CN118134552A - Advertisement media system - Google Patents
Advertisement media system Download PDFInfo
- Publication number
- CN118134552A CN118134552A CN202410360319.9A CN202410360319A CN118134552A CN 118134552 A CN118134552 A CN 118134552A CN 202410360319 A CN202410360319 A CN 202410360319A CN 118134552 A CN118134552 A CN 118134552A
- Authority
- CN
- China
- Prior art keywords
- tag
- merchant
- information
- terminal
- media
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012216 screening Methods 0.000 claims abstract description 22
- 238000000605 extraction Methods 0.000 claims abstract description 15
- 239000011159 matrix material Substances 0.000 claims description 69
- 238000004364 calculation method Methods 0.000 claims description 49
- 238000010276 construction Methods 0.000 claims description 23
- 238000004140 cleaning Methods 0.000 claims description 5
- 238000011156 evaluation Methods 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 4
- 238000000034 method Methods 0.000 abstract description 4
- 238000007726 management method Methods 0.000 description 35
- 230000000052 comparative effect Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2457—Query processing with adaptation to user needs
- G06F16/24578—Query processing with adaptation to user needs using ranking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Computational Linguistics (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an advertisement media system, which comprises an information management module, a media resource management module and an advertisement management module; the information management module is used for logging in the network platform to collect related advertisement information files and information nearby the media terminal, and screening the information. According to the invention, under the condition that personal information sharing is not needed by users, label extraction is directly carried out on information around the media terminals, a terminal label set is constructed, the preference degree and the dependence degree of the merchant on the terminal labels are calculated by analyzing the score of the merchant on the advertising effect of the media terminals, the interest degree of the merchant on the labels is obtained, the interest degree of the final merchant on all the media terminals is ordered in a descending order, a recommendation list is generated, candidate advertisement positions are provided for the merchant, meanwhile, the user privacy is not needed to be collected, the accurate pushing of the media advertisements is directly realized, and the method has high accuracy, and also has good effectiveness and applicability.
Description
Technical Field
The invention relates to the technical field of advertisement media, in particular to an advertisement media system.
Background
The advertisement media is a means for information transmission, which is used for displaying products or services and business information, so that the public can know the purposes, characteristics, effects and the like of new products and new services, and can display and popularize certain things or products to the public.
In the prior art, when the media system delivers advertisements, most of the media system collects and analyzes user information to accurately deliver and push advertisements, user behaviors need to be mined, but general users have a certain mind-resisting mind on the collected user information, and for the media advertisements, the media advertisements are difficult to collect information such as attribute behaviors of the users under the condition that the users do not share personal information, and the advertisement resources cannot be delivered purposefully, so that the advertisement resources are wasted.
Disclosure of Invention
The invention aims to provide an advertisement media system so as to solve the problem that the advertisement delivery cannot be accurately performed under the condition that users do not share personal information in the background technology.
In order to achieve the above purpose, the present invention provides the following technical solutions: the advertisement media system comprises an information management module, a media resource management module and an advertisement management module;
The information management module is used for logging in the network platform to collect related advertisement information files and information nearby the media terminal, and screening the information;
The media resource management module is used for integrating advertisement propagation information, wherein the advertisement propagation information comprises text advertisement information, picture advertisement information and video advertisement information;
The advertisement management module is used for extracting labels from information nearby the terminal, constructing a terminal media label matrix, calculating preference of a merchant to the labels, obtaining label interest of the merchant, constructing an interest matrix of the merchant, matching the interest of the merchant, and obtaining the first N media terminals to be recommended to the merchant as advertisement positions;
The advertisement management module comprises a terminal tag collection module, a merchant interest modeling module and an advertisement position recommendation module;
the terminal tag set module is used for constructing a tag set of the media terminal through an algorithm according to basic information of the existing media terminal;
the merchant interest modeling module is used for calculating the favorites and the dependence of the merchant on the tags, obtaining the tag interests of the merchant and constructing an interest matrix;
and the advertisement space recommending module obtains the interest degree of the commercial tenant on all media terminals according to the tag matrix and the interest degree matrix, performs descending order sequencing on the calculation results, and recommends the first N terminals to the commercial tenant as advertisement spaces.
Preferably, the information management module comprises an initial information collection module and an information screening module;
The initial information collection module is used for modifying, adding and deleting the inputted advertisement information;
the information screening module is used for screening the data marking, the advertisement information, the merchant basic information and the information nearby the media terminal, and the user data is formed after data cleaning links such as preprocessing, data backup and the like.
Preferably, the terminal tag collection module comprises a media tag extraction module and a tag matrix construction module;
The media tag extraction module is used for extracting keywords of media terminal information and acquiring a candidate keyword dataset of the media terminal;
the label matrix construction module is used for using an improved TF-IDF algorithm to sort the improved TF-IDF values of the candidate keyword data set in a descending order, acquiring the first N keywords as a label set, and constructing a label matrix.
Preferably, the improved TF-IDF value is calculated as follows:
Wherein, Represents the sum of the number of occurrences of all candidate keywords in the tag text set, n a represents the total number of occurrences of candidate keyword a in the tag text set, n a,b represents the number of occurrences of candidate keyword a in the tag text of terminal b,/>The number of the entries of the tag text of the terminal b is represented, and n represents the number of the tag text of the terminal in the tag text set, wherein the number of the tag text of the terminal comprises the candidate keyword a in the tag text of the terminal b.
Preferably, the label matrix calculation formula is as follows;
Wherein n represents the number of terminals, m represents the number of tags, t ab (a is equal to or more than 1 and is equal to or less than n, b is equal to or less than 1 and is equal to or less than m) represents the TF-IDF value of the tag b in the terminal a, and the TF-IDF value is 0 when the terminal does not correspond to the tag.
Preferably, the merchant interest modeling module comprises a tag interest degree calculation module and an interest matrix construction module;
The tag interest degree calculation module is used for collecting evaluation data of the merchant on the media terminal and calculating the favorability degree and the dependence degree of the merchant on the tag respectively;
The interest matrix construction module is used for obtaining the favorability degree and the dependence degree of the merchant on the labels, calculating the interest degree of the merchant on each label and constructing an interest degree matrix.
Preferably, the calculation formula of the preference degree of the merchant to the tag is as follows:
The calculation formula of the dependence degree of the merchant on the label is as follows:
Wherein rate (s, h) represents the score of the merchant s to the terminal h, rel (h, t) represents the TF-IDF value of the tag, rs represents the average value of all scores of the merchant s, Ih represents the media terminal set, n (s, t) represents the number of times the merchant s uses the tag t, Representing the total number of times merchant s uses all tags,/>Representing the total number of uses of all tags by all merchants,/>Indicating the total number of uses of the tag t by all merchants.
Preferably, the calculation formula of the interest degree of the merchant on each label is as follows:
P(s,t)＝rate(s,t)*D(s,t)；
The calculation formula of the interest degree matrix is as follows:
Ts＝(t11 t12 … t1m)；
wherein t 1b (1.ltoreq.b.ltoreq.m) represents the interest degree of the merchant in the tag b.
Preferably, the calculation formula of the interest degree of the merchant on all media terminals is as follows:
Compared with the prior art, the invention has the beneficial effects that:
According to the invention, under the condition that personal information sharing is not needed by users, label extraction is directly carried out on information around the media terminals, a terminal label set is constructed, the preference degree and the dependence degree of the merchant on the terminal labels are calculated by analyzing the score of the merchant on the advertising effect of the media terminals, the interest degree of the merchant on the labels is obtained, the interest degree of the final merchant on all the media terminals is ordered in a descending order, a recommendation list is generated, candidate advertisement positions are provided for the merchant, meanwhile, the user privacy is not needed to be collected, the accurate pushing of the media advertisements is directly realized, and the method has high accuracy, and also has good effectiveness and applicability.
