CN116137004A - Attribution method, attribution system and attribution computer for advertisement putting effect - Google Patents

Attribution method, attribution system and attribution computer for advertisement putting effect Download PDF

Info

Publication number
CN116137004A
CN116137004A CN202310417409.2A CN202310417409A CN116137004A CN 116137004 A CN116137004 A CN 116137004A CN 202310417409 A CN202310417409 A CN 202310417409A CN 116137004 A CN116137004 A CN 116137004A
Authority
CN
China
Prior art keywords
advertisement
model
click
attribution
user
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202310417409.2A
Other languages
Chinese (zh)
Other versions
CN116137004B (en
Inventor
姚尧之
廖常训
吴杰
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.)
Jiangxi Moment Interactive Technology Co ltd
Original Assignee
Jiangxi Moment Interactive Technology Co ltd
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 Jiangxi Moment Interactive Technology Co ltd filed Critical Jiangxi Moment Interactive Technology Co ltd
Priority to CN202310417409.2A priority Critical patent/CN116137004B/en
Publication of CN116137004A publication Critical patent/CN116137004A/en
Application granted granted Critical
Publication of CN116137004B publication Critical patent/CN116137004B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G06Q30/0242—Determining effectiveness of advertisements
    • 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
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Strategic Management (AREA)
  • Finance (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention provides an attribution method, a attribution system and a attribution computer for advertisement putting effect, wherein the attribution method comprises the following steps: acquiring the putting information of each advertisement; constructing an advertisement conversion model based on the putting information; constructing a click model according to historical click data of each advertisement in the delivery channel data, and predicting the click rate of each advertisement by utilizing the user preference model and the click model constructed by the delivery channel data to obtain the click rate; calculating attribution coefficients of the advertisements according to the click rate and the putting channel data; and calculating the contribution degree of the user to each advertisement according to the consumption probability model and the attribution coefficient of the user, and determining the attribution result of each advertisement based on the contribution degree. According to the invention, the attribution conditions of the advertisement are supplemented by using the click sequence and the historical click data of each user, and the attribution problems of the advertisement are assisted by using a plurality of models, so that the processing efficiency of attribution of the advertisement is further improved, and the influence of multiple marketing channels on attribution results is reduced.

