WO2017004866A1 - 一种广告价值确定方法及装置 - Google Patents
一种广告价值确定方法及装置 Download PDFInfo
- Publication number
- WO2017004866A1 WO2017004866A1 PCT/CN2015/087384 CN2015087384W WO2017004866A1 WO 2017004866 A1 WO2017004866 A1 WO 2017004866A1 CN 2015087384 W CN2015087384 W CN 2015087384W WO 2017004866 A1 WO2017004866 A1 WO 2017004866A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- advertisement
- value
- advertisement value
- value calculation
- calculation strategy
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 85
- 238000004364 calculation method Methods 0.000 claims abstract description 275
- 238000010801 machine learning Methods 0.000 claims description 9
- 238000007619 statistical method Methods 0.000 claims description 9
- 230000001131 transforming effect Effects 0.000 claims description 3
- 230000006870 function Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 230000009466 transformation Effects 0.000 description 9
- 230000008901 benefit Effects 0.000 description 8
- 238000012937 correction Methods 0.000 description 7
- 238000012545 processing Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000007637 random forest analysis Methods 0.000 description 4
- 230000001360 synchronised effect Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000013145 classification model Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000007477 logistic regression Methods 0.000 description 2
- 238000010295 mobile communication Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000000844 transformation Methods 0.000 description 2
- KLDZYURQCUYZBL-UHFFFAOYSA-N 2-[3-[(2-hydroxyphenyl)methylideneamino]propyliminomethyl]phenol Chemical compound OC1=CC=CC=C1C=NCCCN=CC1=CC=CC=C1O KLDZYURQCUYZBL-UHFFFAOYSA-N 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 201000001098 delayed sleep phase syndrome Diseases 0.000 description 1
- 208000033921 delayed sleep phase type circadian rhythm sleep disease Diseases 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 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
- G06Q30/0243—Comparative campaigns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
Definitions
- Embodiments of the present invention relate to the field of advertising, and more particularly, to a method and apparatus for determining an advertisement value.
- advertising is an important means of profit for media, content distribution platforms, search engines and other applications.
- the advertising application platform uses its communication channels to aggregate advertisements from advertisers and present them to users to obtain profit from advertisers. When it is usually shown to users, ads that are ranked first or important are often ads that the advertising application platform can profit from. However, how can you judge who can bring more profit to the advertising application platform from the vast advertisements?
- the advertiser first gives a first metric parameter of a certain value for the advertisement that needs to be displayed, and multiplies the first metric of the determined value by CTR (click Rate), thereby obtaining the advertisement value corresponding to the advertisement, so that the advertisement with the larger advertisement value is ranked ahead, or the advertisement with the larger advertisement value is displayed to the user with higher priority.
- the first metric parameter is CPC, CPA or CPM, where: CPM (Cost per miller) represents the unit display cost, that is, the cost per thousand impressions, CPC (Cost per click) represents the unit click cost, CPA (Cost per Action) indicates the unit action cost.
- This method requires the advertiser to give a first metric value of a certain value, however the value of this first metric in the real application cannot be accurately calculated because the base metric is given by the advertiser. Value does not accurately calculate the actual value of the ad.
- the prior art provides another method of deciding how much money to allocate to the advertisement application platform based on the actual income obtained by the advertiser in the advertisement display, but such post-payment The mode leads to the inability to calculate the value of the advertisement in advance, and there is no certain advertisement value.
- the advertisement application platform cannot determine the reasonable advertisement order when the advertisement is displayed, so that the advertisement application platform cannot be maximized by the reasonable advertisement ranking.
- the embodiment of the invention provides a method for determining an advertisement value, which is used for improving the accuracy of the calculation of the advertisement value.
- a method for determining an advertisement value including:
- the advertisement information includes: an advertisement ID and operation information of the user on the advertisement;
- the advertisement value of the advertisement is calculated.
- the determining an advertisement value calculation strategy according to the advertisement value element includes: :
- the combining the two or more advertising value elements to obtain the advertising value calculation includes combining the two or more advertisement value elements in a multiplicative manner to form a product formula for calculating an advertisement value, the product formula being the advertisement value calculation strategy.
- the method further includes:
- the determining the advertisement value calculation strategy according to the advertisement value element comprises:
- the advertisement value calculation strategy is determined according to the modified or transformed advertisement value element.
- the method further includes: receiving user information, where the user information includes a user ID, a user age, a user gender, or user occupation information;
- the advertisement value element value and the advertisement value calculation strategy are used as reference factors, and calculating the advertisement value of the advertisement includes:
- the user information is used as another reference factor, and is calculated together with the advertisement value element value and the advertisement value calculation strategy to obtain a personalized advertisement value for the user.
- the fifth possible implementation of the first aspect when the determined advertisement value calculation strategy is two or more, after the determining the advertisement value calculation strategy according to the advertisement value element, or after determining the advertisement value calculation strategy according to the advertisement application platform, the method also includes:
- the advertising value element value and the advertisement value calculation strategy are used as reference factors, and the advertising value of the advertisement is calculated to include:
- the advertisement value element value and the optimal advertisement value calculation strategy are used as reference factors, and the advertisement value of the advertisement is calculated.
- the sixth possible implementation of the first aspect In the mode, after the determined advertisement value calculation strategy is two or more, after determining the advertisement value calculation strategy according to the advertisement value element, or after determining the advertisement value calculation strategy according to the advertisement application platform, The method further includes:
- the advertising value element value and the advertisement value calculation strategy are used as reference factors, and the advertising value of the advertisement is calculated to include:
- the advertisement value element value and the comprehensive advertisement value calculation strategy are used as reference factors, and the advertisement value of the advertisement is calculated.
- the determining an advertisement value element according to the advertisement application platform includes: determining an advertisement value element supported by the advertisement application platform as the advertisement value element.
- the determining an advertisement value calculation strategy according to the advertisement application platform includes: determining an advertisement value calculation strategy supported or pre-stored by the advertisement application platform as the advertisement value calculation strategy.
- the method further includes:
- the advertisement value element value and the advertisement value calculation strategy are used as reference factors, and the advertisement value of the advertisement is calculated to include:
- the advertisement value of the advertisement is calculated.
- the advertisement value element includes: a payment amount (PV) of the user browsing the advertisement, a probability of the user clicking the advertisement (CTR), a value of the user clicking the advertisement (PCPC), and a user payment rate (PR), and the user determines the paid amount.
- PV payment amount
- CTR probability of the user clicking the advertisement
- PCPC value of the user clicking the advertisement
- PR user payment rate
- PPP payment amount
- DPR user post-download rate
- the eleventh possible the predicting the value of the advertisement value element, and obtaining the value value of the advertisement value includes:
- the value of the advertisement value element is predicted according to a historical data statistical method or a classification or regression method in machine learning to obtain an advertisement value element value.
- an advertisement value determining apparatus including:
- a receiving module configured to receive advertisement information, where the advertisement information includes: an advertisement ID and operation information of the user on the advertisement;
- An advertisement value calculation policy determining module configured to determine an advertisement value element according to the advertisement application platform, and determine an advertisement value calculation strategy according to the advertisement value element, wherein the advertisement value element is an element that affects an advertisement value; or, The advertisement application platform determines an advertisement value calculation strategy, and the advertisement value calculation strategy is represented by the advertisement value element;
- a prediction module configured to predict a value of the advertisement value element according to the advertisement information, to obtain an advertisement value element value
- the advertisement value calculation module is configured to calculate the advertisement value of the advertisement by using the advertisement value element value and the advertisement value calculation strategy as reference factors.
- the advertisement value calculation policy determining module determines that the advertisement value element is two or more
- the advertisement value calculation policy determining module Specifically, the two or more advertisement value elements are combined to obtain the advertisement value calculation strategy.
- the advertisement value calculation module determines that the advertisement value element is two or more
- the advertisement value calculation strategy determining module is specifically configured to: use the two or more advertisement values
- the elements are combined in a multiplicative manner to form a product formula for calculating an advertisement value, which is the advertisement value calculation strategy.
- the apparatus further includes an adjustment module For modifying or transforming the advertising value element to obtain a modified or transformed advertising value element;
- the advertisement value calculation strategy determining module is configured to determine an advertisement value calculation strategy according to the modified or transformed advertisement value element.
- the receiving module is further configured to receive user information, where the user information includes a user ID, a user age, a user gender, or user occupation information;
- the advertisement value calculation module is configured to calculate the user information as a further reference factor, together with the advertisement value element value and the advertisement value calculation strategy, to obtain a personalized advertisement value for the user.
- the advertisement value calculation strategy determining module is further configured to: from the two or more advertising values Select the optimal advertising value calculation strategy in the calculation strategy;
- the advertisement value calculation module is configured to calculate the advertisement value of the advertisement by using the advertisement value element value and the optimal advertisement value calculation strategy as reference factors.
- the advertisement value calculation strategy determining module is further configured to: use the two or more advertisement values The calculation strategy is weighted to obtain a comprehensive advertising value calculation strategy;
- the advertisement value calculation module is configured to calculate the advertisement value of the advertisement by using the advertisement value element value and the comprehensive advertisement value calculation strategy as reference factors.
- the advertisement value calculation policy determining module is specifically configured to: determine that the advertisement value element supported by the advertisement application platform is the advertisement value element.
- the advertisement value calculation policy determining module is specifically configured to: determine an advertisement value calculation strategy supported or pre-stored by the advertisement application platform as the advertisement value calculation strategy.
- the adjustment module is further configured to modify the value of the advertisement value element to obtain a corrected value of the advertisement value element;
- the advertisement value calculation module is configured to use the modified advertisement value element value and the The advertisement value calculation strategy is used as a reference factor to calculate the advertisement value of the advertisement.
- the advertisement value element includes: a payment amount (PV) of the user browsing the advertisement, a probability of the user clicking the advertisement (CTR), a value of the user clicking the advertisement (PCPC), and a user payment rate (PR), and the user determines the paid amount.
- PV payment amount
- CTR probability of the user clicking the advertisement
- PCPC value of the user clicking the advertisement
- PR user payment rate
- PPP payment amount
- DPR user post-download rate
- the prediction module is specifically configured to predict a value of the advertisement value element according to a historical data statistical method or a classification or regression method in machine learning, to obtain an advertisement value element value.
- the advertisement value element is predicted according to the advertisement information (for example, the operation information of the user on the advertisement, including operation information such as browsing, clicking, downloading, etc.) (for example, the amount of payment (pV) of the user browsing the advertisement, and the user clicks on the advertisement.
- Probability CTR
- the value of the user clicked on the advertisement pCPC, predicted cost per click
- PR Pay Ratio
- the user determines the paid amount (pPP, predicted per pay) or the user's post-download rate
- the value of (dPR), etc. obtains the value of the advertising value element, and uses the value of the advertising value element and the calculation strategy of the advertising value as a reference factor to calculate the advertising value.
- the value of the advertising value element in the embodiment of the present invention is obtained by prediction, rather than being given by experience or simply not considered, so that the method of the embodiment of the present invention can be calculated in any payment mode of the current advertising application platform. More accurate advertising value.
- FIG. 1 is a schematic diagram of the basic structure of an advertisement application platform.
- FIG. 2 is a schematic diagram of a running network of an embodiment of the present invention.
- FIG. 3 is a flowchart of a method for determining an advertisement value according to an embodiment of the present invention.
- FIG. 4 is a flow chart of a method for determining an advertisement value according to another embodiment of the present invention.
- FIG. 5 is a flowchart of a method for determining an advertisement value according to still another embodiment of the present invention.
- FIG. 6 is a block diagram of an advertisement value determining apparatus according to an embodiment of the present invention.
- FIG. 7 is a block diagram of an advertisement value determining apparatus according to another embodiment of the present invention.
- FIG. 8 is a block diagram of an advertisement value determining apparatus according to still another embodiment of the present invention.
- the advertising application platform is a platform or intermediary that connects application developers and advertisers.
- the developer provides the app
- the advertiser provides the ad
- the ad app platform provides the SDK for the phone system.
- the SDK Software Development Kit
- the developer downloads the SDK and then uses the tools in the SDK to embed the advertisement in the application. Developers then upload these apps to the mobile Internet via other channels.
- the advertiser pays to the advertisement application platform according to the corresponding billing method.
- GOOGLE distributed the advertisements of many advertisers to the small and medium-sized websites where ADSENSE advertisements were placed through the ADSENSE advertising platform.
- This advertising profit model is characterized in that the user clicks on the advertisement, the advertiser does not pay the advertising platform, but when the user actually consumes the advertising product, the actual profit generated by the advertiser is shared by the advertiser and the advertising platform.
- this method is widely used in the promotion business of post-paid App in the application market, and is the most important profit model in the application market.
- the embodiment of the invention provides a method for determining the value of an advertisement, so that the advertisement application platform can accurately identify the advertisement value of different advertisements at the front end, thereby increasing the pushing power of the advertisements with greater value among the advertisements.
- its value category usually refers to the possible benefits of the advertisement to the advertiser or the advertising application platform; there are many ways to push the promotion here, such as the recommendation wall method (such as in the application market). Sort), start screen advertisement push (such as the launch of the App application full screen pop-up), insert screen ads, and so on.
- the advertisement application platform shown in FIG. 1 and the advertiser, developer, and user may specifically run in the network as shown in FIG. 2.
- FIG. 2 it is a schematic diagram of a network according to an embodiment of the present invention.
- the function performed by the management server 81 in FIG. 2 corresponds to the advertisement application platform in FIG. 1, that is, the specific function of the advertisement application platform is implemented by the management server 81;
- the user terminals 51-55 in FIG. 2 correspond to the image in FIG.
- the advertiser, the developer, and the user, wherein the advertiser and the developer may also be other servers connected to the management server 81, and are not limited herein.
- GSM Global System for Mobile Communications
- GPRS General Packet Radio Service
- CDMA Code Division Multiple Access
- CDMA2000 Code Division Multiple Access
- WCDMA Wideband Code Division Multiple Access
- LTE Long Term Evolution
- WiMAX World Interoperability for Microwave Access
- the base station may be a base station (Base Transceiver Station, BTS) in a GSM system, a GPRS system or a CDMA system, or may be a base station (NodeB) in a CDMA2000 system or a WCDMA system, or may be an evolved type in an LTE system.
- BTS Base Transceiver Station
- NodeB base station
- the base station (Evolved NodeB, eNB) may be an access service network base station (ASN BS) of the access service network in the WiMAX network.
- ASN BS access service network base station
- the user terminal may be a device that provides voice and/or data connectivity to the user, a handheld device with wireless connectivity, or other processing device connected to the wireless modem.
- the user terminal can communicate with one or more core networks via a Radio Access Network (RAN), which can be a mobile terminal, such as a mobile phone (or "cellular" phone) and a computer with a mobile terminal.
- RAN Radio Access Network
- RAN Radio Access Network
- PCS Personal Communication Service
- SIP Session Initiation Protocol
- WLL Wireless Local Loop
- PDA Personal Digital Assistants
- the terminal may also be called a system, a subscriber unit, a subscriber station, a mobile station, a remote station, or a remote station. Access Point, Remote Terminal, Access Terminal, User Terminal, User Agent, User Device, or User Equipment .
- FIG. 3 is a schematic flowchart of a method for determining an advertisement value according to an embodiment of the present invention.
- the execution body of the method may be the advertisement application platform in FIG. 1 .
- S101 Receive advertisement information, where the advertisement information includes: an advertisement ID and operation information of the user on the advertisement;
- the advertisement information of the embodiment of the present invention includes, but is not limited to, an advertisement ID and operation information of the user on the advertisement.
- the advertisement information may further include information such as an advertisement category, and is not exhaustive herein.
- the operation information of the user for the advertisement according to the embodiment of the present invention includes: operation information such as browsing, clicking, and downloading, and the operation information such as browsing, clicking, and downloading may include the number of operations, operations, and operations of browsing, clicking, and downloading. Time and other related information.
- the ads described in this article mainly involve online advertising, but do not rule out the value of advertising through this method to the rest The type of advertising presented by the media.
- S103 Determine an advertisement value element according to an advertisement application platform, and determine an advertisement value calculation strategy according to the advertisement value element, where the advertisement value element is an element that affects an advertisement value;
- advertisement value elements such as the amount of payment (pV) of the user browsing the advertisement, the probability of the user clicking the advertisement (CTR), and the value of the user clicking the advertisement (pCPC, predicted cost per click).
- CTR probability of the user clicking the advertisement
- pCPC predicted cost per click
- PR Pay Rate
- pPP predicted payment Post-paid amount
- dPR user download rate
- the advertising value calculation strategy is represented by the advertising value element.
- different advertising value elements correspond to different prediction models.
- the so-called prediction model is used to predict the value elements of the advertisement.
- CTR download rate
- LR can be selected.
- Logistic Regression model
- predictive advertising value element pCPC need to use the regression model, specifically RF (Random Forest) or GBRT (Gradient Boosting Regression Tree) model.
- Predicting the advertising value element by the predictive model can be understood as preparatory work performed offline.
- not all of the advertising value elements are predicted by their corresponding prediction models, and some advertising value elements can be directly calculated by statistical methods.
- each advertisement value element may be combined according to an application requirement to obtain an advertisement value calculation strategy that meets the application requirement, wherein different advertisement value elements determine different properties in the advertisement value calculation strategy, for example, Monotonic, concave and convex, etc.
- the advertising value calculation strategy that combines the respective advertising value elements according to the application requirements to meet the application requirements may be: combining the two or more advertising value elements by multiplication.
- the product is the advertising value calculation strategy we describe, that is, the path method for calculating the value of the advertisement.
- the advertisement value element directly constitutes its corresponding advertisement value calculation strategy, that is, the value of the advertisement value element can be considered directly equal to the advertisement value, but the advertisement value element can be further Correction or transformation, so the advertising value calculation strategy is determined according to the modified or transformed advertising value element, which will be expanded later, not repeated here), directly predict or calculate pV; pCPC*CTR, respectively predict or calculate pCPC and CTR ;pPP*PR, respectively predict or calculate pPP and PR; pPP*dPR*CTR, respectively predict or calculate pPP, dPR and CTR; or may be a combination of any two or more of the above advertising value calculation strategies (such as weighting) average).
- pV only one of the advertising value elements supported by the advertising application platform, or the implementation of the present invention
- the advertisement value element directly constitutes its corresponding advertisement value calculation strategy, that is, the value of the advertisement value element can be considered directly equal to the advertisement value, but the advertisement value element can be further Correction or transformation, so the advertising value calculation strategy is determined according
- the value of the advertisement value element is predicted according to the advertisement information, and the prediction method may be based on a historical data statistical method or a classification or regression method in machine learning.
- N the number of advertisement value elements determined according to the advertisement application platform
- predicting the value of the advertisement value element according to the advertisement information should be understood as: predicting N according to the advertisement information respectively.
- N is a positive integer greater than or equal to one.
- the advertisement value element is one, the value of the one advertisement value element is predicted according to the advertisement information; when the advertisement value element is multiple, the values of the plurality of advertisement value elements are predicted according to the advertisement information. It is obtained that a plurality of them are greater than or equal to two.
- the specific advertising value element value may be substituted into the advertising value calculation strategy, and the advertising value is obtained through calculation.
- an advertisement value element is determined according to an advertisement application platform, and a value of the advertisement value element is predicted according to the advertisement information, and an advertisement value element value is obtained, thereby the value value of the advertisement value element and the
- the advertisement value calculation strategy is used as a reference factor to calculate the advertisement value of the advertisement, thereby accurately determining the advertisement value at the front end, and bringing about the maximum benefit of the advertisement application platform.
- the optional implementation manner is: before the determining the advertisement value calculation strategy according to the advertisement value element, the method further includes: S104: correcting the advertisement value element or Transform to get the corrected or transformed advertising value element.
- the step S103: determining the advertisement value calculation strategy according to the advertisement value element specifically includes: determining an advertisement value calculation strategy according to the modified or transformed advertisement value element.
- the modification and transformation described herein may be performed according to the actual situation of the advertisement application platform. Specifically, the transformation here may be to transform the advertisement value element to make it increase or decrease. To meet the actual needs of the advertising application platform, the correction here may be to adaptively compensate the advertising value element to balance the deviation that may be caused by the advertising value element.
- step S107 before the value of the advertisement value element is predicted based on the advertisement information to obtain an advertisement value element value, an optional implementation manner is:
- the user information includes a user ID, a user age, a user gender, or user occupation information
- the user information herein includes but is not limited to: user ID, user age, user gender or user occupation information; and the user ID, user age, user gender or user occupation information is optional information;
- the user information may further include information indicating the user's interest, the user's social circle information, or the context information of the user browsing the advertisement.
- the advertisement value element value and the advertisement value calculation strategy are used as reference factors, and calculating the advertisement value of the advertisement includes:
- the user information is used as another reference factor, and is calculated together with the advertisement value element value and the advertisement value calculation strategy to obtain a personalized advertisement value for the user.
- the personalized advertising value for the user is obtained, that is, we believe that the same advertisement has different advertising value for different users, for example, for young males, the game Class advertisements are more valuable than shopping ads, and conversely, for young women, shopping ads are more valuable than game ads, and different individuals have different differences, based on user information.
- the advertising application platform can adopt different advertising presentation strategies for different users according to the personalized advertising value, thereby making the profit of the advertising application platform maximized.
- an optional implementation is:
- step S109 the advertisement value element value and the advertisement value calculation strategy are used as reference factors, and the advertisement value of the advertisement is calculated to include:
- the advertisement value element value and the optimal advertisement value calculation strategy are used as reference factors, and the advertisement value of the advertisement is calculated.
- the optimal advertisement value calculation strategy here is result-oriented, that is, the advertisement value is calculated by the advertisement value calculation strategy, so that different advertisements are sorted according to the advertisement value and presented to the user, and then For the most benefit from the application advertising platform, the advertising value calculation strategy is considered to be the optimal advertising value calculation strategy. It is worth noting that when we say that different advertisements are sorted according to the value of advertisements, it often involves the calculation of multiple advertisements and the value of the multiple advertisements, and finally sorting is also the sorting of the advertisement values corresponding to the plurality of advertisements. Multiples can be greater than or equal to two.
- the optimal advertising value calculation strategy may be different in different scenarios.
- the optimal advertising value calculation strategy includes: AUC (area under the curve) and MAE (mean absolute). Error) and other evaluation indicators to evaluate different computing strategies and their prediction models corresponding to the advertising value elements; you can also measure different advertising value calculation strategies based on online income.
- the advertising value element value and the advertisement value calculation strategy are used as reference factors, and the advertising value of the advertisement is calculated to include:
- the advertisement value element value and the comprehensive advertisement value calculation strategy are used as reference factors, and the advertisement value of the advertisement is calculated.
- the comprehensive advertising value calculation strategy described here is any two or more independent advertising values.
- Combination of calculation strategies, in this implementation manner, the combination manner may be weighting.
- the present invention does not limit the combination manner, and any combination method that can achieve the object and effect of the present invention should be within the protection scope of the present invention. I will not repeat them here.
- the use of comprehensive advertising value calculation strategy to calculate the value of advertising can be carried out through integrated learning.
- the so-called integrated learning method refers to: using a series of predictive models for learning, and using some rules to integrate the learning results. A machine learning method that achieves better learning outcomes than a single predictive model.
- the independent advertisement value calculation strategy refers to a complete strategy capable of independently completing the calculation of the advertisement value, such as pV; pCPC*CTR; pPP*PR; pPP*dPR*CTR, etc. described above.
- step S103 determining an advertisement value element according to the advertisement application platform includes: determining an advertisement value element supported by the advertisement application platform as a The advertising value element.
- determining an advertisement value calculation strategy according to the advertisement application platform includes: determining an advertisement value calculation strategy supported or pre-stored by the advertisement application platform as the advertisement value calculation strategy.
- the method further includes S108: correcting the value of the advertisement value element to obtain a corrected value of the advertisement value element;
- step S109 the advertisement value element value and the advertisement value calculation strategy are used as reference factors, and the advertisement value of the advertisement is calculated to include:
- the advertisement value of the advertisement is calculated.
- the corrections and transformations described herein can be made according to the actual situation of the advertising application platform.
- the reason for the correction or transformation is that in the real application scenario, not all predicted value values of the advertising value can be directly used, and we will modify and change the value of the advertising value element that cannot be directly used.
- the sample size is relatively small, which is easy to cause deviations, and the prediction results obtained have no practical significance. According to the value of the advertising value element of these niche ads, if used directly, the prediction of the value of the ad will be inaccurate.
- the value of the value of the ad value needs to be adjusted or changed: for example, when the volume of some niche ads is displayed and When the download volume is small but the download rate is very high, in order to avoid the bias caused by the small sample, you can replace the impression of the niche advertisement with the threshold of the display volume of all advertisements.
- FIG. 6 is a block diagram of an apparatus for determining an advertising value in accordance with one embodiment of the present invention.
- the apparatus 600 shown in FIG. 6 includes a receiving module 601, an advertisement value calculation policy determining module 603, a prediction module 607, and an advertisement value calculating module 609.
- the receiving module 601 is configured to receive advertisement information, where the advertisement information includes: an advertisement ID and operation information of the user on the advertisement;
- the advertisement information of the embodiment of the present invention includes, but is not limited to, an advertisement ID and operation information of the user on the advertisement.
- the advertisement information may further include information such as an advertisement category, and is not exhaustive herein.
- the operation information of the user for the advertisement according to the embodiment of the present invention includes: operation information such as browsing, clicking, and downloading, and the operation information such as browsing, clicking, and downloading may include the number of operations, operations, and operations of browsing, clicking, and downloading. Time and other related information.
- the advertisements described herein mainly relate to online advertisements, but the types of advertisements presented by the remaining media after determining the value of advertisements by the method are not excluded.
- the advertisement value calculation policy determining module 603 is configured to determine an advertisement value element according to the advertisement application platform, and determine an advertisement value calculation strategy according to the advertisement value element, where the advertisement value element is an element that affects the advertisement value; or, An advertisement value calculation strategy is determined according to an advertisement application platform, the advertisement value calculation strategy being represented by the advertisement value element.
- advertisement value elements such as the amount of payment (pV) of the user browsing the advertisement, the probability of the user clicking the advertisement (CTR), and the value of the user clicking the advertisement (pCPC, predicted cost per click).
- CTR probability of the user clicking the advertisement
- pCPC predicted cost per click
- PR Pay Rate
- pPP predicted per pay
- dPR user download rate
- the advertising value calculation strategy is represented by the advertising value element.
- different advertising value elements correspond to different prediction models.
- the so-called prediction model is used to predict the value elements of the advertisement.
- CTR download rate
- LR can be selected.
- Logistic Regression model
- predictive advertising value element pCPC need to use the regression model, specifically RF (Random Forest) or GBRT (Gradient Boosting Regression Tree) model.
- Predicting the advertising value element by the predictive model can be understood as preparatory work performed offline.
- not all of the advertising value elements are predicted by their corresponding prediction models, and some advertising value elements can be directly calculated by statistical methods.
- each advertisement value element may be combined according to an application requirement to obtain an advertisement value calculation strategy that meets the application requirement, wherein different advertisement value elements determine different properties in the advertisement value calculation strategy, for example, Monotonic, concave and convex, etc.
- the advertising value calculation strategy that combines the respective advertising value elements according to the application requirements to meet the application requirements may be: combining the two or more advertising value elements by multiplication.
- the product is the advertising value calculation strategy we describe, that is, the path method for calculating the value of the advertisement.
- the specific advertisement value calculation strategy may be various, for example: pV (when the advertisement application platform supports only one advertisement value element, or the embodiment of the present invention selects only one of the plurality of advertisement value elements, the advertisement value element is directly
- the corresponding advertising value calculation strategy is formed, that is, the value of the advertising value element can be directly equal to the advertising value at this time, but the advertising value element can be further modified or transformed, so that the advertisement is determined according to the modified or transformed advertising value element.
- the value calculation strategy which will be expanded later, will not be described here), directly predict or calculate pV; pCPC*CTR, predict or calculate pCPC and CTR, respectively; pPP*PR, predict or calculate pPP and PR respectively; pPP*dPR*CTR , respectively predict or calculate pPP, dPR and CTR; or may also be a combination of any two or more of the above advertising value calculation strategies (such as weighted average).
- the prediction module 607 is configured to predict a value of the advertisement value element according to the advertisement information, to obtain an advertisement value element value.
- the value of the advertisement value element is predicted according to the advertisement information, and the prediction method may be based on a historical data statistical method or a classification or regression method in machine learning.
- N the number of advertisement value elements determined according to the advertisement application platform
- predicting the value of the advertisement value element according to the advertisement information should be understood as: according to the advertisement information.
- the values of each of the N ad value elements are predicted separately. Where N is a positive integer greater than or equal to one.
- N is a positive integer greater than or equal to one.
- the advertisement value element is one
- the value of the one advertisement value element is predicted according to the advertisement information
- the advertisement value element is multiple, the values of the plurality of advertisement value elements are predicted according to the advertisement information. It is obtained that a plurality of them are greater than or equal to two.
- the advertisement value calculation module 609 is configured to calculate the advertisement value of the advertisement by using the advertisement value element value and the advertisement value calculation strategy as reference factors.
- the specific advertising value element value may be substituted into the advertising value calculation strategy, and the advertising value is obtained through calculation.
- an advertisement value element is determined according to an advertisement application platform, and a value of the advertisement value element is predicted according to the advertisement information, and an advertisement value element value is obtained, thereby the value value of the advertisement value element and the
- the advertisement value calculation strategy is used as a reference factor to calculate the advertisement value of the advertisement, thereby accurately determining the advertisement value at the front end, and bringing about the maximum benefit of the advertisement application platform.
- the device 600 provided by the embodiment of the present invention further includes an adjustment module 604, configured to modify or transform the advertisement value element to obtain a modified or transformed advertisement value element;
- the advertisement value calculation strategy determining module 603 is specifically configured to determine an advertisement value calculation strategy according to the modified or transformed advertisement value element.
- the modification and transformation described herein may be performed according to the actual situation of the advertisement application platform.
- the transformation here may be to transform the advertisement value element to make it increase or decrease.
- the correction here may be to adaptively compensate the advertising value element to balance the advertising value element. deviation.
- the receiving module 601 may be further configured to receive user information, where the user information includes a user ID and a user age. , user gender or user occupation information;
- the user information herein includes but is not limited to: user ID, user age, user gender or user occupation information; and the user ID, user age, user gender or user occupation information is optional information;
- the user information may further include information indicating the user's interest, the user's social circle information, or the context information of the user browsing the advertisement.
- the advertisement value calculation policy determining module 603 is specifically configured to: calculate the user information as another reference factor, calculate together with the advertisement value element value and the advertisement value calculation strategy, and obtain the target user Personalized advertising value.
- the personalized advertising value for the user is obtained, that is, we believe that the same advertisement has different advertising value for different users, for example, for young males, the game Class advertisements are more valuable than shopping ads, and conversely, for young women, shopping ads are more valuable than game ads, and different individuals have different differences, based on user information.
- the advertising application platform can adopt different advertising presentation strategies for different users according to the personalized advertising value, thereby making the profit of the advertising application platform maximized.
- the apparatus 600 provided by the embodiment of the present invention
- the advertisement value calculation strategy determining module 603 is further configured to: from the two or two Selecting the optimal advertising value calculation strategy in the upper advertising value calculation strategy;
- the advertisement value calculation module 607 is specifically configured to calculate the advertisement value of the advertisement by using the advertisement value element value and the optimal advertisement value calculation strategy as reference factors.
- the optimal advertisement value calculation strategy here is result-oriented, that is, the advertisement value is calculated by the advertisement value calculation strategy, so that different advertisements are sorted according to the advertisement value and presented to the user, and then For the most benefit from the application advertising platform, the advertising value calculation strategy is considered to be the optimal advertising value calculation strategy. It is worth noting that when we say that different advertisements are sorted according to the value of advertisements, it often involves the calculation of multiple advertisements and the value of the multiple advertisements, and finally sorting is also the sorting of the advertisement values corresponding to the plurality of advertisements. Multiples can be greater than or equal to two.
- the optimal advertising value calculation strategy may be different in different scenarios.
- the optimal advertising value calculation strategy includes: AUC (area under the curve) and MAE (mean absolute). Error) and other evaluation indicators to evaluate different computing strategies and their prediction models corresponding to the advertising value elements; you can also measure different advertising value calculation strategies based on online income.
- the apparatus 600 provided by the embodiment of the present invention
- the advertisement value calculation strategy determining module 603 is further configured to: weight the two more than two advertisement value calculation strategies to obtain a comprehensive advertisement value calculation strategy;
- the advertisement value calculation module 609 is specifically configured to calculate the advertisement value of the advertisement by using the advertisement value element value and the comprehensive advertisement value calculation strategy as reference factors.
- the strategy is called an independent advertising value calculation strategy.
- the comprehensive advertising value calculation strategy described herein is a combination of any two or more independent advertising value calculation strategies. In this implementation manner, the combination manner may be weighting, of course, the present invention
- the combination method is not limited, and any combination method that can achieve the object and effect of the present invention should be within the scope of the present invention and will not be described herein.
- the use of comprehensive advertising value calculation strategy to calculate the value of advertising can be carried out through integrated learning.
- the so-called integrated learning method refers to: using a series of predictive models for learning, and using some rules to integrate the learning results. A machine learning method that achieves better learning outcomes than a single predictive model.
- the independent advertisement value calculation strategy refers to a complete strategy capable of independently completing the calculation of the advertisement value, such as pV; pCPC*CTR; pPP*PR; pPP*dPR*CTR, etc. described above.
- the advertisement value calculation policy determining module 603 is specifically configured to determine that the advertisement value element supported by the advertisement application platform is the advertisement value element.
- the advertisement value calculation policy determining module 603 is specifically configured to determine that the advertisement value calculation strategy supported or pre-stored by the advertisement application platform is the advertisement value calculation strategy.
- the adjustment module 604 of the device 600 is further configured to modify the value of the advertisement value element to obtain a corrected value of the advertisement value element;
- the advertisement value calculation module is configured to calculate the advertisement value of the advertisement by using the corrected advertisement value element value and the advertisement value calculation strategy as reference factors.
- the corrections and transformations described herein can be made according to the actual situation of the advertising application platform.
- the reason for the correction or transformation is that in the real application scenario, not all predicted value values of the advertising value can be directly used, and we will modify and change the value of the advertising value element that cannot be directly used.
- the sample size is relatively small. It is easy to cause deviations, and the prediction results obtained have no practical significance. According to the value of the advertising value element of these niche ads, if used directly, the prediction of the value of the ad will be inaccurate.
- the value of the value of the ad value needs to be adjusted or changed: for example, when the volume of some niche ads is displayed and When the download volume is small but the download rate is very high, in order to avoid the bias caused by the small sample, you can replace the impression of the niche advertisement with the threshold of the display volume of all advertisements.
- the apparatus 600 shown in FIG. 6 and FIG. 7 can implement the method for determining the advertisement value shown in the foregoing embodiment. To avoid repetition, details are not described herein again.
- FIG. 8 is a block diagram of an advertisement value determining apparatus 800 according to another embodiment of the present invention.
- the device 800 shown in FIG. 8 includes a processor 801, a receiver 802, a transmitter 803, and a memory 804.
- the receiver 802 is configured to receive advertisement information, where the advertisement information includes: an advertisement ID and operation information of the user on the advertisement.
- the processor 801 is configured to determine an advertisement value element according to the advertisement application platform, and configured to determine an advertisement value calculation strategy according to the advertisement value element; the advertisement value element is an element that affects an advertisement value; or, is used according to an advertisement application Determining an advertisement value calculation strategy, the advertisement value calculation strategy being represented by the advertisement value element; and for predicting a value of the advertisement value element according to the advertisement information, obtaining an advertisement value element value; and for using the advertisement
- the value element value and the advertisement value calculation strategy are used as reference factors to calculate the advertisement value of the advertisement.
- an advertisement value element is determined according to an advertisement application platform, and a value of the advertisement value element is predicted according to the advertisement information, and an advertisement value element value is obtained, thereby the value value of the advertisement value element and the
- the advertisement value calculation strategy is used as a reference factor to calculate the advertisement value of the advertisement, thereby accurately determining the advertisement value at the front end, and bringing about the maximum benefit of the advertisement application platform.
- bus system 805 which in addition to the data bus includes a power bus, a control bus, and a status signal bus.
- bus system 805 various buses are labeled as bus system 805 in FIG.
- Processor 801 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the foregoing method may be completed by an integrated logic circuit of hardware in the processor 801 or an instruction in a form of software.
- the processor 801 may be a general-purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a Field Programmable Gate Array (FPGA), or Other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.
- DSP digital signal processor
- ASIC application specific integrated circuit
- FPGA Field Programmable Gate Array
- the methods, steps, and logical block diagrams disclosed in the embodiments of the present invention may be implemented or carried out.
- the general purpose processor may be a microprocessor or the processor or any conventional processor or the like.
- the steps of the method disclosed in the embodiments of the present invention may be directly implemented by the hardware decoding processor, or may be performed by a combination of hardware and software modules in the decoding processor.
- the software module can be located in a conventional storage medium such as random access memory, flash memory, read only memory, programmable read only memory or electrically erasable programmable memory, registers, and the like.
- the storage medium is located in memory 804, and processor 801 reads the information in memory 804 and, in conjunction with its hardware, performs the steps of the above method.
- the memory 804 in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memory.
- the non-volatile memory may be a read-only memory (ROM), a programmable read only memory (PROM), an erasable programmable read only memory (Erasable PROM, EPROM), or an electric Erase programmable read only memory (EEPROM) or flash memory.
- Volatile memory It is a random access memory (RAM), which is used as an external cache.
- RAM random access memory
- RAM random access memory
- SRAM static random access memory
- DRAM dynamic random access memory
- Synchronous DRAM synchronous dynamic random access memory
- Memory 804 of the systems and methods described herein is intended to comprise, without being limited to, these and any other suitable types of memory.
- the embodiments described herein can be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof.
- the processing unit can be implemented in one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processing (DSP), Digital Signal Processing Equipment (DSP Device, DSPD), programmable Programmable Logic Device (PLD), Field-Programmable Gate Array (FPGA), general purpose processor, controller, microcontroller, microprocessor, other for performing the functions described herein In an electronic unit or a combination thereof.
- ASICs Application Specific Integrated Circuits
- DSP Digital Signal Processing
- DSP Device Digital Signal Processing Equipment
- PLD programmable Programmable Logic Device
- FPGA Field-Programmable Gate Array
- a code segment can represent a procedure, a function, a subprogram, a program, a routine, a subroutine, a module, a software group, a class, or any combination of instructions, data structures, or program statements.
- a code segment can be combined into another code segment or hardware circuit by transmitting and/or receiving information, data, arguments, parameters or memory contents. Any suitable means including memory sharing, messaging, token passing, network transmission, etc. can be used to pass, forward or send information, arguments, parameters, Data, etc.
- the techniques described herein can be implemented by modules (eg, procedures, functions, and so on) that perform the functions described herein.
- the software code can be stored in a memory unit and executed by the processor.
- the memory unit can be implemented in the processor or external to the processor, in the latter case the memory unit can be communicatively coupled to the processor via various means known in the art.
- the advertisement value element is determined according to the advertisement application platform, and the value of the advertisement value element is predicted according to the advertisement information, and the value of the advertisement value element is obtained, thereby the value of the advertisement value element and
- the advertisement value calculation strategy is used as a reference factor to calculate the advertisement value of the advertisement, thereby accurately determining the advertisement value at the front end, and bringing about the maximum benefit of the advertisement application platform.
- the processor 801 determines that the advertisement value element is two or more, the processor 801 is specifically configured to combine the two or more advertisement value elements.
- the advertising value calculation strategy is obtained.
- the processor 801 is specifically configured to: modify or transform the advertisement value element to obtain a modified or transformed advertisement value element; and determine, according to the modified or transformed advertisement value element. Advertising value calculation strategy.
- the receiver 802 is further configured to receive user information, where the user information includes a user ID, a user age, a user gender, or user occupation information.
- the processor 801 is specifically configured to use the user information as Another reference factor, calculated along with the value of the advertising value element and the advertising value calculation strategy, results in a personalized advertising value for the user.
- the processor 801 is specifically configured to: select an optimal one from the two or more advertisement value calculation strategies. Advertising value calculation strategy; and further for using the value of the advertising value element and the optimal wide The value calculation strategy is used as a reference factor to calculate the advertising value of the advertisement.
- the processor 801 is specifically configured to: weight the two more than two advertisement value calculation strategies to obtain The integrated advertisement value calculation strategy is further used to calculate the advertisement value of the advertisement by using the advertisement value element value and the comprehensive advertisement value calculation strategy as reference factors.
- the processor 801 is specifically configured to: modify the value of the advertisement value element to obtain a modified value of the advertisement value element; and further convert the value of the modified advertisement value element and the The advertisement value calculation strategy is used as a reference factor to calculate the advertisement value of the advertisement.
- the processor 801 is specifically configured to predict a value of the advertisement value element according to a historical data statistical method or a classification or regression method in machine learning to obtain an advertisement value element value.
- the device 800 shown in FIG. 8 is an advertisement value determining device.
- the apparatus 800 shown in FIG. 8 can implement the advertisement value determining method shown in the foregoing embodiment. To avoid repetition, details are not described herein again.
- the disclosed systems, devices, and methods may be implemented in other manners.
- the device embodiments described above are merely illustrative.
- the division of the unit is only a logical function division.
- there may be another division manner for example, multiple units or components may be combined or Can be integrated into another system, or some features can be ignored or not executed.
- the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be in an electrical, mechanical or other form.
- the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
- each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
- the functions may be stored in a computer readable storage medium if implemented in the form of a software functional unit and sold or used as a standalone product.
- the technical solution of the present invention which is essential or contributes to the prior art, or a part of the technical solution, may be embodied in the form of a software product, which is stored in a storage medium, including
- the instructions are used to cause a computer device (which may be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention.
- the foregoing storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
一种广告价值确定方法,包括:接收广告信息,所述广告信息包括:广告ID以及用户对广告的操作信息(101);根据广告应用平台确定广告价值元素,所述广告价值元素是对广告价值产生影响的元素(103);根据所述广告价值元素确定广告价值计算策略(105);根据所述广告信息预测所述广告价值元素的值,得到广告价值元素值(107);将所述广告价值元素值和所述广告价值计算策略作为参考因子,计算得到所述广告的广告价值(109)。通过对广告价值元素值的预测实现更高的广告价值确定的准确度,从而为广告应用平台的最大化收益带来可能。
Description
本申请要求于2015年7月9日提交的申请号为PCT/CN2015/083666的国际专利申请,发明名称为“一种广告价值确定方法及装置”的国际专利申请的优先权,其全部内容通过引用结合在本申请中。
本发明实施例涉及广告领域,更具体地,涉及一种广告价值确定的方法及装置。
众所周知,广告是媒体、内容分发平台、搜索引擎等应用的重要盈利手段,广告应用平台利用其传播渠道,聚合来自广告主的广告,并将这些广告展示给用户,从而从广告主处获取盈利。通常展示给用户的时候,排序靠前或者说重要级优先的广告往往是广告应用平台能够从中获利更大的广告。然而,如何从浩如繁星的广告中判断谁能为广告应用平台带来更大的获利?现有技术提供了几种方法,一种方法是:由广告主为其需要展示的广告给定一个确定值的第一度量参数,并由该确定值的第一度量乘以CTR(点击率),由此得出该广告对应的广告价值,从而将广告价值越大的广告排在越前,或者给广告价值越大的广告更高的优先级展示给用户。此处第一度量参数为CPC、CPA或CPM,其中:CPM(Cost per miller)表示单位展示成本,即每千次的展示成本,CPC(Cost per click)表示单位点击成本,CPA(Cost per Action)表示单位动作成本。这种方法需要由广告主给定一个确定值的第一度量值,然而这个第一度量在现实应用中的值无法准确计算得到,因为基由广告主给定的这个第一度量的
值并不能准确计算广告的实际价值。为了解决无法准确计算广告的实际价值的问题,现有技术提供了另一种方法:即基于在广告展示中广告主实际获得的收益来决定给广告应用平台分多少钱,然而这样的后置付费模式导致先期无法计算广告价值,没有确定的广告价值,广告应用平台在进行广告展示时便无从决定合理的广告排序,从而无法由合理的广告排序带给广告应用平台最大化收益。
发明内容
本发明实施例提供一种广告价值确定方法,用于提高广告价值计算的准确度。
第一方面,提供了一种广告价值确定方法,包括:
接收广告信息,所述广告信息包括:广告ID以及用户对广告的操作信息;
根据广告应用平台确定广告价值元素,并根据所述广告价值元素确定广告价值计算策略,所述广告价值元素是对广告价值产生影响的元素;或,
根据广告应用平台确定广告价值计算策略,所述广告价值计算策略由所述广告价值元素表示;根据所述广告信息预测所述广告价值元素的值,得到广告价值元素值;
将所述广告价值元素值和所述广告价值计算策略作为参考因子,计算得到所述广告的广告价值。
结合第一方面,在第一方面的第一种可能的实现方式中,当所述确定的广告价值元素为两个或两个以上时,所述根据所述广告价值元素确定广告价值计算策略包括:
将所述两个或两个以上的广告价值元素进行组合得到所述广告价值计算策略。
结合第一方面的第一种可能的实现方式,在第一方面的第二种可能的实现方式中,所述将所述两个或两个以上的广告价值元素进行组合得到所述广告价值计算策略包括:将所述两个或两个以上的广告价值元素以相乘的方式进行组合构成用于计算广告价值的乘积式,所述乘积式为所述广告价值计算策略。
结合第一方面、第一方面的第一种可能的实现方式或第一方面的第二种可能的实现方式,在第一方面的第三种可能的实现方式中,在所述根据所述广告价值元素确定广告价值计算策略之前,所述方法还包括:
对所述广告价值元素进行修正或变换,得到修正或变换后的广告价值元素;
对应地,所述根据所述广告价值元素确定广告价值计算策略包括:
根据所述修正或变换后的广告价值元素确定广告价值计算策略。
结合第一方面、第一方面的第一种可能的实现方式至第一方面的第三种可能的实现方式中的任意一种可能的实现方式,在第一方面的第四种可能的实现方式中,在所述根据所述广告信息预测所述广告价值元素的值,得到广告价值元素值之前还包括:接收用户信息,所述用户信息包括用户ID、用户年龄、用户性别或用户职业信息;
对应地,将所述广告价值元素值和所述广告价值计算策略作为参考因子,计算所述广告的广告价值包括:
将所述用户信息作为另一个参考因子,与所述广告价值元素值和所述广告价值计算策略一起计算,得到针对所述用户的个性化广告价值。
结合第一方面,或第一方面的第一种可能的实现方式至第一方面的第四种可能的实现方式中的任意一种可能的实现方式,在第一方面的第五种可能的实现方式中,当所述确定的广告价值计算策略为两个或两个以上时,所述根据所述广告价值元素确定广告价值计算策略之后,或,根据广告应用平台确定广告价值计算策略之后,所述方法还包括:
从所述两个或两个以上广告价值计算策略中选择最优的广告价值计算策略;
对应地,所述将所述广告价值元素值和所述广告价值计算策略作为参考因子,计算得到所述广告的广告价值包括:
将所述广告价值元素值和所述最优的广告价值计算策略作为参考因子,计算得到所述广告的广告价值。
结合第一方面,或第一方面的第一种可能的实现方式至第一方面的第四种可能的实现方式中的任意一种可能的实现方式,在第一方面的第六种可能的实现方式中,,当所述确定的广告价值计算策略为两个或两个以上时,所述根据所述广告价值元素确定广告价值计算策略之后,或,根据广告应用平台确定广告价值计算策略之后,所述方法还包括:
将所述两个多两个以上广告价值计算策略进行加权,得到综合广告价值计算策略;
对应地,所述将所述广告价值元素值和所述广告价值计算策略作为参考因子,计算得到所述广告的广告价值包括:
将所述广告价值元素值和所述综合广告价值计算策略作为参考因子,计算得到所述广告的广告价值。
结合第一方面,或第一方面的第一种可能的实现方式至第一方面的第六种可能的实现方式中的任意一种可能的实现方式,在第一方面的第七种可能的实现方式中,所述根据广告应用平台确定广告价值元素包括:确定所述广告应用平台支持的广告价值元素为所述广告价值元素。
结合第一方面,或第一方面的第一种可能的实现方式至第一方面的第七种可能的实现方式中的任意一种可能的实现方式,在第一方面的第八种可能的实现方式中,所述根据广告应用平台确定广告价值计算策略包括:确定所述广告应用平台支持的或预存的广告价值计算策略为所述广告价值计算策略。
结合第一方面,或第一方面的第一种可能的实现方式至第一方面的第八种可能的实现方式中的任意一种可能的实现方式,在第一方面的第九种可能的实现方式中,在所述根据所述广告信息预测所述广告价值元素的值,得到广告价值元素值之后,所述方法还包括:
对所述广告价值元素值进行修正,得到修正后的广告价值元素值;
对应地,将所述广告价值元素值和所述广告价值计算策略作为参考因子,计算得到所述广告的广告价值包括:
将所述修正后的广告价值元素值和所述广告价值计算策略作为参考因子,计算得到所述广告的广告价值。
结合第一方面,或第一方面的第一种可能的实现方式至第一方面的第九种可能的实现方式中的任意一种可能的实现方式,在第一方面的第十种可能的实现方式中,所述广告价值元素包括:用户浏览广告的付费量(PV)、用户点击广告的概率(CTR)、用户点击广告的价值(PCPC)、用户付费率(PR),用户确定付费后的付费量(PPP)、用户下载后付费率(DPR)。
结合第一方面,或第一方面的第一种可能的实现方式至第一方面的第十种可能的实现方式中的任意一种可能的实现方式,在第一方面的第十一种可能的实现方式中,所述预测所述广告价值元素的值,得到广告价值元素值包括:
根据历史数据统计方法或机器学习中的分类或回归方法预测所述广告价值元素的值,得到广告价值元素值。
第二方面,提供了一种广告价值确定装置,包括:
接收模块,用于接收广告信息,所述广告信息包括:广告ID以及用户对广告的操作信息;
广告价值计算策略确定模块,用于根据广告应用平台确定广告价值元素,并根据所述广告价值元素确定广告价值计算策略,所述广告价值元素是对广告价值产生影响的元素;或,用于根据广告应用平台确定广告价值计算策略,所述广告价值计算策略由所述广告价值元素表示;
预测模块,用于根据所述广告信息预测所述广告价值元素的值,得到广告价值元素值;
广告价值计算模块,用于将所述广告价值元素值和所述广告价值计算策略作为参考因子,计算得到所述广告的广告价值。
结合第二方面,在第二方面的第一种可能的实现方式中,当所述广告价值计算策略确定模块确定的广告价值元素为两个或两个以上时,所述广告价值计算策略确定模块具体用于将所述两个或两个以上的广告价值元素进行组合得到所述广告价值计算策略。
结合第二方面的第一种可能的实现方式,在第二方面的第二种可能的实现
方式中,当所述广告价值计算策略确定模块确定的广告价值元素为两个或两个以上时,所述广告价值计算策略确定模块具体用于:将所述两个或两个以上的广告价值元素以相乘的方式进行组合构成用于计算广告价值的乘积式,所述乘积式为所述广告价值计算策略。
结合第二方面、第二方面的第一种可能的实现方式或第二方面的第二种可能的实现方式,在第二方面的第三种可能的实现方式中,所述装置还包括调整模块,用于对所述广告价值元素进行修正或变换,得到修正或变换后的广告价值元素;
对应地,所述广告价值计算策略确定模块,用于根据所述修正或变换后的广告价值元素确定广告价值计算策略。
结合第二方面、第二方面的第一种可能的实现方式至第二方面的第三种可能的实现方式中的任意一种可能的实现方式,在第二方面的第四种可能的实现方式中,所述接收模块还用于接收用户信息,所述用户信息包括用户ID、用户年龄、用户性别或用户职业信息;
对应地,所述广告价值计算模块用于将所述用户信息作为另一个参考因子,与所述广告价值元素值和所述广告价值计算策略一起计算,得到针对所述用户的个性化广告价值。
结合第二方面,或第二方面的第一种可能的实现方式至第二方面的第四种可能的实现方式中的任意一种可能的实现方式,在第二方面的第五种可能的实现方式中,当所述广告价值计算策略确定模块确定的广告价值计算策略为两个或两个以上时,所述广告价值计算策略确定模块还用于:从所述两个或两个以上广告价值计算策略中选择最优的广告价值计算策略;
对应地,所述广告价值计算模块用于将所述广告价值元素值和所述最优的广告价值计算策略作为参考因子,计算得到所述广告的广告价值。
结合第二方面,或第二方面的第一种可能的实现方式至第二方面的第四种可能的实现方式中的任意一种可能的实现方式,在第二方面的第六种可能的实现方式中,当所述广告价值计算策略确定模块确定的广告价值计算策略为两个或两个以上时,所述广告价值计算策略确定模块还用于:将所述两个多两个以上广告价值计算策略进行加权,得到综合广告价值计算策略;
对应地,所述广告价值计算模块用于将所述广告价值元素值和所述综合广告价值计算策略作为参考因子,计算得到所述广告的广告价值。
结合第二方面,或第二方面的第一种可能的实现方式至第二方面的第六种可能的实现方式中的任意一种可能的实现方式,在第二方面的第七种可能的实现方式中,所述广告价值计算策略确定模块具体用于:确定所述广告应用平台支持的广告价值元素为所述广告价值元素。
结合第二方面,或第二方面的第一种可能的实现方式至第二方面的第七种可能的实现方式中的任意一种可能的实现方式,在第二方面的第八种可能的实现方式中,所述广告价值计算策略确定模块具体用于:确定所述广告应用平台支持的或预存的广告价值计算策略为所述广告价值计算策略。
结合第二方面,或第二方面的第一种可能的实现方式至第二方面的第八种可能的实现方式中的任意一种可能的实现方式,在第二方面的第九种可能的实现方式中,所述调整模块还用于对所述广告价值元素值进行修正,得到修正后的广告价值元素值;
对应地,所述广告价值计算模块用于将所述修正后的广告价值元素值和所
述广告价值计算策略作为参考因子,计算得到所述广告的广告价值。
结合第二方面,或第二方面的第一种可能的实现方式至第二方面的第九种可能的实现方式中的任意一种可能的实现方式,在第二方面的第十种可能的实现方式中,所述广告价值元素包括:用户浏览广告的付费量(PV)、用户点击广告的概率(CTR)、用户点击广告的价值(PCPC)、用户付费率(PR),用户确定付费后的付费量(PPP)、用户下载后付费率(DPR)。
结合第二方面,或第二方面的第一种可能的实现方式至第二方面的第十种可能的实现方式中的任意一种可能的实现方式,在第二方面的第十一种可能的实现方式中,所述预测模块具体用于根据历史数据统计方法或机器学习中的分类或回归方法预测所述广告价值元素的值,得到广告价值元素值。
在本发明实施例中,根据广告信息(例如:用户对广告的操作信息,包括浏览、点击、下载等操作信息)预测广告价值元素(例如:用户浏览广告的付费量(pV),用户点击广告的概率(CTR),用户点击广告的价值(pCPC,predicted cost per click),用户付费率(PR,Pay Ratio),用户确定付费后的付费量(pPP,predicted per pay)或用户下载后付费率(dPR)等)的值,得到广告价值元素值,将广告价值元素值和广告价值计算策略作为一个参考因子,计算得到广告价值。本发明实施例子中的广告价值元素值通过预测得到,而不是凭经验给定或干脆不予考虑,使得本发明实施例的方法在当前广告应用平台的任何一种付费模式下,都能计算出更准确的广告价值。
为了更清楚地说明本发明实施例的技术方案,下面将对实施例或现有技术
描述中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本发明的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动性的前提下,还可以根据这些附图获得其他的附图。
图1是广告应用平台工作的基本结构示意图。
图2是本发明实施例运行网络示意图。
图3为本发明一个实施例的广告价值确定方法的流程图。
图4为本发明另一个实施例的广告价值确定方法的流程图。
图5为本发明又一个实施例的广告价值确定方法的流程图。
图6为本发明一个实施例的广告价值确定装置的框图。
图7为本发明另一个实施例的广告价值确定装置的框图。
图8为本发明又一个实施例的广告价值确定装置的框图。
如图1所示,广告应用平台是一个平台或者中介,连接着应用开发者和广告主。在平台上,开发者提供应用,广告主提供广告,而广告应用平台就会提供相应手机系统的SDK。SDK(Software Development Kit)是软件开发工具包的意思,开发者下载SDK,然后使用SDK中的工具,用代码将广告嵌入应用中。然后开发者将这些应用通过其他渠道上传到移动互联网。用户下载应用,点击广告后,广告主就会根据相应的计费方式付费给广告应用平台。在PC互联网时代,GOOGLE通过ADSENSE广告平台将众多广告主投放的广告分发到放置了ADSENSE广告位的中小网站上,成就霸业。当前国内的在线广告有:横幅广告、插屏广告、积分墙广告,视频广告,push广告、自由图标广告、开屏
广告、全屏广告、九宫格广告等形式。开发者即App开发师,是指开发手机应用软件的人。开发者盈利模式除了app本身,还有加入广告的收益,随着移动互联网的发展,越来越多的开发者依靠广告应用平台的资源在自己的app内加入广告创造收益。广告主是为推销商品或者提供服务,自行或者委托他人设计、制作、发布广告的法人、其他经济组织或者个人,它是市场经济及广告活动的重要参与者,依靠广告应用平台提供的app资源,投放产品或品牌广告,以达到宣传推广目的。
举例来说,2014年智能手机的出货量超过十亿部,由此,基于智能终端的应用被广泛使用。2013年苹果公司App Store累计下载量达到500亿,应用超过100万。为了更好地服务用户,帮助用户方便快捷地找到感兴趣的应用,中国也涌现了很多应用市场,这里所说的应用市场可以是上文所述的广告应用平台的一种:如Tencent的应用宝,Baidu的91助手,华为应用市场等。当前终端应用市场最主要的盈利模式是:“按用户付费产生的收益,广告主与广告平台分成获取利润”。这种广告盈利模式的特点在于,用户点击广告,广告主并不付钱给广告平台,而是当用户实际消费广告产品后,其实际产生的利润被广告主与广告平台分享。目前该方式被广泛应用于应用市场中后置付费App的推广业务中,是应用市场最主要的盈利模式。
在这样的盈利模式下,当用户实际消费广告产品从而实际产生利润之后,再由广告主和广告平台分享收益,实则让广告平台相当被动。在这种盈利模式下如何主动获取更大的收益,一个重要因素即:如何将有可能产生更大收益的广告在前端识别出来并加大推送的力度?而要解决“如何将有可能产生更大收益的广告在前端识别出来”只需要解决准确确定广告价值的问题。
本发明实施例提供一种确定广告价值的方法,使广告应用平台能够在前端准确识别出不同广告的广告价值,从而将这些广告中价值更大的广告推送力度加大。这里所说的广告价值中,其价值范畴通常指该广告给广告主或者广告应用平台带来的可能的收益;这里所说的推送可以有很多种方式,例如推荐墙方式(如应用市场中的排序)、启动屏广告推送(如App应用的启动全屏弹出)、插屏广告推送等。
基于以上背景知识的介绍及本发明实施例的基本概括,下面将结合本发明实施例中的附图,对本发明实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例是本发明一部分实施例,而不是全部的实施例。基于本发明中的实施例,本领域普通技术人员在没有作出创造性劳动的前提下所获得的所有其他实施例,都属于本发明保护的范围。
图1所示的广告应用平台以及广告主、开发者、用户具体可以在如图2所示的网络中运行。
本发明实施例可以应用于2G,3G,4G等各种网络,请参阅图2,为本发明实施例的一种网络的示意图。如图2所示,包括:用户终端51-55、基站61-63、基站控制器(图中未示意)、网关设备71-72、管理服务器81以及管理客户端设备82(可选的),其中,图2中的管理服务器81执行的功能对应于图1中的广告应用平台,即广告应用平台的具体功能由管理服务器81来实施;图2中的用户终端51-55对应图1中的广告主、开发者、用户,其中广告主和开发者还可以是其他与管理服务器81相连接的服务器,此处不做限制。具体参见如下的各种方法实施例的描述,这里不赘述。
本申请的技术方案,可以应用于各种通信系统,例如,全球移动通信系统
(Global System for Mobile Communications,GSM)、通用分组无线业务(General Packet Radio Service,GPRS)系统、码分多址(Code Division Multiple Access,CDMA)系统、CDMA2000系统、宽带码分多址(Wideband Code Division Multiple Access,WCDMA)系统、长期演进(Long Term Evolution,LTE)系统或全球微波接入互操作性(World Interoperability for Microwave Access,WiMAX)系统等。
其中,所述基站可以是GSM系统、GPRS系统或CDMA系统中的基站(Base Transceiver Station,BTS),还可以是CDMA2000系统或WCDMA系统中的基站(NodeB),还可以是LTE系统中的演进型基站(Evolved NodeB,eNB),还可以是WiMAX网络中的接入服务网络的基站(Access Service Network Base Station,ASN BS)等。
其中,所述用户终端可以是指向用户提供语音和/或数据连通性的设备,具有无线连接功能的手持式设备、或连接到无线调制解调器的其他处理设备。用户终端可以经无线接入网(Radio Access Network,RAN)与一个或多个核心网进行通信,用户终端可以是移动终端,如移动电话(或称为“蜂窝”电话)和具有移动终端的计算机,例如,可以是便携式、袖珍式、手持式、计算机内置的或者车载的移动装置,它们与无线接入网交换语言和/或数据。例如,个人通信业务(Personal Communication Service,PCS)电话、无绳电话、会话发起协议(Session Initiation Protocol,SIP)话机、无线本地环路(Wireless Local Loop,WLL)站、个人数字助理(Personal Digital Assistant,PDA)等设备。终端也可以称为系统、订户单元(Subscriber Unit)、订户站(Subscriber Station)、移动站(Mobile Station)、远程站(Remote Station)、
接入点(Access Point)、远程终端(Remote Terminal)、接入终端(Access Terminal)、用户终端(User Terminal)、用户代理(User Agent)、用户设备(User Device)或用户装备(User Equipment)。
如图3所示,为本发明实施例提供的一种广告价值确定方法的流程示意图,该方法的执行主体可以是图1中的广告应用平台。
S101、接收广告信息,所述广告信息包括:广告ID以及用户对广告的操作信息;
本发明实施例的广告信息包括但不限于广告ID和用户对广告的操作信息,例如广告信息还可以包括广告类别等信息,此处不予穷举。可选的,本发明实施例所述的用户对广告的操作信息包括:浏览、点击、下载等操作信息,所述浏览、点击、下载等操作信息可以包括浏览、点击、下载的操作次数、操作时间等相关信息。
按照广告传播媒介来区分广告类型,通常包括传统纸媒广告,电视广告,广播广告,户外广告以及网络广告,本文所述的广告主要涉及网络广告,但是不排除通过本方法确定出广告价值后以其余传播媒介呈现的广告类型。
S103、根据广告应用平台确定广告价值元素,并根据所述广告价值元素确定广告价值计算策略,所述广告价值元素是对广告价值产生影响的元素;或,
根据广告应用平台确定广告价值计算策略,所述广告价值计算策略由所述广告价值元素表示;
在本发明实施例中,广告价值元素可以有很多种,例如:用户浏览广告的付费量(pV),用户点击广告的概率(CTR),用户点击广告的价值(pCPC,predicted cost per click),用户付费率(PR,Pay Ratio),用户确定付费
后的付费量(pPP,predicted per pay),用户下载后付费率(dPR)等。在具体的应用场景中,不同的广告应用平台支持的广告价值元素也不同,因此,本发明实施例所述的根据广告应用平台确定广告价值元素即:确定所述广告应用平台能够支持的广告价值元素有哪些,或者,直接确定所述广告应用平台能够支持的或预存的广告价值计算策略,所述广告价值计算策略由所述广告价值元素表示。其中,不同的广告价值元素对应不同的预测模型,所谓预测模型,是用来预测所述广告价值元素的,比如,预测广告价值元素CTR(下载率),需要用到分类模型,具体可以选择LR(Logistic Regression)模型;预测广告价值元素pCPC,需要用到回归模型,具体可以选择RF(Random Forest)或者GBRT(Gradient Boosting Regression Tree)模型。通过预测模型预测所述广告价值元素可以理解为在线下进行的预备工作。但是值得注意的是,在本发明的实施例中,并不是所有的广告价值元素都由其对应的预测模型预测得到,有一些广告价值元素可以通过统计的方法直接计算得到。
具体的,本发明实施例中可以将各个广告价值元素根据应用需求进行组合从而得到符合该应用需求的广告价值计算策略,其中,不同的广告价值元素决定广告价值计算策略中的不同性质,比如,单调性、凹凸性等。此处所述将将各个广告价值元素根据应用需求进行组合得到符合该应用需求的广告价值计算策略可以是:将所述两个或两个以上的广告价值元素以相乘的方式进行组合构成用于计算广告价值的乘积式,该乘积式即为我们所述的广告价值计算策略,即用于计算广告价值的路径方法。具体的广告价值计算策略可以有多种,例如:pV(当该广告应用平台支持的广告价值元素只有一个,或者本发明实施
例从多个广告价值元素中只选取一个时,该广告价值元素直接构成其对应地广告价值计算策略,即此时可以认为该广告价值元素的值直接等于广告价值,但该广告价值元素可以进一步进行修正或者变换,如此则依据修正或变换后的广告价值元素决定广告价值计算策略,后面将有展开,此处不赘述),直接预测或者计算pV;pCPC*CTR,分别预测或者计算pCPC和CTR;pPP*PR,分别预测或者计算pPP和PR;pPP*dPR*CTR,分别预测或者计算pPP,dPR和CTR;或者还可以是以上任意两种或两种以上广告价值计算策略的组合(比如加权平均)。
S107、根据所述广告信息预测所述广告价值元素的值,得到广告价值元素值;
可选的,此处根据所述广告信息预测所述广告价值元素的值,其预测方法可以是根据历史数据统计方法或机器学习中的分类或回归方法进行预测。值得说明的是,当根据广告应用平台确定的广告价值元素为N个时,在本发明实施例中,根据广告信息预测所述广告价值元素的值应当被理解为:根据广告信息分别预测N个广告价值元素中的每一个广告价值元素的值。其中N为大于或等于一的正整数。需要说明的是,当广告价值元素为一个时,则根据广告信息预测这一个广告价值元素的值;当广告价值元素为多个时,则该多个广告价值元素的值均要根据广告信息预测得到,其中多个为大于或者等于两个。
S109、将所述广告价值元素值和所述广告价值计算策略作为参考因子,计算得到所述广告的广告价值。
具体的,可以是将具体的广告价值元素值代入广告价值计算策略中,并通过计算得到广告价值。
综上,在本发明实施例中,据广告应用平台确定广告价值元素,并根据所述广告信息预测所述广告价值元素的值,得到广告价值元素值,从而将所述广告价值元素值和所述广告价值计算策略作为参考因子,计算得到所述广告的广告价值,从而准确的在前端确定了广告价值,为广告应用平台的最大化收益带来可能。
在上述实施例的基础上,可选的实施方式有:在步骤S103、所述根据所述广告价值元素确定广告价值计算策略之前,所述方法还包括S104:对所述广告价值元素进行修正或变换,得到修正或变换后的广告价值元素。对应地,步骤S103、根据所述广告价值元素确定广告价值计算策略具体包括:根据所述修正或变换后的广告价值元素确定广告价值计算策略。值得说明的是,此处所述的修正和变换可以根据广告应用平台的实际情况进行,具体的,此处的变换可以是将所述广告价值元素进行变形以使得其产生递增或递减的效果,从而满足所述广告应用平台的实际需求,此处的修正可以是将所述广告价值元素进行适应性补偿以平衡所述广告价值元素可能造成的偏差。
在上述实施例及实施方式的基础上,在步骤S107、根据所述广告信息预测所述广告价值元素的值,得到广告价值元素值之前,一种可选的实现方式为:
接收用户信息,所述用户信息包括用户ID、用户年龄、用户性别或用户职业信息;
值得说明的是,此处的用户信息包括但不限于:用户ID、用户年龄、用户性别或用户职业信息;并且,所述用户ID、用户年龄、用户性别或用户职业信息为可选的信息;在具体的实现过程中,用户信息还可以包括指示用户兴趣的信息,用户社交圈信息,或者用户浏览广告的上下文信息等。
对应地,将所述广告价值元素值和所述广告价值计算策略作为参考因子,计算所述广告的广告价值包括:
将所述用户信息作为另一个参考因子,与所述广告价值元素值和所述广告价值计算策略一起计算,得到针对所述用户的个性化广告价值。
通过将用户信息作为参考因子进行广告价值的计算,得到针对该用户的个性化广告价值,即,我们认为相同的广告对于不同的用户而言具有不同的广告价值,比如对于青年男性而言,游戏类广告较之于购物类广告的价值更大,而反过来,对于青年女性而言,购物类广告较之于游戏类广告的价值更大,具体到不同的个体具有不同的差异,根据用户信息获取用户年龄段、工作性质,受教育程度、兴趣爱好等,从而针对不同用户计算出不同的广告价值。使得广告应用平台得以根据该个性化广告价值面向不同用户采取不同的广告呈现策略,进而使广告应用平台的收益最大化成为可能。
在上述实施例及实施方式的基础上,当所述确定的广告价值计算策略为两个或两个以上时,在步骤S103、根据所述广告价值元素确定广告价值计算策略之后,或,根据广告应用平台确定广告价值计算策略之后,一种可选的实现方式为:
从所述两个或两个以上广告价值计算策略中选择最优的广告价值计算策略;
对应地,步骤S109、将所述广告价值元素值和所述广告价值计算策略作为参考因子,计算得到所述广告的广告价值包括:
将所述广告价值元素值和所述最优的广告价值计算策略作为参考因子,计算得到所述广告的广告价值。
需要说明的是,此处最优的广告价值计算策略是以结果为导向的,即通过该广告价值计算策略计算出广告价值,从而根据该广告价值对不同的广告进行排序并呈现给用户,进而为应用广告平台带来的收益最大,则认为该广告价值计算策略为最优的广告价值计算策略。值得注意的是,当我们说根据广告价值对不同的广告进行排序时,往往涉及多个广告及这多个广告价值的计算,最终进行排序的也是该多个广告对应的广告价值的排序,此处多个可以为大于或等于两个。
另外值得说明的是,在不同场景下最优的广告价值计算策略可能是不同的,选择最优的广告价值计算策略方法包括:可以根据线下的AUC(area under the curve)和MAE(mean absolute error)以及其他的的一些评测指标来评测不同的计算策略及其中广告价值元素对应的预测模型;也可以根据线上的收入情况来测评不同的广告价值计算策略。
在上述实施例及实施方式的基础上,当所述确定的广告价值计算策略为两个或两个以上时,在步骤S103、根据所述广告价值元素确定广告价值计算策略之后,或,根据广告应用平台确定广告价值计算策略之后,另一种可选的实现方式为:
将所述两个多两个以上广告价值计算策略进行加权,得到综合广告价值计算策略;
对应地,所述将所述广告价值元素值和所述广告价值计算策略作为参考因子,计算得到所述广告的广告价值包括:
将所述广告价值元素值和所述综合广告价值计算策略作为参考因子,计算得到所述广告的广告价值。
为了与此处的综合广告价值计算策略相区分,我们把此处的广告价值计算策略叫做独立广告价值计算策略,此处所述的综合广告价值计算策略是任意两种或两种以上独立广告价值计算策略的组合,在本实现方式中,组合方式可以是加权,当然本发明并不对该组合方式进行限定,任何能达到本发明目的及效果的组合方法均应在本发明的保护范围之内,此处不再赘述。需要说明的是,利用综合广告价值计算策略计算广告价值,具体可以通过集成学习的方式进行,所谓集成学习方法是指:使用一系列预测模型进行学习,并使用某种规则把各个学习结果进行整合从而获得比单个预测模型更好的学习效果的一种机器学习方法。此处独立广告价值计算策略是指能够独立完成广告价值计算的完整策略,例如上文所述的pV;pCPC*CTR;pPP*PR;pPP*dPR*CTR等。
在本发明实施例及本发明实施例基础上的所有可能的实现方式上,可选的,步骤S103、根据广告应用平台确定广告价值元素包括:确定所述广告应用平台支持的广告价值元素为所述广告价值元素。
可选的,在步骤S103中,根据广告应用平台确定广告价值计算策略包括:确定所述广告应用平台支持的或预存的广告价值计算策略为所述广告价值计算策略。
进一步可选的,在步骤S107、根据所述广告信息预测所述广告价值元素的值,得到广告价值元素值之后,另一种可选的实现方式为:
所述方法还包括S108:对所述广告价值元素值进行修正,得到修正后的广告价值元素值;
对应地,步骤S109、将所述广告价值元素值和所述广告价值计算策略作为参考因子,计算得到所述广告的广告价值包括:
将所述修正后的广告价值元素值和所述广告价值计算策略作为参考因子,计算得到所述广告的广告价值。
值得说明的是,此处所述的修正和变换可以根据广告应用平台的实际情况进行。之所以要进行修正或变换,是因为在现实的应用场景下,并不是所有预测得到的广告价值元素值都可以直接使用,对于无法直接使用的广告价值元素值我们会对其进行修正和变换。比如,对于一些小众的广告,样本量比较小,容易造成偏差,得到的预测结果并没有实际意义。根据这些小众广告的广告价值元素值,如果直接使用,会造成广告价值的预测不精确,这种情况下需要对广告价值元素值进行调整或者变换:例如,当一些小众广告的展示量和下载量都很少但是下载率却很高的时候,为了避免小样本造成的偏差,可以用所有广告的展示量的阈值来替代这个小众广告的展示量。
图6是本发明一个实施例的用于确定广告价值的装置的框图。图6所示的装置600包括接收模块601、广告价值计算策略确定模块603、、预测模块607、广告价值计算模块609。
接收模块601,用于接收广告信息,所述广告信息包括:广告ID以及用户对广告的操作信息;
本发明实施例的广告信息包括但不限于广告ID和用户对广告的操作信息,例如广告信息还可以包括广告类别等信息,此处不予穷举。可选的,本发明实施例所述的用户对广告的操作信息包括:浏览、点击、下载等操作信息,所述浏览、点击、下载等操作信息可以包括浏览、点击、下载的操作次数、操作时间等相关信息。
按照广告传播媒介来区分广告类型,通常包括传统纸媒广告,电视广告,
广播广告,户外广告以及网络广告,本文所述的广告主要涉及网络广告,但是不排除通过本方法确定出广告价值后以其余传播媒介呈现的广告类型。
广告价值计算策略确定模块603,用于根据广告应用平台确定广告价值元素,并根据所述广告价值元素确定广告价值计算策略,所述广告价值元素是对广告价值产生影响的元素;或,用于根据广告应用平台确定广告价值计算策略,所述广告价值计算策略由所述广告价值元素表示。
在本发明实施例中,广告价值元素可以有很多种,例如:用户浏览广告的付费量(pV),用户点击广告的概率(CTR),用户点击广告的价值(pCPC,predicted cost per click),用户付费率(PR,Pay Ratio),用户确定付费后的付费量(pPP,predicted per pay),用户下载后付费率(dPR)等。在具体的应用场景中,不同的广告应用平台支持的广告价值元素也不同,因此,本发明实施例所述的根据广告应用平台确定广告价值元素即:确定所述广告应用平台能够支持的广告价值元素有哪些,或者,直接确定所述广告应用平台能够支持的或预存的广告价值计算策略,所述广告价值计算策略由所述广告价值元素表示。其中,不同的广告价值元素对应不同的预测模型,所谓预测模型,是用来预测所述广告价值元素的,比如,预测广告价值元素CTR(下载率),需要用到分类模型,具体可以选择LR(Logistic Regression)模型;预测广告价值元素pCPC,需要用到回归模型,具体可以选择RF(Random Forest)或者GBRT(Gradient Boosting Regression Tree)模型。通过预测模型预测所述广告价值元素可以理解为在线下进行的预备工作。但是值得注意的是,在本发明的实施例中,并不是所有的广告价值元素都由其对应的预测模型预测得到,有一些广告价值元素可以通过统计的方法直接计算得到。
具体的,本发明实施例中可以将各个广告价值元素根据应用需求进行组合从而得到符合该应用需求的广告价值计算策略,其中,不同的广告价值元素决定广告价值计算策略中的不同性质,比如,单调性、凹凸性等。此处所述将将各个广告价值元素根据应用需求进行组合得到符合该应用需求的广告价值计算策略可以是:将所述两个或两个以上的广告价值元素以相乘的方式进行组合构成用于计算广告价值的乘积式,该乘积式即为我们所述的广告价值计算策略,即用于计算广告价值的路径方法。具体的广告价值计算策略可以有多种,例如:pV(当该广告应用平台支持的广告价值元素只有一个,或者本发明实施例从多个广告价值元素中只选取一个时,该广告价值元素直接构成其对应地广告价值计算策略,即此时可以认为该广告价值元素的值直接等于广告价值,但该广告价值元素可以进一步进行修正或者变换,如此则依据修正或变换后的广告价值元素决定广告价值计算策略,后面将有展开,此处不赘述),直接预测或者计算pV;pCPC*CTR,分别预测或者计算pCPC和CTR;pPP*PR,分别预测或者计算pPP和PR;pPP*dPR*CTR,分别预测或者计算pPP,dPR和CTR;或者还可以是以上任意两种或两种以上广告价值计算策略的组合(比如加权平均)。
预测模块607,用于根据所述广告信息预测所述广告价值元素的值,得到广告价值元素值。
可选的,此处根据所述广告信息预测所述广告价值元素的值,其预测方法可以是根据历史数据统计方法或机器学习中的分类或回归方法进行预测。值得说明的是,当根据广告应用平台确定的广告价值元素为N个时,在本发明实施例中,根据广告信息预测所述广告价值元素的值应当被理解为:根据广告信息
分别预测N个广告价值元素中的每一个广告价值元素的值。其中N为大于或等于一的正整数。需要说明的是,当广告价值元素为一个时,则根据广告信息预测这一个广告价值元素的值;当广告价值元素为多个时,则该多个广告价值元素的值均要根据广告信息预测得到,其中多个为大于或者等于两个。
广告价值计算模块609,用于将所述广告价值元素值和所述广告价值计算策略作为参考因子,计算得到所述广告的广告价值。
具体的,可以是将具体的广告价值元素值代入广告价值计算策略中,并通过计算得到广告价值。
综上,在本发明实施例中,据广告应用平台确定广告价值元素,并根据所述广告信息预测所述广告价值元素的值,得到广告价值元素值,从而将所述广告价值元素值和所述广告价值计算策略作为参考因子,计算得到所述广告的广告价值,从而准确的在前端确定了广告价值,为广告应用平台的最大化收益带来可能。
在装置600的基础上,本发明实施例提供的装置600还包括调整模块604,用于对所述广告价值元素进行修正或变换,得到修正或变换后的广告价值元素;
对应地,所述广告价值计算策略确定模块603具体用于根据所述修正或变换后的广告价值元素确定广告价值计算策略。
值得说明的是,此处所述的修正和变换可以根据广告应用平台的实际情况进行,具体的,此处的变换可以是将所述广告价值元素进行变形以使得其产生递增或递减的效果,从而满足所述广告应用平台的实际需求,此处的修正可以是将所述广告价值元素进行适应性补偿以平衡所述广告价值元素可能造成的
偏差。
在上述已描述的本发明实施例的基础上,可选的,本发明实施例提供的装置600中,所述接收模块601还可以用于接收用户信息,所述用户信息包括用户ID、用户年龄、用户性别或用户职业信息;
值得说明的是,此处的用户信息包括但不限于:用户ID、用户年龄、用户性别或用户职业信息;并且,所述用户ID、用户年龄、用户性别或用户职业信息为可选的信息;在具体的实现过程中,用户信息还可以包括指示用户兴趣的信息,用户社交圈信息,或者用户浏览广告的上下文信息等。
对应地,所述广告价值计算策略确定模块603具体用于:将所述用户信息作为另一个参考因子,与所述广告价值元素值和所述广告价值计算策略一起计算,得到针对所述用户的个性化广告价值。
通过将用户信息作为参考因子进行广告价值的计算,得到针对该用户的个性化广告价值,即,我们认为相同的广告对于不同的用户而言具有不同的广告价值,比如对于青年男性而言,游戏类广告较之于购物类广告的价值更大,而反过来,对于青年女性而言,购物类广告较之于游戏类广告的价值更大,具体到不同的个体具有不同的差异,根据用户信息获取用户年龄段、工作性质,受教育程度、兴趣爱好等,从而针对不同用户计算出不同的广告价值。使得广告应用平台得以根据该个性化广告价值面向不同用户采取不同的广告呈现策略,进而使广告应用平台的收益最大化成为可能。
在上述已描述的本发明实施例的基础上,可选的,当所述广告价值计算策略确定模块确定的广告价值计算策略为两个或两个以上时,本发明实施例提供的装置600中的广告价值计算策略确定模块603还用于:从所述两个或两个以
上广告价值计算策略中选择最优的广告价值计算策略;
对应地,所述广告价值计算模块607具体用于将所述广告价值元素值和所述最优的广告价值计算策略作为参考因子,计算得到所述广告的广告价值。
需要说明的是,此处最优的广告价值计算策略是以结果为导向的,即通过该广告价值计算策略计算出广告价值,从而根据该广告价值对不同的广告进行排序并呈现给用户,进而为应用广告平台带来的收益最大,则认为该广告价值计算策略为最优的广告价值计算策略。值得注意的是,当我们说根据广告价值对不同的广告进行排序时,往往涉及多个广告及这多个广告价值的计算,最终进行排序的也是该多个广告对应的广告价值的排序,此处多个可以为大于或等于两个。
另外值得说明的是,在不同场景下最优的广告价值计算策略可能是不同的,选择最优的广告价值计算策略方法包括:可以根据线下的AUC(area under the curve)和MAE(mean absolute error)以及其他的的一些评测指标来评测不同的计算策略及其中广告价值元素对应的预测模型;也可以根据线上的收入情况来测评不同的广告价值计算策略。
在上述已描述的本发明实施例的基础上,可选的,当所述广告价值计算策略确定模块确定的广告价值计算策略为两个或两个以上时,本发明实施例提供的装置600中的广告价值计算策略确定模块603还用于:将所述两个多两个以上广告价值计算策略进行加权,得到综合广告价值计算策略;
对应地,所述广告价值计算模块609具体用于将所述广告价值元素值和所述综合广告价值计算策略作为参考因子,计算得到所述广告的广告价值。
为了与此处的综合广告价值计算策略相区分,我们把此处的广告价值计算
策略叫做独立广告价值计算策略,此处所述的综合广告价值计算策略是任意两种或两种以上独立广告价值计算策略的组合,在本实现方式中,组合方式可以是加权,当然本发明并不对该组合方式进行限定,任何能达到本发明目的及效果的组合方法均应在本发明的保护范围之内,此处不再赘述。需要说明的是,利用综合广告价值计算策略计算广告价值,具体可以通过集成学习的方式进行,所谓集成学习方法是指:使用一系列预测模型进行学习,并使用某种规则把各个学习结果进行整合从而获得比单个预测模型更好的学习效果的一种机器学习方法。此处独立广告价值计算策略是指能够独立完成广告价值计算的完整策略,例如上文所述的pV;pCPC*CTR;pPP*PR;pPP*dPR*CTR等。
在上述已描述的所有本发明实施例的基础上,可选的,
所述广告价值计算策略确定模块603具体用于,确定所述广告应用平台支持的广告价值元素为所述广告价值元素。
可选的,所述广告价值计算策略确定模块603具体用于,确定所述广告应用平台支持的或预存的广告价值计算策略为所述广告价值计算策略。
进一步可选的,本发明实施例提供的装置600中调整模块604还用于对所述广告价值元素值进行修正,得到修正后的广告价值元素值;
对应地,所述广告价值计算模块用于将所述修正后的广告价值元素值和所述广告价值计算策略作为参考因子,计算得到所述广告的广告价值。
值得说明的是,此处所述的修正和变换可以根据广告应用平台的实际情况进行。之所以要进行修正或变换,是因为在现实的应用场景下,并不是所有预测得到的广告价值元素值都可以直接使用,对于无法直接使用的广告价值元素值我们会对其进行修正和变换。比如,对于一些小众的广告,样本量比较小,
容易造成偏差,得到的预测结果并没有实际意义。根据这些小众广告的广告价值元素值,如果直接使用,会造成广告价值的预测不精确,这种情况下需要对广告价值元素值进行调整或者变换:例如,当一些小众广告的展示量和下载量都很少但是下载率却很高的时候,为了避免小样本造成的偏差,可以用所有广告的展示量的阈值来替代这个小众广告的展示量。
图6、图7所示的装置600能够实现前述的实施例所示的广告价值确定方法,为避免重复,此处不再赘述。
图8是本发明另一个实施例提供的广告价值确定装置800的框图。图8所示的设备800包括处理器801、接收器802、发送器803和存储器804。
接收器802,用于接收广告信息,所述广告信息包括:广告ID以及用户对广告的操作信息。
处理器801,用于根据广告应用平台确定广告价值元素,并用于根据所述广告价值元素确定广告价值计算策略;所述广告价值元素是对广告价值产生影响的元素;或,用于根据广告应用平台确定广告价值计算策略,所述广告价值计算策略由所述广告价值元素表示;并用于根据所述广告信息预测所述广告价值元素的值,得到广告价值元素值;以及用于将所述广告价值元素值和所述广告价值计算策略作为参考因子,计算得到所述广告的广告价值。
综上,在本发明实施例中,据广告应用平台确定广告价值元素,并根据所述广告信息预测所述广告价值元素的值,得到广告价值元素值,从而将所述广告价值元素值和所述广告价值计算策略作为参考因子,计算得到所述广告的广告价值,从而准确的在前端确定了广告价值,为广告应用平台的最大化收益带来可能。
设备800中的各个组件通过总线系统805耦合在一起,其中总线系统805除包括数据总线之外,还包括电源总线、控制总线和状态信号总线。但是为了清楚说明起见,在图8中将各种总线都标为总线系统805。
上述本发明实施例揭示的方法可以应用于处理器801中,或者由处理器801实现。处理器801可能是一种集成电路芯片,具有信号的处理能力。在实现过程中,上述方法的各步骤可以通过处理器801中的硬件的集成逻辑电路或者软件形式的指令完成。上述的处理器801可以是通用处理器、数字信号处理器(Digital Signal Processor,DSP)、专用集成电路(Appl ication Specific Integrated Circuit,ASIC)、现成可编程门阵列(Field Programmable Gate Array,FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件。可以实现或者执行本发明实施例中的公开的各方法、步骤及逻辑框图。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。结合本发明实施例所公开的方法的步骤可以直接体现为硬件译码处理器执行完成,或者用译码处理器中的硬件及软件模块组合执行完成。软件模块可以位于随机存储器,闪存、只读存储器,可编程只读存储器或者电可擦写可编程存储器、寄存器等本领域成熟的存储介质中。该存储介质位于存储器804,处理器801读取存储器804中的信息,结合其硬件完成上述方法的步骤。
可以理解,本发明实施例中的存储器804可以是易失性存储器或非易失性存储器,或可包括易失性和非易失性存储器两者。其中,非易失性存储器可以是只读存储器(Read-Only Memory,ROM)、可编程只读存储器(Programmable ROM,PROM)、可擦除可编程只读存储器(Erasable PROM,EPROM)、电可擦除可编程只读存储器(Electrically EPROM,EEPROM)或闪存。易失性存储器可
以是随机存取存储器(Random Access Memory,RAM),其用作外部高速缓存。通过示例性但不是限制性说明,许多形式的RAM可用,例如静态随机存取存储器(Static RAM,SRAM)、动态随机存取存储器(Dynamic RAM,DRAM)、同步动态随机存取存储器(Synchronous DRAM,SDRAM)、双倍数据速率同步动态随机存取存储器(Double Data Rate SDRAM,DDR SDRAM)、增强型同步动态随机存取存储器(Enhanced SDRAM,ESDRAM)、同步连接动态随机存取存储器(Synchlink DRAM,SLDRAM)和直接内存总线随机存取存储器(Direct Rambus RAM,DR RAM)。本文描述的系统和方法的存储器804旨在包括但不限于这些和任意其它适合类型的存储器。
可以理解的是,本文描述的这些实施例可以用硬件、软件、固件、中间件、微码或其组合来实现。对于硬件实现,处理单元可以实现在一个或多个专用集成电路(Application Specific Integrated Circuits,ASIC)、数字信号处理器(Digital Signal Processing,DSP)、数字信号处理设备(DSP Device,DSPD)、可编程逻辑设备(Programmable Logic Device,PLD)、现场可编程门阵列(Field-Programmable Gate Array,FPGA)、通用处理器、控制器、微控制器、微处理器、用于执行本申请所述功能的其它电子单元或其组合中。
当在软件、固件、中间件或微码、程序代码或代码段中实现实施例时,它们可存储在例如存储部件的机器可读介质中。代码段可表示过程、函数、子程序、程序、例程、子例程、模块、软件分组、类、或指令、数据结构或程序语句的任意组合。代码段可通过传送和/或接收信息、数据、自变量、参数或存储器内容来稿合至另一代码段或硬件电路。可使用包括存储器共享、消息传递、令牌传递、网络传输等任意适合方式来传递、转发或发送信息、自变量、参数、
数据等。
对于软件实现,可通过执行本文所述功能的模块(例如过程、函数等)来实现本文所述的技术。软件代码可存储在存储器单元中并通过处理器执行。存储器单元可以在处理器中或在处理器外部实现,在后一种情况下存储器单元可经由本领域己知的各种手段以通信方式耦合至处理器。
这样一来,在本发明实施例中,据广告应用平台确定广告价值元素,并根据所述广告信息预测所述广告价值元素的值,得到广告价值元素值,从而将所述广告价值元素值和所述广告价值计算策略作为参考因子,计算得到所述广告的广告价值,从而准确的在前端确定了广告价值,为广告应用平台的最大化收益带来可能。可选的,作为一个实施例,当所述处理器801确定的广告价值元素为两个或两个以上时,处理器801具体用于将所述两个或两个以上的广告价值元素进行组合得到所述广告价值计算策略。
可选的,作为另一个实施例,处理器801具体用于对所述广告价值元素进行修正或变换,得到修正或变换后的广告价值元素;并根据所述修正或变换后的广告价值元素确定广告价值计算策略。
可选的,作为另一个实施例,接收器802还用于接收用户信息,所述用户信息包括用户ID、用户年龄、用户性别或用户职业信息;处理器801具体用于将所述用户信息作为另一个参考因子,与所述广告价值元素值和所述广告价值计算策略一起计算,得到针对所述用户的个性化广告价值。
可选的,作为另一个实施例,当所述广告价值计算策略为两个或两个以上时,处理器801具体用于:从所述两个或两个以上广告价值计算策略中选择最优的广告价值计算策略;并进一步用于将所述广告价值元素值和所述最优的广
告价值计算策略作为参考因子,计算得到所述广告的广告价值。
可选的,作为另一个实施例,当所述广告价值计算策略为两个或两个以上时,处理器801具体用于:将所述两个多两个以上广告价值计算策略进行加权,得到综合广告价值计算策略;并进一步用于将所述广告价值元素值和所述综合广告价值计算策略作为参考因子,计算得到所述广告的广告价值。
可选的,作为另一个实施例,处理器801具体用于对所述广告价值元素值进行修正,得到修正后的广告价值元素值;并进一步将所述修正后的广告价值元素值和所述广告价值计算策略作为参考因子,计算得到所述广告的广告价值。
可选的,作为另一个实施例,处理器801具体用于根据历史数据统计方法或机器学习中的分类或回归方法预测所述广告价值元素的值,得到广告价值元素值。
可选的,图8所示的装置800为广告价值确定装置。图8所示的装置800能够实现前述的实施例所示的广告价值确定方法,为避免重复,此处不再赘述。
本领域普通技术人员可以意识到,结合本文中所公开的实施例描述的各示例的单元及算法步骤,能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行,取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用使用不同方法来实现所描述的功能,但是这种实现不应认为超出本发明的范围。
所属领域的技术人员可以清楚地了解到,为描述的方便和简洁,上述描述的系统、装置和单元的具体工作过程,可以参考前述方法实施例中的对应过程,在此不再赘述。
在本申请所提供的几个实施例中,应该理解到,所揭露的系统、装置和方法,可以通过其它的方式实现。例如,以上所描述的装置实施例仅仅是示意性的,例如,所述单元的划分,仅仅为一种逻辑功能划分,实际实现时可以有另外的划分方式,例如多个单元或组件可以结合或者可以集成到另一个系统,或一些特征可以忽略,或不执行。另一点,所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口,装置或单元的间接耦合或通信连接,可以是电性,机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的,作为单元显示的部件可以是或者也可以不是物理单元,即可以位于一个地方,或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外,在本发明各个实施例中的各功能单元可以集成在一个处理单元中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个单元中。
所述功能如果以软件功能单元的形式实现并作为独立的产品销售或使用时,可以存储在一个计算机可读取存储介质中。基于这样的理解,本发明的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来,该计算机软件产品存储在一个存储介质中,包括若干指令用以使得一台计算机设备(可以是个人计算机,服务器,或者网络设备等)执行本发明各个实施例所述方法的全部或部分步骤。而前述的存储介质包括:U盘、移动硬盘、ROM、RAM、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述,仅为本发明的具体实施方式,但本发明的保护范围并不局限于此,任何熟悉本技术领域的技术人员在本发明揭露的技术范围内,可轻易想到变化或替换,都应涵盖在本发明的保护范围之内。因此,本发明的保护范围应以权利要求的保护范围为准。
Claims (24)
- 一种广告价值确定方法,其特征在于,包括:接收广告信息,所述广告信息包括:广告ID以及用户对广告的操作信息;根据广告应用平台确定广告价值元素,并根据所述广告价值元素确定广告价值计算策略,所述广告价值元素是对广告价值产生影响的元素;或,根据广告应用平台确定广告价值计算策略,所述广告价值计算策略由所述广告价值元素表示;根据所述广告信息预测所述广告价值元素的值,得到广告价值元素值;将所述广告价值元素值和所述广告价值计算策略作为参考因子,计算得到所述广告的广告价值。
- 根据权利要求1所述的方法,其特征在于,当所述确定的广告价值元素为两个或两个以上时,所述根据所述广告价值元素确定广告价值计算策略包括:将所述两个或两个以上的广告价值元素进行组合得到所述广告价值计算策略。
- 根据权利要求2所述的方法,其特征在于,所述将所述两个或两个以上的广告价值元素进行组合得到所述广告价值计算策略包括:将所述两个或两个以上的广告价值元素以相乘的方式进行组合构成用于计算广告价值的乘积式,所述乘积式为所述广告价值计算策略。
- 根据权利要求1至3任一项所述的方法,其特征在于,在所述根据所述广告价值元素确定广告价值计算策略之前,所述方法还包括:对所述广告价值元素进行修正或变换,得到修正或变换后的广告价值元 素;对应地,所述根据所述广告价值元素确定广告价值计算策略包括:根据所述修正或变换后的广告价值元素确定广告价值计算策略。
- 根据权利要求1至4任一项所述的方法,其特征在于,在所述根据所述广告信息预测所述广告价值元素的值,得到广告价值元素值之前还包括:接收用户信息,所述用户信息包括用户ID、用户年龄、用户性别或用户职业信息;对应地,将所述广告价值元素值和所述广告价值计算策略作为参考因子,计算所述广告的广告价值包括:将所述用户信息作为另一个参考因子,与所述广告价值元素值和所述广告价值计算策略一起计算,得到针对所述用户的个性化广告价值。
- 根据权利要求1至5任一项所述的方法,其特征在于,当所述确定的广告价值计算策略为两个或两个以上时,所述根据所述广告价值元素确定广告价值计算策略之后,或,根据广告应用平台确定广告价值计算策略之后,所述方法还包括:从所述两个或两个以上广告价值计算策略中选择最优的广告价值计算策略;对应地,所述将所述广告价值元素值和所述广告价值计算策略作为参考因子,计算得到所述广告的广告价值包括:将所述广告价值元素值和所述最优的广告价值计算策略作为参考因子,计算得到所述广告的广告价值。
- 根据权利要求1至5任一项所述的方法,其特征在于,当所述确定的 广告价值计算策略为两个或两个以上时,所述根据所述广告价值元素确定广告价值计算策略之后,或,根据广告应用平台确定广告价值计算策略之后,所述方法还包括:将所述两个多两个以上广告价值计算策略进行加权,得到综合广告价值计算策略;对应地,所述将所述广告价值元素值和所述广告价值计算策略作为参考因子,计算得到所述广告的广告价值包括:将所述广告价值元素值和所述综合广告价值计算策略作为参考因子,计算得到所述广告的广告价值。
- 根据权利要求1至7任一项所述的方法,其特征在于,所述根据广告应用平台确定广告价值元素包括:确定所述广告应用平台支持的广告价值元素为所述广告价值元素。
- 根据权利要求1至8任一项所述的方法,其特征在于,所述根据广告应用平台确定广告价值计算策略包括:确定所述广告应用平台支持的或预存的广告价值计算策略为所述广告价值计算策略。
- 根据权利要求1至9任一项所述的方法,其特征在于,在所述根据所述广告信息预测所述广告价值元素的值,得到广告价值元素值之后,所述方法还包括:对所述广告价值元素值进行修正,得到修正后的广告价值元素值;对应地,将所述广告价值元素值和所述广告价值计算策略作为参考因子,计算得到所述广告的广告价值包括:将所述修正后的广告价值元素值和所述广告价值计算策略作为参考因子, 计算得到所述广告的广告价值。
- 根据权利要求1至10任一方法,其特征在于,所述广告价值元素包括:用户浏览广告的付费量(PV)、用户点击广告的概率(CTR)、用户点击广告的价值(PCPC)、用户付费率(PR),用户确定付费后的付费量(PPP)、用户下载后付费率(DPR)。
- 根据权利要求1至11任一方法,其特征在于,所述预测所述广告价值元素的值,得到广告价值元素值包括:根据历史数据统计方法或机器学习中的分类或回归方法预测所述广告价值元素的值,得到广告价值元素值。
- 一种广告价值确定装置,其特征在于,包括:接收模块,用于接收广告信息,所述广告信息包括:广告ID以及用户对广告的操作信息;广告价值计算策略确定模块,用于根据广告应用平台确定广告价值元素,并根据所述广告价值元素确定广告价值计算策略,所述广告价值元素是对广告价值产生影响的元素;或,用于根据广告应用平台确定广告价值计算策略,所述广告价值计算策略由所述广告价值元素表示;预测模块,用于根据所述广告信息预测所述广告价值元素的值,得到广告价值元素值;广告价值计算模块,用于将所述广告价值元素值和所述广告价值计算策略作为参考因子,计算得到所述广告的广告价值。
- 根据权利要求13所述的装置,其特征在于,当所述广告价值计算策略确定模块确定的广告价值元素为两个或两个以上时,所述广告价值计算策略 确定模块具体用于将所述两个或两个以上的广告价值元素进行组合得到所述广告价值计算策略。
- 根据权利要求14所述的装置,其特征在于,当所述广告价值计算策略确定模块确定的广告价值元素为两个或两个以上时,所述广告价值计算策略确定模块具体用于:将所述两个或两个以上的广告价值元素以相乘的方式进行组合构成用于计算广告价值的乘积式,所述乘积式为所述广告价值计算策略。
- 根据权利要求13或15所述的装置,其特征在于,所述装置还包括调整模块,用于对所述广告价值元素进行修正或变换,得到修正或变换后的广告价值元素;对应地,所述广告价值计算策略确定模块,用于根据所述修正或变换后的广告价值元素确定广告价值计算策略。
- 根据权利要求13至16任一项所述的装置,其特征在于,所述接收模块还用于接收用户信息,所述用户信息包括用户ID、用户年龄、用户性别或用户职业信息;对应地,所述广告价值计算模块用于将所述用户信息作为另一个参考因子,与所述广告价值元素值和所述广告价值计算策略一起计算,得到针对所述用户的个性化广告价值。
- 根据权利要求13至17任一项所述的装置,其特征在于,当所述广告价值计算策略确定模块确定的广告价值计算策略为两个或两个以上时,所述广告价值计算策略确定模块还用于:从所述两个或两个以上广告价值计算策略中选择最优的广告价值计算策略;对应地,所述广告价值计算模块用于将所述广告价值元素值和所述最优的 广告价值计算策略作为参考因子,计算得到所述广告的广告价值。
- 根据权利要求13至17任一项所述的装置,其特征在于,当所述广告价值计算策略确定模块确定的广告价值计算策略为两个或两个以上时,所述广告价值计算策略确定模块还用于:将所述两个多两个以上广告价值计算策略进行加权,得到综合广告价值计算策略;对应地,所述广告价值计算模块用于将所述广告价值元素值和所述综合广告价值计算策略作为参考因子,计算得到所述广告的广告价值。
- 根据权利要求13至19任一项所述的装置,其特征在于,所述广告价值计算策略确定模块具体用于:确定所述广告应用平台支持的广告价值元素为所述广告价值元素。
- 根据权利要求13至20任一项所述的装置,其特征在于,所述广告价值计算策略确定模块具体用于:确定所述广告应用平台支持的或预存的广告价值计算策略为所述广告价值计算策略。
- 根据权利要求16至20任一项所述的装置,其特征在于,所述调整模块还用于对所述广告价值元素值进行修正,得到修正后的广告价值元素值;对应地,所述广告价值计算模块用于将所述修正后的广告价值元素值和所述广告价值计算策略作为参考因子,计算得到所述广告的广告价值。
- 根据权利要求13至22任一项所述的装置。其特征在于,所述广告价值元素包括:用户浏览广告的付费量(PV)、用户点击广告的概率(CTR)、用户点击广告的价值(PCPC)、用户付费率(PR),用户确定付费后的付费量(PPP)、用户下载后付费率(DPR)。
- 根据权利要求13至23任一项所述的装置,其特征在于,所述预测模 块具体用于根据历史数据统计方法或机器学习中的分类或回归方法预测所述广告价值元素的值,得到广告价值元素值。
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201580081577.2A CN107851262A (zh) | 2015-07-09 | 2015-08-18 | 一种广告价值确定方法及装置 |
EP15897522.7A EP3301628A4 (en) | 2015-07-09 | 2015-08-18 | Method and device for determining advertisement value |
US15/865,273 US20190043076A1 (en) | 2015-07-09 | 2018-01-09 | Method and apparatus for estimating advertisement value, and displaying advertisements on user terminal according to their values |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CNPCT/CN2015/083666 | 2015-07-09 | ||
CN2015083666 | 2015-07-09 |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US15/865,273 Continuation US20190043076A1 (en) | 2015-07-09 | 2018-01-09 | Method and apparatus for estimating advertisement value, and displaying advertisements on user terminal according to their values |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2017004866A1 true WO2017004866A1 (zh) | 2017-01-12 |
Family
ID=57684743
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2015/087384 WO2017004866A1 (zh) | 2015-07-09 | 2015-08-18 | 一种广告价值确定方法及装置 |
Country Status (4)
Country | Link |
---|---|
US (1) | US20190043076A1 (zh) |
EP (1) | EP3301628A4 (zh) |
CN (1) | CN107851262A (zh) |
WO (1) | WO2017004866A1 (zh) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108985804A (zh) * | 2017-05-31 | 2018-12-11 | 百度在线网络技术(北京)有限公司 | 流量分级方法及装置 |
CN109840800A (zh) * | 2018-12-14 | 2019-06-04 | 深圳壹账通智能科技有限公司 | 一种基于积分的产品推荐方法、装置、存储介质和服务器 |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106997333B (zh) * | 2016-01-22 | 2020-07-28 | 阿里巴巴集团控股有限公司 | 逻辑回归梯度的计算方法和装置 |
CN111125502B (zh) * | 2018-10-31 | 2024-02-20 | 北京字节跳动网络技术有限公司 | 用于生成信息的方法和装置 |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102117466A (zh) * | 2011-02-25 | 2011-07-06 | 北京开心人信息技术有限公司 | 一种定向投放网络广告的方法及系统 |
CN102592235A (zh) * | 2011-12-28 | 2012-07-18 | 北京品友互动信息技术有限公司 | 一种互联网广告投放系统 |
CN102693500A (zh) * | 2012-05-24 | 2012-09-26 | 浙江盘石信息技术有限公司 | 网站广告位价值量计算系统及计算方法 |
US20130097011A1 (en) * | 2011-10-14 | 2013-04-18 | Microsoft Corporation | Online Advertisement Perception Prediction |
CN104065672A (zh) * | 2013-03-18 | 2014-09-24 | 华为技术有限公司 | 广告推送方法、客户端及广告推送系统 |
Family Cites Families (44)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8086559B2 (en) * | 2002-09-24 | 2011-12-27 | Google, Inc. | Serving content-relevant advertisements with client-side device support |
WO2005031589A1 (en) * | 2003-09-23 | 2005-04-07 | Marchex, Inc. | Performance-based online advertising system and method |
US8527346B2 (en) * | 2003-09-29 | 2013-09-03 | Yahoo! Inc. | Method and system for scheduling electronic advertising |
US8156519B1 (en) * | 2005-08-01 | 2012-04-10 | Amdoes Software Systems Limited | System, method and computer program product for calculating the cost of an advertisement |
US20070130004A1 (en) * | 2005-12-01 | 2007-06-07 | Microsoft Corporation | AD campaign optimization |
US7827060B2 (en) * | 2005-12-30 | 2010-11-02 | Google Inc. | Using estimated ad qualities for ad filtering, ranking and promotion |
US8700469B2 (en) * | 2006-03-06 | 2014-04-15 | Apple Inc. | System and method for delivering advertising with enhanced effectiveness |
US8688522B2 (en) * | 2006-09-06 | 2014-04-01 | Mediamath, Inc. | System and method for dynamic online advertisement creation and management |
US8589233B2 (en) * | 2006-10-25 | 2013-11-19 | Microsoft Corporation | Arbitrage broker for online advertising exchange |
US20080103955A1 (en) * | 2006-10-25 | 2008-05-01 | Microsoft Corporation | Accounting for trusted participants in an online advertising exchange |
JP4327899B2 (ja) * | 2006-11-08 | 2009-09-09 | 株式会社シリウステクノロジーズ | 広告情報提供方法、広告情報提供システム及び広告情報提供プログラム |
US20080294524A1 (en) * | 2007-03-12 | 2008-11-27 | Google Inc. | Site-Targeted Advertising |
KR20070067021A (ko) * | 2007-03-23 | 2007-06-27 | 주식회사 비즈모델라인 | 광고 제공 정책 운용시스템 |
US7933798B1 (en) * | 2007-05-25 | 2011-04-26 | Google Inc. | Determining and displaying impression share to advertisers |
US20090043649A1 (en) * | 2007-08-08 | 2009-02-12 | Google Inc. | Content Item Pricing |
US9111286B2 (en) * | 2008-02-01 | 2015-08-18 | Qualcomm, Incorporated | Multiple actions and icons for mobile advertising |
US20090327083A1 (en) * | 2008-06-27 | 2009-12-31 | Microsoft Corporation | Automating on-line advertisement placement optimization |
US8224698B2 (en) * | 2008-07-03 | 2012-07-17 | The Search Agency, Inc. | System and method for determining weighted average success probabilities of internet advertisements |
KR20100006467A (ko) * | 2008-07-09 | 2010-01-19 | 엔에이치엔비즈니스플랫폼 주식회사 | 온라인 광고에 대한 과금을 위한 방법, 시스템 및 컴퓨터판독 가능한 기록 매체 |
US20110231254A1 (en) * | 2008-09-05 | 2011-09-22 | Nhn Business Platform Corporation | Method and system for providing advertisements, and computer-readable recording medium |
KR20110061617A (ko) * | 2008-09-08 | 2011-06-09 | 엔에이치엔비즈니스플랫폼 주식회사 | 온라인 광고에 대한 과금을 위한 방법, 시스템 및 컴퓨터 판독 가능한 기록 매체 |
US8738436B2 (en) * | 2008-09-30 | 2014-05-27 | Yahoo! Inc. | Click through rate prediction system and method |
US8175950B1 (en) * | 2008-12-08 | 2012-05-08 | Aol Advertising Inc. | Systems and methods for determining bids for placing advertisements |
US9547865B2 (en) * | 2009-03-30 | 2017-01-17 | Ebay Inc. | System and method for providing advertising server optimization for online computer users |
US20110040635A1 (en) * | 2009-08-14 | 2011-02-17 | Willard Simmons | Dynamic targeting algorithms for real-time valuation of advertising placements |
US20110258052A1 (en) * | 2010-04-16 | 2011-10-20 | Microsoft Corporation | Dynamic mechanism for selling online advertising space |
US8650084B2 (en) * | 2010-06-18 | 2014-02-11 | Microsoft Corporation | Tool for analysis of advertising auctions |
US20120130798A1 (en) * | 2010-11-23 | 2012-05-24 | Cooley Robert W | Model sequencing for managing advertising pricing |
US20120150626A1 (en) * | 2010-12-10 | 2012-06-14 | Zhang Ruofei Bruce | System and Method for Automated Recommendation of Advertisement Targeting Attributes |
US20120253939A1 (en) * | 2011-03-31 | 2012-10-04 | Nokia Corporation | Method and apparatus for processing advertising content based on policy data |
US20130080264A1 (en) * | 2011-09-09 | 2013-03-28 | Dennoo Inc. | Methods and systems for bidding and acquiring advertisement impressions |
CN103295147B (zh) * | 2012-03-02 | 2017-02-15 | 华为技术有限公司 | 投放广告的方法、装置和系统 |
CN103489117B (zh) * | 2012-06-12 | 2015-07-01 | 深圳市腾讯计算机系统有限公司 | 信息投放方法和系统 |
US20130346182A1 (en) * | 2012-06-20 | 2013-12-26 | Yahoo! Inc. | Multimedia features for click prediction of new advertisements |
KR101295086B1 (ko) * | 2012-08-16 | 2013-08-09 | (주)티그레이프 | 광고 효과 분석 장치 및 방법 |
JP5797211B2 (ja) * | 2013-01-08 | 2015-10-21 | ヤフー株式会社 | 広告情報提供装置および広告情報提供方法 |
US20140236710A1 (en) * | 2013-02-19 | 2014-08-21 | Congoo, Llc | On-line advertising valuation |
US20150066659A1 (en) * | 2013-08-27 | 2015-03-05 | Google Inc. | Ranking Content Items Based on a Value of Learning |
US20150242885A1 (en) * | 2014-02-21 | 2015-08-27 | Apple Inc. | Invitational content attribution |
WO2015141931A1 (ko) * | 2014-03-19 | 2015-09-24 | 에스케이플래닛 주식회사 | 광고 제공 장치 및 방법 |
US20160104207A1 (en) * | 2014-10-11 | 2016-04-14 | Papaya Mobile, Inc. | Advertising campaign conversion systems and methods |
US20160180375A1 (en) * | 2014-12-22 | 2016-06-23 | Lochlan H. Rose | System And Method To Estimate The Incrementality Delivered By Online Campaigns Based On Measuring Impression-Level Digital Display Ad Viewability |
US20160335648A1 (en) * | 2015-05-11 | 2016-11-17 | Groupm Worldwide Llc | System and method for multifaceted publisher management of marketing activities |
WO2017030281A1 (ko) * | 2015-08-20 | 2017-02-23 | 에스케이플래닛 주식회사 | 광고플랫폼장치 및 그 동작 방법, 그리고 광고 소프트웨어개발키트 |
-
2015
- 2015-08-18 WO PCT/CN2015/087384 patent/WO2017004866A1/zh active Application Filing
- 2015-08-18 EP EP15897522.7A patent/EP3301628A4/en not_active Withdrawn
- 2015-08-18 CN CN201580081577.2A patent/CN107851262A/zh active Pending
-
2018
- 2018-01-09 US US15/865,273 patent/US20190043076A1/en not_active Abandoned
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102117466A (zh) * | 2011-02-25 | 2011-07-06 | 北京开心人信息技术有限公司 | 一种定向投放网络广告的方法及系统 |
US20130097011A1 (en) * | 2011-10-14 | 2013-04-18 | Microsoft Corporation | Online Advertisement Perception Prediction |
CN102592235A (zh) * | 2011-12-28 | 2012-07-18 | 北京品友互动信息技术有限公司 | 一种互联网广告投放系统 |
CN102693500A (zh) * | 2012-05-24 | 2012-09-26 | 浙江盘石信息技术有限公司 | 网站广告位价值量计算系统及计算方法 |
CN104065672A (zh) * | 2013-03-18 | 2014-09-24 | 华为技术有限公司 | 广告推送方法、客户端及广告推送系统 |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108985804A (zh) * | 2017-05-31 | 2018-12-11 | 百度在线网络技术(北京)有限公司 | 流量分级方法及装置 |
CN109840800A (zh) * | 2018-12-14 | 2019-06-04 | 深圳壹账通智能科技有限公司 | 一种基于积分的产品推荐方法、装置、存储介质和服务器 |
Also Published As
Publication number | Publication date |
---|---|
EP3301628A4 (en) | 2018-04-18 |
EP3301628A1 (en) | 2018-04-04 |
CN107851262A (zh) | 2018-03-27 |
US20190043076A1 (en) | 2019-02-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10181135B2 (en) | Method and apparatus for presenting advertisements | |
US10856022B2 (en) | Dynamically providing digital content to client devices by analyzing insertion points within a digital video | |
US20130191215A1 (en) | Location-based application pop up | |
US20170017986A1 (en) | Tracking digital design asset usage and performance | |
US20200126110A1 (en) | Object selection method and device | |
US11436628B2 (en) | System and method for automated bidding using deep neural language models | |
US20150278877A1 (en) | User Engagement-Based Contextually-Dependent Automated Reserve Price for Non-Guaranteed Delivery Advertising Auction | |
US20190043076A1 (en) | Method and apparatus for estimating advertisement value, and displaying advertisements on user terminal according to their values | |
US10740797B2 (en) | Systems and methods for implementing a mobile application based online advertising system | |
US9734519B2 (en) | Native advertisement smart injection | |
US20150178790A1 (en) | User Engagement-Based Dynamic Reserve Price for Non-Guaranteed Delivery Advertising Auction | |
US20150149275A1 (en) | Quasi-proportional allocation of combination items for serving in an online auction-based marketplace | |
US20170061502A1 (en) | Unified cross-channel advertisement platform | |
US20140122221A1 (en) | Optimizing bidding with multiple campaign types | |
US10957002B2 (en) | Sequence dependent or location based operation processing of protocol based data message transmissions | |
US20090281893A1 (en) | Method, Apparatus and Computer Program Product for Managing Advertising | |
AU2015324168A1 (en) | Generative grammar models for promotion and advertising | |
US9336538B2 (en) | Systems and methods for providing advertising services to devices with an advertising exchange | |
US20150120436A1 (en) | Systems, methods, and computer-readable-media for determining a multilocation predicted click-through rate for advertisements | |
US20170213238A1 (en) | Evaluating performance of content item presentation by modifying parameters determining whether to present content item to users of an online system | |
US20130275223A1 (en) | Future ad targeting | |
CN111815368A (zh) | 广告推送方法、装置、终端及存储介质 | |
CN115545737A (zh) | 广告投放策略校准方法和装置、存储介质及电子设备 | |
WO2015153919A1 (en) | Systems and methods for providing advertising services in a predictive manner to devices with an advertising exchange | |
US20140006171A1 (en) | Method of offline experimentation environment and apparatus conducting the same |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 15897522 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2015897522 Country of ref document: EP |
|
NENP | Non-entry into the national phase |
Ref country code: DE |