Drawings
FIG. 1 is a system block diagram of an advertising media system of the present invention;
FIG. 2 is a system block diagram of a terminal tag aggregation module of the advertising media system of the present invention;
FIG. 3 is a block diagram of a merchant interest modeling module system of the advertising media system of the present invention;
FIG. 4 is a bar graph of the accuracy of the advertising media system of the present invention.
In the figure:
1. An information management module; 11. an initial information collection module; 12. an information screening module; 2. a media resource management module; 3. an advertisement management module; 31. a terminal tag collection module; 311. a media tag extraction module; 312. a label matrix construction module; 32. a merchant interest modeling module; 321. a tag interest calculating module; 322. an interest matrix construction module; 33. and the advertisement position recommending module.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
Referring to fig. 1-4, the present embodiment provides an advertisement media system, which includes an information management module 1, a media resource management module 2, and an advertisement management module 3;
The information management module 1 is used for logging in a network platform to collect related advertisement information files and information nearby a media terminal, and screening the information;
the information management module 1 comprises an initial information collection module 11 and an information screening module 12;
The initial information collection module 11 is used for modifying, adding and deleting the inputted advertisement information;
The information screening module 12 is used for screening information of data labels, advertisement information, basic information of merchants and information near a media terminal, and forming user data after preprocessing, data backup and other data cleaning links.
The media resource management module 2 is used for integrating advertisement propagation information, wherein the advertisement propagation information comprises text advertisement information, picture advertisement information and video advertisement information;
the advertisement management module 3 is used for extracting labels from information near the terminal, constructing a terminal media label matrix, calculating preference of a merchant to the labels, obtaining label interest of the merchant, constructing an interest matrix of the merchant, matching the interest of the merchant, and obtaining the first 15 media terminals to be recommended to the merchant as advertisement positions;
The advertisement management module 3 comprises a terminal tag collection module 31, a merchant interest modeling module 32 and an advertisement position recommending module 33;
the terminal tag set module 31 is configured to construct a tag set of the media terminal through an algorithm according to basic information of the existing media terminal;
the terminal tag collection module 31 comprises a media tag extraction module 311 and a tag matrix construction module 312;
the media tag extraction module 311 is configured to extract keywords of media terminal information, and obtain a candidate keyword dataset of the media terminal;
the tag matrix construction module 312 is configured to use an improved TF-IDF algorithm to sort the improved TF-IDF values of the candidate keyword dataset in a descending order, obtain the first 15 keywords as a tag set, and construct a tag matrix.
The calculation formula of the improved TF-IDF value is as follows:
Wherein, Represents the sum of the number of occurrences of all candidate keywords in the tag text set, n a represents the total number of occurrences of candidate keyword a in the tag text set, n a,b represents the number of occurrences of candidate keyword a in the tag text of terminal b,/>The number of the entries of the tag text of the terminal b is represented, and n represents the number of the tag text of the terminal in the tag text set, wherein the number of the tag text of the terminal comprises the candidate keyword a in the tag text of the terminal b.
The label matrix calculation formula is as follows;
wherein n represents the number of terminals, m represents the number of tags, t ab (a is more than or equal to 1 and less than or equal to n, b is more than or equal to 1 and less than or equal to m) represents the TF-IDF value of tag b in terminal a, and when the terminal does not correspond to the tag, the TF-IDF value is 0;
The merchant interest modeling module 32 is configured to calculate a preference and a dependence of a merchant on a tag, obtain a tag interest of the merchant, and construct an interest matrix;
The merchant interest modeling module 32 includes a tag interest level calculation module 321 and an interest matrix construction module 322;
The tag interest degree calculation module 321 is used for collecting evaluation data of the merchant on the media terminal and calculating the favorites and the dependence degree of the merchant on the tag respectively;
The interest matrix construction module 322 is configured to obtain the preference degree and the dependence degree of the merchant on the labels, calculate the interest degree of the merchant on each label, and construct an interest degree matrix.
