is within the screening starting time point and the screening ending time point corresponding to the preset time period, retaining the advertisement, if the pushing time point corresponding to a certain advertisement is not within the screening starting time point and the screening ending time point corresponding to the preset time period, removing the advertisement, and thus the retained advertisements are the advertisements pushed on the social software of each user corresponding to each age group in the preset time period.
Further, the viewing parameters comprise viewing duration, like parameters and comment parameters, wherein the like parameters comprise like and not like, and the comment parameters comprise comment and not comment.
Further, in S4, the viewing interest index corresponding to each advertisement on the social software of each user in each age group is counted according to the viewing parameter corresponding to each advertisement, and the specific statistical process is as follows:
p1, forming advertisement viewing parameter set R of each age group user by viewing parameters corresponding to each advertisement pushed on the social software of each user in each age groupIi(rIi w1,rIi w2,...,rIi wj,...,rIi wm)，rIi wj is a numerical value corresponding to a viewing parameter of a jth advertisement pushed on social software of an ith user in the ith age group, w is a viewing parameter, and w is f1, f2 and f3 which are respectively expressed as a viewing duration, a praise parameter and a comment parameter;
p2, extracting praise parameters and comment parameters corresponding to each advertisement from the advertisement viewing parameter set of the users in each age group respectively, and comparing the praise interest parameters and the comment interest parameters with praise interest weight coefficients corresponding to the set praise parameters and the comment interest weight coefficients corresponding to the comment parameters respectively to obtain the praise interest weight coefficients and the comment interest weight coefficients corresponding to the advertisements;
p3, counting the viewing interest indexes corresponding to the advertisements on the social software of the users in each age group according to the viewing duration, the praise interest weight coefficient and the comment interest weight coefficient corresponding to each advertisement, wherein the calculation formula is
ηIij is the viewing interest index, alpha, corresponding to the jth advertisement on the social software of the ith user in the ith age groupIij、βIij、rIi f1j is respectively expressed as a praise interest weight coefficient, a comment interest weight coefficient and a watching duration corresponding to the jth advertisement on the social software of the ith user in the ith age group.
Further, the specific analysis method for the preferred advertisement categories corresponding to the users in each age group in S5 includes the following steps:
d1, counting the number of the same advertisement types according to the obtained advertisements corresponding to the same advertisement types corresponding to the users in the age groups, wherein the same advertisement types are marked as candidate advertisement types, and the counted candidate advertisement types are numbered and marked as 1,2, a, b, k, respectively, at the moment, counting the number of the advertisements corresponding to the candidate advertisement types and the number corresponding to each advertisement of the users in the age groups, wherein the number corresponding to each advertisement can be marked as 1,2, a, b, k;
d2, obtaining the watching interest index corresponding to each advertisement according to the number corresponding to each advertisement of each candidate advertisement category corresponding to each user in each age group;
d3, calculating the preference coefficient of each candidate advertisement category corresponding to each user in each age group according to the advertisement quantity of each candidate advertisement category corresponding to each user in each age group and the viewing interest index corresponding to each advertisement;
and D4, sequencing the candidate advertisement categories corresponding to the users in each age group according to the preference coefficients corresponding to the candidate advertisement categories from large to small to obtain the sequencing result of the candidate advertisement categories corresponding to the users in each age group, and further extracting the candidate advertisement category ranked at the first position from the sequencing result to be used as the preference advertisement category corresponding to the users in each age group.
Further, the calculation formula of the preference coefficient of each candidate advertisement category corresponding to each user in each age group is
σIia is expressed as a preference coefficient of the ith user in the ith age group corresponding to the ith candidate advertisement category, qIia represents the number of advertisements corresponding to the a-th candidate advertisement category for the ith user in the I-th age group, etaIi ab represents the viewing interest index corresponding to the b-th advertisement corresponding to the a-th candidate advertisement category corresponding to the ith user in the I-th age group.
