CN108108992B - Advertisement charging processing method and device based on entity clustering - Google Patents
Advertisement charging processing method and device based on entity clustering Download PDFInfo
- Publication number
- CN108108992B CN108108992B CN201611070573.7A CN201611070573A CN108108992B CN 108108992 B CN108108992 B CN 108108992B CN 201611070573 A CN201611070573 A CN 201611070573A CN 108108992 B CN108108992 B CN 108108992B
- Authority
- CN
- China
- Prior art keywords
- advertisement
- entity
- account
- mapping relation
- reserve price
- 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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0273—Determination of fees for advertising
-
- 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
- G06Q30/0277—Online advertisement
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an advertisement charging processing method and device based on entity clustering, wherein the method comprises the following steps: performing aggregation processing on advertisement historical data, and determining a first mapping relation between an advertisement account identifier and an advertisement entity; training the historical account reserve price of the advertising word according to the first mapping relation to generate an advertising value distribution model; and calculating a second mapping relation between the advertisement entity and the entity reserve price of the advertisement word according to the advertisement value distribution model so as to charge the online advertisement according to the first mapping relation and the second mapping relation. The method establishes a relation based on the advertisement entity and the advertisement reserve price, and further carries out charging processing on the advertisement according to the advertisement reserve price corresponding to the advertisement entity, thereby improving the processing efficiency of charging the advertisement.
Description
Technical Field
The invention relates to the technical field of internet, in particular to an advertisement charging processing method and device based on entity clustering.
Background
In the online advertising system, under the principle of incentive compatibility, the operation efficiency of the online advertising system can be improved by reasonably setting the advertisement reserve price.
In the related art, a reserve price is set by adopting the corresponding level of the advertisement account and the advertisement word, for example, a reserve price corresponding to the advertisement word "shower gel" in the user account 1 is set as a, and an advertisement reserve price corresponding to the advertisement word "shower gel" in the user account 1 is set as B, and the like.
However, in order to promote the online advertisement system, the online advertisement system usually sets a relatively low advertisement reserve price for a newly opened advertisement account, and therefore, some advertisers avoid the advertisement reserve price policy by newly opening the advertisement account, which brings inconvenience to the processing of the online advertisement system and results in low processing efficiency.
Disclosure of Invention
The object of the present invention is to solve at least to some extent one of the above mentioned technical problems.
Therefore, a first objective of the present invention is to provide an advertisement charging processing method based on entity clustering, which establishes a relationship between an advertisement entity and an advertisement reserve price, and further charges an advertisement according to the advertisement reserve price corresponding to the advertisement entity, thereby improving the processing efficiency of advertisement charging.
The second purpose of the invention is to provide an advertisement charging processing device based on entity clustering.
The third purpose of the invention is to provide another advertisement charging processing device based on entity clustering.
A fourth object of the invention is to propose a non-transitory computer-readable storage medium.
A fifth object of the invention is to propose a computer program product.
In order to achieve the above object, an embodiment of a first aspect of the present invention provides an advertisement charging processing method based on entity clustering, including the following steps:
performing aggregation processing on advertisement historical data, and determining a first mapping relation between an advertisement account identifier and an advertisement entity;
training the historical account reserve price of the advertising word according to the first mapping relation to generate an advertising value distribution model;
and calculating a second mapping relation between the entity retention prices of the advertisement entities and the advertisement words according to the advertisement value distribution model so as to charge the online advertisements according to the first mapping relation and the second mapping relation.
The advertisement charging processing method based on entity clustering of the embodiment of the invention carries out aggregation processing on advertisement historical data, determines a first mapping relation between an advertisement account identifier and an advertisement entity, trains historical account reserve prices of advertisement words according to the first mapping relation, generates an advertisement value distribution model, and further calculates a second mapping relation between the advertisement entity and entity reserve prices of the advertisement words according to the advertisement value distribution model so as to carry out charging processing on online advertisements according to the first mapping relation and the second mapping relation. Therefore, the relation is established based on the advertisement entity and the advertisement reserve price, and further the advertisement is charged according to the advertisement reserve price corresponding to the advertisement entity, so that the management efficiency of charging the advertisement is improved.
In addition, the advertisement charging processing method based on entity clustering of the embodiment of the invention also has the following additional technical characteristics: in an embodiment of the present invention, the aggregating the advertisement history data and determining a first mapping relationship between an advertisement account identifier and an advertisement entity includes: analyzing the advertisement account identifications displayed historically, grouping the advertisement account identifications with the same entity identification, and determining a first mapping relation between the advertisement account identifications and the advertisement entities.
In an embodiment of the present invention, the aggregating the advertisement history data and determining a first mapping relationship between an advertisement account identifier and an advertisement entity includes:
the method comprises the steps of detecting the content of the advertisement web pages displayed historically, grouping the advertisement account identifications corresponding to the advertisement web pages with the same entity keywords, and determining a first mapping relation between the advertisement account identifications and the advertisement entities.
In an embodiment of the present invention, after the calculating a second mapping relationship between entity retention prices of the advertisement entity and the advertisement word according to the advertisement value distribution model, the method further includes:
acquiring bids of advertising words corresponding to a first advertising account to be processed;
querying the first mapping relation to determine a first advertisement entity corresponding to the identifier of the first advertisement account;
inquiring the second mapping relation to determine a first entity reserve price corresponding to the advertising words of the first advertising entity;
and carrying out charging processing on the online advertisement according to the first entity reserve price and the bid.
In one embodiment of the present invention, the charging process for online advertisements according to the first entity reserve price and the bid includes:
comparing the first entity reserve price and the bid;
if the first entity reserve price is larger than the bid price, filtering the bid price of the advertising word corresponding to the first advertising account;
and if the first entity reserve price is less than or equal to the bid price, performing charging processing on the online advertisement according to the bid price.
In order to achieve the above object, a second aspect of the present invention provides an advertisement charging processing apparatus based on entity clustering, including:
the first determining module is used for carrying out aggregation processing on advertisement historical data and determining a first mapping relation between an advertisement account identifier and an advertisement entity;
the training generation module is used for training the historical account reserve price of the advertising word according to the first mapping relation to generate an advertising value distribution model;
and the calculation module is used for calculating a second mapping relation between the entity retention price of the advertisement entity and the entity retention price of the advertisement word according to the advertisement value distribution model so as to carry out charging processing on the online advertisement according to the first mapping relation and the second mapping relation.
The advertisement charging processing device based on entity clustering of the embodiment of the invention carries out aggregation processing on advertisement historical data, determines a first mapping relation between an advertisement account identifier and an advertisement entity, trains historical account reserve prices of advertisement words according to the first mapping relation, generates an advertisement value distribution model, and further calculates a second mapping relation between the advertisement entity and entity reserve prices of the advertisement words according to the advertisement value distribution model so as to carry out charging processing on online advertisements according to the first mapping relation and the second mapping relation. Therefore, the relation is established based on the advertisement entity and the advertisement reserve price, and further the advertisement is charged according to the advertisement reserve price corresponding to the advertisement entity, so that the processing efficiency of charging the advertisement is improved.
In addition, the advertisement charging processing device based on entity clustering of the embodiment of the present invention also has the following additional technical features:
in one embodiment of the present invention, the first determining module is configured to:
analyzing the advertisement account identifications displayed historically, grouping the advertisement account identifications with the same entity identification, and determining a first mapping relation between the advertisement account identifications and the advertisement entities.
In one embodiment of the present invention, the first determining module is configured to: the method comprises the steps of detecting the content of the advertisement web pages displayed historically, grouping the advertisement account identifications corresponding to the advertisement web pages with the same entity keywords, and determining a first mapping relation between the advertisement account identifications and the advertisement entities.
In one embodiment of the present invention, further comprising:
the acquisition module is used for acquiring bids of advertising words corresponding to the first advertising account to be processed;
the second determining module is used for inquiring the first mapping relation to determine a first advertisement entity corresponding to the identifier of the first advertisement account;
a third determining module, configured to query the second mapping relationship to determine a first entity reserve price corresponding to the advertisement word of the first advertisement entity;
and the processing module is used for carrying out charging processing on the online advertisement according to the first entity reserve price and the bid.
In one embodiment of the invention, the processing module comprises:
a comparison unit for comparing the first entity reserve price and the offer;
the processing unit is used for filtering the bids of the advertising words corresponding to the first advertising account when the first entity reserve price is larger than the bids;
the processing unit is further configured to perform charging processing on the online advertisement according to the bid when the first entity reserve price is less than or equal to the bid.
In order to achieve the above object, an embodiment of a third aspect of the present invention provides an advertisement charging processing apparatus based on entity clustering, including:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to:
performing aggregation processing on advertisement historical data, and determining a first mapping relation between an advertisement account identifier and an advertisement entity;
training the historical account reserve price of the advertising word according to the first mapping relation to generate an advertising value distribution model;
and calculating a second mapping relation between the entity retention prices of the advertisement entities and the advertisement words according to the advertisement value distribution model so as to charge the online advertisements according to the first mapping relation and the second mapping relation.
In order to achieve the above object, a fourth aspect of the present invention provides a non-transitory computer-readable storage medium, wherein instructions, when executed by a processor of a mobile terminal, enable the mobile terminal to perform a method for processing advertisement charging based on entity clustering, the method comprising: performing aggregation processing on advertisement historical data, and determining a first mapping relation between an advertisement account identifier and an advertisement entity;
training the historical account reserve price of the advertising word according to the first mapping relation to generate an advertising value distribution model;
and calculating a second mapping relation between the entity retention prices of the advertisement entities and the advertisement words according to the advertisement value distribution model so as to charge the online advertisements according to the first mapping relation and the second mapping relation.
In order to achieve the above object, a fifth embodiment of the present invention provides a computer program product, which when executed by an instruction processor performs a method for processing advertisement charging based on entity clustering, and the method includes: performing aggregation processing on advertisement historical data, and determining a first mapping relation between an advertisement account identifier and an advertisement entity;
training the historical account reserve price of the advertising word according to the first mapping relation to generate an advertising value distribution model;
and calculating a second mapping relation between the entity retention prices of the advertisement entities and the advertisement words according to the advertisement value distribution model so as to charge the online advertisements according to the first mapping relation and the second mapping relation.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The foregoing and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a flow diagram of a method for entity cluster based advertisement billing processing according to one embodiment of the present invention;
FIG. 2 is a flowchart of a method for entity cluster based advertisement billing processing according to another embodiment of the present invention;
FIG. 3 is a schematic structural diagram of an advertisement billing processing apparatus based on entity clustering according to an embodiment of the present invention;
FIG. 4 is a schematic structural diagram of an advertisement billing processing apparatus based on entity clustering according to another embodiment of the present invention; and
fig. 5 is a schematic structural diagram of an advertisement billing processing apparatus based on entity clustering according to yet another embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative and intended to be illustrative of the invention and are not to be construed as limiting the invention.
The following describes a method and an apparatus for processing advertisement charging based on entity clustering according to an embodiment of the present invention with reference to the accompanying drawings.
Generally, in an online advertising system, a fee is charged according to the effect of an advertiser on publishing an advertisement, and the advertiser generally needs to purchase a plurality of advertisement words when publishing the advertisement, for example, for a shower gel advertiser, the advertisement words "shower gel", "moisten", "whiten", and the like are needed to be purchased.
The reserve price of the advertisement word is generally determined based on the corresponding level of the advertisement account and the advertisement word, and the reserve price of the advertisement word corresponding to the new advertisement account is generally relatively low, for example, for the new advertisement account 1, the reserve price for purchasing the advertisement word "shower gel" is relatively low, compared with the reserve price for purchasing the advertisement word "shower gel" in the old advertisement account 2.
Therefore, in order to avoid the strategy of avoiding the advertisement reserve price by some advertisers in a way of newly opening advertisement accounts, the invention provides an advertisement charging processing method based on entity clustering, which specifically comprises the following steps:
fig. 1 is a flowchart of an advertisement billing processing method based on entity clustering according to an embodiment of the present invention.
As shown in fig. 1, the advertisement billing processing method based on entity clustering may include:
s101, aggregating the advertisement historical data, and determining a first mapping relation between the advertisement account identification and the advertisement entity.
It is understood that even though the account names of the a advertisement account and the B advertisement account are different, the a advertisement account and the B advertisement account correspond to the same advertisement entity, such as the internet advertisement account a and the internet advertisement account B, which both correspond to the same internet company. Wherein, the advertisement entity is a specific enterprise or individual who issues the advertisement, etc.
Since the advertisement account is different, but the advertisement published by the advertisement is the same for the target product, or the corresponding advertisement account ID, registered mailbox, etc. account identification are consistent, the historical data can be aggregated, wherein the historical data can comprise the advertisement account identification and the corresponding advertisement content, advertisement account name, advertisement ID, advertisement publishing place, etc.
And further, determining a first mapping relation between the advertisement account identification and the advertisement entity, and storing the advertisement account identification in a classified manner according to the corresponding advertisement entity in the mapping relation.
For example, in the first mapping relationship, the ad account corresponding to the ad entity a includes ad account a1, ad account a2, and the like.
It should be noted that, according to different application scenarios, different manners may be used to aggregate advertisement history data, and determine a first mapping relationship between an advertisement account identifier and an advertisement entity, which is described as follows:
in a first example, the advertisement account may be aggregated according to the advertisement account identifier, that is, the advertisement account identifiers historically displayed may be parsed, and advertisement account identifiers having the same entity identifier may be grouped to determine a first mapping relationship between the advertisement account identifier and the advertisement entity.
In this example, for example, if the user name of the advertisement account a is analyzed as "internet 1 ×", and the user name of the advertisement account B is analyzed as "internet 1 ×", the advertisement account a and the advertisement account B are divided into the same group, and a first mapping relationship corresponding to the advertisement entity is determined, in which the advertisement account a and the advertisement account B belong to the internet company 1.
In a second example, the advertisement account may be aggregated according to the content of the advertisement web page, that is, the content of the advertisement web page displayed historically is detected, the advertisement account identifiers corresponding to the advertisement web pages with the same entity keywords are grouped, and a first mapping relationship between the advertisement account identifiers and the advertisement entities is determined.
In this example, for example, if the advertisement web page content C includes the entity keywords "internet 1", "browser 1", etc., and the advertisement web page content D also includes the entity keywords "internet 1", "browser 1", etc., then the advertisement account identifications corresponding to the advertisement web page content C and the advertisement web page content D may be divided into a same group, and a first mapping relationship corresponding to the advertisement entities is determined, in which the advertisement account identifications corresponding to the advertisement web page content C and the advertisement web page content D correspond to the same advertisement entity.
S102, training the historical account reserve price of the advertising word according to the first mapping relation, and generating an advertising value distribution model.
It is understood that the advertisement accounts belonging to the same advertisement entity may have different historical account reserve prices for the same advertisement word, for example, for the same advertisement word "browser", the corresponding reserve prices may be different due to different time for registering the account, and thus the historical account reserve prices for the advertisement words need to be standardized. Wherein the reserve price is a minimum auction price set for the advertising word in the online advertising system.
Specifically, the historical account reserve price of the advertising word is trained according to the first mapping relation, the number of times, frequency, display duration and the like of clicking the advertising word are comprehensively considered, and an advertising value distribution model is generated and objectively and accurately stores the reserve price of the advertising word.
S103, calculating a second mapping relation between the advertisement entity and the entity reserve price of the advertisement word according to the advertisement value distribution model, and carrying out charging processing on the online advertisement according to the first mapping relation and the second mapping relation.
Specifically, after the advertisement value distribution model is obtained, a second mapping relationship between the advertisement entity and the entity reserve price of the advertisement word is calculated, and the entity reserve price of the advertisement entity and the corresponding advertisement word is stored in the second mapping relationship.
For example, for advertising entity 1, the corresponding advertising word "browser" has an entity reserve price of x, for advertising entity 2, the corresponding advertising word "browser" has an entity reserve price of y, and so on.
Furthermore, when charging the advertisement entity, inquiring the first mapping relation to obtain the advertisement entity corresponding to the advertisement account, and inquiring the second mapping relation according to the advertisement entity to obtain the reserve price of the advertisement word corresponding to the advertisement entity, so as to charge the advertisement issued by the advertisement entity according to the reserve price.
That is, by establishing the corresponding relationship between the entity reserve price of the advertisement entity and the advertisement word, the charging can be performed based on the advertisement entity level, and the charging is consistent no matter which advertisement account the advertiser uses, and is not influenced by the registration time, thereby effectively avoiding the advertisement entity and avoiding the reserve price strategy by registering a new advertisement account.
In summary, the advertisement billing processing method based on entity clustering according to the embodiment of the present invention aggregates advertisement history data, determines a first mapping relationship between an advertisement account identifier and an advertisement entity, trains a historical account reserve price of an advertisement word according to the first mapping relationship, generates an advertisement value distribution model, and further calculates a second mapping relationship between the advertisement entity and an entity reserve price of the advertisement word according to the advertisement value distribution model, so as to perform billing processing on an online advertisement according to the first mapping relationship and the second mapping relationship. Therefore, the relation is established based on the advertisement entity and the advertisement reserve price, and further the advertisement is charged according to the advertisement reserve price corresponding to the advertisement entity, so that the processing efficiency of charging the advertisement is improved.
In order to describe the advertisement charging processing method based on entity clustering more clearly in the embodiments of the present invention, a detailed description is given below in conjunction with a specific implementation process of charging processing for online advertisements according to the first mapping relationship and the second mapping relationship, where the detailed description is as follows:
fig. 2 is a flowchart of an advertisement billing processing method based on entity clustering according to another embodiment of the present invention, as shown in fig. 2, after calculating a second mapping relationship between the advertisement entity and the entity reserve price of the advertisement word according to the advertisement value distribution model in step S103, the method includes:
s201, obtaining the bid of the advertising word corresponding to the first advertising account to be processed.
Specifically, a bid of an advertisement word corresponding to a first advertisement account to be processed is obtained, wherein the bid is the highest purchase price of the first advertisement account for the advertisement word.
S202, inquiring the first mapping relation to determine a first advertisement entity corresponding to the identification of the first advertisement account.
It can be understood that, in order to avoid that the first advertisement account may be an account newly applied for avoiding the reserve price policy by the corresponding advertisement entity, after obtaining the bid of the advertisement word corresponding to the first advertisement account, the reserve price of the advertisement word is not obtained according to the registration time and the like corresponding to the first advertisement account, but the first advertisement entity to which the first advertisement account belongs is determined first.
Specifically, the first mapping relationship is queried to determine the first advertisement entity corresponding to the identifier of the first advertisement account, for example, the first advertisement entity corresponding to the first advertisement account may be determined according to the account name of the first advertisement account, the entity keyword in the advertisement content, and the like.
S203, inquiring the second mapping relation to determine the first entity reserve price corresponding to the advertising words of the first advertising entity.
S204, the online advertisement is charged according to the reserve price and the bid of the first entity.
Specifically, after a first advertisement entity corresponding to the first advertisement account is determined, the second mapping relation is inquired to determine a first entity reserve price corresponding to the advertisement words of the first advertisement entity, and therefore the online advertisement is charged according to the first entity reserve price and the bids.
It should be noted that, according to different application scenarios, the charging processing manner of the online advertisement according to the reserve price and the bid price of the first entity is different, for example, as follows:
in a first example, a first entity reserve price and a bid are compared, and if the first entity reserve price is greater than the bid, the bid of an advertisement word corresponding to a first advertisement account is filtered, and the first advertisement account cannot acquire the corresponding advertisement word.
And if the first entity reserve price is less than or equal to the bid price, performing charging processing on the online advertisement according to the bid price.
In a second example, in practical application, even if the bid of the first advertisement account is higher than the first entity reserve price, the charging process can be performed by using the price between the first entity reserve price and the bid of the first advertisement account according to the click-through rate of the advertisement words and the like.
In this example, when the bid of the advertisement word is higher than the first entity reserve price, the higher bid of the advertisement word is not charged, but the bid of the advertisement word and the first entity reserve price are calculated, and the calculated price charging process between the bid of the advertisement word and the first entity reserve price is used.
For example, if the bid price of the ad is higher than the first entity reserve price, the final charged reserve price of the ad is calculated using the formula, i.e., bid 30% + first entity reserve price 70%.
In this example, when the bid price of the ad word is lower than the first entity reserve price, the bid charge of the ad word is filtered out, and the first ad account cannot acquire the corresponding ad word.
In summary, in the advertisement charging processing method based on entity clustering according to the embodiment of the present invention, after the second mapping relationship between the advertisement entity and the entity reserve price of the advertisement word is calculated according to the advertisement value distribution model, the bid price of the advertisement word corresponding to the first advertisement account to be processed is obtained, the first mapping relationship is queried to determine the first advertisement entity corresponding to the identifier of the first advertisement account, the second mapping relationship is queried to determine the first entity reserve price corresponding to the advertisement word of the first advertisement entity, and then the online advertisement is charged according to the first entity reserve price and the bid price. Therefore, the processing efficiency of advertisement charging is further improved.
In order to achieve the purpose, the invention further provides an advertisement charging processing device based on entity clustering.
Fig. 3 is a schematic structural diagram of an advertisement billing processing apparatus based on entity clustering according to an embodiment of the present invention.
As shown in fig. 3, the advertisement billing processing apparatus based on entity clustering may include: a first determination module 110, a training generation module 120, and a calculation module 130.
The first determining module 110 is configured to perform aggregation processing on advertisement history data, and determine a first mapping relationship between an advertisement account identifier and an advertisement entity.
Since the advertisement that it issues is the same product, i.e., the corresponding advertising entity is the same, even though the advertisement accounts are different, the first determination module 110 aggregates the historical data, which may include the advertisement account identification and the advertisement content corresponding thereto, the advertisement account name, the advertisement ID, the advertisement issuing location, etc., in order to facilitate accurate charging of advertisers.
The first determining module 110 further determines a first mapping relationship between the advertisement account identifier and the advertisement entity, and in the mapping relationship, the user account is classified and stored according to the corresponding advertisement entity.
It should be noted that, according to different application scenarios, the first determining module 110 may perform aggregation processing on advertisement history data in different manners, and determine a first mapping relationship between an advertisement account identifier and an advertisement entity, which is illustrated as follows:
for a first example, the first determining module 110 may aggregate the advertisement accounts according to the advertisement account identifications, that is, parse the advertisement account identifications displayed historically, and group the advertisement account identifications having the same entity identification to determine a first mapping relationship between the advertisement account identifications and the advertisement entities.
In this example, for example, if the first determining module 110 resolves that the user name of the advertisement account a is "internet 1 ×", and the user name of the advertisement account B is "internet 1 ×", the advertisement account a and the advertisement account B are divided into the same group, and determines a first mapping relationship corresponding to the advertisement entity, in which the advertisement account a and the advertisement account B belong to the internet company 1.
As a second example, the first determining module 110 may aggregate the advertisement accounts according to the content of the advertisement web pages, that is, detect the content of the advertisement web pages displayed historically, group the advertisement account identifications corresponding to the advertisement web pages with the same entity keywords, and determine the first mapping relationship between the advertisement accounts and the advertisement entities.
In this example, for example, if the first determining module 110 detects that the advertisement web page content C includes the entity keywords "internet 1", "browser 1", etc. and the advertisement web page content D also includes the entity keywords "internet 1", "browser 1", etc., the advertisement account identifications corresponding to the advertisement web page content C and the advertisement web page content D may be divided into a same group, and a first mapping relationship corresponding to the advertisement entities is determined, in which the advertisement account identifications corresponding to the advertisement web page content C and the advertisement web page content D correspond to the same advertisement entity.
And the training generation module 120 is configured to train the historical account reserve price of the ad word according to the first mapping relationship, and generate an advertisement value distribution model.
Specifically, the training generating module 120 trains the historical account reserve price of the advertisement word according to the first mapping relationship, and comprehensively considers the number of times, frequency, duration of display, and the like of clicking the advertisement word, so as to generate an advertisement value distribution model, where the advertisement value distribution model objectively and accurately stores the reserve price of the advertisement word.
And the calculating module 130 is configured to calculate a second mapping relationship between the advertisement entity and the entity reserve price of the advertisement word according to the advertisement value distribution model, so as to perform charging processing on the online advertisement according to the first mapping relationship and the second mapping relationship.
Specifically, after obtaining the advertisement value distribution model, the calculation module 130 calculates a second mapping relationship between the advertisement entity and the entity reserve price of the advertisement word, where the second mapping relationship is used to store the entity reserve price of the advertisement entity and the corresponding advertisement word.
And then, when charging the advertisement entity, inquiring the first mapping relation to obtain the advertisement entity corresponding to the advertisement account, and further inquiring the second mapping relation according to the advertisement entity to obtain the reserve price of the advertisement word corresponding to the advertisement entity, so as to charge the advertisement issued by the advertisement entity according to the reserve price.
It should be noted that, the foregoing embodiment of the advertisement charging processing method based on entity clustering corresponds to the advertisement charging processing apparatus based on entity clustering according to the embodiment of the present invention, and details that are not disclosed in the embodiment of the advertisement charging processing apparatus based on entity clustering according to the present invention are not repeated herein.
In summary, the advertisement billing processing apparatus based on entity clustering according to the embodiment of the present invention aggregates advertisement history data, determines a first mapping relationship between an advertisement account identifier and an advertisement entity, trains a historical account reserve price of an advertisement word according to the first mapping relationship, generates an advertisement value distribution model, and further calculates a second mapping relationship between the advertisement entity and an entity reserve price of the advertisement word according to the advertisement value distribution model, so as to perform billing processing on an online advertisement according to the first mapping relationship and the second mapping relationship. Therefore, the relation is established based on the advertisement entity and the advertisement reserve price, and further the advertisement is charged according to the advertisement reserve price corresponding to the advertisement entity, so that the processing efficiency of charging the advertisement is improved.
Fig. 4 is a schematic structural diagram of an advertisement billing processing apparatus based on entity clustering according to another embodiment of the present invention, as shown in fig. 4, and based on fig. 3, the advertisement billing processing apparatus based on entity clustering further includes: an acquisition module 140, a second determination module 150, a third determination module 160, and a processing module 170.
The obtaining module 140 is configured to obtain a bid of an ad word corresponding to the first advertisement account to be processed.
Specifically, the obtaining module 140 obtains a bid for an ad word corresponding to the first ad account to be processed, which may be determined according to a registration time of the first ad account, and so on.
The second determining module 150 is configured to query the first mapping relationship to determine the first advertisement entity corresponding to the identifier of the first advertisement account.
Specifically, the second determining module 150 queries the first mapping relationship to determine the first advertisement entity corresponding to the identifier of the first advertisement account, for example, the second determining module 150 may determine the first advertisement entity corresponding to the first advertisement account according to the account name of the first advertisement account, the keyword in the advertisement content, and the like.
And a third determining module 160, configured to query the second mapping relationship to determine a first entity reserve price corresponding to the advertisement word of the first advertisement entity.
And the processing module 170 is configured to perform charging processing on the online advertisement according to the reserve price and the bid of the first entity.
Specifically, after determining the first advertisement entity corresponding to the first advertisement account, the third determining module 160 queries the second mapping relationship to determine the first entity reserve price corresponding to the advertisement word of the first advertisement entity, so that the processing module 170 performs charging processing on the online advertisement according to the first entity reserve price and the bid price.
It should be noted that, according to different application scenarios, the processing module 170 performs different charging processing on the online advertisement according to the reserve price and the bid price of the first entity, for example, as follows:
in an embodiment of the present invention, fig. 5 is a schematic structural diagram of an advertisement billing processing apparatus based on entity clustering according to another embodiment of the present invention, as shown in fig. 5, and on the basis of fig. 4, the processing module 170 includes a comparing unit 171 and a processing unit 172.
Wherein, the comparing unit 171 is configured to compare the first entity reserve price and the offer.
The processing unit 172 is configured to filter bids of the ad words corresponding to the first advertisement account when the first entity reserve price is greater than the bid.
In one embodiment of the present invention, the processing unit 172 is further configured to perform a billing process for the online advertisement according to the bid when the first entity reserve price is less than or equal to the bid.
It should be noted that, the foregoing embodiment of the advertisement charging processing method based on entity clustering corresponds to the advertisement charging processing apparatus based on entity clustering according to the embodiment of the present invention, and details that are not disclosed in the embodiment of the advertisement charging processing apparatus based on entity clustering according to the present invention are not repeated herein.
In summary, in the advertisement charging processing apparatus based on entity clustering according to the embodiment of the present invention, after the second mapping relationship between the advertisement entity and the entity reserve price of the advertisement word is calculated according to the advertisement value distribution model, the bid price of the advertisement word corresponding to the first advertisement account to be processed is obtained, the first mapping relationship is queried to determine the first advertisement entity corresponding to the identifier of the first advertisement account, the second mapping relationship is queried to determine the first entity reserve price corresponding to the advertisement word of the first advertisement entity, and then the online advertisement is charged according to the first entity reserve price and the bid price. Therefore, the processing efficiency of advertisement charging is further improved.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (10)
1. An advertisement charging processing method based on entity clustering is characterized by comprising the following steps:
performing aggregation processing on advertisement historical data, and determining a first mapping relation between an advertisement account identifier and an advertisement entity;
training the historical account reserve price of the advertising word according to the first mapping relation to generate an advertising value distribution model;
and calculating a second mapping relation between the advertisement entity and the entity reserve price of the advertisement word according to the advertisement value distribution model so as to perform charging processing on the online advertisement according to the first mapping relation and the second mapping relation, wherein the first mapping relation is inquired to obtain the advertisement entity corresponding to the advertisement account, the second mapping relation is inquired according to the advertisement entity to obtain the entity reserve price of the advertisement word corresponding to the advertisement entity, and the advertisement issued by the advertisement entity is charged according to the entity reserve price of the advertisement word.
2. The method of claim 1, wherein aggregating the advertisement history data to determine a first mapping between the advertisement account identification and the advertising entity comprises:
analyzing the advertisement account identifications displayed historically, grouping the advertisement account identifications with the same entity identification, and determining a first mapping relation between the advertisement account identifications and the advertisement entities.
3. The method of claim 1, wherein aggregating the advertisement history data to determine a first mapping between the advertisement account identification and the advertising entity comprises:
the method comprises the steps of detecting the content of the advertisement web pages displayed historically, grouping the advertisement account identifications corresponding to the advertisement web pages with the same entity keywords, and determining a first mapping relation between the advertisement account identifications and the advertisement entities.
4. The method of claim 1, further comprising, after said calculating a second mapping relationship between advertising entities and entity reserve prices for advertising terms according to the advertising value distribution model:
acquiring bids of advertising words corresponding to a first advertising account to be processed;
querying the first mapping relation to determine a first advertisement entity corresponding to the identifier of the first advertisement account;
inquiring the second mapping relation to determine a first entity reserve price corresponding to the advertising words of the first advertising entity;
and carrying out charging processing on the online advertisement according to the first entity reserve price and the bid.
5. The method of claim 4, wherein the billing online advertisements based on the first entity reserve price and the bid comprises:
comparing the first entity reserve price and the bid;
if the first entity reserve price is larger than the bid price, filtering the bid price of the advertising word corresponding to the first advertising account;
and if the first entity reserve price is less than or equal to the bid price, performing charging processing on the online advertisement according to the bid price.
6. An advertisement billing processing apparatus based on entity clustering, comprising:
the first determining module is used for carrying out aggregation processing on advertisement historical data and determining a first mapping relation between an advertisement account identifier and an advertisement entity;
the training generation module is used for training the historical account reserve price of the advertising word according to the first mapping relation to generate an advertising value distribution model;
and the calculation module is used for calculating a second mapping relation between the advertisement entity and the entity reserve price of the advertisement word according to the advertisement value distribution model so as to perform charging processing on the online advertisement according to the first mapping relation and the second mapping relation, wherein the first mapping relation is inquired to obtain the advertisement entity corresponding to the advertisement account, the second mapping relation is inquired according to the advertisement entity to obtain the entity reserve price of the advertisement word corresponding to the advertisement entity, and the advertisement charging processing issued by the advertisement entity is performed according to the entity reserve price of the advertisement word.
7. The apparatus of claim 6, wherein the first determination module is to:
analyzing the advertisement account identifications displayed historically, grouping the advertisement account identifications with the same entity identification, and determining a first mapping relation between the advertisement account identifications and the advertisement entities.
8. The apparatus of claim 6, wherein the first determination module is to:
the method comprises the steps of detecting the content of the advertisement web pages displayed historically, grouping the advertisement account identifications corresponding to the advertisement web pages with the same entity keywords, and determining a first mapping relation between the advertisement account identifications and the advertisement entities.
9. The apparatus of claim 6, further comprising:
the acquisition module is used for acquiring bids of advertising words corresponding to the first advertising account to be processed;
the second determining module is used for inquiring the first mapping relation to determine a first advertisement entity corresponding to the identifier of the first advertisement account;
a third determining module, configured to query the second mapping relationship to determine a first entity reserve price corresponding to the advertisement word of the first advertisement entity;
and the processing module is used for carrying out charging processing on the online advertisement according to the first entity reserve price and the bid.
10. The apparatus of claim 9, wherein the processing module comprises:
a comparison unit for comparing the first entity reserve price and the offer;
the processing unit is used for filtering the bids of the advertising words corresponding to the first advertising account when the first entity reserve price is larger than the bids;
the processing unit is further configured to perform charging processing on the online advertisement according to the bid when the first entity reserve price is less than or equal to the bid.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611070573.7A CN108108992B (en) | 2016-11-25 | 2016-11-25 | Advertisement charging processing method and device based on entity clustering |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611070573.7A CN108108992B (en) | 2016-11-25 | 2016-11-25 | Advertisement charging processing method and device based on entity clustering |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108108992A CN108108992A (en) | 2018-06-01 |
| CN108108992B true CN108108992B (en) | 2021-10-19 |
Family
ID=62206306
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611070573.7A Active CN108108992B (en) | 2016-11-25 | 2016-11-25 | Advertisement charging processing method and device based on entity clustering |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108108992B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110648157B (en) * | 2018-06-27 | 2023-04-07 | 阿里巴巴（中国）有限公司 | Method, device, terminal and storage medium for determining reserve price in advertisement market |
| CN109360017B (en) * | 2018-09-11 | 2021-08-13 | 阿里巴巴（中国）有限公司 | Method and apparatus for determining advertisement reserve price for query statement |
| CN109461066A (en) * | 2018-11-01 | 2019-03-12 | 广东电网有限责任公司 | Electric power enterprise account checking system and method thereof |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101375307A (en) * | 2006-01-26 | 2009-02-25 | 康塔网络公司 | Method for operating a marketplace for internet ad media |
| CN102479367A (en) * | 2010-11-30 | 2012-05-30 | 百度(中国)有限公司 | Method and equipment for determining reserve price of network popularization resource |
| CN102567902A (en) * | 2012-02-10 | 2012-07-11 | 亿赞普(北京)科技有限公司 | Network advertisement dynamic release method and system thereof |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7797197B2 (en) * | 2004-11-12 | 2010-09-14 | Amazon Technologies, Inc. | Method and system for analyzing the performance of affiliate sites |
-
2016
- 2016-11-25 CN CN201611070573.7A patent/CN108108992B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101375307A (en) * | 2006-01-26 | 2009-02-25 | 康塔网络公司 | Method for operating a marketplace for internet ad media |
| CN102479367A (en) * | 2010-11-30 | 2012-05-30 | 百度(中国)有限公司 | Method and equipment for determining reserve price of network popularization resource |
| CN102567902A (en) * | 2012-02-10 | 2012-07-11 | 亿赞普(北京)科技有限公司 | Network advertisement dynamic release method and system thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108108992A (en) | 2018-06-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109214842B (en) | Information popularization method, device and equipment | |
| CN103914468B (en) | A kind of method and apparatus of impression information search | |
| CN105447724B (en) | Content item recommendation method and device | |
| US10567255B2 (en) | Method and system for scoring quality of traffic to network sites | |
| US8103544B2 (en) | Competitive advertising server | |
| US20190130451A1 (en) | Method and system for delivery of a targeted advertisement by an electric vehicle charging apparatus | |
| US20120022937A1 (en) | Advertisement brand engagement value | |
| CN108108992B (en) | Advertisement charging processing method and device based on entity clustering | |
| US20130151331A1 (en) | System and methods thereof for an adaptive learning of advertisements behavior and providing a recommendation respective thereof | |
| JP2015529896A (en) | Advertisement billing method and advertisement billing apparatus | |
| CN102117466A (en) | Method and system for directionally delivering web advertisements | |
| CN102870133A (en) | Bid landscape tool | |
| US20090299855A1 (en) | Predicting keyword monetization | |
| CN111553740A (en) | Flow distribution method and device, electronic equipment and computer storage medium | |
| US20080183558A1 (en) | System and method for automatically determining an advertisement type of a digital advertisement | |
| CN106022836A (en) | Advertisement promotion method combined with advertiser effect feedbacks | |
| US20090132334A1 (en) | System and Method for Estimating an Amount of Traffic Associated with a Digital Advertisement | |
| CN106485551A (en) | A kind of information-pushing method, device and electronic equipment | |
| CN114360222A (en) | State early warning method, device, equipment and medium for rental equipment | |
| CN113408939A (en) | Merchant management method and device, electronic equipment and storage medium | |
| CN114092137A (en) | Push method and device, electronic equipment and storage medium | |
| CN103455510B (en) | Method and device for evaluating user | |
| JP2012502346A5 (en) | ||
| KR101343085B1 (en) | Level advertising exposure advertising medium and billing system | |
| WO2009078591A1 (en) | Method for providing keyword advertisement based on user conversion and system for executing the method |
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 |