CN111080374B - Advertisement putting strategy testing method, bidding server and advertisement putting system - Google Patents
Advertisement putting strategy testing method, bidding server and advertisement putting system Download PDFInfo
- Publication number
- CN111080374B CN111080374B CN201911379135.2A CN201911379135A CN111080374B CN 111080374 B CN111080374 B CN 111080374B CN 201911379135 A CN201911379135 A CN 201911379135A CN 111080374 B CN111080374 B CN 111080374B
- Authority
- CN
- China
- Prior art keywords
- advertisement
- target
- strategy
- bidding
- server
- 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; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0242—Determining effectiveness of advertisements
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The embodiment of the invention provides a test method of advertisement putting strategies, a bidding server and an advertisement putting system, which are applied to the bidding server, wherein the method comprises the following steps: determining a primary advertisement; transmitting the user identification and the click rate prediction category identification to a strategy test server so that the strategy test server determines a distribution rule of advertisement request flow according to the click rate prediction category identification and determines a target click rate prediction strategy according to the distribution rule and the user identification; acquiring first target data; obtaining a click rate prediction result; obtaining bid prices of all primary advertisements; determining a target advertisement and a target bid price; obtaining a current throwing result; and counting the put-in results of a plurality of click rate prediction strategies to be subjected to comparison test, and comparing the click rate prediction strategies to obtain a comparison result. Therefore, by applying the embodiment of the invention, the comparison test can be realized without testing one strategy after the test of the other strategy is finished.
Description
Technical Field
The invention relates to the technical field of advertisement delivery in the Internet, in particular to a test method of advertisement delivery strategies, a bidding server and an advertisement delivery system.
Background
When a user opens a certain application software (APP) or a webpage, if an advertisement space exists in the application software or the webpage, triggering an Internet application system to send advertisement flow request data to an advertisement delivery system; after receiving the advertisement flow request data, the advertisement delivery system determines primary advertisement information of each primary advertisement; predicting the click rate of each primary advertisement; obtaining the bid price of each primary advertisement; and determining the target advertisement and the bid price to be finally put from each primary advertisement, and then sending the target advertisement and the bid price to an Internet application system. After receiving each target advertisement and bid price sent by advertisement delivery systems of different advertisement companies, the internet application system determines a target winning advertisement and a winning price which are successful in final bid from each target advertisement and bid price, and sends a result of whether each target advertisement wins or not to a corresponding advertisement delivery system. And finally, the advertisement putting system puts advertisements in the advertisement positions in the application software or the webpage, and sends the actual conversion result of the target winning advertisements to the corresponding advertisement putting system.
In the process, each step of the advertisement delivery system applies different advertisement delivery strategies, and in order to accurately deliver advertisements to target users, the advertisement delivery strategies need to be continuously optimized and iterated. Therefore, when a new advertisement delivery strategy is added, the new advertisement delivery strategy needs to be tested, and the delivery effect of the new advertisement delivery strategy and the original advertisement delivery strategy is tested to determine the optimal advertisement delivery strategy.
At present, in the related art, a new advertisement putting strategy and an original advertisement putting strategy need to be tested respectively, and a comparison test cannot be directly performed.
Disclosure of Invention
The embodiment of the invention aims to provide a test method, a bid server and an advertisement delivery system for advertisement delivery strategies, so as to directly carry out comparison test on new advertisement delivery strategies and original advertisement delivery strategies. The specific technical scheme is as follows:
in a first aspect, an embodiment of the present invention provides a method for testing an advertisement delivery policy, which is applied to a bidding server in an advertisement delivery system, where the advertisement delivery system further includes: a policy test server and a data processing server; the method comprises the following steps:
Determining each primary advertisement according to advertisement request flow data and a preset advertisement primary selection algorithm; the advertisement request flow data comprises a user identifier;
the user identification and the preset click rate prediction category identification are sent to a policy test server, so that the policy test server determines a distribution rule of advertisement request flow according to the click rate prediction category identification, determines a target click rate prediction policy from a plurality of click rate prediction policies to be subjected to comparison test according to the distribution rule and the user identification, and sends the target click rate prediction policy identification of the target click rate prediction policy to a bidding server;
acquiring first target data corresponding to the target click rate prediction strategy identification from the advertisement request flow data and advertisement information of each primary advertisement;
the first target data and the target click rate prediction strategy identification are sent to a data processing server, so that the data processing server executes the target click rate prediction strategy corresponding to the target click rate prediction strategy identification, generates click rate prediction results of each primary advertisement, and sends the click rate prediction results to a bidding server;
Processing according to a preset bidding strategy based on the advertisement request flow data and the advertisement information of each primary advertisement to obtain the bidding price of each primary advertisement;
processing according to a preset putting strategy based on the click rate prediction result and the bid price of each primary advertisement, and determining a target putting advertisement and a target bid price from each primary advertisement;
the target advertisement and the target bid price are sent to an Internet application system, so that the Internet application system returns a current advertisement result;
after receiving preset number of advertisement request flow data, respectively counting the throwing results of a plurality of click rate prediction strategies to be subjected to comparison test;
and comparing the click rate prediction strategies based on the throwing result to obtain a comparison result.
Optionally, the advertisement request traffic data further includes: media information;
the step of sending the user identifier and the preset click rate prediction type identifier to a policy testing server so that the policy testing server determines a distribution rule of advertisement request traffic according to the click rate prediction type identifier, comprising the following steps:
And sending the media information, the user identification and a preset click rate prediction type identification to a strategy test server so that the strategy test server determines a distribution rule of advertisement request flow according to the click rate prediction type identification and the media information.
Optionally, the step of processing according to a preset bidding strategy to obtain the bidding price of each primary advertisement based on the advertisement request flow data and the advertisement information of each primary advertisement includes:
transmitting media information in the advertisement request flow data, the user identification and a preset bidding strategy category identification to a strategy test server so that the strategy test server determines a shunting rule of the advertisement request flow according to the bidding strategy category identification and the media information, determines a target bidding strategy from a plurality of bidding strategies to be subjected to comparison test according to the shunting rule and the user identification, and transmits the target bidding strategy identification of the target bidding strategy to the bidding server;
acquiring second target data corresponding to the target bidding strategy identification from the advertisement request flow data and the advertisement information of each primary advertisement;
And sending the second target data and the target bidding strategy identifications to a data processing server so that the data processing server executes the target bidding strategies corresponding to the target bidding strategy identifications to obtain the bidding prices of the primary advertisements, and sending the bidding prices of the primary advertisements to the bidding server.