Further, in S5, a specific analysis method of the preferred advertisement display form corresponding to the preferred advertisement category corresponding to each user in each age group is as follows:
g1, counting the numbers of the advertisements corresponding to the preferred advertisement categories of the users in each age group according to the preferred advertisement categories corresponding to the users in each age group, and extracting the praise parameters and comment parameters of the advertisements corresponding to the preferred advertisement categories of the users in each age group from the advertisement watching parameter sets of the users in each age group through the advertisement numbers;
g2, respectively obtaining the advertisement display form of each advertisement corresponding to the preferred advertisement category of each user in each age group;
g3, comparing the advertisement display forms of the advertisements corresponding to the preferential advertisement types of the same user in each age group, classifying the advertisements corresponding to the same advertisement display forms to obtain the advertisements corresponding to the same advertisement display forms corresponding to the preferential advertisement types of the users in each age group, counting the number of the same advertisement display forms, numbering the same advertisement display forms, and marking the same advertisement display forms as 1,2, 1, c, 1, v;
g4, counting the total number of advertisements in the same advertisement display form corresponding to the preference advertisement type of each user in each age group, and counting the advertisement number corresponding to the advertisement display form corresponding to the preference advertisement type of each user in each age group, the advertisement number corresponding to the comment and the comment according to the comment parameters and the preference advertisement type of each user in each age group corresponding to each advertisement display form;
g5, counting preference coefficients of the preference advertisement types of the users in the age groups corresponding to the same advertisement display forms according to the total advertisement quantity, the advertisement quantity corresponding to praise, the advertisement quantity corresponding to comment and the advertisement quantity corresponding to praise and comment of the preference advertisement types of the users in the age groups, wherein the calculation formula is that
ξIic is a preference coefficient, X, of the preferred advertisement category of the ith user in the ith age group corresponding to the display form of the ith same advertisementIic、YIic、OIic、ZIic, respectively representing the number of advertisements corresponding to the liking of the ith user in the ith age group corresponding to the c th same advertisement display form, the number of advertisements corresponding to the comment, the number of advertisements corresponding to both the liking and the comment, and the total number of the advertisements;
g6, according to the preference coefficient of the preference advertisement category of each user in each age group corresponding to each same advertisement display form, screening out the same advertisement display form with the maximum preference coefficient as the preference advertisement display form corresponding to the preference advertisement category of each user in each age group.
Further, the advertisement presentation forms include a text form, a picture form, a video form and a combined form.
Further, in the step S6, the comprehensive preferred advertisement category corresponding to each age group user is determined, and the specific determination method is as follows:
u1, comparing the preference advertisement categories corresponding to each user in the same age group in sequence according to the serial number sequence of the age group, and classifying the users corresponding to the same preference advertisement categories to obtain the users corresponding to the same preference advertisement categories in each age group;
u2, counting the number of users corresponding to the same preferred advertisement categories of each age group, and extracting the same preferred advertisement category with the largest number of users as the comprehensive preferred advertisement category corresponding to the users of each age group.
Further, in S7, according to the comprehensive preferred advertisement category corresponding to each age group of users and the preferred advertisement display form corresponding to the preferred advertisement category corresponding to each user in each age group, performing intelligent advertisement delivery to all users in the corresponding age group on the social software, where the specific delivery method includes the following steps:
e1, screening each advertisement corresponding to the comprehensive preference advertisement type from the advertisement database according to the comprehensive preference advertisement type corresponding to each age group user to form a comprehensive preference advertisement type set, and acquiring the advertisement display form corresponding to each advertisement in the comprehensive preference advertisement type set;
e2, extracting advertisements meeting the preference advertisement display form corresponding to the preference advertisement type corresponding to each user from all advertisements in the comprehensive preference advertisement type set corresponding to each age group according to the preference advertisement display form corresponding to the preference advertisement type corresponding to each user in each age group, and marking the advertisements as target advertisements so as to obtain the target advertisements of the comprehensive preference advertisement type corresponding to each user in each age group;
e3, carrying out targeted advertisement putting of the comprehensive preference advertisement category corresponding to the user in each age group to the social software corresponding to each user in each age group.
The invention has the following beneficial effects:
(1) the invention divides users in age groups registered on the social software, screens advertisements pushed on the social software of each user in each age group in a preset time period according to the registered account number of each user on the social software, analyzes the advertisements simultaneously to obtain the corresponding preference advertisement categories of each user in each age group on the social software, and further determines the corresponding comprehensive preference advertisement categories of each user in each age group, thereby performing intelligent delivery of advertisements corresponding to the comprehensive preference advertisement categories on the social software to all users in the corresponding age groups according to the corresponding comprehensive preference advertisement categories of each user in each age group, realizing accurate and high-matching delivery of the user preference advertisements, having the characteristics of high delivery intelligence level and strong practicability, improving the matching degree with the user preference advertisement categories, and making up the defects of the rough delivery of the advertisements of the social software, the advertisement experience of the user in watching the advertisement in the social software is enhanced, and the advertisement putting effect is improved.
(2) According to the method, the corresponding preference advertisement type of each user in each age group is analyzed, meanwhile, the preference advertisement display form corresponding to the preference advertisement type of each user is analyzed, so that in the process of putting the advertisement corresponding to the comprehensive preference advertisement type of all users in each age group, the targeted personalized putting is performed on the advertisement display form of the put advertisement according to the preference advertisement display form corresponding to the preference advertisement type of each user in each age group, the humanization level of the putting of the advertisement corresponding to the comprehensive preference advertisement type is improved, the comfort level of the user for watching the advertisement on the social software is improved, the advertisement experience of the user for watching the advertisement on the social software is further optimized, and the putting level of the advertisement of the social software is improved.
Drawings
The invention is further illustrated by means of the attached drawings, but the embodiments in the drawings do not constitute any limitation to the invention, and for a person skilled in the art, other drawings can be obtained on the basis of the following drawings without inventive effort.
FIG. 1 is a flow chart of the method steps of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, the social software advertising information delivery method based on feature recognition and data visualization analysis comprises the following steps;
s1, acquiring the age of a user registered by social software: acquiring all users correspondingly registered on the social software, and acquiring the age corresponding to each user according to the registered account corresponding to each user;
s2, user classification: dividing the ages corresponding to the users according to a set age division mode to obtain divided age groups, numbering the divided age groups according to the sequence of the ages from small to large, and respectively marking the divided age groups as A, B, a.
According to the method, the age groups of the users registered on the social software are classified, so that a delivery basis is provided for the accurate advertisement delivery of the user groups corresponding to the age groups;
s3, obtaining advertisement types and viewing parameters: screening advertisements pushed by the social software of each user in each age group in a preset time period according to the corresponding registered account number of each user in each age group on the social software, wherein the specific screening method comprises the following steps:
h1, acquiring all advertisements pushed on the social software of each user according to the registered accounts of the users corresponding to each age bracket on the social software, and acquiring the pushing time points corresponding to the advertisements;
h2, acquiring a screening starting time point and a screening ending time point corresponding to a preset time period;
h3, comparing the pushing time point corresponding to each advertisement pushed on the social software of each user with the screening starting time point and the screening ending time point corresponding to the preset time period, if the pushing time point corresponding to a certain advertisement is within the screening starting time point and the screening ending time point corresponding to the preset time period, retaining the advertisement, if the pushing time point corresponding to a certain advertisement is not within the screening starting time point and the screening ending time point corresponding to the preset time period, rejecting the advertisement, and thus, the retained advertisements are the advertisements pushed on the social software of each user corresponding to each age group in the preset time period;
numbering the screened advertisements according to the sequence of the pushing time points, and respectively marking the advertisements as 1,2, a.
S4, viewing interest index statistics: and counting the viewing interest index corresponding to each advertisement on the social software of each user in each age group according to the viewing parameter corresponding to each advertisement, wherein the specific counting process is as follows:
p1, forming advertisement viewing parameter set R of each age group user by viewing parameters corresponding to each advertisement pushed on the social software of each user in each age groupIi(rIi w1,rIi w2,...,rIi wj,...,rIi wm)，rIi wj is a numerical value corresponding to a viewing parameter of a jth advertisement pushed on social software of an ith user in the ith age group, w is a viewing parameter, and w is f1, f2 and f3 which are respectively expressed as a viewing duration, a praise parameter and a comment parameter;
p2, extracting praise parameters and comment parameters corresponding to each advertisement from the advertisement viewing parameter set of the users in each age group respectively, and comparing the praise interest parameters and the comment interest parameters with praise interest weight coefficients corresponding to the set praise parameters and the comment interest weight coefficients corresponding to the comment parameters respectively to obtain the praise interest weight coefficients and the comment interest weight coefficients corresponding to the advertisements;
p3, counting the viewing interest indexes corresponding to the advertisements on the social software of the users in each age group according to the viewing duration, the praise interest weight coefficient and the comment interest weight coefficient corresponding to each advertisement, wherein the calculation formula is
ηIij is the viewing interest index, alpha, corresponding to the jth advertisement on the social software of the ith user in the ith age groupIij、βIij、rIi f1j is respectively expressed as a praise interest weight coefficient, a comment interest weight coefficient and watching duration corresponding to the jth advertisement on the social software of the ith user in the ith age group;
in the embodiment, the watching duration, the praise parameter and the comment parameter of the advertisement are fused in the process of counting the watching interest indexes corresponding to the advertisements on the social software of each user in each age group, so that the counting result is more comprehensive and reliable, and the problems of one-sided counting and low reliability caused by counting the watching interest indexes only according to the watching duration of the advertisement are solved;
s5, analyzing the preferred advertisement type and the preferred advertisement display form: the method comprises the following steps of summarizing and classifying advertisements corresponding to the same advertisement category on social software of each user in each age group according to the advertisement category corresponding to each advertisement, obtaining each advertisement corresponding to each same advertisement category of each user in each age group, and analyzing the preferred advertisement category corresponding to each user in each age group and the preferred advertisement display form corresponding to the preferred advertisement category, wherein the specific analysis method of the preferred advertisement category corresponding to each user in each age group comprises the following steps:
d1, counting the number of the same advertisement types according to the obtained advertisements corresponding to the same advertisement types corresponding to the users in the age groups, wherein the same advertisement types are marked as candidate advertisement types, and the counted candidate advertisement types are numbered and marked as 1,2, a, b, k, respectively, at the moment, counting the number of the advertisements corresponding to the candidate advertisement types and the number corresponding to each advertisement of the users in the age groups, wherein the number corresponding to each advertisement can be marked as 1,2, a, b, k;
