CN111091218A

CN111091218A - Method and device for generating bidding prediction model and automatically bidding advertisement delivery

Info

Publication number: CN111091218A
Application number: CN201811234541.5A
Authority: CN
Inventors: 贺威; 毛涛; 孔维; 周柯吉; 顾勇镛
Original assignee: 4Paradigm Beijing Technology Co Ltd
Current assignee: 4Paradigm Beijing Technology Co Ltd
Priority date: 2018-10-23
Filing date: 2018-10-23
Publication date: 2020-05-01

Abstract

The invention provides a method and a device for generating a bidding prediction model and automatically bidding advertisement delivery. The automatic bidding method comprises the following steps: generating an advertisement putting bidding prediction model; generating prediction sample data based on the target user set, the advertisement putting related information of the advertisement to be put and different bid prices; inputting the extracted features as prediction data into the advertisement putting bidding prediction model to obtain bidding success probability of each user in the target user set under different bidding prices output by the model; and determining a bidding price for each user in the target user set by taking the preset total amount of the advertisement putting expenses as a limit and maximizing the number of users successfully bidding, and bidding according to the determined price.

Description

Method and device for generating bidding prediction model and automatically bidding advertisement delivery

Technical Field

The invention relates to the technical field of computers, in particular to a method and a device for generating an advertisement delivery bidding prediction model and an automatic bidding method and a device for advertisement delivery.

Background

With the rapid development of internet applications, advertising on the internet is becoming a mainstream way. The method for distributing advertisements via the internet has the advantages of wide coverage, strong initiative and the like, so that the method for distributing advertisements via the internet is more and more favored by various merchants, and thus, a traffic type platform for providing contents for an intelligent terminal is gradually developed, and when a user terminal requests to acquire the platform contents, advertisement delivery or pushing to the user terminal becomes one of the main profitable means of the platform.

In the existing application of internet advertisement delivery, advertisers obtain advertisement traffic provided by a platform in a bidding manner, that is, obtain opportunities for advertisement display on an intelligent terminal used by a platform user through bidding. The bidding mode is that who bids more, corresponding advertisement flow can be obtained.

For example, a browser APP that is popular and used by users may provide an ad slot, such as the one at the top of the home page, through which advertisers want to bid for an advertisement. The current popular internet advertisement delivery mode is mainly the delivery form of real-time bidding advertisement.

However, the existing bidding methods manually propose the price for purchasing the advertisement space, and the proposed purchase price is higher, that is, the bid price is higher, in order to win the advertisement space. However, after a huge amount of advertising fees are invested, it is a problem whether the earmarked advertising display opportunities are converted into earnings after actual purchasing of commodities to be finally profitable; even if profitable in the end, it is still a problem whether the amount of profitability reaches the desired target. These problems can be generalized as one: how does the profit margin between the amount of income for sale of goods and the amount of expenditure for advertising fees maximize? Existing methods of bid ad placement do not provide a good solution to this problem.

In view of the above technical problems of the prior art, there is a need to develop a new bidding method and apparatus for placing advertisements.

Disclosure of Invention

The invention aims to provide a method and a device for generating an advertisement delivery bidding prediction model and an automatic bidding method and a device for advertisement delivery, so as to improve the problems.

The first embodiment of the present invention provides a method for generating a prediction model for bidding placement of advertisements, which includes:

generating training sample data based on at least a historical advertisement placement bidding dataset; wherein each piece of training sample data at least comprises: the method comprises the steps that user identification of an advertisement delivery target user, advertisement delivery related information, a bidding price and marking information are obtained, wherein the marking information is bidding success or bidding failure;

performing feature extraction on the training sample data;

and based on a machine learning algorithm, performing machine learning training by using the extracted features as training data to generate an advertisement putting bidding prediction model.

Wherein the method further comprises:

obtaining a user representation data set, wherein each piece of user representation data in the user representation data set comprises a user identification and user representation information; matching and fusing the historical bidding data set and the user portrait data set based on the user identification to obtain a fused data set;

the generating training sample data based at least on the historical advertisement placement bidding dataset comprises: generating training sample data based on the fused data set; wherein each piece of training sample data comprises: the method comprises the steps of user identification of an advertisement delivery target user, advertisement delivery related information, user portrait information, bid price and marking information, wherein the marking information is bid success or bid failure.

Wherein the advertisement delivery related information comprises one or more of the following: advertisement putting media platform, advertisement space, bid mode.

Wherein the user representation information comprises: user static description data and user behavior data.

Wherein the user identifier is: the mobile phone number, the equipment identification code of the intelligent terminal, the international mobile equipment identification code or the user account information.

Wherein, in the step of performing the matching fusion process, wherein: in the successfully matched fused data, the part of the fused data with the bidding success marking information is regarded as positive sample data, and the part of the fused data with the bidding failure marking information is regarded as negative sample data.

Before performing feature extraction on the training sample data, performing data cleaning on the training sample data according to a preset cleaning rule; the cleaning rule comprises: the method comprises the steps of data type conversion, data format conversion, character string segmentation, splicing processing and irregular and redundant data removal.

Wherein the machine learning algorithm includes, but is not limited to: a logistic regression algorithm, a gradient boosting decision tree algorithm, an HE-TreeNet algorithm, a support vector machine algorithm, a naive Bayes algorithm, or a deep neural network algorithm.

Wherein, the method also comprises:

acquiring a limiting condition of an advertisement delivery target user;

and filtering the user portrait data according to the limiting conditions before matching and fusing the historical bidding data set and the user portrait data set based on the user identification.

A second embodiment of the present invention provides an automatic bidding method for advertisement delivery, including:

generating an ad placement bid prediction model based on the method of the first embodiment or a combination thereof with a preferred embodiment;

generating prediction sample data based on the target user set, the advertisement putting relevant information of the advertisement to be put and different bid prices, wherein each prediction sample data comprises: user identification, advertisement delivery related information and bid price;

performing feature extraction on the prediction sample data;

inputting the extracted features as prediction data into the advertisement putting bidding prediction model to obtain bidding success probability of each user in the target user set under different bidding prices output by the model;

and determining a bidding price for each user in the target user set by taking the preset total amount of the advertisement putting expenses as a limit and maximizing the number of users successfully bidding, and bidding according to the determined price.

Wherein the determining the bid price for each user in the target user set with the preset total amount of advertisement placement expenses as a limit and the number of users who bid successfully as a target comprises:

limit of total amount of advertisement putting expenditure

Wherein k represents a total of k users in the target user data set,

i represents the ith user in the user data set, and i is more than 0 and less than or equal to k;

p_ijrepresents a bid price for user i; p is a radical of_ij∈P_i，0＜j≤N_i，P_iRepresenting the data by N for the ith user_iA set of different bid prices;

pr(i,p_ij) The bid price for the user i which represents the output of the advertisement putting bidding prediction model is p_ijProbability of success of a bid;

r represents the total amount of the preset advertisement putting expenditure;

and solving the limited optimization problem by taking the number of successful bidding users as an optimization target, namely:

by solving the constrained optimization problem, a bid price for each user in the set of target users is obtained.

Wherein the method further comprises:

obtaining a user representation data set, wherein each user representation data in the user representation data set comprises: user identification and user portrait information;

generating prediction sample data based on the user portrait dataset, the target user set, advertisement putting related information of the advertisement to be put and different advertisement putting bid prices; each prediction sample data includes: user identification, advertising delivery related information, user profile information, and bid price.

Wherein, the method also comprises: and accumulating historical advertisement putting bidding data of advertisement putting bids performed by advertisement putting persons within a new preset period of time, and repeating the generation step of the advertisement putting bidding prediction model to continuously optimize the advertisement putting bidding prediction model.

A third embodiment of the present invention provides an apparatus for generating a prediction model for bidding placement of advertisement, including:

the training data generation module is used for generating training sample data at least based on the historical advertisement putting bidding data set; wherein each piece of training sample data at least comprises: the method comprises the steps that user identification of an advertisement delivery target user, advertisement delivery related information, a bidding price and marking information are obtained, wherein the marking information is bidding success or bidding failure;

the characteristic extraction module is used for extracting characteristics of the training sample data;

and the model generation module is used for performing machine learning training by using the extracted features as training data based on a machine learning algorithm to generate an advertisement putting bidding prediction model.

Wherein the training data generation module further comprises:

a data obtaining module, configured to obtain a historical advertisement delivery bidding data set and a user image data set, where each piece of historical advertisement delivery bidding data in the historical advertisement delivery bidding data set includes: the method comprises the following steps of identifying a user of an advertisement delivery target user, advertisement delivery related information, a bid price and marking information, wherein the marking information is bid success or bid failure, and each piece of user portrait data in a user portrait data set comprises: user identification and user portrait information;

the matching fusion module is used for matching and fusing the historical bidding data set and the user portrait data set based on the user identification to obtain a fused data set;

the training data generation module is used for generating training sample data based on the fused data set; wherein each piece of training sample data comprises: the method comprises the steps of user identification of an advertisement delivery target user, advertisement delivery related information, user portrait information, bid price and marking information, wherein the marking information is bid success or bid failure.

Wherein, in the process of matching fusion processing, the following steps are carried out: in the successfully matched fused data, the part of the fused data with the bidding success marking information is regarded as positive sample data, and the part of the fused data with the bidding failure marking information is regarded as negative sample data.

The device further comprises a data cleaning module, a feature extraction module and a data cleaning module, wherein the data cleaning module is used for performing data cleaning on the training sample data according to a preset cleaning rule before the training sample data performs feature extraction; the cleaning rule comprises: the method comprises the steps of data type conversion, data format conversion, character string segmentation, splicing processing and irregular and redundant data removal.

Wherein the training data generation module further comprises:

and the data filtering module is used for acquiring a limiting condition of an advertisement delivery target user, and filtering the user portrait data according to the limiting condition before matching and fusing the historical bidding data set and the user portrait data set based on the user identification.

A fourth embodiment of the present invention provides an automatic bid apparatus for advertisement delivery, including:

generating means for generating a bid prediction model for advertisement placement based on the generating means of the third embodiment or a combination of the third embodiment and the preferred embodiment;

the prediction sample data generation module is used for generating prediction sample data based on the target user set, the advertisement putting relevant information of the advertisement to be put and different bid prices, and each piece of prediction sample data comprises: user identification, advertisement delivery related information and bid price;

the predicted sample data feature extraction module is used for performing feature extraction on the predicted sample data;

the automatic advertisement bidding module is used for inputting the extracted features serving as prediction data into the advertisement putting bidding prediction model to obtain bidding success probability of each user in the target user set under different bidding prices output by the model; and determining a bidding price for each user in the target user set by taking the preset total amount of the advertisement putting expenses as a limit and maximizing the number of users successfully bidding, and bidding according to the determined price.

Wherein the process of determining the bid price for each user in the target user set, with the total amount of the preset advertisement placement expenditure as the limit and the number of users who successfully bid as the target, comprises:

limit of total amount of advertisement putting expenditure

Wherein k represents a total of k users in the target user data set,

r represents the total amount of the preset advertisement putting expenditure;

Wherein the prediction sample data generation module further comprises:

a user representation data acquisition module to acquire a user representation data set, wherein each piece of user representation data in the user representation data set comprises: user identification and user portrait information;

the sample data generating module is used for generating prediction sample data based on the user portrait dataset, the target user set, the advertisement putting related information of the advertisement to be put and different advertisement putting bid prices, and each prediction sample data comprises: user identification, advertising delivery related information, user profile information, and bid price.

Wherein the apparatus further comprises: and the optimization updating module is used for accumulating historical advertisement putting bidding data of advertisement putting bids performed by advertisement putting users within a new preset period of time, and repeating the generation step of the advertisement putting bidding prediction model so as to continuously optimize the advertisement putting bidding prediction model.

The fifth embodiment of the present invention also provides a computer-readable storage medium, wherein a computer program that, when executed by a processor, implements the method according to the first embodiment or the second embodiment is recorded on the computer-readable storage medium.

The sixth embodiment of the present invention further provides a computing apparatus comprising a storage unit and a processor, wherein the storage unit stores therein a set of computer-executable instructions which, when executed by the processor, cause the processor to perform the method according to the first embodiment or the second embodiment.

According to the generation method and the device of the advertisement delivery bidding prediction model and the automatic bidding method and the device of the advertisement delivery based on the advertisement delivery bidding prediction model, the machine learning method is adopted to generate the advertisement delivery bidding prediction model by using the historical advertisement delivery bidding dataset or by using the historical advertisement delivery bidding dataset and the user image dataset, and the prediction model can predict the corresponding successful bidding probability of different bidding prices of the advertisement to be delivered aiming at the advertisement position of the advertisement delivery media platform. By using the automatic bidding method and device for advertisement delivery based on the advertisement delivery bidding prediction model, in a bidding advertisement business mode, particularly a real-time bidding advertisement business mode, the bidding price of each user in a target user set can be determined under the condition that the number of users for predicting successful bidding is maximized, and the automatic bidding is carried out according to the determined price, so that the profit margin between the income amount of commodity sales and the expenditure amount of advertisement fee can be maximized, and higher economic benefit can be brought to advertisers.

Drawings

Fig. 1 is a flowchart of a method for generating a prediction model for bidding placement of advertisement according to a first embodiment of the present invention;

FIG. 2 is a flow chart of a variation of a method for generating a bid prediction model for advertisement placement provided by a first embodiment of the present invention;

FIG. 3 is a flowchart of an automatic bidding method for advertisement delivery according to a second embodiment of the present invention;

fig. 4 is a schematic block diagram of a device for generating a model for predicting bid for advertisement placement according to a third embodiment of the present invention;

FIG. 5 is a schematic block diagram of a variation of an apparatus for generating a bid prediction model for advertisement placement provided by a third embodiment of the present invention;

fig. 6 is a schematic block diagram of an exemplary scheme of a training data generation module included in a device for generating a bid prediction model for advertisement placement according to a third embodiment of the present invention;

fig. 7 is a schematic block diagram of a variation of a training data generation module included in a device for generating a bid prediction model for advertisement placement according to a third embodiment of the present invention;

fig. 8 is a schematic block diagram of an automatic bidding apparatus for advertisement delivery provided by a fourth embodiment of the present invention;

fig. 9 is a schematic block diagram of a prediction sample data generation module included in an automatic bidding apparatus for advertisement delivery according to a fourth embodiment of the present invention.

Detailed Description

The invention provides a novel automatic bid method and a device for advertisement putting based on an artificial intelligence technology. At the heart of artificial intelligence technology is machine learning, which is the fundamental way to make computers intelligent. Different machine learning models can be developed based on different specific algorithms and logic criteria, common algorithms include, for example: logistic regression algorithm, gradient boosting decision tree algorithm (GBDT), HE-TreeNet algorithm, support vector machine algorithm (SVM), naive Bayes algorithm, deep neural network algorithm (DNN), and the like. The technical solutions proposed by the present invention will be clearly and completely described below with reference to specific embodiments and the accompanying drawings, and it is to be understood that the described exemplary embodiments are for illustrative purposes only and are not limiting.

Fig. 1 is a flowchart of a method for generating a prediction model for bidding placement of advertisement according to a first embodiment of the present invention. As shown in fig. 1, a method for generating a bid prediction model for advertisement placement according to a first embodiment of the present invention includes:

s11: and generating training sample data.

Obtaining historical bidding data of advertisement putting to obtain a historical advertisement putting bidding data set. The historical bidding data includes at least: the method comprises the steps of user identification of an advertisement delivery target user, advertisement delivery related information, a bidding price and marking information, wherein the marking information is bidding success or bidding failure. Generating training sample data based on at least a historical advertisement placement bidding dataset; wherein each piece of training sample data at least comprises: the method comprises the steps of user identification of an advertisement delivery target user, advertisement delivery related information, a bidding price and marking information, wherein the marking information is bidding success or bidding failure.

Wherein the user identifier is: the mobile phone number, the equipment identification code of the intelligent terminal, the international mobile equipment identification code or the user account information and the like. The advertisement delivery related information includes one or more of the following: advertisement putting media platform, advertisement space, bid mode. The advertisement delivery media platform can be a today's headline, a UC browser, an love art APP and the like; the advertisement position can be a top detail page of the day, a UC browser home page and the like; bidding modes may include, for example, but are not limited to: charge per click, charge per presentation, charge per conversion, and so forth.

Any distinguishing symbol may be used to indicate either a successful bid or a failed bid. For example, in a software program, a bid success may be indicated by a "1" and a bid failure indicated by a "0".

S12: and performing feature extraction on the training sample data.

The feature extraction involved in the machine learning can be performed by methods known in the art, for example, feature extraction based on feature engineering in machine learning. For example, the original feature space may be changed by processing, correlating, combining, or otherwise varying different attribute features to obtain richer feature attributes.

S13: and based on a machine learning algorithm, performing machine learning training by using the extracted features as training data to generate an advertisement putting bidding prediction model.

The method for performing machine learning training by using the training data is also implemented by using a method known in the art, and a known optimization algorithm is adopted to determine an optimal model parameter combination corresponding to the advertisement putting bidding prediction model to be generated, so as to generate an advertisement putting bidding prediction model corresponding to the optimal model parameter combination. The training process is not described in detail here.

Here, it should be noted that: in an embodiment of the present invention, the output of the generated ad placement bid prediction model is a score for the success of bidding, with a score in the range of 0,1, and therefore the score is considered approximately as the bid success probability in this application.

In a preferred embodiment, the method for generating the advertisement placement bid prediction model further includes data cleaning, that is, before performing the feature extraction on the training sample data in step S12, performing data cleaning on the training sample data according to a predetermined cleaning rule; the cleaning rule comprises: the method comprises the steps of data type conversion, data format conversion, character string segmentation, splicing processing and irregular and redundant data removal. Through data cleaning, the type, format and the like of data meet requirements, irregular and redundant data are removed, and the usability of training data can be improved. In addition, in the technical field, a plurality of data cleaning methods are disclosed and related articles are published, and the data cleaning method mentioned herein is performed by using the known technology disclosed and thus is not described too much.

Based on the concept of the technical scheme described in the first embodiment, the invention also provides a variation scheme. Fig. 2 is a flowchart of a variation of the method for generating a model for predicting bids for advertisement placement according to the first embodiment of the present invention. As shown in fig. 2, a method for generating a bid prediction model for advertisement placement according to a first embodiment of the present invention includes:

s21: and generating training sample data.

Firstly, historical bidding data of advertisement delivery is obtained or collected, and a historical advertisement delivery bidding data set is obtained. The historical advertisement placement bidding data includes at least: the method comprises the steps of user identification of an advertisement delivery target user, advertisement delivery related information, a bidding price and marking information, wherein the marking information is bidding success or bidding failure. Additionally, it is also desirable to obtain or collect a user portrait data set, wherein each piece of user portrait data in the user portrait data set includes: user identification and user portrait information.

Wherein the user identifier is: the mobile phone number, the equipment identification code of the intelligent terminal, the international mobile equipment identification code or the user account information and the like. The user identification is the user identification of the advertisement delivery target user included in the historical advertisement delivery bidding data and the user identification included in the user image data. The advertisement delivery related information includes one or more of the following: advertisement putting media platform, advertisement space, bid mode. The advertisement delivery media platform can be a today's headline, a UC browser, an love art APP and the like; the advertisement position can be a top detail page of the day, a UC browser home page and the like; bidding modes may include, for example, but are not limited to: charge per click, charge per presentation, charge per conversion, and so forth.

The user profile information includes: user static description data and user behavior data. Wherein the user static description data comprises one or more of the following: gender, age, occupation, academic calendar, city of residence, hobbies, specialties, categories of favorite purchased goods, etc.; the user behavior data includes one or more of the following: purchase behavior data (e.g., physical goods, financial goods, other virtual goods, etc.), APP install behavior data, swipe behavior data, and so forth. In addition to the information listed herein, other user portrait information may be included, such as nationality, frequently done, most recent, etc., not to mention here. The method of obtaining the user representation data set may be implemented by known methods, for example, the collected user representation data set may be obtained from a third party, and generally the third party obtains the user representation data set by collecting data input by the user at the time of registration.

And then, matching and fusing the historical advertisement putting bidding data set and the user portrait data set based on the user identification to obtain a fused data set.

Because the historical advertisement delivery bidding data and the user portrait data both include user identification, the user identification is preferably a mobile phone number or user account information, and matching is achieved by comparing whether the user identification of the historical advertisement delivery bidding data and the user portrait data is the same. The matching fusion processing is to combine the historical advertisement putting bidding data and the user image data with the same user identification into a new data, thereby obtaining a fused data set. By two data being combined into a new data is meant that the two data are merged together to form a new data, wherein: identical information is combined into one information, and different information coexists in the new data.

In the process of performing matching fusion processing, wherein: in the successfully matched fused data, the part of the fused data with the bidding success marking information is regarded as positive sample data, and the part of the fused data with the bidding failure marking information is regarded as negative sample data. And for unmatched historical advertisement putting bidding data and user image data, the method is abandoned. The mismatch is that there is no same user identifier between the historical advertisement placement bid data in the historical advertisement placement bid data set and the user profile data in the user profile data set. In practice, when the user profile data is collected in sufficient quantities, the quantity of unmatched historical ad placement bid data in the historical ad placement bid data set will be small or may not be unmatched.

The invention finds the relevance between the advertisement putting bidding data characteristic and the user portrait data characteristic through machine learning, so that the successfully matched historical advertisement putting bidding data and user portrait data are preferably used; the unmatched historical ad placement bid data and/or user profile data is not typically used.

Then, generating training sample data based on the fused data set; wherein each piece of training sample data comprises: the method comprises the steps of user identification of an advertisement delivery target user, advertisement delivery related information, user portrait information, bid price and marking information, wherein the marking information is bid success or bid failure.

S22: and performing feature extraction on the training sample data.

S23: and based on a machine learning algorithm, performing machine learning training by using the extracted features as training data to generate an advertisement putting bidding prediction model.

And using the generated advertisement putting bidding prediction model, predicting the probability of success of corresponding bidding of different bidding prices of the advertisement to be put aiming at the advertisement position of the advertisement putting media platform. It should be understood that the model trained by machine learning outputs simple numerical values without specific meaning. However, since the used training data is from the historical advertisement placement bidding data or the matching fusion data of the historical advertisement placement bidding data and the user figure data, and these data contain rich information, especially the label information of label bidding success or bidding failure, the numerical value output by the advertisement placement bidding prediction model reflects the possibility of successful bidding, and the numerical value output by the advertisement placement bidding prediction model can be approximately regarded as the probability value of successful bidding.

In a preferred embodiment, the method for generating the advertisement placement bid prediction model further includes data cleaning, that is, before performing the feature extraction on the training sample data in step S22, performing data cleaning on the training sample data according to a predetermined cleaning rule; the cleaning rule comprises: the method comprises the steps of data type conversion, data format conversion, character string segmentation, splicing processing and irregular and redundant data removal. Through data cleaning, the type, format and the like of data meet requirements, irregular and redundant data are removed, and the usability of training data can be improved. In addition, in the technical field, a plurality of data cleaning methods are disclosed and related articles are published, and the data cleaning method mentioned herein is performed by using the known technology disclosed and thus is not described too much.

In another preferred embodiment, the method for generating the advertisement placement bid prediction model further comprises the following steps:

acquiring a limiting condition of an advertisement delivery target user; and filtering the user portrait data according to the limiting conditions before matching and fusing the historical bidding data set and the user portrait data set based on the user identification.

The target user restrictions include, but are not limited to: gender, age, location or city of residence, etc. For example, if the advertised product is a female specific product, male user data may be filtered from the user imagery data set by gender restrictions. Further, if the product advertised is a network game product, since the possibility of the aged playing the network game is low, the user data of over a certain age may be filtered out from the user representation data set by the age restriction, for example, over 45 years, or over 50 years, etc. By filtering the user image data under the limiting conditions, the amount of data calculation can be reduced, the target user group can be made clearer, and the expenditure of advertising fees can be reduced.

According to the generation method of the advertisement delivery bidding prediction model provided by the first embodiment of the invention, a machine learning method is adopted to generate the advertisement delivery bidding prediction model by using the historical advertisement delivery bidding dataset or by using the historical advertisement delivery bidding dataset and the user image dataset, and the probability of successful corresponding bidding of different bidding prices of the advertisement to be delivered can be predicted aiming at the advertisement slot of the advertisement delivery media platform by using the prediction model.

Fig. 3 is a flowchart of an automatic bidding method for advertisement delivery according to a second embodiment of the present invention. As shown in fig. 3, an automatic bidding method for advertisement delivery according to a second embodiment of the present invention includes:

s31: the ad placement bid prediction model is generated based on the method described in connection with the first embodiment described in connection with fig. 1 or any combination thereof with the preferred embodiment, or based on the method described in connection with the variation of the first embodiment described in fig. 2 or any combination thereof with the preferred embodiment.

That is, an advertisement placement bid prediction model is first generated, and the generation method of the advertisement placement bid prediction model may adopt the method described in the first embodiment described in conjunction with fig. 1 or any combination thereof with the preferred embodiment, or adopt the method described in the variation of the first embodiment described in conjunction with fig. 2 or any combination thereof with the preferred embodiment, and will not be described repeatedly here.

S32: generating prediction sample data based on the target user set, the advertisement putting relevant information of the advertisement to be put and different bid prices, wherein each prediction sample data comprises: user identification, advertisement placement related information, and bid price.

The target user set is a user group which is expected by an advertiser to receive the advertisement to be placed. The user identification is: the mobile phone number, the equipment identification code of the intelligent terminal, the international mobile equipment identification code or the user account information and the like are preferably adopted.

The advertisement delivery related information includes one or more of the following: an advertising media platform; an advertisement slot; and (4) bidding modes. The advertisement delivery media platform can be a today's headline, a UC browser, an love art APP and the like; the advertisement position can be a top detail page of the day, a UC browser home page and the like; bidding modes may include, for example, but are not limited to: charge per click, charge per presentation, charge per conversion, and so forth.

The different bid prices can assume a variety of different bid prices based on historical empirical prices.

S33: performing feature extraction on the prediction sample data.

In addition, if necessary, data cleaning is also performed before feature extraction is performed on the prediction sample data. For example, performing data cleaning on the training sample data according to a predetermined cleaning rule; the cleaning rule comprises: the method comprises the steps of data type conversion, data format conversion, character string segmentation, splicing processing, irregular and redundant data removal and the like. Through data cleaning, the type, format and the like of data meet requirements, irregular and redundant data are removed, and the availability of prediction sample data can be improved.

S34: and inputting the extracted features as prediction data into the advertisement putting bidding prediction model to obtain the bidding success probability of each user in the target user set under different bidding prices output by the model.

That is, the extracted features are input as prediction data into the ad placement bid prediction model, which is capable of outputting a bid success probability for each user in the target user set at different bid prices for an ad placement of an ad placement media platform with respect to an ad to be placed.

S35: and determining a bidding price for each user in the target user set by taking the preset total amount of the advertisement putting expenses as a limit and maximizing the number of users successfully bidding, and bidding according to the determined price.

The method for determining the bid price for each user in the target user set by taking the preset total amount of advertisement putting expenses as a limit and maximizing the number of users who bid successfully comprises the following steps:

limit of total amount of advertisement putting expenditure

Wherein k represents a total of k users in the target user data set,

r represents the total amount of the preset advertisement putting expenditure;

The following is a simplified explanation of the above method. Assuming that the advertiser sets the advertisement placement amount R to be paid to be 1 ten thousand dollars, the sum of the bid price for each of the selected plurality of users multiplied by the cumulative probability of success of the respective bids is less than or equal to 1 ten thousand dollars. Under the condition that the limitation condition is met, a price set of different bid prices for each user in the selected multiple users is found, and the sum of bidding success probabilities at the bid price for each user in the price set is maximum.

For the purpose of simplicity of explanation, the number of the plurality of users is now limited to 3, different bid prices of an ad spot for a certain ad delivery media platform with respect to an ad to be delivered are set to 1-ary and 2-ary, respectively, and bid success probabilities for the different bid prices of each user are listed in table 1, where the given bid success probabilities are assumed values for illustrative purposes only and do not represent true numbers.

TABLE 1

Thus, for 2 different bid prices offered by 3 users, 8 different sets of bid combinations can be derived, respectively:

group 1: user 1: bid 1 yuan, user 2: bid 1 yuan, user 3: bidding for 1 yuan;

group 2: user 1: bid 1 yuan, user 2: bid 1 yuan, user 3: bidding for 2 yuan;

group 3: user 1: bid 1 yuan, user 2: bid 2-ary, user 3: bidding for 1 yuan;

group 4: user 1: bid 1 yuan, user 2: bid 2-ary, user 3: bidding for 2 yuan;

group 5: user 1: bid 2-ary, user 2: bid 1 yuan, user 3: bidding for 1 yuan;

group 6: user 1: bid 2-ary, user 2: bid 1 yuan, user 3: bidding for 2 yuan;

group 7: user 1: bid 2-ary, user 2: bid 2-ary, user 3: bidding for 1 yuan;

group 8: user 1: bid 2-ary, user 2: bid 2-ary, user 3: and 5, bidding for 2 yuan.

These 8 different sets of bid combinations are respectively substituted into the constraint equations:

obtaining: group 1: 1.85 membered, group 2: 3.01 membered, group 3: 2.96-element (I) is selected,

group 4: 4.12-membered, group 5: 3.05-membered, group 6: 4.21-element of the Chinese herbal medicine,

group 7: 4.16-membered, group 8: 5.32 yuan

Assuming that the preset total amount R of the advertisement delivery expenditure is 4 yuan, only the bid combinations of the 1 st, 2 nd, 3 rd and 5 th groups meeting the restriction condition are substituted into the formula respectively

It can be found out that:

the sum of the bidding success probabilities for the bid combinations of group 1 is: 185% for 60% + 55% + 70%;

the sum of the bidding success probabilities for the bid combinations of group 2 is: 60% + 55% + 93% + 208%;

the sum of the bidding success probabilities for the bid combinations of group 3 is: 60% + 83% + 70% + 213%;

the sum of the bidding success probabilities for the bid combinations of group 5 is: 90% + 55% + 70% + 215%.

It can be seen that the bid combination of the 5 th group is an optimization target for the number of successful users, and thus the bid price for each user in the target user set can be determined as follows: the bid price determined for the user 1 is 2 yuan, the bid price determined for the user 2 is 1 yuan, and the bid price determined for the user 3 is 1 yuan, so that it is possible to make a bid according to the determined price, which makes it possible to maximize a profit margin between an amount of income of sales of goods and an amount of expenditure of advertising fees, and to bring a higher economic benefit to advertisers.

With regard to the method for generating prediction sample data, in a preferred embodiment, the following manner may also be adopted:

The user profile information includes: user static description data and user behavior data. Wherein the user static description data comprises one or more of the following: gender, age, occupation, academic calendar, city of residence, hobbies, specialties, categories of favorite purchased goods, etc.; the user behavior data includes one or more of the following: purchasing behavior data (e.g., physical goods, financial goods, other virtual goods, etc.), APP installation behavior data, card swiping consonance data, and so forth. In addition to the information listed herein, other user portrait information may be included, such as nationality, frequently done, most recent, etc., not to mention here.

In order to further optimize the advertisement placement bid prediction model, in a preferred embodiment, the automatic bidding method for advertisement placement may further include the following steps: and accumulating historical advertisement putting bidding data of advertisement putting bids performed by advertisement putting persons within a new preset period of time, and repeating the generation step of the advertisement putting bidding prediction model to continuously optimize the advertisement putting bidding prediction model.

According to the automatic bidding method for advertisement delivery provided by the second embodiment of the present invention, based on the generated advertisement delivery bidding prediction model, in the bidding advertisement business model, especially in the real-time bidding advertisement business model, it is possible to determine the bid price for each user in the target user set under the condition that the number of users predicting successful bidding is maximized, and automatically bid according to the determined price, which makes it possible to maximize the profit margin between the income amount of commodity sales and the expenditure amount of advertisement charges, and to bring higher economic benefit to advertisers.

Fig. 4 is a schematic block diagram of a device for generating a model for predicting bid for advertisement placement according to a third embodiment of the present invention. The apparatus 400 for generating a prediction model for bidding placement of advertisement according to the third embodiment of the present invention includes:

a training data generation module 401, configured to generate training sample data based on at least a historical advertisement delivery bidding data set; wherein each piece of training sample data at least comprises: the method comprises the steps that user identification of an advertisement delivery target user, advertisement delivery related information, a bidding price and marking information are obtained, wherein the marking information is bidding success or bidding failure;

a feature extraction module 402, configured to perform feature extraction on the training sample data;

and a model generation module 403, configured to perform machine learning training based on a machine learning algorithm by using the extracted features as training data, and generate an advertisement delivery bidding prediction model.

Fig. 5 is a schematic block diagram of a variation of an apparatus 400 for generating a bid prediction model for advertisement placement according to a third embodiment of the present invention. As shown in fig. 5, the generating apparatus 400 may further include a data cleaning module 504, configured to perform data cleaning on the training sample data according to a predetermined cleaning rule before performing feature extraction on the training sample data; the cleaning rule comprises: the method comprises the steps of data type conversion, data format conversion, character string segmentation, splicing processing and irregular and redundant data removal.

In addition, the present invention provides an exemplary specific scheme structure for the training data generation module for generating training sample data. Fig. 6 is a schematic block diagram of an exemplary scheme of a training data generation module 401 included in a device for generating a bid prediction model for advertisement placement according to a third embodiment of the present invention. As shown in fig. 6, the training data generation module 401 may further include:

a data obtaining module 601, configured to obtain a historical advertisement delivery bidding data set and a user image data set, where each piece of historical advertisement delivery bidding data in the historical advertisement delivery bidding data set includes: the method comprises the following steps of identifying a user of an advertisement delivery target user, advertisement delivery related information, a bid price and marking information, wherein the marking information is bid success or bid failure, and each piece of user portrait data in a user portrait data set comprises: user identification and user portrait information;

a matching fusion module 602, configured to perform matching fusion processing on the historical bidding dataset and the user portrait dataset based on a user identifier to obtain a fused dataset;

the training data generation module 401 is configured to generate training sample data based on the fused data set; wherein each piece of training sample data comprises: the method comprises the steps of user identification of an advertisement delivery target user, advertisement delivery related information, user portrait information, bid price and marking information, wherein the marking information is bid success or bid failure.

Wherein the user representation information comprises: user static description data and user behavior data. Wherein the user static description data comprises one or more of the following: gender, age, occupation, academic calendar, city of residence, hobbies, specials, categories of favorite purchases; the user behavior data includes one or more of the following: purchasing behavior data (e.g., physical goods, financial goods, other virtual goods, etc.), APP installation behavior data, card swiping consonance data, and so forth.

The matching fusion module 602 performs matching fusion processing during the process, wherein: in the successfully matched fused data, the part of the fused data with the bidding success marking information is regarded as positive sample data, and the part of the fused data with the bidding failure marking information is regarded as negative sample data.

Fig. 7 is a schematic block diagram of a variation of a training data generation module 401 included in the apparatus 400 for generating a bid prediction model for advertisement placement according to the third embodiment of the present invention. As shown in fig. 7, the training data generation module 401 may further include:

and the data filtering module 704 is configured to obtain a limiting condition of a target user for advertisement delivery, and filter the user portrait data according to the limiting condition before matching and fusing the historical bidding dataset and the user portrait dataset based on the user identifier.

It is clear to those skilled in the art that for convenience and brevity of description, the specific working process of the apparatus described in the technical solution and the modifications thereof of the third embodiment above can refer to the corresponding process of the technical solution and the modifications thereof of the first embodiment above, the technical solution and the modifications of the first embodiment above and the examples and related descriptions listed in the corresponding preferred embodiments above are also applicable to explain the working process of the apparatus described in the technical solution and the modifications thereof of the third embodiment above, and the description is not repeated here.

According to the generation device of the advertisement delivery bidding prediction model provided by the third embodiment of the invention, the historical advertisement delivery bidding dataset is used, or the historical advertisement delivery bidding dataset and the user image dataset are used, a machine learning method is adopted to generate the advertisement delivery bidding prediction model, and the probability of successful corresponding bidding of different bidding prices of the advertisement to be delivered can be predicted aiming at the advertisement slot of the advertisement delivery media platform by using the prediction model.

Fig. 8 is a schematic block diagram of an automatic bidding apparatus for advertisement delivery according to a fourth embodiment of the present invention. An automatic bid apparatus for advertisement delivery according to a fourth embodiment of the present invention includes:

the device 400 for generating an advertisement delivery bid prediction model according to the third embodiment or its variation, or the device 400 for generating an advertisement delivery bid prediction model according to any combination of the third embodiment or its variation and the preferred embodiment, is configured to generate an advertisement delivery bid prediction model;

a prediction sample data generating module 801, configured to generate prediction sample data based on the target user set, the advertisement delivery related information of the advertisement to be delivered, and different bid prices, where each prediction sample data includes: user identification, advertisement delivery related information and bid price;

a prediction sample data feature extraction module 802, configured to perform feature extraction on the prediction sample data;

an automatic advertisement bidding module 803, configured to use the extracted features as prediction data to input to the advertisement delivery bidding prediction model, and obtain a bidding success probability of each user in the target user set at different bidding prices output by the model; and determining a bidding price for each user in the target user set by taking the preset total amount of the advertisement putting expenses as a limit and maximizing the number of users successfully bidding, and bidding according to the determined price.

limit of total amount of advertisement putting expenditure

Wherein k represents a total of k users in the target user data set,

r represents the total amount of the preset advertisement putting expenditure;

In addition, the present invention provides an exemplary specific scheme structure for the prediction sample data generation module 801 for generating prediction sample data. Fig. 9 is a schematic block diagram of a prediction sample data generation module included in an automatic bidding apparatus for advertisement delivery according to a fourth embodiment of the present invention. As shown in fig. 9, the prediction sample data generation module 801 further includes:

a user representation data acquisition module 901 for acquiring a user representation data set, wherein each user representation data in the user representation data set comprises: user identification and user portrait information;

a sample data generating module 902, configured to generate prediction sample data based on the user portrait dataset, the target user set, advertisement delivery related information of an advertisement to be delivered, and different advertisement delivery bid prices, where each prediction sample data includes: user identification, advertising delivery related information, user profile information, and bid price.

Wherein the user representation information comprises: user static description data and user behavior data. Wherein the user static description data comprises one or more of the following: gender, age, occupation, academic calendar, city of residence, hobbies, specialties, categories of favorite purchased goods, etc.; the user behavior data includes one or more of the following: purchasing behavior data (e.g., physical goods, financial goods, other virtual goods, etc.), APP installation behavior data, card swiping consonance data, and so forth.

In addition, the automatic bidding apparatus for advertisement delivery may further include: and an optimization updating module (not shown) for accumulating historical advertisement putting bidding data of advertisement putting bids performed by advertisement putting users within a new preset period of time, and repeating the generation step of the advertisement putting bidding prediction model to continuously optimize the advertisement putting bidding prediction model.

It is clear to those skilled in the art that for convenience and brevity of description, the specific working process of the apparatus described in the technical solution and the modifications thereof of the fourth embodiment above can refer to the corresponding process of the technical solution and the modifications thereof of the second embodiment above, the technical solution and the modifications of the second embodiment above and the examples and related descriptions listed in the corresponding preferred embodiments above are also applicable to explain the working process of the apparatus described in the technical solution and the modifications thereof of the fourth embodiment above, and the description is not repeated here.

According to the automatic bidding device for advertisement delivery provided by the fourth embodiment of the present invention, based on the generated advertisement delivery bidding prediction model, in the bidding advertisement business model, especially in the real-time bidding advertisement business model, it is possible to determine the bid price for each user in the target user set under the condition that the number of users predicting successful bidding is maximized, and automatically bid according to the determined price, which makes it possible to maximize the profit margin between the income amount of commodity sales and the expenditure amount of advertisement charges, and to bring higher economic benefits to advertisers.

The generation method of the bid prediction model for advertisement placement, the automatic bidding method for advertisement placement, the generation apparatus of the bid prediction model for advertisement placement, and the automatic bidding apparatus for advertisement placement according to the exemplary embodiments of the present application have been described above with reference to fig. 1 to 9. However, it should be understood that: the apparatuses and unit modules thereof shown in fig. 4 to 9 may be respectively configured as software, hardware, firmware, or any combination thereof to perform a specific function. For example, these means or unit modules may correspond to dedicated integrated circuits, to pure software code, or to a combination of software and hardware. Furthermore, one or more functions implemented by these means or unit modules may also be uniformly executed by components in a physical entity device (e.g., processor, client or server, etc.).

Furthermore, the above-described method may be implemented by a program recorded on a computer-readable storage medium, for example, according to the exemplary embodiments of the present application, a computer-readable storage medium may be provided, on which a computer program is recorded which, when executed by a processor, implements the method as described in the first embodiment or the method as described in the variation of the first embodiment or their combination with the respective preferred embodiments, respectively. Furthermore, a computer-readable storage medium may also be provided, wherein a computer program is recorded on the computer-readable storage medium, which when executed by a processor implements the method according to the second embodiment or the combination thereof with the respective preferred embodiments.

The computer program in the computer-readable storage medium may be executed in an environment deployed in a computer device such as a client, a host, a proxy device, a server, etc., and it should be noted that the computer program may also be used to perform additional steps other than or in addition to the above steps, and the content of the additional steps and further processing is mentioned in the description of the related method with reference to fig. 1 to 3, so that the description is not repeated here to avoid repetition.

It should be noted that the generation apparatus of the bid prediction model for advertisement placement and the automatic bidding apparatus for advertisement placement according to the exemplary embodiments of the present application may completely depend on the execution of the computer program to implement the corresponding functions, i.e., the units correspond to the steps in the functional architecture of the computer program, so that the whole apparatus is called by a special software package (e.g., lib library) to implement the corresponding functions.

On the other hand, the means or unit modules shown in fig. 4 to 9 may also be implemented by hardware, software, firmware, middleware, microcode, or any combination thereof. When implemented in software, firmware, middleware or microcode, the program code or code segments to perform the corresponding operations may be stored in a computer-readable storage medium such as a storage medium, so that a processor may perform the corresponding operations by reading and executing the corresponding program code or code segments.

For example, the exemplary embodiments of the present application may also be embodied as a computing device comprising a storage component and a processor, the storage component having stored therein a set of computer-executable instructions that, when executed by the processor, perform the method steps as set forth in the first embodiment or a combination thereof with the respective preferred embodiments; or to carry out the method steps as described in the second embodiment or a combination thereof with the respective preferred embodiments.

In particular, the computing devices may be deployed in servers or clients, as well as on node devices in a distributed network environment. Further, the computing device may be a PC computer, tablet device, personal digital assistant, smart phone, web application, or other device capable of executing the set of instructions described above.

The computing device need not be a single computing device, but can be any device or collection of circuits capable of executing the instructions (or sets of instructions) described above, individually or in combination. The computing device may also be part of an integrated control system or system manager, or may be configured as a portable electronic device that interfaces with local or remote (e.g., via wireless transmission).

In the computing device, the processor may include a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), a programmable logic device, a special purpose processor system, a microcontroller, or a microprocessor. By way of example, and not limitation, processors may also include analog processors, digital processors, microprocessors, multi-core processors, processor arrays, network processors, and the like.

Some of the operations described in the method according to the exemplary embodiments of the present application may be implemented by software, some of the operations may be implemented by hardware, and furthermore, the operations may be implemented by a combination of hardware and software.

The processor may execute instructions or code stored in one of the memory components, which may also store data. Instructions and data may also be transmitted and received over a network via a network interface device, which may employ any known transmission protocol.

The memory component may be integral to the processor, e.g., having RAM or flash memory disposed within an integrated circuit microprocessor or the like. Further, the storage component may comprise a stand-alone device, such as an external disk drive, storage array, or any other storage device usable by a database system. The storage component and the processor may be operatively coupled or may communicate with each other, such as through an I/O port, a network connection, etc., so that the processor can read files stored in the storage component.

Further, the computing device may also include a video display (such as a liquid crystal display) and a user interaction interface (such as a keyboard, mouse, touch input device, etc.). All components of the computing device may be connected to each other via a bus and/or a network.

The operations involved in the methods according to the exemplary embodiments of the present application may be described as various interconnected or coupled functional blocks or functional diagrams. However, these functional blocks or functional diagrams may be equally integrated into a single logic device or operated on by non-exact boundaries.

While exemplary embodiments of the present application are described above, it should be understood that: the above description is exemplary only and not exhaustive. The present application is not limited to the disclosed exemplary embodiments, and many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the application. Therefore, the protection scope of the present application shall be subject to the scope of the claims.

Claims

1. A method of generating a bid prediction model for advertisement placement, comprising:

performing feature extraction on the training sample data;

2. The method of claim 1, wherein the first and second light sources are selected from the group consisting of,

further comprising: obtaining a user representation data set, wherein each piece of user representation data in the user representation data set comprises a user identification and user representation information; matching and fusing the historical bidding data set and the user portrait data set based on the user identification to obtain a fused data set;

3. An automatic bidding method for advertisement placement, comprising:

generating an ad placement bid prediction model based on the method of one of the claims 1-2;

performing feature extraction on the prediction sample data;

4. The method of claim 3, wherein the determining a bid price for each user in the target set of users, limited by a preset total amount of advertising placement expenditures and targeted at maximizing a number of users who bid successfully, comprises:

limit of total amount of advertisement putting expenditure

Wherein k represents a total of k users in the target user data set,

r represents the total amount of the preset advertisement putting expenditure;

5. An apparatus for generating a bid prediction model for advertisement placement, comprising:

6. The apparatus of claim 5, wherein the training data generation module further comprises:

7. An automatic bidding apparatus for advertisement placement, comprising:

generating means for generating an ad placement bid prediction model based on the generating means of one of claims 5 to 6;

8. The apparatus of claim 7, wherein the process of determining a bid price for each user in the target set of users, limited by a preset total amount of advertising placement expenditures and targeted at maximizing a number of users who bid successfully, comprises:

limit of total amount of advertisement putting expenditure

Wherein k represents a total of k users in the target user data set,

r represents the total amount of the preset advertisement putting expenditure;

9. A computer-readable storage medium, wherein a computer program is recorded on the computer-readable storage medium, which when executed by a processor implements the method of any of claims 1 to 4.

10. A computing device comprising a storage component and a processor, wherein the storage component has stored therein a set of computer-executable instructions that, when executed by the processor, cause the processor to perform the method of any of claims 1 to 4.