Description

Attribution method, attribution system and attribution computer for advertisement putting effect
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a method, a system, and a computer for attributing an advertisement delivery effect.
Background
With rapid development of science and technology and improvement of living standard of people, advertisement is one of the most popular propaganda means at present, and along with arrival of the Internet age, multi-channel marketing is gradually becoming the propaganda means of advertisement.
Advertisement attribution is a more specific business scenario defined as "evaluation of the contribution value of different contact points of different marketing channels experienced in a user's journey to reach conversion objectives", i.e. attribution problem of users to advertisement conversion in different marketing channels. In the prior art, the attribution problem of the advertisement is that a heuristic method based on rules is adopted, only the first marketing channel or the last marketing channel is always considered in the method, and the influence and the difference caused by other marketing channels are ignored.
Disclosure of Invention
Based on this, an object of the present invention is to provide a method, a system and a computer for attributing advertisement putting effect, so as to at least solve the disadvantages of the above-mentioned technologies.
The invention provides an attribution method of advertisement putting effect, comprising the following steps:
acquiring the putting information of each advertisement, wherein the putting information comprises advertisement type data and putting channel data;
constructing an advertisement conversion model based on the advertisement type data and the delivery channel data, and acquiring historical click data of each advertisement in the corresponding delivery channel data;
constructing a corresponding click model according to the historical click data, constructing a user preference model based on the delivery channel data, and predicting the click rate of each advertisement by using the user preference model and the click model to obtain the click rate corresponding to each advertisement;
calculating attribution coefficients of the advertisements according to the click rate and the delivery channel data, and constructing a consumption probability model of a user;
and calculating the contribution degree of the user to each advertisement according to the consumption probability model and the attribution coefficient, and determining attribution results of each advertisement based on the contribution degree.
Further, the advertisement type data includes a targeted advertisement and a regular advertisement, and the step of constructing an advertisement conversion model based on the advertisement type data and the delivery channel data includes:
calculating cost information corresponding to each piece of delivery channel data by using a cost conversion model, and respectively calculating the accuracy of the targeted advertisement and the conventional advertisement based on the cost information;
respectively acquiring propagation parameters of the targeted advertisement and the conventional advertisement, and respectively constructing an effect perception model according to the accuracy and the propagation parameters of the targeted advertisement and the conventional advertisement;
and acquiring consumption parameters of the user on the targeted advertisement and the conventional advertisement, and constructing a corresponding advertisement conversion model by utilizing the consumption parameters and the effect perception model.
Further, the step of constructing a corresponding click model according to the historical click data includes:
analyzing advertisement click information triggered by a user in the historical click data, wherein the advertisement click information comprises advertisement information clicked by the user and channel information corresponding to the advertisement information;
and constructing a click model corresponding to the historical click data according to the advertisement information and the channel information.
Further, the step of constructing a user preference model based on the delivery channel data includes:
modeling the channel tendency of the delivery channel data by using a channel distribution predictor to obtain a channel tendency model;
and obtaining the usage degree of each putting channel by a user, and carrying out model optimization on the channel trend model based on the usage degree so as to obtain a corresponding user preference model.
Further, the step of predicting the click rate of each advertisement by using the user preference model and the click model to obtain the click rate corresponding to each advertisement includes:
the model learners of the user preference model and the click model are respectively analyzed, and classification learning is carried out on the model learners of the user preference model and the click model respectively;
combining the model learners after the classification learning, and importing the model learners into a click predictor to generate a new model learner, and constructing a click rate prediction model by using the new model learner;
and predicting the click rate of each advertisement by using the click rate prediction model so as to obtain the click rate corresponding to each advertisement.
Further, the calculation formula of the advertisement conversion model is as follows:
Figure SMS_1
；
Figure SMS_2
；
Figure SMS_3
；
in the method, in the process of the invention,
Figure SMS_5
representing consumption parameters of the user for the targeted advertisement; />
Figure SMS_6
Representing the accuracy of the targeted advertisement; />
Figure SMS_14
A propagation parameter representing a targeted advertisement; />
Figure SMS_7
Compensation parameters representing advertisement type data; />
Figure SMS_16
Representing consumption parameters of a user for conventional advertisements; />
Figure SMS_9
Representing the accuracy of the conventional advertisement; />
Figure SMS_17
A propagation parameter representing a regular advertisement; />
Figure SMS_12
Representing an advertisement conversion model;
Figure SMS_18
representing the number of users; />
Figure SMS_4
Representing time; />
Figure SMS_13
Conversion supplement parameter representing advertisement type data, +.>
Figure SMS_11
Conversion factor representing targeted advertisement, +.>
Figure SMS_15
Conversion factor representing conventional advertisement, ++>
Figure SMS_10
Indicating the cross conversion coefficient between the targeted advertisement and the regular advertisement, < >>
Figure SMS_19
Differential indicators representing ad conversion on different users, obeying +.>
Figure SMS_8
Normal distribution.
Further, the calculation formula of the click model is as follows:
Figure SMS_20
；
in the method, in the process of the invention,
Figure SMS_27
representing user +.>
Figure SMS_22
；/>
Figure SMS_33
Indicate->
Figure SMS_23
Clicking for the second time; />
Figure SMS_32
Indicate->
Figure SMS_25
User +.>
Figure SMS_34
In->
Figure SMS_30
An embedded vector of the secondary click; />
Figure SMS_36
Indicate->
Figure SMS_21
User +.>
Figure SMS_31
In->
Figure SMS_28
Clicking the corresponding channel information for the second time; />
Figure SMS_35
Indicate->
Figure SMS_29
User +.>
Figure SMS_37
In->
Figure SMS_24
A binary vector of secondary clicks; />
Figure SMS_38
Representing the conversion result of the whole click sequence, +.>
Figure SMS_26
。/>
The invention also provides an attribution system of the advertisement putting effect, which comprises the following steps:
the system comprises a delivery information acquisition module, a delivery information processing module and a delivery information processing module, wherein the delivery information acquisition module is used for acquiring delivery information of each advertisement, and the delivery information comprises advertisement type data and delivery channel data;
the advertisement conversion model construction module is used for constructing an advertisement conversion model based on the advertisement type data and the delivery channel data and acquiring historical click data of each advertisement in the corresponding delivery channel data;
the user preference model construction module is used for constructing a corresponding click model according to the historical click data, constructing a user preference model based on the delivery channel data, and predicting the click rate of each advertisement by utilizing the user preference model and the click model so as to obtain the click rate corresponding to each advertisement;
the consumption probability model construction module is used for calculating attribution coefficients of the advertisements according to the click rate and the delivery channel data and constructing a consumption probability model of a user;
and the advertisement attribution module is used for calculating the contribution degree of the user to each advertisement according to the consumption probability model and the attribution coefficient, and determining attribution results of each advertisement based on the contribution degree.
Further, the advertisement type data includes targeted advertisements and regular advertisements, and the advertisement conversion model construction module includes:
the precision calculation unit is used for calculating cost information corresponding to each piece of delivery channel data by using a cost conversion model and respectively calculating the precision of the targeted advertisement and the conventional advertisement based on the cost information;
the effect perception model construction unit is used for respectively acquiring the propagation parameters of the targeted advertisement and the conventional advertisement and constructing an effect perception model according to the accuracy and the propagation parameters of the targeted advertisement and the conventional advertisement;
and the advertisement conversion model construction unit is used for acquiring consumption parameters of the user on the targeted advertisement and the conventional advertisement and constructing a corresponding advertisement conversion model by utilizing the consumption parameters and the effect perception model.
Further, the user preference model building module includes:
the click information analysis unit is used for analyzing advertisement click information triggered by a user in the historical click data, wherein the advertisement click information comprises advertisement information clicked by the user and channel information corresponding to the advertisement information;
and the click model construction unit is used for constructing a click model corresponding to the historical click data according to the advertisement information and the channel information.
Further, the user preference model building module further includes:
the channel tendency model construction unit is used for modeling the channel tendency of the put channel data by utilizing a channel distribution predictor so as to obtain a channel tendency model;
the user preference model construction unit is used for acquiring the use degree of the user on each delivery channel and carrying out model optimization on the channel trend model based on the use degree so as to obtain a corresponding user preference model.
Further, the user preference model building module further includes:
the classification learning unit is used for respectively analyzing the model learners of the user preference model and the click model and respectively performing classification learning on the model learners of the user preference model and the click model;
the click rate prediction model construction unit is used for combining the model learners after classification learning and importing the model learners into a click predictor to generate a new model learner, and constructing a click rate prediction model by using the new model learner;
and the click rate prediction unit is used for predicting the click rate of each advertisement by using the click rate prediction model so as to obtain the click rate corresponding to each advertisement.
The invention also provides a computer, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the attribution method for realizing the advertising effect when the processor executes the computer program.
According to the attribution method, the attribution system and the computer for the advertisement putting effect, the advertisement conversion model is built through the advertisement type data and the putting channel data, the corresponding click model and the corresponding user preference model are respectively built according to the historical click data and the putting channel data, click rate prediction is conducted on the advertisement based on the click model and the user preference model, the corresponding attribution coefficient is calculated through the click rate and the putting channel data, the contribution degree of the user to each advertisement is obtained through the consumption probability model and the attribution coefficient of the user, attribution results of each advertisement are obtained, attribution conditions of the advertisement are supplemented through the click sequence and the historical click data of each user, auxiliary processing is conducted on attribution problems of the advertisement through the multiple models, and therefore advertising attribution processing efficiency is further improved, and influences of multiple marketing channels on attribution results are reduced.
Drawings
FIG. 1 is a flow chart of a method of attributing advertising effectiveness in a first embodiment of the present invention;
FIG. 2 is a detailed flowchart of step S102 in FIG. 1;
FIG. 3 is a detailed flowchart of step S103 in FIG. 1;
FIG. 4 is a flowchart of the construction process of the user preference model in step S103 in FIG. 1;
FIG. 5 is a flowchart showing the calculation of the click rate in step S103 in FIG. 1;
FIG. 6 is a block diagram of a attribution system for advertisement impression according to a second embodiment of the present invention;
fig. 7 is a block diagram showing a structure of a computer according to a third embodiment of the present invention.
The invention will be further described in the following detailed description in conjunction with the above-described figures.
Detailed Description
In order that the invention may be readily understood, a more complete description of the invention will be rendered by reference to the appended drawings. Several embodiments of the invention are presented in the figures. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
It will be understood that when an element is referred to as being "mounted" on another element, it can be directly on the other element or intervening elements may also be present. When an element is referred to as being "connected" to another element, it can be directly connected to the other element or intervening elements may also be present. The terms "vertical," "horizontal," "left," "right," and the like are used herein for illustrative purposes only.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.
Example 1
Referring to fig. 1, a method for attributing advertisement putting effects in a first embodiment of the present invention is shown, and the method specifically includes steps S101 to S105:
s101, acquiring release information of each advertisement, wherein the release information comprises advertisement type data and release channel data;
in practice, each advertisement is delivered through different advertisement channels, such as print media, broadcast, television, and billboards. The advertisement contacts the user through various channels, which is helpful for the user to form a certain attitude, belief and cognition to the brand, thereby generating purchasing behavior. In this embodiment, the advertisement data received by each platform is parsed to obtain advertisement delivery information in the advertisement data, where the delivery information includes advertisement type data and delivery channel data.
S102, constructing an advertisement conversion model based on the advertisement type data and the delivery channel data, and acquiring historical click data of each advertisement in the corresponding delivery channel data;
further, referring to fig. 2, the advertisement type data includes a targeted advertisement and a regular advertisement, and the step S102 specifically includes steps S1021 to S1023:
s1021, calculating cost information corresponding to each delivery channel data by using a cost conversion model, and respectively calculating the accuracy of the targeted advertisement and the conventional advertisement based on the cost information;
s1022, respectively acquiring propagation parameters of the targeted advertisement and the conventional advertisement, and respectively constructing an effect perception model according to the accuracy and the propagation parameters of the targeted advertisement and the conventional advertisement;
s1023, obtaining consumption parameters of the user on the targeted advertisement and the conventional advertisement, and constructing a corresponding advertisement conversion model by utilizing the consumption parameters and the effect perception model.
When the advertising is carried out in each channel, the cost corresponding to each channel is different, the cost conversion model constructed in advance is utilized to carry out cost calculation on the data of each delivery channel, so that the cost information corresponding to the data of each delivery channel can be obtained, after the cost information of each channel is obtained, the accuracy of the advertising with different advertising types is calculated by utilizing the cost information, the accuracy corresponding to the advertising with different advertising types in each channel is also different, however, as the accuracy of the advertising is higher, the advertising effect perceived by a user can also be in an inverted U shape;
specifically, in this embodiment, the advertisement type data includes targeted advertisements and regular advertisements, where the targeted advertisements are advertisements of specific scenes, and the marketing information is conveyed to accurate target audience groups through a network targeting technology, for example: when a certain shopping requirement exists and the shopping requirement is input in the browsing shopping website, the advertisement pushed by the shopping website; conventional advertisements are advertisements of unspecified scenes, and are randomly spread to the masses, for example: advertisement pushed in the advertisement screen in the elevator.
Further, the spreading property of the advertisement can enhance brand perception of the user and promote the user to perform next-layer spreading on the advertisement, so that the advertisement is secondarily spread, and spreading parameters of the targeted advertisement and the conventional advertisement are obtained, and it can be understood that the probability of the secondary spreading of the targeted advertisement is larger than that of the conventional advertisement, and a corresponding effect perception model is constructed according to the obtained precision and the spreading parameters of the two advertisements, and consumption parameters corresponding to the two advertisements by the user are calculated according to the precision and the spreading parameters of the two advertisements by the following formula:
Figure SMS_39
；
Figure SMS_40
；
in the method, in the process of the invention,
Figure SMS_41
representing consumption parameters of the user for the targeted advertisement; />
Figure SMS_42
Representing the accuracy of the targeted advertisement; />
Figure SMS_43
A propagation parameter representing a targeted advertisement; />
Figure SMS_44
Compensation parameters representing advertisement type data; />
Figure SMS_45
Representing consumption parameters of a user for conventional advertisements; />
Figure SMS_46
Representing the accuracy of the conventional advertisement; />
Figure SMS_47
Representing the propagation parameters of the regular advertisement.
Further, after the consumption parameters are obtained, the consumption parameters and the constructed effect perception model are utilized to construct a corresponding advertisement conversion model:
Figure SMS_48
；
in the method, in the process of the invention,
Figure SMS_50
representing an advertisement conversion model; />
Figure SMS_53
Representing the number of users; />
Figure SMS_56
Representing time; />
Figure SMS_51
Conversion supplement parameter representing advertisement type data, +.>
Figure SMS_54
Conversion factor representing targeted advertisement, +.>
Figure SMS_55
Conversion factor representing conventional advertisement, ++>
Figure SMS_57
Indicating the cross conversion coefficient between the targeted advertisement and the regular advertisement, < >>
Figure SMS_49
Differential indicators representing ad conversion on different users, obeying +.>
Figure SMS_52
Normal distribution.
In the conversion process of the advertisement, the user may be triggered to convert by the same advertisement on a plurality of channels, so after the corresponding advertisement conversion model is obtained, the historical click data of each advertisement in the corresponding delivery channel data is obtained, and it can be understood that the historical click data is the data recorded by clicking or converting after the user touches the advertisement.
S103, constructing a corresponding click model according to the historical click data, constructing a user preference model based on the delivery channel data, and predicting the click rate of each advertisement by using the user preference model and the click model to obtain the click rate corresponding to each advertisement;
further, referring to fig. 3, the step S103 specifically includes steps S1031 to S1032:
s1031, analyzing advertisement click information triggered by a user in the historical click data, wherein the advertisement click information comprises advertisement information clicked by the user and channel information corresponding to the advertisement information;
s1032, constructing a click model corresponding to the historical click data according to the advertisement information and the channel information.
In specific implementation, analyzing advertisement click information triggered by the same user in the historical click data, wherein the advertisement click information comprises advertisement information clicked by the user and channel information corresponding to the advertisement information, and carrying out model construction on the advertisement information and the obtained channel information:
Figure SMS_58
；
in the method, in the process of the invention,
Figure SMS_68
representing user +.>
Figure SMS_60
；/>
Figure SMS_70
Indicate->
Figure SMS_65
Clicking for the second time; />
Figure SMS_72
Indicate->
Figure SMS_67
User +.>
Figure SMS_74
In->
Figure SMS_61
An embedded vector of the secondary click; />
Figure SMS_75
Indicate->
Figure SMS_59
User +.>
Figure SMS_69
In->
Figure SMS_64
Clicking the corresponding channel information for the second time; />
Figure SMS_73
Indicate->
Figure SMS_62
User +.>
Figure SMS_76
In->
Figure SMS_63
A binary vector of secondary clicks; />
Figure SMS_71
Representing the conversion result of the whole click sequence, +.>
Figure SMS_66
。
Further, referring to fig. 4, in step S103, the construction process of the user preference model is as follows:
s1033, modeling the channel tendency of the delivery channel data by using a channel distribution predictor so as to obtain a channel tendency model;
s1034, obtaining the usage degree of each delivery channel by the user, and carrying out model optimization on the channel trend model based on the usage degree to obtain a corresponding user preference model.
In particular implementations, each user's preferences for different delivery channels will be different, meaning that the probability of clicking or converting the user's advertisement in its preferred channel will also increase, thus, in this embodiment, the user's preferences for different channels are learned by minimizing the maximum loss function, the channel propensity is modeled on the delivery channel data described above using the channel allocation predictor, the purpose of which is to learn to a balanced representation for each time step for the channel propensity model
Figure SMS_77
The expression of the channel allocation predictor is as follows: />
Figure SMS_78
；
In the method, in the process of the invention,
Figure SMS_79
representing channel allocation predictor, ++>
Figure SMS_80
Representing channel tendency weight vector,/->
Figure SMS_81
Representing training parameters (i.e., compensation coefficients) of the channel allocation predictor.
Specifically, the usage degree of each delivery channel by the user is extracted, the usage degree is the usage condition of each delivery channel by the user, when the usage of a certain delivery channel by the user is more frequent, the usage degree of the delivery channel is higher, and the channel trend model is optimized by using the usage degree, so that a corresponding user preference model is obtained.
Further, referring to fig. 5, in step S103, the click rate prediction is performed on each advertisement by using the user preference model and the click model, so as to obtain the click rate corresponding to each advertisement, which is as follows:
s1035, respectively analyzing the model learners of the user preference model and the click model, and respectively performing classification learning on the model learners of the user preference model and the click model;
s1036, combining the model learners after the classification learning, and importing the model learners into a click predictor to generate a new model learner, and constructing a click rate prediction model by using the new model learner;
s1037, carrying out click rate prediction on the advertisements by utilizing the click rate prediction model so as to obtain the click rate corresponding to the advertisements.
In the implementation, after a user preference model and a click model are obtained, combining the models according to a preset frame, independently classifying or regressively learning learners of the models, after the learners of the models are independently learned, combining the learners after learning of the models, and importing a click predictor into the combined learners to obtain a new model learner, constructing a click rate prediction model by using the new model learner, and predicting the click rate of each advertisement by using the obtained click rate prediction model to obtain the click rate corresponding to each advertisement.
S104, calculating attribution coefficients of the advertisements according to the click rate and the delivery channel data, and constructing a consumption probability model of the user;
in particular, a higher click rate means that the attribution coefficient of the corresponding advertisement delivery channel data is larger, and when the user has stronger ideas of purchasing advertisements, corresponding purchase will be generated
Figure SMS_82
When a purchase occurs, the purchase will
Figure SMS_83
1, when no purchase occurs, the purchase will +.>
Figure SMS_84
0, with user's purchase willingness +.>
Figure SMS_85
Constructing a consumption probability model of a user:
Figure SMS_86
；
in the method, in the process of the invention,
Figure SMS_87
representing a standard normal distribution function.
S105, calculating the contribution degree of the user to each advertisement according to the consumption probability model and the attribution coefficient, and determining attribution results of each advertisement based on the contribution degree.
In the implementation, the model regression calculation is performed on the consumption model and the attribution coefficient, so that the purchase contribution degree of the user to each advertisement can be obtained, wherein the purchase contribution degree is the contribution proportion of the advertisement in the delivery channel, the larger the contribution degree is, the more obvious the advertisement effect is, the higher the possibility of conversion of the advertisement after clicking is, and the calculation of the follow-up advertisement delivery marketing budget is facilitated.
In summary, according to the attribution method of the advertisement putting effect in the embodiment of the invention, the attribution results of each advertisement are obtained by constructing an advertisement conversion model from advertisement type data and putting channel data, respectively constructing a corresponding click model and a user preference model according to historical click data and putting channel data, predicting the click rate of the advertisement based on the click model and the user preference model, calculating the corresponding attribution coefficient by using the click rate and the putting channel data, obtaining the contribution degree of the user to each advertisement by using the consumption probability model and the attribution coefficient of the user, supplementing attribution conditions of the advertisement by using the click sequence and the historical click data of each user, carrying out auxiliary processing on attribution problems of the advertisement by using a plurality of models, further improving the processing efficiency of advertisement attribution and reducing the influence of multiple marketing channels on attribution results.
Example two
In another aspect, referring to fig. 6, an attribution system for advertisement putting effect in a second embodiment of the present invention is shown, where the system includes:
a delivery information obtaining module 11, configured to obtain delivery information of each advertisement, where the delivery information includes advertisement type data and delivery channel data;
an advertisement conversion model construction module 12, configured to construct an advertisement conversion model based on the advertisement type data and the delivery channel data, and obtain historical click data of each advertisement in the corresponding delivery channel data;
further, the advertisement type data includes targeted advertisements and regular advertisements, and the advertisement conversion model construction module 12 includes:
the precision calculation unit is used for calculating cost information corresponding to each piece of delivery channel data by using a cost conversion model and respectively calculating the precision of the targeted advertisement and the conventional advertisement based on the cost information;
the effect perception model construction unit is used for respectively acquiring the propagation parameters of the targeted advertisement and the conventional advertisement and constructing an effect perception model according to the accuracy and the propagation parameters of the targeted advertisement and the conventional advertisement;
and the advertisement conversion model construction unit is used for acquiring consumption parameters of the user on the targeted advertisement and the conventional advertisement and constructing a corresponding advertisement conversion model by utilizing the consumption parameters and the effect perception model.
The user preference model construction module 13 is configured to construct a corresponding click model according to the historical click data, construct a user preference model based on the delivery channel data, and predict click rates of the advertisements by using the user preference model and the click model so as to obtain click rates corresponding to the advertisements;
further, the user preference model building module 13 includes:
the click information analysis unit is used for analyzing advertisement click information triggered by a user in the historical click data, wherein the advertisement click information comprises advertisement information clicked by the user and channel information corresponding to the advertisement information;
and the click model construction unit is used for constructing a click model corresponding to the historical click data according to the advertisement information and the channel information.
Further, the user preference model building module 13 further includes:
the channel tendency model construction unit is used for modeling the channel tendency of the put channel data by utilizing a channel distribution predictor so as to obtain a channel tendency model;
the user preference model construction unit is used for acquiring the use degree of the user on each delivery channel and carrying out model optimization on the channel trend model based on the use degree so as to obtain a corresponding user preference model.
Further, the user preference model building module 13 further includes:
the classification learning unit is used for respectively analyzing the model learners of the user preference model and the click model and respectively performing classification learning on the model learners of the user preference model and the click model;
the click rate prediction model construction unit is used for combining the model learners after classification learning and importing the model learners into a click predictor to generate a new model learner, and constructing a click rate prediction model by using the new model learner;
and the click rate prediction unit is used for predicting the click rate of each advertisement by using the click rate prediction model so as to obtain the click rate corresponding to each advertisement.
A consumption probability model construction module 14, configured to calculate attribution coefficients of each advertisement according to the click rate and the delivery channel data, and construct a consumption probability model of a user;
and an advertisement attribution module 15, configured to calculate a contribution degree of the user to each advertisement according to the consumption probability model and the attribution coefficient, and determine an attribution result of each advertisement based on the contribution degree.
The functions or operation steps implemented when the above modules and units are executed are substantially the same as those in the above method embodiments, and are not described herein again.
The attribution system of advertisement putting effect provided by the embodiment of the invention has the same implementation principle and technical effect as those of the embodiment of the method, and for the purposes of brief description, the corresponding content in the embodiment of the method can be referred to for the part of the embodiment of the system which is not mentioned.
Example III
The present invention also proposes a computer, please refer to fig. 7, which shows a computer according to a third embodiment of the present invention, including a memory 10, a processor 20, and a computer program 30 stored in the memory 10 and executable on the processor 20, wherein the processor 20 implements the attribution method of advertising effect described above when executing the computer program 30.
The memory 10 includes at least one type of readable storage medium including flash memory, a hard disk, a multimedia card, a card memory (e.g., SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. Memory 10 may in some embodiments be an internal storage unit of a computer, such as a hard disk of the computer. The memory 10 may also be an external storage device in other embodiments, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card), etc. Further, the memory 10 may also include both internal storage units and external storage devices of the computer. The memory 10 may be used not only for storing application software installed in a computer and various types of data, but also for temporarily storing data that has been output or is to be output.
The processor 20 may be, in some embodiments, an electronic control unit (Electronic Control Unit, ECU), a central processing unit (Central Processing Unit, CPU), a controller, a microcontroller, a microprocessor, or other data processing chip, for executing program codes or processing data stored in the memory 10, such as executing an access restriction program, or the like.
It should be noted that the structure shown in fig. 7 is not limiting of the computer, and in other embodiments, the computer may include fewer or more components than shown, or may combine certain components, or may have a different arrangement of components.
The embodiment of the invention also provides a readable storage medium, on which a computer program is stored, which when executed by a processor, implements the attribution method of advertising effects as described above.
Those of skill in the art will appreciate that the logic and/or steps represented in the flow diagrams or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
It is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
The technical features of the above-described embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above-described embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples merely represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application is to be determined by the claims appended hereto.

Claims (10)

1. A method for attributing advertising effectiveness, comprising:
acquiring the putting information of each advertisement, wherein the putting information comprises advertisement type data and putting channel data;
constructing an advertisement conversion model based on the advertisement type data and the delivery channel data, and acquiring historical click data of each advertisement in the corresponding delivery channel data;
constructing a corresponding click model according to the historical click data, constructing a user preference model based on the delivery channel data, and predicting the click rate of each advertisement by using the user preference model and the click model to obtain the click rate corresponding to each advertisement;
calculating attribution coefficients of the advertisements according to the click rate and the delivery channel data, and constructing a consumption probability model of a user;
and calculating the contribution degree of the user to each advertisement according to the consumption probability model and the attribution coefficient, and determining attribution results of each advertisement based on the contribution degree.
2. The attribution method of advertisement effectiveness according to claim 1, wherein the advertisement type data includes a targeted advertisement and a regular advertisement, and the step of constructing an advertisement conversion model based on the advertisement type data and the delivery channel data includes:
calculating cost information corresponding to each piece of delivery channel data by using a cost conversion model, and respectively calculating the accuracy of the targeted advertisement and the conventional advertisement based on the cost information;
respectively acquiring propagation parameters of the targeted advertisement and the conventional advertisement, and respectively constructing an effect perception model according to the accuracy and the propagation parameters of the targeted advertisement and the conventional advertisement;
and acquiring consumption parameters of the user on the targeted advertisement and the conventional advertisement, and constructing a corresponding advertisement conversion model by utilizing the consumption parameters and the effect perception model.
3. The method of attribution of an advertising effectiveness according to claim 1, wherein the step of constructing a corresponding click model from the historical click data comprises:
analyzing advertisement click information triggered by a user in the historical click data, wherein the advertisement click information comprises advertisement information clicked by the user and channel information corresponding to the advertisement information;
and constructing a click model corresponding to the historical click data according to the advertisement information and the channel information.
4. The attribution method of advertisement putting effect according to claim 1, wherein the step of constructing a user preference model based on the putting channel data comprises:
modeling the channel tendency of the delivery channel data by using a channel distribution predictor to obtain a channel tendency model;
and obtaining the usage degree of each putting channel by a user, and carrying out model optimization on the channel trend model based on the usage degree so as to obtain a corresponding user preference model.
5. The attribution method of advertisement putting effect according to claim 1, wherein the step of predicting the click rate of each advertisement using the user preference model and the click model to obtain the click rate corresponding to each advertisement comprises:
the model learners of the user preference model and the click model are respectively analyzed, and classification learning is carried out on the model learners of the user preference model and the click model respectively;
combining the model learners after the classification learning, and importing the model learners into a click predictor to generate a new model learner, and constructing a click rate prediction model by using the new model learner;
and predicting the click rate of each advertisement by using the click rate prediction model so as to obtain the click rate corresponding to each advertisement.
6. The attribution method of advertisement putting effect according to claim 2, wherein the calculation formula of the advertisement conversion model is:
Figure QLYQS_1
；
Figure QLYQS_2
；
Figure QLYQS_3
；
in the method, in the process of the invention,
Figure QLYQS_12
representing consumption parameters of the user for the targeted advertisement; />
Figure QLYQS_5
Representing the accuracy of the targeted advertisement; />
Figure QLYQS_14
A propagation parameter representing a targeted advertisement; />
Figure QLYQS_7
Compensation parameters representing advertisement type data; />
Figure QLYQS_16
Representing consumption parameters of a user for conventional advertisements; />
Figure QLYQS_8
Representing the accuracy of the conventional advertisement; />
Figure QLYQS_18
A propagation parameter representing a regular advertisement; />
Figure QLYQS_10
Representing an advertisement conversion model; />
Figure QLYQS_17
Representing the number of users; />
Figure QLYQS_4
Representing time; />
Figure QLYQS_13
Conversion supplement parameter representing advertisement type data, +.>
Figure QLYQS_9
Conversion factor representing targeted advertisement, +.>
Figure QLYQS_15
Conversion factor representing conventional advertisement, ++>
Figure QLYQS_11
Indicating the cross conversion coefficient between the targeted advertisement and the regular advertisement, < >>
Figure QLYQS_19
Differential indicators representing ad conversion on different users, obeying +.>
Figure QLYQS_6
Normal distribution.
7. The attribution method of advertisement putting effect according to claim 3, wherein the calculation formula of the click model is:
Figure QLYQS_20
；
in the method, in the process of the invention,
Figure QLYQS_25
representing user +.>
Figure QLYQS_22
；/>
Figure QLYQS_34
Indicate->
Figure QLYQS_23
Clicking for the second time; />
Figure QLYQS_32
Indicate->
Figure QLYQS_26
User +.>
Figure QLYQS_36
In->
Figure QLYQS_28
An embedded vector of the secondary click; />
Figure QLYQS_37
Indicate->
Figure QLYQS_21
User +.>
Figure QLYQS_31
In->
Figure QLYQS_29
Clicking the corresponding channel information for the second time; />
Figure QLYQS_38
Indicate->
Figure QLYQS_30
User +.>
Figure QLYQS_35
In->
Figure QLYQS_24
A binary vector of secondary clicks; />
Figure QLYQS_33
Representing the conversion result of the whole click sequence, +.>
Figure QLYQS_27
。
8. An attribution system for advertising effectiveness, comprising:
the system comprises a delivery information acquisition module, a delivery information processing module and a delivery information processing module, wherein the delivery information acquisition module is used for acquiring delivery information of each advertisement, and the delivery information comprises advertisement type data and delivery channel data;
the advertisement conversion model construction module is used for constructing an advertisement conversion model based on the advertisement type data and the delivery channel data and acquiring historical click data of each advertisement in the corresponding delivery channel data;
the user preference model construction module is used for constructing a corresponding click model according to the historical click data, constructing a user preference model based on the delivery channel data, and predicting the click rate of each advertisement by utilizing the user preference model and the click model so as to obtain the click rate corresponding to each advertisement;
the consumption probability model construction module is used for calculating attribution coefficients of the advertisements according to the click rate and the delivery channel data and constructing a consumption probability model of a user;
and the advertisement attribution module is used for calculating the contribution degree of the user to each advertisement according to the consumption probability model and the attribution coefficient, and determining attribution results of each advertisement based on the contribution degree.
9. The attribution system of advertising effectiveness of claim 8, wherein the advertisement type data comprises targeted advertisements as well as regular advertisements, the advertisement conversion model building module comprising:
the precision calculation unit is used for calculating cost information corresponding to each piece of delivery channel data by using a cost conversion model and respectively calculating the precision of the targeted advertisement and the conventional advertisement based on the cost information;
the effect perception model construction unit is used for respectively acquiring the propagation parameters of the targeted advertisement and the conventional advertisement and constructing an effect perception model according to the accuracy and the propagation parameters of the targeted advertisement and the conventional advertisement;
and the advertisement conversion model construction unit is used for acquiring consumption parameters of the user on the targeted advertisement and the conventional advertisement and constructing a corresponding advertisement conversion model by utilizing the consumption parameters and the effect perception model.
10. A computer comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the attribution method of advertising effectiveness of any of claims 1 to 7 when the computer program is executed.
CN202310417409.2A 2023-04-19 2023-04-19 Attribution method, attribution system and attribution computer for advertisement putting effect Active CN116137004B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310417409.2A CN116137004B (en) 2023-04-19 2023-04-19 Attribution method, attribution system and attribution computer for advertisement putting effect

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310417409.2A CN116137004B (en) 2023-04-19 2023-04-19 Attribution method, attribution system and attribution computer for advertisement putting effect

Publications (2)

Publication Number Publication Date
CN116137004A true CN116137004A (en) 2023-05-19
CN116137004B CN116137004B (en) 2023-07-07

Family

ID=86333608

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310417409.2A Active CN116137004B (en) 2023-04-19 2023-04-19 Attribution method, attribution system and attribution computer for advertisement putting effect

Country Status (1)

Country Link
CN (1) CN116137004B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116402553A (en) * 2023-06-07 2023-07-07 江西时刻互动科技股份有限公司 Advertisement effect evaluation method, device and readable storage medium
CN117934080A (en) * 2024-03-18 2024-04-26 长沙掌控智能科技有限公司 Sharing benefit optimization method and system based on intelligent popularization tool
CN117934087A (en) * 2024-03-25 2024-04-26 湖南创研科技股份有限公司 Intelligent advertisement delivery method and system based on user interaction data

Citations (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102663616A (en) * 2012-03-19 2012-09-12 北京国双科技有限公司 Method and system for measuring web advertising effectiveness based on multiple-contact attribution model
US20120303447A1 (en) * 2011-05-27 2012-11-29 Google Inc. Multiple attribution models with return on ad spend
US20140236705A1 (en) * 2013-02-15 2014-08-21 Turn Inc. Method and apparatus for data-driven multi-touch attribution determination in multichannel advertising campaigns
CN104169959A (en) * 2012-03-15 2014-11-26 微软公司 Cost-per-action model based on advertiser-reported actions
US20150161662A1 (en) * 2013-12-10 2015-06-11 Acquisio System and Method for Directing Online Advertising Across Multiple Channels
CN107481062A (en) * 2017-08-21 2017-12-15 小草数语（北京）科技有限公司 The distribution method and device of advertisement putting budget
CN107563781A (en) * 2016-06-30 2018-01-09 阿里巴巴集团控股有限公司 A kind of information launches effect attribution method and device
CN110020893A (en) * 2019-04-03 2019-07-16 阿里巴巴集团控股有限公司 A kind of advertisement contribution degree determines method, device and equipment
CN110189152A (en) * 2018-02-23 2019-08-30 北京国双科技有限公司 The attribution method and apparatus of channel
CN110910165A (en) * 2019-10-29 2020-03-24 深圳市星河互动科技有限公司 Multi-channel attribution method and related equipment
CN111242700A (en) * 2020-02-15 2020-06-05 晓推(武汉)信息科技有限公司 Method and device for obtaining predicted click rate of advertisement, electronic equipment and storage medium
CN111784380A (en) * 2020-06-05 2020-10-16 北京沃东天骏信息技术有限公司 Advertisement putting attribution method and device
CN112348564A (en) * 2020-09-27 2021-02-09 北京淇瑀信息科技有限公司 Method and device for automatically managing advertisement delivery and electronic equipment
CN112381582A (en) * 2020-11-18 2021-02-19 广州市昊盟计算机科技有限公司 Mobile advertisement attribution method and system
WO2022127543A1 (en) * 2020-12-17 2022-06-23 百果园技术(新加坡)有限公司 Advertisement information processing method and apparatus, device and storage medium
CN115471271A (en) * 2022-09-29 2022-12-13 北京邮电大学 Method and device for attributing advertisements, computer equipment and readable storage medium

Patent Citations (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120303447A1 (en) * 2011-05-27 2012-11-29 Google Inc. Multiple attribution models with return on ad spend
CN103562946A (en) * 2011-05-27 2014-02-05 谷歌公司 Multiple attribution models with return on ad spend
CN104169959A (en) * 2012-03-15 2014-11-26 微软公司 Cost-per-action model based on advertiser-reported actions
CN102663616A (en) * 2012-03-19 2012-09-12 北京国双科技有限公司 Method and system for measuring web advertising effectiveness based on multiple-contact attribution model
US20140236705A1 (en) * 2013-02-15 2014-08-21 Turn Inc. Method and apparatus for data-driven multi-touch attribution determination in multichannel advertising campaigns
US20150161662A1 (en) * 2013-12-10 2015-06-11 Acquisio System and Method for Directing Online Advertising Across Multiple Channels
CN107563781A (en) * 2016-06-30 2018-01-09 阿里巴巴集团控股有限公司 A kind of information launches effect attribution method and device
CN107481062A (en) * 2017-08-21 2017-12-15 小草数语（北京）科技有限公司 The distribution method and device of advertisement putting budget
CN110189152A (en) * 2018-02-23 2019-08-30 北京国双科技有限公司 The attribution method and apparatus of channel
CN110020893A (en) * 2019-04-03 2019-07-16 阿里巴巴集团控股有限公司 A kind of advertisement contribution degree determines method, device and equipment
CN110910165A (en) * 2019-10-29 2020-03-24 深圳市星河互动科技有限公司 Multi-channel attribution method and related equipment
CN111242700A (en) * 2020-02-15 2020-06-05 晓推(武汉)信息科技有限公司 Method and device for obtaining predicted click rate of advertisement, electronic equipment and storage medium
CN111784380A (en) * 2020-06-05 2020-10-16 北京沃东天骏信息技术有限公司 Advertisement putting attribution method and device
CN112348564A (en) * 2020-09-27 2021-02-09 北京淇瑀信息科技有限公司 Method and device for automatically managing advertisement delivery and electronic equipment
CN112381582A (en) * 2020-11-18 2021-02-19 广州市昊盟计算机科技有限公司 Mobile advertisement attribution method and system
WO2022127543A1 (en) * 2020-12-17 2022-06-23 百果园技术(新加坡)有限公司 Advertisement information processing method and apparatus, device and storage medium
CN115471271A (en) * 2022-09-29 2022-12-13 北京邮电大学 Method and device for attributing advertisements, computer equipment and readable storage medium

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
纪文迪;王晓玲;周傲英;: "广告点击率估算技术综述", 华东师范大学学报(自然科学版), no. 03 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116402553A (en) * 2023-06-07 2023-07-07 江西时刻互动科技股份有限公司 Advertisement effect evaluation method, device and readable storage medium
CN116402553B (en) * 2023-06-07 2023-08-18 江西时刻互动科技股份有限公司 Advertisement effect evaluation method, device and readable storage medium
CN117934080A (en) * 2024-03-18 2024-04-26 长沙掌控智能科技有限公司 Sharing benefit optimization method and system based on intelligent popularization tool
CN117934087A (en) * 2024-03-25 2024-04-26 湖南创研科技股份有限公司 Intelligent advertisement delivery method and system based on user interaction data

Also Published As

Publication number Publication date
CN116137004B (en) 2023-07-07

Similar Documents

Publication Publication Date Title
CN116137004B (en) Attribution method, attribution system and attribution computer for advertisement putting effect
CN109902849B (en) User behavior prediction method and device, and behavior prediction model training method and device
CN108491529B (en) Information recommendation method and device
WO2005006140A2 (en) Methods to attribute conversions for online advertisement campaigns
CN107357874A (en) User classification method and device, electronic equipment, storage medium
CN110515904B (en) Quality prediction model training method, quality prediction method and device for media file
JP7215324B2 (en) Prediction program, prediction method and prediction device
CN109299356A (en) Activity recommendation method, apparatus, electronic equipment and storage medium based on big data
JPWO2008075524A1 (en) Polarity estimation system, information distribution system, polarity estimation method, polarity estimation program, and evaluation polarity estimation program
CN110889725B (en) Online advertisement CTR estimation method, device, equipment and storage medium
CN112348592A (en) Advertisement recommendation method and device, electronic equipment and medium
KR101441164B1 (en) Object customization and management system
CN111325614B (en) Recommendation method and device of electronic object and electronic equipment
CN113886697A (en) Clustering algorithm based activity recommendation method, device, equipment and storage medium
US20230316106A1 (en) Method and apparatus for training content recommendation model, device, and storage medium
CN107665202B (en) Method and device for constructing interest model and electronic equipment
CN112269943A (en) Information recommendation system and method
CN115829159A (en) Social media fan newly-increased prediction method, device, equipment and storage medium
CN114971726A (en) Advertisement point location screening method and device, computer equipment and computer readable storage medium
CN112200602B (en) Neural network model training method and device for advertisement recommendation
CN113254759B (en) Click rate prediction method, click rate prediction device, medium and electronic equipment
CN115344774A (en) User account screening method and device and server
CN112990967A (en) Advertisement creative analysis method and system
CN114971664A (en) Advertisement putting method and related equipment
CN112508615A (en) Feature extraction method, feature extraction device, storage medium, and electronic apparatus

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