d2, obtaining the watching interest index corresponding to each advertisement according to the number corresponding to each advertisement of each candidate advertisement category corresponding to each user in each age group;
d3 advertisement quantity and advertisement category corresponding to each candidate advertisement category according to each user in each age groupThe watching interest index corresponding to each advertisement counts the preference coefficient of each candidate advertisement category corresponding to each user in each age group
σIia is expressed as a preference coefficient of the ith user in the ith age group corresponding to the ith candidate advertisement category, qIia represents the number of advertisements corresponding to the a-th candidate advertisement category for the ith user in the I-th age group, etaIi ab represents the viewing interest index corresponding to the b-th advertisement corresponding to the a-th candidate advertisement category of the ith user in the I-th age group;
d4, sorting the candidate advertisement categories corresponding to the users in each age group according to the preference coefficients corresponding to the candidate advertisement categories from large to small to obtain the sorting results of the candidate advertisement categories corresponding to the users in each age group, and further extracting the candidate advertisement category ranked at the first position from the sorting results to serve as the preference advertisement category corresponding to the users in each age group;
in the embodiment, the characteristic identification analysis is carried out on the preferred advertisement categories corresponding to the users in all age groups on the social software, so that a reference basis is provided for determining the comprehensive preferred advertisement categories corresponding to the users in all age groups;
the specific analysis method of the preferred advertisement display form corresponding to the preferred advertisement category corresponding to each user in each age group is as follows:
g1, counting the numbers of the advertisements corresponding to the preferred advertisement categories of the users in each age group according to the preferred advertisement categories corresponding to the users in each age group, and extracting the praise parameters and comment parameters of the advertisements corresponding to the preferred advertisement categories of the users in each age group from the advertisement watching parameter sets of the users in each age group through the advertisement numbers;
g2, respectively obtaining the advertisement display form of each advertisement corresponding to the preferred advertisement category of each user in each age group;
g3, comparing the advertisement display forms of the advertisements corresponding to the preferential advertisement types of the same user in each age group, classifying the advertisements corresponding to the same advertisement display forms to obtain the advertisements corresponding to the same advertisement display forms corresponding to the preferential advertisement types of the users in each age group, counting the number of the same advertisement display forms, numbering the same advertisement display forms, and marking the same advertisement display forms as 1,2, 1, c, 1, v;
g4, counting the total number of advertisements in the same advertisement display form corresponding to the preference advertisement type of each user in each age group, and counting the advertisement number corresponding to the advertisement display form corresponding to the preference advertisement type of each user in each age group, the advertisement number corresponding to the comment and the comment according to the comment parameters and the preference advertisement type of each user in each age group corresponding to each advertisement display form;
g5, counting preference coefficients of the preference advertisement types of the users in the age groups corresponding to the same advertisement display forms according to the total advertisement quantity, the advertisement quantity corresponding to praise, the advertisement quantity corresponding to comment and the advertisement quantity corresponding to praise and comment of the preference advertisement types of the users in the age groups, wherein the calculation formula is that
ξIic is a preference coefficient, X, of the preferred advertisement category of the ith user in the ith age group corresponding to the display form of the ith same advertisementIic、YIic、OIic、ZIic, respectively representing the number of advertisements corresponding to the liking of the ith user in the ith age group corresponding to the c th same advertisement display form, the number of advertisements corresponding to the comment, the number of advertisements corresponding to both the liking and the comment, and the total number of the advertisements;
g6, according to the preference coefficient of the preference advertisement category of each user in each age group corresponding to each same advertisement display form, screening out the same advertisement display form with the maximum preference coefficient as the preference advertisement display form corresponding to the preference advertisement category of each user in each age group;
in the embodiment, by analyzing the preferred advertisement display forms corresponding to the preferred advertisement types corresponding to the users in the age groups, a delivery basis is provided for the subsequent targeted personalized delivery of the preferred advertisement display forms corresponding to the comprehensive preferred advertisement types to all the users in the age groups;
s6, determining the comprehensive preference advertisement types of the age group users: analyzing the preferred advertisement categories corresponding to the users in all the age groups, and determining the comprehensive preferred advertisement categories corresponding to the users in all the age groups, wherein the specific determination method comprises the following steps:
u1, comparing the preference advertisement categories corresponding to each user in the same age group in sequence according to the serial number sequence of the age group, and classifying the users corresponding to the same preference advertisement categories to obtain the users corresponding to the same preference advertisement categories in each age group;
u2, counting the number of users corresponding to the same preferred advertisement categories of each age group, and extracting the same preferred advertisement category with the largest number of users as the comprehensive preferred advertisement category corresponding to the users of each age group;
according to the method, the comprehensive preference advertisement category corresponding to the users in each age group is determined according to the preference advertisement category corresponding to each user in each age group on the social software, so that the intelligent delivery of the advertisement corresponding to the comprehensive preference advertisement category is carried out on the social software for all the users in the corresponding age group according to the comprehensive preference advertisement category corresponding to each user in each age group, the accurate high-matching delivery of the user preference advertisement is realized, the method has the characteristics of high delivery intelligence level and strong practicability, the matching degree with the user preference advertisement category is improved, the defects of the coarse delivery of the advertisement of the social software are overcome, the advertisement experience of the users watching the advertisement in the social software is enhanced, and the delivery effect of the advertisement is also improved;
s7, intelligent advertisement putting for age group users: according to the comprehensive preferred advertisement category corresponding to each age group of users and the preferred advertisement display form corresponding to the preferred advertisement category corresponding to each user in each age group, carrying out intelligent advertisement putting on the social software for all users in the corresponding age group, wherein the specific putting method comprises the following steps:
e1, screening each advertisement corresponding to the comprehensive preference advertisement type from the advertisement database according to the comprehensive preference advertisement type corresponding to each age group user to form a comprehensive preference advertisement type set, and acquiring the advertisement display form corresponding to each advertisement in the comprehensive preference advertisement type set;
e2, extracting advertisements meeting the preference advertisement display form corresponding to the preference advertisement type corresponding to each user from all advertisements in the comprehensive preference advertisement type set corresponding to each age group according to the preference advertisement display form corresponding to the preference advertisement type corresponding to each user in each age group, and marking the advertisements as target advertisements so as to obtain the target advertisements of the comprehensive preference advertisement type corresponding to each user in each age group;
e3, carrying out targeted advertisement putting of the comprehensive preference advertisement category corresponding to the user in each age group to the social software corresponding to each user in each age group.
In the embodiment, in the process of putting advertisements corresponding to the comprehensive preference advertisement types to all users in all age groups, targeted personalized putting is carried out on the advertisement display forms of the put advertisements according to the preference advertisement display forms corresponding to the preference advertisement types of the users in all age groups, the humanization level of putting the advertisements corresponding to the comprehensive preference advertisement types is improved, the comfort level of watching the advertisements on social software by the users is improved, the advertisement experience feeling of watching the advertisements on the social software by the users is further optimized, and the putting level of the advertisements of the social software is improved.
The foregoing is merely exemplary and illustrative of the present invention and various modifications, additions and substitutions may be made by those skilled in the art to the specific embodiments described without departing from the scope of the invention as defined in the following claims.
Claims (10)
1. The social software advertisement information delivery method based on feature recognition and data visualization analysis is characterized by comprising the following steps;
s1, acquiring the age of a user registered by social software: acquiring all users correspondingly registered on the social software, and acquiring the age corresponding to each user according to the registered account corresponding to each user;
s2, user classification: dividing the ages corresponding to the users according to a set age division mode to obtain divided age groups, numbering the divided age groups according to the sequence of the ages from small to large, and respectively marking the divided age groups as A, B, a.
S3, obtaining advertisement types and viewing parameters: screening advertisements pushed on the social software of each user in each age group in a preset time period according to the corresponding registered account number of each user in each age group on the social software, numbering the screened advertisements according to the sequence of pushing time points, and respectively marking the advertisements as 1,2,. once, j,. once, m so as to obtain the advertisement types and the viewing parameters corresponding to the advertisements;
s4, viewing interest index statistics: counting viewing interest indexes corresponding to the advertisements on the social software of the users in all age groups according to the viewing parameters corresponding to the advertisements;
s5, analyzing the preferred advertisement type and the preferred advertisement display form: summarizing and classifying advertisements corresponding to the same advertisement category on social software of each user in each age group according to the advertisement category corresponding to each advertisement, so as to obtain each advertisement corresponding to each same advertisement category of each user in each age group, and further analyzing the preference advertisement category corresponding to each user in each age group and the preference advertisement display form corresponding to the preference advertisement category according to the above;
s6, determining the comprehensive preference advertisement types of the age group users: analyzing the preferred advertisement categories corresponding to the users in all age groups, and determining the comprehensive preferred advertisement categories corresponding to the users in all age groups;
s7, intelligent advertisement putting for age group users: and carrying out intelligent advertisement putting on the social software for all users in the corresponding age bracket according to the comprehensive preferred advertisement category corresponding to the user in each age bracket and the preferred advertisement display form corresponding to the preferred advertisement category corresponding to each user in each age bracket.
2. The method for social software advertising information based on feature recognition and data visualization analysis as claimed in claim 1, wherein: in S3, screening advertisements pushed by the social software of each user corresponding to each age group within a preset time period according to the registered account corresponding to each user corresponding to each age group on the social software, where the specific screening method includes the following steps:
h1, acquiring all advertisements pushed on the social software of each user according to the registered accounts of the users corresponding to each age bracket on the social software, and acquiring the pushing time points corresponding to the advertisements;
h2, acquiring a screening starting time point and a screening ending time point corresponding to a preset time period;
h3, comparing the pushing time point corresponding to each advertisement pushed on the social software of each user with the screening starting time point and the screening ending time point corresponding to the preset time period, if the pushing time point corresponding to a certain advertisement is within the screening starting time point and the screening ending time point corresponding to the preset time period, retaining the advertisement, if the pushing time point corresponding to a certain advertisement is not within the screening starting time point and the screening ending time point corresponding to the preset time period, removing the advertisement, and thus the retained advertisements are the advertisements pushed on the social software of each user corresponding to each age group in the preset time period.
3. The method for social software advertising information based on feature recognition and data visualization analysis as claimed in claim 1, wherein: the viewing parameters comprise viewing duration, praise parameters and comment parameters, wherein the praise parameters comprise praise and non-praise, and the comment parameters comprise comment and non-comment.
4. The method for social software advertising information based on feature recognition and data visualization analysis as claimed in claim 1, wherein: in S4, the viewing interest index corresponding to each advertisement on the social software of each user in each age group is counted according to the viewing parameter corresponding to each advertisement, and the specific counting process is as follows:
p1, forming advertisement viewing parameter set R of each age group user by viewing parameters corresponding to each advertisement pushed on the social software of each user in each age groupIi(rIi w1,rIi w2,...,rIi wj,...,rIi wm)，rIi wj is a numerical value corresponding to a viewing parameter of a jth advertisement pushed on social software of an ith user in the ith age group, w is a viewing parameter, and w is f1, f2 and f3 which are respectively expressed as a viewing duration, a praise parameter and a comment parameter;
p2, extracting praise parameters and comment parameters corresponding to each advertisement from the advertisement viewing parameter set of the users in each age group respectively, and comparing the praise interest parameters and the comment interest parameters with praise interest weight coefficients corresponding to the set praise parameters and the comment interest weight coefficients corresponding to the comment parameters respectively to obtain the praise interest weight coefficients and the comment interest weight coefficients corresponding to the advertisements;
p3, counting the viewing interest indexes corresponding to the advertisements on the social software of the users in each age group according to the viewing duration, the praise interest weight coefficient and the comment interest weight coefficient corresponding to each advertisement, wherein the calculation formula is
ηIij is the viewing interest index, alpha, corresponding to the jth advertisement on the social software of the ith user in the ith age groupIij、βIij、rIi f1j is respectively expressed as a praise interest weight coefficient, a comment interest weight coefficient and a watching duration corresponding to the jth advertisement on the social software of the ith user in the ith age group.
5. The method for social software advertising information based on feature recognition and data visualization analysis as claimed in claim 1, wherein: the specific analysis method for the preferred advertisement categories corresponding to the users in the age groups in S5 includes the following steps:
d1, counting the number of the same advertisement types according to the obtained advertisements corresponding to the same advertisement types corresponding to the users in the age groups, wherein the same advertisement types are marked as candidate advertisement types, and the counted candidate advertisement types are numbered and marked as 1,2, a, b, k, respectively, at the moment, counting the number of the advertisements corresponding to the candidate advertisement types and the number corresponding to each advertisement of the users in the age groups, wherein the number corresponding to each advertisement can be marked as 1,2, a, b, k;
d2, obtaining the watching interest index corresponding to each advertisement according to the number corresponding to each advertisement of each candidate advertisement category corresponding to each user in each age group;
d3, calculating the preference coefficient of each candidate advertisement category corresponding to each user in each age group according to the advertisement quantity of each candidate advertisement category corresponding to each user in each age group and the viewing interest index corresponding to each advertisement;
and D4, sequencing the candidate advertisement categories corresponding to the users in each age group according to the preference coefficients corresponding to the candidate advertisement categories from large to small to obtain the sequencing result of the candidate advertisement categories corresponding to the users in each age group, and further extracting the candidate advertisement category ranked at the first position from the sequencing result to be used as the preference advertisement category corresponding to the users in each age group.
6. The method for social software advertising information based on feature recognition and data visualization analysis according to claim 5, wherein: the calculation formula of the preference coefficient of each candidate advertisement category corresponding to each user in each age group is
σIia is expressed as a preference coefficient of the ith user in the ith age group corresponding to the ith candidate advertisement category, qIia represents the number of advertisements corresponding to the a-th candidate advertisement category for the ith user in the I-th age group, etaIi ab tableAnd showing the viewing interest index corresponding to the b-th advertisement corresponding to the a-th candidate advertisement category by the ith user in the I-th age group.
7. The method for social software advertising information based on feature recognition and data visualization analysis as claimed in claim 1, wherein: the specific analysis method of the preferred advertisement display form corresponding to the preferred advertisement category corresponding to each user in each age group in S5 is as follows:
g1, counting the numbers of the advertisements corresponding to the preferred advertisement categories of the users in each age group according to the preferred advertisement categories corresponding to the users in each age group, and extracting the praise parameters and comment parameters of the advertisements corresponding to the preferred advertisement categories of the users in each age group from the advertisement watching parameter sets of the users in each age group through the advertisement numbers;
g2, respectively obtaining the advertisement display form of each advertisement corresponding to the preferred advertisement category of each user in each age group;
g3, comparing the advertisement display forms of the advertisements corresponding to the preferential advertisement types of the same user in each age group, classifying the advertisements corresponding to the same advertisement display forms to obtain the advertisements corresponding to the same advertisement display forms corresponding to the preferential advertisement types of the users in each age group, counting the number of the same advertisement display forms, numbering the same advertisement display forms, and marking the same advertisement display forms as 1,2, 1, c, 1, v;
g4, counting the total number of advertisements in the same advertisement display form corresponding to the preference advertisement type of each user in each age group, and counting the advertisement number corresponding to the advertisement display form corresponding to the preference advertisement type of each user in each age group, the advertisement number corresponding to the comment and the comment according to the comment parameters and the preference advertisement type of each user in each age group corresponding to each advertisement display form;
g5 total number of advertisements and praise corresponding advertisements in the same advertisement display form according to the preference advertisement category of each user in each age groupCounting the number of advertisements corresponding to the comments and the like, and counting the preference coefficients of the preferred advertisement types of the users corresponding to the same advertisement display forms in all age groups, wherein the calculation formula is
ξIic is a preference coefficient, X, of the preferred advertisement category of the ith user in the ith age group corresponding to the display form of the ith same advertisementIic、YIic、OIic、ZIic, respectively representing the number of advertisements corresponding to the liking of the ith user in the ith age group corresponding to the c th same advertisement display form, the number of advertisements corresponding to the comment, the number of advertisements corresponding to both the liking and the comment, and the total number of the advertisements;
g6, according to the preference coefficient of the preference advertisement category of each user in each age group corresponding to each same advertisement display form, screening out the same advertisement display form with the maximum preference coefficient as the preference advertisement display form corresponding to the preference advertisement category of each user in each age group.
8. The method for social software advertising information based on feature recognition and data visualization analysis as claimed in claim 7, wherein: the advertisement display forms comprise a text form, a picture form, a video form and a picture and text combined form.
9. The method for social software advertising information based on feature recognition and data visualization analysis as claimed in claim 1, wherein: in S6, the comprehensive preferred advertisement category corresponding to each age group user is determined, and the specific determination method is as follows:
u1, comparing the preference advertisement categories corresponding to each user in the same age group in sequence according to the serial number sequence of the age group, and classifying the users corresponding to the same preference advertisement categories to obtain the users corresponding to the same preference advertisement categories in each age group;
u2, counting the number of users corresponding to the same preferred advertisement categories of each age group, and extracting the same preferred advertisement category with the largest number of users as the comprehensive preferred advertisement category corresponding to the users of each age group.