The calculation formula of the preference degree of the merchant to the label is as follows:
The calculation formula of the dependence degree of the merchant on the label is as follows:
Wherein rate (s, h) represents the score of the merchant s to the terminal h, rel (h, t) represents the TF-IDF value of the tag, rs represents the average value of all scores of the merchant s, Ih represents the media terminal set, n (s, t) represents the number of times the merchant s uses the tag t, Representing the total number of times merchant s uses all tags,/>Representing the total number of uses of all tags by all merchants,/>Indicating the total number of uses of the tag t by all merchants.
The calculation formula of the interest degree of the merchant on each label is as follows:
P(s,t)＝rate(s,t)*D(s,t)；
The interestingness matrix calculation formula is as follows:
Ts＝(t11 t12 … t1m)；
wherein t 1b (1.ltoreq.b.ltoreq.m) represents the interest degree of the merchant in the tag b.
The calculation formula of the interest degree of the merchant to all media terminals is as follows:
The advertisement space recommending module 33 obtains the interest degree of the commercial tenant on all media terminals according to the tag matrix and the interest degree matrix, sorts the calculation results in a descending order, and recommends the first 15 terminals to the commercial tenant as advertisement spaces.
Example 2
Referring to fig. 1-4, the present embodiment provides an advertisement media system, which includes an information management module 1, a media resource management module 2, and an advertisement management module 3;
The information management module 1 is used for logging in a network platform to collect related advertisement information files and information nearby a media terminal, and screening the information;
the information management module 1 comprises an initial information collection module 11 and an information screening module 12;
The initial information collection module 11 is used for modifying, adding and deleting the inputted advertisement information;
The information screening module 12 is used for screening information of data labels, advertisement information, basic information of merchants and information near a media terminal, and forming user data after preprocessing, data backup and other data cleaning links.
The media resource management module 2 is used for integrating advertisement propagation information, wherein the advertisement propagation information comprises text advertisement information, picture advertisement information and video advertisement information;
The advertisement management module 3 is used for extracting labels from information near the terminal, constructing a terminal media label matrix, calculating preference of a merchant to the labels, obtaining label interest of the merchant, constructing an interest matrix of the merchant, matching the interest of the merchant, and obtaining the first 10 media terminals to be recommended to the merchant as advertisement slots;
The advertisement management module 3 comprises a terminal tag collection module 31, a merchant interest modeling module 32 and an advertisement position recommending module 33;
the terminal tag set module 31 is configured to construct a tag set of the media terminal through an algorithm according to basic information of the existing media terminal;
the terminal tag collection module 31 comprises a media tag extraction module 311 and a tag matrix construction module 312;
the media tag extraction module 311 is configured to extract keywords of media terminal information, and obtain a candidate keyword dataset of the media terminal;
The tag matrix construction module 312 is configured to use an improved TF-IDF algorithm to sort the improved TF-IDF values of the candidate keyword dataset in a descending order, obtain the first 10 keywords as a tag set, and construct a tag matrix.
The calculation formula of the improved TF-IDF value is as follows:
Wherein, Represents the sum of the number of occurrences of all candidate keywords in the tag text set, n a represents the total number of occurrences of candidate keyword a in the tag text set, n a,b represents the number of occurrences of candidate keyword a in the tag text of terminal b,/>The number of the entries of the tag text of the terminal b is represented, and n represents the number of the tag text of the terminal in the tag text set, wherein the number of the tag text of the terminal comprises the candidate keyword a in the tag text of the terminal b.
The label matrix calculation formula is as follows;
wherein n represents the number of terminals, m represents the number of tags, t ab (a is more than or equal to 1 and less than or equal to n, b is more than or equal to 1 and less than or equal to m) represents the TF-IDF value of tag b in terminal a, and when the terminal does not correspond to the tag, the TF-IDF value is 0;
The merchant interest modeling module 32 is configured to calculate a preference and a dependence of a merchant on a tag, obtain a tag interest of the merchant, and construct an interest matrix;
The merchant interest modeling module 32 includes a tag interest level calculation module 321 and an interest matrix construction module 322;
The tag interest degree calculation module 321 is used for collecting evaluation data of the merchant on the media terminal and calculating the favorites and the dependence degree of the merchant on the tag respectively;
The interest matrix construction module 322 is configured to obtain the preference degree and the dependence degree of the merchant on the labels, calculate the interest degree of the merchant on each label, and construct an interest degree matrix.
The calculation formula of the preference degree of the merchant to the label is as follows:
The calculation formula of the dependence degree of the merchant on the label is as follows:
Wherein rate (s, h) represents the score of the merchant s to the terminal h, rel (h, t) represents the TF-IDF value of the tag, rs represents the average value of all scores of the merchant s, Ih represents the media terminal set, n (s, t) represents the number of times the merchant s uses the tag t, Representing the total number of times merchant s uses all tags,/>Representing the total number of uses of all tags by all merchants,/>Indicating the total number of uses of the tag t by all merchants.
The calculation formula of the interest degree of the merchant on each label is as follows:
P(s,t)＝rate(s,t)*D(s,t)；
The interestingness matrix calculation formula is as follows:
Ts＝(t11 t12 … t1m)；
wherein t 1b (1.ltoreq.b.ltoreq.m) represents the interest degree of the merchant in the tag b.
The calculation formula of the interest degree of the merchant to all media terminals is as follows:
The advertisement space recommending module 33 obtains the interest degree of the commercial tenant on all media terminals according to the tag matrix and the interest degree matrix, sorts the calculation results in a descending order, and recommends the first 10 terminals to the commercial tenant as advertisement spaces.
Example 3
Referring to fig. 1-4, the present embodiment provides an advertisement media system, which includes an information management module 1, a media resource management module 2, and an advertisement management module 3;
The information management module 1 is used for logging in a network platform to collect related advertisement information files and information nearby a media terminal, and screening the information;
the information management module 1 comprises an initial information collection module 11 and an information screening module 12;
The initial information collection module 11 is used for modifying, adding and deleting the inputted advertisement information;
The information screening module 12 is used for screening information of data labels, advertisement information, basic information of merchants and information near a media terminal, and forming user data after preprocessing, data backup and other data cleaning links.
The media resource management module 2 is used for integrating advertisement propagation information, wherein the advertisement propagation information comprises text advertisement information, picture advertisement information and video advertisement information;
The advertisement management module 3 is used for extracting labels from information near the terminal, constructing a terminal media label matrix, calculating preference of a merchant to the labels, obtaining label interest of the merchant, constructing an interest matrix of the merchant, matching the interest of the merchant, and obtaining the first 20 media terminals to be recommended to the merchant as advertisement slots;
The advertisement management module 3 comprises a terminal tag collection module 31, a merchant interest modeling module 32 and an advertisement position recommending module 33;
the terminal tag set module 31 is configured to construct a tag set of the media terminal through an algorithm according to basic information of the existing media terminal;
the terminal tag collection module 31 comprises a media tag extraction module 311 and a tag matrix construction module 312;
the media tag extraction module 311 is configured to extract keywords of media terminal information, and obtain a candidate keyword dataset of the media terminal;
the tag matrix construction module 312 is configured to use an improved TF-IDF algorithm to sort the improved TF-IDF values of the candidate keyword dataset in a descending order, obtain the first 20 keywords as a tag set, and construct a tag matrix.
The calculation formula of the improved TF-IDF value is as follows:
Wherein, Represents the sum of the number of occurrences of all candidate keywords in the tag text set, n a represents the total number of occurrences of candidate keyword a in the tag text set, n a,b represents the number of occurrences of candidate keyword a in the tag text of terminal b,/>The number of the entries of the tag text of the terminal b is represented, and n represents the number of the tag text of the terminal in the tag text set, wherein the number of the tag text of the terminal comprises the candidate keyword a in the tag text of the terminal b.
The label matrix calculation formula is as follows;
wherein n represents the number of terminals, m represents the number of tags, t ab (a is more than or equal to 1 and less than or equal to n, b is more than or equal to 1 and less than or equal to m) represents the TF-IDF value of tag b in terminal a, and when the terminal does not correspond to the tag, the TF-IDF value is 0;
The merchant interest modeling module 32 is configured to calculate a preference and a dependence of a merchant on a tag, obtain a tag interest of the merchant, and construct an interest matrix;
The merchant interest modeling module 32 includes a tag interest level calculation module 321 and an interest matrix construction module 322;
The tag interest degree calculation module 321 is used for collecting evaluation data of the merchant on the media terminal and calculating the favorites and the dependence degree of the merchant on the tag respectively;
The interest matrix construction module 322 is configured to obtain the preference degree and the dependence degree of the merchant on the labels, calculate the interest degree of the merchant on each label, and construct an interest degree matrix.
The calculation formula of the preference degree of the merchant to the label is as follows:
The calculation formula of the dependence degree of the merchant on the label is as follows:
Wherein rate (s, h) represents the score of the merchant s to the terminal h, rel (h, t) represents the TF-IDF value of the tag, rs represents the average value of all scores of the merchant s, Ih represents the media terminal set, n (s, t) represents the number of times the merchant s uses the tag t, Representing the total number of times merchant s uses all tags,/>Representing the total number of uses of all tags by all merchants,/>Indicating the total number of uses of the tag t by all merchants.
The calculation formula of the interest degree of the merchant on each label is as follows:
P(s,t)＝rate(s,t)*D(s,t)；
The interestingness matrix calculation formula is as follows:
Ts＝(t11 t12 … t1m)；
wherein t 1b (1.ltoreq.b.ltoreq.m) represents the interest degree of the merchant in the tag b.
The calculation formula of the interest degree of the merchant to all media terminals is as follows:
The advertisement space recommending module 33 obtains the interest degree of the commercial tenant on all media terminals according to the tag matrix and the interest degree matrix, sorts the calculation results in a descending order, and recommends the first 20 terminals to the commercial tenant as advertisement spaces.
Comparative example 1
Referring to fig. 1-4, this embodiment provides an advertisement media system, which is substantially the same as embodiment 1, and the main difference is that: in the tag matrix construction module 312, candidate keywords are obtained using PR algorithms.
Test and result analysis:
the advertisement media systems used by examples 1-3 were recorded as example groups 1-3, the advertisement media system used by comparative example 1 was recorded as comparative group 1, the accuracy and response time of the advertisement media systems of example groups 1-3 and comparative group 1 were tested, and the relevant test data were recorded in table 1.
Table 1: test data record table
As can be seen from Table 1, the accuracy of the advertisement media system used in embodiments 1-3 is higher than that of comparative group 1, wherein the accuracy of the advertisement media system used in embodiment 1 is higher than that of embodiments 2 and 3, the accuracy of the advertisement media system is affected by the value of N, when the optimal value of N is 15 and the value of N is less than 15, the accuracy increases with the increase of N, and when the value of N is greater than 15, the accuracy decreases with the increase of N, and the end with the post-ranking is also recommended due to the increase of the recommended number, thereby affecting the accuracy of the advertisement media system, so that the advertisement media system used in embodiment 1 can realize the accurate pushing of the advertisement media without acquiring the privacy information of the user.
According to the invention, through collecting relevant advertisement information files, the input advertisement information can be modified, added and deleted, advertisement propagation information including text advertisement information, picture advertisement information and video advertisement information is integrated, meanwhile, information nearby the media terminal is obtained, including basic information, position information, business attribute, crowd attribute, business circle information and social information, label extraction is carried out on information nearby the media terminal, label collection of the media terminal is built through an algorithm, the favorability and dependence of the media terminal on the labels are calculated, the label interest degree of the merchants is obtained, an interest matrix of the merchants is built, the interest degree of the merchants is matched, the front N media terminal is obtained and is recommended to the merchants as an advertisement position, label extraction is directly carried out on information nearby the media terminal under the condition that users do not need to share personal information, the interest degree of the media terminal on the labels is obtained through analyzing the score of the merchant on the advertisement effect of the media terminal, the interest degree of all the media terminals is finally ordered in descending order, a recommendation list is generated, and candidate advertisement positions are provided for the merchants, meanwhile, the user privacy is not required to be collected, accurate pushing of the media advertisement is directly realized, and the method is not provided, and the method has high accuracy and good applicability is good.
Although the present invention has been described with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments described, or equivalents may be substituted for elements thereof, and any modifications, equivalents, improvements and changes may be made without departing from the spirit and principles of the present invention.
Claims (9)
1. The advertisement media system is characterized in that: comprises an information management module (1), a media resource management module (2) and an advertisement management module (3);
The information management module (1) is used for logging in a network platform to collect related advertisement information files and information nearby a media terminal, and screening the information;
The media resource management module (2) is used for integrating advertisement propagation information, wherein the advertisement propagation information comprises text advertisement information, picture advertisement information and video advertisement information;
The advertisement management module (3) is used for extracting labels from information near the terminals, constructing a terminal media label matrix, calculating preference of merchants on the labels, obtaining the label interest of the merchants, constructing an interest matrix of the merchants, matching the interest of the merchants, and obtaining the first N media terminals to be recommended to the merchants as advertisement positions;
The advertisement management module (3) comprises a terminal tag collection module (31), a merchant interest modeling module (32) and an advertisement position recommendation module (33);
the terminal tag set module (31) is used for constructing a tag set of the media terminal through an algorithm according to basic information of the existing media terminal;
The merchant interest modeling module (32) is used for calculating the favorability and the dependence of the merchant on the tag, obtaining the tag interest of the merchant and constructing an interest matrix;
The advertisement space recommending module (33) obtains the interest degree of the commercial tenant on all media terminals according to the tag matrix and the interest degree matrix, performs descending order sequencing on the calculation results, and recommends the first N terminals to the commercial tenant as advertisement spaces.
2. The advertising media system of claim 1, wherein: the information management module (1) comprises an initial information collection module (11) and an information screening module (12);
The initial information collection module (11) is used for modifying, adding and deleting the inputted advertisement information;
the information screening module (12) is used for screening information of data labels, advertisement information, merchant basic information and information nearby a media terminal, and user data is formed after data cleaning links such as preprocessing and data backup.
3. The advertising media system of claim 1, wherein: the terminal tag collection module (31) comprises a media tag extraction module (311) and a tag matrix construction module (312);
The media tag extraction module (311) is used for extracting keywords of media terminal information and acquiring a candidate keyword dataset of the media terminal;
The tag matrix construction module (312) is configured to use an improved TF-IDF algorithm to sort the improved TF-IDF values of the candidate keyword dataset in a descending order, obtain the first N keywords as a tag set, and construct a tag matrix.
4. An advertising media system as claimed in claim 3, wherein: the calculation formula of the improved TF-IDF value is as follows:
Wherein, Representing the sum of the number of occurrences of all candidate keywords in the set of tab texts, n a representing the total number of occurrences of candidate keyword a in the set of tab texts, n a,b representing the number of occurrences of candidate keyword a in the tab text of terminal b,The number of the entries of the tag text of the terminal b is represented, and n represents the number of the tag text of the terminal in the tag text set, wherein the number of the tag text of the terminal comprises the candidate keyword a in the tag text of the terminal b.
5. An advertising media system as claimed in claim 3, wherein: the label matrix calculation formula is as follows;
Wherein n represents the number of terminals, m represents the number of tags, t ab (a is equal to or more than 1 and is equal to or less than n, b is equal to or less than 1 and is equal to or less than m) represents the TF-IDF value of the tag b in the terminal a, and the TF-IDF value is 0 when the terminal does not correspond to the tag.
6. The advertising media system of claim 1, wherein: the merchant interest modeling module (32) comprises a tag interest degree calculation module (321) and an interest matrix construction module (322);
the tag interest degree calculation module (321) is used for collecting evaluation data of the merchant on the media terminal and calculating the favorite degree and the dependence degree of the merchant on the tag respectively;
the interest matrix construction module (322) is used for obtaining the favorability and the dependence degree of the merchant on the labels, calculating the interest degree of the merchant on each label and constructing an interest degree matrix.
7. The advertising media system of claim 6, wherein: the calculation formula of the favor degree of the merchant to the label is as follows:
The calculation formula of the dependence degree of the merchant on the label is as follows:
Wherein rate (s, h) represents the score of the merchant s to the terminal h, rel (h, t) represents the TF-IDF value of the tag, rs represents the average value of all scores of the merchant s, Ih represents the media terminal set, n (s, t) represents the number of times the merchant s uses the tag t, Representing the total number of times merchant s uses all tags,/>Representing the total number of uses of all tags by all merchants,/>Indicating the total number of uses of the tag t by all merchants.
8. The advertising media system of claim 6, wherein: the interest degree calculation formula of the merchant on each label is as follows:
P(s,t)＝rate(s,t)*D(s,t)；
The calculation formula of the interest degree matrix is as follows:
Ts＝(t11 t12…t1m)；
wherein t 1b (1.ltoreq.b.ltoreq.m) represents the interest degree of the merchant in the tag b.
9. The advertising media system of claim 6, wherein: the interest degree calculation formula of the merchant on all media terminals is as follows:
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410360319.9A CN118134552A (en) | 2024-03-27 | 2024-03-27 | Advertisement media system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410360319.9A CN118134552A (en) | 2024-03-27 | 2024-03-27 | Advertisement media system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118134552A true CN118134552A (en) | 2024-06-04 |
Family
ID=91235582
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410360319.9A Pending CN118134552A (en) | 2024-03-27 | 2024-03-27 | Advertisement media system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118134552A (en) |
-
2024
- 2024-03-27 CN CN202410360319.9A patent/CN118134552A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chen et al. | Uncovering the importance of relationship characteristics in social networks: Implications for seeding strategies | |
| CN106886518B (en) | Microblog account number classification method | |
| CN106126582A (en) | Recommend method and device | |
| US20150205580A1 (en) | Method and System for Sorting Online Videos of a Search | |
| US8341101B1 (en) | Determining relationships between data items and individuals, and dynamically calculating a metric score based on groups of characteristics | |
| US20110218859A1 (en) | Method, Apparatus and System for Increasing Website Data Transfer Speed | |
| CN106168953B (en) | Bo-Weak-relationship social network-oriented blog recommendation method | |
| CN108805598B (en) | Similarity information determination method, server and computer-readable storage medium | |
| US9213733B2 (en) | Computerized internet search system and method | |
| US9015158B2 (en) | Contents creating device and contents creating method | |
| CN106779827A (en) | A kind of Internet user's behavior collection and the big data method of analysis detection | |
| CN114448921B (en) | Information display method and device based on social relation chain and server | |
| CN101454771A (en) | System and method of segmenting and tagging entities based on profile matching using a multi-media survey | |
| Dhingra et al. | Spam analysis of big reviews dataset using Fuzzy Ranking Evaluation Algorithm and Hadoop | |
| US20120173338A1 (en) | Method and apparatus for data traffic analysis and clustering | |
| US20100100443A1 (en) | User classification apparatus, advertisement distribution apparatus, user classification method, advertisement distribution method, and program used thereby | |
| JP2009193465A (en) | Information processor, information providing system, information processing method, and program | |
| CN105378730A (en) | Social media content analysis and output | |
| CN107808346B (en) | Evaluation method and evaluation device for potential target object | |
| Guo et al. | Calibration of voting-based helpfulness measurement for online reviews: an iterative bayesian probability approach | |
| US20150142782A1 (en) | Method for associating metadata with images | |
| CN112182390A (en) | Letter pushing method and device, computer equipment and storage medium | |
| CN118134552A (en) | Advertisement media system | |
| KR20210012495A (en) | Ad recommendation techniques and methods that combine the similarity of SNS text with ad content and the fairness of advertisement impressions | |
| CN116823410A (en) | Data processing method, object processing method, recommending method and computing device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication |