CN111160983A - Advertisement putting effect evaluation method and device, computer equipment and storage medium - Google Patents
Advertisement putting effect evaluation method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN111160983A CN111160983A CN201911410592.3A CN201911410592A CN111160983A CN 111160983 A CN111160983 A CN 111160983A CN 201911410592 A CN201911410592 A CN 201911410592A CN 111160983 A CN111160983 A CN 111160983A
- Authority
- CN
- China
- Prior art keywords
- advertisement
- cost
- user
- target advertisement
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000000694 effects Effects 0.000 title claims abstract description 46
- 238000011156 evaluation Methods 0.000 title claims abstract description 31
- 238000000034 method Methods 0.000 claims abstract description 36
- 230000004927 fusion Effects 0.000 claims description 35
- 238000004590 computer program Methods 0.000 claims description 15
- 230000006399 behavior Effects 0.000 claims description 14
- 230000006870 function Effects 0.000 claims description 13
- 238000000605 extraction Methods 0.000 claims description 7
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 230000002860 competitive effect Effects 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 5
- 238000009472 formulation Methods 0.000 description 5
- 239000000203 mixture Substances 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004883 computer application Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
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
- G06Q30/0247—Calculate past, present or future revenues
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an evaluation method and device for advertisement putting effect, computer equipment and a storage medium, belonging to the field of internet advertisement, wherein the method comprises the following steps: aiming at each user in a plurality of users, obtaining a marginal cost rate estimated value of the user for the target advertisement through a pre-trained cost prediction model; calculating an investment yield pre-estimated value of the target advertisement based on the marginal cost rate pre-estimated value of each user to the target advertisement, the income of each user after the target advertisement is converted and the bid value of the target advertisement; and evaluating the delivery effect of the target advertisement based on the investment yield pre-estimated value of the target advertisement. The embodiment of the invention can realize more accurate evaluation of the advertising effect of the target advertisement, thereby providing data support for reasonably formulating the subsequent advertising scheme of the advertiser and further providing effective reference for reasonably controlling the advertising cost of the advertiser.
Description
Technical Field
The invention relates to the technical field of computer application, in particular to an advertisement putting effect evaluation method and device, computer equipment and a storage medium.
Background
Currently, the competitive advertising of internet information flow products has become a mainstream choice for advertisers, and the demand is continuously increasing, and the coverage industry is also more and more extensive. In the information flow bidding advertisement putting process, the display opportunities are not guaranteed, but compete in a bidding sorting mode, and in order to better formulate an advertisement putting strategy, the advertisement putting effect needs to be evaluated so as to provide reference for the subsequent formulation of an advertisement putting scheme.
Currently, the evaluation of an advertiser on the advertisement putting effect is generally judged through an investment income rate ROI, but the ROI calculated income only considers the current income, and for the business such as financial insurance and the like with marginal cost rate changing along with a customer group, the current income cannot accurately reflect the expiring income, so that the accuracy of the evaluation of the advertisement putting effect cannot be ensured, the formulation of a subsequent advertisement putting scheme is influenced, and effective reference cannot be provided for reasonably controlling the advertisement putting cost.
Disclosure of Invention
In order to solve at least one of the problems mentioned in the background art, the invention provides an advertisement delivery effect evaluation method, an advertisement delivery effect evaluation device, a computer device and a storage medium.
The embodiment of the invention provides the following specific technical scheme:
in a first aspect, a method for evaluating effectiveness of advertisement placement is provided, the method including:
aiming at each user in a plurality of users, obtaining a marginal cost rate estimated value of the user for the target advertisement through a pre-trained cost prediction model;
calculating an investment profit rate pre-estimated value of the target advertisement based on the marginal cost rate pre-estimated value of each user for the target advertisement, the converted income of each user for the target advertisement and the competitive value of the target advertisement;
and evaluating the delivery effect of the target advertisement based on the investment profitability estimated value of the target advertisement.
Further, the cost prediction model includes a representation extractor layer, a feature fusion layer and a cost prediction layer, and the obtaining, for each of a plurality of users, a marginal cost rate predicted value of the user for the target advertisement through a pre-trained cost prediction model includes:
for each user in a plurality of users, inputting the behavior data of the user and the advertisement data of the target advertisement into the representation extractor layer for feature extraction to obtain a plurality of feature data;
inputting the plurality of feature data into the feature fusion layer for weighted fusion to obtain fusion features for marginal cost rate prediction;
and inputting the fusion features into the cost prediction layer to obtain a marginal cost rate prediction value of the user for the target advertisement.
Further, the training process of the cost prediction model comprises:
constructing a training data set, wherein the training data set is an intersection of sample data provided by an advertiser and labeled with a cost label and guest group data provided by a volume platform after collision, and the cost label is normalized cost data;
and training the cost prediction model based on the training data set to obtain the trained cost prediction model.
Further, the training the cost prediction model based on the training data set to obtain the trained cost prediction model includes:
iteratively training the cost prediction model based on the training data set;
in each iterative training, calculating a loss value between a marginal cost rate estimated value output by the cost prediction model and a marginal cost rate true value of a corresponding sample by using a preset loss function;
and stopping iterative training of the cost prediction model when the loss value reaches a preset value, so as to obtain the trained cost prediction model.
Further, the method further comprises:
adjusting a delivery strategy of the target advertisement based on the evaluation result of the delivery effect of the target advertisement, wherein the delivery strategy at least comprises one of the following: whether to deliver the targeted advertisement, a delivery time of the targeted advertisement, and a bid value of the targeted advertisement.
In a second aspect, an apparatus for evaluating effectiveness of advertisement placement is provided, the apparatus comprising:
the acquisition module is used for acquiring a marginal cost rate estimated value of each user for the target advertisement through a pre-trained cost prediction model aiming at each user in a plurality of users;
a calculation module, configured to calculate an investment profitability budget value of the targeted advertisement based on a marginal cost rate budget value of each user for the targeted advertisement, revenue of each user after conversion of the targeted advertisement, and a bid value of the targeted advertisement;
and the evaluation module is used for evaluating the delivery effect of the target advertisement based on the investment profitability prediction value of the target advertisement.
Further, the cost prediction model includes a representation extractor layer, a feature fusion layer, and a cost prediction layer, and the obtaining module is specifically configured to:
for each user in a plurality of users, inputting the behavior data of the user and the advertisement data of the target advertisement into the representation extractor layer for feature extraction to obtain a plurality of feature data;
inputting the plurality of feature data into the feature fusion layer for weighted fusion to obtain fusion features for marginal cost rate prediction;
and inputting the fusion features into the cost prediction layer to obtain a marginal cost rate prediction value of the user for the target advertisement.
Further, the apparatus further comprises a training module, the training module comprising:
the construction submodule is used for constructing a training data set, wherein the training data set is an intersection of sample data which is provided by an advertiser and labeled with a cost label and guest group data which are provided by a volume platform after collision, and the cost label is normalized cost data;
and the training submodule is used for training the cost prediction model based on the training data set to obtain the trained cost prediction model.
Further, the training submodule is specifically configured to:
iteratively training the cost prediction model based on the training data set;
in each iterative training, calculating a loss value between a marginal cost rate estimated value output by the cost prediction model and a marginal cost rate true value of a corresponding sample by using a preset loss function;
and stopping iterative training of the cost prediction model when the loss value reaches a preset value, so as to obtain the trained cost prediction model.
Further, the apparatus further comprises:
an adjusting module, configured to adjust a delivery policy of the target advertisement based on an evaluation result of a delivery effect of the target advertisement, where the delivery policy at least includes one of: whether to deliver the targeted advertisement, a delivery time of the targeted advertisement, and a bid value of the targeted advertisement.
In a third aspect, a computer device is provided, which comprises a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method for evaluating the effectiveness of advertisement placement according to the first aspect.
In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, which computer program, when being executed by a processor, carries out the steps of the method for evaluating an effectiveness of an advertisement placement according to the first aspect.
The embodiment of the invention provides an evaluation method, a device, a computer device and a storage medium for advertisement putting effect, wherein aiming at each user in a plurality of users, a pre-trained cost prediction model is used for obtaining a marginal cost rate pre-evaluation value of the user for a target advertisement, and the putting effect of the target advertisement is evaluated based on the marginal cost rate pre-evaluation value of each user for the target advertisement, income of each user after conversion of the target advertisement and a bid price value of the target advertisement, the investment profitability pre-evaluation value of the target advertisement is calculated, and the investment profitability pre-evaluation value of the target advertisement is based on, because the income of each user after conversion of the target advertisement and the bid price value of the target advertisement are considered in the process of estimating the investment profitability of the target advertisement, and the simple marginal cost of each user for the target advertisement is also considered, therefore, the assessment of the advertising effect of the target advertisement is more accurate, data support can be provided for reasonable formulation of follow-up advertising schemes of advertisers, and effective reference is provided for reasonably controlling advertising cost of the advertisers.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a flowchart of an advertisement delivery effect evaluation method according to an embodiment of the present invention;
FIG. 2 is a detailed flowchart of step S11 of the method shown in FIG. 1; (ii) a
FIG. 3 is a detailed flowchart of the training process of the cost prediction model in the method shown in FIG. 1;
fig. 4 is a structural diagram of an apparatus for evaluating an advertisement delivery effect according to an embodiment of the present invention;
fig. 5 is an internal structural diagram of a computer device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying 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.
It is to be understood that, unless the context clearly requires otherwise, throughout the description and the claims, the words "comprise", "comprising", and the like are to be construed in an inclusive sense as opposed to an exclusive or exhaustive sense; that is, what is meant is "including, but not limited to".
Furthermore, in the description of the present invention, it is to be understood that the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. In addition, in the description of the present invention, "a plurality" means two or more unless otherwise specified.
In the prior art, the evaluation of an advertiser on the advertisement putting effect is generally judged through an investment income rate ROI, but the ROI calculated income only considers the current income, and for the business such as financial insurance and the like with the marginal cost rate changing along with a customer group, the current income cannot accurately reflect the expiring income, so that the accuracy of the evaluation of the advertisement putting effect cannot be ensured, the formulation of a subsequent advertisement putting scheme is influenced, and effective reference cannot be provided for reasonably controlling the advertisement putting cost. In addition, advertisers in the industries of financial insurance and the like can accurately hook with the risk level of target crowds when desiring to show the advertisement, and the goals that relatively high bids and low bids of high-risk crowds can be configured for low-risk crowds, similar expense discount linkage is realized, and the overall marginal cost rate is kept stable are achieved. Therefore, the method for evaluating the advertising effect provided by the embodiment of the invention adopts the optimized version ROI weighted based on the simple marginal cost, so that the advertiser can evaluate the advertising effect more accurately, data support can be provided for the reasonable formulation of a subsequent advertising scheme, and effective reference is provided for reasonably controlling the advertising cost.
It should be noted that, in the description of the present invention, the Marginal cost refers to "simple Marginal cost", and the simple Marginal cost MR (the Marginal cost refers to a Marginal cost without considering the expense apportionment, the Marginal cost rate refers to "simple Marginal cost rate", and the simple Marginal cost rate is a probability value between 0 and 1.
Example one
An embodiment of the present invention provides an advertisement delivery effect evaluation method, as shown in fig. 1, the method may include:
and step S11, for each user in the plurality of users, obtaining a marginal cost rate estimated value of the user for the target advertisement through a pre-trained cost prediction model.
And step S12, calculating the investment profitability estimated value of the target advertisement based on the marginal cost rate estimated value of each user for the target advertisement, the converted income of each user for the target advertisement and the bid value of the target advertisement.
During actual placement, the advertiser's assessment of the effectiveness of the ad placement is typically determined by the return on investment ROI, and the bidding (bid) strategy will be adjusted according to the expected ROI. In this mode, the advertiser's evaluation of the advertising effect can calculate the optimized version ROI based on simple marginal profit weighting by using the following formula, so as to adjust the bidding strategy more precisely:
wherein the oROI is an investment yield prediction value of the target advertisement, the Revenue is the income of each user to the target advertisement, the Revenue is equal to the actual income after the user is converted, the Revenue is equal to 0 when the user is not converted, eMR is a marginal cost rate prediction value of each user to the target advertisement after the user is actually converted, and the actual _ bids is the competitive value of the target advertisement, namely the advertisement investment cost.
And step S13, evaluating the delivery effect of the target advertisement based on the investment profitability estimate of the target advertisement.
In the embodiment of the invention, aiming at each user in a plurality of users, the marginal cost rate pre-estimated value of the user for the target advertisement is obtained through a pre-trained cost prediction model, the investment profitability pre-estimated value of the target advertisement is calculated based on the marginal cost rate pre-estimated value of each user for the target advertisement, the income of each user after the target advertisement is converted and the bid price of the target advertisement, the delivery effect of the target advertisement is evaluated based on the investment profitability pre-estimated value of the target advertisement, because the income of each user after the target advertisement is converted and the bid price of each user for the target advertisement are not only considered in the process of pre-estimating the investment profitability of the target advertisement, but also the simple marginal cost of each user for the target advertisement is also considered, the evaluation of the advertisement effect of the target advertisement can be more accurate, thereby reasonably providing data support for the subsequent advertisement delivery scheme of an advertiser, and further provides effective reference for the advertiser to reasonably control the advertisement putting cost.
In one embodiment, the cost prediction model comprises a representation extractor layer, a feature fusion layer and a cost prediction layer, and specifically, the whole architecture of the cost prediction model is divided into three layers, and each layer can be internally provided with a multilayer neural network substructure:
a) the bottom layer is provided with a plurality of relatively weak sub-networks of the representation extractor, the sub-networks are not connected, a deep neural network structure (DNN) can be adopted as the (representation) extractor, a specific network sub-structure does not need to be specified, the network sub-structure can be replaced in a pluggable mode in the whole framework, and different representation extractors can extract different feature data;
b) the second layer is a feature fusion layer, namely a sparse connection fusion layer, and integrates the output results of the weak extractors by adopting the idea of ensemble learning, wherein the integration mode can be various, such as weighted sum, and the weight is learnable;
c) and the third layer is a cost prediction layer, which indicates that the result output by the sub-network of the extractor is input into the third layer after being synthesized, and a marginal cost rate prediction value is output through the cost prediction layer.
As shown in fig. 2, the implementation process of step S11 may include:
step S21 is to input the behavior data of the user and the advertisement data of the target advertisement to the presentation extractor layer for feature extraction for each of the plurality of users, and to obtain a plurality of feature data.
Here, the user refers to a user who refreshes the information flow provided by the traffic platform through a client. When refreshing information flow, a user can obtain a user identifier and/or a terminal identifier of the user through the flow platform, and behavior data of the user is obtained through the user identifier and/or the terminal identifier.
The behavior data of the user is data within a preset time range, for example, the behavior data of the last week or the last month, or the behavior data of the last half year, and the like, wherein the preset time range can be flexibly adjusted according to actual needs. The behavior data can sufficiently feed back online behaviors of the user on the traffic platform within a preset time range, such as how many times a certain type of video is watched, which articles are browsed, which keywords are used for searching the video, and the like.
The advertisement data may include, but is not limited to, literature data and picture data. Wherein, the file data can include but not limited to advertisement keywords, and the picture data can include but not limited to pixel values, etc.
In this embodiment, by inputting the behavior data of the user and the advertisement data of the targeted advertisement into the representation extractor layer for feature extraction, the behavior features of the user including but not limited to gender, age, hobbies, shopping, occupation, activity geographic location, focus, and the like, and the advertisement features including but not limited to advertisement file features and advertisement picture features can be obtained.
And step S22, inputting the plurality of feature data into the feature fusion layer for weighted fusion to obtain fusion features for marginal cost rate prediction.
Wherein, a weighting parameter is preset in the feature fusion layer, and the weighting parameter comprises
Specifically, the plurality of feature data are input into the feature fusion layer and weighted and summed according to weight values respectively corresponding to the plurality of feature data, so as to obtain fusion features for marginal cost rate prediction.
And step S23, inputting the fusion characteristics into the cost prediction layer to obtain a marginal cost rate predicted value of the user for the target advertisement.
In one embodiment, as shown in fig. 3, the training process of the cost prediction model includes:
and step S31, constructing a training data set, wherein the training data set is an intersection of sample data provided by the advertiser and labeled with a cost label and guest group data provided by the volume platform after collision, and the cost label is normalized cost data.
And step S32, training the cost prediction model based on the training data set to obtain the trained cost prediction model.
Specifically, the implementation process of step S32 may include:
performing iterative training on the cost prediction model based on a training data set;
in each iterative training, calculating a loss value between a marginal cost rate estimated value output by the cost prediction model and a marginal cost rate true value of a corresponding sample by using a preset loss function;
and when the loss value reaches a preset value, stopping iteratively training the cost prediction model to obtain a trained cost prediction model.
The preset loss function may adopt a cross entropy, wherein the cross entropy is a widely adopted loss function in the neural network loss functions, and the cross entropy is the prior art, and therefore is not described herein again.
In this embodiment, the training of the cost prediction model is suitable for a combined modeling scenario.
It should be noted that the fact Label (Label) information of the cost prediction model is a cost Label of the colliding customers provided by the advertiser, and is other cost besides the cost of the advertisement placement, the cost Label being normalized cost data, such as insurance claim payment cost.
In a specific embodiment, after step S14, the method may further include:
and adjusting the target advertisement delivery strategy based on the evaluation result of the target advertisement delivery effect.
The releasing strategy at least comprises one of the following steps: whether to deliver the targeted advertisement, a delivery time of the targeted advertisement, and a bid value of the targeted advertisement.
In this embodiment, the advertisement putting strategy is adjusted based on the evaluation result of the advertisement putting effect, so that the bid (bid) strategy of the advertiser can be more reasonable.
Example two
The present invention provides an apparatus for evaluating an advertisement putting effect, as shown in fig. 4, the apparatus for evaluating an advertisement putting effect may include:
an obtaining module 41, configured to obtain, for each of multiple users, a marginal cost rate prediction value of the user for the target advertisement through a pre-trained cost prediction model;
a calculating module 42, configured to calculate an investment profitability prediction value of the target advertisement based on the marginal cost rate prediction value of each user for the target advertisement, revenue of each user after conversion of the target advertisement, and a bid value of the target advertisement;
and the evaluation module 43 is configured to evaluate the delivery effect of the targeted advertisement based on the predicted value of the return on investment of the targeted advertisement.
In a specific embodiment, the cost prediction model includes a representation extractor layer, a feature fusion layer, and a cost prediction layer, and the obtaining module 41 is specifically configured to:
aiming at each user in a plurality of users, inputting behavior data of the user and advertisement data of a target advertisement into a representation extractor layer for feature extraction to obtain a plurality of feature data;
inputting a plurality of feature data into a feature fusion layer for weighted fusion to obtain fusion features for marginal cost rate prediction;
and inputting the fusion characteristics into a cost prediction layer to obtain a marginal cost rate predicted value of the user for the target advertisement.
In one embodiment, the apparatus further comprises a training module, the training module comprising:
the construction submodule is used for constructing a training data set, wherein the training data set is an intersection of sample data which is provided by an advertiser and is marked with a cost label and guest group data which are provided by a volume platform after collision, and the cost label is normalized cost data;
and the training submodule is used for training the cost prediction model based on the training data set to obtain the trained cost prediction model.
In one embodiment, the training submodule is specifically configured to:
performing iterative training on the cost prediction model based on a training data set;
in each iterative training, calculating a loss value between a marginal cost rate estimated value output by the cost prediction model and a marginal cost rate true value of a corresponding sample by using a preset loss function;
and when the loss value reaches a preset value, stopping iteratively training the cost prediction model to obtain a trained cost prediction model.
In one embodiment, the apparatus further comprises:
the adjusting module is used for adjusting the delivery strategy of the target advertisement based on the evaluation result of the delivery effect of the target advertisement, wherein the delivery strategy at least comprises one of the following: whether to deliver the targeted advertisement, a delivery time of the targeted advertisement, and a bid value of the targeted advertisement.
It should be noted that: in the evaluation apparatus for advertisement delivery effect provided in this embodiment, only the division of the above function modules is exemplified, and in practical application, the function distribution may be completed by different function modules according to needs, that is, the internal structure of the apparatus is divided into different function modules to complete all or part of the above described functions. In addition, the apparatus for evaluating an advertisement delivery effect of the present embodiment and the method for evaluating an advertisement delivery effect of the above embodiments belong to the same concept, and specific implementation processes and beneficial effects thereof are described in detail in the embodiment of the method for evaluating an advertisement delivery effect, and are not described herein again.
Fig. 5 is an internal structural diagram of a computer device according to an embodiment of the present invention. The computer device may be a server, and its internal structure diagram may be as shown in fig. 5. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of evaluating effectiveness of advertisement placement.
Those skilled in the art will appreciate that the configuration shown in fig. 5 is a block diagram of only a portion of the configuration associated with aspects of the present invention and is not intended to limit the computing devices to which aspects of the present invention may be applied, and that a particular computing device may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
aiming at each user in a plurality of users, obtaining a marginal cost rate estimated value of the user for the target advertisement through a pre-trained cost prediction model;
calculating an investment yield pre-estimated value of the target advertisement based on the marginal cost rate pre-estimated value of each user to the target advertisement, the income of each user after the target advertisement is converted and the bid value of the target advertisement;
and evaluating the delivery effect of the target advertisement based on the investment yield pre-estimated value of the target advertisement.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
aiming at each user in a plurality of users, obtaining a marginal cost rate estimated value of the user for the target advertisement through a pre-trained cost prediction model;
calculating an investment yield pre-estimated value of the target advertisement based on the marginal cost rate pre-estimated value of each user to the target advertisement, the income of each user after the target advertisement is converted and the bid value of the target advertisement;
and evaluating the delivery effect of the target advertisement based on the investment yield pre-estimated value of the target advertisement.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, databases, or other media used in embodiments provided herein may include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A method for evaluating effectiveness of advertisement placement, the method comprising:
aiming at each user in a plurality of users, obtaining a marginal cost rate estimated value of the user for the target advertisement through a pre-trained cost prediction model;
calculating an investment profit rate pre-estimated value of the target advertisement based on the marginal cost rate pre-estimated value of each user for the target advertisement, the converted income of each user for the target advertisement and the competitive value of the target advertisement;
and evaluating the delivery effect of the target advertisement based on the investment profitability estimated value of the target advertisement.
2. The method of claim 1, wherein the cost prediction model comprises a representation extractor layer, a feature fusion layer, and a cost prediction layer, and wherein obtaining, for each of a plurality of users, a marginal cost rate prediction value of the user for a targeted advertisement through a pre-trained cost prediction model comprises:
for each user in a plurality of users, inputting the behavior data of the user and the advertisement data of the target advertisement into the representation extractor layer for feature extraction to obtain a plurality of feature data;
inputting the plurality of feature data into the feature fusion layer for weighted fusion to obtain fusion features for marginal cost rate prediction;
and inputting the fusion features into the cost prediction layer to obtain a marginal cost rate prediction value of the user for the target advertisement.
3. The method according to claim 1 or 2, wherein the training process of the cost prediction model comprises:
constructing a training data set, wherein the training data set is an intersection of sample data provided by an advertiser and labeled with a cost label and guest group data provided by a volume platform after collision, and the cost label is normalized cost data;
and training the cost prediction model based on the training data set to obtain the trained cost prediction model.
4. The method of claim 3, wherein the training the cost prediction model based on the training data set to obtain the trained cost prediction model comprises:
iteratively training the cost prediction model based on the training data set;
in each iterative training, calculating a loss value between a marginal cost rate estimated value output by the cost prediction model and a marginal cost rate true value of a corresponding sample by using a preset loss function;
and stopping iterative training of the cost prediction model when the loss value reaches a preset value, so as to obtain the trained cost prediction model.
5. The method of any of claims 1 to 4, further comprising:
adjusting a delivery strategy of the target advertisement based on the evaluation result of the delivery effect of the target advertisement, wherein the delivery strategy at least comprises one of the following: whether to deliver the targeted advertisement, a delivery time of the targeted advertisement, and a bid value of the targeted advertisement.
6. An apparatus for evaluating an effectiveness of advertisement placement, the apparatus comprising:
the acquisition module is used for acquiring a marginal cost rate estimated value of each user for the target advertisement through a pre-trained cost prediction model aiming at each user in a plurality of users;
a calculation module, configured to calculate an investment profitability budget value of the targeted advertisement based on a marginal cost rate budget value of each user for the targeted advertisement, revenue of each user after conversion of the targeted advertisement, and a bid value of the targeted advertisement;
and the evaluation module is used for evaluating the delivery effect of the target advertisement based on the investment profitability prediction value of the target advertisement.
7. The apparatus of claim 6, wherein the cost prediction model comprises a representation extractor layer, a feature fusion layer, and a cost prediction layer, and wherein the obtaining module is specifically configured to:
for each user in a plurality of users, inputting the behavior data of the user and the advertisement data of the target advertisement into the representation extractor layer for feature extraction to obtain a plurality of feature data;
inputting the plurality of feature data into the feature fusion layer for weighted fusion to obtain fusion features for marginal cost rate prediction;
and inputting the fusion features into the cost prediction layer to obtain a marginal cost rate prediction value of the user for the target advertisement.
8. The apparatus of claim 6 or 7, further comprising:
an adjusting module, configured to adjust a delivery policy of the target advertisement based on an evaluation result of a delivery effect of the target advertisement, where the delivery policy at least includes one of: whether to deliver the targeted advertisement, a delivery time of the targeted advertisement, and a bid value of the targeted advertisement.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor executes the computer program to implement the method for evaluating the effectiveness of an advertisement placement according to any one of claims 1 to 5.
10. A computer-readable storage medium on which a computer program is stored, the computer program, when being executed by a processor, implementing the method for evaluating an effectiveness of an advertisement placement according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911410592.3A CN111160983A (en) | 2019-12-31 | 2019-12-31 | Advertisement putting effect evaluation method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911410592.3A CN111160983A (en) | 2019-12-31 | 2019-12-31 | Advertisement putting effect evaluation method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111160983A true CN111160983A (en) | 2020-05-15 |
Family
ID=70560008
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911410592.3A Pending CN111160983A (en) | 2019-12-31 | 2019-12-31 | Advertisement putting effect evaluation method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111160983A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111784395A (en) * | 2020-06-30 | 2020-10-16 | 百度在线网络技术（北京）有限公司 | Warning method, apparatus, computing device and medium for advertising revenue fluctuation |
| CN112258214A (en) * | 2020-09-22 | 2021-01-22 | 北京达佳互联信息技术有限公司 | Video delivery method and device and server |
| CN112270436A (en) * | 2020-10-26 | 2021-01-26 | 北京明略昭辉科技有限公司 | Resource delivery effect evaluation method, device and system |
| CN113256339A (en) * | 2021-06-04 | 2021-08-13 | 脸萌有限公司 | Resource delivery method and device, storage medium and electronic equipment |
| CN113344619A (en) * | 2021-05-31 | 2021-09-03 | 北京达佳互联信息技术有限公司 | Resource release control method, device, server and storage medium |
| CN113723982A (en) * | 2020-05-26 | 2021-11-30 | 北京达佳互联信息技术有限公司 | Method, device, server and storage medium for evaluating influence of advertisement on user experience |
| CN113763017A (en) * | 2021-01-19 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Information processing method and device and storage medium |
| CN113780710A (en) * | 2021-01-27 | 2021-12-10 | 北京沃东天骏信息技术有限公司 | Resource allocation method and resource allocation device executed by electronic equipment |
| CN116823353A (en) * | 2023-08-29 | 2023-09-29 | 阿里巴巴(成都)软件技术有限公司 | Method and equipment for predicting advertisement putting effect |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103440584A (en) * | 2013-07-31 | 2013-12-11 | 北京亿赞普网络技术有限公司 | Advertisement putting method and system |
| CN107977859A (en) * | 2017-11-14 | 2018-05-01 | 广州优视网络科技有限公司 | Advertisement placement method, device, computing device and storage medium |
| CN110570232A (en) * | 2019-08-05 | 2019-12-13 | 科大讯飞股份有限公司 | Internet advertisement putting method, device, server and storage medium |
-
2019
- 2019-12-31 CN CN201911410592.3A patent/CN111160983A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103440584A (en) * | 2013-07-31 | 2013-12-11 | 北京亿赞普网络技术有限公司 | Advertisement putting method and system |
| CN107977859A (en) * | 2017-11-14 | 2018-05-01 | 广州优视网络科技有限公司 | Advertisement placement method, device, computing device and storage medium |
| CN110570232A (en) * | 2019-08-05 | 2019-12-13 | 科大讯飞股份有限公司 | Internet advertisement putting method, device, server and storage medium |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113723982A (en) * | 2020-05-26 | 2021-11-30 | 北京达佳互联信息技术有限公司 | Method, device, server and storage medium for evaluating influence of advertisement on user experience |
| CN113723982B (en) * | 2020-05-26 | 2024-04-16 | 北京达佳互联信息技术有限公司 | Method, device, server and storage medium for evaluating influence of advertisement on user experience |
| CN111784395B (en) * | 2020-06-30 | 2024-02-13 | 百度在线网络技术（北京）有限公司 | Alarm method, device, computing equipment and medium for advertisement income fluctuation |
| CN111784395A (en) * | 2020-06-30 | 2020-10-16 | 百度在线网络技术（北京）有限公司 | Warning method, apparatus, computing device and medium for advertising revenue fluctuation |
| CN112258214A (en) * | 2020-09-22 | 2021-01-22 | 北京达佳互联信息技术有限公司 | Video delivery method and device and server |
| CN112270436A (en) * | 2020-10-26 | 2021-01-26 | 北京明略昭辉科技有限公司 | Resource delivery effect evaluation method, device and system |
| CN113763017A (en) * | 2021-01-19 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Information processing method and device and storage medium |
| CN113780710A (en) * | 2021-01-27 | 2021-12-10 | 北京沃东天骏信息技术有限公司 | Resource allocation method and resource allocation device executed by electronic equipment |
| CN113344619A (en) * | 2021-05-31 | 2021-09-03 | 北京达佳互联信息技术有限公司 | Resource release control method, device, server and storage medium |
| CN113256339A (en) * | 2021-06-04 | 2021-08-13 | 脸萌有限公司 | Resource delivery method and device, storage medium and electronic equipment |
| CN113256339B (en) * | 2021-06-04 | 2023-08-29 | 脸萌有限公司 | Resource release method and device, storage medium and electronic equipment |
| CN116823353B (en) * | 2023-08-29 | 2024-01-19 | 阿里巴巴(成都)软件技术有限公司 | Method and equipment for predicting advertisement putting effect |
| CN116823353A (en) * | 2023-08-29 | 2023-09-29 | 阿里巴巴(成都)软件技术有限公司 | Method and equipment for predicting advertisement putting effect |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111178981B (en) | Advertisement putting method and device, computer equipment and storage medium | |
| CN111160983A (en) | Advertisement putting effect evaluation method and device, computer equipment and storage medium | |
| Dubé et al. | Scalable price targeting | |
| US8473328B2 (en) | System and method for strategizing interactions with a client base | |
| US9177326B2 (en) | Method and system for determining overall content values for content elements in a web network and for optimizing internet traffic flow through the web network | |
| US10825061B2 (en) | Ad serving with multiple goals using constraint error minimization | |
| US20190080363A1 (en) | Methods and systems for intelligent adaptive bidding in an automated online exchange network | |
| US20120130798A1 (en) | Model sequencing for managing advertising pricing | |
| US11288709B2 (en) | Training and utilizing multi-phase learning models to provide digital content to client devices in a real-time digital bidding environment | |
| Ye et al. | Cold start to improve market thickness on online advertising platforms: Data-driven algorithms and field experiments | |
| US20130124302A1 (en) | Individual-level modeling | |
| US20170148051A1 (en) | Systems and methods for one-to-one advertising management | |
| JP6955888B2 (en) | Forecasting device, forecasting method, and forecasting program | |
| US20170330231A1 (en) | Method and system to display targeted ads based on ranking output of transactions | |
| CN111052167A (en) | Method and system for intelligent adaptive bidding in automated online trading network | |
| US11144968B2 (en) | Systems and methods for controlling online advertising campaigns | |
| US20150127470A1 (en) | Bid suggestions for online advertising auctions | |
| US20120130828A1 (en) | Source of decision considerations for managing advertising pricing | |
| JP2016177660A (en) | Advertisement distribution system, advertisement distribution method and advertisement distribution program | |
| US10855786B1 (en) | Optimizing value of content items delivered for a content provider | |
| CN111899049B (en) | Advertisement putting method, device and equipment | |
| JP6407185B2 (en) | Correction apparatus, correction method, and correction program | |
| US20160019583A1 (en) | Systems and methods for smooth and effective budget delivery in online advertising | |
| US20150134416A1 (en) | Initial marketing campaign targets | |
| CN113139825A (en) | Method and device for determining distribution authority of advertisement space and computer equipment |
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 |