10. The method for social software advertising information based on feature recognition and data visualization analysis as claimed in claim 1, wherein: in S7, according to the comprehensive preferred advertisement category corresponding to each age group of users and the preferred advertisement display form corresponding to the preferred advertisement category corresponding to each user in each age group, intelligently delivering advertisements to all users in the corresponding age group on the social software, wherein the specific delivery method comprises the following steps:
e1, screening each advertisement corresponding to the comprehensive preference advertisement type from the advertisement database according to the comprehensive preference advertisement type corresponding to each age group user to form a comprehensive preference advertisement type set, and acquiring the advertisement display form corresponding to each advertisement in the comprehensive preference advertisement type set;
e2, extracting advertisements meeting the preference advertisement display form corresponding to the preference advertisement type corresponding to each user from all advertisements in the comprehensive preference advertisement type set corresponding to each age group according to the preference advertisement display form corresponding to the preference advertisement type corresponding to each user in each age group, and marking the advertisements as target advertisements so as to obtain the target advertisements of the comprehensive preference advertisement type corresponding to each user in each age group;
e3, carrying out targeted advertisement putting of the comprehensive preference advertisement category corresponding to the user in each age group to the social software corresponding to each user in each age group.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110506067.2A CN113129078A (en) | 2021-05-10 | 2021-05-10 | Social software advertisement information delivery method based on feature recognition and data visualization analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110506067.2A CN113129078A (en) | 2021-05-10 | 2021-05-10 | Social software advertisement information delivery method based on feature recognition and data visualization analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113129078A true CN113129078A (en) | 2021-07-16 |
Family
ID=76781283
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110506067.2A Withdrawn CN113129078A (en) | 2021-05-10 | 2021-05-10 | Social software advertisement information delivery method based on feature recognition and data visualization analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113129078A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113327140A (en) * | 2021-08-02 | 2021-08-31 | 深圳小蝉文化传媒股份有限公司 | Video advertisement putting effect intelligent analysis management system based on big data analysis |
| CN115222456A (en) * | 2022-07-27 | 2022-10-21 | 中科泰岳(北京)科技有限公司 | Marketing method, platform, equipment and medium based on big data user consumption preference |
| CN118132821A (en) * | 2024-03-05 | 2024-06-04 | 苏州嘟米信息科技有限公司 | Network information classified storage system based on big data analysis |
-
2021
- 2021-05-10 CN CN202110506067.2A patent/CN113129078A/en not_active Withdrawn
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113327140A (en) * | 2021-08-02 | 2021-08-31 | 深圳小蝉文化传媒股份有限公司 | Video advertisement putting effect intelligent analysis management system based on big data analysis |
| CN115222456A (en) * | 2022-07-27 | 2022-10-21 | 中科泰岳(北京)科技有限公司 | Marketing method, platform, equipment and medium based on big data user consumption preference |
| CN118132821A (en) * | 2024-03-05 | 2024-06-04 | 苏州嘟米信息科技有限公司 | Network information classified storage system based on big data analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113129078A (en) | Social software advertisement information delivery method based on feature recognition and data visualization analysis | |
| CN112102037B (en) | Live E-commerce platform commodity content intelligent pushing management system based on big data | |
| CN103714130B (en) | Video recommendation system and method | |
| CN110532379B (en) | Electronic information recommendation method based on LSTM (least Square TM) user comment sentiment analysis | |
| CN109241255A (en) | A kind of intension recognizing method based on deep learning | |
| CN106062730A (en) | Systems and methods for actively composing content for use in continuous social communication | |
| CN110851718B (en) | Movie recommendation method based on long and short term memory network and user comments | |
| CN106570718A (en) | Information releasing method and releasing system | |
| CN107635151A (en) | A kind of machine learning TV programme suggesting method based on domain disassembler | |
| CN107391582A (en) | The information recommendation method of user preference similarity is calculated based on context ontology tree | |
| CN105279148B (en) | A kind of APP software users comment on uniformity determination methods | |
| CN113034238B (en) | Commodity brand feature extraction and intelligent recommendation management method based on electronic commerce platform transaction | |
| CN107526810A (en) | Establish method and device, methods of exhibiting and the device of clicking rate prediction model | |
| CN108132964A (en) | A kind of collaborative filtering method to be scored based on user item class | |
| CN109508407A (en) | The tv product recommended method of time of fusion and Interest Similarity | |
| CN109391829A (en) | Video gets position analysis system, analysis method and storage media ready | |
| CN118093884B (en) | Text clustering method and system based on keyword matching | |
| CN117788108B (en) | Live commodity real-time scheduling system and method based on deep reinforcement learning | |
| CN115860870A (en) | Commodity recommendation method, system and device and readable medium | |
| CN117541322B (en) | Advertisement content intelligent generation method and system based on big data analysis | |
| CN116911926B (en) | Advertisement marketing recommendation method based on data analysis | |
| CN110851893A (en) | Home furnishing system and method based on big data | |
| CN108133296B (en) | Event attendance prediction method combining environmental data under social network based on events | |
| CN105354720B (en) | A method of mixed recommendation is carried out to consumption place based on visual cluster | |
| CN108287902B (en) | Recommendation system method based on data non-random missing mechanism |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210716 |
|
| WW01 | Invention patent application withdrawn after publication | ||
| DD01 | Delivery of document by public notice |
Addressee: Wuhan Jifeng World Network Technology Co.,Ltd. Document name: Refund Approval Notice |
|
| DD01 | Delivery of document by public notice |