Optionally, the step of determining the target advertisement and the target bid price from the primary advertisement based on the click rate prediction result and the bid price of each primary advertisement according to a preset advertisement delivery policy includes:
the media information, the user identification and a preset delivery strategy type identification are sent to a strategy test server, so that the strategy test server determines a distribution rule of advertisement request flow according to the delivery strategy type identification and the media information, determines a target delivery strategy from a plurality of delivery strategies to be subjected to comparison test according to the distribution rule and the user identification, and sends a target delivery strategy identification of the target delivery strategy to a bidding server;
and sending the click rate prediction result, the bid prices of the primary advertisements and the target bid prices to a data processing server so that the data processing server executes according to the target bid strategies corresponding to the target bid strategy identifications, determines target bid prices and target advertisement, and sends the target bid prices and the target advertisement to the bid server.
Optionally, the step of determining each primary advertisement according to the user identifier in the advertisement request flow data and a preset advertisement primary selection algorithm includes:
receiving advertisement request flow data; the advertisement request flow data comprises a user identifier;
acquiring user tag information corresponding to the user identification stored in advance according to the user identification in the advertisement request flow data;
based on the advertisement request flow data, the user tag information and preset matching conditions of each advertisement, processing according to a preset advertisement primary selection algorithm, determining each primary selection advertisement, and acquiring advertisement information of each primary selection advertisement.
Optionally, the delivering result includes: indicating whether the target advertisement is thrown winning results and non-winning results or indicating whether the target advertisement is thrown with effective conversion success results and conversion failure results;
the step of comparing the click rate prediction strategies based on the putting result to obtain a comparison result comprises the following steps:
and comparing the click rate prediction strategies based on the throwing result, and taking the click rate prediction strategy with the highest winning rate or conversion rate as the optimal strategy.
In a second aspect, an embodiment of the present invention provides another method for testing an advertisement delivery policy, which is applied to a bidding server in an advertisement delivery system, where the advertisement delivery system further includes: a policy test server and a data processing server; the method comprises the following steps:
determining each primary advertisement according to the user identification in the advertisement request flow data and a preset advertisement primary selection algorithm;
processing according to a preset click rate prediction strategy based on the advertisement request flow data and advertisement information of each primary advertisement to obtain click rate prediction results of each primary advertisement;
the user identification and the preset bidding strategy category identification are sent to a strategy test server, so that the strategy test server determines a diversion rule of advertisement request flow according to the bidding strategy category identification, determines a target bidding strategy identification of a target bidding strategy from a plurality of bidding strategies to be compared and tested according to the diversion rule and the user identification, and sends the target bidding strategy identification to the bidding server;
acquiring second target data corresponding to the target bidding strategy identification from the advertisement request flow data and advertisement information of each primary advertisement;
The second target data and the target bidding strategy identification are sent to a data processing server, so that the data processing server executes according to the target bidding strategy corresponding to the target bidding strategy identification to obtain the bidding price of each primary advertisement, and the bidding price of each primary advertisement is sent to the bidding server;
processing according to a preset putting strategy based on the click rate prediction result and the bid price of each primary advertisement, and determining a target putting advertisement and a target bid price from each primary advertisement;
the target advertisement and the target bid price are sent to an Internet application system, so that the Internet application system returns a current advertisement result;
after receiving preset number of advertisement request flow data, respectively counting the throwing results of a plurality of bidding strategies to be subjected to comparison test;
and comparing the bidding strategies based on the throwing result to obtain a comparison result.
In a third aspect, an embodiment of the present invention provides a method for testing an advertisement delivery policy, where the method is applied to a bid server in an advertisement delivery system, and the advertisement delivery system further includes: a policy test server and a data processing server; the method comprises the following steps:
Determining each primary advertisement according to the user identification in the advertisement request flow data and a preset advertisement primary selection algorithm;
processing according to a preset click rate prediction strategy based on the advertisement request flow data and advertisement information of each primary advertisement to obtain click rate prediction results of each primary advertisement;
processing according to a preset bidding strategy based on the advertisement request flow data and the advertisement information of each primary advertisement to obtain the bidding price of each primary advertisement;
the user identification and a preset delivery strategy type identification are sent to a strategy test server, so that the strategy test server determines a distribution rule of advertisement request flow according to the delivery strategy type identification, determines a target delivery strategy identification of a target delivery strategy from a plurality of delivery strategies to be subjected to comparison test according to the distribution rule and the user identification, and sends the delivery strategy identification to a bidding server;
the click rate prediction result, the bid price of each primary advertisement and the target bid price are sent to a data processing server, so that the data processing server executes according to the target bid strategy corresponding to the target bid strategy identification, the target advertisement and the target bid price are determined, and the target advertisement and the target bid price are sent to the bid server;
The target advertisement and the target bid price are sent to an Internet application system, so that the Internet application system returns a current advertisement result;
after receiving preset number of advertisement request flow data, respectively counting the delivery results of a plurality of delivery strategies to be subjected to comparison test;
and comparing the plurality of delivery strategies based on the delivery results to obtain comparison results.
In a fourth aspect, an embodiment of the present invention provides a bidding server, including a processor, a communication interface, a memory, and a communication bus, where the processor, the communication interface, and the memory complete communication with each other through the communication bus;
a memory for storing a computer program;
and the processor is used for realizing the method step of testing any advertisement putting strategy when executing the program stored in the memory.
In a fifth aspect, an embodiment of the present invention provides an advertisement delivery system, where the system includes the bidding server, the policy testing server, and the data processing server according to the fourth aspect.
The method for testing the advertisement putting strategy, the bidding server and the advertisement putting system provided by the embodiment of the invention are applied to the bidding server, and the method comprises the following steps: determining each primary advertisement; transmitting the user identification and the preset click rate prediction category identification to a strategy test server, so that the strategy test server determines a distribution rule of advertisement request flow according to the preset click rate prediction category identification, and determines a target click rate prediction strategy from a plurality of click rate prediction strategies to be subjected to comparison test according to the distribution rule and the user identification; the bidding server acquires each first target data corresponding to the target click rate prediction strategy identifier; obtaining a click rate prediction result; obtaining bid prices of all primary advertisements; determining a target advertisement and a target bid price; obtaining a current delivery result returned by an Internet application system; and after receiving the preset number of advertisement request flow data, respectively counting the put-in results of a plurality of click rate prediction strategies to be subjected to comparison test, and comparing the click rate prediction strategies based on the put-in results to obtain comparison results.
Therefore, by applying the embodiment of the invention, the new advertisement putting strategy and the original advertisement putting strategy can be directly compared and tested, and one strategy does not need to be tested before the other strategy is tested.
Of course, it is not necessary for any one product or method of practicing the invention to achieve all of the advantages set forth above at the same time.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1a is a schematic diagram of an advertisement delivery system according to an embodiment of the present invention;
FIG. 1b is a schematic diagram of another exemplary configuration of an advertisement delivery system according to an embodiment of the present invention;
FIG. 2 is a flowchart of a method for testing a first advertisement delivery strategy according to an embodiment of the present invention, which is applied to a bid server in an advertisement delivery system;
FIG. 3 is a specific interaction flow chart based on FIG. 2 according to an embodiment of the present invention;
FIG. 4 is a flowchart of a second method for testing an advertisement delivery strategy according to an embodiment of the present invention, applied to a bid server in an advertisement delivery system;
FIG. 5 is a flowchart of a third method for testing an advertisement delivery strategy, applied to a bid server in an advertisement delivery system, according to an embodiment of the present invention;
fig. 6 is a schematic diagram of a bid server according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In order to solve the problem that in the related art, a new advertisement delivery strategy and an original advertisement delivery strategy need to be tested respectively and cannot be directly compared and tested, the embodiment of the invention provides a test method of the advertisement delivery strategy, a bidding server and an advertisement delivery system.
Referring to fig. 1a, a schematic structural diagram of an advertisement delivery system according to an embodiment of the present invention includes:
In the practical application process, a plurality of advertisement request flow data can be received at the same time, and the data size is larger. Accordingly, a bid server cluster composed of a plurality of bid servers, a policy test server cluster composed of a plurality of policy test servers, and a data processing server cluster composed of a plurality of data processing servers may be included in the advertisement delivery system.
Wherein the advertisement placement policy to be tested may be pre-stored in the data processing server 130. In order to more flexibly perform policy updating, in other embodiments, referring to fig. 1b, fig. 1b is another schematic structural diagram of an advertisement delivery system provided in an embodiment of the present invention, and a policy update server 140 and a policy storage server 150 may be disposed in the advertisement delivery system.
In this way, a new advertisement placement strategy to be tested can be set on the strategy updating server 140, the new advertisement placement strategy to be tested is sent to the strategy storage server 150 to be stored, and then the distribution rule aiming at the new advertisement placement strategy to be tested and the original strategy is configured on the strategy testing server 120. Specifically, policy store server 150 may be a store server such as a redis server.
In this case, the advertisement placement policy to be tested does not need to be pre-saved in the data processing server 130. In the testing process, when the data processing server 130 needs to use the advertisement delivery strategy to be tested, the advertisement delivery strategy is only required to be read from the strategy storage server 150. In this way, not only is the storage pressure of the data processing server 130 reduced, but policy updates can be made more flexibly.
The following describes in detail a method for testing an advertisement delivery strategy provided by the embodiment of the present invention.
Referring to fig. 2, a flowchart of a testing method of a first advertisement delivery policy provided by an embodiment of the present invention is applied to a bidding server in an advertisement delivery system, where the advertisement delivery system further includes: the specific process flow of the method may include, as shown in fig. 2:
step S201, each primary advertisement is determined according to the user identification in the advertisement request flow data and a preset advertisement primary selection algorithm.
Step S202, the user identification and the preset click rate prediction category identification are sent to a policy test server, so that the policy test server determines a distribution rule of advertisement request flow according to the click rate prediction category identification, determines a target click rate prediction policy from a plurality of click rate prediction policies to be subjected to comparison test according to the distribution rule and the user identification, and sends the target click rate prediction policy identification of the target click rate prediction policy to a bidding server.
Step S203, obtaining each first target data corresponding to the target click rate prediction policy identifier from the advertisement request traffic data and advertisement information of each primary advertisement.
Step S204, the first target data and the target click rate prediction strategy identification are sent to a data processing server, so that the data processing server executes the target click rate prediction strategy corresponding to the target click rate prediction strategy identification, generates click rate prediction results of the initially selected advertisements, and sends the click rate prediction results to a bidding server.
Step S205, based on the advertisement request flow data and the advertisement information of each primary advertisement, processing according to a preset bidding strategy to obtain the bidding price of each primary advertisement.
And S206, processing according to a preset delivery strategy based on the click rate prediction result and the bid prices of the primary advertisements, and determining target delivery advertisements and target bid prices from the primary advertisements.
And step S207, the target advertisement and the target bid price are sent to an Internet application system, so that the Internet application system returns the current advertisement result.
Step S208, after receiving the preset number of advertisement request flow data, respectively counting the throwing results of a plurality of click rate prediction strategies to be subjected to comparison test.
Step S209, comparing the click rate prediction strategies based on the throwing result to obtain a comparison result.
Therefore, by applying the embodiment of the invention, the new advertisement putting strategy and the original advertisement putting strategy can be directly compared and tested, and one strategy does not need to be tested before the other strategy is tested.
Referring to fig. 3, a specific interaction flow chart based on fig. 2 provided for an embodiment of the present invention, as shown in fig. 3, may include:
step S301, a bid server receives advertisement request flow data; the advertisement request flow data comprises: user identification and media information.
In one embodiment, the advertisement request traffic data is sent by an internet application system.
In practice, the advertisement request traffic data may further include: target webpage information of a third-party website accessed by a user, a source IP address used for accessing the target webpage, time information for accessing the target webpage, equipment information, region, longitude and latitude, advertisement position information and the like where the user accesses the target webpage.
In practice, the user identifier is device identification information, including computer identification Cookie information or DeviceId information for identifying the mobile terminal device.
In step S302, the bidding server obtains user tag information corresponding to the user identifier stored in advance according to the user identifier in the advertisement request flow data.
The user tag information may be stored in the bidding server after manually calibrating the plurality of advertisement request traffic data corresponding to the user identifier in advance. The user tag information may include: : men or women, age, shopping tendencies and interests, etc.
Step S303, the bidding server processes according to a preset advertisement primary selection algorithm based on the advertisement request flow data, the user tag information and preset matching conditions of each advertisement, determines each primary advertisement, and acquires advertisement information of each primary advertisement.
The advertisement initial selection algorithm can be implemented by matching the data in the advertisement request flow and the user tag information with preset matching conditions of each advertisement. For example: the advertisement one preset matching condition is that the user tag is a woman, the media information is a media one, and the region where the user accesses the target webpage is a region one. Acquiring media information and regions from the advertisement request flow, acquiring whether the user tag is male or female from the user tag information, and judging whether a preset matching condition of advertisement is met; if so, advertisement one is taken as a primary advertisement. And similarly, processing each advertisement to determine each primary advertisement. For example: and finally determining that the initially selected advertisements are advertisement one, advertisement two and advertisement three.
And step S304, the bidding server sends the media information, the user identification and the preset click rate prediction category identification to a strategy testing server.
Step S305, the strategy test server determines a distribution rule of advertisement request flow according to the click rate prediction category identification and the media information, and determines a target click rate prediction strategy from a plurality of click rate prediction strategies to be subjected to comparison test according to the distribution rule and the user identification.
The policy test server may determine a layer based on the click rate prediction class identification; determining experiments corresponding to the media information in advance according to the media information; and determining a target click rate prediction strategy from a plurality of click rate prediction strategies to be subjected to comparison test according to the diversion rules in the experiment and based on the user identification. For example: when the media information is a website, a preset corresponding experiment distribution rule is that 30% of users predict the click rate by using an A method and 70% of users predict the click rate by using a B method; the user identification can be processed based on a Hash function, then the remainder operation is performed, and whether the click rate is predicted by the method A or the click rate is predicted by the method B is determined according to the result of the remainder operation.
In step S306, the policy testing server sends the target click rate prediction policy identifier of the target click rate prediction policy to the bidding server.
In step S307, the bidding server obtains each first target data corresponding to the target click rate prediction policy identifier from the advertisement request traffic data and the advertisement information of each primary advertisement.
In the implementation manner, user identification, media information, equipment information of a computer or mobile equipment and advertisement position information of a target webpage accessed by a user can be obtained from advertisement request flow data to serve as first target data obtained from the advertisement request flow data; advertisement position information of each primary advertisement is obtained from advertisement information of each primary advertisement as first target data obtained from advertisement request flow data.
In practice, the first target data category required is different because of the different click rate prediction strategies. Thus, for each first target data acquired from the advertisement request traffic data and the advertisement information of each primary advertisement, the target click rate prediction policy identification corresponds to the first target data. For example, other click-through rate prediction strategies may only require media information.
In step S308, the bidding server sends the first target data and the target click rate prediction policy identifier to a data processing server.
Step S309, the data processing server executes according to the target click rate prediction strategy corresponding to the target click rate prediction strategy identification, and generates click rate prediction results of each primary advertisement.
In this step, if the target click rate prediction policy is not stored in the data processing server, the target click rate prediction policy may be obtained from the policy storage server 150 shown in fig. 1b and executed.
In step S310, the data processing server sends the click rate prediction result to the bidding server.
In step S311, the bidding server sends the media information in the advertisement request traffic data, the user identifier and the preset bidding policy category identifier to the policy testing server.
In step S312, the policy testing server determines a distribution rule of the advertisement request flow according to the bid policy category identifier and the media information, and determines a target bid policy from a plurality of bid policies to be compared according to the distribution rule and the user identifier.
In practice, the policy testing server may identify a determination tier based on the bidding policy category; determining experiments corresponding to the media information in advance according to the media information; according to the diversion rules in the experiment, and based on the user identification, determining a target bidding strategy from a plurality of bidding strategies to be subjected to comparison test.
In step S313, the policy testing server sends a target bidding policy identification of the target bidding policy to the bidding server.
In step S314, the bidding server obtains each second target data corresponding to the target bidding strategy identifier from the advertisement request flow data and the advertisement information of each primary advertisement.
The second target data category required may be different because of the different bidding strategies. Thus, each second target data acquired from the advertisement request traffic data and the advertisement information of each primary advertisement corresponds to the target bidding strategy identification.
In step S315, the bidding server sends the second target data and the target bidding strategy identifier to the data processing server.
In step S316, the data processing server executes according to the target bidding strategy corresponding to the target bidding strategy identification, and obtains the bidding price of each primary advertisement.
In step S317, the data processing server sends the bid prices of the primary selected advertisements to the bid server.
And step S318, the bidding server sends the media information, the user identification and the preset delivery strategy category identification to a strategy test server.
Step S319, the strategy test server determines a distribution rule of advertisement request flow according to the distribution strategy category identification and the media information, and determines a target distribution strategy from a plurality of distribution strategies to be subjected to comparison test according to the distribution rule and the user identification.
Step S320, the strategy test server sends the target delivery strategy identification of the target delivery strategy to the bidding server.
And step S321, the bid server sends the click rate prediction result, the bid price of each primary advertisement and the target delivery strategy identification to a data processing server.
And step S322, the data processing server executes according to the target delivery strategy corresponding to the target delivery strategy identification to determine the target delivery advertisement and the target bid price.
For example, the steps described above determine: the click rate prediction result is that if the advertisement I is put, the possibility of being clicked is 0.1%; if advertisement two is placed, the possibility of being clicked is 0.2%; if advertisement three is placed, the likelihood of being clicked is 0.3%.
For example, the steps described above determine: the bid price for advertisement one is 1 element, the bid price for advertisement two is 1.5 element, and the bid price for advertisement three is 2 element.
Executing according to the target delivery strategy identification corresponding to the target delivery strategy, wherein the target delivery strategy can be a common delivery strategy, and the result after executing is as follows: and finally, determining the targeted advertisement as advertisement one, wherein the targeted bid price is 0.8 yuan.
Step S323, the data processing server sends the target advertisement and the target bid price to the bid server.
In step S324, the bid server sends the targeted advertisement and the targeted bid price to an internet application system.
Step S325, the Internet application system returns the current delivery result.
The putting result comprises the following steps: indicating whether the targeted advertisement is delivered winning results and non-winning results or indicating whether the targeted advertisement is delivered with effective conversion success results and conversion failure results.
In step S326, after receiving the preset number of advertisement request traffic data, the bid server counts the delivering results of the multiple click rate prediction strategies to be compared and tested respectively.
In step S327, the bidding server compares the click rate prediction strategies based on the result of the delivering, and uses the click rate prediction strategy with the highest winning rate or conversion rate as the optimal strategy.
Therefore, by applying the embodiment of the invention, the new advertisement putting strategy and the original advertisement putting strategy can be directly compared and tested, and one strategy does not need to be tested before the other strategy is tested.
Moreover, by applying the embodiment of the invention, the policy testing server determines the experiments corresponding to the media information in advance according to the policy category identification determination layer and the media information, so that the same bidding server can test the policies such as predicted click rate, the bidding policies and the throwing policies, and in each type of policies, different experiments are configured for different media, a plurality of machines are not required to be configured, and the machine cost and the manpower maintenance cost are reduced.
Referring to fig. 4, a flowchart of a second method for testing an advertisement delivery policy according to an embodiment of the present invention is applied to a bid server in an advertisement delivery system, where the advertisement delivery system further includes: the specific process flow of the method may include, as shown in fig. 4:
Step S401, each primary advertisement is determined according to the user identification in the advertisement request flow data and a preset advertisement primary selection algorithm.
The specific implementation of this step may be the same as steps S301 to S303 in the example shown in fig. 3.
Step S402, processing according to a preset click rate prediction strategy based on the advertisement request flow data and advertisement information of each primary advertisement to obtain a click rate prediction result of each primary advertisement.
The preset click rate prediction strategy may be stored in the bidding server in advance.
Step S403, transmitting the user identifier and a preset bidding strategy category identifier to a strategy test server, so that the strategy test server determines a distribution rule of advertisement request traffic according to the bidding strategy category identifier, determines a target bidding strategy identifier of a target bidding strategy from a plurality of bidding strategies to be compared and tested according to the distribution rule and the user identifier, and transmits the target bidding strategy identifier to the bidding server.
In one embodiment of this step, this step may be the same as step S304 in the embodiment shown in fig. 3.
Step S404, obtaining each second target data corresponding to the target bidding strategy identification from the advertisement request flow data and advertisement information of each primary advertisement.
In practical application, step 404 may be the same as step S308.
And step S405, sending the second target data and the target bidding strategy identification to a data processing server so that the data processing server executes according to the target bidding strategy corresponding to the target bidding strategy identification to obtain the bidding price of each primary advertisement, and sending the bidding price of each primary advertisement to the bidding server.
And step S406, processing according to a preset delivery strategy based on the click rate prediction result and the bid price of each primary advertisement, and determining the target delivery advertisement and the target bid price from each primary advertisement.
The preset delivery strategy can be stored in the bidding server in advance.
And step S407, the target advertisement and the target bid price are sent to an Internet application system, so that the Internet application system returns the current advertisement result.
In practical application, this step may be the same as step S312.
Step S408, after receiving the preset number of advertisement request flow data, respectively counting the throwing results of a plurality of bidding strategies to be subjected to comparison test.
And S409, comparing the bidding strategies based on the throwing result to obtain a comparison result.
The multiple bidding strategies can be compared based on the throwing result, and the bidding strategy with the highest winning rate or conversion rate is used as the optimal strategy.
Therefore, by applying the embodiment of the invention, the new advertisement putting strategy and the original advertisement putting strategy can be directly compared and tested, and one strategy does not need to be tested before the other strategy is tested.
Referring to fig. 5, a flowchart of a third method for testing an advertisement delivery policy according to an embodiment of the present invention is applied to a bid server in an advertisement delivery system, where the advertisement delivery system further includes: the specific process flow of the method may include, as shown in fig. 5:
step S501, each primary advertisement is determined according to the user identification in the advertisement request flow data and a preset advertisement primary selection algorithm.
The specific implementation of this step may be the same as steps S301 to S303 in the example shown in fig. 3.
Step S502, processing according to a preset click rate prediction strategy based on the advertisement request flow data and advertisement information of each primary advertisement to obtain a click rate prediction result of each primary advertisement.
The preset click rate prediction strategy may be stored in the bidding server in advance.
Step S503, processing according to a preset bidding strategy based on the advertisement request flow data and the advertisement information of each primary advertisement, to obtain the bidding price of each primary advertisement.
The preset bidding strategy can be stored in the bidding server in advance.
Step S504, the user identification and the preset delivery strategy type identification are sent to a strategy test server, so that the strategy test server determines a diversion rule of advertisement request flow according to the delivery strategy type identification, determines a target delivery strategy identification of a target delivery strategy from a plurality of delivery strategies to be subjected to comparison test according to the diversion rule and the user identification, and sends the delivery strategy identification to a bidding server.
Step S505, the click rate prediction result, the bid price of each primary advertisement and the target bid price are sent to a data processing server, so that the data processing server executes according to the target bid policy corresponding to the target bid policy identifier, determines the target advertisement and the target bid price, and sends the target advertisement and the target bid price to the bid server.
And step S506, the target advertisement and the target bid price are sent to the Internet application system, so that the Internet application system returns the current advertisement result.
In practical application, this step may be the same as step S312.
Step S507, after receiving the preset number of advertisement request flow data, respectively counting the delivery results of a plurality of delivery strategies to be subjected to comparison test.
And step S508, comparing the plurality of delivery strategies based on the delivery results to obtain comparison results.
The multiple delivery strategies can be compared based on the delivery results, and the delivery strategy with the highest winning rate or conversion rate is used as the optimal strategy.
Therefore, by applying the embodiment of the invention, the new advertisement putting strategy and the original advertisement putting strategy can be directly compared and tested, and one strategy does not need to be tested before the other strategy is tested.
The embodiment of the present invention also provides a bidding server, as shown in fig. 6, comprising a processor 601, a communication interface 602, a memory 603 and a communication bus 604, wherein the processor 601, the communication interface 602, the memory 603 complete the communication between each other through the communication bus 604,
a memory 603 for storing a computer program;
the processor 601 is configured to execute the program stored in the memory 603, and implement the following steps:
determining each primary advertisement according to advertisement request flow data and a preset advertisement primary selection algorithm; the advertisement request flow data comprises a user identifier;
the user identification and the preset click rate prediction category identification are sent to a policy test server, so that the policy test server determines a distribution rule of advertisement request flow according to the click rate prediction category identification, determines a target click rate prediction policy from a plurality of click rate prediction policies to be subjected to comparison test according to the distribution rule and the user identification, and sends the target click rate prediction policy identification of the target click rate prediction policy to a bidding server;
acquiring first target data corresponding to the target click rate prediction strategy identification from the advertisement request flow data and advertisement information of each primary advertisement;
The first target data and the target click rate prediction strategy identification are sent to a data processing server, so that the data processing server executes the target click rate prediction strategy corresponding to the target click rate prediction strategy identification, generates click rate prediction results of each primary advertisement, and sends the click rate prediction results to a bidding server;
processing according to a preset bidding strategy based on the advertisement request flow data and the advertisement information of each primary advertisement to obtain the bidding price of each primary advertisement;
processing according to a preset putting strategy based on the click rate prediction result and the bid price of each primary advertisement, and determining a target putting advertisement and a target bid price from each primary advertisement;
the target advertisement and the target bid price are sent to an Internet application system, so that the Internet application system returns a current advertisement result;
after receiving preset number of advertisement request flow data, respectively counting the throwing results of a plurality of click rate prediction strategies to be subjected to comparison test;
and comparing the click rate prediction strategies based on the throwing result to obtain a comparison result.
Or the steps of the following are implemented,
determining each primary advertisement according to the user identification in the advertisement request flow data and a preset advertisement primary selection algorithm;
processing according to a preset click rate prediction strategy based on the advertisement request flow data and advertisement information of each primary advertisement to obtain click rate prediction results of each primary advertisement;
the user identification and the preset bidding strategy category identification are sent to a strategy test server, so that the strategy test server determines a diversion rule of advertisement request flow according to the bidding strategy category identification, determines a target bidding strategy identification of a target bidding strategy from a plurality of bidding strategies to be compared and tested according to the diversion rule and the user identification, and sends the target bidding strategy identification to the bidding server;
acquiring second target data corresponding to the target bidding strategy identification from the advertisement request flow data and advertisement information of each primary advertisement;
the second target data and the target bidding strategy identification are sent to a data processing server, so that the data processing server executes according to the target bidding strategy corresponding to the target bidding strategy identification to obtain the bidding price of each primary advertisement, and the bidding price of each primary advertisement is sent to the bidding server;
Processing according to a preset putting strategy based on the click rate prediction result and the bid price of each primary advertisement, and determining a target putting advertisement and a target bid price from each primary advertisement;
the target advertisement and the target bid price are sent to an Internet application system, so that the Internet application system returns a current advertisement result;
after receiving preset number of advertisement request flow data, respectively counting the throwing results of a plurality of bidding strategies to be subjected to comparison test;
and comparing the bidding strategies based on the throwing result to obtain a comparison result.
Or the steps of the following are implemented,
determining each primary advertisement according to the user identification in the advertisement request flow data and a preset advertisement primary selection algorithm;
processing according to a preset click rate prediction strategy based on the advertisement request flow data and advertisement information of each primary advertisement to obtain click rate prediction results of each primary advertisement;
processing according to a preset bidding strategy based on the advertisement request flow data and the advertisement information of each primary advertisement to obtain the bidding price of each primary advertisement;
The user identification and a preset delivery strategy type identification are sent to a strategy test server, so that the strategy test server determines a distribution rule of advertisement request flow according to the delivery strategy type identification, determines a target delivery strategy identification of a target delivery strategy from a plurality of delivery strategies to be subjected to comparison test according to the distribution rule and the user identification, and sends the delivery strategy identification to a bidding server;
the click rate prediction result, the bid price of each primary advertisement and the target bid price are sent to a data processing server, so that the data processing server executes according to the target bid strategy corresponding to the target bid strategy identification, the target advertisement and the target bid price are determined, and the target advertisement and the target bid price are sent to the bid server;
the target advertisement and the target bid price are sent to an Internet application system, so that the Internet application system returns a current advertisement result;
after receiving preset number of advertisement request flow data, respectively counting the delivery results of a plurality of delivery strategies to be subjected to comparison test;
And comparing the plurality of delivery strategies based on the delivery results to obtain comparison results.
Therefore, by applying the embodiment of the invention, the new advertisement putting strategy and the original advertisement putting strategy can be directly compared and tested, and one strategy does not need to be tested before the other strategy is tested.
In practice, the bid server is an electronic device.
The communication bus mentioned above for the electronic devices may be a peripheral component interconnect standard (Peripheral Component Interconnect, PCI) bus or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, etc. The communication bus may be classified as an address bus, a data bus, a control bus, or the like. For ease of illustration, the figures are shown with only one bold line, but not with only one bus or one type of bus.
The communication interface is used for communication between the electronic device and other devices.
The Memory may include random access Memory (Random Access Memory, RAM) or may include Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the aforementioned processor.
The processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; but also digital signal processors (Digital Signal Processing, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
In yet another embodiment of the present invention, a computer readable storage medium is provided, in which a computer program is stored, which when executed by a processor, implements the steps of the method for testing any of the above-described advertising policies.
In yet another embodiment of the present invention, a computer program product containing instructions that, when run on a computer, cause the computer to perform the method of testing the advertising strategy of any of the above embodiments is also provided.
In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, produces a flow or function in accordance with embodiments of the present invention, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another, for example, by wired (e.g., coaxial cable, optical fiber, digital Subscriber Line (DSL)), or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid State Disk (SSD)), etc.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
In this specification, each embodiment is described in a related manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for embodiments of the apparatus, electronic device, computer readable storage medium, and computer program product, which are substantially similar to method embodiments, the description is relatively simple, and reference is made to the section of the method embodiments for relevance.
The foregoing description is only of the preferred embodiments of the present invention and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.
Claims (10)
1. The method for testing the advertisement putting strategy is characterized by being applied to a bidding server in an advertisement putting system, and the advertisement putting system further comprises: a policy test server and a data processing server; the method comprises the following steps:
determining each primary advertisement according to advertisement request flow data and a preset advertisement primary selection algorithm; the advertisement request flow data comprises a user identifier;
the user identification and the preset click rate prediction category identification are sent to a policy test server, so that the policy test server determines a distribution rule of advertisement request flow according to the click rate prediction category identification, determines a target click rate prediction policy from a plurality of click rate prediction policies to be subjected to comparison test according to the distribution rule and the user identification, and sends the target click rate prediction policy identification of the target click rate prediction policy to a bidding server;
Acquiring first target data corresponding to the target click rate prediction strategy identification from the advertisement request flow data and advertisement information of each primary advertisement;
the first target data and the target click rate prediction strategy identification are sent to a data processing server, so that the data processing server executes the target click rate prediction strategy corresponding to the target click rate prediction strategy identification, generates click rate prediction results of each primary advertisement, and sends the click rate prediction results to a bidding server;
processing according to a preset bidding strategy based on the advertisement request flow data and the advertisement information of each primary advertisement to obtain the bidding price of each primary advertisement;
processing according to a preset putting strategy based on the click rate prediction result and the bid price of each primary advertisement, and determining a target putting advertisement and a target bid price from each primary advertisement;
the target advertisement and the target bid price are sent to an Internet application system, so that the Internet application system returns a current advertisement result;
after receiving preset number of advertisement request flow data, respectively counting the throwing results of a plurality of click rate prediction strategies to be subjected to comparison test;
And comparing the click rate prediction strategies based on the throwing result to obtain a comparison result.
2. The method of claim 1, wherein the advertisement request traffic data further comprises: media information;
the step of sending the user identifier and the preset click rate prediction type identifier to a policy testing server so that the policy testing server determines a distribution rule of advertisement request traffic according to the click rate prediction type identifier, comprising the following steps:
and sending the media information, the user identification and a preset click rate prediction type identification to a strategy test server so that the strategy test server determines a distribution rule of advertisement request flow according to the click rate prediction type identification and the media information.
3. The method of claim 2, wherein the step of processing according to a preset bidding strategy based on the advertisement request traffic data and the advertisement information of each primary advertisement to obtain a bid price of each primary advertisement comprises:
transmitting media information in the advertisement request flow data, the user identification and a preset bidding strategy category identification to a strategy test server so that the strategy test server determines a shunting rule of the advertisement request flow according to the bidding strategy category identification and the media information, determines a target bidding strategy from a plurality of bidding strategies to be subjected to comparison test according to the shunting rule and the user identification, and transmits the target bidding strategy identification of the target bidding strategy to the bidding server;
Acquiring second target data corresponding to the target bidding strategy identification from the advertisement request flow data and the advertisement information of each primary advertisement;
and sending the second target data and the target bidding strategy identifications to a data processing server so that the data processing server executes the target bidding strategies corresponding to the target bidding strategy identifications to obtain the bidding prices of the primary advertisements, and sending the bidding prices of the primary advertisements to the bidding server.
4. The method of claim 2, wherein the step of determining the targeted advertisement and the targeted bid price from each of the primary advertisements based on the click-through rate prediction result and the bid price of each of the primary advertisements by processing according to a preset delivery strategy comprises:
the media information, the user identification and a preset delivery strategy type identification are sent to a strategy test server, so that the strategy test server determines a distribution rule of advertisement request flow according to the delivery strategy type identification and the media information, determines a target delivery strategy from a plurality of delivery strategies to be subjected to comparison test according to the distribution rule and the user identification, and sends a target delivery strategy identification of the target delivery strategy to a bidding server;
And sending the click rate prediction result, the bid prices of the primary advertisements and the target bid prices to a data processing server so that the data processing server executes according to the target bid strategies corresponding to the target bid strategy identifications, determines target bid prices and target advertisement, and sends the target bid prices and the target advertisement to the bid server.
5. The method of claim 1, wherein the step of determining each primary advertisement based on the user identification in the advertisement request traffic data and a preset advertisement primary selection algorithm comprises:
receiving advertisement request flow data; the advertisement request flow data comprises a user identifier;
acquiring user tag information corresponding to the user identification stored in advance according to the user identification in the advertisement request flow data;
based on the advertisement request flow data, the user tag information and preset matching conditions of each advertisement, processing according to a preset advertisement primary selection algorithm, determining each primary selection advertisement, and acquiring advertisement information of each primary selection advertisement.
6. The method of claim 1, wherein the delivery results comprise: indicating whether the target advertisement is thrown winning results and non-winning results or indicating whether the target advertisement is thrown with effective conversion success results and conversion failure results;
The step of comparing the click rate prediction strategies based on the putting result to obtain a comparison result comprises the following steps:
and comparing the click rate prediction strategies based on the throwing result, and taking the click rate prediction strategy with the highest winning rate or conversion rate as the optimal strategy.
7. The method for testing the advertisement putting strategy is characterized by being applied to a bidding server in an advertisement putting system, and the advertisement putting system further comprises: a policy test server and a data processing server; the method comprises the following steps:
determining each primary advertisement according to the user identification in the advertisement request flow data and a preset advertisement primary selection algorithm;
processing according to a preset click rate prediction strategy based on the advertisement request flow data and advertisement information of each primary advertisement to obtain click rate prediction results of each primary advertisement;
the user identification and the preset bidding strategy category identification are sent to a strategy test server, so that the strategy test server determines a diversion rule of advertisement request flow according to the bidding strategy category identification, determines a target bidding strategy identification of a target bidding strategy from a plurality of bidding strategies to be compared and tested according to the diversion rule and the user identification, and sends the target bidding strategy identification to the bidding server;
Acquiring second target data corresponding to the target bidding strategy identification from the advertisement request flow data and advertisement information of each primary advertisement;
the second target data and the target bidding strategy identification are sent to a data processing server, so that the data processing server executes according to the target bidding strategy corresponding to the target bidding strategy identification to obtain the bidding price of each primary advertisement, and the bidding price of each primary advertisement is sent to the bidding server;
processing according to a preset putting strategy based on the click rate prediction result and the bid price of each primary advertisement, and determining a target putting advertisement and a target bid price from each primary advertisement;
the target advertisement and the target bid price are sent to an Internet application system, so that the Internet application system returns a current advertisement result;
after receiving preset number of advertisement request flow data, respectively counting the throwing results of a plurality of bidding strategies to be subjected to comparison test;
and comparing the bidding strategies based on the throwing result to obtain a comparison result.
8. The method for testing the advertisement putting strategy is characterized by being applied to a bidding server in an advertisement putting system, and the advertisement putting system further comprises: a policy test server and a data processing server; the method comprises the following steps:
determining each primary advertisement according to the user identification in the advertisement request flow data and a preset advertisement primary selection algorithm;
processing according to a preset click rate prediction strategy based on the advertisement request flow data and advertisement information of each primary advertisement to obtain click rate prediction results of each primary advertisement;
processing according to a preset bidding strategy based on the advertisement request flow data and the advertisement information of each primary advertisement to obtain the bidding price of each primary advertisement;
the user identification and a preset delivery strategy type identification are sent to a strategy test server, so that the strategy test server determines a distribution rule of advertisement request flow according to the delivery strategy type identification, determines a target delivery strategy identification of a target delivery strategy from a plurality of delivery strategies to be subjected to comparison test according to the distribution rule and the user identification, and sends the delivery strategy identification to a bidding server;
The click rate prediction result, the bid price of each primary advertisement and the target bid price are sent to a data processing server, so that the data processing server executes according to the target bid strategy corresponding to the target bid strategy identification, the target advertisement and the target bid price are determined, and the target advertisement and the target bid price are sent to the bid server;
the target advertisement and the target bid price are sent to an Internet application system, so that the Internet application system returns a current advertisement result;
after receiving preset number of advertisement request flow data, respectively counting the delivery results of a plurality of delivery strategies to be subjected to comparison test;
and comparing the plurality of delivery strategies based on the delivery results to obtain comparison results.
9. The bidding server is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus;
a memory for storing a computer program;
a processor for implementing the method steps of any one of claims 1-6 when executing a program stored on a memory; or to carry out the method steps of claim 7; or to carry out the method steps of claim 8.
10. An advertisement delivery system comprising the bid server of claim 9, a policy testing server, and a data processing server.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911379135.2A CN111080374B (en) | 2019-12-27 | 2019-12-27 | Advertisement putting strategy testing method, bidding server and advertisement putting system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911379135.2A CN111080374B (en) | 2019-12-27 | 2019-12-27 | Advertisement putting strategy testing method, bidding server and advertisement putting system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111080374A CN111080374A (en) | 2020-04-28 |
| CN111080374B true CN111080374B (en) | 2023-05-23 |
Family
ID=70318669
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911379135.2A Active CN111080374B (en) | 2019-12-27 | 2019-12-27 | Advertisement putting strategy testing method, bidding server and advertisement putting system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111080374B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113793164A (en) * | 2020-11-27 | 2021-12-14 | 北京沃东天骏信息技术有限公司 | Advertisement putting method, device, equipment and storage medium |
| CN112950273B (en) * | 2021-03-09 | 2024-04-09 | 加和（北京）信息科技有限公司 | Advertisement putting strategy processing method and device |
| CN113742577A (en) * | 2021-08-10 | 2021-12-03 | 深圳市东信时代信息技术有限公司 | AB test scheme processing method, device, equipment and storage medium based on SaaS |
| CN115033580A (en) * | 2022-05-30 | 2022-09-09 | 一点灵犀信息技术(广州)有限公司 | Resource delivery processing method, device, equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101582946A (en) * | 2009-06-15 | 2009-11-18 | 卓望数码技术（深圳）有限公司 | Method and system for launching advertisement |
| CN102164311A (en) * | 2010-12-02 | 2011-08-24 | 青岛海信传媒网络技术有限公司 | Advertising strategy verification method, device and system |
| CN102385729A (en) * | 2011-10-25 | 2012-03-21 | 北京亿赞普网络技术有限公司 | Method and device for evaluating advertisement serving policy |
| CN107909395A (en) * | 2017-11-09 | 2018-04-13 | 深圳云麦科技有限公司 | Based on the advertising testing method, apparatus and system for clicking on effect |
| CN109426980A (en) * | 2017-08-31 | 2019-03-05 | 腾讯科技（深圳）有限公司 | Determine method, apparatus, server and the storage medium of advertisement bidding |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9996853B2 (en) * | 2015-04-02 | 2018-06-12 | Vungle, Inc. | Systems and methods for selecting an ad campaign among advertising campaigns having multiple bid strategies |
| US20170091828A1 (en) * | 2015-09-24 | 2017-03-30 | Cox Media Group Digital Development, Inc. | Optimization of online advertising bid requests and dynamic floor pricing |
-
2019
- 2019-12-27 CN CN201911379135.2A patent/CN111080374B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101582946A (en) * | 2009-06-15 | 2009-11-18 | 卓望数码技术（深圳）有限公司 | Method and system for launching advertisement |
| CN102164311A (en) * | 2010-12-02 | 2011-08-24 | 青岛海信传媒网络技术有限公司 | Advertising strategy verification method, device and system |
| CN102385729A (en) * | 2011-10-25 | 2012-03-21 | 北京亿赞普网络技术有限公司 | Method and device for evaluating advertisement serving policy |
| CN109426980A (en) * | 2017-08-31 | 2019-03-05 | 腾讯科技（深圳）有限公司 | Determine method, apparatus, server and the storage medium of advertisement bidding |
| CN107909395A (en) * | 2017-11-09 | 2018-04-13 | 深圳云麦科技有限公司 | Based on the advertising testing method, apparatus and system for clicking on effect |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111080374A (en) | 2020-04-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111080374B (en) | Advertisement putting strategy testing method, bidding server and advertisement putting system | |
| CN109426980B (en) | Method, device, server and storage medium for determining advertisement bidding | |
| CN108681915B (en) | Click rate estimation method and device and electronic equipment | |
| JP5580372B2 (en) | Advertisement distribution apparatus, advertisement distribution method, terminal estimation apparatus, terminal estimation method, and program | |
| CN111062013B (en) | Account filtering method and device, electronic equipment and machine-readable storage medium | |
| CN110769052B (en) | Channel information determination method and device, storage medium and electronic device | |
| US20120239590A1 (en) | Managing customer communications among a plurality of channels | |
| CN109284321A (en) | Data load method, calculates equipment and computer readable storage medium at device | |
| JP5905531B2 (en) | Advertisement distribution apparatus, advertisement distribution method, terminal estimation apparatus, terminal estimation method, and program | |
| CN109150757B (en) | Advertisement resource processing method and device and electronic equipment | |
| CN111008059A (en) | Control method and device for popup window display, terminal and storage medium | |
| CN108805332B (en) | Feature evaluation method and device | |
| CN115757406A (en) | Data storage method and device, electronic equipment and storage medium | |
| JP6283045B2 (en) | Advertisement distribution apparatus, advertisement distribution method, terminal estimation apparatus, terminal estimation method, and program | |
| KR102008452B1 (en) | Method and its apparatus for collecting information of a device | |
| CN111125240B (en) | Distributed transaction realization method and device, electronic equipment and storage medium | |
| CN112437148B (en) | Service request processing method and device, service server and system | |
| CN108280024B (en) | Flow distribution strategy testing method and device and electronic equipment | |
| CN112862544A (en) | Object information acquisition method and device and storage medium | |
| CN109525654B (en) | Data acquisition and sending method, device, client and server | |
| CN116611921A (en) | Information pushing method and device | |
| CN112163932A (en) | Malicious seat occupying order identification method and device and electronic equipment | |
| CN113362104B (en) | Anti-cheating charging method, device and storage medium for effect advertisements | |
| CN111695012A (en) | Method and device for acquiring internet surfing information, electronic equipment and computer storage medium | |
| CN110875831A (en) | Method and device for monitoring network quality |
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 |