WO2017157130A1 - Method and device for pushing value-added service information and electronic apparatus - Google Patents

Abstract

Disclosed in an embodiment of the application are a method and device for pushing value-added service information and an electronic apparatus. The method comprises: acquiring a candidate value-added service information set according to a value-added service information distribution request; using service feature information of each value-added service information item and a value-added service information model to calculate a corresponding cost parameter; writing, to a common dimension group, extracted service feature information of the value-added service information item to obtain a dimension group of the value-added service information item; querying, according to a charging type of the value-added service information item, a mapping relationship between the dimension group and a charging modification parameter to obtain the charging modification parameter mapped with the dimension group of the value-added service information item; and applying the cost parameter and the charging modification parameter to a preset charging adjustment formula to obtain a modified eCPM for each value-added service information item, sorting according to the modified eCPM obtained by calculation, and pushing the sorted value-added service information items. The application can increase the efficiency of pushing value-added service information.

Description

Method, device and electronic device for pushing value-added business information

Cross-reference to related applications

The present application claims the priority of the Chinese Patent Application No. 201610156894.2, filed on March 18, 2016 by the Beijing Jinshan Security Software Co., Ltd., entitled "Method, Apparatus and Electronic Device for Pushing Value-Added Business Information".

Technical field

The present application relates to a value-added service application technology, and in particular, to a method, device, and electronic device for pushing value-added service information.

Background technique

With the continuous development of computer communication and Internet technology, electronic devices such as smart mobile phones, personal digital assistants, handheld computers, and notebook computers have become more and more widely used. Many value-added service operators have seen opportunities to place value-added service information based on electronic devices. For example, value-added service operators push value-added service information to mobile phones through value-added service platforms provided by Internet operators. Wide, easy to use, and high efficiency of value-added services.

On the value-added service platform provided by the Internet service provider, the value-added service platform can deliver value-added service information of multiple charging types based on multiple types of value-added service charging types, where the charging type includes but is not limited to: per thousand times Show how to charge (CPM, Cost-Per-Mille), how to charge per click (CPC, Cost-Per-Click), how to charge per installation (CPI, Cost-Per-Install) , according to the method of charging per action (CPA, Cost-Per-Action), charging according to each purchase (CPS, Cost-Per-Sale), charging according to each video broadcast (CPV, Cost) -Per-Video)etc.

Since the same value-added service platform will deliver value-added service information corresponding to multiple applications at a time, the design level of different value-added service information is uneven. In order to measure the level or quality of value-added service information of different charging types, determine which value-added service information. Displayed in the front position to the user, the value-added service platform proposes a method for sorting and displaying the value-added service information to be pushed, and normalizes the value-added service information of different charging types separately, and calculates The unified expected per-1000 value-added service information display fee (eCPM, expected-Cost-Per-Mille), and sorting the value-added service information according to the level of eCPM, and displaying the value-added service information according to the sorted sequence user. Among them, the value-added service information of different charging types uses different algorithms to calculate eCPM. For example, for CPM value-added service information, eCPM is the bid-per-thousand impression (bid) bid of the operator that pushes the value-added service information, and the bid is a click/present/installation of the value-added service information by the operator that pushes the value-added service information. price.

For CPC value-added service information, calculate eCPM using the following formula:

eCPM=CTR*bid

In the formula,

eCPM charges for the expected value-added business information per thousand times;

CTR is Click-Through-Rate, which is the ratio of the value-added business information hits to the value-added business information.

Bid is the operator’s bid for thousand impressions.

For CPA/CPI/CPS value-added service information, calculate eCPM using the following formula:

eCPM=CTR*CVR*bid

In the formula,

CVR is the conversion rate (Conversion-Rate), which is the ratio of the purchase/installation amount generated by value-added service information to the value-added service information click volume.

or,

eCPM=ICVR*bid

In the formula,

The ICVR is the installation-conversion-Rate, which is the ratio of the purchase/installation amount generated by the value-added service information to the value-added service information.

Among them, CTR, CVR, and ICVR are collectively referred to as charging coefficients. The following briefly describes the process of calculating CTR, CVR, and ICVR:

Step 1: training a value-added service information model for calculating CTR/CVR/ICVR according to a history log of each value-added service information;

Step 2, according to the targeting conditions in the value-added service information request, for example, the country, gender, and age required to be delivered The directional condition, from the value-added service information set, selects the candidate value-added service information set that meets the directional condition.

Step 3: Extract, for each value-added service information in the candidate value-added service information set, user attributes (eg, gender, age, country, language, device type, and the like) of the value-added service information, and value-added service information attributes (eg, material size, Effect class, conversion class, industry classification), context attribute (for example, media, value-added service information bit), generate model value-added service feature information;

Step 4: The generated model value-added service feature information is input into the trained value-added service information model, and the CTR/CVR/ICVR of the value-added service information is calculated.

In this way, after the CTR/CVR/ICVR of the value-added service information is calculated, the eCPM is calculated according to the eCPM calculation formula corresponding to the charging type of the value-added service information, and then the value-added service of the candidate value-added service information is concentrated by using the eCPM. The information is sorted to return to the user some of the top value-added service information.

In the above calculation of eCPM, since CTR, CVR, ICVR and other indicators are usually trained on different data sets using different models, for example, using Logistic Regression (LR, Logistic Regression) model, gradient lifting decision tree (GBDT, Gradient) Boosting Decision Tree) model. In the data set used for model training, the positive sample (purchase/click behavior) data and the negative sample (without subsequent purchase/click presentation) are heavily unevenly distributed (the former is much smaller than the latter), resulting in predictions by the model. The value-added service information CTR/CVR/ICVR has a certain deviation from the historical real value-added service information CTR/ICVR, which may be overestimated or underestimated, so that the calculated eCPM accuracy is not high. When the value-added service information estimated by the model is CTR/ When the CVR/ICVR gap is too large, the overall ranking effect of the value-added service information will be affected, and the push efficiency of the value-added service information is low.

Summary of the invention

In view of this, the embodiments of the present application provide a method, a device, and an electronic device for pushing value-added service information, which improve the push efficiency of value-added service information.

To achieve the above objective, the embodiment of the present application adopts the following technical solutions:

In a first aspect, the embodiment of the present application provides a method for pushing value-added service information, including:

Parsing the received value-added service information delivery request, obtaining the feature information included in the value-added service information delivery request, and selecting a candidate value-added service information set that meets the feature information from the preset value-added service information set;

And sequentially extracting service characteristic information of each value-added service information in the candidate value-added service information set, inputting the pre-trained value-added service information model, and calculating a charging coefficient for each value-added service information;

The service characteristic information of the extracted value-added service information is written into a preset universal dimension group to obtain a dimension group of the value-added service information;

According to the charging type of the value-added service information, querying the mapping relationship between the pre-stored charging type correction coefficient centralized dimension group and the charging correction coefficient, and acquiring the charging correction coefficient of the dimensional group mapping of the value-added service information;

Applying the charging coefficient and the charging correction coefficient to a preset charging adjustment formula, and obtaining a charging eCPM displayed per thousand value-added service information of each modified value-added service information, and sorting according to the calculated corrected eCPM and Push sorted value-added business information.

Optionally, obtaining the mapping relationship between the dimension group and the charging correction coefficient includes:

Calculating an average estimated charging coefficient and an average historical charging coefficient according to a pre-stored presentation history log;

Calculating a ratio of an average historical charging coefficient of the dimensional group to an average estimated charging coefficient, obtaining a charging correction coefficient, and storing a mapping relationship between the dimensional group and the charging correction coefficient.

Optionally, the average estimated charging coefficient includes: a CTR average estimated charging coefficient, a CVR average estimated charging coefficient, and an ICVR average estimated charging coefficient; and the average historical charging coefficient includes: a CTR average history. Billing factor, CVR average historical billing factor, and ICVR average historical billing factor.

Optionally, the CTR average estimated charging coefficient and the CTR average historical charging coefficient are calculated by using the following formula:

In the formula,

CTR _PREDICT (dims(n)) is the CTR average estimated charging factor;

CTR _REAL (dims(n)) is the CTR average historical charging factor;

C(dims(n)) is a pre-stored set of presentation history logs;

Ac(i) is the behavior type of the i-th value-added service information, wherein the behavior type includes: presentation, click, and installation, the presentation identifier is imp, the click identifier is clk, and the installation identifier is ins;

CTR _PREDICT (i) is the estimated eCPM value of the i-th value-added business information.

Optionally, the ICVR average estimated charging coefficient and the ICVR average historical charging coefficient are calculated by using the following formula:

In the formula,

ICVR _PREDICT (dims(n)) is the ICVR average estimated charging factor;

ICVR _REAL (dims(n)) is the ICVR average historical charging factor.

Optionally, the CVR average estimated charging coefficient and the CVR average historical charging coefficient are calculated by using the following formula:

In the formula,

CVR _PREDICT (dims(n)) is the average estimated charging factor of CVR;

CVR _REAL (dims(n)) is the CVR average historical charging factor.

Optionally, the charging correction coefficient includes: a CTR correction coefficient, an ICVR correction coefficient, and a CVR correction coefficient, and the CTR correction coefficient, the ICVR correction coefficient, and the CVR correction coefficient are respectively calculated by using the following formula:

In the formula,

ADJUST _CTR (dims(n)) is the CTR correction factor;

ADJUST _ICVR (dims(n)) is the ICVR correction factor;

ADJUST _CVR (dims(n)) is the CVR correction factor.

Optionally, the modified eCPM is calculated using the following formula:

eCPM _ADJUST-CPC =CTR _ADJUST *bid

CTR _ADJUST =CTR*ADJUST _CTR (b,v ₂ ,...,v _n ) ^α

among them,

eCPM _ADJUST-CPC is a modified eCPM based on CPC billing type;

CTR _ADJUST is the CTR charge adjustment factor;

0 ≤ α ≤ 1, which is a constant;

(b, v ₂ , . . . , v _n ) is a dimension group obtained by writing service characteristic information of the value-added service information into a preset common dimension group.

Optionally, the modified eCPM is calculated using the following formula:

eCPM _ADJUST-ICVR =ICVR _ADJUST *bid

ICVR _ADJUST =ICVR*ADJUST _ICVR (b,v ₂ ,...,v _n ) ^α

among them,

eCPM _ADJUST-ICVR is a modified eCPM based on the first charging type of CPA/CPI/CPS;

ICVR _ADJUST is the ICVR charging adjustment factor;

0 ≤ α ≤ 1, which is a constant;

(b, v ₂ , . . . , v _n ) is a dimension group obtained by writing service characteristic information of the value-added service information into a preset common dimension group.

Optionally, the modified eCPM is calculated using the following formula:

eCPM _ADJUST-CVR =CTR _ADJUST *CVR _ADJUST *bid

CVR _ADJUST =CVR*ADJUST _CVR (b,v ₂ ,...,v _n ) ^β

among them,

eCPM _ADJUST-CVR is a modified eCPM based on CPA/CPI/CPS second charging type;

CVR _ADJUST is the CVR charging adjustment factor;

0 ≤ α ≤ 1, which is a constant;

(b, v ₂ , . . . , v _n ) is a dimension group obtained by writing service characteristic information of the value-added service information into a preset common dimension group.

Optionally, the method further includes:

The user behavior information of the pushed value-added service information is recorded in the history log.

In a second aspect, the embodiment of the present application provides an apparatus for pushing value-added service information, including: a candidate value-added service information set acquisition module, a charging coefficient calculation module, a dimension group acquisition module, a charging correction coefficient query module, and a value-added service information push module. ,among them,

The candidate value-added service information collection module is configured to parse the received value-added service information delivery request, obtain the feature information included in the value-added service information delivery request, and select the qualified information from the preset value-added service information set. Candidate value-added service information set;

a charging coefficient calculation module, configured to sequentially extract service characteristic information of each value-added service information in the candidate value-added service information set, input the pre-trained value-added service information model, and calculate a charging coefficient for each value-added service information;

a dimension group obtaining module, configured to write the service characteristic information of the extracted value-added service information into a preset universal dimension group, to obtain a dimension group of the value-added service information;

The charging correction coefficient querying module is configured to query a mapping relationship between the pre-stored charging type correction coefficient centralized dimension group and the charging correction coefficient according to the charging type of the value-added service information, and obtain the dimensional group mapping of the value-added service information. Billing correction factor;

a value-added service information pushing module, configured to apply the charging coefficient and the charging correction coefficient to a preset charging adjustment formula, and obtain a charging eCPM for each thousand times of value-added service information that is corrected for each value-added service information, according to The calculated corrected eCPM sorts and pushes the sorted value-added service information.

Optionally, the charging correction coefficient querying module includes: a calculating unit, a mapping relationship building unit, and a charging correction coefficient query unit, where

a calculating unit, configured to calculate an average estimated charging coefficient and an average historical charging coefficient according to the pre-stored presentation history log;

a mapping relationship construction unit, configured to calculate a ratio of an average historical charging coefficient of the dimensional group to an average estimated charging coefficient, and obtain a charging correction coefficient of the dimensional group mapping, and set the charging type correction coefficient set;

The charging correction coefficient querying unit is configured to query the mapping relationship construction unit according to the charging type of the value-added service information, and acquire the charging correction coefficient of the dimension group mapping of the value-added service information.

Optionally, the average estimated charging coefficient includes: a CTR average estimated charging coefficient, a CVR average estimated charging coefficient, and an ICVR average estimated charging coefficient; and the average historical charging coefficient includes: a CTR average history. Billing factor, CVR average historical billing factor and ICVR average historical billing factor.

Optionally, the CTR average estimated charging coefficient and the CTR average historical charging coefficient are calculated by using the following formula:

In the formula,

CTR _PREDICT (dims(n)) is the CTR average estimated charging factor;

CTR _REAL (dims(n)) is the CTR average historical charging factor;

C(dims(n)) is a pre-stored set of presentation history logs;

Ac(i) is the behavior type of the i-th value-added service information, wherein the behavior type includes: presentation, click, and installation, the presentation identifier is imp, the click identifier is clk, and the installation identifier is ins;

CTR _PREDICT (i) is the estimated eCPM value of the i-th value-added business information.

Optionally, the ICVR average estimated charging coefficient and the ICVR average historical charging coefficient are calculated by using the following formula:

In the formula,

ICVR _PREDICT (dims(n)) is the ICVR average estimated charging factor;

ICVR _REAL (dims(n)) is the ICVR average historical charging factor.

Optionally, the CVR average estimated charging coefficient and the CVR average historical charging coefficient are calculated by using the following formula:

In the formula,

CVR _PREDICT (dims(n)) is the average estimated charging factor of CVR;

CVR _REAL (dims(n)) is the CVR average historical charging factor.

Optionally, the charging correction coefficient includes: a CTR correction coefficient, an ICVR correction coefficient, and a CVR correction coefficient, and the CTR correction coefficient, the ICVR correction coefficient, and the CVR correction coefficient are respectively calculated by using the following formula:

In the formula,

ADJUST _CTR (dims(n)) is the CTR correction factor;

ADJUST _ICVR (dims(n)) is the ICVR correction factor;

ADJUST _CVR (dims(n)) is the CVR correction factor.

Optionally, the modified eCPM is calculated using the following formula:

eCPM _ADJUST-CPC =CTR _ADJUST *bid

CTR _ADJUST =CTR*ADJUST _CTR (b,v ₂ ,...,v _n ) ^α

among them,

eCPM _ADJUST-CPC is a modified eCPM based on CPC billing type;

CTR _ADJUST is the CTR charge adjustment factor;

0 ≤ α ≤ 1, which is a constant;

(b, v ₂ , . . . , v _n ) is a dimension group obtained by writing service characteristic information of the value-added service information into a preset common dimension group.

Optionally, the modified eCPM is calculated using the following formula:

eCPM _ADJUST-ICVR =ICVR _ADJUST *bid

ICVR _ADJUST =ICVR*ADJUST _ICVR (b,v ₂ ,...,v _n ) ^α

among them,

eCPM _ADJUST-ICVR is a modified eCPM based on the first charging type of CPA/CPI/CPS;

ICVR _ADJUST is the ICVR charging adjustment factor;

0 ≤ α ≤ 1, which is a constant;

(b, v ₂ , . . . , v _n ) is a dimension group obtained by writing service characteristic information of the value-added service information into a preset common dimension group.

Optionally, the modified eCPM is calculated using the following formula:

eCPM _ADJUST-CVR =CTR _ADJUST *CVR _ADJUST *bid

CVR _ADJUST =CVR*ADJUST _CVR (b,v ₂ ,...,v _n ) ^β

among them,

eCPM _ADJUST-CVR is a modified eCPM based on CPA/CPI/CPS second charging type;

CVR _ADJUST is the CVR charging adjustment factor;

0 ≤ α ≤ 1, which is a constant;

(b, v ₂ , . . . , v _n ) is a dimension group obtained by writing service characteristic information of the value-added service information into a preset common dimension group.

Optionally, the device further includes:

And a recording module, configured to record user behavior information of the pushed value-added service information into the history log.

In a third aspect, an embodiment of the present application provides an electronic device, including: a housing, a processor, a memory, a circuit board, and a power supply circuit, wherein the circuit board is disposed inside the space enclosed by the housing, and the processor And a memory disposed on the circuit board; a power supply circuit for powering each circuit or device of the electronic device; a memory for storing executable program code; and the processor operating by reading executable program code stored in the memory The program corresponding to the program code is used to execute the method for pushing the value-added service information according to any of the foregoing.

The method, device, and electronic device for pushing the value-added service information provided by the embodiment of the present application, parsing the received value-added service information delivery request, and acquiring the feature information included in the value-added service information delivery request, from the preset value-added service information set, Selecting a candidate value-added service information set that meets the feature information; sequentially extracting service feature information of each value-added service information in the candidate value-added service information set, inputting the pre-trained value-added service information model, and calculating for each value-added service The charging coefficient of the information; the service characteristic information of the extracted value-added service information is written into a preset universal dimension group to obtain a dimension group of the value-added service information; and the pre-stored charging type correction is queried according to the charging type of the value-added service information. And a charging correction coefficient of the dimension group mapping of the value-added service information, and applying the charging coefficient and the charging correction coefficient to a preset charging adjustment formula, Corrected eCPM for each value-added service information, according to The calculated corrected eCPM is sorted and the sorted value-added service information is pushed. In this way, the value-added service information is counted according to the historical log of the value-added service information. The average estimated index value and the average true index value are calculated, and the charging correction coefficient of each value-added service information is calculated, and the estimated index outputted by the value-added service information model is corrected, so that the overall estimated eCPM of the value-added service information is more accurate. Thereby optimizing the overall ranking effect of the value-added service information and improving the push efficiency of the value-added service information.

DRAWINGS

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings to be used in the embodiments or the prior art description will be briefly described below. Obviously, the drawings in the following description are only It is a certain embodiment of the present application, and other drawings can be obtained from those skilled in the art without any creative work.

1 is a schematic flowchart of a method for pushing value-added service information according to an embodiment of the present application;

2 is a schematic flowchart of obtaining a mapping relationship between a dimension group and a charging correction coefficient according to an embodiment of the present application;

3 is a schematic structural diagram of an apparatus for pushing value-added service information according to an embodiment of the present application;

FIG. 4 is a schematic structural diagram of an embodiment of an electronic device according to the present application.

detailed description

The embodiments of the present application are described in detail below with reference to the accompanying drawings.

It should be understood that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present application without departing from the inventive scope are the scope of the present application.

FIG. 1 is a schematic flowchart of a method for pushing value-added service information according to an embodiment of the present application. Referring to Figure 1, the method includes:

Step 11: parsing the received value-added service information delivery request, acquiring the feature information included in the value-added service information delivery request, and selecting a candidate value-added service information set that meets the feature information from the preset value-added service information set;

In this step, as an optional embodiment, the feature information includes, but is not limited to, one of a value-added service information group identifier, a user attribute, a value-added service information attribute, and a context attribute, or any combination thereof, where

The value-added service information group, also known as the value-added service information series, refers to a set of value-added service information with the same budget, billing type, bidding, delivery period and targeting conditions.

User attributes include, but are not limited to, gender, age, country, language, device type, etc.

Value-added service information attributes include but are not limited to: material size, effect class, conversion class, industry classification;

Context attributes include, but are not limited to, media, value-added service information bits.

In the embodiment of the present application, the user or the value-added service operator may initiate a value-added service information delivery request through the client/browser, and the value-added service information delivery request includes feature information such as user attributes and context information.

In an embodiment of the present application, as an optional embodiment, the feature information may be an orientation condition.

Step 12: sequentially extract service characteristic information of each value-added service information in the candidate value-added service information set, input the pre-trained value-added service information model, and calculate a charging coefficient for each value-added service information;

In this step, for each value-added service information in the candidate value-added service information set, the service feature information of the value-added service information is extracted, including: user attributes (eg, gender, age, country, language, device type, etc.), value-added service information. Attributes (eg, material size, effect class, conversion class, industry classification), context attributes (eg, media, value-added service information bits), or any combination thereof, generate model value-added service feature information, and add value to the generated model The service feature information is input into a pre-trained corresponding value-added service information model, and a charging coefficient for each value-added service information is calculated.

In this embodiment of the present application, the service feature information includes, but is not limited to, one of a user attribute, a value-added service information attribute, and a context attribute, or any combination thereof.

In the embodiment of the present application, the charging coefficient includes but is not limited to: CTR, CVR, and ICVR.

Step 13: The service feature information of the extracted value-added service information is written into a preset universal dimension group to obtain a dimension group of the value-added service information.

In this step, the universal dimension group is a dimension space generated according to the service feature information included in the value-added service information group or the value-added service information creation. As an alternative embodiment, the generic dimension group is expressed as follows:

Dims(n)=<offer_ID, dim2, dim3,...,dimn>

among them,

The offer_ID is a value-added service information group identifier, and identifies a unique value-added service information group or a value-added service information creation. The value-added service information creation refers to a collection of information including a title, description, and image link of a value-added service information, which is a mandatory option;

Dim2~dimn are other dimensions;

n is the general dimension group dimension.

In the embodiment of the present application, other dimensions may be selected from user attributes, and/or value-added service information attributes, and/or information included in the context attributes, and the selected number of dimensions may be set according to actual needs.

As an optional embodiment, the universal dimension group includes all the service feature information in the value-added service information group or the value-added service information creation. For example, the following:

Gender corresponds to dim2, value dim2=v2; age corresponds to dim3, value dim3=v3; country corresponds to dim4, value dim4=v4; language corresponds to dim5, value dim5=v5; device type corresponds to dim6, value dim6=v6 Etc; the material size corresponds to dim7, the value dim7=v7 and so on. The value is a variable. For example, depending on the gender, you can set the male value to 1 and the female value to 0. You can also set it directly to gender. For example, set dim2=v2=male. For another example, depending on the age group, the juvenile's value can be set to 0, the youth value is 1, the middle-aged value is 2, and the old-aged value is 3, so that a common dimension of different values can be formed. group.

As another optional embodiment, if the number of all service feature information included in the value-added service information group or the value-added service information creation is 4, the dimension of the universal dimension group is 4, for example,

Dim s(4)=<offer_ID=billing type, dim2=sex, dim3=default, dim4=country, dim 5=default,

Dim 6=default, dim 7=material size>

For a certain value-added service information, if the default value is set to 0, the dimension group of the value-added service information may be:

Dims(4)=<CPC advertising, male, 0, China, 0,0, large size>.

Step 14: Query the mapping relationship between the pre-stored charging type correction coefficient centralized dimension group and the charging correction coefficient according to the charging type of the value-added service information, and obtain the charging correction coefficient of the dimension group mapping of the value-added service information;

In this step, in the charging type, the charging coefficient corresponding to the CPC is CTR, and the charging coefficient corresponding to CPA/CPI/CPS is CTR and CVR; or, ICVR. Therefore, in the embodiment of the present application, the CPC corresponds to a charging type correction coefficient set, and the CPA/CPI/CPS corresponds to another charging type correction coefficient set. The charging type correction coefficient is set, and the mapping relationship between the dimension groups of different values and the corresponding charging correction coefficient is included.

In the embodiment of the present application, as an optional embodiment, FIG. 2 is a schematic flowchart of obtaining a mapping relationship between a dimension group and a charging correction coefficient according to an embodiment of the present application. Referring to Figure 2, the process includes:

Step 21: Calculate an average estimated charging coefficient and an average historical charging coefficient according to the pre-stored display history log;

In this step, from the pre-stored presentation history log, the average estimated charging coefficient and the average historical charging coefficient of all value-added service information under each value of the common dimension group dims(n) are calculated.

In the embodiment of the present application, the average estimated charging coefficient includes: CTR average estimated charging coefficient, CVR average estimated charging coefficient, and ICVR average estimated charging coefficient; average historical charging coefficient includes: CTR average historical charging Coefficient, CVR average historical charging factor, and ICVR average historical charging factor, where

1) Calculate the CTR average estimated charging coefficient and the CTR average historical charging coefficient by using the following formula:

In the formula,

CTR _PREDICT (dims(n)) is the CTR average estimated charging factor;

CTR _REAL (dims(n)) is the CTR average historical charging factor;

C(dims(n)) represents a pre-stored set of presentation history logs, each history log containing an estimated eCPM corresponding to the behavior type of the value-added service information;

Ac(i) is the behavior type of the i-th value-added service information, wherein the behavior type includes: presentation, click, and installation, the presentation identifier is imp, the click identifier is clk, and the installation identifier is ins;

CTR _PREDICT (i) is the estimated eCPM value of the i-th value-added business information.

In the embodiment of the present application, each value-added service information corresponds to a common dimension group of values. In the calculation formula of the CTR average estimated charging coefficient, the numerator is the value-added service of all the value-added service information recorded, and the behavior type is displayed. The sum of the estimated eCPM values corresponding to the information, and the denominator is the sum of the value-added service information of all the value-added service information recorded;

In the calculation formula of the CTR average historical charging coefficient, the numerator is the sum of the value-added service information of the click type in all the value-added service information recorded, and the denominator is the recorded value-added service information, and the behavior type is displayed. The sum of the number of value-added business information.

In an embodiment of the present application, as an optional embodiment, the history log may select logs of the previous day or days, or may use the log of the hourly level, depending on the value-added service information log of each value of dims(n). How much is the amount.

2) Calculate the ICVR average estimated charging coefficient and the ICVR average historical charging coefficient by using the following formula:

In the formula,

ICVR _PREDICT (dims(n)) is the ICVR average estimated charging factor;

ICVR _REAL (dims(n)) is the ICVR average historical charging factor.

3) Calculate the CVR average estimated charging coefficient and the CVR average historical charging coefficient by using the following formula:

In the formula,

CVR _PREDICT (dims(n)) is the average estimated charging factor of CVR;

CVR _REAL (dims(n)) is the CVR average historical charging factor.

In the embodiment of the present application, each value-added service information corresponds to a CVR average estimated charging coefficient and a CVR average historical charging coefficient.

Step 22: Calculate a ratio of an average historical charging coefficient of the dimension group to an average estimated charging coefficient, obtain a charging correction coefficient, and store a mapping relationship between the dimension group and the charging correction coefficient.

In this step, the CTR correction coefficient, the ICVR correction coefficient, and the CVR correction coefficient are calculated by the following equations:

In the formula,

ADJUST _CTR (dims(n)) is the CTR correction factor;

ADJUST _ICVR (dims(n)) is the ICVR correction factor;

ADJUST _CVR (dims(n)) is the CVR correction factor.

In the embodiment of the present application, as an optional embodiment, the ADJUST value of the dims(n) various values (for example, the value of the gender and the value of the age, etc.) is stored in an offline file or a database.

In the embodiment of the present application, as an optional embodiment, if the charging type correction coefficient is concentrated, the mapping relationship between the dimension group and the charging correction coefficient, the charging correction coefficient of the dimension group mapping of the value-added service information is not queried. The billing correction coefficient can be set to 1, that is, processed by the prior art.

Step 15: Apply the charging coefficient and the charging correction coefficient to a preset charging adjustment formula, obtain a modified eCPM for each value-added service information, sort and push the sorted value-added industry according to the calculated corrected eCPM. Information.

In this step, it is assumed that the service feature information of the value-added service information is written into a preset universal dimension group, and the obtained dimension group is:

Dims(n)=(b,v ₂ ,...,v _n )

Calculate the CTR charge adjustment factor using the following formula:

CTR _ADJUST =CTR*ADJUST _CTR (b,v ₂ ,...,v _n ) ^α

among them,

CTR _ADJUST is the CTR charge adjustment factor;

0 ≤ α ≤ 1, which is a constant. The larger the value, the stronger the correction strength. In practical applications, α is the same for all value-added service information and all value-added service information delivery requests.

In the embodiment of the present application, the above formula reduces the current estimated CTR for the value-added service information whose historical real CTR is lower than the historical estimated CTR; otherwise, it increases the current estimated CTR.

Then, use the following formula to calculate the corrected eCPM:

eCPM _ADJUST-CPC =CTR _ADJUST *bid

In the formula,

eCPM _ADJUST-CPC is a modified eCPM based on CPC billing type.

Calculate the ICVR charge adjustment factor using the following formula:

ICVR _ADJUST =ICVR*ADJUST _ICVR (b,v ₂ ,...,v _n ) ^α

among them,

ICVR _ADJUST is the ICVR charging adjustment factor;

0 ≤ α ≤ 1, which is a constant.

Then, use the following formula to calculate the corrected eCPM:

eCPM _ADJUST-ICVR =ICVR _ADJUST *bid

In the formula,

eCPM _ADJUST-ICVR is a modified eCPM based on the first billing type of CPA/CPI/CPS.

Calculate the CVR charge adjustment factor using the following formula:

CVR _ADJUST =CVR*ADJUST _CVR (b,v ₂ ,...,v _n ) ^β

among them,

CVR _ADJUST is the CVR charging adjustment factor;

0 ≤ β ≤ 1, which is a constant. The larger the value, the stronger the correction force.

Then, use the following formula to calculate the corrected eCPM:

eCPM _ADJUST-CVR =CTR _ADJUST *CVR _ADJUST *bid

In the formula,

eCPM _ADJUST-CVR is a modified eCPM for the second billing type based on CPA/CPI/CPS.

In the embodiment of the present application, a plurality of value-added service information (the value-added service information of the top N bits before sorting) ranked first in the score may be selected and returned to the client/browser.

In an embodiment of the present application, as an optional embodiment, the method may further include:

The user behavior information of the pushed value-added service information is recorded in the history log.

In this step, by using the useful user behavior information generated in the above process, for example, including the presentation of the value-added service information, the user clicks the value-added service information, and the behavior type of the user installing the value-added service information is recorded in the history log, so that the user can continuously expand. Value-added business information model.

In the embodiment of the present application, the feature information included in the value-added service information delivery request is obtained by parsing the received value-added service information delivery request, and the candidate value-added service conforming to the feature information is selected from the preset value-added service information set. Information set; sequentially extracting service characteristic information of each value-added service information in the candidate value-added service information set, inputting the pre-trained value-added service information model, calculating a charging coefficient for each value-added service information; and extracting the value-added service information The service characteristic information is written into a preset universal dimension group to obtain a dimension group of the value-added service information; and according to the charging type of the value-added service information, the mapping of the pre-stored charging type correction coefficient centralized dimension group and the charging correction coefficient is queried. a relationship, obtaining a charging correction coefficient of the dimension group mapping of the value-added service information; applying the charging coefficient and the charging correction coefficient to a preset charging adjustment formula, and obtaining a corrected eCPM for each value-added service information, according to the calculation Get corrected eCPM for sorting and push sorting Value-added business information. In this way, according to the historical log of the value-added service information, the average estimated index value (CTR/CVR/ICVR) and the average true index value of each value-added service information are counted, and the deviation between the estimated index and the true index of each value-added service information is calculated. (Billing correction factor), when the deviation is used to sort the value-added service information online, the estimated index outputted by the value-added service information model is corrected, and the estimated index and the historical value-added service information through the value-added service information model are avoided. Large deviation of indicators In this case, the overall estimated eCPM of the value-added service information is more accurate, and the accuracy of the eCPM is improved, thereby optimizing the overall ranking effect of the value-added service information, and improving the push efficiency of the value-added service information; further, dynamically calculating the history based on the historical log statistics information. The CTR/CVR/ICVR correction factor has better timeliness; moreover, the set universal dimension group can support multiple dimensions when calculating the historical CTR/CVR/ICVR correction coefficient, which can better adapt to the value-added service information in different scenarios. CTR/CVR/ICVR distribution.

FIG. 3 is a schematic structural diagram of an apparatus for pushing value-added service information according to an embodiment of the present application. Referring to FIG. 3, the device includes: a candidate value-added service information collection module 31, a charging coefficient calculation module 32, a dimension group acquisition module 33, a charging correction coefficient query module 34, and a value-added service information pushing module 35, where

The candidate value-added service information collection module 31 is configured to parse the received value-added service information delivery request, obtain the feature information included in the value-added service information delivery request, and select the qualified information from the preset value-added service information set. Candidate value-added service information set;

In an embodiment of the present application, as an optional embodiment, the feature information includes, but is not limited to, one of a value-added service information group identifier, a user attribute, a value-added service information attribute, and a context attribute, or any combination thereof.

The charging coefficient calculation module 32 is configured to sequentially extract service characteristic information of each value-added service information in the candidate value-added service information set, input the pre-trained value-added service information model, and calculate a charging coefficient for each value-added service information;

In an embodiment of the present application, as an optional embodiment, the service feature information includes, but is not limited to, one of a user attribute, a value-added service information attribute, and a context attribute, or any combination thereof.

In the embodiment of the present application, the charging coefficient includes but is not limited to: CTR, CVR, and ICVR. among them,

For the value-added service information of the charging type CPC, the CTR is calculated; and for the value-added service information of the charging type CPA/CPI/CPS, the CTR and the CVR are calculated; or, the ICVR.

The dimension group obtaining module 33 is configured to write the service feature information of the extracted value-added service information into a preset universal dimension group to obtain a dimension group of the value-added service information;

In the embodiment of the present application, as an optional embodiment, the universal dimension group is expressed as follows:

Dims(n)=<offer_ID, dim2, dim3,...,dimn>

among them,

The offer_ID is a value-added service information group identifier, which is mandatory;

Dim2~dimn are other dimensions;

n is the general dimension group dimension.

In the embodiment of the present application, other dimensions may be selected from user attributes, and/or value-added service information attributes, and/or information included in the context attributes, and each included information corresponds to one dimension.

The billing correction coefficient querying module 34 is configured to query a mapping relationship between the pre-stored billing type correction coefficient concentration dimension group and the billing correction coefficient according to the billing type of the value-added service information, and obtain the dimension group mapping of the value-added service information. Billing correction factor;

In the embodiment of the present application, in the charging type, the charging coefficient corresponding to the CPC is CTR, and the charging coefficient corresponding to CPA/CPI/CPS is CTR and CVR; or ICVR. Therefore, in the embodiment of the present application, the CPC corresponds to a charging type correction coefficient set, and the CPA/CPI/CPS corresponds to another charging type correction coefficient set. The charging type correction coefficient is set, and the mapping relationship between the dimension groups of different values and the corresponding charging correction coefficient is included.

The value-added service information pushing module 35 is configured to apply the charging coefficient and the charging correction coefficient to a preset charging adjustment formula, and obtain a charging eCPM for each thousand times of value-added service information that is corrected for each value-added service information. The corrected eCPM is sorted according to the calculation and the sorted value-added service information is pushed.

In the embodiment of the present application, as an optional embodiment, the charging correction coefficient query module 34 includes: a calculating unit, a mapping relationship constructing unit, and a charging correction coefficient query unit (not shown), wherein

a calculating unit, configured to calculate an average estimated charging coefficient and an average historical charging coefficient according to the pre-stored presentation history log;

a mapping relationship construction unit, configured to calculate a ratio of an average historical charging coefficient of the dimensional group to an average estimated charging coefficient, and obtain a charging correction coefficient of the dimensional group mapping, and set the charging type correction coefficient set;

The charging correction coefficient querying unit is configured to query the mapping relationship construction unit according to the charging type of the value-added service information, and acquire the charging correction coefficient of the dimension group mapping of the value-added service information.

In an embodiment of the present application, as an optional embodiment, the average estimated charging coefficient includes: a CTR average estimated charging coefficient, a CVR average estimated charging coefficient, and an ICVR average estimated charging coefficient; The historical charging coefficient includes: CTR average historical charging coefficient, CVR average historical charging coefficient, and ICVR average historical charging coefficient.

In the embodiment of the present application, as an optional embodiment, the CTR average estimated charging coefficient and the CTR average historical charging coefficient are calculated by using the following formula:

In the formula,

CTR _PREDICT (dims(n)) is the CTR average estimated charging factor;

CTR _REAL (dims(n)) is the CTR average historical charging factor;

C(dims(n)) is a pre-stored set of presentation history logs;

Ac(i) is the behavior type of the i-th value-added service information, wherein the behavior type includes: presentation, click, and installation, the presentation identifier is imp, the click identifier is clk, and the installation identifier is ins;

CTR _PREDICT (i) is the estimated eCPM value of the i-th value-added business information.

Calculate the ICVR average estimated charging coefficient and the ICVR average historical charging coefficient by using the following formula:

In the formula,

ICVR _PREDICT (dims(n)) is the ICVR average estimated charging factor;

ICVR _REAL (dims(n)) is the ICVR average historical charging factor.

Calculate the CVR average estimated charging coefficient and the CVR average historical charging coefficient by using the following formula:

In the formula,

CVR _PREDICT (dims(n)) is the average estimated charging factor of CVR;

CVR _REAL (dims(n)) is the CVR average historical charging factor.

In an embodiment of the present application, as another optional embodiment, the charging correction coefficient includes: a CTR correction coefficient, an ICVR correction coefficient, and a CVR correction coefficient, and the CTR correction coefficient, the ICVR correction coefficient, and the CVR are respectively calculated by using the following formula: Correction factor:

In the formula,

ADJUST _CTR (dims(n)) is the CTR correction factor;

ADJUST _ICVR (dims(n)) is the ICVR correction factor;

ADJUST _CVR (dims(n)) is the CVR correction factor.

In the embodiment of the present application, as another optional embodiment, the modified eCPM is calculated by using the following formula:

eCPM _ADJUST-CPC =CTR _ADJUST *bid

CTR _ADJUST =CTR*ADJUST _CTR (b,v ₂ ,...,v _n ) ^α

among them,

eCPM _ADJUST-CPC is a modified eCPM based on CPC billing type;

CTR _ADJUST is the CTR charge adjustment factor;

0 ≤ α ≤ 1, which is a constant;

(b, v ₂ , . . . , v _n ) is a dimension group obtained by writing service characteristic information of the value-added service information into a preset common dimension group.

In the embodiment of the present application, as an optional embodiment, the modified eCPM is calculated by using the following formula:

eCPM _ADJUST-ICVR =ICVR _ADJUST *bid

ICVR _ADJUST =ICVR*ADJUST _ICVR (b,v ₂ ,...,v _n ) ^α

among them,

eCPM _ADJUST-ICVR is a modified eCPM based on the first charging type of CPA/CPI/CPS;

ICVR _ADJUST is the ICVR charging adjustment factor;

0 ≤ α ≤ 1, which is a constant;

(b, v ₂ , . . . , v _n ) is a dimension group obtained by writing service characteristic information of the value-added service information into a preset common dimension group.

In the embodiment of the present application, as another alternative embodiment, the modified eCPM is calculated by using the following formula:

eCPM _ADJUST-CVR =CTR _ADJUST *CVR _ADJUST *bid

CVR _ADJUST =CVR*ADJUST _CVR (b,v ₂ ,...,v _n ) ^β

among them,

eCPM _ADJUST-CVR is a modified eCPM based on CPA/CPI/CPS second charging type;

CVR _ADJUST is the CVR charging adjustment factor;

0 ≤ α ≤ 1, which is a constant;

(b, v ₂ , . . . , v _n ) is a dimension group obtained by writing service characteristic information of the value-added service information into a preset common dimension group.

In an embodiment of the present application, as an optional embodiment, the apparatus further includes:

The recording module 36 is configured to record user behavior information of the pushed value-added service information into the history log.

The embodiment of the present application further provides an electronic device, where the electronic device includes the device described in any of the foregoing embodiments.

FIG. 4 is a schematic structural diagram of an embodiment of an electronic device according to the present application, which may implement the process of the embodiment shown in FIG. 1-3 of the present application. As shown in FIG. 4, the electronic device may include: a housing 41, a processor 42, and a memory. 43. The circuit board 44 and the power supply circuit 45, wherein the circuit board 44 is disposed inside the space surrounded by the housing 41, the processor 42 and the memory 43 are disposed on the circuit board 44, and the power supply circuit 45 is used for the electronic device Each circuit or device is powered; the memory 43 is for storing executable program code; the processor 42 is operative to execute a program corresponding to the executable program code by reading the executable program code stored in the memory 43 for performing any of the foregoing embodiments The method of pushing value-added service information.

For the specific execution of the foregoing steps by the processor 42 and the steps performed by the processor 42 by running the executable program code, refer to the description of the embodiment shown in FIG. 1-3 of the present application, and details are not described herein again.

The electronic device exists in a variety of forms including, but not limited to:

(1) Mobile communication devices: These devices are characterized by mobile communication functions and are mainly aimed at providing voice and data communication. Such terminals include: smart phones (such as iPhone), multimedia phones, functional phones, and low-end phones.

(2) Ultra-mobile personal computer equipment: This type of equipment belongs to the category of personal computers, has computing and processing functions, and generally has mobile Internet access. Such terminals include: PDAs, MIDs, and UMPC devices, such as the iPad.

(3) Portable entertainment devices: These devices can display and play multimedia content. Such devices include: audio, video players (such as iPod), handheld game consoles, e-books, and smart toys and portable car navigation devices.

(4) Server: A device that provides computing services. The server consists of a processor, a hard disk, a memory, a system bus, etc. The server is similar to a general-purpose computer architecture, but because of the need to provide highly reliable services, processing power and stability High reliability in terms of reliability, security, scalability, and manageability.

(5) Other electronic devices with data interaction functions.

One of ordinary skill in the art can understand that all or part of the process of implementing the foregoing embodiments can be completed by a computer program to instruct related hardware, and the program can be stored in a computer readable storage medium. When executed, the flow of an embodiment of the methods as described above may be included. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

The foregoing is only a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto, and any change or replacement that can be easily conceived by those skilled in the art within the technical scope disclosed by the present application is All should be covered by the scope of this application. Therefore, the scope of protection of this application should be determined by the scope of protection of the claims.

Claims (23)

1. A method for pushing value-added service information, characterized in that the method comprises:

   Parsing the received value-added service information delivery request, obtaining the feature information included in the value-added service information delivery request, and selecting a candidate value-added service information set that meets the feature information from the preset value-added service information set;

   And sequentially extracting service characteristic information of each value-added service information in the candidate value-added service information set, inputting the pre-trained value-added service information model, and calculating a charging coefficient for each value-added service information;

   The service characteristic information of the extracted value-added service information is written into a preset universal dimension group to obtain a dimension group of the value-added service information;

   According to the charging type of the value-added service information, querying the mapping relationship between the pre-stored charging type correction coefficient centralized dimension group and the charging correction coefficient, and acquiring the charging correction coefficient of the dimensional group mapping of the value-added service information;

   Applying the charging coefficient and the charging correction coefficient to a preset charging adjustment formula, and obtaining a charging eCPM displayed per thousand value-added service information of each modified value-added service information, and sorting according to the calculated corrected eCPM and Push sorted value-added business information.
2. The method according to claim 1, wherein the obtaining the mapping relationship between the dimension group and the charging correction coefficient comprises:

   Calculating an average estimated charging coefficient and an average historical charging coefficient according to a pre-stored presentation history log;

   Calculating a ratio of an average historical charging coefficient of the dimensional group to an average estimated charging coefficient, obtaining a charging correction coefficient, and storing a mapping relationship between the dimensional group and the charging correction coefficient.
3. The method according to claim 2, wherein said average estimated charging coefficient comprises: CTR average estimated charging coefficient, CVR average estimated charging coefficient, and ICVR average estimated charging coefficient; said average The historical charging coefficient includes: CTR average historical charging coefficient, CVR average historical charging coefficient, and ICVR average historical charging coefficient.
4. The method according to claim 3, wherein the CTR average estimated charging coefficient and the CTR average historical charging coefficient are calculated by using the following formulas, respectively:

   

   

   In the formula,

   CTR _PREDICT (dims(n)) is the CTR average estimated charging factor;

   CTR _REAL (dims(n)) is the CTR average historical charging factor;

   C(dims(n)) is a pre-stored set of presentation history logs;

   Ac(i) is the behavior type of the i-th value-added service information, wherein the behavior type includes: presentation, click, and installation, the presentation identifier is imp, the click identifier is clk, and the installation identifier is ins;

   CTR _PREDICT (i) is the estimated eCPM value of the i-th value-added business information.
5. The method according to claim 3, wherein the ICVR average estimated charging coefficient and the ICVR average historical charging coefficient are calculated by using the following formula:

   

   

   In the formula,

   ICVR _PREDICT (dims(n)) is the ICVR average estimated charging factor;

   ICVR _REAL (dims(n)) is the ICVR average historical charging factor.
6. The method according to claim 3, wherein the CVR average estimated charging coefficient and the CVR average historical charging coefficient are calculated by using the following formula:

   

   

   In the formula,

   CVR _PREDICT (dims(n)) is the average estimated charging factor of CVR;

   CVR _REAL (dims(n)) is the CVR average historical charging factor.
7. The method according to any one of claims 4 to 6, wherein the charging correction coefficient comprises: a CTR correction coefficient, an ICVR correction coefficient, and a CVR correction coefficient, and the CTR correction coefficient and the ICVR are calculated by using the following formulas, respectively. Correction factor and CVR correction factor:

   

   

   

   In the formula,

   ADJUST _CTR (dims(n)) is the CTR correction factor;

   ADJUST _ICVR (dims(n)) is the ICVR correction factor;

   ADJUST _CVR (dims(n)) is the CVR correction factor.
8. The method according to any one of claims 4 to 6, wherein the modified eCPM is calculated using the following formula:

   eCPM _ADJUST-CPC =CTR _ADJUST *bid

   CTR _ADJUST =CTR*ADJUST _CTR (b,v ₂ ,...,v _n ) ^α

   among them,

   eCPM _ADJUST-CPC is a modified eCPM based on CPC billing type;

   CTR _ADJUST is the CTR charge adjustment factor;

   0 ≤ α ≤ 1, which is a constant;

   (b, v ₂ , . . . , v _n ) is a dimension group obtained by writing service characteristic information of the value-added service information into a preset common dimension group.
9. The method according to any one of claims 4 to 6, wherein the modified eCPM is calculated using the following formula:

   eCPM _ADJUST-ICVR =ICVR _ADJUST *bid

   ICVR _ADJUST =ICVR*ADJUST _ICVR (b,v ₂ ,...,v _n ) ^α

   among them,

   eCPM _ADJUST-ICVR is a modified eCPM based on the first charging type of CPA/CPI/CPS;

   ICVR _ADJUST is the ICVR charging adjustment factor;

   0 ≤ α ≤ 1, which is a constant;

   (b, v ₂ , . . . , v _n ) is a dimension group obtained by writing service characteristic information of the value-added service information into a preset common dimension group.
10. The method according to any one of claims 4 to 6, wherein the modified eCPM is calculated using the following formula:

    eCPM _ADJUST-CVR =CTR _ADJUST *CVR _ADJUST *bid

    CVR _ADJUST =CVR*ADJUST _CVR (b,v ₂ ,...,v _n ) ^β

    among them,

    eCPM _ADJUST-CVR is a modified eCPM based on CPA/CPI/CPS second charging type;

    CVR _ADJUST is the CVR charging adjustment factor;

    0 ≤ α ≤ 1, which is a constant;

    (b, v ₂ , . . . , v _n ) is a dimension group obtained by writing service characteristic information of the value-added service information into a preset common dimension group.
11. The method according to any one of claims 1 to 6, wherein the method further comprises:

    The user behavior information of the pushed value-added service information is recorded in the history log.
12. An apparatus for pushing value-added service information, the device comprising: a candidate value-added service information set acquisition module, a charging coefficient calculation module, a dimension group acquisition module, a charging correction coefficient query module, and a value-added service information push module, wherein

    The candidate value-added service information collection module is configured to parse the received value-added service information delivery request, obtain the feature information included in the value-added service information delivery request, and select the qualified information from the preset value-added service information set. Candidate value-added service information set;

    a charging coefficient calculation module, configured to sequentially extract service characteristic information of each value-added service information in the candidate value-added service information set, input the pre-trained value-added service information model, and calculate a charging coefficient for each value-added service information;

    a dimension group obtaining module, configured to write the service characteristic information of the extracted value-added service information into a preset universal dimension group, to obtain a dimension group of the value-added service information;

    The charging correction coefficient querying module is configured to query a mapping relationship between the pre-stored charging type correction coefficient centralized dimension group and the charging correction coefficient according to the charging type of the value-added service information, and obtain the dimensional group mapping of the value-added service information. Billing correction factor;

    And a value-added service information pushing module, configured to apply the charging coefficient and the charging correction coefficient to a preset charging adjustment formula, to obtain a charging eCPM for each thousand times of value-added service information that is expected to be corrected for each value-added service information, The corrected eCPM is sorted according to the calculation and the sorted value-added service information is pushed.
13. The device according to claim 12, wherein the charging correction coefficient querying module comprises: a calculating unit, a mapping relationship building unit, and a charging correction coefficient query unit, wherein

    a calculating unit, configured to calculate an average estimated charging coefficient and an average historical charging coefficient according to the pre-stored presentation history log;

    a mapping relationship construction unit, configured to calculate a ratio of an average historical charging coefficient of the dimensional group to an average estimated charging coefficient, and obtain a charging correction coefficient of the dimensional group mapping, and set the charging type correction coefficient set;

    The charging correction coefficient querying unit is configured to query the mapping relationship construction unit according to the charging type of the value-added service information, and acquire the charging correction coefficient of the dimension group mapping of the value-added service information.
14. The apparatus according to claim 13, wherein said average estimated charging coefficient comprises: a CTR average estimated charging coefficient, a CVR average estimated charging coefficient, and an ICVR average estimated charging coefficient; said average The historical charging coefficient includes: CTR average historical charging coefficient, CVR average historical charging coefficient, and ICVR average historical charging coefficient.
15. The apparatus according to claim 14, wherein said CTR average estimated charging coefficient and CTR average historical charging coefficient are calculated by the following equations, respectively:

    

    

    In the formula,

    CTR _PREDICT (dims(n)) is the CTR average estimated charging factor;

    CTR _REAL (dims(n)) is the CTR average historical charging factor;

    C(dims(n)) is a pre-stored set of presentation history logs;

    Ac(i) is the behavior type of the i-th value-added service information, wherein the behavior type includes: presentation, click, and installation, the presentation identifier is imp, the click identifier is clk, and the installation identifier is ins;

    CTR _PREDICT (i) is the estimated eCPM value of the i-th value-added business information.
16. The apparatus according to claim 14, wherein the ICVR average estimated charging coefficient and the ICVR average historical charging coefficient are calculated by using the following formula:

    

    

    In the formula,

    ICVR _PREDICT (dims(n)) is the ICVR average estimated charging factor;

    ICVR _REAL (dims(n)) is the ICVR average historical charging factor.
17. The apparatus according to claim 14, wherein the CVR average estimated charging coefficient and the CVR average historical charging coefficient are calculated by using the following formulas, respectively:

    

    

    In the formula,

    CVR _PREDICT (dims(n)) is the average estimated charging factor of CVR;

    CVR _REAL (dims(n)) is the CVR average historical charging factor.
18. The apparatus according to any one of claims 15 to 17, wherein the charging correction coefficient comprises: a CTR correction coefficient, an ICVR correction coefficient, and a CVR correction coefficient, and the CTR correction coefficient and the ICVR are calculated by the following equations, respectively. Correction factor and CVR correction factor:

    

    

    

    In the formula,

    ADJUST _CTR (dims(n)) is the CTR correction factor;

    ADJUST _ICVR (dims(n)) is the ICVR correction factor;

    ADJUST _CVR (dims(n)) is the CVR correction factor.
19. Apparatus according to any one of claims 15 to 17, wherein said modified eCPM is calculated using:

    eCPM _ADJUST-CPC =CTR _ADJUST *bid

    CTR _ADJUST =CTR*ADJUST _CTR (b,v ₂ ,...,v _n ) ^α

    among them,

    eCPM _ADJUST-CPC is a modified eCPM based on CPC billing type;

    CTR _ADJUST is the CTR charge adjustment factor;

    0 ≤ α ≤ 1, which is a constant;

    (b, v ₂ , . . . , v _n ) is a dimension group obtained by writing service characteristic information of the value-added service information into a preset common dimension group.
20. Apparatus according to any one of claims 15 to 17, wherein said modified eCPM is calculated using:

    eCPM _ADJUST-ICVR =ICVR _ADJUST *bid

    ICVR _ADJUST =ICVR*ADJUST _ICVR (b,v ₂ ,...,v _n ) ^α

    among them,

    eCPM _ADJUST-ICVR is a modified eCPM based on the first charging type of CPA/CPI/CPS;

    ICVR _ADJUST is the ICVR charging adjustment factor;

    0 ≤ α ≤ 1, which is a constant;

    (b, v ₂ , . . . , v _n ) is a dimension group obtained by writing service characteristic information of the value-added service information into a preset common dimension group.
21. Apparatus according to any one of claims 15 to 17, wherein said modified eCPM is calculated using:

    eCPM _ADJUST-CVR =CTR _ADJUST *CVR _ADJUST *bid

    CVR _ADJUST =CVR*ADJUST _CVR (b,v ₂ ,...,v _n ) ^β

    among them,

    eCPM _ADJUST-CVR is a modified eCPM based on CPA/CPI/CPS second charging type;

    CVR _ADJUST is the CVR charging adjustment factor;

    0 ≤ α ≤ 1, which is a constant;

    (b, v ₂ , . . . , v _n ) is a dimension group obtained by writing service characteristic information of the value-added service information into a preset common dimension group.
22. The device according to any one of claims 12 to 17, wherein the device further comprises:

    And a recording module, configured to record user behavior information of the pushed value-added service information into the history log.
23. An electronic device, comprising: a housing, a processor, a memory, a circuit board, and a power supply circuit, wherein the circuit board is disposed inside a space enclosed by the housing, and the processor and the memory are disposed in the circuit a power supply circuit for supplying power to each circuit or device of the electronic device; a memory for storing executable program code; and a processor for operating the executable program code by reading executable program code stored in the memory A program for performing the method of pushing value-added service information according to any of claims 1-11.

Images