CN113868549B - Advertisement putting optimization method and device, electronic equipment and storage medium - Google Patents

Advertisement putting optimization method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN113868549B
CN113868549B CN202111106131.4A CN202111106131A CN113868549B CN 113868549 B CN113868549 B CN 113868549B CN 202111106131 A CN202111106131 A CN 202111106131A CN 113868549 B CN113868549 B CN 113868549B
Authority
CN
China
Prior art keywords
advertisement
keyword
consumer
information
consumers
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.)
Active
Application number
CN202111106131.4A
Other languages
Chinese (zh)
Other versions
CN113868549A (en
Inventor
高云君
陈璐
禹函琳
蔡鑫伟
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhejiang University ZJU
Original Assignee
Zhejiang University ZJU
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Zhejiang University ZJU filed Critical Zhejiang University ZJU
Priority to CN202111106131.4A priority Critical patent/CN113868549B/en
Publication of CN113868549A publication Critical patent/CN113868549A/en
Application granted granted Critical
Publication of CN113868549B publication Critical patent/CN113868549B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • 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
    • G06F16/9536—Search customisation based on social or collaborative filtering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0255—Targeted advertisements based on user history
    • 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
    • G06Q30/0261—Targeted advertisements based on user location
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0269—Targeted advertisements based on user profile or attribute
    • G06Q30/0271—Personalized advertisement

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Development Economics (AREA)
  • Strategic Management (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Databases & Information Systems (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

The invention discloses an advertisement putting optimization method, an advertisement putting optimization device, electronic equipment and a storage medium, wherein the advertisement putting optimization method comprises the following steps: acquiring social relations among consumers in a social network, advertisements on a road network and position information of the consumers, and keyword information of the advertisements and the consumers; predicting the current audience of the original advertisement delivery through the anti-Top-k geographic social keyword query according to the social relationship, the position information and the keyword information; if the current audience quantity is less than the set threshold value, obtaining candidate advertisements according to the difference of the keyword information; establishing a set of the candidate advertisements through an RQ-tree; and on the set, accelerating the evaluation of the candidate advertisements by using a lower limit count table, and finding the advertisement with the minimum cost as the final advertisement. The invention can effectively optimize and evaluate the advertisement to find the optimal advertisement delivery scheme.

Description

Advertisement putting optimization method and device, electronic equipment and storage medium
Technical Field
The present application relates to the field of advertisement technologies, and in particular, to an advertisement delivery optimization method, an advertisement delivery optimization device, an electronic device, and a storage medium.
Background
The current advertisement delivery is mainly divided into three steps: (1) data collection: collecting throwing data, historical throwing data and the like of similar products on the market; (2) material preparation: marketing staff positions the products and prepares corresponding materials such as posters, videos and the like; (3) Off-line or on-line platforms, such as short video platforms, station billboards, etc.
Accurate advertisement delivery is always a big problem in the field, especially the influence of off-line advertisement geographical positions is big, the delivery effect is often not satisfactory, and potential consumers cannot be attracted as much as possible. Meanwhile, the off-line advertisement putting cost is high, and the problem of how to quickly and effectively optimize advertisement putting is urgent.
Disclosure of Invention
In view of the foregoing, an objective of an embodiment of the present application is to provide an advertisement delivery optimization method, apparatus, electronic device, and storage medium, so as to solve the foregoing problems.
According to a first aspect of an embodiment of the present application, there is provided an advertisement delivery optimization method, including:
acquiring social relations among consumers in a social network, advertisements on a road network and position information of the consumers, and keyword information of the advertisements and the consumers;
predicting the current audience of the original advertisement delivery through the anti-Top-k geographic social keyword query according to the social relationship, the position information and the keyword information;
if the current audience quantity is less than the set threshold value, obtaining candidate advertisements according to the difference of the keyword information;
establishing a set of the candidate advertisements through an RQ-tree;
And on the set, accelerating the evaluation of the candidate advertisements by using a lower limit count table, and finding the advertisement with the minimum cost as the final advertisement.
Further, predicting the current audience of the advertisement delivery through the reverse Top-k geographic social keyword query according to the acquired information comprises the following steps:
based on the social relationship between the consumers As an advertisement propagation analysis, where Q ' represents any advertisement in advertisement set Q, F (u) represents u's friends, CU u→q represents u's friends that received advertisement Q, and C u→q represents the number of times consumer u received advertisement Q;
Based on the advertisement and the location information of the consumer Evaluating similarity of a spatial distance of consumer u to advertisement q, wherein D (u, q) represents a distance of consumer u to advertisement q;
According to the keyword information, obtaining advertisement promotion product type and consumer preference information, using Evaluating the pertinence of advertisement delivery, wherein ω and ω' represent keyword groups of the advertisement and the consumer, respectively;
combining the three information, using the reverse Top-k geographic social keyword query as an original query, and obtaining the current audience C (q).
Further, if the current audience quantity is less than the set threshold, obtaining a candidate advertisement according to the difference of the keyword information, including:
comparing the number of the current audience C (q) with a set threshold according to the number of the current audience C (q);
If less than the set threshold, the following two ways are performed:
(1) Adding keywords which are interested by consumers into the keywords of the original advertisement, and deleting keywords which are not interested by consumers;
(2) Expanding the spreading force k of the original advertisement until each consumer becomes an audience for the advertisement;
According to (1) and (2) above, a candidate advertisement S Q is obtained.
Further, establishing the set of candidate advertisements through the RQ-tree includes:
Constructing an RQ-tree for the candidate advertisements S Q by using iterative partitioning and a k-means algorithm, and if the tree height is h, fanning out each non-leaf node is as follows: The partitioning S Q continues until only one advertisement is contained in each leaf node.
Further, accelerating the evaluation of the candidate advertisements on the set by using a lower bound count table to find the advertisement with the smallest cost as the final advertisement, including:
given a set of candidate advertisements S Q, the lower bound similarity count table (i.e., CL l) contains t (1. Ltoreq.t. Ltoreq.Q'. Ltoreq.k) tuples < r i,Oi,si >, and is arranged in descending order of r i, where O i (1. Ltoreq.i.ltoreq.t) is a GIM tree node without parent-child relationships, r i is MinSim GSK(Oi,SQ) or MinMaxSim GSK(Oi,SQ), and t is satisfied with the formula And (2) minimum value of
Given a set of space objects O i and a set of candidate advertisements S Q, if CL l.rt≥MaxSimGSK(Oi,SQ), then the result of candidate q' ∈S Q does not exist in O i, and therefore O i can be pruned;
the cost of quantifying each advertisement q' is calculated as follows:
wherein η is a modification preference for the advertisement propagation force k value, 1- η is a modification preference for the advertisement keyword, |k '-k| is the degree of expansion of k, max u∈C(q) R (q, u) represents the maximum rank of the set C (q), D (q'. Key, q.key) is the Euclidean distance of the two keyword groups of the consumer, max u∈C(q) D (q.key, u.key) is the maximum distance from q.key to { u.key|u e C (q) };
and returning the advertisement with the minimum cost as the final advertisement.
According to a second aspect of an embodiment of the present application, there is provided an advertisement delivery optimization apparatus, including:
The acquisition module is used for acquiring social relations among consumers in the social network, advertisement on the road network, position information of the consumers and keyword information of the advertisement and the consumers;
The prediction module is used for predicting the current audience of the original advertisement delivery through the anti-Top-k geographic social keyword query according to the social relationship, the position information and the keyword information;
the candidate advertisement obtaining module is used for obtaining candidate advertisements according to the difference of the keyword information if the current audience quantity is less than a set threshold value;
a building module for building a set of the candidate advertisements through a RQ-tree;
And the evaluation module is used for accelerating the evaluation of the candidate advertisements by utilizing a lower limit count table on the collection, and finding the advertisement with the minimum cost as the final advertisement.
According to a third aspect of an embodiment of the present application, there is provided an electronic apparatus including:
one or more processors;
A memory for storing one or more programs;
The one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of the first aspect.
According to a fourth aspect of embodiments of the present application there is provided a computer readable storage medium having stored thereon computer instructions which when executed by a processor perform the steps of the method according to the first aspect.
The technical scheme provided by the embodiment of the application can comprise the following beneficial effects:
As can be seen from the above embodiments, the application utilizes the anti-Top-k geographic social keyword query modification technique to effectively solve the problem that the original advertisement cannot attract enough potential consumers; evaluating candidate advertisements in batch by utilizing the RQ-tree structure; the advertisement evaluation efficiency is improved by utilizing a lower limit count table structure; and finally, returning the optimal advertisement with the minimum cost so as to meet the advertisement putting requirement of the user.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application as claimed.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application.
FIG. 1 is a flow chart illustrating a method of advertisement placement optimization according to an example embodiment.
Fig. 2 is a schematic diagram of an illustrated RQ-tree, according to an example embodiment.
FIG. 3 is a flow chart illustrating an advertisement delivery optimization apparatus according to an example embodiment.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the application. Rather, they are merely examples of apparatus and methods consistent with aspects of the application as detailed in the accompanying claims.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any or all possible combinations of one or more of the associated listed items.
FIG. 1 is a flowchart illustrating a method of advertisement placement optimization, as shown in FIG. 1, according to an exemplary embodiment, which may include the steps of:
step S11, obtaining social relations among consumers in a social network, advertisement on a road network, position information of the consumers and keyword information of the advertisement and the consumers;
Step S12, predicting the current audience of the original advertisement delivery through the anti-Top-k geographic social keyword query according to the social relationship, the position information and the keyword information;
step S13, if the current audience quantity is less than a set threshold value, obtaining candidate advertisements according to the difference of the keyword information;
step S14, establishing a set of candidate advertisements through RQ-trees;
And S15, accelerating the evaluation of the candidate advertisements by using a lower limit count table on the collection, and finding the advertisement with the minimum cost as the final advertisement.
As can be seen from the above embodiments, the application utilizes the anti-Top-k geographic social keyword query to effectively solve the problem that the original advertisement cannot attract enough potential consumers; evaluating candidate advertisements in batch by utilizing the RQ-tree structure; the advertisement evaluation efficiency is improved by utilizing a lower limit count table structure; and finally, returning the optimal advertisement with the minimum cost so as to meet the advertisement putting requirement of the user.
In the implementation of step S11, social relationships among consumers in the social network, advertisement on the road network, location information of the consumers, and keyword information of the advertisement and the consumers are obtained;
In a social network, the potential social relationship before a consumer is an important ring in advertisement propagation, and the accuracy of advertisement propagation analysis can be effectively enhanced by considering the social relationship; the road network comprises advertisement delivery places and position information of consumers, whether the advertisement delivery can affect corresponding consumers is estimated through the distance between the advertisement delivery places and the consumers, and secondly, the consumers have respective preference, advertisements have different types and positions, and the keyword information can effectively help the advertisements to attract more corresponding consumers. The application utilizes the reverse Top-k geographic social keyword query modification technology to effectively solve the problem that the original advertisement can not attract enough potential consumers; evaluating candidate advertisements in batch by utilizing the RQ-tree structure; the advertisement evaluation efficiency is improved by utilizing a lower limit count table structure; and finally, returning the optimal advertisement with the minimum cost so as to meet the advertisement putting requirement of the user.
In the implementation of step S12, the current audience of the original advertisement delivery is predicted by the inverse Top-k geographic social keyword query according to the social relationship, the location information and the keyword information;
in particular, according to the social relationship between the consumers, using As an advertisement propagation analysis, where Q ' represents any advertisement in advertisement set Q, F (u) represents u's friends, CU u→q represents u's friends that received advertisement Q, and C u→q represents the number of times consumer u received advertisement Q;
Based on the advertisement and the location information of the consumer Evaluating similarity of a spatial distance of consumer u to advertisement q, wherein D (u, q) represents a distance of consumer u to advertisement q;
According to the keyword information, obtaining advertisement promotion product type and consumer preference information, using Evaluating the pertinence of advertisement delivery, wherein ω and ω' represent keyword groups of the advertisement and the consumer, respectively;
combining the three information, using the reverse Top-k geographic social keyword query as an original query, and obtaining the current audience C (q).
In the implementation of step S13, if the number of the current audience is less than the set threshold, obtaining a candidate advertisement according to the difference of the keyword information;
Specifically, comparing the number of the current audience C (q) with a set threshold according to the number of the current audience C (q);
If less than the set threshold, the following two ways are performed:
(1) Adding keywords which are interested by consumers into the keywords of the original advertisement, and deleting keywords which are not interested by consumers; that is, for each consumer u e C (q), a set of keys - =q.key-u.key and key + =u.key-q.key is obtained, and the keywords contained in key + are added to the original advertisement, while the keywords contained in key - are reduced;
(2) Expanding the spreading force k of the original advertisement until each consumer becomes an audience for the advertisement; that is, for each consumer u e C (q), k is continually expanded until R (q, u), where R (q, u) is the ranking of advertisement q under consumer u's anti-Top-k geo-social keyword query;
According to (1) and (2) above, a candidate advertisement S Q is obtained.
In a specific implementation of step S14, a set of said candidate advertisements is established by means of an RQ-tree;
Specifically, for the candidate advertisement S Q, an RQ-tree is constructed by using iterative partitioning and a k-means algorithm, as shown in fig. 2, if the tree height is h, the fan-out of each non-leaf node is: The partitioning S Q continues until only one advertisement is contained in each leaf node.
I2U is an inverted merge file describing the keywords of the modified query stored in the node. I2U is an extension of the inverted file, comprising a word list containing all the different keywords and a set of inverted lists, each inverted list corresponding to a keyword. The inverted list for key t contains a series of tuples < q i,t.wmin,qj,t.wmax >, where q i is the modified query with the smallest key weight t.w min and q j is the modified query with the largest key weight t.w max.
In a specific implementation of step S15, the evaluation of the candidate advertisements is accelerated on the set using a lower-bound count table, and the advertisement with the smallest cost is found as the final advertisement.
Specifically, the calculation of the lower limit count table is specifically as follows:
given a set of candidate advertisements S Q, the lower bound similarity count table (i.e., CL l) contains t (1. Ltoreq.t. Ltoreq.Q'. Ltoreq.k) tuples < r i,Oi,si >, and is arranged in descending order of r i, where O i (1. Ltoreq.i.ltoreq.t) is a GIM tree node without parent-child relationships, r i is MinSim GSK(Oi,SQ) or MinMaxSim GSK(Oi,SQ), and t is satisfied with the formula And (2) minimum value of
The evaluation of accelerating candidate advertisements using the lower bound count table is specifically as follows:
Given a set of space objects O i and a set of candidate advertisements S Q, if CL l.rt≥MaxSimGSK(Oi,SQ), then the result of candidate q' ∈S Q does not exist in O i, and therefore O i can be pruned;
Given a set of spatial objects O i and a set of candidate advertisements S Q, the upper and lower bounds of similarity for each of step S12 are estimated as follows:
The upper limit of the similarity of the geographic social keywords is ：MaxSimGSK(Oi,SQ)＝α×Maxs(Oi,SQ)+β×Maxt(Oi,SQ)+γ×(1-Mind(Oi,SQ));, and the lower limit of the similarity of the geographic social keywords is ：MinSimGSK(Oi,SQ)＝α×Mins(Oi,SQ)+β×Mint(Oi,SQ)+γ×(1-Maxd(Oi,SQ));
The stricter geographical social key word similarity lower bound is ：MinMaxSimGSK(Oi,SQ)＝max{α×Mins(Oi,SQ)+β×MinMaxt(Oi,SQ)+γ×(1-Maxd(Oi,SQ)),α×MinMaxs(Oi,SQ)+β×Mint(Oi,SQ)+γ×(1-Maxd(Oi,SQ))}.
The geographical position similarity upper and lower bounds are estimated specifically as follows:
For the spatial object O e O i and advertisement q' e S Q, let D (O, q) be the shortest path distance from O to q, and maxD be the maximum distance of any two points in the road network, then the spatial distance is upper bound: and a spatial distance lower bound: /(I)
The social relationship similarity upper and lower bounds are estimated specifically as follows:
Given a set of candidate advertisements S Q and a set of spatial objects O i, the upper bound of social relationship similarity is: The social relationship similarity lower bound is: the stricter social relationship similarity lower bound is: /(I)
The keyword similarity upper and lower bounds are estimated specifically as follows:
Given a set of candidate advertisements S Q and a set of space objects O i,Nkey represent all the different numbers of keywords in the dataset, And/>The keyword similarity upper bound is calculated as follows:
The keyword similarity lower bound is calculated as follows:
the stricter keyword similarity lower bound is calculated as follows:
Wherein:
In addition, O i.ωj and S Q.ωj are defined as in formula Min t(Oi,SQ).
The cost of quantifying each advertisement q' is calculated as follows:
wherein η is a modification preference for the advertisement propagation force k value, 1- η is a modification preference for the advertisement keyword, |k '-k| is the degree of expansion of k, max u∈C(q) R (q, u) represents the maximum rank of the set C (q), D (q'. Key, q.key) is the Euclidean distance of the two keyword groups of the consumer, max u∈C(q) D (q.key, u.key) is the maximum distance from q.key to { u.key|u e C (q) };
and returning the advertisement with the minimum cost as the final advertisement.
The application also provides an embodiment of an advertisement delivery optimizing device corresponding to the embodiment of the advertisement delivery optimizing method.
FIG. 3 is a block diagram illustrating an advertisement delivery optimization device, according to an example embodiment. Referring to fig. 3, the apparatus includes:
an acquisition module 21, configured to acquire social relationships among consumers in a social network, advertisement and location information of consumers on a road, and keyword information of the advertisement and the consumers;
the prediction module 22 is configured to predict a current audience of the original advertisement delivery through the anti-Top-k geographic social keyword query according to the social relationship, the location information and the keyword information;
a candidate advertisement obtaining module 23, configured to obtain a candidate advertisement according to the difference of the keyword information if the current audience number is less than a set threshold;
A building module 24 for building a set of said candidate advertisements via RQ-tree;
The evaluation module 25 is configured to accelerate the evaluation of the candidate advertisements on the set using a lower-bound count table, and the specific manner in which the respective modules perform the operations in the above-described embodiments are described in detail in connection with the method embodiments, which will not be described in detail herein.
For the device embodiments, reference is made to the description of the method embodiments for the relevant points, since they essentially correspond to the method embodiments. The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purposes of the present application. Those of ordinary skill in the art will understand and implement the present application without undue burden.
Correspondingly, the application also provides electronic equipment, which comprises: one or more processors; a memory for storing one or more programs; the one or more programs, when executed by the one or more processors, cause the one or more processors to implement an advertisement placement optimization method as described above.
Correspondingly, the application further provides a computer readable storage medium, wherein computer instructions are stored, and the instructions are executed by a processor to realize the advertisement putting optimization method.
Other embodiments of the application will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of the application following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the application pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.
It is to be understood that the application is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the application is limited only by the appended claims.

Claims (7)

1. An advertisement delivery optimization method, comprising:
acquiring social relations among consumers in a social network, advertisements on a road network and position information of the consumers, and keyword information of the advertisements and the consumers;
predicting the current audience of the original advertisement delivery through the anti-Top-k geographic social keyword query according to the social relationship, the position information and the keyword information;
if the current audience quantity is less than the set threshold value, obtaining candidate advertisements according to the difference of the keyword information;
establishing a set of the candidate advertisements through an RQ-tree;
accelerating the evaluation of the candidate advertisements by using a lower limit count table on the set, and finding the advertisement with the minimum cost as a final advertisement;
according to the obtained information, predicting the current audience of advertisement delivery through the reverse Top-k geographic social keyword query comprises the following steps:
based on the social relationship between the consumers As an advertisement propagation analysis, where Q ' represents any advertisement in advertisement set Q, F (u) represents u's friends, CU u→q represents u's friends that received advertisement Q, and C u→q represents the number of times consumer u received advertisement Q;
Based on the advertisement and the location information of the consumer Evaluating similarity of a spatial distance of consumer u to advertisement q, wherein D (u, q) represents a distance of consumer u to advertisement q;
According to the keyword information, obtaining advertisement promotion product type and consumer preference information, using Evaluating the pertinence of advertisement delivery, wherein ω and ω' represent keyword groups of the advertisement and the consumer, respectively;
Combining the three information, using the reverse Top-k geographic social keyword query as an original query, and obtaining a current audience C (q);
Wherein establishing the set of candidate advertisements through the RQ-tree comprises:
Constructing an RQ-tree for the candidate advertisements S Q by using iterative partitioning and a k-means algorithm, and if the tree height is h, fanning out each non-leaf node is as follows: The partitioning S Q continues until only one advertisement is contained in each leaf node.
2. The method of claim 1, wherein if the current audience quantity is less than a set threshold, obtaining a candidate advertisement based on the difference in keyword information, comprising:
comparing the number of the current audience C (q) with a set threshold according to the number of the current audience C (q);
If less than the set threshold, the following two ways are performed:
(1) Adding keywords which are interested by consumers into the keywords of the original advertisement, and deleting keywords which are not interested by consumers;
(2) Expanding the spreading force k of the original advertisement until each consumer becomes an audience for the advertisement;
According to (1) and (2) above, a candidate advertisement S Q is obtained.
3. The method of claim 1, wherein accelerating the evaluation of the candidate advertisements on the set using a lower bound count table, finding the least costly advertisement as the final advertisement, comprises:
given a set of candidate advertisements S Q, the lower bound similarity count table (i.e., CL l) contains t (1. Ltoreq.t. Ltoreq.Q'. Ltoreq.k) tuples < r i,Oi,si >, and is arranged in descending order of r i, where O i (1. Ltoreq.i.ltoreq.t) is a GIM tree node without parent-child relationships, r i is MinSim GSK(Oi,SQ) or MinMaxSim GSK(Oi,SQ), and t is satisfied with the formula And (2) minimum value of
Given a set of space objects O i and a set of candidate advertisements S Q, if CL l.rt≥MaxSimGSK(Oi,SQ), then the result of candidate q' ∈S Q does not exist in O i, and therefore O i is pruned;
the cost of quantifying each advertisement q' is calculated as follows:
Wherein η is a modification preference for the advertisement propagation force k value, 1- η is a modification preference for the advertisement keyword, |k '-k| is the degree of expansion of k, max u∈C(q) R (q, u) represents the maximum rank of the set C (q), D (q'. Key, q.key) is the Euclidean distance of the two keyword groups of the consumer, max u∈C(q) D (q.key, u.key) is the maximum distance from q.key to { u.key|u e C (q) };
and returning the advertisement with the minimum cost as the final advertisement.
4. An advertisement delivery optimizing apparatus, comprising:
The acquisition module is used for acquiring social relations among consumers in the social network, advertisement on the road network, position information of the consumers and keyword information of the advertisement and the consumers;
The prediction module is used for predicting the current audience of the original advertisement delivery through the anti-Top-k geographic social keyword query according to the social relationship, the position information and the keyword information;
the candidate advertisement obtaining module is used for obtaining candidate advertisements according to the difference of the keyword information if the current audience quantity is less than a set threshold value;
a building module for building a set of the candidate advertisements through a RQ-tree;
the evaluation module is used for accelerating the evaluation of the candidate advertisements by utilizing a lower limit count table on the collection, and finding the advertisement with the minimum cost as a final advertisement;
according to the obtained information, predicting the current audience of advertisement delivery through the reverse Top-k geographic social keyword query comprises the following steps:
based on the social relationship between the consumers As an advertisement propagation analysis, where Q ' represents any advertisement in advertisement set Q, F (u) represents u's friends, CU u→q represents u's friends that received advertisement Q, and C u→q represents the number of times consumer u received advertisement Q;
Based on the advertisement and the location information of the consumer Evaluating similarity of a spatial distance of consumer u to advertisement q, wherein D (u, q) represents a distance of consumer u to advertisement q;
According to the keyword information, obtaining advertisement promotion product type and consumer preference information, using Evaluating the pertinence of advertisement delivery, wherein ω and ω' represent keyword groups of the advertisement and the consumer, respectively;
Combining the three information, using the reverse Top-k geographic social keyword query as an original query, and obtaining a current audience C (q);
Wherein establishing the set of candidate advertisements through the RQ-tree comprises:
Constructing an RQ-tree for the candidate advertisements S Q by using iterative partitioning and a k-means algorithm, and if the tree height is h, fanning out each non-leaf node is as follows: The partitioning S Q continues until only one advertisement is contained in each leaf node.
5. The apparatus of claim 4, wherein accelerating the evaluation of the candidate advertisements on the set using a lower bound count table to find the least costly advertisement as the final advertisement comprises:
Given a set of candidate advertisements S Q, whose lower bound similarity count table (i.e., CL l) contains t (1.ltoreq.t.ltoreq.Q'. Times.k) tuples > r i,Oi,si And (2) minimum value of
Given a set of space objects O i and a set of candidate advertisements S Q, if CL l.rt≥MaxSimGSK(Oi,SQ), then the result of candidate q' ∈S Q does not exist in O i, and therefore O i is pruned;
the cost of quantifying each advertisement q' is calculated as follows:
Wherein η is a modification preference for the advertisement propagation force k value, 1- η is a modification preference for the advertisement keyword, |k '-k| is the degree of expansion of k, max u∈C(q) R (q, u) represents the maximum rank of the set C (q), D (q'. Key, q.key) is the Euclidean distance of the two keyword groups of the consumer, max u∈C(q) D (q.key, u.key) is the maximum distance from q.key to { u.key|u e C (q) };
and returning the advertisement with the minimum cost as the final advertisement.
6. An electronic device, comprising:
one or more processors;
A memory for storing one or more programs;
The one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of any of claims 1-3.
7. A computer readable storage medium having stored thereon computer instructions which, when executed by a processor, implement the steps of the method of any of claims 1-3.
CN202111106131.4A 2021-09-22 2021-09-22 Advertisement putting optimization method and device, electronic equipment and storage medium Active CN113868549B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111106131.4A CN113868549B (en) 2021-09-22 2021-09-22 Advertisement putting optimization method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111106131.4A CN113868549B (en) 2021-09-22 2021-09-22 Advertisement putting optimization method and device, electronic equipment and storage medium

Publications (2)

Publication Number Publication Date
CN113868549A CN113868549A (en) 2021-12-31
CN113868549B true CN113868549B (en) 2024-05-17

Family

ID=78993208

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111106131.4A Active CN113868549B (en) 2021-09-22 2021-09-22 Advertisement putting optimization method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN113868549B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117743813B (en) * 2024-02-05 2024-04-23 蓝色火焰科技成都有限公司 Advertisement classification evaluation method, device and storage medium

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106844792A (en) * 2017-03-30 2017-06-13 微梦创科网络科技（中国）有限公司 A kind of primary information of social networks specifies audient's advertisement implementation method and system
CN107145526A (en) * 2017-04-14 2017-09-08 浙江大学 Geographical social activity keyword Reverse nearest neighbor inquiry processing method under a kind of road network
CN107846615A (en) * 2016-09-20 2018-03-27 创意引晴(开曼)控股有限公司 Visualize advertisement delivery system, put-on method and advertisement broadcast method
CN111292136A (en) * 2020-03-09 2020-06-16 李维 Mobile advertisement screening and putting method and system
CN112270569A (en) * 2020-11-02 2021-01-26 创新奇智(成都)科技有限公司 Advertisement putting method and device, electronic equipment and storage medium

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140236715A1 (en) * 2013-02-20 2014-08-21 Kenshoo Ltd. Targeted advertising in social media networks

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107846615A (en) * 2016-09-20 2018-03-27 创意引晴(开曼)控股有限公司 Visualize advertisement delivery system, put-on method and advertisement broadcast method
CN106844792A (en) * 2017-03-30 2017-06-13 微梦创科网络科技（中国）有限公司 A kind of primary information of social networks specifies audient's advertisement implementation method and system
CN107145526A (en) * 2017-04-14 2017-09-08 浙江大学 Geographical social activity keyword Reverse nearest neighbor inquiry processing method under a kind of road network
CN111292136A (en) * 2020-03-09 2020-06-16 李维 Mobile advertisement screening and putting method and system
CN112270569A (en) * 2020-11-02 2021-01-26 创新奇智(成都)科技有限公司 Advertisement putting method and device, electronic equipment and storage medium

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
节日文化的广告表征及建构-以2013-2014年央视公益性节日广告为例;陈璐;新闻界;20151231(012);全文 *

Also Published As

Publication number Publication date
CN113868549A (en) 2021-12-31

Similar Documents

Publication Publication Date Title
US11593894B2 (en) Interest recommendation method, computer device, and storage medium
CN108921221B (en) User feature generation method, device, equipment and storage medium
JP5543471B2 (en) Geo-time based forecast ad refinement
US20130232154A1 (en) Social network message categorization systems and methods
US20110093455A1 (en) Search and retrieval methods and systems of short messages utilizing messaging context and keyword frequency
US20100082653A1 (en) Event media search
US20110238591A1 (en) Automated profile standardization and competency profile generation
Wang et al. A flexible spatio-temporal indexing scheme for large-scale GPS track retrieval
US20140156669A1 (en) Apparatus and method for indexing electronic content
US8660901B2 (en) Matching of advertising sources and keyword sets in online commerce platforms
CN104063383A (en) Information recommendation method and device
CN102750292A (en) Method and device for providing interest points
CN109949089B (en) Method, device and terminal for determining display rate
CN105574208A (en) Calling card recommendation method and device
CN111400546B (en) Video recall method and video recommendation method and device
JP7166116B2 (en) Information processing device, information processing method, and program
CN112559901B (en) Resource recommendation method and device, electronic equipment, storage medium and computer program product
CN113868549B (en) Advertisement putting optimization method and device, electronic equipment and storage medium
Li et al. Dissecting foursquare venue popularity via random region sampling
US8799314B2 (en) System and method for managing information map
CN102331929A (en) Service classification and recommendation method based on service combination history
JP2011238169A (en) User attribute estimating device, user attribute estimating method, and program
US9529855B2 (en) Systems and methods for point of interest data ingestion
CN109299368B (en) Method and system for intelligent and personalized recommendation of environmental information resources AI
CN112529646A (en) Commodity classification method and device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant