CN109191160B - Advertisement putting method and system based on information flow scene refreshing behavior - Google Patents
Advertisement putting method and system based on information flow scene refreshing behavior Download PDFInfo
- Publication number
- CN109191160B CN109191160B CN201810732032.9A CN201810732032A CN109191160B CN 109191160 B CN109191160 B CN 109191160B CN 201810732032 A CN201810732032 A CN 201810732032A CN 109191160 B CN109191160 B CN 109191160B
- Authority
- CN
- China
- Prior art keywords
- advertisement
- information flow
- current user
- information
- scene
- 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
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
- G06Q30/0255—Targeted advertisements based on user history
- G06Q30/0256—User search
-
- 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
-
- 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
Abstract
The embodiment of the invention provides an advertisement putting method and system based on information flow scene refreshing behavior, wherein the method comprises the steps of screening an advertisement set with an putting target as a current user according to the putting orientation requirement of advertisements in an advertisement pool when the current user refreshes an information flow; according to historical refreshing behavior information of a current user, selecting an information flow scene of advertisement delivery of the current user and calculating a threshold value of the information flow scene; and if the quantity of the advertisements in the screened advertisement set is larger than the threshold value of the information flow scene of the advertisement delivery of the current user, delivering the advertisements to the current user according to a preset rule. The method increases the advertisement putting mode from the information flow to the information flow scene, effectively improves the upper limit of the putting capacity of the platform advertisement, and ensures the putting effect of the platform advertisement by combining the estimation scheme of the information flow scene threshold value and the click through rate.
Description
Technical Field
The invention relates to the technical field of Internet advertisement putting, in particular to an advertisement putting method and system based on information flow scene refreshing behavior.
Background
The information flow scene advertisement is a new favorite of internet advertisement, and the information flow scene advertisement is an advertisement mixed with content and is also called as the advertisement most similar to the content. In the prior art, there are two methods, one, that is, a method for delivering advertisements in an information flow scene based on a quantitative delivery method of advertisements in an information flow scene, and a method for distributing and delivering the total amount of advertisements to be delivered in proportion according to advertisement delivery capacities of different information flow scenes, so as to realize priority control of different information flow scenes, and in different information flow scenes, pre-estimation of ctr (Click-Through-Rate, i.e. an english abbreviation, or a Click Through Rate) is performed respectively. ctr is a general term for internet advertisement, and refers to the click arrival rate of the internet advertisement (picture advertisement, text advertisement, keyword advertisement, ranking advertisement, video advertisement, etc.), that is, the actual number of clicks of the advertisement (strictly speaking, the number of hits to the target page) divided by the display amount of the advertisement. And in the second method, the information flow scene is used as a characteristic, and the advertising is carried out after ctr (logistic regression) estimation is carried out by utilizing an lr algorithm.
In the process of implementing the invention, the inventor finds that at least the following problems exist in the prior art: the method for delivering the information flow scene advertisement based on the rationing has the following defects: the division of the priority of information flow scene release is not flexible, and the waste of high-quality exposure resources is easily caused; the estimated click through rate of the ctr is actually a local estimated result in different information flow scenes, so the advertisement delivery effect is limited by local optimization. The disadvantages of the second method are as follows: under the condition of large difference of information flow scenes, the difference of advertisement putting effects of different information flow scenes cannot be fully utilized, so that the advertisement is put on the information flow scene with higher priority and better effect; under the conditions that the fluctuation of the advertisement putting quantity is large and the advertisement putting capacity is relatively constant, the advertisement putting quantity is difficult to guarantee.
Disclosure of Invention
The embodiment of the invention provides an advertisement putting method and system based on information flow scene refreshing behavior, which automatically allocate different information flow scenes in real time, estimate the information flow scenes through uniform crt and put advertisements, realize global optimization under the condition of large difference of advertisement putting effects of different information flow scenes, and solve the problem of advertisement putting allocation of different information flow scenes under the condition of limited advertisement putting capacity.
In one aspect, an embodiment of the present invention provides an advertisement delivery method based on information flow scene refreshing behavior, where the method includes:
when the current user refreshes the information flow, screening out an advertisement set with the target of the current user according to the advertisement putting orientation requirement in the advertisement pool;
according to historical refreshing behavior information of a current user, selecting an information flow scene of advertisement delivery of the current user and calculating a threshold value of the information flow scene;
and if the quantity of the advertisements in the screened advertisement set is larger than the threshold value of the information flow scene of the advertisement delivery of the current user, delivering the advertisements to the current user according to a preset rule.
On the other hand, an embodiment of the present invention provides an advertisement delivery system based on information flow scene refreshing behavior, where the system includes:
the screening unit is used for screening out an advertisement set with the target of delivery as the current user according to the delivery orientation requirement of the advertisements in the advertisement pool when the current user refreshes the information flow;
the information flow scene selection unit is used for selecting the information flow scene of the advertisement delivery of the current user and calculating the threshold value of the information flow scene according to the historical refreshing behavior information of the current user;
and the advertisement putting unit is used for putting the advertisements to the current user according to a preset rule if the number of the advertisements in the screened advertisement set is larger than the threshold value of the information flow scene of the advertisement putting of the current user.
The technical scheme has the following beneficial effects: because the technical means of screening the advertisement set with the target of serving as the current user according to the serving orientation requirement of the advertisements in the advertisement pool when the current user refreshes the information flow is adopted, the technical effects of screening the advertisements to be served for the first time according to the current user and improving the accuracy of advertisement serving are achieved; because the information of the historical refreshing behavior of the current user is adopted, the information flow scene of the advertisement delivery of the current user is selected, so that the overall optimal technical effect under the condition of large difference of advertisement delivery effects under different information flow scenes is achieved; because the technical means that the advertisement is delivered to the current user according to the preset rule is adopted when the number of the advertisement sets with the delivery targets screened out as the current user is larger than the threshold value of the information flow scene of the advertisement delivery of the current user, the technical effect of ensuring the delivery effect of the advertisement is achieved while the advertisement delivery capacity is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flowchart of an advertisement delivery method based on information flow scene refresh behavior according to an embodiment of the present invention;
FIG. 2 is a schematic structural diagram of an advertisement delivery system based on information flow scene refresh behavior according to an embodiment of the present invention;
FIG. 3 is an overall framework diagram of advertisement delivery based on information flow scene refresh behavior according to an embodiment of the present invention;
fig. 4 is a schematic diagram of inserting an advertisement after information flow according to an embodiment 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, fig. 1 is a flowchart of an advertisement delivery method based on information flow scene refresh behavior according to an embodiment of the present invention;
101. when the current user refreshes the information flow, screening out an advertisement set with the target of the current user according to the advertisement putting orientation requirement in the advertisement pool;
102. according to historical refreshing behavior information of a current user, selecting an information flow scene of advertisement delivery of the current user and calculating a threshold value of the information flow scene;
103. and if the quantity of the advertisements in the screened advertisement set is larger than the threshold value of the information flow scene of the advertisement delivery of the current user, delivering the advertisements to the current user according to a preset rule.
Preferably, the information flow scene includes: the main information flow is forward, the main information flow is backward, the hot flow is forward, and the hot flow is backward;
preferably, the historical refresh behavior information of the current user includes: historical refreshing times of the current user in all information flow field scenes;
preferably, the selecting an information flow scenario for advertisement delivery of the current user according to the information of the historical refresh behavior of the current user specifically includes:
and selecting the advertisement delivery information flow scene of the current user according to the mean value and the variance of the historical refreshing times of the current user in all information flow scenes and the preset experience value range of the mean value and the variance corresponding to each information flow scene.
Preferably, the historical refresh behavior information of the current user further includes: feedback information of the current user to the advertisements put under different information flow scenes;
preferably, the calculating the threshold of the advertisement delivery information flow scenario of the current user according to the historical flow updating behavior information of the current user specifically includes:
obtaining priority coefficients of different information flow scenes according to feedback information of a current user on advertisements launched under different information flow scenes, wherein the feedback information of the current user on the advertisements launched under the different information flow scenes comprises the following steps: the actual click rate of the advertisements delivered under different information flow scenes is subjected to negative feedback;
obtaining a basic value of the current user according to the mean value or the median value of historical refreshing times of the current user in all information flow field scenes;
and obtaining the threshold value of the information flow scene of the advertisement delivery of the current user according to the basic value of the current user and the selected priority coefficient of the information flow scene of the advertisement delivery of the current user.
Preferably, if the number of the advertisements in the screened advertisement set is greater than the threshold of the information flow scene of the advertisement delivery of the current user, the advertisements are delivered to the current user according to a preset rule, and the method specifically includes:
according to the historical characteristics of the advertisement delivered by the advertiser, determining the estimated click through rate of the advertisement in the advertisement set with the delivery target of the current user, wherein the historical characteristics of the advertisement delivered by the advertiser comprise: historical click rate of advertisement delivery, gender of user delivering advertisement, age of user delivering advertisement, information flow scene of advertisement delivery, intersection of historical click rate of advertisement delivery and gender of user, intersection of historical click rate of advertisement delivery and age of user, and intersection of historical click rate of advertisement delivery and information flow scene;
obtaining the ordering of the advertisements in the advertisement set according to the estimated click through rate of the advertisements in the advertisement set with the current user as a delivery target;
and according to the sequence of the advertisements in the advertisement set, releasing a preset number of advertisements to the preset position of the selected advertisement releasing information flow scene of the current user according to an insertion rule.
Further preferably, the insertion rule for placing the advertisement to the preset position of the advertisement placement information flow scene of the user specifically includes:
when the current user refreshes the information stream in the selected advertisement delivery information stream scene, acquiring the number of unread information and the total number of information in a divided area of the current user;
if the difference between the total number of the information in the divided area and the number of the unread information is not less than a set number (for example, the set number is 2), an advertisement is inserted in the first position of the unread information.
Referring to fig. 2, fig. 2 is a schematic structural diagram of an advertisement delivery system based on information flow scene refresh behavior according to an embodiment of the present invention;
the screening unit 21 is configured to screen out an advertisement set with an advertisement target of the current user according to the advertisement delivery targeting requirement in the advertisement pool when the current user refreshes the information stream;
an information flow scene selection unit 22, configured to select an information flow scene for advertisement delivery of a current user and calculate a threshold of the information flow scene according to historical refresh behavior information of the current user;
and the advertisement putting unit 23 is configured to put the advertisement to the current user according to a preset rule if the number of the advertisements in the screened advertisement set is greater than the threshold of the information flow scene of advertisement putting of the current user.
Preferably, the information flow scene includes: the main information flow is forward, the main information flow is backward, the hot flow is forward, and the hot flow is backward;
preferably, the historical refresh behavior information of the current user includes: historical refreshing times of the current user in all information flow field scenes;
preferably, the information flow scene selection unit specifically includes:
and the selection module is used for selecting the advertisement delivery information flow scene of the current user according to the mean value and the variance of the historical information flow refreshing times of the current user under all information flow scenes and the preset experience range of the mean value and the variance corresponding to each information flow scene.
The historical refreshing behavior information of the current user further comprises: feedback information of the current user to the advertisements put under different information flow scenes;
further preferably, the information flow scene selection unit specifically further includes:
the coefficient acquisition module is configured to obtain priority coefficients of different information flow scenarios according to feedback information of a current user on advertisements delivered under different information flow scenarios, where the feedback information of the current user on the advertisements delivered under different information flow scenarios includes: the actual click rate of the advertisements delivered under different information flow scenes is subjected to negative feedback;
the basic value acquisition unit is used for acquiring the basic value of the current user according to the mean value or the median value of the historical refreshing times of the current user in all information flow fields;
and the calculation module is used for obtaining the threshold value of the information flow scene of the advertisement delivery of the current user according to the basic value of the current user and the selected priority coefficient of the information flow scene of the advertisement delivery of the current user.
Preferably, the advertisement delivery unit specifically includes:
the estimation module is used for determining the estimation click through rate of the advertisement in the advertisement set with the current user as the delivery target according to the historical characteristics of the advertisement delivered by the advertiser, and the historical characteristics of the advertisement delivered by the advertiser include: historical click rate of advertisement delivery, gender of user delivering advertisement, age of user delivering advertisement, information flow scene of advertisement delivery, intersection of historical click rate of advertisement delivery and gender of user, intersection of historical click rate of advertisement delivery and age of user, and intersection of historical click rate of advertisement delivery and information flow scene;
the ordering module is used for obtaining the ordering of the advertisements in the advertisement sets according to the estimated click through rate of the advertisements in the advertisement sets with the delivery targets of the current users;
and the advertisement insertion module is used for putting a preset number of advertisements to the preset positions of the selected advertisement putting information flow scene of the current user according to the ordering of the advertisements in the advertisement set and the insertion rule.
Further preferably, the advertisement insertion module specifically includes:
the number obtaining submodule is used for obtaining the number of unread messages and the total number of messages in the divided area of the current user when the current user refreshes the message stream in the selected advertisement delivery message stream scene;
and the inserting sub-module is used for inserting an advertisement at the first position of the unread information if the difference between the total number of the information in the divided areas and the number of the unread information is not less than the set number.
The technical scheme has the following technical effects: because the advertisement is put in four different information flow scenes, namely, the forward information flow, the backward information flow, the forward hot flow and the backward hot flow, the advertisement is put in the information flow scene refreshed backward after the main information flow and the backward hot flow, the putting capacity of the information flow scene advertisement is effectively improved, and the upper limit of the putting quantity of the information flow scene advertisement is improved; the technical means of selecting the advertisement delivery information flow scene of the current user according to the mean value and the variance of the historical information flow refreshing behavior of the current user and the preset experience value range of the mean value and the variance corresponding to each information flow scene respectively is adopted, so that the technical effect of improving the advertisement delivery effect is achieved; because the threshold value of the advertisement putting information flow scene of the current user is calculated, the technical means of putting the advertisement can be realized only on the premise that the number of the advertisements to be put is larger than the threshold value of the information scene, meanwhile, the technical means of estimating the ctr of the advertisement to be put and the technical means of putting the advertisement with higher ctr are adopted according to the crossing of the historical click rate of the advertisement put by an advertiser, the gender of the user who puts the advertisement, the age of the user who puts the advertisement and the information flow scene of the advertisement, the crossing of the historical click rate of the advertisement to be put and the gender of the user, the crossing of the historical click rate of the advertisement to be put and the age of the user and the crossing of the information flow scene of the advertisement to be put, and the advertisement with higher ctr, so that the advertisement putting accuracy is improved. In conclusion, the technical scheme improves the upper limit of the delivery quantity of the information flow scene advertisements on the premise of ensuring the advertisement delivery effect.
The technical solution is further explained by taking specific examples as follows:
referring specifically to fig. 3, fig. 3 is an overall framework diagram of advertisement delivery based on information flow scene refresh behavior according to an embodiment of the present invention.
When the current user refreshes the information flow, according to the refreshing behavior, the targeted delivery target of the advertisement screened from the advertisement pool is the advertisement set of the current user, which is the first round of screening, and the number of the advertisements in the advertisement set is less than that in the advertisement pool. According to the historical refreshing behavior information of the current user, the historical refreshing behavior information of the user comprises the following steps: and the current user selects the information flow scene of the advertisement delivery of the current user according to the feedback information of the advertisement delivered under different information flow scenes. Historical refreshing times of the current user in all information flow field scenes; and selecting the advertisement delivery information flow scene of the current user according to the mean value and the variance of the historical information flow refreshing times of the current user and the preset experience value range of the mean value and the variance corresponding to each information flow scene. In a preferred embodiment, when the average value of daily refreshing of the current user is less than or equal to 3 and the variance is equal to 4, the information flow scene after the main information flow is performed on the current user is selected to insert the advertisement.
Obtaining priority coefficients of different information flow scenes according to feedback information of a current user on advertisements launched under the different information flow scenes, wherein the information flow scenes comprise: the main information flow is forward, the main information flow is backward, the hot flow is forward, and the hot flow is backward; the feedback information of the current user on the advertisement released under different information flow scenes comprises the following steps: and negatively feeding back the actual click rate of the advertisements delivered under different information flow scenes. In a preferred embodiment, the information flow scenario is a description of a microblog refreshing behavior of a current user, and the main information flow forward direction refers to a refreshing behavior of the current user pulling down from the top to the bottom of the main information flow; the main information flow backward direction refers to a refresh behavior of a current user pulling down from the bottom to the top of the main information flow, the hot flow forward direction refers to a refresh behavior of a current user pulling down from the top of the hot information flow, and the hot flow backward direction refers to a refresh behavior of a current user pulling down from the bottom to the top of the hot information flow. The negative feedback of the current user on the advertisements delivered under different information flow scenes means that the current user selects options such as uninteresting and poor content quality of the viewed advertisements under different information flow scenes, and performs shielding operation on the delivered advertisements, and the shielding operation is called as negative feedback of the advertisements.
Obtaining a basic value of the current user according to the mean value or the median value of the historical refreshing times of the current user; and obtaining the threshold value of the advertisement delivery information flow scene of the current user according to the basic value of the current user and the selected priority coefficient of the advertisement delivery information flow scene of the current user. The four kinds of information flow scenes, i.e. the main information flow forward direction, the main information flow backward direction, the hot flow forward direction and the hot flow backward direction, respectively correspond to the threshold value Tmf，Tmb，ThfAnd Thb. The calculation formula of the information flow scene is as follows: t isx＝wxBase, wherein TxAre respectively Tmf，Tmb，ThfAnd Thb，wxRespectively as follows: w is amfPriority coefficient, w, for the forward direction of the main information streammbBackward priority coefficient of main information flow, whfPriority coefficient of hot-stream forward, whbAnd the higher the priority coefficient is, the smaller the coefficient is. Continuing with the preferred embodiment, the base can take the mean or median of the historical refresh behavior of the current user, and can release the information flow field in a wide rangeWhen telling, wxThe threshold for this information flow scenario is also 0.
If the quantity C of the advertisements in the screened advertisement set is larger than the threshold value T of the information flow scene of the advertisement delivery of the current userxAnd if not, not delivering the advertisement to the current user.
And respectively estimating ctr for the advertisements in the advertisement set of which the targeted delivery target is the current user and which are obtained through the first round of screening, wherein the estimation of ctr is that the system estimates the possible click through rate of a certain advertisement before the advertisement is delivered under a certain condition. Extraction: the method comprises the steps of training original characteristics and estimating click through rate by adopting 7 characteristics such as historical click rate of delivered advertisements, gender of users delivered advertisements, age of users delivered advertisements, information flow scenes of delivered advertisements, intersection of historical click rate of delivered advertisements and gender of users, intersection of historical click rate of delivered advertisements and age of users, intersection of historical click rate of delivered advertisements and information flow scenes and the like as the original characteristics by adopting a conventional lr (logistic regression) method. Wherein: the intersection of the historical click rate of the delivered advertisements and the gender of the user refers to the click rate of the advertisements on different genders, the intersection of the historical click rate of the delivered advertisements and the age of the user refers to the click rate of the advertisements on different age groups, and the intersection of the historical click rate of the delivered advertisements and the information flow scene refers to the click rate of the advertisements on different information flow scenes. The original features are the basis of model training, the final upper limit of the model effect is determined, the re-extraction and abstraction of the original features belong to detail optimization, and the re-optimization determines the degree of approaching the upper limit of the effect.
Referring to fig. 4 in particular, fig. 4 is a schematic diagram illustrating advertisement insertion after information flow according to an embodiment of the present invention. The information flow direction comprises the following steps: the main information flow is backward and the hot flow is backward. And obtaining the ordering of the advertisements in the advertisement set according to the estimated ctr of each advertisement, and putting a preset number of advertisements to the information flow scene of the current user according to the ordering of the advertisements. Continuing with the preferred embodiment, when the current user refreshes the main information stream backward each time, the intelligent advertisement delivery platform obtains Unread (Unread information) and Span (within a partition region), belongs to an intra-row element in the CSS definition, and defines a region within a row, that is, a region within a row can be divided into several regions by < Span >, so as to achieve a certain specific effect) parameters, where the Unread parameter is the number of Unread information within the partition region, and the Span parameter is the total number of information within the partition region. When Span-Unread is more than or equal to 2, inserting an advertisement into the first Unread position of the user after the main information flow, wherein the advertisement position is 1; if Span-Unread < 2, no advertisement is inserted.
It should be understood that the specific order or hierarchy of steps in the processes disclosed is an example of exemplary approaches. Based upon design preferences, it is understood that the specific order or hierarchy of steps in the processes may be rearranged without departing from the scope of the present disclosure. The accompanying method claims present elements of the various steps in a sample order, and are not intended to be limited to the specific order or hierarchy presented.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. To those skilled in the art; various modifications to these embodiments will be readily apparent, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the disclosure. Thus, the present disclosure is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
What has been described above includes examples of one or more embodiments. It is, of course, not possible to describe every conceivable combination of components or methodologies for purposes of describing the aforementioned embodiments, but one of ordinary skill in the art may recognize that many further combinations and permutations of various embodiments are possible. Accordingly, the embodiments described herein are intended to embrace all such alterations, modifications and variations that fall within the scope of the appended claims. Furthermore, to the extent that the term "includes" is used in either the detailed description or the claims, such term is intended to be inclusive in a manner similar to the term "comprising" as "comprising" is interpreted when employed as a transitional word in a claim. Furthermore, any use of the term "or" in the specification of the claims is intended to mean a "non-exclusive or".
Those of skill in the art will further appreciate that the various illustrative logical blocks, units, and steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both. To clearly illustrate the interchangeability of hardware and software, various illustrative components, elements, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design requirements of the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present embodiments.
The various illustrative logical blocks, or elements, described in connection with the embodiments disclosed herein may be implemented or performed with a general purpose processor, a digital signal processor, an Application Specific Integrated Circuit (ASIC), a field programmable gate array or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general-purpose processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices, e.g., a digital signal processor and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a digital signal processor core, or any other similar configuration.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may be stored in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. For example, a storage medium may be coupled to the processor such the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium may be integral to the processor. The processor and the storage medium may reside in an ASIC, which may be located in a user terminal. In the alternative, the processor and the storage medium may reside in different components in a user terminal.
In one or more exemplary designs, the functions described above in connection with the embodiments of the invention may be implemented in hardware, software, firmware, or any combination of the three. If implemented in software, the functions may be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Computer-readable media includes both computer storage media and communication media that facilitate transfer of a computer program from one place to another. Storage media may be any available media that can be accessed by a general purpose or special purpose computer. For example, such computer-readable media can include, but is not limited to, RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to carry or store program code in the form of instructions or data structures and which can be read by a general-purpose or special-purpose computer, or a general-purpose or special-purpose processor. Additionally, any connection is properly termed a computer-readable medium, and, thus, is included if the software is transmitted from a website, server, or other remote source via a coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL), or wirelessly, e.g., infrared, radio, and microwave. Such discs (disk) and disks (disc) include compact disks, laser disks, optical disks, DVDs, floppy disks and blu-ray disks where disks usually reproduce data magnetically, while disks usually reproduce data optically with lasers. Combinations of the above may also be included in the computer-readable medium.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are merely exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (6)
1. An advertisement putting method based on information flow scene refreshing behavior is characterized by comprising the following steps:
when the current user refreshes the information flow, screening out an advertisement set with the target of the current user according to the advertisement putting orientation requirement in the advertisement pool;
according to historical refreshing behavior information of a current user, selecting an information flow scene of advertisement delivery of the current user and calculating a threshold value of the information flow scene;
if the quantity of the advertisements in the screened advertisement set is larger than the threshold value of the information flow scene of the advertisement delivery of the current user, delivering the advertisements to the current user according to a preset rule;
the information flow scene comprises: the main information flow is forward, the main information flow is backward, the hot flow is forward, and the hot flow is backward;
the historical refreshing behavior information of the current user comprises the following steps: historical refreshing times of the current user in all information flow field scenes;
the selecting an information flow scene of advertisement delivery of the current user according to the historical refreshing behavior information of the current user specifically includes: selecting an advertisement delivery information flow scene of the current user according to the mean value and the variance of historical refreshing times of the current user in all information flow scenes and the preset experience value range of the mean value and the variance corresponding to each information flow scene;
the historical refreshing behavior information of the current user further comprises: feedback information of the current user to the advertisements put under different information flow scenes;
the calculating the threshold of the information flow scene of the advertisement delivery of the current user according to the historical refreshing behavior information of the current user specifically includes:
obtaining priority coefficients of different information flow scenes according to feedback information of a current user on advertisements launched under different information flow scenes, wherein the feedback information of the current user on the advertisements launched under the different information flow scenes comprises the following steps: the actual click rate of the advertisements delivered under different information flow scenes is subjected to negative feedback;
obtaining a basic value of the current user according to the mean value or the median value of historical refreshing times of the current user in all information flow field scenes;
and obtaining the threshold value of the information flow scene of the advertisement delivery of the current user according to the basic value of the current user and the selected priority coefficient of the information flow scene of the advertisement delivery of the current user.
2. The advertisement delivery method based on information flow scene refreshing behavior according to claim 1, wherein if the number of advertisements in the screened advertisement set is greater than the threshold of the information flow scene of advertisement delivery of the current user, the advertisement is delivered to the current user according to a preset rule, specifically comprising:
according to the historical characteristics of the advertisement delivered by the advertiser, determining the estimated click through rate of the advertisement in the advertisement set with the delivery target of the current user, wherein the historical characteristics of the advertisement delivered by the advertiser comprise: historical click rate of advertisement delivery, gender of user delivering advertisement, age of user delivering advertisement, information flow scene of advertisement delivery, intersection of historical click rate of advertisement delivery and gender of user, intersection of historical click rate of advertisement delivery and age of user, and intersection of historical click rate of advertisement delivery and information flow scene;
obtaining the ordering of the advertisements in the advertisement set according to the estimated click through rate of the advertisements in the advertisement set with the current user as a delivery target;
and according to the sequence of the advertisements in the advertisement set, releasing a preset number of advertisements to the preset position of the selected advertisement releasing information flow scene of the current user according to an insertion rule.
3. The advertisement delivery method based on information flow scene refreshing behavior according to claim 2, wherein the insertion rule specifically comprises:
when the current user refreshes the information stream in the selected advertisement delivery information stream scene, acquiring the number of unread information and the total number of information in the divided area of the current user;
and if the difference between the total number of the information in the divided area and the number of the unread information is not less than the set number, inserting an advertisement at the first position of the unread information.
4. An advertisement delivery system based on information flow scene refreshing behavior, the system comprising:
the screening unit is used for screening out an advertisement set with the target of delivery as the current user according to the delivery orientation requirement of the advertisements in the advertisement pool when the current user refreshes the information flow;
the information flow scene selection unit is used for selecting the information flow scene of the advertisement delivery of the current user and calculating the threshold value of the information flow scene according to the historical refreshing behavior information of the current user;
the advertisement putting unit is used for putting advertisements to the current user according to a preset rule if the number of the advertisements in the screened advertisement set is larger than the threshold value of the information flow scene of the advertisement putting of the current user;
the information flow scene comprises: the main information flow is forward, the main information flow is backward, the hot flow is forward, and the hot flow is backward;
the historical refreshing behavior information of the current user comprises the following steps: historical refreshing times of the current user in all information flow field scenes;
the information flow scene selection unit specifically includes:
the selection module is used for selecting the advertisement delivery information flow scene of the current user according to the mean value and the variance of the historical refreshing times of the current user under all information flow scenes and the preset experience value range of the mean value and the variance corresponding to each information flow scene;
the historical refreshing behavior information of the current user further comprises: feedback information of the current user to the advertisements put under different information flow scenes;
the information flow scene selection unit specifically further includes:
the coefficient acquisition module is configured to obtain priority coefficients of different information flow scenarios according to feedback information of a current user on advertisements delivered under different information flow scenarios, where the feedback information of the current user on the advertisements delivered under different information flow scenarios includes: the actual click rate of the advertisements delivered under different information flow scenes is subjected to negative feedback;
the basic value acquisition unit is used for acquiring the basic value of the current user according to the mean value or the median value of the historical refreshing times of the current user in all information flow fields;
and the calculation module is used for obtaining the threshold value of the information flow scene of the advertisement delivery of the current user according to the basic value of the current user and the selected priority coefficient of the information flow scene of the advertisement delivery of the current user.
5. The advertisement delivery system based on information flow scene refreshing behavior according to claim 4, wherein the advertisement delivery unit specifically comprises:
the estimation module is used for determining the estimation click through rate of the advertisement in the advertisement set with the current user as the delivery target according to the historical characteristics of the advertisement delivered by the advertiser, and the historical characteristics of the advertisement delivered by the advertiser include: historical click rate of advertisement delivery, gender of user delivering advertisement, age of user delivering advertisement, information flow scene of advertisement delivery, intersection of historical click rate of advertisement delivery and gender of user, intersection of historical click rate of advertisement delivery and age of user, and intersection of historical click rate of advertisement delivery and information flow scene;
the ordering module is used for obtaining the ordering of the advertisements in the advertisement sets according to the estimated click through rate of the advertisements in the advertisement sets with the delivery targets of the current users;
and the advertisement insertion module is used for putting a preset number of advertisements to the preset positions of the selected advertisement putting information flow scene of the current user according to the insertion rule and the sequencing of the advertisements in the advertisement set.
6. The advertisement delivery system based on information flow scene refreshing behavior according to claim 5, wherein the advertisement insertion module specifically comprises:
the number obtaining submodule is used for obtaining the number of unread messages and the total number of messages in the divided area of the current user when the current user refreshes the message stream in the selected advertisement delivery message stream scene;
and the inserting sub-module is used for inserting an advertisement at the first position of the unread information if the difference between the total number of the information in the divided areas and the number of the unread information is not less than the set number.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810732032.9A CN109191160B (en) | 2018-07-05 | 2018-07-05 | Advertisement putting method and system based on information flow scene refreshing behavior |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810732032.9A CN109191160B (en) | 2018-07-05 | 2018-07-05 | Advertisement putting method and system based on information flow scene refreshing behavior |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109191160A CN109191160A (en) | 2019-01-11 |
| CN109191160B true CN109191160B (en) | 2022-02-01 |
Family
ID=64948907
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810732032.9A Active CN109191160B (en) | 2018-07-05 | 2018-07-05 | Advertisement putting method and system based on information flow scene refreshing behavior |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109191160B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111274513B (en) * | 2020-01-20 | 2023-11-28 | 北京有竹居网络技术有限公司 | Window display method, device, terminal and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106846044A (en) * | 2016-12-29 | 2017-06-13 | 新浪网技术(中国)有限公司 | Method and device is delivered on a kind of display advertisement line |
| 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 |
| CN107507043A (en) * | 2017-09-20 | 2017-12-22 | 微梦创科网络科技（中国）有限公司 | Online advertisement put-on method and system |
| CN107657488A (en) * | 2017-10-19 | 2018-02-02 | 厦门美柚信息科技有限公司 | Advertisement putting processing method and processing device based on advertisement matching |
| CN107657486A (en) * | 2017-10-19 | 2018-02-02 | 厦门美柚信息科技有限公司 | A kind of advertisement placement method and device |
-
2018
- 2018-07-05 CN CN201810732032.9A patent/CN109191160B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106846044A (en) * | 2016-12-29 | 2017-06-13 | 新浪网技术(中国)有限公司 | Method and device is delivered on a kind of display advertisement line |
| 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 |
| CN107507043A (en) * | 2017-09-20 | 2017-12-22 | 微梦创科网络科技（中国）有限公司 | Online advertisement put-on method and system |
| CN107657488A (en) * | 2017-10-19 | 2018-02-02 | 厦门美柚信息科技有限公司 | Advertisement putting processing method and processing device based on advertisement matching |
| CN107657486A (en) * | 2017-10-19 | 2018-02-02 | 厦门美柚信息科技有限公司 | A kind of advertisement placement method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109191160A (en) | 2019-01-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106846044B (en) | Online advertising display method and device | |
| US9424595B2 (en) | Customized content delivery based on geographic area | |
| KR101228965B1 (en) | Systems and methods for auctioning wireless device assets and providing wireless devices with an asset allocation option | |
| US10282758B1 (en) | Pricing control in a real-time network-based bidding environment | |
| US20130212611A1 (en) | User directed customized adjustable content insertion | |
| CN110348908B (en) | Advertisement delivery budget control method and device | |
| CN104751343A (en) | Advertisement putting method and device and advertisement putting server | |
| CN107507043B (en) | Online advertisement putting method and system | |
| JP2012533109A (en) | Method and mechanism for analyzing multimedia content | |
| US11915268B2 (en) | Transmedia story management systems and methods | |
| CN108269109A (en) | A kind of Advertisement arrangement injected volume equalization methods and device | |
| CN110264268B (en) | Advertisement putting device, method, equipment and storage medium thereof | |
| CN104967690A (en) | Information push method and device | |
| CN109886735A (en) | A kind of method and device of advertisement pushing | |
| CN106412635B (en) | A kind of intelligence advertisement placement method and system | |
| CN109191160B (en) | Advertisement putting method and system based on information flow scene refreshing behavior | |
| CN104602041A (en) | Content supply device and method | |
| CN109688217B (en) | Message pushing method and device and electronic equipment | |
| CN110362751B (en) | Service recommendation method, device, computer equipment and storage medium | |
| CN111815373A (en) | Conversion cost optimization method and device, electronic equipment and storage medium | |
| CN111090810A (en) | Application message pushing method and device and electronic equipment | |
| US9854290B2 (en) | System and method for data-driven ad-insertion in online video streams | |
| US11175807B1 (en) | Intelligent contextual video thumbnail display | |
| CN109272358B (en) | Media information display method and device | |
| CN104506892B (en) | Data adjustment 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 |