CN107203892B - Method and device for pushing value added service information and electronic equipment - Google Patents
Method and device for pushing value added service information and electronic equipment Download PDFInfo
- Publication number
- CN107203892B CN107203892B CN201610157453.4A CN201610157453A CN107203892B CN 107203892 B CN107203892 B CN 107203892B CN 201610157453 A CN201610157453 A CN 201610157453A CN 107203892 B CN107203892 B CN 107203892B
- Authority
- CN
- China
- Prior art keywords
- added service
- service information
- ecpm
- value added
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06Q30/0283—Price estimation or determination
Landscapes
- Business, Economics & Management (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Marketing (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention discloses a method and a device for pushing value-added service information and electronic equipment. The method comprises the following steps: acquiring a candidate value-added service information set according to the value-added service information release request; calculating a corresponding charging coefficient by using the service characteristic information of each value added service information and the value added service information model; calculating eCPM according to the charging coefficient; writing the service characteristic information into a universal dimension group according to the extracted service characteristic information to obtain a dimension group of the value added service information; according to the charging type of the value added service information, inquiring the mapping relation between the dimension group and the eCPM correction coefficient, and acquiring the eCPM correction coefficient mapped by the dimension group of the value added service information; and applying the eCPM correction coefficient to an eCPM correction formula to obtain a corrected eCPM of each value added service information, sequencing according to the corrected eCPM obtained by calculation, and pushing the sequenced value added service information. By applying the method and the device, the pushing efficiency of the value added service information can be improved.
Description
Technical Field
The present invention relates to a value added service application technology, and in particular, to a method, an apparatus, and an electronic device for pushing value added service information.
Background
With the continuous development of computer communication and internet technology, electronic devices such as smart mobile phones, personal digital assistants, palm computers, notebook computers and the like are increasingly widely used. Many value added service operators have seen business opportunities for delivering value added service information based on electronic devices, for example, the value added service operators push the value added service information to mobile phones through a value added service platform provided by internet operators, and the value added service delivery method has the characteristics of low delivery cost, wide delivery range, easiness for users, high value added service delivery efficiency and the like.
On a value added service platform provided by an internet operator, the value added service platform can put in value added service information of various charging types based on various value added service charging types, wherein the charging types include but are not limited to: the manner of charging Per thousand presentations (CPM, Cost-Per-mill), the manner of charging Per Click (CPC, Cost-Per-Click), the manner of charging Per installation (CPI, Cost-Per-Install), the manner of charging Per Action (CPA, Cost-Per-Action), the manner of charging Per purchase (CPS, Cost-Per-Sale), the manner of charging Per Video playback (CPV, Cost-Per-Video), and the like.
Because the same value added service platform can put in value added service information corresponding to a plurality of applications once, the design levels of different value added service information are different, in order to measure the levels or the qualities of the value added service information of different charging types and determine which value added service information is arranged at the front position and displayed to a user, the value added service platform provides a method for displaying each value added service information to be pushed in a sequencing way, the value added service information of different charging types is respectively provided with corresponding planting coefficients w (bid _ type), wherein w (bid _ type) >0, after calculating the unified expected charge (eCPM, expected-Cost-Per-mile) displayed by each thousand times of the value added service information of each charging type, the eCPM is multiplied by the planting coefficients to obtain corrected eCPM, the value added service information is sequenced according to the height of the corrected eCPM, and sequenced according to the sequencing sequence, and displaying the value added service information to the user. And calculating eCPM by using different algorithms according to the value-added service information of different charging types. The flow of calculating eCPM is briefly described as follows:
step 1, training a corresponding value added service information model for calculating CTR/CVR/ICVR according to a historical log of each value added service information;
and 2, selecting a candidate value added service information set meeting the orientation conditions from the value added service information set according to the orientation conditions in the value added service information request, such as the orientation conditions of the country, sex, age and the like required to be released.
Step 3, for each value added service information in the candidate value added service information set, extracting user attributes (such as gender, age, country, language, equipment type and the like), value added service information attributes (such as material size, effect, conversion and industry classification) and context attributes (such as media and value added service information bits) of the value added service information, and generating model value added service characteristic information;
step 4, inputting the generated value added service characteristic information of the model into the trained corresponding value added service information model, and calculating the CTR/CVR/ICVR of the value added service information;
and 5, after the CTR/CVR/ICVR of the value added service information is calculated, calculating eCPM according to an eCPM calculation formula corresponding to the charging type of the value added service information, then sequencing each value added service information in the candidate value added service information set by using the product of the eCPM and the planting coefficient, and returning a plurality of the value added service information arranged at the top to the user.
In the data set used for model training, for value added service information data of different charging types, positive sample (purchase/click behavior) data and negative sample (no subsequent purchase/click display) data are seriously unevenly distributed (the former is far smaller than the latter), so that the value added service information CTR/CVR/ICVR estimated through the model has larger deviation from the historical real value added service information CTR/ICVR, the calculated difference of the score distribution of the eCPM is larger, the effect after the value added service information of different charging types is not good, so that the 'eCPM' of a certain charging type has a lower effect, the 'eCPM' of a certain charging type is lower than the 'eCPM' of another charging type, the 'eCPM' of the other charging type is not good, the calculated value added service information is not good, the eCPM is not high in the efficiency, the eCPM is not high in the influence of the value added service information, the other charging types, the factor is not high in advance, the influence of the calculation of the value added service information is not high, the PM is not high efficiency, the PM, the influence of the PM, the PM is not high PM, the PM, and the PM, the PM is not high PM, the PM, and the PM is.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method, an apparatus, and an electronic device for pushing value-added service information, so as to improve the pushing efficiency of the value-added service information.
In order to achieve the above purpose, the embodiment of the invention adopts the following technical scheme:
in a first aspect, an embodiment of the present invention provides a method for pushing value-added service information, including:
analyzing the received value added service information release request, acquiring characteristic information contained in the value added service information release request, and selecting a candidate value added service information set which accords with the characteristic information from a preset value added service information set;
extracting service characteristic information of each value added service information in the candidate value added service information set in sequence, inputting the service characteristic information into a value added service information model trained in advance, and calculating a charging coefficient aiming at each value added service information;
calculating expected charging eCPM displayed by the value added service information every thousand times according to the charging coefficient corresponding to the charging type of the value added service information;
writing the extracted service characteristic information of the value added service information into a preset general dimension group to obtain the dimension group of the value added service information;
inquiring a mapping relation between a dimensionality group and an eCPM correction coefficient in a prestored charging type eCPM correction coefficient set according to the charging type of the value added service information to obtain an eCPM correction coefficient mapped by the dimensionality group of the value added service information;
and applying the eCPM correction coefficient to a preset eCPM correction formula to obtain a corrected eCPM of each value-added service information, sequencing according to the corrected eCPM obtained by calculation, and pushing the sequenced value-added service information.
Optionally, obtaining the mapping relationship between the dimension group and the eCPM correction coefficient includes:
calculating average estimated eCPM according to a pre-stored display history log;
fixing values of other dimensions except the value added service information group identification in the general dimension group, traversing the value added service information group identification, and calculating an eCPM correction coefficient.
Optionally, the average estimated eCPM is calculated using the following equation:
in the formula,
eCPMHISTORY(dims (n)) is the average estimated eCPM;
c (dims (n)) is a presentation history log set;
ac (i) is the behavior type of the ith value added service information, wherein the behavior type comprises: displaying, clicking and installing, wherein the display identifier is imp, the click identifier is clk and the installation identifier is ins;
eCPMPREDICT(i) estimating an eCPM value for the ith value-added service information;
and # i | i ∈ C (dims (n)) ∩ ac (i) ═ imp } is the sum of the number of the presented value added service information in all the recorded value added service information.
Optionally, the eCPM correction coefficient is calculated by using the following formula:
in the formula,
delta(b，v2，K，vn) An eCPM correction coefficient;
bithe charging type is the ith type;
b is the designated charging type;
m is the charging type category contained in the dimension group;
v2～vnrespectively different service characteristic information in the value added service information group or value added service information originality.
Optionally, the method further includes:
and calculating a historical real eCPM according to a pre-stored display historical log.
Optionally, the historical true eCPM is calculated using the following formula:
in the formula,
eCPMREAL(dims (n)) is historical true eCPM;
TOTA L _ COST (dims (n)) is the total revenue corresponding to the pre-stored presentation history log;
TOTA L _ impress (dims (n)) is a total display amount corresponding to a pre-stored display history log.
Optionally, the eCPM correction coefficient is calculated by using the following formula:
in the formula,
delta(b，v2，...，vn) An eCPM correction coefficient;
bithe charging type is the ith type;
b is the designated charging type;
m is the charging type category contained in the dimension group;
v2～vnrespectively different service characteristic information in the value added service information group or value added service information originality.
Optionally, the corrected eCPM is calculated using the following equation:
in the formula,
delta(b，v2，...，vn) An eCPM correction coefficient;
b is the designated charging type;
v2～vndifferent service characteristic information in the value added service information group or value added service information originality respectively;
0 is equal to or less than α is equal to or less than 1 and is a constant.
Optionally, the method further includes:
and recording the user behavior information of the pushed value added service information into the history log.
In a second aspect, an embodiment of the present invention provides an apparatus for pushing value-added service information, including: a candidate value-added service information set acquisition module, a charging coefficient calculation module, an eCPM calculation module, a dimension group acquisition module, an eCPM correction coefficient query module and a value-added service information push module, wherein,
the candidate value added service information set acquisition module is used for analyzing the received value added service information release request, acquiring the characteristic information contained in the value added service information release request, and selecting a candidate value added service information set which accords with the characteristic information from a preset value added service information set;
the charging coefficient calculation module is used for sequentially extracting the service characteristic information of each value-added service information in the candidate value-added service information set, inputting the service characteristic information into a value-added service information model trained in advance, and calculating the charging coefficient aiming at each value-added service information;
the eCPM calculation module is used for calculating expected charging eCPM displayed by the value added service information every thousand times according to the charging coefficient corresponding to the charging type of the value added service information;
the dimensionality group acquisition module is used for writing the extracted service characteristic information of the value added service information into a preset general dimensionality group to obtain the dimensionality group of the value added service information;
the eCPM correction coefficient query module is used for querying a mapping relation between a dimension group and an eCPM correction coefficient in a prestored charging type eCPM correction coefficient set according to the charging type of the value added service information to obtain an eCPM correction coefficient mapped by the dimension group of the value added service information;
and the value added service information pushing module is used for applying the eCPM correction coefficient to a preset eCPM correction formula to obtain a corrected eCPM of each value added service information, sequencing the corrected eCPM according to the corrected eCPM obtained by calculation and pushing the sequenced value added service information.
Optionally, the eCPM correction coefficient query module includes: an average estimated eCPM calculation unit, a mapping relation construction unit and an eCPM correction coefficient query unit, wherein,
the average estimated eCPM calculating unit is used for calculating the average estimated eCPM according to a pre-stored display history log;
the mapping relation construction unit is used for fixing values of other dimensions in the general dimension group except the value added service information group identification, traversing the value added service information group identification, calculating an eCPM correction coefficient corresponding to the dimension group of the corresponding value added service information, and placing the eCPM correction coefficient into a charging type eCPM correction coefficient set;
and the eCPM correction coefficient query unit is used for querying the mapping relation construction unit according to the charging type of the value added service information and acquiring the eCPM correction coefficient mapped by the dimension group of the value added service information.
Optionally, the average estimated eCPM is calculated using the following equation:
in the formula,
eCPMHISTORY(dims (n)) is the average estimated eCPM;
c (dims (n)) is a presentation history log set;
ac (i) is the behavior type of the ith value added service information, wherein the behavior type comprises: displaying, clicking and installing, wherein the display identifier is imp, the click identifier is clk and the installation identifier is ins;
eCPMPREDICT(i) estimating an eCPM value for the ith value-added service information;
and in all the value added service information recorded by # { i | i ∈ C (dims (n))) ∩ ac (i) ═ imp }, the behavior type is the sum of the number of the displayed value added service information.
Optionally, the eCPM correction coefficient is calculated by using the following formula:
in the formula,
delta(b，v2，K，vn) An eCPM correction coefficient;
bithe charging type is the ith type;
b is the designated charging type;
m is the charging type category contained in the dimension group;
v2～vnrespectively for value added service information group or value added service information creationMeaning different traffic characteristic information.
Optionally, the eCPM correction coefficient query module further includes:
and the historical true eCPM calculating unit is used for calculating the historical true eCPM according to a pre-stored display historical log.
Optionally, the historical true eCPM is calculated using the following formula:
in the formula,
eCPMREAL(dims (n)) is historical true eCPM;
TOTA L _ COST (dims (n)) is the total revenue corresponding to the pre-stored presentation history log;
TOTA L _ impress (dims (n)) is a total display amount corresponding to a pre-stored display history log.
Optionally, the eCPM correction coefficient is calculated by using the following formula:
in the formula,
delta(b，v2，...，vn) An eCPM correction coefficient;
bithe charging type is the ith type;
b is the designated charging type;
m is the charging type category contained in the dimension group;
v2～vnrespectively different service characteristic information in the value added service information group or value added service information originality.
Optionally, the corrected eCPM is calculated using the following equation:
in the formula,
delta(b，v2，...，vn) An eCPM correction coefficient;
b is the designated charging type;
v2～vndifferent service characteristic information in the value added service information group or value added service information originality respectively;
0 is equal to or less than α is equal to or less than 1 and is a constant.
Optionally, the apparatus further comprises:
and the recording module is used for recording the user behavior information of the pushed value-added service information into the history log.
In a third aspect, an embodiment of the present invention provides an electronic device, where the electronic device includes: the device comprises a shell, a processor, a memory, a circuit board and a power circuit, wherein the circuit board is arranged in a space enclosed by the shell, and the processor and the memory are arranged on the circuit board; a power supply circuit for supplying power to each circuit or device of the electronic apparatus; the memory is used for storing executable program codes; the processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, and is configured to execute any one of the foregoing methods for pushing value-added service information.
The method, the device and the electronic equipment for pushing the value added service information analyze a received value added service information release request, acquire characteristic information contained in the value added service information release request, and select a candidate value added service information set which accords with the characteristic information from a preset value added service information set; extracting service characteristic information of each value-added service information in the candidate value-added service information set in sequence, inputting the service characteristic information into a value-added service information model trained in advance, and calculating a charging coefficient for each value-added service information; calculating expected charge displayed by the value added service information every thousand times according to a charge coefficient corresponding to the charging type of the value added service information; writing the service characteristic information of the extracted value added service information into a preset general dimension group to obtain a dimension group of the value added service information; inquiring a prestored charging type eCPM correction coefficient set and a mapping relation between a dimension group and an eCPM correction coefficient according to the charging type of the value added service information to obtain an eCPM correction coefficient mapped by the dimension group of the value added service information; and applying the eCPM correction coefficient to a preset eCPM correction formula to obtain a corrected eCPM of each value-added service information, sequencing according to the corrected eCPM obtained by calculation, and pushing the sequenced value-added service information. Therefore, according to the estimated eCPM value recorded in the historical log of the value added service information, the eCPM correction coefficient of the estimated eCPM of the value added service information of different charging types is calculated, the current estimated eCPM value is adjusted, the eCPM difference among the value added service information of different charging types can be effectively reduced, the total estimated eCPM of the value added service information is more accurate, the integral ordering effect of the value added service information is optimized, and the pushing efficiency of the value added service information is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a method for pushing value-added service information according to an embodiment of the present invention;
fig. 2 is a schematic flow chart illustrating a process of obtaining a mapping relationship between a dimension group and an eCPM correction coefficient according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a device for pushing value-added service information according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an embodiment of an electronic device according to the present invention.
Detailed Description
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
It should be understood that the described embodiments are only some embodiments of the invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a schematic flow chart of a device for pushing value added service information according to an embodiment of the present invention. Referring to fig. 1, the method includes:
in this step, as an optional embodiment, the feature information includes but is not limited to: one or any combination of the value added service information group identification, the user attribute, the value added service information attribute and the context attribute, wherein,
the value added service information group is also called value added service information series, and refers to a group of value added service information with the same budget, charging type, bid price, release time period and directional condition.
User attributes include, but are not limited to: gender, age, country, language, device type, etc.;
the value added service information attributes include, but are not limited to: material size, effect class, conversion class and industry class;
contextual attributes include, but are not limited to: media, value added service information bits.
In the embodiment of the invention, a user or a value added service operator can initiate a value added service information release request through a client/browser, wherein the value added service information release request comprises characteristic information such as user attributes, context information and the like.
In this embodiment of the present invention, as an optional embodiment, the feature information may be an orientation condition including a user attribute.
in this step, for each value added service information in the candidate value added service information set, extracting the service feature information of the value added service information, including: the method comprises the steps of generating model value-added service characteristic information by one or any combination of user attributes (such as gender, age, country, language, equipment type and the like), value-added service information attributes (such as material size, effect type, conversion type and industry classification) and context attributes (such as media and value-added service information bits), inputting the generated model value-added service characteristic information into a value-added service information model trained in advance, and calculating a charging coefficient aiming at each value-added service information. For example, for the value added service information with the charging type of CPC, the CTR is calculated by inputting the service characteristic information of the value added service information into a value added service information model containing the CPC value added service information; for the value added service information with the charging type of CPA/CPI/CPS, the CTR and the CVR are calculated by inputting the service characteristic information of the value added service information into a value added service information model containing the CPA/CPI/CPS value added service information; alternatively, ICVR.
In the embodiment of the present invention, the service feature information includes but is not limited to: one or any combination of the user attribute, the value added service information attribute and the context attribute.
In the embodiment of the present invention, the charging coefficient includes but is not limited to: CTR, CVR, and ICVR.
in this step, for the value added service information with the charging type of CPC, the expected charge exhibited by the value added service information every thousand times is calculated by using the following formula:
eCPM＝CTR*bid
in the formula,
eCPM is the expected charge for each thousand times of value-added service information display;
the CTR is Click-Through-Rate (Click-Through-Rate), namely the ratio of the Click quantity of the value-added service information to the display quantity of the value-added service information;
bid is shown for each thousand times by the operator.
For the value added service information with the charging type of CPA/CPI/CPS, calculating the expected charge displayed by the value added service information every thousand times by using the following formula:
eCPM＝CTR*CVR*bid
in the formula,
the CVR is a Conversion-Rate (Conversion-Rate), which is a ratio of a purchase/installation amount generated by the value added service information to a click Rate of the value added service information.
Or,
eCPM＝ICVR*bid
in the formula,
the ICVR is an installation-Conversion Rate (Install-Conversion-Rate), which is a ratio of a purchase/installation amount generated by the value added service information to a value added service information display amount.
in this step, the general dimension group is a dimension space generated according to the value added service information group or the service characteristic information included in the value added service information creative idea. As an alternative embodiment, the general set of dimensions is represented as follows:
dims(n)＝<offer_ID，dim2，dim3，…，dimn>
wherein,
the offer _ ID is a value added service information group identifier which identifies a unique value added service information group or value added service information creative, wherein the value added service information creative refers to an information set which contains a title, description and picture link of value added service information and is a necessary option;
dim 2-dim are other dimensions;
n is the general dimension set dimension.
In the embodiment of the invention, other dimensions can be selected from the user attributes and/or the value added service information attributes and/or the information contained in the context attributes, and the selected dimension number can be set according to actual needs.
As an alternative embodiment, the common dimension group includes all service feature information in the value added service information group or value added service information creative, for example, it may be set as follows:
sex corresponds to dim2, and the value dim2 is v 2; age corresponds to dim3, and the value dim3 is v 3; the country corresponds to dim4, and the value dim4 is v 4; the language corresponds to dim5, and the value dim5 is v 5; the equipment type corresponds to dim6, and the value dim6 is v 6; the material size corresponds to dim7, and the value dim7 is v7 and the like. The value is a variable, for example, depending on the sex, the value for male may be set to 1, and the value for female may be set to O, or the value may be directly set to the sex, for example, set dim2 ═ v2 ═ male. For another example, according to the difference of age groups, the value of teenagers can be set to 0, the value of young adults can be set to 1, the value of middle-aged adults can be set to 2, the value of old people can be set to 3, and the like, so that a universal dimension group with different values can be formed.
As another alternative, if the number of all service characteristic information included in the value added service information group or value added service information creative is 4, the dimension of the universal dimension group is 4, for example,
billing type, dim2 gender, dim3, dim4, country, dim5, dim6, dim7 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 ad, male, 0, china, 0, 0, large size >.
in this embodiment of the present invention, as an optional embodiment, fig. 2 is a schematic flowchart of a process of obtaining a mapping relationship between a dimension group and an eCPM correction coefficient according to an embodiment of the present invention. Referring to fig. 2, the process includes:
in this step, an average pre-estimated eCPM under each value of the universal dimension group dims (n) is calculated from the pre-stored display history log of each value-added service information group.
In the embodiment of the invention, the average estimated eCPM is calculated by using the following formula:
in the formula,
eCPMHISTORY(dims (n)) is the average estimated eCPM;
c (dims (n)) is a set of displayed historical logs, and each historical log comprises a real-time estimated eCPM of the behavior type of the value-added service information;
ac (i) is the behavior type of the ith value added service information, wherein the behavior type comprises: displaying, clicking and installing, wherein the display identifier is imp, the click identifier is clk and the installation identifier is ins;
eCPMPREDICT(i) estimating an eCPM value for the ith value-added service information;
and # i | i ∈ C (dims (n)) ∩ ac (i) ═ imp } is the sum of the number of the presented value added service information in all the recorded value added service information.
In the embodiment of the invention, each value-added service information corresponds to a value-taking general dimension group, and the general dimension group contains value-added service information of various charging types. In the above calculation formula, the numerator is the sum of real-time estimated eCPM values of the presented value-added service information in all the value-added service information recorded, and the denominator is the sum of the number of the presented value-added service information in all the value-added service information recorded.
In the embodiment of the present invention, as an optional embodiment, the history log may be a log of the previous day or multiple days, or an hourly log, depending on the amount of the value-added service information log of each value of dims (n).
In this embodiment of the present invention, as an optional embodiment, the method may further include:
and calculating a historical real eCPM according to a pre-stored display historical log.
In this step, the historical true eCPM is calculated using the following formula:
in the formula,
eCPMREAL(dims (n)) is historical true eCPM;
TOTA L _ COST (dims (n)) is the total revenue corresponding to the pre-stored presentation history log;
TOTA L _ impress (dims (n)) is a total display amount corresponding to a pre-stored display history log.
In the embodiment of the invention, the eCPM correction coefficient can be calculated according to the historical real eCPM in the following process.
And step 22, fixing values of other dimensions in the general dimension group except the value-added service information group identification, traversing the value-added service information group identification, and calculating an eCPM correction coefficient.
In this step, the values of dim2, … and dim are fixed, that is, dim2 ═ v2, dim3 ═ v3 and dim ═ v. If a certain presentation history log does not contain the characteristics of a certain dimension, the presentation history log is set as the default value of the certain dimension, namely, a default value is predefined for the characteristics corresponding to each dimension in the general dimension group. For example, if there are two pieces of value added service information, the first value added service information only includes gender 1, country 1 and material size 1, the second value added service information only includes gender 2, age 2, language 2 and device type 2, and for the first value added service information, the dimension group of the value added service information is: (gender 1, country 1, material size 1, default age, default language, default equipment, …); for the second value added service information, the dimension group of the value added service information is as follows: (gender 2, default country, default material size, age 2, language 2, device 2, …).
In the embodiment of the invention, because the different value added service information releasing requests contain different characteristic information, the corresponding eCPM correction coefficients of the same value added service information in the different value added service information releasing requests can also be different.
For each value b of the charging type, calculating an eCPM correction coefficient by using the following formula:
in the formula,
de/ta(b，v2，K，vn) For the eCPM correction coefficient, the eCPM correction coefficients corresponding to the same value added service information can be different under different value added service information release requests;
bithe charging type is the ith type;
b is the designated charging type;
m is the charging type category contained in the dimension group;
v2～vnrespectively different service characteristic information in the value added service information group or value added service information originality.
In this embodiment of the present invention, as another optional embodiment, the eCPM correction coefficient may also be calculated by using the following formula:
in the formula,
delta(b，v2，...，vn) An eCPM correction coefficient;
bithe charging type is the ith type;
b is the designated charging type;
m is the charging type category contained in the dimension group;
v2～vnrespectively different service characteristic information in the value added service information group or value added service information originality.
In the embodiment of the present invention, as an optional embodiment, the delta values under various combinations of values of dims (n) may be stored in an offline file or a database.
And step 16, applying the eCPM correction coefficient to a preset eCPM correction formula to obtain a corrected eCPM of each value added service information, sequencing according to the corrected eCPM obtained by calculation, and pushing the sequenced value added service information.
In this step, when performing online scoring, for a value added service information push request and corresponding candidate value added service information, the value bid _ type ═ b, dim2 ═ v2, dim3 ═ v3, and dim ═ vn of each dimension in the dimension group dims (n) corresponding to each value added service information in the value added service information push request are analyzed first, and eCPM is calculated. Then, inquiring a charging type eCPM correction coefficient set to find delta (b, v)2，...，vn)。
In the embodiment of the invention, the corrected eCPM is calculated by using the following formula:
in the formula,
delta(b，v2，...，vn) An eCPM correction coefficient;
b is the designated charging type;
v2～vndifferent service characteristic information in the value added service information group or value added service information originality respectively;
the value is equal to or greater than 0 and equal to or less than α and equal to or less than 1, the value is larger, the correction strength is stronger, and in practical application, α is the same for all value-added service information and all value-added service information release requests.
In the embodiment of the invention, the formula can improve the current estimated eCPM for the value-added service information with lower historical estimated eCPM; otherwise, the current estimated eCPM is reduced.
In the embodiment of the invention, a plurality of pieces of value added service information (the value added service information with the top N bits of the sequence) with scores arranged at the top can be selected and returned to the client/browser.
In this embodiment of the present invention, as an optional embodiment, the method may further include:
and recording the user behavior information of the pushed value added service information into the history log.
In this step, the value added service information is clicked by the user through the useful user behavior information generated in the above-mentioned process, for example, the value added service information is displayed, and the value added service information installed by the user is recorded in the history log, so that the value added service information model can be continuously expanded.
In the embodiment of the invention, the characteristic information contained in the value added service information putting request is obtained by analyzing the received value added service information putting request, and a candidate value added service information set which accords with the characteristic information is selected from a preset value added service information set; extracting service characteristic information of each value-added service information in the candidate value-added service information set in sequence, inputting the service characteristic information into a value-added service information model trained in advance, and calculating a charging coefficient for each value-added service information; calculating expected charge displayed by the value added service information every thousand times according to a charge coefficient corresponding to the charging type of the value added service information; writing the service characteristic information of the extracted value added service information into a preset general dimension group to obtain a dimension group of the value added service information; inquiring a prestored charging type eCPM correction coefficient set and a mapping relation between a dimension group and an eCPM correction coefficient according to the charging type of the value added service information to obtain an eCPM correction coefficient mapped by the dimension group of the value added service information; and applying the eCPM correction coefficient to a preset eCPM correction formula to obtain a corrected eCPM of each value-added service information, sequencing according to the corrected eCPM obtained by calculation, and pushing the sequenced value-added service information. Thus, according to the estimated eCPM value recorded in the historical log of the value added service information, calculating the deviation (eCPM correction coefficient) of the historical distribution of the estimated eCPM of the value added service information of different charging types, and adjusting the current estimated eCPM value on the line by using the deviation to reduce the eCPM difference between the value added service information of different charging types, so that the historical eCPM factor of the value added service information is considered during sorting, so that the value added service information of different charging types can compete more fairly, the accuracy of the ordered eCPM is improved, the total estimated eCPM of the value added service information is more accurate, the accuracy of the eCPM is improved, the overall sorting effect of the value added service information is optimized, and the pushing efficiency of the value added service information is improved; furthermore, according to the historical log, a historical eCPM correction coefficient is dynamically calculated, and the timeliness is good; moreover, the set general dimension group can support multiple dimensions, and can better adapt to the eCPM distribution of the value-added service information under different situations.
Fig. 3 is a schematic structural diagram of a device for pushing value-added service information according to an embodiment of the present invention. Referring to fig. 3, the apparatus includes: a candidate value added service information set acquisition module 31, a charging coefficient calculation module 32, an eCPM calculation module 33, a dimension group acquisition module 34, an eCPM correction coefficient query module 35, and a value added service information push module 36, wherein,
a candidate value-added service information set acquisition module 31, configured to analyze the received value-added service information delivery request, acquire feature information included in the value-added service information delivery request, and select a candidate value-added service information set that matches the feature information from a preset value-added service information set;
in the embodiment of the present invention, as an optional embodiment, the feature information includes but is not limited to: one or any combination of the value added service information group identification, the user attribute, the value added service information attribute and the context attribute.
A charging coefficient calculation module 32, configured to sequentially extract service feature information of each value-added service information in the candidate value-added service information set, input the service feature information into a value-added service information model trained in advance, and calculate a charging coefficient for each value-added service information;
in this embodiment of the present invention, as an optional embodiment, the service feature information includes, but is not limited to: one or any combination of the user attribute, the value added service information attribute and the context attribute.
In the embodiment of the present invention, the charging coefficient includes but is not limited to: CTR, CVR, and ICVR. Wherein,
calculating CTR for the value added service information with the charging type of CPC; calculating CTR and CVR for value added service information with CPA/CPI/CPS charging type; alternatively, ICVR.
The eCPM calculation module 33 is used for calculating expected charging eCPM displayed by the value added service information every thousand times according to the charging coefficient corresponding to the charging type of the value added service information;
in the embodiment of the invention, for the value added service information with the charging type of CPC, the expected charge displayed by the value added service information every thousand times is calculated by using the following formula:
eCPM＝CTR*bid
in the formula,
eCPM is the expected charge for each thousand times of value-added service information display;
CTR is click rate;
bid is shown for each thousand times by the operator.
For the value added service information with the charging type of CPA/CPI/CPS, calculating the expected charge displayed by the value added service information every thousand times by using the following formula:
eCPM＝CTR*CVR*bid
in the formula,
CVR is the conversion.
Or,
eCPM＝ICVR*bid
in the formula,
ICVR is the installed conversion.
The dimension group acquisition module 34 is configured to write the extracted service feature information of the value added service information into a preset general dimension group, so as to obtain a dimension group of the value added service information;
in the embodiment of the present invention, as an optional embodiment, the general dimension group is represented as follows:
dims(n)＝<offer_ID，dim2，dim3，…，dimn>
wherein,
the offer _ ID is a value added service information group identifier and is a necessary option;
dim 2-dim are other dimensions;
n is the general dimension set dimension.
In the embodiment of the present invention, the other dimensions may be selected from the information included in the user attribute, and/or the value added service information attribute, and/or the context attribute, and each included information corresponds to one dimension.
The eCPM correction coefficient query module 35 is configured to query, according to the charging type of the value added service information, a mapping relationship between a dimension group and an eCPM correction coefficient in a prestored charging type eCPM correction coefficient set, and obtain an eCPM correction coefficient mapped by the dimension group of the value added service information;
in this embodiment of the present invention, as an optional embodiment, the eCPM correction coefficient query module 35 includes: an average estimated eCPM calculation unit, a mapping construction unit, and an eCPM correction coefficient search unit (not shown), wherein,
the average estimated eCPM calculating unit is used for calculating the average estimated eCPM according to a pre-stored display history log;
the mapping relation construction unit is used for fixing values of other dimensions in the general dimension group except the value added service information group identification, traversing the value added service information group identification, calculating an eCPM correction coefficient corresponding to the dimension group of the corresponding value added service information, and placing the eCPM correction coefficient into a charging type eCPM correction coefficient set;
and the eCPM correction coefficient query unit is used for querying the mapping relation construction unit according to the charging type of the value added service information and acquiring the eCPM correction coefficient mapped by the dimension group of the value added service information.
In this embodiment of the present invention, as an optional embodiment, the average estimated eCPM is calculated by using the following formula:
in the formula,
eCPMHISTORY(dims (n)) is the average estimated eCPM;
c (dims (n)) is a presentation history log set;
ac (i) is the behavior type of the ith value added service information, wherein the behavior type comprises: displaying, clicking and installing, wherein the display identifier is imp, the click identifier is clk and the installation identifier is ins;
eCPMPREDICT(i) the behavior type of all the value added service information recorded in the value added service information item is the value added service information item shown in the (i) th value added service information item, the (i) i ∈ C (dims (n)) ∩ ac (i) imp)The sum of the numbers.
Accordingly, the eCPM correction factor is calculated using the following equation:
in the formula,
delta(b，v2，K，vn) An eCPM correction coefficient;
bithe charging type is the ith type;
b is the designated charging type;
m is the charging type category contained in the dimension group;
v2～vnrespectively different service characteristic information in the value added service information group or value added service information originality.
As another alternative embodiment, the eCPM correction coefficient query module 35 may further include:
and the historical true eCPM calculating unit is used for calculating the historical true eCPM according to a pre-stored display historical log.
In this embodiment of the present invention, as an optional embodiment, the historical true eCPM is calculated by using the following formula:
in the formula,
eCPMREAL(dims (n)) is historical true eCPM;
TOTA L _ COST (dims (n)) is the total revenue corresponding to the pre-stored presentation history log;
TOTA L _ impress (dims (n)) is a total display amount corresponding to a pre-stored display history log.
Accordingly, the eCPM correction factor is calculated using the following equation:
in the formula,
delta(b，v2，...，vn) An eCPM correction coefficient;
bithe charging type is the ith type;
b is the designated charging type;
m is the charging type category contained in the dimension group;
v2～vnrespectively different service characteristic information in the value added service information group or value added service information originality.
The value added service information pushing module 36 is configured to apply the eCPM correction coefficient to a preset eCPM correction formula to obtain a corrected eCPM of each value added service information, sort the corrected eCPM according to the corrected eCPM obtained through calculation, and push the sorted value added service information.
In this embodiment of the present invention, as an optional embodiment, the corrected eCPM is calculated by using the following formula:
delta(b，v2，...，vn) An eCPM correction coefficient;
b is the designated charging type;
v2～vndifferent service characteristic information in the value added service information group or value added service information originality respectively;
0 is equal to or less than α is equal to or less than 1 and is a constant.
In this embodiment of the present invention, as an optional embodiment, the apparatus further includes:
the recording module 37 is configured to record the user behavior information of the pushed value-added service information into the history log.
The embodiment of the invention also provides electronic equipment, and the electronic equipment comprises the device in any one of the embodiments.
Fig. 4 is a schematic structural diagram of an embodiment of an electronic device of the present invention, which can implement the processes of the embodiments shown in fig. 1 to 3 of the present invention, and as shown in fig. 4, the electronic device may include: the device comprises a shell 41, a processor 42, a memory 43, a circuit board 44 and a power circuit 45, wherein the circuit board 44 is arranged inside a space enclosed by the shell 41, and the processor 42 and the memory 43 are arranged on the circuit board 44; a power supply circuit 45 for supplying power to each circuit or device of the electronic apparatus; the memory 43 is used for storing executable program code; the processor 42 executes a program corresponding to the executable program code by reading the executable program code stored in the memory 43, and is configured to perform the method for pushing value added service information according to any of the foregoing embodiments.
The specific execution process of the above steps by the processor 42 and the steps further executed by the processor 42 by running the executable program code may refer to the description of the embodiment shown in fig. 1 to 3 of the present invention, and are not described herein again.
The electronic device exists in a variety of forms, including but not limited to:
(1) a mobile communication device: such devices are characterized by mobile communications capabilities and are primarily targeted at providing voice, data communications. Such terminals include: smart phones (e.g., iphones), multimedia phones, functional phones, and low-end phones, among others.
(2) Ultra mobile personal computer device: the equipment belongs to the category of personal computers, has calculation and processing functions and generally has the characteristic of mobile internet access. Such terminals include: PDA, MID, and UMPC devices, etc., such as ipads.
(3) A portable entertainment device: such devices can display and play multimedia content. This type of device comprises: audio, video players (e.g., ipods), handheld game consoles, electronic books, and smart toys and portable car navigation devices.
(4) A server: the device for providing the computing service comprises a processor, a hard disk, a memory, a system bus and the like, and the server is similar to a general computer architecture, but has higher requirements on processing capacity, stability, reliability, safety, expandability, manageability and the like because of the need of providing high-reliability service.
(5) And other electronic equipment with data interaction function.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
The above description is only for the specific embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (19)
1. A method for pushing value added service information is characterized in that the method comprises the following steps:
analyzing the received value added service information release request, acquiring characteristic information contained in the value added service information release request, and selecting a candidate value added service information set which accords with the characteristic information from a preset value added service information set;
extracting service characteristic information of each value added service information in the candidate value added service information set in sequence, inputting the service characteristic information into a value added service information model trained in advance, and calculating a charging coefficient aiming at each value added service information;
calculating expected charging eCPM displayed by the value added service information every thousand times according to the charging coefficient corresponding to the charging type of the value added service information;
writing the extracted service characteristic information of the value added service information into a preset general dimension group to obtain the dimension group of the value added service information;
inquiring a mapping relation between a dimensionality group and an eCPM correction coefficient in a prestored charging type eCPM correction coefficient set according to the charging type of the value added service information to obtain an eCPM correction coefficient mapped by the dimensionality group of the value added service information;
and applying the eCPM correction coefficient to a preset eCPM correction formula to obtain a corrected eCPM of each value-added service information, sequencing according to the corrected eCPM obtained by calculation, and pushing the sequenced value-added service information.
2. The method of claim 1, wherein obtaining the mapping relationship between the dimension group and the eCPM correction coefficient comprises:
calculating average estimated eCPM according to a pre-stored display history log;
fixing values of other dimensions except the value added service information group identification in the general dimension group, traversing the value added service information group identification, and calculating an eCPM correction coefficient.
3. The method of claim 2, wherein the average estimated eCPM is calculated using the following equation:
in the formula,
eCPMHISTORY(dims (n)) is the average estimated eCPM;
c (dims (n)) is a presentation history log set;
ac (i) is the behavior type of the ith value added service information, wherein the behavior type comprises: displaying, clicking and installing, wherein the display identifier is imp, the click identifier is clk and the installation identifier is ins;
eCPMPREDICT(i) estimating an eCPM value for the ith value-added service information;
and # i | i ∈ C (dims (n)) ∩ ac (i) ═ imp } is the sum of the number of the presented value added service information in all the recorded value added service information.
4. The method of claim 3, wherein the eCPM correction factor is calculated using the following equation:
in the formula,
delta(b，v2，...，vn) An eCPM correction coefficient;
bithe charging type is the ith type;
b is the designated charging type;
m is the charging type category contained in the dimension group;
v2～vnrespectively different service characteristic information in the value added service information group or value added service information originality.
5. The method of claim 2, further comprising:
and calculating a historical real eCPM according to a pre-stored display historical log.
6. The method of claim 5, wherein the historical true eCPM is calculated using the following equation:
in the formula,
eCPMREAL(dims (n)) is historical true eCPM;
TOTA L _ COST (dims (n)) is the total revenue corresponding to the pre-stored presentation history log;
TOTA L _ impress (dims (n)) is a total display amount corresponding to a pre-stored display history log.
7. The method of claim 6, wherein the eCPM correction factor is calculated using the following equation:
in the formula,
delta(b，v2，...，vn) An eCPM correction coefficient;
bithe charging type is the ith type;
b is the designated charging type;
m is the charging type category contained in the dimension group;
v2～vnrespectively different service characteristic information in the value added service information group or value added service information originality.
8. The method according to any of claims 1 to 7, characterized in that said modified eCPM is calculated using the following formula:
in the formula,
delta(b，v2，...，vn) An eCPM correction coefficient;
b is the designated charging type;
v2～vndifferent service characteristic information in the value added service information group or value added service information originality respectively;
0 is equal to or less than α is equal to or less than 1 and is a constant.
9. The method according to any one of claims 1 to 7, further comprising:
and recording the user behavior information of the pushed value added service information into a historical log.
10. An apparatus for pushing value added service information, the apparatus comprising: a candidate value-added service information set acquisition module, a charging coefficient calculation module, an eCPM calculation module, a dimension group acquisition module, an eCPM correction coefficient query module and a value-added service information push module, wherein,
the candidate value added service information set acquisition module is used for analyzing the received value added service information release request, acquiring the characteristic information contained in the value added service information release request, and selecting a candidate value added service information set which accords with the characteristic information from a preset value added service information set;
the charging coefficient calculation module is used for sequentially extracting the service characteristic information of each value-added service information in the candidate value-added service information set, inputting the service characteristic information into a value-added service information model trained in advance, and calculating the charging coefficient aiming at each value-added service information;
the eCPM calculation module is used for calculating expected charging eCPM displayed by the value added service information every thousand times according to the charging coefficient corresponding to the charging type of the value added service information;
the dimensionality group acquisition module is used for writing the extracted service characteristic information of the value added service information into a preset general dimensionality group to obtain the dimensionality group of the value added service information;
the eCPM correction coefficient query module is used for querying a mapping relation between a dimension group and an eCPM correction coefficient in a prestored charging type eCPM correction coefficient set according to the charging type of the value added service information to obtain an eCPM correction coefficient mapped by the dimension group of the value added service information;
and the value added service information pushing module is used for applying the eCPM correction coefficient to a preset eCPM correction formula to obtain a corrected eCPM of each value added service information, sequencing the corrected eCPM according to the corrected eCPM obtained by calculation and pushing the sequenced value added service information.
11. The apparatus of claim 10, wherein the eCPM correction factor query module comprises: an average estimated eCPM calculation unit, a mapping relation construction unit and an eCPM correction coefficient query unit, wherein,
the average estimated eCPM calculating unit is used for calculating the average estimated eCPM according to a pre-stored display history log;
the mapping relation construction unit is used for fixing values of other dimensions in the general dimension group except the value added service information group identification, traversing the value added service information group identification, calculating an eCPM correction coefficient corresponding to the dimension group of the corresponding value added service information, and placing the eCPM correction coefficient into a charging type eCPM correction coefficient set;
and the eCPM correction coefficient query unit is used for querying the mapping relation construction unit according to the charging type of the value added service information and acquiring the eCPM correction coefficient mapped by the dimension group of the value added service information.
12. The apparatus of claim 11, wherein the average estimated eCPM is calculated using the following equation:
in the formula,
eCPMHISTORY(dims (n)) is the average estimated eCPM;
c (dims (n)) is a presentation history log set;
ac (i) is the behavior type of the ith value added service information, wherein the behavior type comprises: displaying, clicking and installing, wherein the display identifier is imp, the click identifier is clk and the installation identifier is ins;
eCPMPREDICT(i) estimating an eCPM value for the ith value-added service information;
and in all the value added service information recorded by # { i | i ∈ C (dims (n))) ∩ ac (i) ═ imp }, the behavior type is the sum of the number of the displayed value added service information.
13. The apparatus of claim 12, wherein the eCPM correction factor is calculated using the following equation:
in the formula,
delta(b，v2，...，vn) An eCPM correction coefficient;
bithe charging type is the ith type;
b is the designated charging type;
m is the charging type category contained in the dimension group;
v2～vnrespectively different service characteristic information in the value added service information group or value added service information originality.
14. The apparatus of claim 11, wherein the eCPM correction factor query module further comprises:
and the historical true eCPM calculating unit is used for calculating the historical true eCPM according to a pre-stored display historical log.
15. The apparatus of claim 14, wherein the historical true eCPM is calculated using the following equation:
in the formula,
eCPMREAL(dims (n)) is historical true eCPM;
TOTA L _ COST (dims (n)) is the total revenue corresponding to the pre-stored presentation history log;
TOTA L _ impress (dims (n)) is a total display amount corresponding to a pre-stored display history log.
16. The apparatus of claim 15, wherein the eCPM correction factor is calculated using the following equation:
in the formula,
delta(b，v2，...，vn) An eCPM correction coefficient;
bithe charging type is the ith type;
b is the designated charging type;
m is the charging type category contained in the dimension group;
v2～vnrespectively value added service information group or value added service informationDifferent business feature information in the creative.
17. The apparatus according to any of claims 10 to 16, wherein the modified eCPM is calculated using the formula:
in the formula,
delta(b，v2，...，vn) An eCPM correction coefficient;
b is the designated charging type;
v2～vndifferent service characteristic information in the value added service information group or value added service information originality respectively;
0 is equal to or less than α is equal to or less than 1 and is a constant.
18. The apparatus of any one of claims 10 to 16, further comprising:
and the recording module is used for recording the user behavior information of the pushed value-added service information into a historical log.
19. An electronic device, characterized in that the electronic device comprises: the device comprises a shell, a processor, a memory, a circuit board and a power circuit, wherein the circuit board is arranged in a space enclosed by the shell, and the processor and the memory are arranged on the circuit board; a power supply circuit for supplying power to each circuit or device of the electronic apparatus; the memory is used for storing executable program codes; the processor executes a program corresponding to the executable program code by reading the executable program code stored in the memory, and is used for executing the method for pushing the value added service information according to any one of claims 1 to 9.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610157453.4A CN107203892B (en) | 2016-03-18 | 2016-03-18 | Method and device for pushing value added service information and electronic equipment |
| PCT/CN2017/075063 WO2017157159A1 (en) | 2016-03-18 | 2017-02-27 | Method, device, and electronic apparatus for pushing value-added service information item |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610157453.4A CN107203892B (en) | 2016-03-18 | 2016-03-18 | Method and device for pushing value added service information and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107203892A CN107203892A (en) | 2017-09-26 |
| CN107203892B true CN107203892B (en) | 2020-07-31 |
Family
ID=59850426
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610157453.4A Active CN107203892B (en) | 2016-03-18 | 2016-03-18 | Method and device for pushing value added service information and electronic equipment |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN107203892B (en) |
| WO (1) | WO2017157159A1 (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110990677B (en) * | 2019-12-13 | 2023-03-31 | 北京搜狐新媒体信息技术有限公司 | Information storage quantity inquiring method and device |
| CN111865933B (en) * | 2020-06-30 | 2022-02-22 | 上海瀚之友信息技术服务有限公司 | A value-added service management system |
| CN115098738B (en) * | 2022-06-27 | 2025-03-07 | 中国工商银行股份有限公司 | Business data extraction method, device, storage medium and electronic device |
| CN119624672B (en) * | 2024-12-02 | 2025-09-30 | 中国平安人寿保险股份有限公司 | Insurance service push method, electronic device, and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101689273A (en) * | 2007-05-04 | 2010-03-31 | 谷歌公司 | Metric conversion for online advertising |
| CN103379161A (en) * | 2012-04-25 | 2013-10-30 | 腾讯科技（北京）有限公司 | Method, system and device for displaying medium information |
| WO2015051025A1 (en) * | 2013-10-01 | 2015-04-09 | Vantage Media LLC | Engagement mode marketplace with enhanced bidding and adjusted pricing based on engagement performance |
| CN104636940A (en) * | 2013-11-07 | 2015-05-20 | 深圳市腾讯计算机系统有限公司 | Advertisement delivery method, advertisement delivery system, advertisement screening method, advertisement screening device, and server |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130262218A1 (en) * | 2012-03-30 | 2013-10-03 | Google Inc. | Incorporating Delayed Feedback In Performance-Based Content Distribution |
| CN103914468B (en) * | 2012-12-31 | 2018-01-09 | 阿里巴巴集团控股有限公司 | A kind of method and apparatus of impression information search |
| US11017425B2 (en) * | 2013-10-02 | 2021-05-25 | Apple Inc. | Optimization of promotional content campaigns |
| CN105184586A (en) * | 2015-09-18 | 2015-12-23 | 北京金山安全软件有限公司 | Method and device for controlling information display |
-
2016
- 2016-03-18 CN CN201610157453.4A patent/CN107203892B/en active Active
-
2017
- 2017-02-27 WO PCT/CN2017/075063 patent/WO2017157159A1/en not_active Ceased
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101689273A (en) * | 2007-05-04 | 2010-03-31 | 谷歌公司 | Metric conversion for online advertising |
| CN103379161A (en) * | 2012-04-25 | 2013-10-30 | 腾讯科技（北京）有限公司 | Method, system and device for displaying medium information |
| WO2015051025A1 (en) * | 2013-10-01 | 2015-04-09 | Vantage Media LLC | Engagement mode marketplace with enhanced bidding and adjusted pricing based on engagement performance |
| CN104636940A (en) * | 2013-11-07 | 2015-05-20 | 深圳市腾讯计算机系统有限公司 | Advertisement delivery method, advertisement delivery system, advertisement screening method, advertisement screening device, and server |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2017157159A1 (en) | 2017-09-21 |
| CN107203892A (en) | 2017-09-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11157956B2 (en) | Application recommendation method and server | |
| CN106372249B (en) | A kind of clicking rate predictor method, device and electronic equipment | |
| CN108460082B (en) | Recommendation method and device and electronic equipment | |
| US20100250335A1 (en) | System and method using text features for click prediction of sponsored search advertisements | |
| US20120030015A1 (en) | Automatic abstracted creative generation from a web site | |
| CN105095311B (en) | The processing method of promotion message, apparatus and system | |
| CN105678587A (en) | Recommendation feature determination method and information recommendation method and device | |
| CN104536980A (en) | To-be-commented item quality information determination method and device | |
| CN106919575A (en) | application program searching method and device | |
| CN111612581A (en) | A method, device, device and storage medium for item recommendation | |
| CN113850643B (en) | Product recommendation method and device, electronic equipment and readable storage medium | |
| CN107203892B (en) | Method and device for pushing value added service information and electronic equipment | |
| CN113570413A (en) | Method and device for generating advertisement keywords, storage medium and electronic equipment | |
| CN115907868A (en) | Advertisement delivery analysis method and device | |
| CN106919588A (en) | A kind of application program search system and method | |
| CN109299378B (en) | Search result display method and device, terminal and storage medium | |
| WO2015148420A1 (en) | User inactivity aware recommendation system | |
| CN107205009B (en) | Method and device for pushing value added service information and electronic equipment | |
| KR20210052746A (en) | Method, apparatus and computer program for estimating sales volume of content to be productized | |
| CN111695922B (en) | Potential user determination method and device, storage medium and electronic device | |
| CN116188120A (en) | Method, device and system for recommending audio books and storage medium | |
| CN111597469B (en) | Display position determining method and device, electronic equipment and storage medium | |
| CN117725295A (en) | Creative recommendation method and device, electronic equipment and storage medium | |
| CN115082120A (en) | Traffic value-based advertising delivery method, device, electronic device and storage medium | |
| CN111949876B (en) | Information processing method and device, electronic device and computer readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |